public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v33 3/5] Subscripting for jsonb 204+ messages / 5 participants [nested] [flat]
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v35 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v30 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v34 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v29 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v32 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v32 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v31 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v38] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v39] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v40 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 204+ 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] 204+ messages in thread
* Re: Temporary file access API @ 2022-03-01 14:34 Stephen Frost <[email protected]> 0 siblings, 1 reply; 204+ messages in thread From: Stephen Frost @ 2022-03-01 14:34 UTC (permalink / raw) To: Antonin Houska <[email protected]>; +Cc: [email protected] Greetings, * Antonin Houska ([email protected]) wrote: > Here I'm starting a new thread to discuss a topic that's related to the > Transparent Data Encryption (TDE), but could be useful even without that. The > problem has been addressed somehow in the Cybertec TDE fork, and I can post > the code here if it helps. However, after reading [1] (and the posts > upthread), I've got another idea, so let's try to discuss it first. Yeah, I tend to agree that it makes sense to discuss the general idea of doing buffered I/O for the temporary files that are being created today with things like fwrite and have that be independent of encryption. As mentioned on that thread, doing our own buffering and having file accesses done the same way throughout the system is just generally a good thing and focusing on that will certainly help with any TDE effort that may or may not happen later. > It makes sense to me if we first implement the buffering (i.e. writing/reading > certain amount of data at a time) and make the related functions aware of > encryption later: as long as we use a block cipher, we also need to read/write > (suitably sized) chunks rather than individual bytes (or arbitrary amounts of > data). (In theory, someone might need encryption but reject buffering, but I'm > not sure if this is a realistic use case.) Agreed. > For the buffering, I imagine a "file stream" object that user creates on the > top of a file descriptor, such as > > FileStream *FileStreamCreate(File file, int buffer_size) > > or > > FileStream *FileStreamCreateFD(int fd, int buffer_size) > > and uses functions like > > int FileStreamWrite(FileStream *stream, char *buffer, int amount) > > and > > int FileStreamRead(FileStream *stream, char *buffer, int amount) > > to write and read data respectively. Yeah, something along these lines was also what I had in mind, in particular as it would mean fewer changes to places like reorderbuffer.c (or, at least, very clear changes). > Besides functions to close the streams explicitly (e.g. FileStreamClose() / > FileStreamFDClose()), we'd need to ensure automatic closing where that happens > to the file. For example, if OpenTemporaryFile() was used to obtain the file > descriptor, the user expects that the file will be closed and deleted on > transaction boundary, so the corresponding stream should be freed > automatically as well. Sure. We do have some places that want to write using offsets and we'll want to support that also, I'd think. > To avoid code duplication, buffile.c should use these streams internally as > well, as it also performs buffering. (Here we'd also need functions to change > reading/writing position.) Yeah... though we should really go through and make sure that we understand the use-cases for each of the places that decided to use their own code rather than what already existed, to the extent that we can figure that out, and make sure that we're solving those cases and not writing a bunch of new code that won't end up getting used. We really want to be sure that all writes are going through these code paths and make sure there aren't any reasons for them not to be used. > Once we implement the encryption, we might need add an argument to the > FileStreamCreate...() functions that helps to generate an unique IV, but the > ...Read() / ...Write() functions would stay intact. And possibly one more > argument to specify the kind of cipher, in case we support more than one. As long as we're only needing to pass these into the Create function, that seems reasonable to me. I wouldn't want to go through the effort of this and then still have to change every single place we read/write using this system. Thanks, Stephen Attachments: [application/pgp-signature] signature.asc (819B, ../../[email protected]/2-signature.asc) download ^ permalink raw reply [nested|flat] 204+ messages in thread
