IS JSON predicate

This patch intrdocuces the SQL standard IS JSON predicate. It operates
on text and bytea values representing JSON as well as on the json and
jsonb types. Each test has an IS and IS NOT variant. The tests are:

IS JSON [VALUE]
IS JSON ARRAY
IS JSON OBJECT
IS JSON SCALAR
IS JSON  WITH | WITHOUT UNIQUE KEYS

These are mostly self-explanatory, but note that IS JSON WITHOUT UNIQUE
KEYS is true whenever IS JSON is true, and IS JSON WITH UNIQUE KEYS is
true whenever IS JSON is true except it IS JSON OBJECT is true and there
are duplicate keys (which is never the case when applied to jsonb values).

Nikita Glukhov

Reviewers have included (in no particular order) Andres Freund, Alexander
Korotkov, Pavel Stehule, Andrew Alsup, Erik Rijkers, Zihong Yu,
Himanshu Upadhyaya, Daniel Gustafsson, Justin Pryzby.

Discussion: https://postgr.es/m/cd0bb935-0158-78a7-08b5-904886deac4b@postgrespro.ru

16 files changed, 519 insertions, 17 deletions

diff --git a/src/backend/executor/execExpr.c b/src/backend/executor/execExpr.c
index a9547aaef15..acd3ea61344 100644
--- a/src/backend/executor/execExpr.c
+++ b/src/backend/executor/execExpr.c
@@ -2513,6 +2513,19 @@ ExecInitExprRec(Expr *node, ExprState *state,
 			}
 			break;
 
+		case T_JsonIsPredicate:
+			{
+				JsonIsPredicate *pred = (JsonIsPredicate *) node;
+
+				ExecInitExprRec((Expr *) pred->expr, state, resv, resnull);
+
+				scratch.opcode = EEOP_IS_JSON;
+				scratch.d.is_json.pred = pred;
+
+				ExprEvalPushStep(state, &scratch);
+				break;
+			}
+
 		default:
 			elog(ERROR, "unrecognized node type: %d",
 				 (int) nodeTag(node));
diff --git a/src/backend/executor/execExprInterp.c b/src/backend/executor/execExprInterp.c
index f2a0821a7ab..c0bd9556209 100644
--- a/src/backend/executor/execExprInterp.c
+++ b/src/backend/executor/execExprInterp.c
@@ -73,6 +73,7 @@
 #include "utils/expandedrecord.h"
 #include "utils/json.h"
 #include "utils/jsonb.h"
+#include "utils/jsonfuncs.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/timestamp.h"
@@ -480,6 +481,7 @@ ExecInterpExpr(ExprState *state, ExprContext *econtext, bool *isnull)
 		&&CASE_EEOP_WINDOW_FUNC,
 		&&CASE_EEOP_SUBPLAN,
 		&&CASE_EEOP_JSON_CONSTRUCTOR,
+		&&CASE_EEOP_IS_JSON,
 		&&CASE_EEOP_AGG_STRICT_DESERIALIZE,
 		&&CASE_EEOP_AGG_DESERIALIZE,
 		&&CASE_EEOP_AGG_STRICT_INPUT_CHECK_ARGS,
@@ -1799,6 +1801,14 @@ ExecInterpExpr(ExprState *state, ExprContext *econtext, bool *isnull)
 			EEO_NEXT();
 		}
 
+		EEO_CASE(EEOP_IS_JSON)
+		{
+			/* too complex for an inline implementation */
+			ExecEvalJsonIsPredicate(state, op);
+
+			EEO_NEXT();
+		}
+
 		EEO_CASE(EEOP_LAST)
 		{
 			/* unreachable */
@@ -3909,6 +3919,91 @@ ExecEvalXmlExpr(ExprState *state, ExprEvalStep *op)
 	}
 }
 
