On 2022-12-09 Fr 10:37, Andrew Dunstan wrote:
> I am currently looking at the json types. I think that will be enough to
> let us rework the sql/json patches as discussed a couple of months ago.
>
OK, json is a fairly easy case, see attached. But jsonb is a different
kettle of fish. Both the semantic routines called by the parser and the
subsequent call to JsonbValueToJsonb() can raise errors. These are
pretty much all about breaking various limits (for strings, objects,
arrays). There's also a call to numeric_in, but I assume that a string
that's already parsed as a valid json numeric literal won't upset
numeric_in. Many of these occur several calls down the stack, so
adjusting everything to deal with them would be fairly invasive. Perhaps
we could instead document that this class of input error won't be
trapped, at least for jsonb. We could still test for well-formed jsonb
input, just as I propose for json. That means that we would not be able
to trap one of these errors in the ON ERROR clause of JSON_TABLE. I
think we can probably live with that.
Thoughts?
cheers
andrew
--
Andrew Dunstan
EDB: https://www.enterprisedb.com
From 945ede5fa99f5aa9fb0740fe04303f37aa511528 Mon Sep 17 00:00:00 2001
From: Andrew Dunstan <and...@dunslane.net>
Date: Sat, 10 Dec 2022 08:18:57 -0500
Subject: [PATCH] adjustments for json_in
---
src/backend/utils/adt/json.c | 7 ++++---
src/backend/utils/adt/jsonfuncs.c | 26 +++++++++++++++++---------
src/include/utils/jsonfuncs.h | 14 +++++++++-----
src/test/regress/expected/json.out | 19 +++++++++++++++++++
src/test/regress/sql/json.sql | 5 +++++
5 files changed, 54 insertions(+), 17 deletions(-)
diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c
index fee2ffb55c..d5c48c99c3 100644
--- a/src/backend/utils/adt/json.c
+++ b/src/backend/utils/adt/json.c
@@ -81,9 +81,10 @@ json_in(PG_FUNCTION_ARGS)
/* validate it */
lex = makeJsonLexContext(result, false);
- pg_parse_json_or_ereport(lex, &nullSemAction);
+ if ( ! pg_parse_json_or_errsave(lex, &nullSemAction, fcinfo->context))
+ PG_RETURN_NULL();
- /* Internal representation is the same as text, for now */
+ /* Internal representation is the same as text */
PG_RETURN_TEXT_P(result);
}
@@ -1337,7 +1338,7 @@ json_typeof(PG_FUNCTION_ARGS)
/* Lex exactly one token from the input and check its type. */
result = json_lex(lex);
if (result != JSON_SUCCESS)
- json_ereport_error(result, lex);
+ json_errsave_error(result, lex, NULL);
tok = lex->token_type;
switch (tok)
{
diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c
index bfc3f02a86..1a3cec59cb 100644
--- a/src/backend/utils/adt/jsonfuncs.c
+++ b/src/backend/utils/adt/jsonfuncs.c
@@ -490,21 +490,28 @@ static void transform_string_values_object_field_start(void *state, char *fname,
static void transform_string_values_array_element_start(void *state, bool isnull);
static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype);
+
/*
- * pg_parse_json_or_ereport
+ * pg_parse_json_or_errsave
*
* This function is like pg_parse_json, except that it does not return a
* JsonParseErrorType. Instead, in case of any failure, this function will
- * ereport(ERROR).
+ * call errsave(escontext), which will call ereport(ERROR) if escontext is NULL.
+ * Otherwise, returns a boolean indicating success or failure.
*/
-void
-pg_parse_json_or_ereport(JsonLexContext *lex, JsonSemAction *sem)
+bool
+pg_parse_json_or_errsave(JsonLexContext *lex, JsonSemAction *sem,
+ Node *escontext)
{
JsonParseErrorType result;
result = pg_parse_json(lex, sem);
if (result != JSON_SUCCESS)
- json_ereport_error(result, lex);
+ {
+ json_errsave_error(result, lex, escontext);
+ return false;
+ }
+ return true;
}
/*
@@ -608,17 +615,18 @@ jsonb_object_keys(PG_FUNCTION_ARGS)
* Report a JSON error.
