From e56cad84d542a8cc2056390a9c651118cfa6c89c Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Fri, 20 Sep 2019 14:22:58 -0400 Subject: 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 --- src/test/regress/sql/jsonpath_encoding.sql | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'src/test/regress/sql/jsonpath_encoding.sql') diff --git a/src/test/regress/sql/jsonpath_encoding.sql b/src/test/regress/sql/jsonpath_encoding.sql index a3b5bc39a1c..3a23b728182 100644 --- a/src/test/regress/sql/jsonpath_encoding.sql +++ b/src/test/regress/sql/jsonpath_encoding.sql @@ -24,29 +24,6 @@ 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 single-quoted values - --- basic unicode input -SELECT E'\'\u\''::jsonpath; -- ERROR, incomplete escape -SELECT E'\'\u00\''::jsonpath; -- ERROR, incomplete escape -SELECT E'\'\u000g\''::jsonpath; -- ERROR, g is not a hex digit -SELECT E'\'\u0000\''::jsonpath; -- OK, legal escape -SELECT E'\'\uaBcD\''::jsonpath; -- OK, uppercase and lower case both OK - --- handling of unicode surrogate pairs -select E'\'\ud83d\ude04\ud83d\udc36\''::jsonpath as correct_in_utf8; -select E'\'\ud83d\ud83d\''::jsonpath; -- 2 high surrogates in a row -select E'\'\ude04\ud83d\''::jsonpath; -- surrogates in wrong order -select E'\'\ud83dX\''::jsonpath; -- orphan high surrogate -select E'\'\ude04X\''::jsonpath; -- orphan low surrogate - ---handling of simple unicode escapes -select E'\'the Copyright \u00a9 sign\''::jsonpath as correct_in_utf8; -select E'\'dollar \u0024 character\''::jsonpath as correct_everywhere; -select E'\'dollar \\u0024 character\''::jsonpath as not_an_escape; -select E'\'null \u0000 escape\''::jsonpath as not_unescaped; -select E'\'null \\u0000 escape\''::jsonpath as not_an_escape; - -- checks for quoted key names -- basic unicode input -- cgit v1.2.3