public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v28 3/5] Subscripting for jsonb
6+ messages / 4 participants
[nested] [flat]

* [PATCH v28 3/5] Subscripting for jsonb
@ 2019-02-01 10:41  erthalion <[email protected]>
  0 siblings, 0 replies; 6+ 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   | 324 ++++++++++++++++++++++++++----------
 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, 629 insertions(+), 108 deletions(-)

diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c
index 74b4bbe..7af55fc 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 8b73903..7be928f 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 1b0fb2a..ca9e134 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.
  */
@@ -4034,58 +4105,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS)
 }
 
 /*
- * Add values from the jsonb to the parse state.
- *
- * If the parse state container is an object, the jsonb is pushed as
- * a value, not a key.
- *
- * This needs to be done using an iterator because pushJsonbValue doesn't
- * like getting jbvBinary values, so we can't just push jb as a whole.
- */
-static void
-addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb)
-{
-	JsonbIterator *it;
-	JsonbValue *o = &(*jbps)->contVal;
-	JsonbValue	v;
-	JsonbIteratorToken type;
-
-	it = JsonbIteratorInit(&jb->root);
-
-	Assert(o->type == jbvArray || o->type == jbvObject);
-
-	if (JB_ROOT_IS_SCALAR(jb))
-	{
-		(void) JsonbIteratorNext(&it, &v, false);	/* skip array header */
-		Assert(v.type == jbvArray);
-		(void) JsonbIteratorNext(&it, &v, false);	/* fetch scalar value */
-
-		switch (o->type)
-		{
-			case jbvArray:
-				(void) pushJsonbValue(jbps, WJB_ELEM, &v);
-				break;
-			case jbvObject:
-				(void) pushJsonbValue(jbps, WJB_VALUE, &v);
-				break;
-			default:
-				elog(ERROR, "unexpected parent of nested structure");
-		}
-	}
-	else
-	{
-		while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE)
-		{
-			if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM)
-				(void) pushJsonbValue(jbps, type, &v);
-			else
-				(void) pushJsonbValue(jbps, type, NULL);
-		}
-	}
-
-}
-
-/*
  * SQL function jsonb_pretty (jsonb)
  *
  * Pretty-printed text for the 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;
 			}
@@ -4879,13 +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.
+ */
+
+/*
+ * 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
  * format, so that it can be easily extended in the future.
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 38474a7..b3358c7 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10665,6 +10665,14 @@
   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,float4_pass_by_value,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 3e3fa26..32500f7 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 5e81796..6081fab 100644
--- a/src/include/utils/jsonb.h
+++ b/src/include/utils/jsonb.h
@@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate,
 extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container);
 extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, 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 a2a19f8..c7d7e30 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 efd4c45..934fa9d 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);
 
-- 
2.7.4


--------------3C456A3C89C0AEF059999FAB
Content-Type: text/x-patch;
 name="v28-0004-Subscripting-documentation.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v28-0004-Subscripting-documentation.patch"



^ permalink  raw  reply  [nested|flat] 6+ messages in thread

* [PATCH v30 3/6] Subscripting for jsonb
@ 2019-02-01 10:41  erthalion <[email protected]>
  0 siblings, 0 replies; 6+ 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] 6+ messages in thread

* Outdated description of PG_CACHE_LINE_SIZE
@ 2023-07-01 07:49  Julien Rouhaud <[email protected]>
  0 siblings, 1 reply; 6+ messages in thread

From: Julien Rouhaud @ 2023-07-01 07:49 UTC (permalink / raw)
  To: [email protected]

Hi,

I just noticed that the comment for PG_CACHE_LINE_SIZE still says that "it's
currently used in xlog.c", which hasn't been true for quite some time.

PFA a naive patch to make the description more generic.


Attachments:

  [text/x-patch] v1-0001-Fix-PG_CACHE_LINE_SIZE-description.patch (1.7K, ../../20230701074936.p3qcssl4t7murt2q@jrouhaud/2-v1-0001-Fix-PG_CACHE_LINE_SIZE-description.patch)
  download | inline diff:
From a554ee9ca3558c1cc67b2f4024c13b26aacff3c9 Mon Sep 17 00:00:00 2001
From: Julien Rouhaud <[email protected]>
Date: Sat, 1 Jul 2023 15:41:54 +0800
Subject: [PATCH v1] Fix PG_CACHE_LINE_SIZE description.

