Fix some minor spec-compliance issues in jsonpath lexer.

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

1 files changed, 0 insertions, 78 deletions

diff --git a/src/test/regress/expected/jsonpath_encoding.out b/src/test/regress/expected/jsonpath_encoding.out
index 8db6e47dbbc..ecffe095b59 100644
--- a/src/test/regress/expected/jsonpath_encoding.out
+++ b/src/test/regress/expected/jsonpath_encoding.out
@@ -81,84 +81,6 @@ select '"null \\u0000 escape"'::jsonpath as not_an_escape;
  "null \\u0000 escape"
 (1 row)
 
--- checks for single-quoted values
--- basic unicode input
-SELECT E'\'\u\''::jsonpath;		-- ERROR, incomplete escape
-ERROR:  invalid Unicode escape
-LINE 1: SELECT E'\'\u\''::jsonpath;
-               ^
-HINT:  Unicode escapes must be \uXXXX or \UXXXXXXXX.
-SELECT E'\'\u00\''::jsonpath;	-- ERROR, incomplete escape
-ERROR:  invalid Unicode escape
-LINE 1: SELECT E'\'\u00\''::jsonpath;
-               ^
-HINT:  Unicode escapes must be \uXXXX or \UXXXXXXXX.
-SELECT E'\'\u000g\''::jsonpath;	-- ERROR, g is not a hex digit
-ERROR:  invalid Unicode escape
-LINE 1: SELECT E'\'\u000g\''::jsonpath;
-               ^
-HINT:  Unicode escapes must be \uXXXX or \UXXXXXXXX.
-SELECT E'\'\u0000\''::jsonpath;	-- OK, legal escape
-ERROR:  invalid Unicode escape value at or near "E'\'\u0000"
-LINE 1: SELECT E'\'\u0000\''::jsonpath;
-               ^
-SELECT E'\'\uaBcD\''::jsonpath;	-- OK, uppercase and lower case both OK
- jsonpath 
-----------
- "ꯍ"
-(1 row)
-
--- handling of unicode surrogate pairs
-select E'\'\ud83d\ude04\ud83d\udc36\''::jsonpath as correct_in_utf8;
- correct_in_utf8 
------------------
- "😄🐶"
-(1 row)
-
-select E'\'\ud83d\ud83d\''::jsonpath; -- 2 high surrogates in a row
-ERROR:  invalid Unicode surrogate pair at or near "E'\'\ud83d\ud83d"
-LINE 1: select E'\'\ud83d\ud83d\''::jsonpath;
-               ^
-select E'\'\ude04\ud83d\''::jsonpath; -- surrogates in wrong order
-ERROR:  invalid Unicode surrogate pair at or near "E'\'\ude04"
-LINE 1: select E'\'\ude04\ud83d\''::jsonpath;
-               ^
-select E'\'\ud83dX\''::jsonpath; -- orphan high surrogate
-ERROR:  invalid Unicode surrogate pair at or near "E'\'\ud83dX"
-LINE 1: select E'\'\ud83dX\''::jsonpath;
-               ^
-select E'\'\ude04X\''::jsonpath; -- orphan low surrogate
-ERROR:  invalid Unicode surrogate pair at or near "E'\'\ude04"
-LINE 1: select E'\'\ude04X\''::jsonpath;
-               ^
---handling of simple unicode escapes
-select E'\'the Copyright \u00a9 sign\''::jsonpath as correct_in_utf8;
-    correct_in_utf8     
-------------------------
- "the Copyright © sign"
-(1 row)
-
-select E'\'dollar \u0024 character\''::jsonpath as correct_everywhere;
-  correct_everywhere  
-----------------------
- "dollar $ character"
-(1 row)
-
-select E'\'dollar \\u0024 character\''::jsonpath as not_an_escape;
-    not_an_escape     
-----------------------
- "dollar $ character"
-(1 row)
-
-select E'\'null \u0000 escape\''::jsonpath as not_unescaped;
-ERROR:  invalid Unicode escape value at or near "E'\'null \u0000"
-LINE 1: select E'\'null \u0000 escape\''::jsonpath as not_unescaped;
-               ^
-select E'\'null \\u0000 escape\''::jsonpath as not_an_escape;
-ERROR:  unsupported Unicode escape sequence
-LINE 1: select E'\'null \\u0000 escape\''::jsonpath as not_an_escape...
-               ^
-DETAIL:  \u0000 cannot be converted to text.
 -- checks for quoted key names
 -- basic unicode input
 SELECT '$."\u"'::jsonpath;		-- ERROR, incomplete escape