From 444ebd4da72a6d959563c9ac29927c2ccc11e003 Mon Sep 17 00:00:00 2001 From: Bruno Haible Date: Tue, 4 Apr 2023 23:21:04 +0200 Subject: [PATCH] c32tolower: New module. * lib/uchar.in.h (c32tolower): New declaration. * lib/c32tolower.c: New file. * lib/c32to-impl.h: New file, based on lib/c32is-impl.h. * modules/c32tolower: New file. * m4/uchar_h.m4 (gl_UCHAR_H_REQUIRE_DEFAULTS): Initialize GNULIB_C32TOLOWER. * modules/uchar (Makefile.am): Substitute GNULIB_C32TOLOWER. --- ChangeLog | 11 ++++++ lib/c32to-impl.h | 92 ++++++++++++++++++++++++++++++++++++++++++++++ lib/c32tolower.c | 34 +++++++++++++++++ lib/uchar.in.h | 18 +++++++++ m4/uchar_h.m4 | 3 +- modules/c32tolower | 44 ++++++++++++++++++++++ modules/uchar | 1 + 7 files changed, 202 insertions(+), 1 deletion(-) create mode 100644 lib/c32to-impl.h create mode 100644 lib/c32tolower.c create mode 100644 modules/c32tolower diff --git a/ChangeLog b/ChangeLog index ea2857a38c..79a570e891 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +2023-04-09 Bruno Haible + + c32tolower: New module. + * lib/uchar.in.h (c32tolower): New declaration. + * lib/c32tolower.c: New file. + * lib/c32to-impl.h: New file, based on lib/c32is-impl.h. + * modules/c32tolower: New file. + * m4/uchar_h.m4 (gl_UCHAR_H_REQUIRE_DEFAULTS): Initialize + GNULIB_C32TOLOWER. + * modules/uchar (Makefile.am): Substitute GNULIB_C32TOLOWER. + 2023-04-09 Bruno Haible c32is*: Ensure GNULIB_defined_mbstate_t is defined on AIX. diff --git a/lib/c32to-impl.h b/lib/c32to-impl.h new file mode 100644 index 0000000000..724691a116 --- /dev/null +++ b/lib/c32to-impl.h @@ -0,0 +1,92 @@ +/* Case mapping of a 32-bit wide character. + Copyright (C) 2020-2023 Free Software Foundation, Inc. + + This file is free software. + It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+". + You can redistribute it and/or modify it under either + - the terms of the GNU Lesser General Public License as published + by the Free Software Foundation, either version 3, or (at your + option) any later version, or + - the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2, or (at your option) + any later version, or + - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". + + This file is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License and the GNU General Public License + for more details. + + You should have received a copy of the GNU Lesser General Public + License and of the GNU General Public License along with this + program. If not, see . */ + +/* Written by Bruno Haible , 2023. */ + +#include +#include + +#if GNULIB_defined_mbstate_t +# include "localcharset.h" +# include "streq.h" +#endif + +#include "unicase.h" + +#if _GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t +_GL_EXTERN_INLINE +#endif +wint_t +FUNC (wint_t wc) +{ + /* The char32_t encoding of a multibyte character is defined by the way + mbrtoc32() is defined. */ + +#if GNULIB_defined_mbstate_t /* AIX, IRIX */ + /* mbrtoc32() is defined on top of mbtowc() for the non-UTF-8 locales + and directly for the UTF-8 locales. */ + if (wc != WEOF) + { + const char *encoding = locale_charset (); + if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0)) + return UCS_FUNC (wc); + else + return WCHAR_FUNC (wc); + } + else + return wc; + +#elif HAVE_WORKING_MBRTOC32 /* glibc */ + /* mbrtoc32() is essentially defined by the system libc. */ + +# if _GL_WCHAR_T_IS_UCS4 + /* The char32_t encoding of a multibyte character is known to be the same as + the wchar_t encoding. */ + return WCHAR_FUNC (wc); +# else + /* The char32_t encoding of a multibyte character is known to be UCS-4, + different from the wchar_t encoding. */ + if (wc != WEOF) + return UCS_FUNC (wc); + else + return wc; +# endif + +#elif _GL_SMALL_WCHAR_T /* Cygwin, mingw, MSVC */ + /* The wchar_t encoding is UTF-16. + The char32_t encoding is UCS-4. */ + + if (wc == WEOF || wc == (wchar_t) wc) + /* wc is in the range for the tow* functions. */ + return WCHAR_FUNC (wc); + else + return UCS_FUNC (wc); + +#else /* macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Minix, Android */ + /* char32_t and wchar_t are equivalent. */ + static_assert (sizeof (char32_t) == sizeof (wchar_t)); + + return WCHAR_FUNC (wc); +#endif +} diff --git a/lib/c32tolower.c b/lib/c32tolower.c new file mode 