From 52a2a3fa9a9eeaa19d477863d15282045c40dd3a Mon Sep 17 00:00:00 2001 From: Bruno Haible Date: Sat, 31 Aug 2024 19:22:37 +0200 Subject: [PATCH] Prepare for stronger LC_CTYPE tests on OpenBSD, Android, Haiku. * m4/locale-en.m4: New file, based on m4/locale-fr.m4. * m4/locale-ar.m4 (gt_LOCALE_AR): Update comments. * m4/locale-fr.m4 (gt_LOCALE_FR, gt_LOCALE_FR_UTF8): Likewise. * m4/locale-ja.m4 (gt_LOCALE_JA): Likewise. * m4/locale-tr.m4 (gt_LOCALE_TR_UTF8): Likewise. * m4/locale-zh.m4 (gt_LOCALE_ZH_CN): Likewise. --- ChangeLog | 10 ++++ m4/locale-ar.m4 | 7 +-- m4/locale-en.m4 | 137 ++++++++++++++++++++++++++++++++++++++++++++++++ m4/locale-fr.m4 | 22 ++++---- m4/locale-ja.m4 | 7 +-- m4/locale-tr.m4 | 7 +-- m4/locale-zh.m4 | 7 +-- 7 files changed, 176 insertions(+), 21 deletions(-) create mode 100644 m4/locale-en.m4 diff --git a/ChangeLog b/ChangeLog index 08621c00ab..9c19b7677b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,13 @@ +2024-08-31 Bruno Haible + + Prepare for stronger LC_CTYPE tests on OpenBSD, Android, Haiku. + * m4/locale-en.m4: New file, based on m4/locale-fr.m4. + * m4/locale-ar.m4 (gt_LOCALE_AR): Update comments. + * m4/locale-fr.m4 (gt_LOCALE_FR, gt_LOCALE_FR_UTF8): Likewise. + * m4/locale-ja.m4 (gt_LOCALE_JA): Likewise. + * m4/locale-tr.m4 (gt_LOCALE_TR_UTF8): Likewise. + * m4/locale-zh.m4 (gt_LOCALE_ZH_CN): Likewise. + 2024-08-31 Bruno Haible trim, unicodeio tests: Fix module description. diff --git a/m4/locale-ar.m4 b/m4/locale-ar.m4 index e7d23f44b4..f346e569b5 100644 --- a/m4/locale-ar.m4 +++ b/m4/locale-ar.m4 @@ -1,4 +1,4 @@ -# locale-ar.m4 serial 11 +# locale-ar.m4 serial 12 dnl Copyright (C) 2003, 2005-2024 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -64,10 +64,11 @@ int main () { if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Note that on native Windows, the Arabic locale is diff --git a/m4/locale-en.m4 b/m4/locale-en.m4 new file mode 100644 index 0000000000..39d08a23b0 --- /dev/null +++ b/m4/locale-en.m4 @@ -0,0 +1,137 @@ +# locale-en.m4 +# serial 1 +dnl Copyright (C) 2003-2024 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. + +dnl From Bruno Haible. + +dnl Determine the name of an English (or American English) locale with +dnl UTF-8 encoding. +AC_DEFUN_ONCE([gt_LOCALE_EN_UTF8], +[ + AC_REQUIRE([AC_CANONICAL_HOST]) + AC_REQUIRE([AM_LANGINFO_CODESET]) + AC_CACHE_CHECK([for an english Unicode locale], [gt_cv_locale_en_utf8], [ + case "$host_os" in + *-musl* | midipix*) + dnl On musl libc, all kinds of ll_CC.UTF-8 locales exist, even without + dnl any locale file on disk. But they are effectively equivalent to the + dnl C.UTF-8 locale, except for locale categories (such as LC_MESSSAGES) + dnl for which localizations (.mo files) have been installed. + gt_cv_locale_en_utf8=en_US.UTF-8 + ;; + *) + AC_LANG_CONFTEST([AC_LANG_SOURCE([[ +#include +#include +#if HAVE_LANGINFO_CODESET +# include +#endif +#include +#include +struct tm t; +char buf[16]; +int main () { + /* On BeOS and Haiku, locales are not implemented in libc. Rather, libintl + imitates locale dependent behaviour by looking at the environment + variables, and all locales use the UTF-8 encoding. */ +#if !