From e8bd88d1fcded01ccd066572eeaae1b507989cb3 Mon Sep 17 00:00:00 2001 From: RincewindsHat <12514511+RincewindsHat@users.noreply.github.com> Date: Tue, 31 Jan 2023 14:46:01 +0100 Subject: Sync with the latest Gnulib code 668c0b8ffa --- gl/m4/mbrtowc.m4 | 358 ++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 288 insertions(+), 70 deletions(-) (limited to 'gl/m4/mbrtowc.m4') diff --git a/gl/m4/mbrtowc.m4 b/gl/m4/mbrtowc.m4 index 4c9f3886..bb393041 100644 --- a/gl/m4/mbrtowc.m4 +++ b/gl/m4/mbrtowc.m4 @@ -1,5 +1,5 @@ -# mbrtowc.m4 serial 25 -dnl Copyright (C) 2001-2002, 2004-2005, 2008-2013 Free Software Foundation, +# mbrtowc.m4 serial 38 -*- coding: utf-8 -*- +dnl Copyright (C) 2001-2002, 2004-2005, 2008-2023 Free Software Foundation, dnl Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -8,6 +8,8 @@ dnl with or without modifications, as long as this notice is preserved. AC_DEFUN([gl_FUNC_MBRTOWC], [ AC_REQUIRE([gl_WCHAR_H_DEFAULTS]) + AC_REQUIRE([gl_PTHREADLIB]) + AC_CHECK_HEADERS_ONCE([threads.h]) AC_REQUIRE([AC_TYPE_MBSTATE_T]) gl_MBSTATE_T_BROKEN @@ -16,15 +18,8 @@ AC_DEFUN([gl_FUNC_MBRTOWC], if test $ac_cv_func_mbrtowc = no; then HAVE_MBRTOWC=0 AC_CHECK_DECLS([mbrtowc],,, [[ -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include -#include -]]) + #include + ]]) if test $ac_cv_have_decl_mbrtowc = yes; then dnl On Minix 3.1.8, the system's declares mbrtowc() although dnl it does not have the function. Avoid a collision with gnulib's @@ -39,6 +34,9 @@ AC_DEFUN([gl_FUNC_MBRTOWC], gl_MBRTOWC_NULL_ARG2 gl_MBRTOWC_RETVAL gl_MBRTOWC_NUL_RETVAL + gl_MBRTOWC_STORES_INCOMPLETE + gl_MBRTOWC_EMPTY_INPUT + gl_MBRTOWC_C_LOCALE case "$gl_cv_func_mbrtowc_null_arg1" in *yes) ;; *) AC_DEFINE([MBRTOWC_NULL_ARG1_BUG], [1], @@ -67,8 +65,47 @@ AC_DEFUN([gl_FUNC_MBRTOWC], REPLACE_MBRTOWC=1 ;; esac + case "$gl_cv_func_mbrtowc_stores_incomplete" in + *no) ;; + *) AC_DEFINE([MBRTOWC_STORES_INCOMPLETE_BUG], [1], + [Define if the mbrtowc function stores a wide character when reporting incomplete input.]) + REPLACE_MBRTOWC=1 + ;; + esac + case "$gl_cv_func_mbrtowc_empty_input" in + *yes) ;; + *) AC_DEFINE([MBRTOWC_EMPTY_INPUT_BUG], [1], + [Define if the mbrtowc function does not return (size_t) -2 + for empty input.]) + REPLACE_MBRTOWC=1 + ;; + esac + case "$gl_cv_func_mbrtowc_C_locale_sans_EILSEQ" in + *yes) ;; + *) AC_DEFINE([MBRTOWC_IN_C_LOCALE_MAYBE_EILSEQ], [1], + [Define if the mbrtowc function may signal encoding errors in the C locale.]) + REPLACE_MBRTOWC=1 + ;; + esac fi fi + if test $REPLACE_MBSTATE_T = 1; then + case "$host_os" in + mingw*) LIB_MBRTOWC= ;; + *) + gl_WEAK_SYMBOLS + case "$gl_cv_have_weak" in + *yes) LIB_MBRTOWC= ;; + *) LIB_MBRTOWC="$LIBPTHREAD" ;; + esac + ;; + esac + else + LIB_MBRTOWC= + fi + dnl LIB_MBRTOWC is expected to be '-pthread' or '-lpthread' on AIX + dnl with gcc or xlc, and empty otherwise. + AC_SUBST([LIB_MBRTOWC]) ]) dnl Test whether mbsinit() and mbrtowc() need to be overridden in a way that @@ -80,11 +117,19 @@ dnl avoid