lib/c32is-impl.h

   1 /* Test whether a 32-bit wide character belongs to a specific character class.
   2    Copyright (C) 2020 Free Software Foundation, Inc.
   3
   4    This program is free software; you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation; either version 2, or (at your option)
   7    any later version.
   8
   9    This program 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 General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License along
  15    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 #include "unictype.h"
  32 #include "verify.h"
  33
  34 int
  35 FUNC (wint_t wc)
  36 {
  37   /* The char32_t encoding of a multibyte character is defined by the way
  38      mbrtoc32() is defined.  */
  39
  40 #if GNULIB_defined_mbstate_t            /* AIX, IRIX */
  41   /* mbrtoc32() is defined on top of mbtowc() for the non-UTF-8 locales
  42      and directly for the UTF-8 locales.  */
  43   if (wc != WEOF)
  44     {
  45       const char *encoding = locale_charset ();
  46       if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
  47         return UCS_FUNC (wc);
  48       else
  49         return WCHAR_FUNC (wc);
  50     }
  51   else
  52     return 0;
  53
  54 #elif HAVE_WORKING_MBRTOC32             /* glibc */
  55   /* mbrtoc32() is essentially defined by the system libc.  */
  56
  57 # if defined __GLIBC__
  58   /* The char32_t encoding of a multibyte character is known to be the same as
  59      the wchar_t encoding.  */
  60   return WCHAR_FUNC (wc);
  61 # else
  62   /* The char32_t encoding of a multibyte character is known to be UCS-4,
  63      different from the the wchar_t encoding.  */
  64   if (wc != WEOF)
  65     return UCS_FUNC (wc);
  66   else
  67     return 0;
  68 # endif
  69
  70 #elif _GL_LARGE_CHAR32_T                /* Cygwin, mingw, MSVC */
  71   /* The wchar_t encoding is UTF-16.
  72      The char32_t encoding is UCS-4.  */
  73
  74 # if defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007
  75   /* As an extension to POSIX, the iswalnum() function of Cygwin >= 1.7
  76      supports also wc arguments outside the Unicode BMP, that is, outside
  77      the 'wchar_t' range.  See
  78      <https://lists.gnu.org/archive/html/bug-gnulib/2011-02/msg00019.html>
  79      = <https://cygwin.com/ml/cygwin/2011-02/msg00044.html>.  */
  80   return WCHAR_FUNC (wc);
  81 # else
  82   if (wc == WEOF || wc == (wchar_t) wc)
  83     /* wc is in the range for the isw* functions.  */
  84     return WCHAR_FUNC (wc);
  85   else
  86     return UCS_FUNC (wc);
  87 # endif
  88
  89 #else /* macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Minix, Android */
  90   /* char32_t and wchar_t are equivalent.  */
  91   verify (sizeof (char32_t) == sizeof (wchar_t));
  92
  93   return WCHAR_FUNC (wc);
  94 #endif
  95 }