diff options
| author | Jeff Davis <jdavis@postgresql.org> | 2025-01-17 15:56:30 -0800 |
|---|---|---|
| committer | Jeff Davis <jdavis@postgresql.org> | 2025-01-17 15:56:30 -0800 |
| commit | d3d0983169130a9b81e3fe48d5c2ca4931480956 (patch) | |
| tree | 75e680ff03b4af3fd21a36be49515367133e6d02 /src/backend/utils/adt/pg_locale_builtin.c | |
| parent | 286a365b9c25479f8ad82043ed136748733adfa6 (diff) | |
| download | postgresql-d3d0983169130a9b81e3fe48d5c2ca4931480956.tar.gz postgresql-d3d0983169130a9b81e3fe48d5c2ca4931480956.zip | |
Support PG_UNICODE_FAST locale in the builtin collation provider.
The PG_UNICODE_FAST locale uses code point sort order (fast,
memcmp-based) combined with Unicode character semantics. The character
semantics are based on Unicode full case mapping.
Full case mapping can map a single codepoint to multiple codepoints,
such as "ß" uppercasing to "SS". Additionally, it handles
context-sensitive mappings like the "final sigma", and it uses
titlecase mappings such as "Dž" when titlecasing (rather than plain
uppercase mappings).
Importantly, the uppercasing of "ß" as "SS" is specifically mentioned
by the SQL standard. In Postgres, UCS_BASIC uses plain ASCII semantics
for case mapping and pattern matching, so if we changed it to use the
PG_UNICODE_FAST locale, it would offer better compliance with the
standard. For now, though, do not change the behavior of UCS_BASIC.
Discussion: https://postgr.es/m/ddfd67928818f138f51635712529bc5e1d25e4e7.camel@j-davis.com
Discussion: https://postgr.es/m/27bb0e52-801d-4f73-a0a4-02cfdd4a9ada@eisentraut.org
Reviewed-by: Peter Eisentraut, Daniel Verite
Diffstat (limited to 'src/backend/utils/adt/pg_locale_builtin.c')
| -rw-r--r-- | src/backend/utils/adt/pg_locale_builtin.c | 12 |
1 files changed, 9 insertions, 3 deletions
diff --git a/src/backend/utils/adt/pg_locale_builtin.c b/src/backend/utils/adt/pg_locale_builtin.c index fef5b6e6d38..436e32c0ca0 100644 --- a/src/backend/utils/adt/pg_locale_builtin.c +++ b/src/backend/utils/adt/pg_locale_builtin.c @@ -78,7 +78,8 @@ size_t strlower_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { - return unicode_strlower(dest, destsize, src, srclen, false); + return unicode_strlower(dest, destsize, src, srclen, + locale->info.builtin.casemap_full); } size_t @@ -93,7 +94,8 @@ strtitle_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, .prev_alnum = false, }; - return unicode_strtitle(dest, destsize, src, srclen, false, + return unicode_strtitle(dest, destsize, src, srclen, + locale->info.builtin.casemap_full, initcap_wbnext, &wbstate); } @@ -101,7 +103,8 @@ size_t strupper_builtin(char *dest, size_t destsize, const char *src, ssize_t srclen, pg_locale_t locale) { - return unicode_strupper(dest, destsize, src, srclen, false); + return unicode_strupper(dest, destsize, src, srclen, + locale->info.builtin.casemap_full); } pg_locale_t @@ -142,6 +145,7 @@ create_pg_locale_builtin(Oid collid, MemoryContext context) result = MemoryContextAllocZero(context, sizeof(struct pg_locale_struct)); result->info.builtin.locale = MemoryContextStrdup(context, locstr); + result->info.builtin.casemap_full = (strcmp(locstr, "PG_UNICODE_FAST") == 0); result->provider = COLLPROVIDER_BUILTIN; result->deterministic = true; result->collate_is_c = true; @@ -164,6 +168,8 @@ get_collation_actual_version_builtin(const char *collcollate) return "1"; else if (strcmp(collcollate, "C.UTF-8") == 0) return "1"; + else if (strcmp(collcollate, "PG_UNICODE_FAST") == 0) + return "1"; else ereport(ERROR, (errcode(ERRCODE_WRONG_OBJECT_TYPE), |