inconsistencies. AC_DEFUN([gl_MBSTATE_T_BROKEN], [ AC_REQUIRE([gl_WCHAR_H_DEFAULTS]) + AC_REQUIRE([AC_CANONICAL_HOST]) AC_REQUIRE([AC_TYPE_MBSTATE_T]) AC_CHECK_FUNCS_ONCE([mbsinit]) AC_CHECK_FUNCS_ONCE([mbrtowc]) - if test $ac_cv_func_mbsinit = yes && test $ac_cv_func_mbrtowc = yes; then + dnl On native Windows, we know exactly how mbsinit() behaves and don't need + dnl to override it, even if - like on MSVC - mbsinit() is only defined as + dnl an inline function, not as a global function. + if case "$host_os" in + mingw*) true ;; + *) test $ac_cv_func_mbsinit = yes ;; + esac \ + && test $ac_cv_func_mbrtowc = yes; then gl_MBRTOWC_INCOMPLETE_STATE gl_MBRTOWC_SANITYCHECK REPLACE_MBSTATE_T=0 @@ -109,6 +154,7 @@ AC_DEFUN([gl_MBRTOWC_INCOMPLETE_STATE], [ AC_REQUIRE([AC_PROG_CC]) AC_REQUIRE([gt_LOCALE_JA]) + AC_REQUIRE([gt_LOCALE_FR_UTF8]) AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles AC_CACHE_CHECK([whether mbrtowc handles incomplete characters], [gl_cv_func_mbrtowc_incomplete_state], @@ -128,13 +174,6 @@ changequote([,])dnl [AC_LANG_SOURCE([[ #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -147,13 +186,39 @@ int main () memset (&state, '\0', sizeof (mbstate_t)); if (mbrtowc (&wc, input + 1, 1, &state) == (size_t)(-2)) if (mbsinit (&state)) - return 1; + return 2; + } + return 0; +}]])], + [gl_cv_func_mbrtowc_incomplete_state=yes], + [gl_cv_func_mbrtowc_incomplete_state=no], + [:]) + else + if test $LOCALE_FR_UTF8 != none; then + AC_RUN_IFELSE( + [AC_LANG_SOURCE([[ +#include +#include +#include +int main () +{ + if (setlocale (LC_ALL, "$LOCALE_FR_UTF8") != NULL) + { + const char input[] = "B\303\274\303\237er"; /* "Büßer" */ + mbstate_t state; + wchar_t wc; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, input + 1, 1, &state) == (size_t)(-2)) + if (mbsinit (&state)) + return 2; } return 0; }]])], [gl_cv_func_mbrtowc_incomplete_state=yes], [gl_cv_func_mbrtowc_incomplete_state=no], [:]) + fi fi ]) ]) @@ -185,13 +250,6 @@ changequote([,])dnl #include #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -207,7 +265,7 @@ int main () memset (&state, '\0', sizeof (mbstate_t)); if (mbrtowc (&wc, input + 3, 6, &state) != 4 && mbtowc (&wc, input + 3, 6) == 4) - return 1; + return 2; } return 0; }]])], @@ -245,13 +303,6 @@ changequote([,])dnl #include #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -314,13 +365,6 @@ changequote([,])dnl [AC_LANG_SOURCE([[ #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -335,7 +379,7 @@ int main () mbrtowc (&wc, NULL, 5, &state); /* Check that wc was not modified. */ if (wc != (wchar_t) 0xBADFACE) - return 1; + return 2; } return 0; }]])], @@ -376,13 +420,6 @@ changequote([,])dnl [AC_LANG_SOURCE([[ #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -504,13 +541,6 @@ changequote([,])dnl [AC_LANG_SOURCE([[ #include #include -/* Tru64 with Desktop Toolkit C has a bug: must be included before - . - BSD/OS 4.0.1 has a bug: , and must be - included before . */ -#include -#include -#include #include int main () { @@ -522,7 +552,7 @@ int main () memset (&state, '\0', sizeof (mbstate_t)); if (mbrtowc (&wc, "", 1, &state) != 0) - return 1; + return 2; } return 0; }]])], @@ -533,11 +563,206 @@ int main () ]) ]) -# Prerequisites of lib/mbrtowc.c. +dnl Test whether mbrtowc stores a wide character when reporting incomplete +dnl input. + +AC_DEFUN([gl_MBRTOWC_STORES_INCOMPLETE], +[ + AC_REQUIRE([AC_PROG_CC]) + AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles + AC_CACHE_CHECK([whether mbrtowc stores incomplete characters], + [gl_cv_func_mbrtowc_stores_incomplete], + [ + dnl Initial guess, used when cross-compiling or when no suitable locale + dnl is present. +changequote(,)dnl + case "$host_os" in + # Guess yes on native Windows. + mingw*) gl_cv_func_mbrtowc_stores_incomplete="guessing yes" ;; + *) gl_cv_func_mbrtowc_stores_incomplete="guessing no" ;; + esac +changequote([,])dnl + case "$host_os" in + mingw*) + AC_RUN_IFELSE( + [AC_LANG_SOURCE([[ +#include +#include +#include +int main () +{ + int result = 0; + if (setlocale (LC_ALL, "French_France.65001") != NULL) + { + wchar_t wc = (wchar_t) 0xBADFACE; + mbstate_t state; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, "\303", 1, &state) == (size_t)(-2) + && wc != (wchar_t) 0xBADFACE) + result |= 1; + } + if (setlocale (LC_ALL, "Japanese_Japan.932") != NULL) + { + wchar_t wc = (wchar_t) 0xBADFACE; + mbstate_t state; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, "\226", 1, &state) == (size_t)(-2) + && wc != (wchar_t) 0xBADFACE) + result |= 2; + } + if (setlocale (LC_ALL, "Chinese_Taiwan.950") != NULL) + { + wchar_t wc = (wchar_t) 0xBADFACE; + mbstate_t state; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, "\245", 1, &state) == (size_t)(-2) + && wc != (wchar_t) 0xBADFACE) + result |= 4; + } + if (setlocale (LC_ALL, "Chinese_China.936") != NULL) + { + wchar_t wc = (wchar_t) 0xBADFACE; + mbstate_t state; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, "\261", 1, &state) == (size_t)(-2) + && wc != (wchar_t) 0xBADFACE) + result |= 8; + } + return result; +}]])], + [gl_cv_func_mbrtowc_stores_incomplete=no], + [gl_cv_func_mbrtowc_stores_incomplete=yes], + [:]) + ;; + *) + AC_REQUIRE([gt_LOCALE_FR_UTF8]) + if test $LOCALE_FR_UTF8 != none; then + AC_RUN_IFELSE( + [AC_LANG_SOURCE([[ +#include +#include +#include +int main () +{ + if (setlocale (LC_ALL, "$LOCALE_FR_UTF8") != NULL) + { + wchar_t wc = (wchar_t) 0xBADFACE; + mbstate_t state; + + memset (&state, '\0', sizeof (mbstate_t)); + if (mbrtowc (&wc, "\303", 1, &state) == (size_t)(-2) + && wc != (wchar_t) 0xBADFACE) + return 1; + } + return 0; +}]])], + [gl_cv_func_mbrtowc_stores_incomplete=no], + [gl_cv_func_mbrtowc_stores_incomplete=yes], + [:]) + fi + ;; + esac + ]) +]) + +dnl Test whether mbrtowc returns the correct value on empty input. + +AC_DEFUN([gl_MBRTOWC_EMPTY_INPUT], +[ + AC_REQUIRE([AC_PROG_CC]) + AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles + AC_CACHE_CHECK([whether mbrtowc works on empty input], + [gl_cv_func_mbrtowc_empty_input], + [ + dnl Initial guess, used when cross-compiling or when no suitable locale + dnl is present. +changequote(,)dnl + case "$host_os" in + # Guess no on AIX and glibc systems. + aix* | *-gnu* | gnu*) gl_cv_func_mbrtowc_empty_input="guessing no" ;; + # Guess yes on native Windows. + mingw*) gl_cv_func_mbrtowc_empty_input="guessing yes" ;; + *) gl_cv_func_mbrtowc_empty_input="guessing yes" ;; + esac +changequote([,])dnl + AC_RUN_IFELSE( + [AC_LANG_SOURCE([[ + #include + static wchar_t wc; + static mbstate_t mbs; + int + main (void) + { + return mbrtowc (&wc, "", 0, &mbs) != (size_t) -2; + }]])], + [gl_cv_func_mbrtowc_empty_input=yes], + [gl_cv_func_mbrtowc_empty_input=no], + [:]) + ]) +]) + +dnl Test whether mbrtowc reports encoding errors in the C locale. +dnl Although POSIX was never intended to allow this, the GNU C Library +dnl and other implementations do it. See: +dnl https://sourceware.org/bugzilla/show_bug.cgi?id=19932 + +AC_DEFUN([gl_MBRTOWC_C_LOCALE], +[ + AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles + AC_CACHE_CHECK([whether the C locale is free of encoding errors], + [gl_cv_func_mbrtowc_C_locale_sans_EILSEQ], + [ + dnl Initial guess, used when cross-compiling or when no suitable locale + dnl is present. + gl_cv_func_mbrtowc_C_locale_sans_EILSEQ="$gl_cross_guess_normal" + + AC_RUN_IFELSE( + [AC_LANG_PROGRAM( + [[#include + #include + #include + ]], [[ + int i; + char *locale = setlocale (LC_ALL, "C"); + if (! locale) + return 2; + for (i = CHAR_MIN; i <= CHAR_MAX; i++) + { + char c = i; + wchar_t wc; + mbstate_t mbs = { 0, }; + size_t ss = mbrtowc (&wc, &c, 1, &mbs); + if (1 < ss) + return 3; + } + return 0; + ]])], + [gl_cv_func_mbrtowc_C_locale_sans_EILSEQ=yes], + [gl_cv_func_mbrtowc_C_locale_sans_EILSEQ=no], + [case "$host_os" in + # Guess yes on native Windows. + mingw*) gl_cv_func_mbrtowc_C_locale_sans_EILSEQ="guessing yes" ;; + esac + ]) + ]) +]) + +# Prerequisites of lib/mbrtowc.c and lib/lc-charset-dispatch.c. AC_DEFUN([gl_PREREQ_MBRTOWC], [ + AC_REQUIRE([AC_C_INLINE]) : ]) +# Prerequisites of lib/mbtowc-lock.c. +AC_DEFUN([gl_PREREQ_MBTOWC_LOCK], +[ + gl_VISIBILITY +]) + dnl From Paul Eggert @@ -547,24 +772,17 @@ AC_DEFUN([AC_FUNC_MBRTOWC], [ dnl Same as AC_FUNC_MBRTOWC in autoconf-2.60. AC_CACHE_CHECK([whether mbrtowc and mbstate_t are properly declared], - gl_cv_func_mbrtowc, + [gl_cv_func_mbrtowc], [AC_LINK_IFELSE( [AC_LANG_PROGRAM( - [[/* Tru64 with Desktop Toolkit C has a bug: must be - included before . - BSD/OS 4.0.1 has a bug: , and - must be included before . */ - #include - #include - #include - #include ]], + [[#include ]], [[wchar_t wc; char const s[] = ""; size_t n = 1; mbstate_t state; return ! (sizeof state && (mbrtowc) (&wc, s, n, &state));]])], - gl_cv_func_mbrtowc=yes, - gl_cv_func_mbrtowc=no)]) + [gl_cv_func_mbrtowc=yes], + [gl_cv_func_mbrtowc=no])]) if test $gl_cv_func_mbrtowc = yes; then AC_DEFINE([HAVE_MBRTOWC], [1], [Define to 1 if mbrtowc and mbstate_t are properly declared.]) -- cgit v1.2.3-74-g34f1