+void
+ExecEvalJsonIsPredicate(ExprState *state, ExprEvalStep *op)
+{
+	JsonIsPredicate *pred = op->d.is_json.pred;
+	Datum		js = *op->resvalue;
+	Oid			exprtype;
+	bool		res;
+
+	if (*op->resnull)
+	{
+		*op->resvalue = BoolGetDatum(false);
+		return;
+	}
+
+	exprtype = exprType(pred->expr);
+
+	if (exprtype == TEXTOID || exprtype == JSONOID)
+	{
+		text	   *json = DatumGetTextP(js);
+
+		if (pred->value_type == JS_TYPE_ANY)
+			res = true;
+		else
+		{
+			switch (json_get_first_token(json, false))
+			{
+				case JSON_TOKEN_OBJECT_START:
+					res = pred->value_type == JS_TYPE_OBJECT;
+					break;
+				case JSON_TOKEN_ARRAY_START:
+					res = pred->value_type == JS_TYPE_ARRAY;
+					break;
+				case JSON_TOKEN_STRING:
+				case JSON_TOKEN_NUMBER:
+				case JSON_TOKEN_TRUE:
+				case JSON_TOKEN_FALSE:
+				case JSON_TOKEN_NULL:
+					res = pred->value_type == JS_TYPE_SCALAR;
+					break;
+				default:
+					res = false;
+					break;
+			}
+		}
+
+		/*
+		 * Do full parsing pass only for uniqueness check or for
+		 * JSON text validation.
+		 */
+		if (res && (pred->unique_keys || exprtype == TEXTOID))
+			res = json_validate(json, pred->unique_keys);
+	}
+	else if (exprtype == JSONBOID)
+	{
+		if (pred->value_type == JS_TYPE_ANY)
+			res = true;
+		else
+		{
+			Jsonb	   *jb = DatumGetJsonbP(js);
+
+			switch (pred->value_type)
+			{
+				case JS_TYPE_OBJECT:
+					res = JB_ROOT_IS_OBJECT(jb);
+					break;
+				case JS_TYPE_ARRAY:
+					res = JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb);
+					break;
+				case JS_TYPE_SCALAR:
+					res = JB_ROOT_IS_ARRAY(jb) && JB_ROOT_IS_SCALAR(jb);
+					break;
+				default:
+					res = false;
+					break;
+			}
+		}
+
+		/* Key uniqueness check is redundant for jsonb */
+	}
+	else
+		res = false;
+
+	*op->resvalue = BoolGetDatum(res);
+}
+
 /*
  * ExecEvalGroupingFunc
  *
diff --git a/src/backend/jit/llvm/llvmjit_expr.c b/src/backend/jit/llvm/llvmjit_expr.c
index d0c26cf58b7..02511c6aecc 100644
--- a/src/backend/jit/llvm/llvmjit_expr.c
+++ b/src/backend/jit/llvm/llvmjit_expr.c
@@ -2354,6 +2354,12 @@ llvm_compile_expr(ExprState *state)
 				LLVMBuildBr(b, opblocks[opno + 1]);
 				break;
 
+			case EEOP_IS_JSON:
+				build_EvalXFunc(b, mod, "ExecEvalJsonIsPredicate",
+								v_state, op);
+				LLVMBuildBr(b, opblocks[opno + 1]);
+				break;
+
 			case EEOP_LAST:
 				Assert(false);
 				break;
diff --git a/src/backend/jit/llvm/llvmjit_types.c b/src/backend/jit/llvm/llvmjit_types.c
index 53c75dd9d69..4d7029a27f1 100644
--- a/src/backend/jit/llvm/llvmjit_types.c
+++ b/src/backend/jit/llvm/llvmjit_types.c
@@ -132,6 +132,7 @@ void	   *referenced_functions[] =
 	ExecEvalWholeRowVar,
 	ExecEvalXmlExpr,
 	ExecEvalJsonConstructor,
+	ExecEvalJsonIsPredicate,
 	MakeExpandedObjectReadOnlyInternal,
 	slot_getmissingattrs,
 	slot_getsomeattrs_int,
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index c09172164b9..cb4b4d01f80 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -2491,6 +2491,23 @@ _copyJsonArrayQueryConstructor(const JsonArrayQueryConstructor *from)
 	return newnode;
 }
 