* Re: Temporary file access API @ 2022-03-08 11:14 Antonin Houska <[email protected]> parent: Stephen Frost <[email protected]> 0 siblings, 1 reply; 204+ messages in thread From: Antonin Houska @ 2022-03-08 11:14 UTC (permalink / raw) To: Stephen Frost <[email protected]>; +Cc: [email protected] Stephen Frost <[email protected]> wrote: > * Antonin Houska ([email protected]) wrote: > > Here I'm starting a new thread to discuss a topic that's related to the > > Transparent Data Encryption (TDE), but could be useful even without that. The > > problem has been addressed somehow in the Cybertec TDE fork, and I can post > > the code here if it helps. However, after reading [1] (and the posts > > upthread), I've got another idea, so let's try to discuss it first. > > Yeah, I tend to agree that it makes sense to discuss the general idea of > doing buffered I/O for the temporary files that are being created today > with things like fwrite and have that be independent of encryption. As > mentioned on that thread, doing our own buffering and having file > accesses done the same way throughout the system is just generally a > good thing and focusing on that will certainly help with any TDE effort > that may or may not happen later. Thanks for your comments, the initial version is attached here. The buffer size is not configurable yet. Besides the new API itself, the patch series shows how it can be used to store logical replication data changes as well as statistics. Further comments are welcome, thanks in advance. -- Antonin Houska Web: https://www.cybertec-postgresql.com Attachments: [application/gzip] temp_file_api_v1.tgz (17.3K, ../../27013.1646738099@antos/2-temp_file_api_v1.tgz) download ^ permalink raw reply [nested|flat] 204+ messages in thread
* Re: Temporary file access API @ 2022-04-05 19:29 Robert Haas <[email protected]> parent: Antonin Houska <[email protected]> 0 siblings, 1 reply; 204+ messages in thread From: Robert Haas @ 2022-04-05 19:29 UTC (permalink / raw) To: Antonin Houska <[email protected]>; +Cc: Stephen Frost <[email protected]>; PostgreSQL Hackers <[email protected]> On Tue, Mar 8, 2022 at 6:12 AM Antonin Houska <[email protected]> wrote: > Thanks for your comments, the initial version is attached here. I've been meaning to look at this thread for some time but have not found enough time to do that until just now. And now I have questions... 1. Supposing we accepted this, how widely do you think that we could adopt it? I see that this patch set adapts a few places to use it and that's nice, but I have a feeling there's a lot more places that are making use of system calls directly, or through some other abstraction, than just this. I'm not sure that we actually want to use something like this everywhere, but what would be the rule for deciding where to use it and where not to use it? If the plan for this facility is just to adapt these two particular places to use it, that doesn't feel like enough to be worthwhile. 2. What about frontend code? Most frontend code won't examine data files directly, but at least pg_controldata, pg_checksums, and pg_resetwal are exceptions. 3. How would we extend this to support encryption? Add an extra argument to BufFileStreamInit(V)FD passing down the encryption details? There are some smaller things about the patch with which I'm not 100% comfortable, but I'd like to start by understanding the big picture. Thanks, -- Robert Haas EDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 204+ messages in thread
* Re: Temporary file access API @ 2022-04-08 08:54 Antonin Houska <[email protected]> parent: Robert Haas <[email protected]> 0 siblings, 1 reply; 204+ messages in thread From: Antonin Houska @ 2022-04-08 08:54 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: Stephen Frost <[email protected]>; PostgreSQL Hackers <[email protected]> Robert Haas <[email protected]> wrote: > On Tue, Mar 8, 2022 at 6:12 AM Antonin Houska <[email protected]> wrote: > > Thanks for your comments, the initial version is attached here. > > I've been meaning to look at this thread for some time but have not > found enough time to do that until just now. And now I have > questions... > > 1. Supposing we accepted this, how widely do you think that we could > adopt it? I see that this patch set adapts a few places to use it and > that's nice, but I have a feeling there's a lot more places that are > making use of system calls directly, or through some other > abstraction, than just this. I'm not sure that we actually want to use > something like this everywhere, but what would be the rule for > deciding where to use it and where not to use > it? If the plan for this facility is just to adapt these two > particular places to use it, that doesn't feel like enough to be > worthwhile. Admittedly I viewed the problem from the perspective of the TDE, so I haven't spent much time looking for other opportunities. Now, with the stats collector using shared memory, even one of the use cases implemented here no longer exists. I need to do more research. Do you think that the use of a system call is a problem itself (e.g. because the code looks less simple if read/write is used somewhere and fread/fwrite elsewhere; of course of read/write is mandatory in special cases like WAL, heap pages, etc.) or is the problem that the system calls are used too frequently? I suppose only the latter. Anyway, I'm not sure there are *many* places where system calls are used too frequently. Instead, the coding uses to be such that the information is first assembled in memory and then written to file at once. So the value of the (buffered) stream is that it makes the code simpler (eliminates the need to prepare the data in