PG_CACHE_LINE_SIZE was originally only used in xlog.c, but this hasn't been
true for a very long time and is now wildly used, so modify its description to
not mention any explicit source code file.

Author: Julien Rouhaud
Reviewed-by: FIXME
Discussion: FIXME
---
 src/include/pg_config_manual.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
index a1a93ad706..01fe2af499 100644
--- a/src/include/pg_config_manual.h
+++ b/src/include/pg_config_manual.h
@@ -218,12 +218,11 @@
 
 /*
  * Assumed cache line size. This doesn't affect correctness, but can be used
- * for low-level optimizations. Currently, this is used to pad some data
- * structures in xlog.c, to ensure that highly-contended fields are on
- * different cache lines. Too small a value can hurt performance due to false
- * sharing, while the only downside of too large a value is a few bytes of
- * wasted memory. The default is 128, which should be large enough for all
- * supported platforms.
+ * for low-level optimizations. This is mostly used to pad various data
+ * structures, to ensure that highly-contended fields are on different cache
+ * lines. Too small a value can hurt performance due to false sharing, while
+ * the only downside of too large a value is a few bytes of wasted memory. The
+ * default is 128, which should be large enough for all supported platforms.
  */
 #define PG_CACHE_LINE_SIZE		128
 
-- 
2.37.0



^ permalink  raw  reply  [nested|flat] 6+ messages in thread

* Re: Outdated description of PG_CACHE_LINE_SIZE
@ 2023-07-03 09:01  Heikki Linnakangas <[email protected]>
  parent: Julien Rouhaud <[email protected]>
  0 siblings, 1 reply; 6+ messages in thread

From: Heikki Linnakangas @ 2023-07-03 09:01 UTC (permalink / raw)
  To: Julien Rouhaud <[email protected]>; [email protected]

On 01/07/2023 10:49, Julien Rouhaud wrote:
> Hi,
> 
> I just noticed that the comment for PG_CACHE_LINE_SIZE still says that "it's
> currently used in xlog.c", which hasn't been true for quite some time.
> 
> PFA a naive patch to make the description more generic.

Applied, thanks!

-- 
Heikki Linnakangas
Neon (https://neon.tech)







^ permalink  raw  reply  [nested|flat] 6+ messages in thread

* Re: Outdated description of PG_CACHE_LINE_SIZE
@ 2023-07-03 09:24  Julien Rouhaud <[email protected]>
  parent: Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 6+ messages in thread

From: Julien Rouhaud @ 2023-07-03 09:24 UTC (permalink / raw)
  To: Heikki Linnakangas <[email protected]>; +Cc: [email protected]

On Mon, Jul 03, 2023 at 12:01:55PM +0300, Heikki Linnakangas wrote:
> On 01/07/2023 10:49, Julien Rouhaud wrote:
> >
> > I just noticed that the comment for PG_CACHE_LINE_SIZE still says that "it's
> > currently used in xlog.c", which hasn't been true for quite some time.
> >
> > PFA a naive patch to make the description more generic.
>
> Applied, thanks!

Thanks!






^ permalink  raw  reply  [nested|flat] 6+ messages in thread

* [PATCH v6 4/7] Row pattern recognition patch (executor).
@ 2023-09-12 05:22  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 6+ messages in thread

From: Tatsuo Ishii @ 2023-09-12 05:22 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 842 ++++++++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  |  37 +-
 src/include/catalog/pg_proc.dat      |   6 +
 src/include/nodes/execnodes.h        |  26 +
 4 files changed, 898 insertions(+), 13 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..32270d051a 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -36,6 +36,7 @@
 #include "access/htup_details.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_collation_d.h"
 #include "catalog/pg_proc.h"
 #include "executor/executor.h"
 #include "executor/nodeWindowAgg.h"
@@ -48,6 +49,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -182,8 +184,9 @@ static void begin_partition(WindowAggState *winstate);
 static void spool_tuples(WindowAggState *winstate, int64 pos);
 static void release_partition(WindowAggState *winstate);
 
