Adjust pg_parse_json() so that it does not directly ereport().

Instead, it now returns a value indicating either success or the
type of error which occurred. The old behavior is still available
by calling pg_parse_json_or_ereport(). If the new interface is
used, an error can be thrown by passing the return value of
pg_parse_json() to json_ereport_error().

pg_parse_json() can still elog() in can't-happen cases, but it
seems like that issue is best handled separately.

Adjust json_lex() and json_count_array_elements() to return an
error code, too.

This is all in preparation for making the backend's json parser
available to frontend code.

Reviewed and/or tested by Mark Dilger and Andrew Dunstan.

Discussion: http://postgr.es/m/CA+TgmoYfOXhd27MUDGioVh6QtpD0C1K-f6ObSA10AWiHBAL5bA@mail.gmail.com

src/backend/utils/adt/json.c

@@ -81,7 +81,7 @@ json_in(PG_FUNCTION_ARGS)
 
 	/* validate it */
 	lex = makeJsonLexContext(result, false);
-	pg_parse_json(lex, &nullSemAction);
+	pg_parse_json_or_ereport(lex, &nullSemAction);
 
 	/* Internal representation is the same as text, for now */
 	PG_RETURN_TEXT_P(result);
@@ -128,7 +128,7 @@ json_recv(PG_FUNCTION_ARGS)
 
 	/* Validate it. */
 	lex = makeJsonLexContextCstringLen(str, nbytes, false);
-	pg_parse_json(lex, &nullSemAction);
+	pg_parse_json_or_ereport(lex, &nullSemAction);
 
 	PG_RETURN_TEXT_P(cstring_to_text_with_len(str, nbytes));
 }
@@ -1337,12 +1337,15 @@ json_typeof(PG_FUNCTION_ARGS)
 	JsonLexContext *lex;
 	JsonTokenType tok;
 	char	   *type;
+	JsonParseErrorType	result;
 
 	json = PG_GETARG_TEXT_PP(0);
 	lex = makeJsonLexContext(json, false);
 
 	/* Lex exactly one token from the input and check its type. */
-	json_lex(lex);
+	result = json_lex(lex);
+	if (result != JSON_SUCCESS)
+		json_ereport_error(result, lex);
 	tok = lex->token_type;
 	switch (tok)
 	{

src/backend/utils/adt/jsonb.c

@@ -272,7 +272,7 @@ jsonb_from_cstring(char *json, int len)
 	sem.scalar = jsonb_in_scalar;
 	sem.object_field_start = jsonb_in_object_field_start;
 
-	pg_parse_json(lex, &sem);
+	pg_parse_json_or_ereport(lex, &sem);
 
 	/* after parsing, the item member has the composed jsonb structure */
 	PG_RETURN_POINTER(JsonbValueToJsonb(state.res));
@@ -860,7 +860,7 @@ datum_to_jsonb(Datum val, bool is_null, JsonbInState *result,
 					sem.scalar = jsonb_in_scalar;
 					sem.object_field_start = jsonb_in_object_field_start;
 
-					pg_parse_json(lex, &sem);
+					pg_parse_json_or_ereport(lex, &sem);
 
 				}
 				break;

src/backend/utils/adt/jsonfuncs.c

@@ -606,7 +606,7 @@ json_object_keys(PG_FUNCTION_ARGS)
 		sem->object_field_start = okeys_object_field_start;
 		/* remainder are all NULL, courtesy of palloc0 above */
 
-		pg_parse_json(lex, sem);
+		pg_parse_json_or_ereport(lex, sem);
 		/* keys are now in state->result */
 
 		pfree(lex->strval->data);
@@ -1000,7 +1000,7 @@ get_worker(text *json,
 		sem->array_element_end = get_array_element_end;
 	}
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	return state->tresult;
 }
@@ -1148,7 +1148,12 @@ get_array_start(void *state)
 			_state->path_indexes[lex_level] != INT_MIN)
 		{
 			/* Negative subscript -- convert to positive-wise subscript */
-			int			nelements = json_count_array_elements(_state->lex);
+			JsonParseErrorType error;
+			int			nelements;
+
+			error = json_count_array_elements(_state->lex, &nelements);
+			if (error != JSON_SUCCESS)
+				json_ereport_error(error, _state->lex);
 
 			if (-_state->path_indexes[lex_level] <= nelements)
 				_state->path_indexes[lex_level] += nelements;
@@ -1548,7 +1553,7 @@ json_array_length(PG_FUNCTION_ARGS)
 	sem->scalar = alen_scalar;
 	sem->array_element_start = alen_array_element_start;
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	PG_RETURN_INT32(state->count);
 }
@@ -1814,7 +1819,7 @@ each_worker(FunctionCallInfo fcinfo, bool as_text)
 										   "json_each temporary cxt",
 										   ALLOCSET_DEFAULT_SIZES);
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	MemoryContextDelete(state->tmp_cxt);
 
@@ -2113,7 +2118,7 @@ elements_worker(FunctionCallInfo fcinfo, const char *funcname, bool as_text)
 										   "json_array_elements temporary cxt",
 										   ALLOCSET_DEFAULT_SIZES);
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	MemoryContextDelete(state->tmp_cxt);
 
