lib/c32is-impl.h

   1 /* Test whether a 32-bit wide character belongs to a specific character class.
   2    Copyright (C) 2020-2024 Free Software Foundation, Inc.
   3
   4    This file is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU Lesser General Public License as
   6    published by the Free Software Foundation; either version 2.1 of the
   7    License, or (at your option) any later version.
   8
   9    This file is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 /* Written by Bruno Haible <bruno@clisp.org>, 2020.  */
  18
  19 #include <wchar.h>
  20 #include <wctype.h>
  21
  22 #ifdef __CYGWIN__
  23 # include <cygwin/version.h>
  24 #endif
  25
  26 #if GNULIB_defined_mbstate_t
  27 # include "localcharset.h"
  28 # include "streq.h"
  29 #endif
  30
  31 #if GL_CHAR32_T_IS_UNICODE
  32 # include "lc-charset-unicode.h"
  33 #endif
  34
  35 #include "unictype.h"
  36
  37 #if _GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t
  38 _GL_EXTERN_INLINE
  39 #endif
  40 int
  41 FUNC (wint_t wc)
  42 {
  43   /* The char32_t encoding of a multibyte character is defined by the way
  44      mbrtoc32() is defined.  */
  45
  46 #if GNULIB_defined_mbstate_t            /* AIX, IRIX */
  47   /* mbrtoc32() is defined on top of mbtowc() for the non-UTF-8 locales
  48      and directly for the UTF-8 locales.  */
  49   if (wc != WEOF)
  50     {
  51       const char *encoding = locale_charset ();
  52       if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
  53         return UCS_FUNC (wc);
  54       else
  55         return WCHAR_FUNC (wc);
  56     }
  57   else
  58     return 0;
  59
  60 #elif HAVE_WORKING_MBRTOC32 && HAVE_WORKING_C32RTOMB /* glibc, Android */
  61   /* mbrtoc32() is essentially defined by the system libc.  */
  62
  63 # if _GL_WCHAR_T_IS_UCS4
  64   /* The char32_t encoding of a multibyte character is known to be the same as
  65      the wchar_t encoding.  */
  66   return WCHAR_FUNC (wc);
  67 # else
  68   /* The char32_t encoding of a multibyte character is known to be UCS-4,
  69      different from the wchar_t encoding.  */
  70   if (wc != WEOF)
  71     return UCS_FUNC (wc);
  72   else
  73     return 0;
  74 # endif
  75
  76 #elif _GL_SMALL_WCHAR_T                 /* Cygwin, mingw, MSVC */
  77   /* The wchar_t encoding is UTF-16.
  78      The char32_t encoding is UCS-4.  */
  79
  80 # if defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007
  81   /* As an extension to POSIX, the iswalnum() function of Cygwin >= 1.7
  82      supports also wc arguments outside the Unicode BMP, that is, outside
  83      the 'wchar_t' range.  See
  84      <https://lists.gnu.org/archive/html/bug-gnulib/2011-02/msg00019.html>
  85      = <https://cygwin.com/ml/cygwin/2011-02/msg00044.html>.  */
  86   return WCHAR_FUNC (wc);
  87 # else
  88   if (wc == WEOF || wc == (wchar_t) wc)
  89     /* wc is in the range for the isw* functions.  */
  90     return WCHAR_FUNC (wc);
  91   else
  92     return UCS_FUNC (wc);
  93 # endif
  94
  95 #else /* macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Minix, Android */
  96   /* char32_t and wchar_t are equivalent.  */
  97   static_assert (sizeof (char32_t) == sizeof (wchar_t));
  98
  99 # if GL_CHAR32_T_IS_UNICODE && GL_CHAR32_T_VS_WCHAR_T_NEEDS_CONVERSION
 100   return UCS_FUNC (wc);
 101 # else
 102   return WCHAR_FUNC (wc);
 103 # endif
 104 #endif
 105 }