lib/unistr/u16-mbtoucr.c

   1 /* Look at first character in UTF-16 string, returning an error code.
   2    Copyright (C) 1999-2002, 2006-2007, 2009-2021 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2001.
   4
   5    This program is free software: you can redistribute it and/or modify it
   6    under the terms of the GNU Lesser General Public License as published
   7    by the Free Software Foundation; either version 3 of the License, or
   8    (at your option) 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 GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public License
  16    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  17
  18 #include <config.h>
  19
  20 /* Specification.  */
  21 #include "unistr.h"
  22
  23 int
  24 u16_mbtoucr (ucs4_t *puc, const uint16_t *s, size_t n)
  25 {
  26   uint16_t c = *s;
  27
  28   if (c < 0xd800 || c >= 0xe000)
  29     {
  30       *puc = c;
  31       return 1;
  32     }
  33   if (c < 0xdc00)
  34     {
  35       if (n >= 2)
  36         {
  37           if (s[1] >= 0xdc00 && s[1] < 0xe000)
  38             {
  39               *puc = 0x10000 + ((c - 0xd800) << 10) + (s[1] - 0xdc00);
  40               return 2;
  41             }
  42           /* invalid multibyte character */
  43         }
  44       else
  45         {
  46           /* incomplete multibyte character */
  47           *puc = 0xfffd;
  48           return -2;
  49         }
  50     }
  51   /* invalid multibyte character */
  52   *puc = 0xfffd;
  53   return -1;
  54 }