+/*
+ * _copyJsonIsPredicate
+ */
+static JsonIsPredicate *
+_copyJsonIsPredicate(const JsonIsPredicate *from)
+{
+	JsonIsPredicate *newnode = makeNode(JsonIsPredicate);
+
+	COPY_NODE_FIELD(expr);
+	COPY_SCALAR_FIELD(format);
+	COPY_SCALAR_FIELD(value_type);
+	COPY_SCALAR_FIELD(unique_keys);
+	COPY_LOCATION_FIELD(location);
+
+	return newnode;
+}
+
 /* ****************************************************************
  *						pathnodes.h copy functions
  *
@@ -5625,6 +5642,9 @@ copyObjectImpl(const void *from)
 		case T_JsonArrayAgg:
 			retval = _copyJsonArrayAgg(from);
 			break;
+		case T_JsonIsPredicate:
+			retval = _copyJsonIsPredicate(from);
+			break;
 
 			/*
 			 * RELATION NODES
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 3fb423be47a..084d98b34cc 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -976,6 +976,18 @@ _equalJsonArrayQueryConstructor(const JsonArrayQueryConstructor *a,
 	return true;
 }
 
+static bool
+_equalJsonIsPredicate(const JsonIsPredicate *a,
+					  const JsonIsPredicate *b)
+{
+	COMPARE_NODE_FIELD(expr);
+	COMPARE_SCALAR_FIELD(value_type);
+	COMPARE_SCALAR_FIELD(unique_keys);
+	COMPARE_LOCATION_FIELD(location);
+
+	return true;
+}
+
 /*
  * Stuff from pathnodes.h
  */
@@ -3546,6 +3558,9 @@ equal(const void *a, const void *b)
 		case T_JsonConstructorExpr:
 			retval = _equalJsonConstructorExpr(a, b);
 			break;
+		case T_JsonIsPredicate:
+			retval = _equalJsonIsPredicate(a, b);
+			break;
 
 			/*
 			 * RELATION NODES
diff --git a/src/backend/nodes/makefuncs.c b/src/backend/nodes/makefuncs.c
index 7b4f7972e62..b67e7c52973 100644
--- a/src/backend/nodes/makefuncs.c
+++ b/src/backend/nodes/makefuncs.c
@@ -887,3 +887,22 @@ makeJsonKeyValue(Node *key, Node *value)
 
 	return (Node *) n;
 }
+
+/*
+ * makeJsonIsPredicate -
+ *	  creates a JsonIsPredicate node
+ */
+Node *
+makeJsonIsPredicate(Node *expr, JsonFormat *format, JsonValueType value_type,
+					bool unique_keys, int location)
+{
+	JsonIsPredicate *n = makeNode(JsonIsPredicate);
+
+	n->expr = expr;
+	n->format = format;
+	n->value_type = value_type;
+	n->unique_keys = unique_keys;
+	n->location = location;
+
+	return (Node *) n;
+}
diff --git a/src/backend/nodes/nodeFuncs.c b/src/backend/nodes/nodeFuncs.c
index 50898246f96..d697c7abd8c 100644
--- a/src/backend/nodes/nodeFuncs.c
+++ b/src/backend/nodes/nodeFuncs.c
@@ -260,6 +260,9 @@ exprType(const Node *expr)
 		case T_JsonConstructorExpr:
 			type = ((const JsonConstructorExpr *) expr)->returning->typid;
 			break;
+		case T_JsonIsPredicate:
+			type = BOOLOID;
+			break;
 		default:
 			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(expr));
 			type = InvalidOid;	/* keep compiler quiet */
@@ -985,6 +988,9 @@ exprCollation(const Node *expr)
 					coll = InvalidOid;
 			}
 			break;
+		case T_JsonIsPredicate:
+			coll = InvalidOid;	/* result is always an boolean type */
+			break;
 		default:
 			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(expr));
 			coll = InvalidOid;	/* keep compiler quiet */
@@ -1211,6 +1217,9 @@ exprSetCollation(Node *expr, Oid collation)
 					Assert(!OidIsValid(collation)); /* result is always a json[b] type */
 			}
 			break;
+		case T_JsonIsPredicate:
+			Assert(!OidIsValid(collation)); /* result is always boolean */
+			break;
 		default:
 			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(expr));
 			break;
@@ -1663,6 +1672,9 @@ exprLocation(const Node *expr)
 		case T_JsonConstructorExpr:
 			loc = ((const JsonConstructorExpr *) expr)->location;
 			break;
+		case T_JsonIsPredicate:
+			loc = ((const JsonIsPredicate *) expr)->location;
+			break;
 		default:
 			/* for any other node type it's just unknown... */
 			loc = -1;
@@ -2429,6 +2441,8 @@ expression_tree_walker(Node *node,
 					return true;
 			}
 			break;
+		case T_JsonIsPredicate:
+			return walker(((JsonIsPredicate *) node)->expr, context);
 		default:
 			elog(ERROR, "unrecognized node type: %d",
 				 (int) nodeTag(node));
@@ -3440,6 +3454,16 @@ expression_tree_mutator(Node *node,
 
