database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-09-02 04:21:28 +03:00
Code Activity

Fix JSON error reporting for many cases of erroneous string values.

Browse Source 
The majority of error exit cases in json_lex_string() failed to
set lex->token_terminator, causing problems for the error context
reporting code: it would see token_terminator less than token_start
and do something more or less nuts.  In v14 and up the end result
could be as bad as a crash in report_json_context().  Older
versions accidentally avoided that fate; but all versions produce
error context lines that are far less useful than intended,
because they'd stop at the end of the prior token instead of
continuing to where the actually-bad input is.

To fix, invent some macros that make it less notationally painful
to do the right thing.  Also add documentation about what the
function is actually required to do; and in >= v14, add an assertion
in report_json_context about token_terminator being sufficiently
far advanced.

Per report from Nikolay Shaplov.  Back-patch to all supported
versions.

Discussion: https://postgr.es/m/7332649.x5DLKWyVIX@thinkpad-pgpro
This commit is contained in:
Tom Lane
2023-03-13 15:19:00 -04:00
parent 096e708056
commit 0ee9d685dd
4 changed files with 72 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/test/regress/expected/json_encoding.out
View File

@@ -56,19 +56,19 @@ select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
ERROR: invalid input syntax for type json
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
--handling of simple unicode escapes
select json '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
correct_in_utf8
@@ -121,7 +121,7 @@ select json '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
@@ -159,7 +159,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT '"\u0000"'::jsonb;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: ...
CONTEXT: JSON data, line 1: "\u0000...
-- use octet_length here so we don't get an odd unicode char in the
-- output
SELECT octet_length('"\uaBcD"'::jsonb::text); -- OK, uppercase and lower case both OK
@@ -180,25 +180,25 @@ ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a';
^
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83dX" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04X" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
correct_in_utf8
@@ -223,7 +223,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
not_an_escape
------------------------------
@@ -253,7 +253,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fai...
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------

24
src/test/regress/expected/json_encoding_1.out
View File

@@ -52,19 +52,19 @@ ERROR: conversion between UTF8 and SQL_ASCII is not supported
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
ERROR: invalid input syntax for type json
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
--handling of simple unicode escapes
select json '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
correct_in_utf8
@@ -113,7 +113,7 @@ select json '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
@@ -151,7 +151,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT '"\u0000"'::jsonb;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: ...
CONTEXT: JSON data, line 1: "\u0000...
-- use octet_length here so we don't get an odd unicode char in the
-- output
SELECT octet_length('"\uaBcD"'::jsonb::text); -- OK, uppercase and lower case both OK
@@ -168,25 +168,25 @@ ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a';
^
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83dX" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04X" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "\ude04...
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
ERROR: conversion between UTF8 and SQL_ASCII is not supported
@@ -209,7 +209,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
not_an_escape
------------------------------
@@ -237,7 +237,7 @@ ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fai...
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------