*/
void
-json_ereport_error(JsonParseErrorType error, JsonLexContext *lex)
+json_errsave_error(JsonParseErrorType error, JsonLexContext *lex,
+ Node *escontext)
{
if (error == JSON_UNICODE_HIGH_ESCAPE ||
error == JSON_UNICODE_CODE_POINT_ZERO)
- ereport(ERROR,
+ errsave(escontext,
(errcode(ERRCODE_UNTRANSLATABLE_CHARACTER),
errmsg("unsupported Unicode escape sequence"),
errdetail_internal("%s", json_errdetail(error, lex)),
report_json_context(lex)));
else
- ereport(ERROR,
+ errsave(escontext,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid input syntax for type %s", "json"),
errdetail_internal("%s", json_errdetail(error, lex)),
@@ -1260,7 +1268,7 @@ get_array_start(void *state)
error = json_count_array_elements(_state->lex, &nelements);
if (error != JSON_SUCCESS)
- json_ereport_error(error, _state->lex);
+ json_errsave_error(error, _state->lex, NULL);
if (-_state->path_indexes[lex_level] <= nelements)
_state->path_indexes[lex_level] += nelements;
diff --git a/src/include/utils/jsonfuncs.h b/src/include/utils/jsonfuncs.h
index 865b2ff7c1..f5cd2aef23 100644
--- a/src/include/utils/jsonfuncs.h
+++ b/src/include/utils/jsonfuncs.h
@@ -16,7 +16,6 @@
#include "common/jsonapi.h"
#include "utils/jsonb.h"
-
/*
* Flag types for iterate_json(b)_values to specify what elements from a
* json(b) document we want to iterate.
@@ -39,11 +38,16 @@ typedef text *(*JsonTransformStringValuesAction) (void *state, char *elem_value,
/* build a JsonLexContext from a text datum */
extern JsonLexContext *makeJsonLexContext(text *json, bool need_escapes);
-/* try to parse json, and ereport(ERROR) on failure */
-extern void pg_parse_json_or_ereport(JsonLexContext *lex, JsonSemAction *sem);
+/* try to parse json, and errsave(escontext) on failure */
+extern bool pg_parse_json_or_errsave(JsonLexContext *lex, JsonSemAction *sem,
+ Node *escontext);
-/* report an error during json lexing or parsing */
-extern void json_ereport_error(JsonParseErrorType error, JsonLexContext *lex);
+#define pg_parse_json_or_ereport(lex, sem) \
+ (void) pg_parse_json_or_errsave(lex, sem, NULL)
+
+/* save an error during json lexing or parsing */
+extern void json_errsave_error(JsonParseErrorType error, JsonLexContext *lex,
+ Node *escontext);
extern uint32 parse_jsonb_index_flags(Jsonb *jb);
extern void iterate_jsonb_values(Jsonb *jb, uint32 flags, void *state,
diff --git a/src/test/regress/expected/json.out b/src/test/regress/expected/json.out
index cb181226e9..674f1c59d4 100644
--- a/src/test/regress/expected/json.out
+++ b/src/test/regress/expected/json.out
@@ -2649,3 +2649,22 @@ select ts_headline('[]'::json, tsquery('aaa & bbb'));
[]
(1 row)
+-- test non-error-throwing input
+select pg_input_is_valid('{"a":true}','json');
+ pg_input_is_valid
+-------------------
+ t
+(1 row)
+
+select pg_input_is_valid('{"a":true','json');
+ pg_input_is_valid
+-------------------
+ f
+(1 row)
+
+select pg_input_error_message('{"a":true','json');
+ pg_input_error_message
+------------------------------------
+ invalid input syntax for type json
+(1 row)
+
diff --git a/src/test/regress/sql/json.sql b/src/test/regress/sql/json.sql
index 589e0cea36..2ba883dfe5 100644
--- a/src/test/regress/sql/json.sql
+++ b/src/test/regress/sql/json.sql
@@ -855,3 +855,8 @@ select ts_headline('english', '{"a": "aaa bbb", "b": {"c": "ccc ddd fff", "c1":
select ts_headline('null'::json, tsquery('aaa & bbb'));
select ts_headline('{}'::json, tsquery('aaa & bbb'));
select ts_headline('[]'::json, tsquery('aaa & bbb'));
+
+-- test non-error-throwing input
+select pg_input_is_valid('{"a":true}','json');
+select pg_input_is_valid('{"a":true','json');
+select pg_input_error_message('{"a":true','json');
--
2.34.1