 				return (Node *) newnode;
 			}
+		case T_JsonIsPredicate:
+			{
+				JsonIsPredicate *pred = (JsonIsPredicate *) node;
+				JsonIsPredicate *newnode;
+
+				FLATCOPY(newnode, pred, JsonIsPredicate);
+				MUTATE(newnode->expr, pred->expr, Node *);
+
+				return (Node *) newnode;
+			}
 		default:
 			elog(ERROR, "unrecognized node type: %d",
 				 (int) nodeTag(node));
@@ -4290,6 +4314,8 @@ raw_expression_tree_walker(Node *node,
 					return true;
 			}
 			break;
+		case T_JsonIsPredicate:
+			return walker(((JsonIsPredicate *) node)->expr, context);
 		default:
 			elog(ERROR, "unrecognized node type: %d",
 				 (int) nodeTag(node));
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 0c01f350867..278e87259dc 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -1797,6 +1797,17 @@ _outJsonConstructorExpr(StringInfo str, const JsonConstructorExpr *node)
 	WRITE_LOCATION_FIELD(location);
 }
 
+static void
+_outJsonIsPredicate(StringInfo str, const JsonIsPredicate *node)
+{
+	WRITE_NODE_TYPE("JSONISPREDICATE");
+
+	WRITE_NODE_FIELD(expr);
+	WRITE_ENUM_FIELD(value_type, JsonValueType);
+	WRITE_BOOL_FIELD(unique_keys);
+	WRITE_LOCATION_FIELD(location);
+}
+
 /*****************************************************************************
  *
  *	Stuff from pathnodes.h.
@@ -4630,6 +4641,9 @@ outNode(StringInfo str, const void *obj)
 			case T_JsonConstructorExpr:
 				_outJsonConstructorExpr(str, obj);
 				break;
+			case T_JsonIsPredicate:
+				_outJsonIsPredicate(str, obj);
+				break;
 
 			default:
 
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 3ee8ba6f159..5b9e235e9ad 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1493,6 +1493,22 @@ _readJsonConstructorExpr(void)
 }
 
 /*
+ * _readJsonIsPredicate
+ */
+static JsonIsPredicate *
+_readJsonIsPredicate()
+{
+	READ_LOCALS(JsonIsPredicate);
+
+	READ_NODE_FIELD(expr);
+	READ_ENUM_FIELD(value_type, JsonValueType);
+	READ_BOOL_FIELD(unique_keys);
+	READ_LOCATION_FIELD(location);
+
+	READ_DONE();
+}
+
+/*
  *	Stuff from pathnodes.h.
  *
  * Mostly we don't need to read planner nodes back in again, but some
@@ -3090,6 +3106,8 @@ parseNodeString(void)
 		return_value = _readJsonValueExpr();
 	else if (MATCH("JSONCTOREXPR", 12))
 		return_value = _readJsonConstructorExpr();
+	else if (MATCH("JSONISPREDICATE", 15))
+		return_value = _readJsonIsPredicate();
 	else
 	{
 		elog(ERROR, "badly formatted node string \"%.32s\"...", token);
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 9399fff610f..b658bcc182c 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -665,6 +665,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 
 %type <ival>		json_encoding
 					json_encoding_clause_opt
+					json_predicate_type_constraint_opt
 
