lib/libc/string/strcoll.c

   1 /*
   2  * Copyright 2010 Nexenta Systems, Inc.  All rights reserved.
   3  * Copyright (c) 1995 Alex Tatmanjants <alex@elvisti.kiev.ua>
   4  *              at Electronni Visti IA, Kiev, Ukraine.
   5  *                      All rights reserved.
   6  *
   7  * Copyright (c) 2011 The FreeBSD Foundation
   8  * All rights reserved.
   9  * Portions of this software were developed by David Chisnall
  10  * under sponsorship from the FreeBSD Foundation.
  11  *
  12  * Redistribution and use in source and binary forms, with or without
  13  * modification, are permitted provided that the following conditions
  14  * are met:
  15  * 1. Redistributions of source code must retain the above copyright
  16  *    notice, this list of conditions and the following disclaimer.
  17  * 2. Redistributions in binary form must reproduce the above copyright
  18  *    notice, this list of conditions and the following disclaimer in the
  19  *    documentation and/or other materials provided with the distribution.
  20  *
  21  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND
  22  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  23  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  24  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE LIABLE
  25  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  26  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  27  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  28  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  29  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  30  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  31  * SUCH DAMAGE.
  32  */
  33
  34 #include <stdlib.h>
  35 #include <string.h>
  36 #include <errno.h>
  37 #include <wchar.h>
  38 #include "collate.h"
  39
  40
  41 /*
  42  * In order to properly handle multibyte locales, its easiest to just
  43  * convert to wide characters and then use wcscoll.  However if an
  44  * error occurs, we gracefully fall back to simple strcmp.  Caller
  45  * should check errno.
  46  */
  47 int
  48 strcoll_l(const char *s, const char *s2, locale_t locale)
  49 {
  50         int ret;
  51         wchar_t *t1 = NULL, *t2 = NULL;
  52         wchar_t *w1 = NULL, *w2 = NULL;
  53         const char *cs1, *cs2;
  54         mbstate_t mbs1;
  55         mbstate_t mbs2;
  56         size_t sz1, sz2;
  57
  58         memset(&mbs1, 0, sizeof(mbstate_t));
  59         memset(&mbs2, 0, sizeof(mbstate_t));
  60
  61         /*
  62          * The mbsrtowcs_l function can set the src pointer to null upon
  63          * failure, so it should act on a copy to avoid:
  64          *   - sending null pointer to strcmp
  65          *   - having strcoll/strcoll_l change *s or *s2 to null
  66          */
  67         cs1 = s;
  68         cs2 = s2;
  69
  70         FIX_LOCALE(locale);
  71         struct xlocale_collate *table =
  72                 (struct xlocale_collate*)locale->components[XLC_COLLATE];
  73
  74         if (table->__collate_load_error)
  75                 goto error;
  76
  77         sz1 = strlen(s) + 1;
  78         sz2 = strlen(s2) + 1;
  79
  80         /*
  81          * Simple assumption: conversion to wide format is strictly
  82          * reducing, i.e. a single byte (or multibyte character)
  83          * cannot result in multiple wide characters.
  84          */
  85         if ((t1 = malloc(sz1 * sizeof (wchar_t))) == NULL)
  86                 goto error;
  87         w1 = t1;
  88         if ((t2 = malloc(sz2 * sizeof (wchar_t))) == NULL)
  89                 goto error;
  90         w2 = t2;
  91
  92         if ((mbsrtowcs_l(w1, &cs1, sz1, &mbs1, locale)) == (size_t)-1)
  93                 goto error;
  94
  95         if ((mbsrtowcs_l(w2, &cs2, sz2, &mbs2, locale)) == (size_t)-1)
  96                 goto error;
  97
  98         ret = wcscoll_l(w1, w2, locale);
  99         if (t1)
 100                 free(t1);
 101         if (t2)
 102                 free(t2);
 103
 104         return (ret);
 105
 106 error:
 107         if (t1)
 108                 free(t1);
 109         if (t2)
 110                 free(t2);
 111         return (strcmp(s, s2));
 112 }
 113
 114 int
 115 strcoll(const char *s, const char *s2)
 116 {
 117         return strcoll_l(s, s2, __get_locale());
 118 }
 119