(defined __BEOS__ || defined __HAIKU__) + /* Check whether the given locale name is recognized by the system. */ +# if defined _WIN32 && !defined __CYGWIN__ + /* On native Windows, setlocale(category, "") looks at the system settings, + not at the environment variables. Also, when an encoding suffix such + as ".65001" or ".54936" is specified, it succeeds but sets the LC_CTYPE + category of the locale to "C". */ + if (setlocale (LC_ALL, getenv ("LC_ALL")) == NULL + || strcmp (setlocale (LC_CTYPE, NULL), "C") == 0) + return 1; +# else + if (setlocale (LC_ALL, "") == NULL) return 1; +# endif + /* Check whether nl_langinfo(CODESET) is "UTF-8" or equivalent. */ +# if HAVE_LANGINFO_CODESET + { + const char *cs = nl_langinfo (CODESET); + if (!(strcmp (cs, "UTF-8") == 0 || strcmp (cs, "UTF8") == 0 + || strcmp (cs, "utf-8") == 0 || strcmp (cs, "utf8") == 0)) + return 1; + } +# endif +# ifdef __CYGWIN__ + /* On Cygwin, avoid locale names without encoding suffix, because the + locale_charset() function relies on the encoding suffix. Note that + LC_ALL is set on the command line. */ + if (strchr (getenv ("LC_ALL"), '.') == NULL) return 1; +# endif + /* Check the third month name. */ + t.tm_year = 1975 - 1900; t.tm_mon = 3 - 1; t.tm_mday = 24; + if (strftime (buf, sizeof (buf), "%B", &t) < 5 || strcmp (buf, "March") != 0) + return 1; +#endif +#if !defined __BIONIC__ /* Bionic libc's 'struct lconv' is just a dummy. */ + /* Check whether the decimal separator is a dot. */ + if (localeconv () ->decimal_point[0] != '.') return 1; +#endif + return 0; +} + ]])]) + if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then + case "$host_os" in + # Handle native Windows specially, because there setlocale() interprets + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", + # "fr" or "fra" as "French" or "French_France.1252", + # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", + # and similar. + mingw* | windows*) + # Test for the hypothetical native Windows locale name. + if (LC_ALL='English_United States.65001' LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then + gt_cv_locale_en_utf8='English_United States.65001' + else + # None found. + gt_cv_locale_en_utf8=none + fi + ;; + *) + # Setting LC_ALL is not enough. Need to set LC_TIME to empty, because + # otherwise on Mac OS X 10.3.5 the LC_TIME=C from the beginning of the + # configure script would override the LC_ALL setting. Likewise for + # LC_CTYPE, which is also set at the beginning of the configure script. + # Test for the locale name with explicit encoding suffix first + # (this is necessary on Haiku). + if (LC_ALL=en_US.UTF-8 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then + gt_cv_locale_en_utf8=en_US.UTF-8 + else + # Test for the locale name without encoding suffix. + if (LC_ALL=en_US LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then + gt_cv_locale_en_utf8=en_US + else + # Test for the Solaris 10 locale name. + if (LC_ALL=en.UTF-8 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then + gt_cv_locale_en_utf8=en.UTF-8 + else + # None found. + gt_cv_locale_en_utf8=none + fi + fi + fi + ;; + esac + fi + rm -fr conftest* + ;; + esac + ]) + LOCALE_EN_UTF8="$gt_cv_locale_en_utf8" + case "$LOCALE_EN_UTF8" in #( + '' | *[[\"\$\'*@<:@]]*) + dnl The empty value occurs when the conftest.c program above could not + dnl be compiled. The other values might cause trouble with sh or make. + AC_MSG_WARN([invalid locale "$LOCALE_EN_UTF8"; assuming "none"]) + LOCALE_EN_UTF8=none;; + esac + AC_SUBST([LOCALE_EN_UTF8]) +]) diff --git a/m4/locale-fr.m4 b/m4/locale-fr.m4 index c9528562e7..cf0121b27f 