 %type <boolean>		json_key_uniqueness_constraint_opt
 					json_object_constructor_null_clause_opt
@@ -734,7 +735,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 
 	JOIN JSON JSON_ARRAY JSON_ARRAYAGG JSON_OBJECT JSON_OBJECTAGG
 
-	KEY KEYS
+	KEY KEYS KEEP
 
 	LABEL LANGUAGE LARGE_P LAST_P LATERAL_P
 	LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL
@@ -763,9 +764,9 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
-	SAVEPOINT SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT SEQUENCE SEQUENCES
-	SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW
-	SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SQL_P STABLE STANDALONE_P
+	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
+	SEQUENCE SEQUENCES SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF
+	SHARE SHOW SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRIP_P
 	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P
 
@@ -853,13 +854,14 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
  * Using the same precedence as IDENT seems right for the reasons given above.
  */
 %nonassoc	UNBOUNDED		/* ideally would have same precedence as IDENT */
-%nonassoc	ABSENT UNIQUE
+%nonassoc	ABSENT UNIQUE JSON
 %nonassoc	IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
 %left		'^'
 %left		KEYS						/* UNIQUE [ KEYS ] */
+%left		OBJECT_P SCALAR VALUE_P		/* JSON [ OBJECT | SCALAR | VALUE ] */
 /* Unary Operators */
 %left		AT				/* sets precedence for AT TIME ZONE */
 %left		COLLATE
@@ -14141,6 +14143,46 @@ a_expr:		c_expr									{ $$ = $1; }
 														   @2),
 									 @2);
 				}
+			| a_expr
+				IS json_predicate_type_constraint_opt
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					JsonFormat *format = makeJsonFormat(JS_FORMAT_DEFAULT, JS_ENC_DEFAULT, -1);
+					$$ = makeJsonIsPredicate($1, format, $3, $4, @1);
+				}
+			/*
+			 * Required by standard, but it would conflict with expressions
+			 * like: 'str' || format(...)
+			| a_expr
+				FORMAT json_representation
+				IS  json_predicate_type_constraint_opt
+					json_key_uniqueness_constraint_opt		%prec FORMAT
+				{
+					$3.location = @2;
+					$$ = makeJsonIsPredicate($1, $3, $5, $6, @1);
+				}
+			*/
+			| a_expr
+				IS NOT
+					json_predicate_type_constraint_opt
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					JsonFormat *format = makeJsonFormat(JS_FORMAT_DEFAULT, JS_ENC_DEFAULT, -1);
+					$$ = makeNotExpr(makeJsonIsPredicate($1, format, $4, $5, @1), @1);
+				}
+			/*
+			 * Required by standard, but it would conflict with expressions
+			 * like: 'str' || format(...)
+			| a_expr
+				FORMAT json_representation
+				IS NOT
+					json_predicate_type_constraint_opt
+					json_key_uniqueness_constraint_opt		%prec FORMAT
+				{
+					$3.location = @2;
+					$$ = makeNotExpr(makeJsonIsPredicate($1, $3, $6, $7, @1), @1);
+				}
+			*/
 			| DEFAULT
 				{
 					/*
@@ -14223,6 +14265,14 @@ b_expr:		c_expr
 				}
 		;
 
