All supported systems have locale_t.

locale_t is defined by POSIX.1-2008 and SUSv4, and available on all
targeted systems.  For Windows, win32_port.h redirects to a partial
implementation called _locale_t.  We can now remove a lot of
compile-time tests for HAVE_LOCALE_T, and associated comments and dead
code branches that were needed for older computers.

Since configure + MinGW builds didn't detect locale_t but now we assume
that all systems have it, further inconsistencies among the 3 Windows build
systems were revealed.  With this commit, we no longer define
HAVE_WCSTOMBS_L and HAVE_MBSTOWCS_L on any Windows build system, but
we have logic to deal with that so that replacements are available where
appropriate.

Reviewed-by: Noah Misch <noah@leadboat.com>
Reviewed-by: Tristan Partin <tristan@neon.tech>
Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Discussion: https://postgr.es/m/CA%2BhUKGLg7_T2GKwZFAkEf0V7vbnur-NfCjZPKZb%3DZfAXSV1ORw%40mail.gmail.com

Author: macdice

config/c-library.m4

@@ -86,9 +86,9 @@ AC_DEFUN([PGAC_STRUCT_SOCKADDR_SA_LEN],
 # PGAC_TYPE_LOCALE_T
 # ------------------
 # Check for the locale_t type and find the right header file.  macOS
-# needs xlocale.h; standard is locale.h, but glibc also has an
-# xlocale.h file that we should not use.
-#
+# needs xlocale.h; standard is locale.h, but glibc <= 2.25 also had an
+# xlocale.h file that we should not use, so we check the standard
+# header first.
 AC_DEFUN([PGAC_TYPE_LOCALE_T],
 [AC_CACHE_CHECK([for locale_t], pgac_cv_type_locale_t,
 [AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
@@ -102,10 +102,6 @@ locale_t x;],
 [])],
 [pgac_cv_type_locale_t='yes (in xlocale.h)'],
 [pgac_cv_type_locale_t=no])])])
-if test "$pgac_cv_type_locale_t" != no; then
-  AC_DEFINE(HAVE_LOCALE_T, 1,
-            [Define to 1 if the system has the type `locale_t'.])
-fi
 if test "$pgac_cv_type_locale_t" = 'yes (in xlocale.h)'; then
   AC_DEFINE(LOCALE_T_IN_XLOCALE, 1,
             [Define to 1 if `locale_t' requires <xlocale.h>.])

configure

@@ -15120,11 +15120,6 @@ rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
 fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_type_locale_t" >&5
 $as_echo "$pgac_cv_type_locale_t" >&6; }
-if test "$pgac_cv_type_locale_t" != no; then
-
-$as_echo "#define HAVE_LOCALE_T 1" >>confdefs.h
-
-fi
 if test "$pgac_cv_type_locale_t" = 'yes (in xlocale.h)'; then
 
 $as_echo "#define LOCALE_T_IN_XLOCALE 1" >>confdefs.h

meson.build

@@ -2283,17 +2283,13 @@ else
   cdata.set('STRERROR_R_INT', false)
 endif
 
-# Check for the locale_t type and find the right header file.  macOS
-# needs xlocale.h; standard is locale.h, but glibc also has an
-# xlocale.h file that we should not use.  MSVC has a replacement
-# defined in src/include/port/win32_port.h.
-if cc.has_type('locale_t', prefix: '#include <locale.h>')
-  cdata.set('HAVE_LOCALE_T', 1)
-elif cc.has_type('locale_t', prefix: '#include <xlocale.h>')
-  cdata.set('HAVE_LOCALE_T', 1)
+# Find the right header file for the locale_t type.  macOS needs xlocale.h;
+# standard is locale.h, but glibc <= 2.25 also had an xlocale.h file that
+# we should not use so we check the standard header first.  MSVC has a
+# replacement defined in src/include/port/win32_port.h.
+if not cc.has_type('locale_t', prefix: '#include <locale.h>') and \
+   cc.has_type('locale_t', prefix: '#include <xlocale.h>')
   cdata.set('LOCALE_T_IN_XLOCALE', 1)
-elif cc.get_id() == 'msvc'
-  cdata.set('HAVE_LOCALE_T', 1)
 endif
 
