e56cad84d5
Although the SQL/JSON tech report makes reference to ECMAScript which allows both single- and double-quoted strings, all the rest of the report speaks only of double-quoted string literals in jsonpaths. That's more compatible with JSON itself; moreover single-quoted strings are hard to use inside a jsonpath that is itself a single-quoted SQL literal. So guess that the intent is to allow only double-quoted literals, and remove lexer support for single-quoted literals. It'll be less painful to add this again later if we're wrong, than to remove a shipped feature. Also, adjust the lexer so that unrecognized backslash sequences are treated as just meaning the escaped character, not as errors. This change has much better support in the standards, as JSON, JavaScript and ECMAScript all make it plain that that's what's supposed to happen. Back-patch to v12. Discussion: https://postgr.es/m/CAPpHfdvDci4iqNF9fhRkTqhe-5_8HmzeLt56drH%2B_Rv2rNRqfg@mail.gmail.com
166 lines
5.6 KiB
Plaintext
166 lines
5.6 KiB
Plaintext
-- encoding-sensitive tests for jsonpath
|
|
-- checks for double-quoted values
|
|
-- basic unicode input
|
|
SELECT '"\u"'::jsonpath; -- ERROR, incomplete escape
|
|
ERROR: invalid unicode sequence at or near "\u" of jsonpath input
|
|
LINE 1: SELECT '"\u"'::jsonpath;
|
|
^
|
|
SELECT '"\u00"'::jsonpath; -- ERROR, incomplete escape
|
|
ERROR: invalid unicode sequence at or near "\u00" of jsonpath input
|
|
LINE 1: SELECT '"\u00"'::jsonpath;
|
|
^
|
|
SELECT '"\u000g"'::jsonpath; -- ERROR, g is not a hex digit
|
|
ERROR: invalid unicode sequence at or near "\u000" of jsonpath input
|
|
LINE 1: SELECT '"\u000g"'::jsonpath;
|
|
^
|
|
SELECT '"\u0000"'::jsonpath; -- OK, legal escape
|
|
ERROR: unsupported Unicode escape sequence
|
|
LINE 1: SELECT '"\u0000"'::jsonpath;
|
|
^
|
|
DETAIL: \u0000 cannot be converted to text.
|
|
SELECT '"\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
|
|
jsonpath
|
|
----------
|
|
"ꯍ"
|
|
(1 row)
|
|
|
|
-- handling of unicode surrogate pairs
|
|
select '"\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
|
|
correct_in_utf8
|
|
-----------------
|
|
"😄🐶"
|
|
(1 row)
|
|
|
|
select '"\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '"\ud83d\ud83d"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode high surrogate must not follow a high surrogate.
|
|
select '"\ude04\ud83d"'::jsonpath; -- surrogates in wrong order
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '"\ude04\ud83d"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
select '"\ud83dX"'::jsonpath; -- orphan high surrogate
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '"\ud83dX"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
select '"\ude04X"'::jsonpath; -- orphan low surrogate
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '"\ude04X"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
--handling of simple unicode escapes
|
|
select '"the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
|
|
correct_in_utf8
|
|
------------------------
|
|
"the Copyright © sign"
|
|
(1 row)
|
|
|
|
select '"dollar \u0024 character"'::jsonpath as correct_everywhere;
|
|
correct_everywhere
|
|
----------------------
|
|
"dollar $ character"
|
|
(1 row)
|
|
|
|
select '"dollar \\u0024 character"'::jsonpath as not_an_escape;
|
|
not_an_escape
|
|
----------------------------
|
|
"dollar \\u0024 character"
|
|
(1 row)
|
|
|
|
select '"null \u0000 escape"'::jsonpath as not_unescaped;
|
|
ERROR: unsupported Unicode escape sequence
|
|
LINE 1: select '"null \u0000 escape"'::jsonpath as not_unescaped;
|
|
^
|
|
DETAIL: \u0000 cannot be converted to text.
|
|
select '"null \\u0000 escape"'::jsonpath as not_an_escape;
|
|
not_an_escape
|
|
-----------------------
|
|
"null \\u0000 escape"
|
|
(1 row)
|
|
|
|
-- checks for quoted key names
|
|
-- basic unicode input
|
|
SELECT '$."\u"'::jsonpath; -- ERROR, incomplete escape
|
|
ERROR: invalid unicode sequence at or near "\u" of jsonpath input
|
|
LINE 1: SELECT '$."\u"'::jsonpath;
|
|
^
|
|
SELECT '$."\u00"'::jsonpath; -- ERROR, incomplete escape
|
|
ERROR: invalid unicode sequence at or near "\u00" of jsonpath input
|
|
LINE 1: SELECT '$."\u00"'::jsonpath;
|
|
^
|
|
SELECT '$."\u000g"'::jsonpath; -- ERROR, g is not a hex digit
|
|
ERROR: invalid unicode sequence at or near "\u000" of jsonpath input
|
|
LINE 1: SELECT '$."\u000g"'::jsonpath;
|
|
^
|
|
SELECT '$."\u0000"'::jsonpath; -- OK, legal escape
|
|
ERROR: unsupported Unicode escape sequence
|
|
LINE 1: SELECT '$."\u0000"'::jsonpath;
|
|
^
|
|
DETAIL: \u0000 cannot be converted to text.
|
|
SELECT '$."\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
|
|
jsonpath
|
|
----------
|
|
$."ꯍ"
|
|
(1 row)
|
|
|
|
-- handling of unicode surrogate pairs
|
|
select '$."\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
|
|
correct_in_utf8
|
|
-----------------
|
|
$."😄🐶"
|
|
(1 row)
|
|
|
|
select '$."\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '$."\ud83d\ud83d"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode high surrogate must not follow a high surrogate.
|
|
select '$."\ude04\ud83d"'::jsonpath; -- surrogates in wrong order
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '$."\ude04\ud83d"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
select '$."\ud83dX"'::jsonpath; -- orphan high surrogate
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '$."\ud83dX"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
select '$."\ude04X"'::jsonpath; -- orphan low surrogate
|
|
ERROR: invalid input syntax for type jsonpath
|
|
LINE 1: select '$."\ude04X"'::jsonpath;
|
|
^
|
|
DETAIL: Unicode low surrogate must follow a high surrogate.
|
|
--handling of simple unicode escapes
|
|
select '$."the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
|
|
correct_in_utf8
|
|
--------------------------
|
|
$."the Copyright © sign"
|
|
(1 row)
|
|
|
|
select '$."dollar \u0024 character"'::jsonpath as correct_everywhere;
|
|
correct_everywhere
|
|
------------------------
|
|
$."dollar $ character"
|
|
(1 row)
|
|
|
|
select '$."dollar \\u0024 character"'::jsonpath as not_an_escape;
|
|
not_an_escape
|
|
------------------------------
|
|
$."dollar \\u0024 character"
|
|
(1 row)
|
|
|
|
select '$."null \u0000 escape"'::jsonpath as not_unescaped;
|
|
ERROR: unsupported Unicode escape sequence
|
|
LINE 1: select '$."null \u0000 escape"'::jsonpath as not_unescaped;
|
|
^
|
|
DETAIL: \u0000 cannot be converted to text.
|
|
select '$."null \\u0000 escape"'::jsonpath as not_an_escape;
|
|
not_an_escape
|
|
-------------------------
|
|
$."null \\u0000 escape"
|
|
(1 row)
|
|
|