gnu/dist/gettext/gettext-tools/lib/utf16-ucs4.h

   1 /* Conversion UTF-16 to UCS-4.
   2    Copyright (C) 2001-2002 Free Software Foundation, Inc.
   3    Written by Bruno Haible <haible@clisp.cons.org>, 2001.
   4
   5 This program is free software; you can redistribute it and/or modify
   6 it under the terms of the GNU General Public License as published by
   7 the Free Software Foundation; either version 2, or (at your option)
   8 any later version.
   9
  10 This program is distributed in the hope that it will be useful,
  11 but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13 GNU General Public License for more details.
  14
  15 You should have received a copy of the GNU General Public License
  16 along with this program; if not, write to the Free Software
  17 Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
  18
  19
  20 #include <stddef.h>
  21
  22 /* Return the length (number of units) of the first character in S, putting
  23    its 'ucs4_t' representation in *PUC.  */
  24 static int
  25 u16_mbtouc_aux (unsigned int *puc, const unsigned short *s, size_t n)
  26 {
  27   unsigned short c = *s;
  28
  29   if (c < 0xdc00)
  30     {
  31       if (n >= 2)
  32         {
  33           if (s[1] >= 0xdc00 && s[1] < 0xe000)
  34             {
  35               *puc = 0x10000 + ((c - 0xd800) << 10) + (s[1] - 0xdc00);
  36               return 2;
  37             }
  38           /* invalid multibyte character */
  39         }
  40       else
  41         {
  42           /* incomplete multibyte character */
  43           *puc = 0xfffd;
  44           return n;
  45         }
  46     }
  47   /* invalid multibyte character */
  48   *puc = 0xfffd;
  49   return 1;
  50 }
  51 static inline int
  52 u16_mbtouc (unsigned int *puc, const unsigned short *s, size_t n)
  53 {
  54   unsigned short c = *s;
  55
  56   if (c < 0xd800 || c >= 0xe000)
  57     {
  58       *puc = c;
  59       return 1;
  60     }
  61   else
  62     return u16_mbtouc_aux (puc, s, n);
  63 }