 # Check if the C compiler understands typeof or a variant.  Define
@@ -2489,13 +2485,6 @@ if cc.has_function('syslog', args: test_c_args) and \
 endif
 
 
-# MSVC has replacements defined in src/include/port/win32_port.h.
-if cc.get_id() == 'msvc'
-  cdata.set('HAVE_WCSTOMBS_L', 1)
-  cdata.set('HAVE_MBSTOWCS_L', 1)
-endif
-
-
 # if prerequisites for unnamed posix semas aren't fulfilled, fall back to sysv
 # semaphores
 if sema_kind == 'unnamed_posix' and \

src/backend/commands/collationcmds.c

@@ -534,7 +534,7 @@ pg_collation_actual_version(PG_FUNCTION_ARGS)
 
 
 /* will we use "locale -a" in pg_import_system_collations? */
-#if defined(HAVE_LOCALE_T) && !defined(WIN32)
+#if !defined(WIN32)
 #define READ_LOCALE_A_OUTPUT
 #endif
 

src/backend/regex/regc_pg_locale.c

@@ -44,8 +44,7 @@
  * the platform's wchar_t representation matches what we do in pg_wchar
  * conversions.
  *
- * 3. Other collations are only supported on platforms that HAVE_LOCALE_T.
- * Here, we use the locale_t-extended forms of the <wctype.h> and <ctype.h>
+ * 3. Here, we use the locale_t-extended forms of the <wctype.h> and <ctype.h>
  * functions, under exactly the same cases as #2.
  *
  * There is one notable difference between cases 2 and 3: in the "default"
@@ -252,11 +251,6 @@ pg_set_regex_collation(Oid collation)
 	}
 	else
 	{
-		/*
-		 * NB: pg_newlocale_from_collation will fail if not HAVE_LOCALE_T; the
-		 * case of pg_regex_locale != 0 but not HAVE_LOCALE_T does not have to
-		 * be considered below.
-		 */
 		pg_regex_locale = pg_newlocale_from_collation(collation);
 
 		if (!pg_locale_deterministic(pg_regex_locale))
@@ -304,16 +298,12 @@ pg_wc_isdigit(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isdigit((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswdigit_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isdigit_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -340,16 +330,12 @@ pg_wc_isalpha(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalpha((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswalpha_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalpha_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -376,16 +362,12 @@ pg_wc_isalnum(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalnum((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswalnum_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isalnum_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -421,16 +403,12 @@ pg_wc_isupper(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isupper((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswupper_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isupper_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -457,16 +435,12 @@ pg_wc_islower(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					islower((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswlower_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					islower_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -493,16 +467,12 @@ pg_wc_isgraph(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isgraph((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswgraph_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isgraph_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -529,16 +499,12 @@ pg_wc_isprint(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isprint((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswprint_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isprint_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -565,16 +531,12 @@ pg_wc_ispunct(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					ispunct((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswpunct_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					ispunct_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -601,16 +563,12 @@ pg_wc_isspace(pg_wchar c)
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isspace((unsigned char) c));
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return iswspace_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			return (c <= (pg_wchar) UCHAR_MAX &&
 					isspace_l((unsigned char) c, pg_regex_locale->info.lt));
-#endif
 			break;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -645,16 +603,12 @@ pg_wc_toupper(pg_wchar c)
 				return toupper((unsigned char) c);
 			return c;
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return towupper_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return toupper_l((unsigned char) c, pg_regex_locale->info.lt);
-#endif
 			return c;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU
@@ -689,16 +643,12 @@ pg_wc_tolower(pg_wchar c)
 				return tolower((unsigned char) c);
 			return c;
 		case PG_REGEX_LOCALE_WIDE_L:
-#ifdef HAVE_LOCALE_T
 			if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
 				return towlower_l((wint_t) c, pg_regex_locale->info.lt);
-#endif
 			/* FALL THRU */
 		case PG_REGEX_LOCALE_1BYTE_L:
-#ifdef HAVE_LOCALE_T
 			if (c <= (pg_wchar) UCHAR_MAX)
 				return tolower_l((unsigned char) c, pg_regex_locale->info.lt);
-#endif
 			return c;
 		case PG_REGEX_LOCALE_ICU:
 #ifdef USE_ICU

