lib/unistr/u8-prev.c

   1 /* Iterate over previous character in UTF-8 string.
   2    Copyright (C) 2002, 2006-2007, 2009-2010 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 <http://www.gnu.org/licenses/>.  */
  17
  18 #include <config.h>
  19
  20 /* Specification.  */
  21 #include "unistr.h"
  22
  23 const uint8_t *
  24 u8_prev (ucs4_t *puc, const uint8_t *s, const uint8_t *start)
  25 {
  26   /* Keep in sync with unistr.h and utf8-ucs4.c.  */
  27   if (s != start)
  28     {
  29       uint8_t c_1 = s[-1];
  30
  31       if (c_1 < 0x80)
  32         {
  33           *puc = c_1;
  34           return s - 1;
  35         }
  36 #if CONFIG_UNICODE_SAFETY
  37       if ((c_1 ^ 0x80) < 0x40)
  38 #endif
  39         if (s - 1 != start)
  40           {
  41             uint8_t c_2 = s[-2];
  42
  43             if (c_2 >= 0xc2 && c_2 < 0xe0)
  44               {
  45                 *puc = ((unsigned int) (c_2 & 0x1f) << 6)
  46                        | (unsigned int) (c_1 ^ 0x80);
  47                 return s - 2;
  48               }
  49 #if CONFIG_UNICODE_SAFETY
  50             if ((c_2 ^ 0x80) < 0x40)
  51 #endif
  52               if (s - 2 != start)
  53                 {
  54                   uint8_t c_3 = s[-3];
  55
  56                   if (c_3 >= 0xe0 && c_3 < 0xf0
  57 #if CONFIG_UNICODE_SAFETY
  58                       && (c_3 >= 0xe1 || c_2 >= 0xa0)
  59                       && (c_3 != 0xed || c_2 < 0xa0)
  60 #endif
  61                      )
  62                     {
  63                       *puc = ((unsigned int) (c_3 & 0x0f) << 12)
  64                              | ((unsigned int) (c_2 ^ 0x80) << 6)
  65                              | (unsigned int) (c_1 ^ 0x80);
  66                       return s - 3;
  67                     }
  68 #if CONFIG_UNICODE_SAFETY
  69                   if ((c_3 ^ 0x80) < 0x40)
  70 #endif
  71                     if (s - 3 != start)
  72                       {
  73                         uint8_t c_4 = s[-4];
  74
  75                         if (c_4 >= 0xf0 && c_4 < 0xf8
  76 #if CONFIG_UNICODE_SAFETY
  77                             && (c_4 >= 0xf1 || c_3 >= 0x90)
  78                             && (c_4 < 0xf4 || (c_4 == 0xf4 && c_3 < 0x90))
  79 #endif
  80                            )
  81                           {
  82                             *puc = ((unsigned int) (c_4 & 0x07) << 18)
  83                                    | ((unsigned int) (c_3 ^ 0x80) << 12)
  84                                    | ((unsigned int) (c_2 ^ 0x80) << 6)
  85                                    | (unsigned int) (c_1 ^ 0x80);
  86                             return s - 4;
  87                           }
  88                       }
  89                 }
  90           }
  91     }
  92   return NULL;
  93 }