@@ -2485,7 +2490,7 @@ populate_array_json(PopulateArrayContext *ctx, char *json, int len)
 	sem.array_element_end = populate_array_element_end;
 	sem.scalar = populate_array_scalar;
 
-	pg_parse_json(state.lex, &sem);
+	pg_parse_json_or_ereport(state.lex, &sem);
 
 	/* number of dimensions should be already known */
 	Assert(ctx->ndims > 0 && ctx->dims);
@@ -3342,7 +3347,7 @@ get_json_object_as_hash(char *json, int len, const char *funcname)
 	sem->object_field_start = hash_object_field_start;
 	sem->object_field_end = hash_object_field_end;
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	return tab;
 }
@@ -3641,7 +3646,7 @@ populate_recordset_worker(FunctionCallInfo fcinfo, const char *funcname,
 
 		state->lex = lex;
 
-		pg_parse_json(lex, sem);
+		pg_parse_json_or_ereport(lex, sem);
 	}
 	else
 	{
@@ -3971,7 +3976,7 @@ json_strip_nulls(PG_FUNCTION_ARGS)
 	sem->array_element_start = sn_array_element_start;
 	sem->object_field_start = sn_object_field_start;
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	PG_RETURN_TEXT_P(cstring_to_text_with_len(state->strval->data,
 											  state->strval->len));
@@ -5110,7 +5115,7 @@ iterate_json_values(text *json, uint32 flags, void *action_state,
 	sem->scalar = iterate_values_scalar;
 	sem->object_field_start = iterate_values_object_field_start;
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 }
 
 /*
@@ -5230,7 +5235,7 @@ transform_json_string_values(text *json, void *action_state,
 	sem->array_element_start = transform_string_values_array_element_start;
 	sem->object_field_start = transform_string_values_object_field_start;
 
-	pg_parse_json(lex, sem);
+	pg_parse_json_or_ereport(lex, sem);
 
 	return cstring_to_text_with_len(state->strval->data, state->strval->len);
 }

src/include/utils/jsonapi.h

@@ -33,6 +33,28 @@ typedef enum
 	JSON_TOKEN_END
 } JsonTokenType;
 
+typedef enum
+{
+	JSON_SUCCESS,
+	JSON_ESCAPING_INVALID,
+	JSON_ESCAPING_REQUIRED,
+	JSON_EXPECTED_ARRAY_FIRST,
+	JSON_EXPECTED_ARRAY_NEXT,
+	JSON_EXPECTED_COLON,
+	JSON_EXPECTED_END,
+	JSON_EXPECTED_JSON,
+	JSON_EXPECTED_MORE,
+	JSON_EXPECTED_OBJECT_FIRST,
+	JSON_EXPECTED_OBJECT_NEXT,
+	JSON_EXPECTED_STRING,
+	JSON_INVALID_TOKEN,
+	JSON_UNICODE_CODE_POINT_ZERO,
+	JSON_UNICODE_ESCAPE_FORMAT,
+	JSON_UNICODE_HIGH_ESCAPE,
+	JSON_UNICODE_HIGH_SURROGATE,
+	JSON_UNICODE_LOW_SURROGATE
+} JsonParseErrorType;
+
 
 /*
  * All the fields in this structure should be treated as read-only.
@@ -101,7 +123,14 @@ typedef struct JsonSemAction
  * points to. If the action pointers are NULL the parser
  * does nothing and just continues.
  */
-extern void pg_parse_json(JsonLexContext *lex, JsonSemAction *sem);
+extern JsonParseErrorType pg_parse_json(JsonLexContext *lex,
+										JsonSemAction *sem);
+
+/*
+ * Same thing, but signal errors via ereport(ERROR) instead of returning
+ * a result code.
+ */
+extern void pg_parse_json_or_ereport(JsonLexContext *lex, JsonSemAction *sem);
 
 /* the null action object used for pure validation */
 extern JsonSemAction nullSemAction;
@@ -110,8 +139,13 @@ extern JsonSemAction nullSemAction;
  * json_count_array_elements performs a fast secondary parse to determine the
  * number of elements in passed array lex context. It should be called from an
  * array_start action.
+ *
+ * The return value indicates whether any error occurred, while the number
+ * of elements is stored into *elements (but only if the return value is
+ * JSON_SUCCESS).
  */
-extern int	json_count_array_elements(JsonLexContext *lex);
+extern JsonParseErrorType json_count_array_elements(JsonLexContext *lex,
+													int *elements);
 
 /*
  * constructors for JsonLexContext, with or without strval element.
@@ -128,7 +162,13 @@ extern JsonLexContext *makeJsonLexContextCstringLen(char *json,
 													bool need_escapes);
 
 /* lex one token */
-extern void json_lex(JsonLexContext *lex);
+extern JsonParseErrorType json_lex(JsonLexContext *lex);
+
+/* report an error during json lexing or parsing */
+extern void json_ereport_error(JsonParseErrorType error, JsonLexContext *lex);
+
+/* construct an error detail string for a json error */
+extern char *json_errdetail(JsonParseErrorType error, JsonLexContext *lex);
 
 /*
  * Utility function to check if a string is a valid JSON number.