Line data    Source code

       1             : /* mbschr.c - strchr(3) that handles multibyte characters. */
       2             : 
       3             : /* Copyright (C) 2002 Free Software Foundation, Inc.
       4             : 
       5             :    This file is part of GNU Bash, the Bourne Again SHell.
       6             : 
       7             :    Bash is free software: you can redistribute it and/or modify
       8             :    it under the terms of the GNU General Public License as published by
       9             :    the Free Software Foundation, either version 3 of the License, or
      10             :    (at your option) any later version.
      11             : 
      12             :    Bash is distributed in the hope that it will be useful,
      13             :    but WITHOUT ANY WARRANTY; without even the implied warranty of
      14             :    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
      15             :    GNU General Public License for more details.
      16             : 
      17             :    You should have received a copy of the GNU General Public License
      18             :    along with Bash.  If not, see <http://www.gnu.org/licenses/>.
      19             : */
      20             : 
      21             : #include <config.h>
      22             : 
      23             : #ifdef HAVE_STDLIB_H
      24             : #  include <stdlib.h>
      25             : #endif
      26             : 
      27             : #include "bashansi.h"
      28             : #include "shmbutil.h"
      29             : 
      30             : extern int locale_mb_cur_max;
      31             : 
      32             : #undef mbschr
      33             : 
      34             : /* In some locales, the non-first byte of some multibyte characters have
      35             :    the same value as some ascii character.  Faced with these strings, a
      36             :    legacy strchr() might return the wrong value. */
      37             : 
      38             : char *
      39             : #if defined (PROTOTYPES)
      40  7210255792 : mbschr (const char *s, int c)
      41             : #else
      42             : mbschr (s, c)
      43             :      const char *s;
      44             :      int c;
      45             : #endif
      46             : {
      47             : #if HANDLE_MULTIBYTE
      48  7210255792 :   char *pos;
      49  7210255792 :   mbstate_t state;
      50  7210255792 :   size_t strlength, mblength;
      51             : 
      52             :   /* The locale encodings with said weird property are BIG5, BIG5-HKSCS,
      53             :      GBK, GB18030, SHIFT_JIS, and JOHAB.  They exhibit the problem only
      54             :      when c >= 0x30.  We can therefore use the faster bytewise search if
      55             :      c <= 0x30. */
      56  7210255792 :   if ((unsigned char)c >= '0' && locale_mb_cur_max > 1)
      57             :     {
      58  5932727744 :       pos = (char *)s;
      59  5932727744 :       memset (&state, '\0', sizeof(mbstate_t));
      60  5932727744 :       strlength = strlen (s);
      61             : 
      62 63462780293 :       while (strlength > 0)
      63             :         {
      64 >11530*10^7 :           if (is_basic (*pos))
      65             :             mblength = 1;
      66             :           else
      67             :             {
      68  5630403020 :               mblength = mbrlen (pos, strlength, &state);
      69  5630403020 :               if (mblength == (size_t)-2 || mblength == (size_t)-1 || mblength == (size_t)0)
      70             :                 mblength = 1;
      71             :             }
      72             : 
      73 57654104676 :           if (mblength == 1 && c == (unsigned char)*pos)
      74   124052127 :             return pos;
      75             : 
      76 57530052549 :           strlength -= mblength;
      77 57530052549 :           pos += mblength;
      78             :         }
      79             : 
      80             :       return ((char *)NULL);
      81             :     }
      82             :   else
      83             : #endif
      84  1277528048 :   return (strchr (s, c));
      85             : }