100644 --- a/m4/locale-fr.m4 +++ b/m4/locale-fr.m4 @@ -1,4 +1,4 @@ -# locale-fr.m4 serial 23 +# locale-fr.m4 serial 24 dnl Copyright (C) 2003, 2005-2024 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -70,8 +70,9 @@ int main () { if (strftime (buf, sizeof (buf), "%b", &t) < 3 || buf[2] != 'v') return 1; # if !defined __BIONIC__ /* Bionic libc's 'struct lconv' is just a dummy. */ /* Check whether the decimal separator is a comma. - On NetBSD 3.0 in the fr_FR.ISO8859-1 locale, localeconv()->decimal_point - are nl_langinfo(RADIXCHAR) are both ".". */ + On NetBSD 3.0 in the fr_FR.ISO8859-1 locale + and on Haiku in the fr_FR.UTF-8 locale, + localeconv()->decimal_point are nl_langinfo(RADIXCHAR) are both ".". */ if (localeconv () ->decimal_point[0] != ',') return 1; # endif return 0; @@ -81,10 +82,11 @@ int main () { if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Test for the native Windows locale name. @@ -213,8 +215,9 @@ int main () { #endif #if !defined __BIONIC__ /* Bionic libc's 'struct lconv' is just a dummy. */ /* Check whether the decimal separator is a comma. - On NetBSD 3.0 in the fr_FR.ISO8859-1 locale, localeconv()->decimal_point - are nl_langinfo(RADIXCHAR) are both ".". */ + On NetBSD 3.0 in the fr_FR.ISO8859-1 locale + and on Haiku in the fr_FR.UTF-8 locale, + localeconv()->decimal_point are nl_langinfo(RADIXCHAR) are both ".". */ if (localeconv () ->decimal_point[0] != ',') return 1; #endif return 0; @@ -223,10 +226,11 @@ int main () { if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Test for the hypothetical native Windows locale name. diff --git a/m4/locale-ja.m4 b/m4/locale-ja.m4 index 71a9863b47..b783e8495a 100644 --- a/m4/locale-ja.m4 +++ b/m4/locale-ja.m4 @@ -1,4 +1,4 @@ -# locale-ja.m4 serial 18 +# locale-ja.m4 serial 19 dnl Copyright (C) 2003, 2005-2024 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -85,10 +85,11 @@ int main () if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Note that on native Windows, the Japanese locale is diff --git a/m4/locale-tr.m4 b/m4/locale-tr.m4 index b68e429a87..91fe12ab63 100644 --- a/m4/locale-tr.m4 +++ b/m4/locale-tr.m4 @@ -1,4 +1,4 @@ -# locale-tr.m4 serial 15 +# locale-tr.m4 serial 16 dnl Copyright (C) 2003, 2005-2024 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -78,10 +78,11 @@ int main () { if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Test for the hypothetical native Windows locale name. diff --git a/m4/locale-zh.m4 b/m4/locale-zh.m4 index 030bffa924..54822eb404 100644 --- a/m4/locale-zh.m4 +++ b/m4/locale-zh.m4 @@ -1,4 +1,4 @@ -# locale-zh.m4 serial 19 +# locale-zh.m4 serial 20 dnl Copyright (C) 2003, 2005-2024 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -100,10 +100,11 @@ int main () if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then case "$host_os" in # Handle native Windows specially, because there setlocale() interprets - # "ar" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "ar" or "ara" as "Arabic" or "Arabic_Saudi Arabia.1256", + # "en" or "eng" as "English" or "English_United States.1252", # "fr" or "fra" as "French" or "French_France.1252", # "ge"(!) or "deu"(!) as "German" or "German_Germany.1252", - # "ja" as "Japanese" or "Japanese_Japan.932", + # "ja" or "jpn" as "Japanese" or "Japanese_Japan.932", # and similar. mingw* | windows*) # Test for the hypothetical native Windows locale name. -- 2.39.5