c8h4/postgresql
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

Fix t_isspace(), etc., when datlocprovider=i and datctype=C.

Browse source 
Check whether the datctype is C to determine whether t_isspace() and
related functions use isspace() or iswspace().

Previously, t_isspace() checked whether the database default collation
was C; which is incorrect when the default collation uses the ICU
provider.

Discussion: https://postgr.es/m/79e4354d9eccfdb00483146a6b9f6295202e7890.camel@j-davis.com
Reviewed-by: Peter Eisentraut
Backpatch-through: 15
This commit is contained in:
Jeff Davis 2023-03-17 11:47:35 -07:00
parent 064709f803
commit f413941f41
8 changed files with 16 additions and 42 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
contrib/unaccent/expected/unaccent.out
View file

@ -1,12 +1,3 @@
-- unaccent is broken if the default collation is provided by ICU and
-- LC_CTYPE=C
SELECT current_setting('lc_ctype') = 'C' AND
(SELECT datlocprovider='i' FROM pg_database
WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit
\endif
CREATE EXTENSION unaccent;
-- must have a UTF8 database
SELECT getdatabaseencoding();

8
contrib/unaccent/expected/unaccent_1.out
View file

@ -1,8 +0,0 @@
-- unaccent is broken if the default collation is provided by ICU and
-- LC_CTYPE=C
SELECT current_setting('lc_ctype') = 'C' AND
(SELECT datlocprovider='i' FROM pg_database
WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit

11
contrib/unaccent/sql/unaccent.sql
View file

@ -1,14 +1,3 @@
-- unaccent is broken if the default collation is provided by ICU and
-- LC_CTYPE=C
SELECT current_setting('lc_ctype') = 'C' AND
(SELECT datlocprovider='i' FROM pg_database
WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit
\endif
CREATE EXTENSION unaccent;
-- must have a UTF8 database

18
src/backend/tsearch/ts_locale.c
View file

@ -38,10 +38,9 @@ t_isdigit(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[WC_BUF_LEN];
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
if (clen == 1 || database_ctype_is_c)
return isdigit(TOUCHAR(ptr));
char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
@ -54,10 +53,9 @@ t_isspace(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[WC_BUF_LEN];
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
if (clen == 1 || database_ctype_is_c)
return isspace(TOUCHAR(ptr));
char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
@ -70,10 +68,9 @@ t_isalpha(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[WC_BUF_LEN];
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
if (clen == 1 || database_ctype_is_c)
return isalpha(TOUCHAR(ptr));
char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
@ -86,10 +83,9 @@ t_isalnum(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[WC_BUF_LEN];
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
if (clen == 1 || database_ctype_is_c)
return isalnum(TOUCHAR(ptr));
char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
@ -102,10 +98,9 @@ t_isprint(const char *ptr)
{
int clen = pg_mblen(ptr);
wchar_t character[WC_BUF_LEN];
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (clen == 1 || lc_ctype_is_c(collation))
if (clen == 1 || database_ctype_is_c)
return isprint(TOUCHAR(ptr));
char2wchar(character, WC_BUF_LEN, ptr, clen, mylocale);
@ -273,7 +268,6 @@ char *
lowerstr_with_len(const char *str, int len)
{
char *out;
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
if (len == 0)
@ -285,7 +279,7 @@ lowerstr_with_len(const char *str, int len)
* Also, for a C locale there is no need to process as multibyte. From
* backend/utils/adt/oracle_compat.c Teodor
*/
if (pg_database_encoding_max_length() > 1 && !lc_ctype_is_c(collation))
if (pg_database_encoding_max_length() > 1 && !database_ctype_is_c)
{
wchar_t *wstr,
*wptr;

3
src/backend/tsearch/wparser_def.c
View file

@ -297,11 +297,10 @@ TParserInit(char *str, int len)
*/
if (prs->charmaxlen > 1)
{
Oid collation = DEFAULT_COLLATION_OID; /* TODO */
pg_locale_t mylocale = 0; /* TODO */
prs->usewide = true;
if (lc_ctype_is_c(collation))
if (database_ctype_is_c)
{
/*
* char2wchar doesn't work for C-locale and sizeof(pg_wchar) could

3
src/backend/utils/adt/pg_locale.c
View file

@ -107,6 +107,9 @@ char *localized_full_days[7 + 1];
char *localized_abbrev_months[12 + 1];
char *localized_full_months[12 + 1];
/* is the databases's LC_CTYPE the C locale? */
bool database_ctype_is_c = false;
/* indicates whether locale information cache is valid */
static bool CurrentLocaleConvValid = false;
static bool CurrentLCTimeValid = false;

4
src/backend/utils/init/postinit.c
View file

@ -419,6 +419,10 @@ CheckMyDatabase(const char *name, bool am_superuser, bool override_allow_connect
" which is not recognized by setlocale().", ctype),
errhint("Recreate the database with another locale or install the missing locale.")));
if (strcmp(ctype, "C") == 0 ||
strcmp(ctype, "POSIX") == 0)
database_ctype_is_c = true;
if (dbform->datlocprovider == COLLPROVIDER_ICU)
{
char *icurules;

2
src/include/utils/pg_locale.h
View file

@ -47,6 +47,8 @@ extern PGDLLIMPORT char *localized_full_days[];
extern PGDLLIMPORT char *localized_abbrev_months[];
extern PGDLLIMPORT char *localized_full_months[];
/* is the databases's LC_CTYPE the C locale? */
extern PGDLLIMPORT bool database_ctype_is_c;
extern bool check_locale(int category, const char *locale, char **canonname);
extern char *pg_perm_setlocale(int category, const char *locale);