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