100644 index 0000000000..447016214e --- /dev/null +++ b/lib/c32tolower.c @@ -0,0 +1,34 @@ +/* Map a 32-bit wide character to lowercase. + Copyright (C) 2023 Free Software Foundation, Inc. + + This file is free software. + It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+". + You can redistribute it and/or modify it under either + - the terms of the GNU Lesser General Public License as published + by the Free Software Foundation, either version 3, or (at your + option) any later version, or + - the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2, or (at your option) + any later version, or + - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". + + This file is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License and the GNU General Public License + for more details. + + You should have received a copy of the GNU Lesser General Public + License and of the GNU General Public License along with this + program. If not, see . */ + +#include + +#define IN_C32TOLOWER +/* Specification. */ +#include + +#define FUNC c32tolower +#define WCHAR_FUNC towlower +#define UCS_FUNC uc_tolower +#include "c32to-impl.h" diff --git a/lib/uchar.in.h b/lib/uchar.in.h index 4461a35901..c6795f7e91 100644 --- a/lib/uchar.in.h +++ b/lib/uchar.in.h @@ -343,6 +343,24 @@ _GL_CXXALIASWARN (c32isxdigit); #endif +/* Case mapping of a 32-bit wide character. */ +#if @GNULIB_C32TOLOWER@ +# if (_GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t) && !defined IN_C32TOLOWER +_GL_BEGIN_C_LINKAGE +_GL_INLINE wint_t +c32tolower (wint_t wc) +{ + return towlower (wc); +} +_GL_END_C_LINKAGE +# else +_GL_FUNCDECL_SYS (c32tolower, wint_t, (wint_t wc)); +# endif +_GL_CXXALIAS_SYS (c32tolower, wint_t, (wint_t wc)); +_GL_CXXALIASWARN (c32tolower); +#endif + + /* Converts a 32-bit wide character to a multibyte character. */ #if @GNULIB_C32RTOMB@ # if @REPLACE_C32RTOMB@ diff --git a/m4/uchar_h.m4 b/m4/uchar_h.m4 index 3af24cf3e4..6bb83adb6a 100644 --- a/m4/uchar_h.m4 +++ b/m4/uchar_h.m4 @@ -1,4 +1,4 @@ -# uchar_h.m4 serial 22 +# uchar_h.m4 serial 23 dnl Copyright (C) 2019-2023 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -214,6 +214,7 @@ AC_DEFUN([gl_UCHAR_H_REQUIRE_DEFAULTS], gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32ISSPACE]) gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32ISUPPER]) gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32ISXDIGIT]) + gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32TOLOWER]) gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32RTOMB]) gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32SNRTOMBS]) gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32SRTOMBS]) diff --git a/modules/c32tolower b/modules/c32tolower new file mode 100644 index 0000000000..b6ed633aec --- /dev/null +++ b/modules/c32tolower @@ -0,0 +1,44 @@ +Description: +c32tolower() function: map 32-bit wide character to lowercase. + +Files: +lib/c32tolower.c +lib/c32to-impl.h +m4/mbrtoc32.m4 +m4/mbrtowc.m4 +m4/locale-fr.m4 +m4/locale-ja.m4 +m4/locale-zh.m4 +m4/codeset.m4 + +Depends-on: +uchar +wchar +wctype-h +localcharset [test $REPLACE_MBSTATE_T = 1] +streq [test $REPLACE_MBSTATE_T = 1] +unicase/tolower +assert-h + +configure.ac: +AC_REQUIRE([gl_UCHAR_H]) +dnl Determine REPLACE_MBSTATE_T, from which GNULIB_defined_mbstate_t is +dnl determined. It describes how mbrtoc32 is implemented. +AC_REQUIRE([gl_MBSTATE_T_BROKEN]) +AC_REQUIRE([gl_MBRTOC32_SANITYCHECK]) +gl_UCHAR_MODULE_INDICATOR([c32tolower]) + +Makefile.am: +lib_SOURCES += c32tolower.c + +Include: + + +Link: +$(LTLIBUNISTRING) when linking with libtool, $(LIBUNISTRING) otherwise + +License: +LGPLv3+ or GPLv2+ + +Maintainer: +Bruno Haible diff --git a/modules/uchar b/modules/uchar index 985b58206f..f49db7d42c 100644 --- a/modules/uchar +++ b/modules/uchar @@ -51,6 +51,7 @@ uchar.h: uchar.in.h $(top_builddir)/config.status $(CXXDEFS_H) -e 's/@''GNULIB_C32ISSPACE''@/$(GNULIB_C32ISSPACE)/g' \ -e 's/@''GNULIB_C32ISUPPER''@/$(GNULIB_C32ISUPPER)/g' \ -e 's/@''GNULIB_C32ISXDIGIT''@/$(GNULIB_C32ISXDIGIT)/g' \ + -e 's/@''GNULIB_C32TOLOWER''@/$(GNULIB_C32TOLOWER)/g' \ -e 's/@''GNULIB_C32RTOMB''@/$(GNULIB_C32RTOMB)/g' \ -e 's/@''GNULIB_C32SNRTOMBS''@/$(GNULIB_C32SNRTOMBS)/g' \ -e 's/@''GNULIB_C32SRTOMBS''@/$(GNULIB_C32SRTOMBS)/g' \ -- 2.39.5