lib/btoc32.c

   1 /* Convert unibyte character to 32-bit wide character.
   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 <config.h>
  20
  21 #define IN_BTOC32
  22 /* Specification.  */
  23 #include <uchar.h>
  24
  25 #include <stdio.h>
  26 #include <string.h>
  27 #include <wchar.h>
  28
  29 #if GL_CHAR32_T_IS_UNICODE
  30 # include "lc-charset-unicode.h"
  31 #endif
  32
  33 #if _GL_WCHAR_T_IS_UCS4
  34 _GL_EXTERN_INLINE
  35 #endif
  36 wint_t
  37 btoc32 (int c)
  38 {
  39 #if HAVE_WORKING_MBRTOC32 && !_GL_WCHAR_T_IS_UCS4
  40   /* The char32_t encoding of a multibyte character may be different than its
  41      wchar_t encoding.  */
  42   if (c != EOF)
  43     {
  44       mbstate_t state;
  45       char s[1];
  46       char32_t wc;
  47
  48       mbszero (&state);
  49       s[0] = (unsigned char) c;
  50       if (mbrtoc32 (&wc, s, 1, &state) <= 1)
  51         return wc;
  52     }
  53   return WEOF;
  54 #else
  55   /* In all known locale encodings, unibyte characters correspond only to
  56      characters in the BMP.  */
  57   wint_t wc = btowc (c);
  58 # if GL_CHAR32_T_IS_UNICODE && GL_CHAR32_T_VS_WCHAR_T_NEEDS_CONVERSION
  59   if (wc != WEOF && wc != 0)
  60     {
  61       wc = locale_encoding_to_unicode (wc);
  62       if (wc == 0)
  63         return WEOF;
  64     }
  65 # endif
  66   return wc;
  67 #endif
  68 }