database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-19 13:42:17 +03:00
Code Activity

Support PG_UNICODE_FAST locale in the builtin collation provider.

Browse Source 
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
This commit is contained in:
Jeff Davis
2025-01-17 15:56:30 -08:00
parent 286a365b9c
commit d3d0983169
13 changed files with 283 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/backend/utils/adt/pg_locale.c
View File

@@ -1590,8 +1590,11 @@ builtin_locale_encoding(const char *locale)
{
if (strcmp(locale, "C") == 0)
return -1;
if (strcmp(locale, "C.UTF-8") == 0)
else if (strcmp(locale, "C.UTF-8") == 0)
return PG_UTF8;
else if (strcmp(locale, "PG_UNICODE_FAST") == 0)
return PG_UTF8;
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
@@ -1616,6 +1619,8 @@ builtin_validate_locale(int encoding, const char *locale)
canonical_name = "C";
else if (strcmp(locale, "C.UTF-8") == 0 || strcmp(locale, "C.UTF8") == 0)
canonical_name = "C.UTF-8";
else if (strcmp(locale, "PG_UNICODE_FAST") == 0)
canonical_name = "PG_UNICODE_FAST";
if (!canonical_name)
ereport(ERROR,

12
src/backend/utils/adt/pg_locale_builtin.c
View File

@@ -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),