database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Remove ts_locale.c's lowerstr()

Browse Source 
lowerstr() and lowerstr_with_len() in ts_locale.c do the same thing as
str_tolower() that the rest of the system uses, except that the former
don't use the common locale provider framework but instead use the
global libc locale settings.

This patch replaces uses of lowerstr*() with str_tolower(...,
DEFAULT_COLLATION_OID).  For instances that use a libc locale
globally, this will result in exactly the same behavior.  For
instances that use other locale providers, you now get consistent
behavior and are no longer dependent on the libc locale settings (for
this case; there are others).

Most uses of these functions are for processing dictionary and
configuration files.  In those cases, using the default collation
seems appropriate.  At least we don't have a more specific collation
available.  But the code in contrib/pg_trgm should really depend on
the collation of the columns being processed.  This is not done here,
this can be done in a separate patch.

(You can probably construct some edge cases where this change would
create some locale-related upgrade incompatibility, for example if
before you used a combination of ICU and a differently-behaving libc
locale.  We can document this in the release notes, but I don't think
there is anything more we can do about this.)

Reviewed-by: Jeff Davis <pgsql@j-davis.com>
Discussion: https://www.postgresql.org/message-id/flat/653f3b84-fc87-45a7-9a0c-bfb4fcab3e7d%40eisentraut.org
This commit is contained in:
Peter Eisentraut
2024-12-17 14:04:55 +01:00
parent d3aad4ac57
commit fb1a18810f
12 changed files with 43 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
contrib/dict_xsyn/dict_xsyn.c
View File

@ -14,9 +14,11 @@
#include <ctype.h>
#include "catalog/pg_collation_d.h"
#include "commands/defrem.h"
#include "tsearch/ts_locale.h"
#include "tsearch/ts_public.h"
#include "utils/formatting.h"
PG_MODULE_MAGIC;
@ -93,7 +95,7 @@ read_dictionary(DictSyn *d, const char *filename)
if (*line == '\0')
continue;
value = lowerstr(line);
value = str_tolower(line, strlen(line), DEFAULT_COLLATION_OID);
pfree(line);
pos = value;
@ -210,7 +212,7 @@ dxsyn_lexize(PG_FUNCTION_ARGS)
{
char *temp = pnstrdup(in, length);
word.key = lowerstr(temp);
word.key = str_tolower(temp, length, DEFAULT_COLLATION_OID);
pfree(temp);
word.value = NULL;
}

6
contrib/pg_trgm/trgm_op.c
View File

@ -5,12 +5,14 @@
#include <ctype.h>
#include "catalog/pg_collation_d.h"
#include "catalog/pg_type.h"
#include "common/int.h"
#include "lib/qunique.h"
#include "miscadmin.h"
#include "trgm.h"
#include "tsearch/ts_locale.h"
#include "utils/formatting.h"
#include "utils/guc.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
@ -303,7 +305,7 @@ generate_trgm_only(trgm *trg, char *str, int slen, TrgmBound *bounds)
while ((bword = find_word(eword, slen - (eword - str), &eword, &charlen)) != NULL)
{
#ifdef IGNORECASE
bword = lowerstr_with_len(bword, eword - bword);
bword = str_tolower(bword, eword - bword, DEFAULT_COLLATION_OID);
bytelen = strlen(bword);
#else
bytelen = eword - bword;
@ -899,7 +901,7 @@ generate_wildcard_trgm(const char *str, int slen)
buf, &bytelen, &charlen)) != NULL)
{
#ifdef IGNORECASE
buf2 = lowerstr_with_len(buf, bytelen);
buf2 = str_tolower(buf, bytelen, DEFAULT_COLLATION_OID);
bytelen = strlen(buf2);
#else
buf2 = buf;

16
contrib/pg_trgm/trgm_regexp.c
View File

@ -191,9 +191,11 @@
*/
#include "postgres.h"
#include "catalog/pg_collation_d.h"
#include "regex/regexport.h"
#include "trgm.h"
#include "tsearch/ts_locale.h"
#include "utils/formatting.h"
#include "utils/hsearch.h"
#include "utils/memutils.h"
#include "varatt.h"
@ -847,16 +849,16 @@ convertPgWchar(pg_wchar c, trgm_mb_char *result)
* within each color, since we used the REG_ICASE option; so there's no
* need to process the uppercase version.
*
* XXX this code is dependent on the assumption that lowerstr() works the
* same as the regex engine's internal case folding machinery. Might be
* wiser to expose pg_wc_tolower and test whether c == pg_wc_tolower(c).
* On the other hand, the trigrams in the index were created using
* lowerstr(), so we're probably screwed if there's any incompatibility
* anyway.
* XXX this code is dependent on the assumption that str_tolower() works
* the same as the regex engine's internal case folding machinery. Might
* be wiser to expose pg_wc_tolower and test whether c ==
* pg_wc_tolower(c). On the other hand, the trigrams in the index were
* created using str_tolower(), so we're probably screwed if there's any
* incompatibility anyway.
*/
#ifdef IGNORECASE
{
char *lowerCased = lowerstr(s);
char *lowerCased = str_tolower(s, strlen(s), DEFAULT_COLLATION_OID);
if (strcmp(lowerCased, s) != 0)
{