+json_predicate_type_constraint_opt:
+			JSON									{ $$ = JS_TYPE_ANY; }
+			| JSON VALUE_P							{ $$ = JS_TYPE_ANY; }
+			| JSON ARRAY							{ $$ = JS_TYPE_ARRAY; }
+			| JSON OBJECT_P							{ $$ = JS_TYPE_OBJECT; }
+			| JSON SCALAR							{ $$ = JS_TYPE_SCALAR; }
+		;
+
 json_key_uniqueness_constraint_opt:
 			WITH_LA_UNIQUE unique_keys				{ $$ = true; }
 			| WITHOUT unique_keys					{ $$ = false; }
@@ -16412,6 +16462,7 @@ unreserved_keyword:
 			| ROWS
 			| RULE
 			| SAVEPOINT
+			| SCALAR
 			| SCHEMA
 			| SCHEMAS
 			| SCROLL
@@ -16882,6 +16933,7 @@ bare_label_keyword:
 			| JSON_ARRAYAGG
 			| JSON_OBJECT
 			| JSON_OBJECTAGG
+			| KEEP
 			| KEY
 			| KEYS
 			| LABEL
@@ -17011,6 +17063,7 @@ bare_label_keyword:
 			| ROWS
 			| RULE
 			| SAVEPOINT
+			| SCALAR
 			| SCHEMA
 			| SCHEMAS
 			| SCROLL
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 84be354f714..0b972ea6322 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -85,6 +85,7 @@ static Node *transformJsonArrayQueryConstructor(ParseState *pstate,
 												JsonArrayQueryConstructor *ctor);
 static Node *transformJsonObjectAgg(ParseState *pstate, JsonObjectAgg *agg);
 static Node *transformJsonArrayAgg(ParseState *pstate, JsonArrayAgg *agg);
+static Node *transformJsonIsPredicate(ParseState *pstate, JsonIsPredicate *p);
 static Node *make_row_comparison_op(ParseState *pstate, List *opname,
 									List *largs, List *rargs, int location);
 static Node *make_row_distinct_op(ParseState *pstate, List *opname,
@@ -332,6 +333,10 @@ transformExprRecurse(ParseState *pstate, Node *expr)
 			result = transformJsonArrayAgg(pstate, (JsonArrayAgg *) expr);
 			break;
 
+		case T_JsonIsPredicate:
+			result = transformJsonIsPredicate(pstate, (JsonIsPredicate *) expr);
+			break;
+
 		default:
 			/* should not reach here */
 			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(expr));
@@ -3869,3 +3874,74 @@ transformJsonArrayConstructor(ParseState *pstate, JsonArrayConstructor *ctor)
 								   returning, false, ctor->absent_on_null,
 								   ctor->location);
 }
+
+static Node *
+transformJsonParseArg(ParseState *pstate, Node *jsexpr, JsonFormat *format,
+					  Oid *exprtype)
+{
+	Node	   *raw_expr = transformExprRecurse(pstate, jsexpr);
+	Node	   *expr = raw_expr;
+
+	*exprtype = exprType(expr);
+
+	/* prepare input document */
+	if (*exprtype == BYTEAOID)
+	{
+		JsonValueExpr *jve;
+
+		expr = makeCaseTestExpr(raw_expr);
+		expr = makeJsonByteaToTextConversion(expr, format, exprLocation(expr));
+		*exprtype = TEXTOID;
+
+		jve = makeJsonValueExpr((Expr *) raw_expr, format);
+
+		jve->formatted_expr = (Expr *) expr;
+		expr = (Node *) jve;
+	}
+	else
+	{
+		char		typcategory;
+		bool		typispreferred;
+
+		get_type_category_preferred(*exprtype, &typcategory, &typispreferred);
+
+		if (*exprtype == UNKNOWNOID || typcategory == TYPCATEGORY_STRING)
+		{
+			expr = coerce_to_target_type(pstate, (Node *) expr, *exprtype,
+										 TEXTOID, -1,
+										 COERCION_IMPLICIT,
+										 COERCE_IMPLICIT_CAST, -1);
+			*exprtype = TEXTOID;
+		}
+
+		if (format->encoding != JS_ENC_DEFAULT)
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 parser_errposition(pstate, format->location),
+					 errmsg("cannot use JSON FORMAT ENCODING clause for non-bytea input types")));
+	}
+
+	return expr;
+}
+
+/*
+ * Transform IS JSON predicate into
+ * json[b]_is_valid(json, value_type [, check_key_uniqueness]) call.
+ */
+static Node *
+transformJsonIsPredicate(ParseState *pstate, JsonIsPredicate *pred)
+{
+	Oid			exprtype;
+	Node	   *expr = transformJsonParseArg(pstate, pred->expr, pred->format,
+											 &exprtype);
+
+	/* make resulting expression */
+	if (exprtype != TEXTOID && exprtype != JSONOID && exprtype != JSONBOID)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATATYPE_MISMATCH),
+				 errmsg("cannot use type %s in IS JSON predicate",
+						format_type_be(exprtype))));
+
+	return makeJsonIsPredicate(expr, NULL, pred->value_type,
+							   pred->unique_keys, pred->location);
+}
diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c
index d088fafc567..5edcb8bb60e 100644
--- a/src/backend/utils/adt/json.c
+++ b/src/backend/utils/adt/json.c
@@ -13,6 +13,7 @@
  */
 #include "postgres.h"
 