-static int	row_is_in_frame(WindowAggState *winstate, int64 pos,
+static int  row_is_in_frame(WindowAggState *winstate, int64 pos,
 							TupleTableSlot *slot);
+
 static void update_frameheadpos(WindowAggState *winstate);
 static void update_frametailpos(WindowAggState *winstate);
 static void update_grouptailpos(WindowAggState *winstate);
@@ -195,9 +198,32 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static int	WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							  int relpos, int seektype, bool set_mark,
+							  bool *isnull, bool *isout);
+static bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+static void attno_map(Node *node);
+static bool attno_map_walker(Node *node, void *context);
+static int	row_is_in_reduced_frame(WindowObject winobj, int64 pos);
+static bool rpr_is_defined(WindowAggState *winstate);
+
+static void create_reduced_frame_map(WindowAggState *winstate);
+static int	get_reduced_frame_map(WindowAggState *winstate, int64 pos);
+static void register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val);
+static void clear_reduced_frame_map(WindowAggState *winstate);
+static void update_reduced_frame(WindowObject winobj, int64 pos);
+
+static int64 evaluate_pattern(WindowObject winobj, int64 current_pos,
+							  char *vname, StringInfo encoded_str, bool *result);
+
+static bool get_slots(WindowObject winobj, int64 current_pos);
+
+static int	search_str_set(char *pattern, StringInfo *str_set, int set_size);
+static void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index,
+								   char *encoded_str, int *resultlen);
+static char	pattern_initial(WindowAggState *winstate, char *vname);
 
 /*
  * initialize_windowaggregate
@@ -673,6 +699,7 @@ eval_windowaggregates(WindowAggState *winstate)
 	WindowObject agg_winobj;
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot;
+	bool		agg_result_isnull;
 
 	numaggs = winstate->numaggs;
 	if (numaggs == 0)
@@ -778,6 +805,9 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * Note that we don't strictly need to restart in the last case, but if
 	 * we're going to remove all rows from the aggregation anyway, a restart
 	 * surely is faster.
+	 *
+	 *   - if RPR is enabled and skip mode is SKIP TO NEXT ROW,
+	 *     we restart aggregation too.
 	 *----------
 	 */
 	numaggs_restart = 0;
@@ -788,8 +818,11 @@ eval_windowaggregates(WindowAggState *winstate)
 			(winstate->aggregatedbase != winstate->frameheadpos &&
 			 !OidIsValid(peraggstate->invtransfn_oid)) ||
 			(winstate->frameOptions & FRAMEOPTION_EXCLUSION) ||
-			winstate->aggregatedupto <= winstate->frameheadpos)
+			winstate->aggregatedupto <= winstate->frameheadpos ||
+			(rpr_is_defined(winstate) &&
+			 winstate->rpSkipTo == ST_NEXT_ROW))
 		{
+			elog(DEBUG1, "peraggstate->restart is set");
 			peraggstate->restart = true;
 			numaggs_restart++;
 		}
@@ -861,8 +894,10 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * If we created a mark pointer for aggregates, keep it pushed up to frame
 	 * head, so that tuplestore can discard unnecessary rows.
 	 */
+#ifdef NOT_USED
 	if (agg_winobj->markptr >= 0)
 		WinSetMarkPosition(agg_winobj, winstate->frameheadpos);
+#endif
 
 	/*
 	 * Now restart the aggregates that require it.
@@ -917,6 +952,29 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		winstate->aggregatedupto = winstate->frameheadpos;
 		ExecClearTuple(agg_row_slot);
+
+		/*
+		 * If RPR is defined, we do not use aggregatedupto_nonrestarted.  To
+		 * avoid assertion failure below, we reset aggregatedupto_nonrestarted
+		 * to frameheadpos.
+		 */
+		if (rpr_is_defined(winstate))
+			aggregatedupto_nonrestarted = winstate->frameheadpos;
+	}
+
+	agg_result_isnull = false;
+	/* RPR is defined? */
+	if (rpr_is_defined(winstate))
+	{
+		/*
+		 * If the skip mode is SKIP TO PAST LAST ROW and we already know that
+		 * current row is a skipped row or an unmatched row, we don't need to
+		 * accumulate rows, just return NULL.
+		 */
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW &&
+			(get_reduced_frame_map(winstate, winstate->currentpos) == RF_SKIPPED ||
+			 get_reduced_frame_map(winstate, winstate->currentpos) == RF_UNMATCHED))
+			agg_result_isnull = true;
 	}
 
 	/*
@@ -930,6 +988,11 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		int			ret;
 
+		elog(DEBUG1, "===== loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
+		if (agg_result_isnull)
+			break;
+
 		/* Fetch next row if we didn't already */
 		if (TupIsNull(agg_row_slot))
 		{
@@ -945,9 +1008,28 @@ eval_windowaggregates(WindowAggState *winstate)
 		ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot);
 		if (ret < 0)
 			break;
+
 		if (ret == 0)
 			goto next_tuple;
 
