lib/unistr/u8-strmbtouc.c

   1 /* Look at first character in UTF-8 string.
   2    Copyright (C) 1999-2000, 2002, 2006-2007, 2009-2021 Free Software
   3    Foundation, Inc.
   4    Written by Bruno Haible <bruno@clisp.org>, 2002.
   5
   6    This program is free software: you can redistribute it and/or modify it
   7    under the terms of the GNU Lesser General Public License as published
   8    by the Free Software Foundation; either version 3 of the License, or
   9    (at your option) any later version.
  10
  11    This program is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public License
  17    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  18
  19 #include <config.h>
  20
  21 /* Specification.  */
  22 #include "unistr.h"
  23
  24 int
  25 u8_strmbtouc (ucs4_t *puc, const uint8_t *s)
  26 {
  27   /* Keep in sync with unistr.h and u8-mbtouc-aux.c.  */
  28   uint8_t c = *s;
  29
  30   if (c < 0x80)
  31     {
  32       *puc = c;
  33       return (c != 0 ? 1 : 0);
  34     }
  35   if (c >= 0xc2)
  36     {
  37       if (c < 0xe0)
  38         {
  39           if ((s[1] ^ 0x80) < 0x40)
  40             {
  41               *puc = ((unsigned int) (c & 0x1f) << 6)
  42                      | (unsigned int) (s[1] ^ 0x80);
  43               return 2;
  44             }
  45         }
  46       else if (c < 0xf0)
  47         {
  48           if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  49               && (c >= 0xe1 || s[1] >= 0xa0)
  50               && (c != 0xed || s[1] < 0xa0))
  51             {
  52               *puc = ((unsigned int) (c & 0x0f) << 12)
  53                      | ((unsigned int) (s[1] ^ 0x80) << 6)
  54                      | (unsigned int) (s[2] ^ 0x80);
  55               return 3;
  56             }
  57         }
  58       else if (c < 0xf8)
  59         {
  60           if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  61               && (s[3] ^ 0x80) < 0x40
  62               && (c >= 0xf1 || s[1] >= 0x90)
  63               && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)))
  64             {
  65               *puc = ((unsigned int) (c & 0x07) << 18)
  66                      | ((unsigned int) (s[1] ^ 0x80) << 12)
  67                      | ((unsigned int) (s[2] ^ 0x80) << 6)
  68                      | (unsigned int) (s[3] ^ 0x80);
  69               return 4;
  70             }
  71         }
  72     }
  73   /* invalid or incomplete multibyte character */
  74   return -1;
  75 }