lib/unistr/u8-check.c

   1 /* Check UTF-8 string.
   2    Copyright (C) 2002, 2006-2007, 2009-2021 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2002.
   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 const uint8_t *
  24 u8_check (const uint8_t *s, size_t n)
  25 {
  26   const uint8_t *s_end = s + n;
  27
  28   while (s < s_end)
  29     {
  30       /* Keep in sync with unistr.h and u8-mbtouc-aux.c.  */
  31       uint8_t c = *s;
  32
  33       if (c < 0x80)
  34         {
  35           s++;
  36           continue;
  37         }
  38       if (c >= 0xc2)
  39         {
  40           if (c < 0xe0)
  41             {
  42               if (s + 2 <= s_end
  43                   && (s[1] ^ 0x80) < 0x40)
  44                 {
  45                   s += 2;
  46                   continue;
  47                 }
  48             }
  49           else if (c < 0xf0)
  50             {
  51               if (s + 3 <= s_end
  52                   && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  53                   && (c >= 0xe1 || s[1] >= 0xa0)
  54                   && (c != 0xed || s[1] < 0xa0))
  55                 {
  56                   s += 3;
  57                   continue;
  58                 }
  59             }
  60           else if (c < 0xf8)
  61             {
  62               if (s + 4 <= s_end
  63                   && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
  64                   && (s[3] ^ 0x80) < 0x40
  65                   && (c >= 0xf1 || s[1] >= 0x90)
  66                   && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)))
  67                 {
  68                   s += 4;
  69                   continue;
  70                 }
  71             }
  72         }
  73       /* invalid or incomplete multibyte character */
  74       return s;
  75     }
  76   return NULL;
  77 }