+		if (rpr_is_defined(winstate))
+		{
+			/*
+			 * If the row status at currentpos is already decided and current
+			 * row status is not decided yet, it means we passed the last
+			 * reduced frame. Time to break the loop.
+			 */
+			if (get_reduced_frame_map(winstate, winstate->currentpos) != RF_NOT_DETERMINED &&
+				get_reduced_frame_map(winstate, winstate->aggregatedupto) == RF_NOT_DETERMINED)
+				break;
+			/*
+			 * Otherwise we need to calculate the reduced frame.
+			 */
+			ret = row_is_in_reduced_frame(winstate->agg_winobj, winstate->aggregatedupto);
+			if (ret == -1)	/* unmatched row */
+				break;
+		}
+
 		/* Set tuple context for evaluation of aggregate arguments */
 		winstate->tmpcontext->ecxt_outertuple = agg_row_slot;
 
@@ -976,6 +1058,7 @@ next_tuple:
 		ExecClearTuple(agg_row_slot);
 	}
 
+
 	/* The frame's end is not supposed to move backwards, ever */
 	Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto);
 
@@ -996,6 +1079,16 @@ next_tuple:
 								 peraggstate,
 								 result, isnull);
 
+		/*
+		 * RPR is enabled and we just return NULL. because skip mode is SKIP
+		 * TO PAST LAST ROW and current row is skipped row or unmatched row.
+		 */
+		if (agg_result_isnull)
+		{
+			*isnull = true;
+			*result = (Datum) 0;
+		}
+
 		/*
 		 * save the result in case next row shares the same frame.
 		 *
@@ -1090,6 +1183,7 @@ begin_partition(WindowAggState *winstate)
 	winstate->framehead_valid = false;
 	winstate->frametail_valid = false;
 	winstate->grouptail_valid = false;
+	create_reduced_frame_map(winstate);
 	winstate->spooled_rows = 0;
 	winstate->currentpos = 0;
 	winstate->frameheadpos = 0;
@@ -2053,6 +2147,8 @@ ExecWindowAgg(PlanState *pstate)
 
 	CHECK_FOR_INTERRUPTS();
 
+	elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT , winstate->currentpos);
+
 	if (winstate->status == WINDOWAGG_DONE)
 		return NULL;
 
@@ -2221,6 +2317,17 @@ ExecWindowAgg(PlanState *pstate)
 		/* don't evaluate the window functions when we're in pass-through mode */
 		if (winstate->status == WINDOWAGG_RUN)
 		{
+			/*
+			 * If RPR is defined and skip mode is next row, we need to clear existing
+			 * reduced frame info so that we newly calculate the info starting from
+			 * current row.
+			 */
+			if (rpr_is_defined(winstate))
+			{
+				if (winstate->rpSkipTo == ST_NEXT_ROW)
+					clear_reduced_frame_map(winstate);
+			}
+
 			/*
 			 * Evaluate true window functions
 			 */
@@ -2388,6 +2495,9 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2593,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2787,39 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+	winstate->defineInitial = node->defineInitial;
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		/*
+		 * Tweak arg var of PREV/NEXT so that it refers to scan/inner slot.
+		 */
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			attno_map((Node *)expr);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2827,57 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite varno of Var node that is the argument of PREV/NET so that it sees
+ * scan tuple (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node)
+{
+	(void) expression_tree_walker(node, attno_map_walker, NULL);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+
+	if (node == NULL)
+		return false;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				/*
+				 * Rewrite varno from OUTER_VAR to regular var no so that the
+				 * var references scan tuple.
+				 */
+				var->varno = var->varnosyn;
+			else
+				var->varno = INNER_VAR;
+			elog(DEBUG1, "PREV/NEXT's varno is rewritten to: %d", var->varno);
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, NULL);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2895,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2946,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3100,7 +3308,7 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 		return false;
 
 	if (pos < winobj->markpos)
-		elog(ERROR, "cannot fetch row before WindowObject's mark position");
+		elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT,  pos, winobj->markpos );
 
 	oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory);
 
