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

Author: adunstan

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));

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
  *

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;

src/backend/jit/llvm/llvmjit_types.c

@@ -132,6 +132,7 @@ void	   *referenced_functions[] =
 	ExecEvalWholeRowVar,
 	ExecEvalXmlExpr,
 	ExecEvalJsonConstructor,
+	ExecEvalJsonIsPredicate,
 	MakeExpandedObjectReadOnlyInternal,
 	slot_getmissingattrs,
 	slot_getsomeattrs_int,

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

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

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;
+}

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));
@@ -3438,6 +3452,16 @@ expression_tree_mutator(Node *node,
 				MUTATE(newnode->coercion, jve->coercion, Expr *);
 				MUTATE(newnode->returning, jve->returning, JsonReturning *);
 
+				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:
@@ -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));

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:
 

src/backend/nodes/readfuncs.c

@@ -1492,6 +1492,22 @@ _readJsonConstructorExpr(void)
 	READ_DONE();
 }
 
+/*
+ * _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.
  *
@@ -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);