diff options
author | Tom Lane <tgl@sss.pgh.pa.us> | 2023-03-13 15:19:00 -0400 |
---|---|---|
committer | Tom Lane <tgl@sss.pgh.pa.us> | 2023-03-13 15:19:00 -0400 |
commit | 25a7812cd0867043ec0a045c41e6bd3981d69bc4 (patch) | |
tree | b6072ba81457f86b3aa890baab117ed7f49454db /src/test | |
parent | 30dbdbe75384bcb034172c781b24bc982434a967 (diff) | |
download | postgresql-25a7812cd0867043ec0a045c41e6bd3981d69bc4.tar.gz postgresql-25a7812cd0867043ec0a045c41e6bd3981d69bc4.zip |
Fix JSON error reporting for many cases of erroneous string values.
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
Diffstat (limited to 'src/test')
-rw-r--r-- | src/test/regress/expected/json_encoding.out | 24 | ||||
-rw-r--r-- | src/test/regress/expected/json_encoding_1.out | 36 |
2 files changed, 30 insertions, 30 deletions
diff --git a/src/test/regress/expected/json_encoding.out b/src/test/regress/expected/json_encoding.out index f18ba9ebb2c..fe729db8c9d 100644 --- a/src/test/regress/expected/json_encoding.out +++ b/src/test/regress/expected/json_encoding.out @@ -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 -------------------- diff --git a/src/test/regress/expected/json_encoding_1.out b/src/test/regress/expected/json_encoding_1.out index 77bdaf63a1d..5c8d91ad0b6 100644 --- a/src/test/regress/expected/json_encoding_1.out +++ b/src/test/regress/expected/json_encoding_1.out @@ -50,23 +50,23 @@ SELECT '"\uaBcD"'::json; -- OK, uppercase and lower case both OK select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8; ERROR: unsupported Unicode escape sequence DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: { "a":... +CONTEXT: JSON data, line 1: { "a": "\ud83d\ude04... 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 @@ -101,7 +101,7 @@ select json '{ "a": "null \\u0000 escape" }' as not_an_escape; select json '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8; ERROR: unsupported Unicode escape sequence DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: { "a":... +CONTEXT: JSON data, line 1: { "a": "the Copyright \u00a9... select json '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere; correct_everywhere -------------------- @@ -117,7 +117,7 @@ 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 -------------------- @@ -155,7 +155,7 @@ 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 @@ -163,45 +163,45 @@ ERROR: unsupported Unicode escape sequence LINE 1: SELECT octet_length('"\uaBcD"'::jsonb::text); ^ DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: ... +CONTEXT: JSON data, line 1: "\uaBcD... -- handling of unicode surrogate pairs SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8; ERROR: unsupported Unicode escape sequence LINE 1: SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc3... ^ DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: { "a":... +CONTEXT: JSON data, line 1: { "a": "\ud83d\ude04... SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row 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: unsupported Unicode escape sequence LINE 1: SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as corr... ^ DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: { "a":... +CONTEXT: JSON data, line 1: { "a": "the Copyright \u00a9... SELECT jsonb '{ "a": "dollar \u0024 character" }' as correct_everywhere; correct_everywhere ----------------------------- @@ -219,7 +219,7 @@ 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 ------------------------------ @@ -231,7 +231,7 @@ ERROR: unsupported Unicode escape sequence LINE 1: SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a'... ^ DETAIL: Unicode escape value could not be translated to the server's encoding SQL_ASCII. -CONTEXT: JSON data, line 1: { "a":... +CONTEXT: JSON data, line 1: { "a": "the Copyright \u00a9... SELECT jsonb '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere; correct_everywhere -------------------- @@ -249,7 +249,7 @@ 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 -------------------- |