@@ -3420,14 +3628,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+static int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+	int			num_reduced_frame;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3494,11 +3742,21 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 						 winstate->frameOptions);
 					break;
 			}
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				if (relpos >= num_reduced_frame)
+					goto out_of_frame;
 			break;
 		case WINDOW_SEEK_TAIL:
 			/* rejecting relpos > 0 is easy and simplifies code below */
 			if (relpos > 0)
 				goto out_of_frame;
+
+			/* RPR cares about frame head pos. Need to call update_frameheadpos */
+			update_frameheadpos(winstate);
+
 			update_frametailpos(winstate);
 			abs_pos = winstate->frametailpos - 1 + relpos;
 
@@ -3565,6 +3823,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 					mark_pos = 0;	/* keep compiler quiet */
 					break;
 			}
+
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos + relpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				abs_pos = winstate->frameheadpos + relpos + num_reduced_frame - 1;
 			break;
 		default:
 			elog(ERROR, "unrecognized window seek type: %d", seektype);
@@ -3583,15 +3847,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3884,561 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+/*
+ * rpr_is_defined
+ * return true if Row pattern recognition is defined.
+ */
+static
+bool rpr_is_defined(WindowAggState *winstate)
+{
+	return winstate->patternVariableList != NIL;
+}
+
+/*
+ * row_is_in_reduced_frame
+ * Determine whether a row is in the current row's reduced window frame according
+ * to row pattern matching
+ *
+ * The row must has been already determined that it is in a full window frame
+ * and fetched it into slot.
+ *
+ * Returns:
+ * = 0, RPR is not defined.
+ * >0, if the row is the first in the reduced frame. Return the number of rows in the reduced frame.
+ * -1, if the row is unmatched row
+ * -2, if the row is in the reduced frame but needed to be skipped because of
+ * AFTER MATCH SKIP PAST LAST ROW
+ */
+static
+int row_is_in_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	int		state;
+	int		rtn;
+
+	if (!rpr_is_defined(winstate))
+	{
+		/*
+		 * RPR is not defined. Assume that we are always in the the reduced
+		 * window frame.
+		 */
+		rtn = 0;
+		elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, rtn, pos);
+		return rtn;
+	}
+
+	state = get_reduced_frame_map(winstate, pos);
+
+	if (state == RF_NOT_DETERMINED)
+	{
+		update_frameheadpos(winstate);
+		update_reduced_frame(winobj, pos);
+	}
+
+	state = get_reduced_frame_map(winstate, pos);
+
+	switch (state)
+	{
+		int64	i;
+		int		num_reduced_rows;
+
+		case RF_FRAME_HEAD:
+			num_reduced_rows = 1;
+			for (i = pos + 1; get_reduced_frame_map(winstate,i) == RF_SKIPPED; i++)
+				num_reduced_rows++;
+			rtn = num_reduced_rows;
+			break;
+
+		case RF_SKIPPED:
+			rtn = -2;
+			break;
+
+		case RF_UNMATCHED:
+			rtn = -1;
+			break;
+
+		default:
+			elog(ERROR, "Unrecognized state: %d at: " INT64_FORMAT, state, pos);
+			break;
+	}
+
+	elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, rtn, pos);
+	return rtn;
+}
+
+#define REDUCED_FRAME_MAP_INIT_SIZE	1024L
+
+/*
+ * Create reduced frame map
+ */
+static
+void create_reduced_frame_map(WindowAggState *winstate)
+{
+	winstate->reduced_frame_map =
+		MemoryContextAlloc(winstate->partcontext, REDUCED_FRAME_MAP_INIT_SIZE);
+	winstate->alloc_sz = REDUCED_FRAME_MAP_INIT_SIZE;
+	clear_reduced_frame_map(winstate);
+}
+
+/*
+ * Clear reduced frame map
+ */
+static
+void clear_reduced_frame_map(WindowAggState *winstate)
+{
+	Assert(winstate->reduced_frame_map != NULL);
+	MemSet(winstate->reduced_frame_map, RF_NOT_DETERMINED,
+		   winstate->alloc_sz);
+}
+
+/*
+ * Get reduced frame map specified by pos
+ */
+static
+int get_reduced_frame_map(WindowAggState *winstate, int64 pos)
+{
+	Assert(winstate->reduced_frame_map != NULL);
+
+	if (pos < 0 || pos >= winstate->alloc_sz)
+		elog(ERROR, "wrong pos: " INT64_FORMAT, pos);
+
+	return winstate->reduced_frame_map[pos];
+}
+
+/*
+ * Add/replace reduced frame map member at pos.
+ * If there's no enough space, expand the map.
+ */
+static
+void register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val)
+{
+	int64	realloc_sz;
+
+	Assert(winstate->reduced_frame_map != NULL);
+
+	if (pos < 0)
+		elog(ERROR, "wrong pos: " INT64_FORMAT, pos);
+
+	if (pos > winstate->alloc_sz - 1)
+	{
+		realloc_sz = winstate->alloc_sz * 2;
+
+		winstate->reduced_frame_map =
+			repalloc(winstate->reduced_frame_map, realloc_sz);
+
+		MemSet(winstate->reduced_frame_map + winstate->alloc_sz,
+			   RF_NOT_DETERMINED, realloc_sz - winstate->alloc_sz);
+
+		winstate->alloc_sz = realloc_sz;
+	}
