database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2026-10-23 13:29:09 +03:00
Code Activity

Fix pg_strupper/lower/title/fold() functions to work with C locale

Browse Source 
Starting with commit 011384ba45, calling to_date() or to_timestamp()
with "TMMonth" or other TM-prefixed format keyword, with the C locale,
would crash.

In REL_19_STABLE and above, pg_strupper(), pg_strlower(),
pg_strtitle(), and pg_strfold() functions have a special case for the
C locale, but that was missing in REL_18_STABLE.  On REL_18_STABLE,
the functions call the libc function even in C locale, even though the
native locale object is NULL.  On Linux, the underlying libc functions
will crash when called with NULL locale.  (On macOS, they reportedly
do not, but even then it's not clear if they will do what you'd
expect.)

This went unnoticed because until commit 011384ba45, we never called
these functions in C locale, all the callers had a special codepath
for C locale.  We could add a special path in the new callers too, but
it's an accident waiting to happen, so let's backport the C
locale-specific handling from REL_19_STABLE to REL_18_STABLE.  Older
versions did not have these functions at all, hence no problem.

This applies to REL_18_STABLE only.

Reported-by: Masashi Kamura <kamura.masashi@fujitsu.com>
Reviewed-by: Álvaro Herrera <alvherre@kurilemu.de>
Discussion: https://www.postgresql.org/message-id/OS9PR01MB1317436E07D06281AD1A0452F94DD2%40OS9PR01MB13174.jpnprd01.prod.outlook.com
This commit is contained in:
Heikki Linnakangas
2026-08-11 21:18:45 +03:00
parent 17fae4fbdd
commit 5f003855e7
1 changed files with 64 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
src/backend/utils/adt/pg_locale.c
View File

@@ -1273,11 +1273,64 @@ get_collation_actual_version(char collprovider, const char *collcollate)
return collversion;
}
/* lowercasing/casefolding in C locale */
static size_t
strlower_c(char *dst, size_t dstsize, const char *src, size_t srclen)
{
int i;
for (i = 0; i < srclen && i < dstsize; i++)
dst[i] = pg_ascii_tolower(src[i]);
if (i < dstsize)
dst[i] = '\0';
return srclen;
}
/* titlecasing in C locale */
static size_t
strtitle_c(char *dst, size_t dstsize, const char *src, size_t srclen)
{
bool wasalnum = false;
int i;
for (i = 0; i < srclen && i < dstsize; i++)
{
char c = src[i];
if (wasalnum)
dst[i] = pg_ascii_tolower(c);
else
dst[i] = pg_ascii_toupper(c);
wasalnum = ((c >= '0' && c <= '9') ||
(c >= 'A' && c <= 'Z') ||
(c >= 'a' && c <= 'z'));
}
if (i < dstsize)
dst[i] = '\0';
return srclen;
}
/* uppercasing in C locale */
static size_t
strupper_c(char *dst, size_t dstsize, const char *src, size_t srclen)
{
int i;
for (i = 0; i < srclen && i < dstsize; i++)
dst[i] = pg_ascii_toupper(src[i]);
if (i < dstsize)
dst[i] = '\0';
return srclen;
}
size_t
pg_strlower(char *dst, size_t dstsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
if (locale->provider == COLLPROVIDER_BUILTIN)
if (locale->ctype_is_c)
return strlower_c(dst, dstsize, src, srclen);
else if (locale->provider == COLLPROVIDER_BUILTIN)
return strlower_builtin(dst, dstsize, src, srclen, locale);
#ifdef USE_ICU
else if (locale->provider == COLLPROVIDER_ICU)
@@ -1296,7 +1349,9 @@ size_t
pg_strtitle(char *dst, size_t dstsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
if (locale->provider == COLLPROVIDER_BUILTIN)
if (locale->ctype_is_c)
return strtitle_c(dst, dstsize, src, srclen);
else if (locale->provider == COLLPROVIDER_BUILTIN)
return strtitle_builtin(dst, dstsize, src, srclen, locale);
#ifdef USE_ICU
else if (locale->provider == COLLPROVIDER_ICU)
@@ -1315,7 +1370,9 @@ size_t
pg_strupper(char *dst, size_t dstsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
if (locale->provider == COLLPROVIDER_BUILTIN)
if (locale->ctype_is_c)
return strupper_c(dst, dstsize, src, srclen);
else if (locale->provider == COLLPROVIDER_BUILTIN)
return strupper_builtin(dst, dstsize, src, srclen, locale);
#ifdef USE_ICU
else if (locale->provider == COLLPROVIDER_ICU)
@@ -1334,7 +1391,10 @@ size_t
pg_strfold(char *dst, size_t dstsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
if (locale->provider == COLLPROVIDER_BUILTIN)
/* in the C locale, casefolding is the same as lowercasing */
if (locale->ctype_is_c)
return strlower_c(dst, dstsize, src, srclen);
else if (locale->provider == COLLPROVIDER_BUILTIN)
return strfold_builtin(dst, dstsize, src, srclen, locale);
#ifdef USE_ICU
else if (locale->provider == COLLPROVIDER_ICU)