mirror of
https://github.com/zebrajr/postgres.git
synced 2025-12-07 12:20:31 +01:00
a6525588b7
SQL includes provisions for numeric Unicode escapes in string literals and identifiers. Previously we only accepted those if they represented ASCII characters or the server encoding was UTF-8, making the conversion to internal form trivial. This patch adjusts things so that we'll call the appropriate encoding conversion function in less-trivial cases, allowing the escape sequence to be accepted so long as it corresponds to some character available in the server encoding. This also applies to processing of Unicode escapes in JSONB. However, the old restriction still applies to client-side JSON processing, since that hasn't got access to the server's encoding conversion infrastructure. This patch includes some lexer infrastructure that simplifies throwing errors with error cursors pointing into the middle of a string (or other complex token). For the moment I only used it for errors relating to Unicode escapes, but we might later expand the usage to some other cases. Patch by me, reviewed by John Naylor. Discussion: https://postgr.es/m/2393.1578958316@sss.pgh.pa.us
60 lines
2.4 KiB
SQL
60 lines
2.4 KiB
SQL
--
|
|
-- encoding-sensitive tests for jsonpath
|
|
--
|
|
|
|
-- We provide expected-results files for UTF8 (jsonpath_encoding.out)
|
|
-- and for SQL_ASCII (jsonpath_encoding_1.out). Skip otherwise.
|
|
SELECT getdatabaseencoding() NOT IN ('UTF8', 'SQL_ASCII')
|
|
AS skip_test \gset
|
|
\if :skip_test
|
|
\quit
|
|
\endif
|
|
|
|
SELECT getdatabaseencoding(); -- just to label the results files
|
|
|
|
-- checks for double-quoted values
|
|
|
|
-- basic unicode input
|
|
SELECT '"\u"'::jsonpath; -- ERROR, incomplete escape
|
|
SELECT '"\u00"'::jsonpath; -- ERROR, incomplete escape
|
|
SELECT '"\u000g"'::jsonpath; -- ERROR, g is not a hex digit
|
|
SELECT '"\u0000"'::jsonpath; -- OK, legal escape
|
|
SELECT '"\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
|
|
|
|
-- handling of unicode surrogate pairs
|
|
select '"\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
|
|
select '"\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
|
|
select '"\ude04\ud83d"'::jsonpath; -- surrogates in wrong order
|
|
select '"\ud83dX"'::jsonpath; -- orphan high surrogate
|
|
select '"\ude04X"'::jsonpath; -- orphan low surrogate
|
|
|
|
--handling of simple unicode escapes
|
|
select '"the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
|
|
select '"dollar \u0024 character"'::jsonpath as correct_everywhere;
|
|
select '"dollar \\u0024 character"'::jsonpath as not_an_escape;
|
|
select '"null \u0000 escape"'::jsonpath as not_unescaped;
|
|
select '"null \\u0000 escape"'::jsonpath as not_an_escape;
|
|
|
|
-- checks for quoted key names
|
|
|
|
-- basic unicode input
|
|
SELECT '$."\u"'::jsonpath; -- ERROR, incomplete escape
|
|
SELECT '$."\u00"'::jsonpath; -- ERROR, incomplete escape
|
|
SELECT '$."\u000g"'::jsonpath; -- ERROR, g is not a hex digit
|
|
SELECT '$."\u0000"'::jsonpath; -- OK, legal escape
|
|
SELECT '$."\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
|
|
|
|
-- handling of unicode surrogate pairs
|
|
select '$."\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
|
|
select '$."\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
|
|
select '$."\ude04\ud83d"'::jsonpath; -- surrogates in wrong order
|
|
select '$."\ud83dX"'::jsonpath; -- orphan high surrogate
|
|
select '$."\ude04X"'::jsonpath; -- orphan low surrogate
|
|
|
|
--handling of simple unicode escapes
|
|
select '$."the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
|
|
select '$."dollar \u0024 character"'::jsonpath as correct_everywhere;
|
|
select '$."dollar \\u0024 character"'::jsonpath as not_an_escape;
|
|
select '$."null \u0000 escape"'::jsonpath as not_unescaped;
|
|
select '$."null \\u0000 escape"'::jsonpath as not_an_escape;
|