+
+	winstate->reduced_frame_map[pos] = val;
+}
+
+/*
+ * update_reduced_frame
+ *		Update reduced frame info.
+ */
+static
+void update_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	ListCell	*lc1, *lc2;
+	bool		expression_result;
+	int			num_matched_rows;
+	int64		original_pos;
+	bool		anymatch;
+	StringInfo	encoded_str;
+	StringInfo	pattern_str = makeStringInfo();
+
+	/*
+	 * Array of pattern variables evaluted to true.
+	 * Each character corresponds to pattern variable.
+	 * Example:
+	 * str_set[0] = "AB";
+	 * str_set[1] = "AC";
+	 * In this case at row 0 A and B are true, and A and C are true in row 1.
+	 */
+	#define ENCODED_STR_ARRAY_ALLOC_SIZE	128
+	StringInfo	*str_set = NULL;
+	int		str_set_index;
+	int		str_set_size;
+
+	/* save original pos */
+	original_pos = pos;
+
+	/*
+	 * Loop over until none of pattern matches or encounters end of frame.
+	 */
+	for (;;)
+	{
+		int64	result_pos = -1;
+
+		/*
+		 * Loop over each PATTERN variable.
+		 */
+		anymatch = false;
+		encoded_str = makeStringInfo();
+
+		forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+		{
+			char	*vname = strVal(lfirst(lc1));
+			char	*quantifier = strVal(lfirst(lc2));
+
+			elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", pos, vname, quantifier);
+
+			expression_result = false;
+
+			/* evaluate row pattern against current row */
+			result_pos = evaluate_pattern(winobj, pos, vname, encoded_str, &expression_result);
+			if (expression_result)
+			{
+				elog(DEBUG1, "expression result is true");
+				anymatch = true;
+			}
+
+			/*
+			 * If out of frame, we are done.
+			 */
+			 if (result_pos < 0)
+				 break;
+		}
+
+		if (!anymatch)
+		{
+			/* none of patterns matched. */
+			break;
+		}
+
+		/* build encoded string array */
+		if (str_set == NULL)
+		{
+			str_set_index = 0;
+			str_set_size = ENCODED_STR_ARRAY_ALLOC_SIZE * sizeof(StringInfo);
+			str_set = palloc(str_set_size);
+		}
+
+		str_set[str_set_index++] = encoded_str;
+
+		elog(DEBUG1, "pos: " INT64_FORMAT " str_set_index: %d encoded_str: %s", pos, str_set_index, encoded_str->data);
+
+		if (str_set_index >= str_set_size)
+		{
+			str_set_size *= 2;
+			str_set = repalloc(str_set, str_set_size);
+		}
+
+		/* move to next row */
+		pos++;
+
+		if (result_pos < 0)
+		{
+			/* out of frame */
+			break;
+		}
+	}
+
+	if (str_set == NULL)
+	{
+		/* no match found in the first row */
+		register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED);
+		return;
+	}
+
+	elog(DEBUG2, "pos: " INT64_FORMAT " encoded_str: %s", pos, encoded_str->data);
+
+	/* build regular expression */
+	pattern_str = makeStringInfo();
+	appendStringInfoChar(pattern_str, '^');
+	forboth (lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc1));
+		char	*quantifier = strVal(lfirst(lc2));
+		char	 initial;
+
+		initial = pattern_initial(winstate, vname);
+		Assert(initial != 0);
+		appendStringInfoChar(pattern_str, initial);
+		if (quantifier[0])
+			appendStringInfoChar(pattern_str, quantifier[0]);
+		elog(DEBUG1, "vname: %s initial: %c quantifier: %s", vname, initial, quantifier);
+	}
+
+	elog(DEBUG2, "pos: " INT64_FORMAT " pattern: %s", pos, pattern_str->data);
+
+	/* look for matching pattern variable sequence */
+	num_matched_rows = search_str_set(pattern_str->data, str_set, str_set_index);
+	/*
+	 * We are at the first row in the reduced frame.  Save the number of
+	 * matched rows as the number of rows in the reduced frame.
+	 */
+	if (num_matched_rows <= 0)
+	{
+		/* no match */
+		register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED);
+	}
+	else
+	{
+		int64		i;
+
+		register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD);
+
+		for (i = original_pos + 1; i < original_pos + num_matched_rows; i++)
+		{
+			register_reduced_frame_map(winstate, i, RF_SKIPPED);
+		}
+	}
+
+	return;
+}
+
+/*
+ * search set of encode_str.
+ * set_size: size of set_str array.
+ */
+static
+int search_str_set(char *pattern, StringInfo *str_set, int set_size)
+{
+	char		*encoded_str = palloc0(set_size+1);
+	int			resultlen = 0;
+
+	search_str_set_recurse(pattern, str_set, set_size, 0, encoded_str, &resultlen);
+	elog(DEBUG1, "search_str_set returns %d", resultlen);
+	return resultlen;
+}
+
+/*
+ * Workhorse of search_str_set.
+ */
+static
+void search_str_set_recurse(char *pattern, StringInfo *str_set,
+							int set_size, int set_index, char *encoded_str, int *resultlen)
+{
+	char	*p;
+
+	if (set_index >= set_size)
+	{
+		Datum	d;
+		text	*res;
+		char	*substr;
+
+		/*
+		 * We first perform pattern matching using regexp_instr, then call
+		 * textregexsubstr to get matched substring to know how log the
+		 * matched string is. That is the number of rows in the reduced window
+		 * frame.  The reason why we can't call textregexsubstr is, it error