memory). That's what I tried to do for reorderbuffer.c and pgstat.c in my patch. Related question is whether we should try to replace some uses of the libc stream (FILE *) at some places. You seem to suggest that in [1]. One example is snapmgr.c:ExportSnapshot(), if we also implement output formatting. Of course there are places where (FILE *) cannot be replaced because, besides regular file, the code needs to work with stdin/stdout in general. (Parsing of configuration files falls into this category, but that doesn't matter because bison-generated parser seems to implement buffering anyway.) > 2. What about frontend code? Most frontend code won't examine data > files directly, but at least pg_controldata, pg_checksums, and > pg_resetwal are exceptions. If the frequency of using system calls is the problem, then I wouldn't change these because ControlFileData structure needs to be initialized in memory anyway and then written at once. And pg_checksums reads whole blocks anyway. I'll take a closer look. > 3. How would we extend this to support encryption? Add an extra > argument to BufFileStreamInit(V)FD passing down the encryption > details? Yes. > There are some smaller things about the patch with which I'm not 100% > comfortable, but I'd like to start by understanding the big picture. Thanks! [1] https://www.postgresql.org/message-id/[email protected]... -- Antonin Houska Web: https://www.cybertec-postgresql.com ^ permalink raw reply [nested|flat] 204+ messages in thread
* Re: Temporary file access API @ 2022-04-08 16:01 Robert Haas <[email protected]> parent: Antonin Houska <[email protected]> 0 siblings, 0 replies; 204+ messages in thread From: Robert Haas @ 2022-04-08 16:01 UTC (permalink / raw) To: Antonin Houska <[email protected]>; +Cc: Stephen Frost <[email protected]>; PostgreSQL Hackers <[email protected]> On Fri, Apr 8, 2022 at 4:54 AM Antonin Houska <[email protected]> wrote: > Do you think that the use of a system call is a problem itself (e.g. because > the code looks less simple if read/write is used somewhere and fread/fwrite > elsewhere; of course of read/write is mandatory in special cases like WAL, > heap pages, etc.) or is the problem that the system calls are used too > frequently? I suppose only the latter. I'm not really super-interested in reducing the number of system calls. It's not a dumb thing in which to be interested and I know that for example Thomas Munro is very interested in it and has done a bunch of work in that direction just to improve performance. But for me the attraction of this is mostly whether it gets us closer to TDE. And that's why I'm asking these questions about adopting it in different places. I kind of thought that your previous patches needed to encrypt, I don't know, 10 or 20 different kinds of files. So I was surprised to see this patch touching the handling of only 2 kinds of files. If we consolidate the handling of let's say 15 of 20 cases into a single mechanism, we've really moved the needle in the right direction -- but consolidating the handling of 2 of 20 cases, or whatever the real numbers are, isn't very exciting. -- Robert Haas EDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 204+ messages in thread
end of thread, other threads:[~2022-04-08 16:01 UTC | newest] Thread overview: 204+ 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 v32 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 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 v31 3/6] 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 v34 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 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 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 v32 3/6] 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 v44 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 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 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 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 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 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 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 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 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 v39] 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 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 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 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 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 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 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 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 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 v38] 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 v46 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 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]> 2022-03-01 14:34 Re: Temporary file access API Stephen Frost <[email protected]> 2022-03-08 11:14 ` Re: Temporary file access API Antonin Houska <[email protected]> 2022-04-05 19:29 ` Re: Temporary file access API Robert Haas <[email protected]> 2022-04-08 08:54 ` Re: Temporary file access API Antonin Houska <[email protected]> 2022-04-08 16:01 ` Re: Temporary file access API 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