lib/c32rtomb.c

   1 /* Convert 32-bit wide character to multibyte character.
   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 3 of the License, or
   7    (at your option) 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
  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 /* Specification.  */
  22 #include <uchar.h>
  23
  24 #include <errno.h>
  25 #include <wchar.h>
  26
  27 #include "attribute.h" /* FALLTHROUGH */
  28 #include "localcharset.h"
  29 #include "streq.h"
  30
  31 size_t
  32 c32rtomb (char *s, char32_t wc, mbstate_t *ps)
  33 #undef c32rtomb
  34 {
  35 #if HAVE_WORKING_MBRTOC32
  36
  37 # if C32RTOMB_RETVAL_BUG
  38   if (s == NULL)
  39     /* We know the NUL wide character corresponds to the NUL character.  */
  40     return 1;
  41 # endif
  42
  43   return c32rtomb (s, wc, ps);
  44
  45 #elif _GL_LARGE_CHAR32_T
  46
  47   if (s == NULL)
  48     return wcrtomb (NULL, 0, ps);
  49   else
  50     {
  51       /* Special-case all encodings that may produce wide character values
  52          > WCHAR_MAX.  */
  53       const char *encoding = locale_charset ();
  54       if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
  55         {
  56           /* Special-case the UTF-8 encoding.  Assume that the wide-character
  57              encoding in a UTF-8 locale is UCS-2 or, equivalently, UTF-16.  */
  58           if (wc < 0x80)
  59             {
  60               s[0] = (unsigned char) wc;
  61               return 1;
  62             }
  63           else
  64             {
  65               int count;
  66
  67               if (wc < 0x800)
  68                 count = 2;
  69               else if (wc < 0x10000)
  70                 {
  71                   if (wc < 0xd800 || wc >= 0xe000)
  72                     count = 3;
  73                   else
  74                     {
  75                       errno = EILSEQ;
  76                       return (size_t)(-1);
  77                     }
  78                 }
  79               else if (wc < 0x110000)
  80                 count = 4;
  81               else
  82                 {
  83                   errno = EILSEQ;
  84                   return (size_t)(-1);
  85                 }
  86
  87               switch (count) /* note: code falls through cases! */
  88                 {
  89                 case 4: s[3] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x10000;
  90                   FALLTHROUGH;
  91                 case 3: s[2] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0x800;
  92                   FALLTHROUGH;
  93                 case 2: s[1] = 0x80 | (wc & 0x3f); wc = wc >> 6; wc |= 0xc0;
  94               /*case 1:*/ s[0] = wc;
  95                 }
  96               return count;
  97             }
  98         }
  99       else
 100         {
 101           if ((wchar_t) wc == wc)
 102             return wcrtomb (s, (wchar_t) wc, ps);
 103           else
 104             {
 105               errno = EILSEQ;
 106               return (size_t)(-1);
 107             }
 108         }
 109     }
 110
 111 #else
 112
 113   /* char32_t and wchar_t are equivalent.  */
 114   return wcrtomb (s, (wchar_t) wc, ps);
 115
 116 #endif
 117 }