SQL/JSON: support the IS JSON predicate

This patch introduces 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 IS and IS NOT variants and supports a WITH
UNIQUE KEYS flag. The tests are:

IS JSON [VALUE]
IS JSON ARRAY
IS JSON OBJECT
IS JSON SCALAR

These should be self-explanatory.

The WITH UNIQUE KEYS flag makes these return false when duplicate keys
exist in any object within the value, not necessarily directly contained
in the outermost object.

Author: Nikita Glukhov <n.gluhov@postgrespro.ru>
Author: Teodor Sigaev <teodor@sigaev.ru>
Author: Oleg Bartunov <obartunov@gmail.com>
Author: Alexander Korotkov <aekorotkov@gmail.com>
Author: Amit Langote <amitlangote09@gmail.com>
Author: Andrew Dunstan <andrew@dunslane.net>

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/CAF4Au4w2x-5LTnN_bxky-mq4=WOqsGsxSpENCzHRAzSnEd8+WQ@mail.gmail.com
Discussion: https://postgr.es/m/cd0bb935-0158-78a7-08b5-904886deac4b@postgrespro.ru
Discussion: https://postgr.es/m/20220616233130.rparivafipt6doj3@alap3.anarazel.de
Discussion: https://postgr.es/m/abd9b83b-aa66-f230-3d6d-734817f0995d%40postgresql.org

2 files changed, 138 insertions, 6 deletions

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index f3ddc34afbe..1b5daf6734b 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -655,6 +655,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 					json_array_aggregate_order_by_clause_opt
 
 %type <ival>		json_encoding_clause_opt
+					json_predicate_type_constraint
 
 %type <boolean>		json_key_uniqueness_constraint_opt
 					json_object_constructor_null_clause_opt
@@ -754,7 +755,8 @@ 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
+	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
@@ -818,6 +820,12 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %nonassoc	'<' '>' '=' LESS_EQUALS GREATER_EQUALS NOT_EQUALS
 %nonassoc	BETWEEN IN_P LIKE ILIKE SIMILAR NOT_LA
 %nonassoc	ESCAPE			/* ESCAPE must be just above LIKE/ILIKE/SIMILAR */
+
+/* SQL/JSON related keywords */
+%nonassoc	UNIQUE JSON
+%nonassoc	KEYS OBJECT_P SCALAR VALUE_P
+%nonassoc	WITH WITHOUT_LA
+
 /*
  * To support target_el without AS, it used to be necessary to assign IDENT an
  * explicit precedence just less than Op.  While that's not really necessary
@@ -14850,6 +14858,44 @@ a_expr:		c_expr									{ $$ = $1; }
 														   @2),
 									 @2);
 				}
+			| a_expr IS json_predicate_type_constraint
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					JsonFormat *format = makeJsonFormat(JS_FORMAT_DEFAULT, JS_ENC_DEFAULT, -1);
+
+					$$ = makeJsonIsPredicate($1, format, $3, $4, @1);
+				}
+			/*
+			 * Required by SQL/JSON, but there are conflicts
+			| a_expr
+				FORMAT_LA JSON json_encoding_clause_opt
+				IS  json_predicate_type_constraint
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					$3.location = @2;
+					$$ = makeJsonIsPredicate($1, $3, $5, $6, @1);
+				}
+			*/
+			| a_expr IS NOT
+					json_predicate_type_constraint
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					JsonFormat *format = makeJsonFormat(JS_FORMAT_DEFAULT, JS_ENC_DEFAULT, -1);
+
+					$$ = makeNotExpr(makeJsonIsPredicate($1, format, $4, $5, @1), @1);
+				}
+			/*
+			 * Required by SQL/JSON, but there are conflicts
+			| a_expr
+				FORMAT_LA JSON json_encoding_clause_opt
+				IS NOT
+					json_predicate_type_constraint
+					json_key_uniqueness_constraint_opt		%prec IS
+				{
+					$3.location = @2;
+					$$ = makeNotExpr(makeJsonIsPredicate($1, $3, $6, $7, @1), @1);
+				}
+			*/
 			| DEFAULT
 				{
 					/*
@@ -16406,13 +16452,21 @@ json_output_clause_opt:
 			| /* EMPTY */							{ $$ = NULL; }
 		;
 
+json_predicate_type_constraint:
+			JSON									{ $$ = JS_TYPE_ANY; }
+			| JSON VALUE_P							{ $$ = JS_TYPE_ANY; }
+			| JSON ARRAY							{ $$ = JS_TYPE_ARRAY; }
+			| JSON OBJECT_P							{ $$ = JS_TYPE_OBJECT; }
+			| JSON SCALAR							{ $$ = JS_TYPE_SCALAR; }
+		;
+
 /* KEYS is a noise word here */
 json_key_uniqueness_constraint_opt:
-			WITH UNIQUE KEYS				{ $$ = true; }
-			| WITH UNIQUE				    { $$ = true; }
-			| WITHOUT_LA UNIQUE KEYS		{ $$ = false; }
-			| WITHOUT_LA UNIQUE			    { $$ = false; }
-			| /* EMPTY */ 					{ $$ = false; }
+			WITH UNIQUE KEYS							{ $$ = true; }
+			| WITH UNIQUE								{ $$ = true; }
+			| WITHOUT_LA UNIQUE KEYS					{ $$ = false; }
+			| WITHOUT_LA UNIQUE							{ $$ = false; }
+			| /* EMPTY */ 				%prec KEYS		{ $$ = false; }
 		;
 
 json_name_and_value_list:
@@ -17182,6 +17236,7 @@ unreserved_keyword:
 			| ROWS
 			| RULE
 			| SAVEPOINT
+			| SCALAR
 			| SCHEMA
 			| SCHEMAS
 			| SCROLL
@@ -17784,6 +17839,7 @@ 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 737b479f541..4c99dd1dec3 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -83,6 +83,7 @@ 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,
@@ -325,6 +326,10 @@ 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));
@@ -3818,3 +3823,74 @@ 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.
+ */
+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))));
+
+	/* This intentionally(?) drops the format clause. */
+	return makeJsonIsPredicate(expr, NULL, pred->item_type,
+							   pred->unique_keys, pred->location);
+}