lib/unistr/u8-mblen.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_mblen (const uint8_t *s, size_t n)
  26 {
  27   if (n > 0)
  28     {
  29       /* Keep in sync with unistr.h and u8-mbtouc-aux.c.  */
  30       uint8_t c = *s;
  31
  32       if (c < 0x80)
  33         return (c != 0 ? 1 : 0);
  34       if (c >= 0xc2)
  35         {
  36           if (c < 0xe0)
  37             {
  38               if (n >= 2
  39                   && (s[1] ^ 0x80) < 0x40)
  40                 return 2;
  41             }
  42           else if (c < 0xf0)
  43             {
  44               if (n >= 3
  45                   && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  46                   && (c >= 0xe1 || s[1] >= 0xa0)
  47                   && (c != 0xed || s[1] < 0xa0))
  48                 return 3;
  49             }
  50           else if (c < 0xf8)
  51             {
  52               if (n >= 4
  53                   && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  54                   && (s[3] ^ 0x80) < 0x40
  55                   && (c >= 0xf1 || s[1] >= 0x90)
  56                   && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)))
  57                 return 4;
  58             }
  59         }
  60     }
  61   /* invalid or incomplete multibyte character */
  62   return -1;
  63 }