+		 * out if pattern is not match.
+		 */
+		if (DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+												  PointerGetDatum(cstring_to_text(encoded_str)),
+												  PointerGetDatum(cstring_to_text(pattern)))) > 0)
+		{
+			d = DirectFunctionCall2Coll(textregexsubstr,
+										DEFAULT_COLLATION_OID,
+										PointerGetDatum(cstring_to_text(encoded_str)),
+										PointerGetDatum(cstring_to_text(pattern)));
+			if (d != 0)
+			{
+				int		len;
+
+				res = DatumGetTextPP(d);
+				substr = text_to_cstring(res);
+				len = strlen(substr);
+				if (len > *resultlen)
+					/* remember the longest match */
+					*resultlen = len;
+			}
+		}
+		return;
+	}
+
+	p = str_set[set_index]->data;
+	while (*p)
+	{
+		encoded_str[set_index] = *p;
+		p++;
+		search_str_set_recurse(pattern, str_set, set_size, set_index + 1, encoded_str, resultlen);
+	}
+}
+
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match absolute row position
+ * other wise out of frame.
+ */
+static
+int64 evaluate_pattern(WindowObject winobj, int64 current_pos,
+						char *vname, StringInfo encoded_str, bool *result)
+{
+	WindowAggState	*winstate = winobj->winstate;
+	ExprContext		*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell		*lc1, *lc2, *lc3;
+	ExprState		*pat;
+	Datum			eval_result;
+	bool			out_of_frame = false;
+	bool			isnull;
+
+	forthree (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList, lc3, winstate->defineInitial)
+	{
+		char	initial;
+		char	*name = strVal(lfirst(lc1));
+
+		if (strcmp(vname, name))
+			continue;
+
+		initial = *(strVal(lfirst(lc3)));
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		/* get current, previous and next tuples */
+		if (!get_slots(winobj, current_pos))
+		{
+			out_of_frame = true;
+		}
+		else
+		{
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, vname, current_pos);
+				*result = false;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, vname, current_pos);
+					*result = false;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, vname, current_pos);
+					appendStringInfoChar(encoded_str, initial);
+					*result = true;
+				}
+			}
+			break;
+		}
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+	}
+	return current_pos;
+}
+
+/*
+ * Get current, previous and next tuples.
+ * Returns false if current row is out of partition/full frame.
+ */
+static
+bool get_slots(WindowObject winobj, int64 current_pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	TupleTableSlot *slot;
+	int		ret;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* set up current row tuple slot */
+	slot = winstate->temp_slot_1;
+	if (!window_gettupleslot(winobj, current_pos, slot))
+	{
+		elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, current_pos);
+		return false;
+
+		ret = row_is_in_frame(winstate, current_pos, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, current_pos);
+			return false;
+		}
+	}
+	econtext->ecxt_outertuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		if (!window_gettupleslot(winobj, current_pos - 1, slot))
+		{
+			elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, current_pos - 1);
+			econtext->ecxt_scantuple = winstate->null_slot;
+		}
+		else
+		{
+			ret = row_is_in_frame(winstate, current_pos - 1, slot);
+			if (ret <= 0)
+			{
+				elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, current_pos - 1);
+				econtext->ecxt_scantuple = winstate->null_slot;
+			}
+			else
+			{
+				econtext->ecxt_scantuple = slot;
+			}
+		}
+	}
+	else
+		econtext->ecxt_scantuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	if (!window_gettupleslot(winobj, current_pos + 1, slot))
+	{
+		elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, current_pos + 1);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+	{
+		ret = row_is_in_frame(winstate, current_pos + 1, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, current_pos + 1);
+			econtext->ecxt_innertuple = winstate->null_slot;
+		}
+		else
+			econtext->ecxt_innertuple = slot;
+	}
+	return true;
+}
+
+/*
+ * Return pattern variable initial character
+ * matching with pattern variable name vname.
+ * If not found, return 0.
+ */
+static
+char	pattern_initial(WindowAggState *winstate, char *vname)
+{
+	char		initial;
+	char		*name;
+	ListCell	*lc1, *lc2;
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineInitial)
+	{
+		name = strVal(lfirst(lc1));				/* DEFINE variable name */
+		initial = *(strVal(lfirst(lc2)));		/* DEFINE variable initial */
+
+
+		if (!strcmp(name, vname))
+				return initial;					/* found */
+	}
+	return 0;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..9ebcc7b5d2 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,11 +39,19 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
 