src/backend/utils/adt/formatting.c

@@ -1613,12 +1613,6 @@ u_strToTitle_default_BI(UChar *dest, int32_t destCapacity,
  * in multibyte character sets.  Note that in either case we are effectively
  * assuming that the database character encoding matches the encoding implied
  * by LC_CTYPE.
- *
- * If the system provides locale_t and associated functions (which are
- * standardized by Open Group's XBD), we can support collations that are
- * neither default nor C.  The code is written to handle both combinations
- * of have-wide-characters and have-locale_t, though it's rather unlikely
- * a platform would have the latter without the former.
  */
 
 /*
@@ -1696,11 +1690,9 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
 
 				for (curr_char = 0; workspace[curr_char] != 0; curr_char++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 						workspace[curr_char] = towlower_l(workspace[curr_char], mylocale->info.lt);
 					else
-#endif
 						workspace[curr_char] = towlower(workspace[curr_char]);
 				}
 
@@ -1729,11 +1721,9 @@ str_tolower(const char *buff, size_t nbytes, Oid collid)
 				 */
 				for (p = result; *p; p++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 						*p = tolower_l((unsigned char) *p, mylocale->info.lt);
 					else
-#endif
 						*p = pg_tolower((unsigned char) *p);
 				}
 			}
@@ -1818,11 +1808,9 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
 
 				for (curr_char = 0; workspace[curr_char] != 0; curr_char++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 						workspace[curr_char] = towupper_l(workspace[curr_char], mylocale->info.lt);
 					else
-#endif
 						workspace[curr_char] = towupper(workspace[curr_char]);
 				}
 
@@ -1851,11 +1839,9 @@ str_toupper(const char *buff, size_t nbytes, Oid collid)
 				 */
 				for (p = result; *p; p++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 						*p = toupper_l((unsigned char) *p, mylocale->info.lt);
 					else
-#endif
 						*p = pg_toupper((unsigned char) *p);
 				}
 			}
@@ -1941,7 +1927,6 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 
 				for (curr_char = 0; workspace[curr_char] != 0; curr_char++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 					{
 						if (wasalnum)
@@ -1951,7 +1936,6 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 						wasalnum = iswalnum_l(workspace[curr_char], mylocale->info.lt);
 					}
 					else
-#endif
 					{
 						if (wasalnum)
 							workspace[curr_char] = towlower(workspace[curr_char]);
@@ -1986,7 +1970,6 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 				 */
 				for (p = result; *p; p++)
 				{
-#ifdef HAVE_LOCALE_T
 					if (mylocale)
 					{
 						if (wasalnum)
@@ -1996,7 +1979,6 @@ str_initcap(const char *buff, size_t nbytes, Oid collid)
 						wasalnum = isalnum_l((unsigned char) *p, mylocale->info.lt);
 					}
 					else
-#endif
 					{
 						if (wasalnum)
 							*p = pg_tolower((unsigned char) *p);

src/backend/utils/adt/like.c

@@ -95,10 +95,8 @@ SB_lower_char(unsigned char c, pg_locale_t locale, bool locale_is_c)
 {
 	if (locale_is_c)
 		return pg_ascii_tolower(c);
-#ifdef HAVE_LOCALE_T
 	else if (locale)
 		return tolower_l(c, locale->info.lt);
-#endif
 	else
 		return pg_tolower(c);
 }