+#include "access/hash.h"
 #include "catalog/pg_proc.h"
 #include "catalog/pg_type.h"
 #include "common/hashfn.h"
@@ -1655,6 +1656,94 @@ escape_json(StringInfo buf, const char *str)
 	appendStringInfoCharMacro(buf, '"');
 }
 
+/* Semantic actions for key uniqueness check */
+static void
+json_unique_object_start(void *_state)
+{
+	JsonUniqueParsingState *state = _state;
+	JsonUniqueStackEntry *entry;
+
+	if (!state->unique)
+		return;
+
+	/* push object entry to stack */
+	entry = palloc(sizeof(*entry));
+	entry->object_id = state->id_counter++;
+	entry->parent = state->stack;
+	state->stack = entry;
+}
+
+static void
+json_unique_object_end(void *_state)
+{
+	JsonUniqueParsingState *state = _state;
+	JsonUniqueStackEntry *entry;
+
+	if (!state->unique)
+		return;
+
+	entry = state->stack;
+	state->stack = entry->parent;	/* pop object from stack */
+	pfree(entry);
+}
+
+static void
+json_unique_object_field_start(void *_state, char *field, bool isnull)
+{
+	JsonUniqueParsingState *state = _state;
+	JsonUniqueStackEntry *entry;
+
+	if (!state->unique)
+		return;
+
+	/* find key collision in the current object */
+	if (json_unique_check_key(&state->check, field, state->stack->object_id))
+		return;
+
+	state->unique = false;
+
+	/* pop all objects entries */
+	while ((entry = state->stack))
+	{
+		state->stack = entry->parent;
+		pfree(entry);
+	}
+}
+
+/* Validate JSON text and additionally check key uniqueness */
+bool
+json_validate(text *json, bool check_unique_keys)
+{
+	JsonLexContext *lex = makeJsonLexContext(json, check_unique_keys);
+	JsonSemAction uniqueSemAction = {0};
+	JsonUniqueParsingState state;
+	JsonParseErrorType result;
+
+	if (check_unique_keys)
+	{
+		state.lex = lex;
+		state.stack = NULL;
+		state.id_counter = 0;
+		state.unique = true;
+		json_unique_check_init(&state.check);
+
+		uniqueSemAction.semstate = &state;
+		uniqueSemAction.object_start = json_unique_object_start;
+		uniqueSemAction.object_field_start = json_unique_object_field_start;
+		uniqueSemAction.object_end = json_unique_object_end;
+	}
+
+	result = pg_parse_json(lex, check_unique_keys ? &uniqueSemAction : &nullSemAction);
+
+	if (result != JSON_SUCCESS)
+		return false;	/* invalid json */
+
+	if (check_unique_keys && !state.unique)
+		return false;	/* not unique keys */
+
+	return true;	/* ok */
+}
+
 /*
  * SQL function json_typeof(json) -> text
  *
@@ -1670,21 +1759,13 @@ escape_json(StringInfo buf, const char *str)
 Datum
 json_typeof(PG_FUNCTION_ARGS)
 {
-	text	   *json;
-
-	JsonLexContext *lex;
-	JsonTokenType tok;
+	text	   *json = PG_GETARG_TEXT_PP(0);
 	char	   *type;
-	JsonParseErrorType result;
-
-	json = PG_GETARG_TEXT_PP(0);
-	lex = makeJsonLexContext(json, false);
+	JsonTokenType tok;
 