-
 /*
  * utility routine for *_rank functions.
  */
@@ -673,7 +684,7 @@ window_last_value(PG_FUNCTION_ARGS)
 	bool		isnull;
 
 	result = WinGetFuncArgInFrame(winobj, 0,
-								  0, WINDOW_SEEK_TAIL, true,
+								  0, WINDOW_SEEK_TAIL, false,
 								  &isnull, NULL);
 	if (isnull)
 		PG_RETURN_NULL();
@@ -713,3 +724,25 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 9805bc6118..d20f803cf5 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10416,6 +10416,12 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6123', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..63feb68f60 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2471,6 +2471,11 @@ typedef enum WindowAggStatus
 									 * tuples during spool */
 } WindowAggStatus;
 
+#define	RF_NOT_DETERMINED	0
+#define	RF_FRAME_HEAD		1
+#define	RF_SKIPPED			2
+#define	RF_UNMATCHED		3
+
 typedef struct WindowAggState
 {
 	ScanState	ss;				/* its first field is NodeTag */
@@ -2519,6 +2524,15 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+	List	   *defineInitial;		/* list of row pattern definition variable initials (list of String) */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2569,18 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
+
+	/*
+	 * Each byte corresponds to a row positioned at absolute its pos in
+	 * partition.  See above definition for RF_*
+	 */
+	char		*reduced_frame_map;
+	int64		alloc_sz;	/* size of the map */
 } WindowAggState;
 
 /* ----------------
-- 
2.25.1


----Next_Part(Tue_Sep_12_15_18_43_2023_359)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v6-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 6+ messages in thread


end of thread, other threads:[~2023-09-12 05:22 UTC | newest]

Thread overview: 6+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2019-02-01 10:41 [PATCH v28 3/5] Subscripting for jsonb erthalion <[email protected]>
2019-02-01 10:41 [PATCH v30 3/6] Subscripting for jsonb erthalion <[email protected]>
2023-07-01 07:49 Outdated description of PG_CACHE_LINE_SIZE Julien Rouhaud <[email protected]>
2023-07-03 09:01 ` Re: Outdated description of PG_CACHE_LINE_SIZE Heikki Linnakangas <[email protected]>
2023-07-03 09:24   ` Re: Outdated description of PG_CACHE_LINE_SIZE Julien Rouhaud <[email protected]>
2023-09-12 05:22 [PATCH v6 4/7] Row pattern recognition patch (executor). Tatsuo Ishii <[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