Fix handling of nested JSON objects in json_populate_recordset and friends.

tglsfdc · tglsfdc · commit a1fc36495f00 · 2014-06-24T21:22:47.000-07:00
populate_recordset_object_start() improperly created a new hash table
(overwriting the link to the existing one) if called at nest levels
greater than one.  This resulted in previous fields not appearing in
the final output, as reported by Matti Hameister in bug #10728.
In 9.4 the problem also affects json_to_recordset.

This perhaps missed detection earlier because the default behavior is to
throw an error for nested objects: you have to pass use_json_as_text = true
to see the problem.

In addition, fix query-lifespan leakage of the hashtable created by
json_populate_record().  This is pretty much the same problem recently
fixed in dblink: creating an intended-to-be-temporary context underneath
the executor's per-tuple context isn't enough to make it go away at the
end of the tuple cycle, because MemoryContextReset is not
MemoryContextResetAndDeleteChildren.

Michael Paquier and Tom Lane
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
@@ -1282,8 +1282,10 @@ json_populate_record(PG_FUNCTION_ARGS)
 	 * nulls.
 	 */
 	if (hash_get_num_entries(json_hash) == 0 && rec)
+	{
+		hash_destroy(json_hash);
 		PG_RETURN_POINTER(rec);
-
+	}
 
 	tupdesc = lookup_rowtype_tupdesc(tupType, tupTypmod);
 	ncolumns = tupdesc->natts;
@@ -1408,6 +1410,8 @@ json_populate_record(PG_FUNCTION_ARGS)
 
 	ReleaseTupleDesc(tupdesc);
 
+	hash_destroy(json_hash);
+
 	PG_RETURN_DATUM(HeapTupleGetDatum(rettuple));
 }
 
@@ -1698,16 +1702,23 @@ populate_recordset_object_start(void *state)
 	int			lex_level = _state->lex->lex_level;
 	HASHCTL		ctl;
 
+	/* Reject object at top level: we must have an array at level 0 */
 	if (lex_level == 0)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 				 errmsg("cannot call json_populate_recordset on an object")));
-	else if (lex_level > 1 && !_state->use_json_as_text)
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
-		 errmsg("cannot call json_populate_recordset with nested objects")));
 
-	/* set up a new hash for this entry */
+	/* Nested objects, if allowed, require no special processing */
+	if (lex_level > 1)
+	{
+		if (!_state->use_json_as_text)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("cannot call json_populate_recordset with nested objects")));
+		return;
+	}
+
+	/* Object at level 1: set up a new hash table for this object */
 	memset(&ctl, 0, sizeof(ctl));
 	ctl.keysize = NAMEDATALEN;
 	ctl.entrysize = sizeof(JsonHashEntry);
@@ -1734,9 +1745,11 @@ populate_recordset_object_end(void *state)
 	HeapTupleHeader rec = _state->rec;
 	HeapTuple	rettuple;
 
+	/* Nested objects require no special processing */
 	if (_state->lex->lex_level > 1)
 		return;
 
+	/* Otherwise, construct and return a tuple based on this level-1 object */
 	values = (Datum *) palloc(ncolumns * sizeof(Datum));
 	nulls = (bool *) palloc(ncolumns * sizeof(bool));
 
@@ -1828,7 +1841,9 @@ populate_recordset_object_end(void *state)
 
 	tuplestore_puttuple(_state->tuple_store, rettuple);
 
+	/* Done with hash for this object */
 	hash_destroy(json_hash);
+	_state->json_hash = NULL;
 }
 
 static void
diff --git a/src/test/regress/expected/json.out b/src/test/regress/expected/json.out
@@ -901,6 +901,13 @@ select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,3
 
 select * from json_populate_recordset(row('def',99,null)::jpop,'[{"c":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]',true) q;
 ERROR:  invalid input syntax for type timestamp: "[100,200,300]"
+create type jpop2 as (a int, b json, c int, d int);
+select * from json_populate_recordset(null::jpop2, '[{"a":2,"c":3,"b":{"z":4},"d":6}]',true) q;
+ a |    b    | c | d 
+---+---------+---+---
+ 2 | {"z":4} | 3 | 6
+(1 row)
+
 -- using the default use_json_as_text argument
 select * from json_populate_recordset(null::jpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
    a    | b |            c             
diff --git a/src/test/regress/expected/json_1.out b/src/test/regress/expected/json_1.out
@@ -901,6 +901,13 @@ select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,3
 
 select * from json_populate_recordset(row('def',99,null)::jpop,'[{"c":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]',true) q;
 ERROR:  invalid input syntax for type timestamp: "[100,200,300]"
+create type jpop2 as (a int, b json, c int, d int);
+select * from json_populate_recordset(null::jpop2, '[{"a":2,"c":3,"b":{"z":4},"d":6}]',true) q;
+ a |    b    | c | d 
+---+---------+---+---
+ 2 | {"z":4} | 3 | 6
+(1 row)
+
 -- using the default use_json_as_text argument
 select * from json_populate_recordset(null::jpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
    a    | b |            c             
diff --git a/src/test/regress/sql/json.sql b/src/test/regress/sql/json.sql
@@ -290,6 +290,9 @@ select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":"blurfl","
 select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]',true) q;
 select * from json_populate_recordset(row('def',99,null)::jpop,'[{"c":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]',true) q;
 
+create type jpop2 as (a int, b json, c int, d int);
+select * from json_populate_recordset(null::jpop2, '[{"a":2,"c":3,"b":{"z":4},"d":6}]',true) q;
+
 -- using the default use_json_as_text argument
 
 select * from json_populate_recordset(null::jpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