 	/* Lex exactly one token from the input and check its type. */
-	result = json_lex(lex);
-	if (result != JSON_SUCCESS)
-		json_ereport_error(result, lex);
-	tok = lex->token_type;
+	tok = json_get_first_token(json, true);
+
 	switch (tok)
 	{
 		case JSON_TOKEN_OBJECT_START:
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index 29664aa6e40..a24d498b060 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -5528,3 +5528,23 @@ transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype
 	else
 		appendStringInfoString(_state->strval, token);
 }
+
+JsonTokenType
+json_get_first_token(text *json, bool throw_error)
+{
+	JsonLexContext *lex;
+	JsonParseErrorType result;
+
+	lex = makeJsonLexContext(json, false);
+
+	/* Lex exactly one token from the input and check its type. */
+	result = json_lex(lex);
+
+	if (result == JSON_SUCCESS)
+		return lex->token_type;
+
+	if (throw_error)
+		json_ereport_error(result, lex);
+
+	return JSON_TOKEN_INVALID;	/* invalid json */
+}
diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index 38da2695197..0ed774f6e66 100644
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -8230,6 +8230,7 @@ isSimpleNode(Node *node, Node *parentNode, int prettyFlags)
 		case T_NullTest:
 		case T_BooleanTest:
 		case T_DistinctExpr:
+		case T_JsonIsPredicate:
 			switch (nodeTag(parentNode))
 			{
 				case T_FuncExpr:
@@ -9635,6 +9636,40 @@ get_rule_expr(Node *node, deparse_context *context,
 			get_json_constructor((JsonConstructorExpr *) node, context, false);
 			break;
 
+		case T_JsonIsPredicate:
+			{
+				JsonIsPredicate *pred = (JsonIsPredicate *) node;
+
+				if (!PRETTY_PAREN(context))
+					appendStringInfoChar(context->buf, '(');
+
+				get_rule_expr_paren(pred->expr, context, true, node);
+
+				appendStringInfoString(context->buf, " IS JSON");
+
+				switch (pred->value_type)
+				{
+					case JS_TYPE_SCALAR:
+						appendStringInfoString(context->buf, " SCALAR");
+						break;
+					case JS_TYPE_ARRAY:
+						appendStringInfoString(context->buf, " ARRAY");
+						break;
+					case JS_TYPE_OBJECT:
+						appendStringInfoString(context->buf, " OBJECT");
+						break;
+					default:
+						break;
+				}
+
+				if (pred->unique_keys)
+					appendStringInfoString(context->buf, " WITH UNIQUE KEYS");
+
+				if (!PRETTY_PAREN(context))
+					appendStringInfoChar(context->buf, ')');
+			}
+			break;
+
 		case T_List:
 			{
 				char	   *sep;
diff --git a/src/backend/utils/misc/queryjumble.c b/src/backend/utils/misc/queryjumble.c
index d14b7510581..83158127936 100644
--- a/src/backend/utils/misc/queryjumble.c
+++ b/src/backend/utils/misc/queryjumble.c
@@ -775,6 +775,16 @@ JumbleExpr(JumbleState *jstate, Node *node)
 				APP_JUMB(ctor->absent_on_null);
 			}
 			break;
+		case T_JsonIsPredicate:
+			{
+				JsonIsPredicate *pred = (JsonIsPredicate *) node;
+
+				JumbleExpr(jstate, (Node *) pred->expr);
+				JumbleExpr(jstate, (Node *) pred->format);
+				APP_JUMB(pred->unique_keys);
+				APP_JUMB(pred->value_type);
+			}
+			break;
 		case T_List:
 			foreach(temp, (List *) node)
 			{