1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
/* gunicollate.c - Collation
*
* Copyright 2001 Red Hat, Inc.
*
* The Gnome Library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public License as
* published by the Free Software Foundation; either version 2 of the
* License, or (at your option) any later version.
*
* The Gnome Library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with the Gnome Library; see the file COPYING.LIB. If not,
* write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 02111-1307, USA.
*/
#include <locale.h>
#include <string.h>
#ifdef __STDC_ISO_10646__
#include <wchar.h>
#endif
#include "glib.h"
extern gunichar *_g_utf8_normalize_wc (const gchar *str,
GNormalizeMode mode);
/**
* g_utf8_collate:
* @str1: a UTF-8 encoded string
* @str2: a UTF-8 encoded string
*
* Compares two strings for ordering using the linguistically
* correct rules for the current locale. When sorting a large
* number of strings, it will be significantly faster to
* obtain collation keys with g_utf8_collate_key() and
* compare the keys with strcmp() when sorting instead of
* sorting the original strings.
*
* Return value: -1 if str1 compares before str2, 0 if they
* compare equal, 1 if str1 compares after str2.
**/
gint
g_utf8_collate (const gchar *str1,
const gchar *str2)
{
gint result;
#ifdef __STDC_ISO_10646__
gunichar *str1_norm = _g_utf8_normalize_wc (str1, G_NORMALIZE_ALL_COMPOSE);
gunichar *str2_norm = _g_utf8_normalize_wc (str2, G_NORMALIZE_ALL_COMPOSE);
result = wcscoll ((wchar_t *)str1_norm, (wchar_t *)str2_norm);
g_free (str1_norm);
g_free (str2_norm);
#else /* !__STDC_ISO_10646__ */
const gchar *charset;
gchar *str1_norm = g_utf8_normalize (str1, G_NORMALIZE_ALL_COMPOSE);
gchar *str2_norm = g_utf8_normalize (str2, G_NORMALIZE_ALL_COMPOSE);
if (g_get_charset (&charset))
{
result = strcoll (str1_norm, str2_norm);
}
else
{
gchar *str1_locale = g_convert (str1_norm, -1, "UTF-8", charset, NULL, NULL, NULL);
gchar *str2_locale = g_convert (str2_norm, -1, "UTF-8", charset, NULL, NULL, NULL);
if (str1_locale && str2_locale)
result = strcoll (str1_locale, str2_locale);
else if (str1_locale)
result = -1;
else if (str2_locale)
result = 1;
else
result = strcmp (str1_norm, str2_norm);
g_free (str1_locale);
g_free (str2_locale);
}
g_free (str1_norm);
g_free (str2_norm);
#endif /* __STDC_ISO_10646__ */
return result;
}
#ifdef __STDC_ISO_10646__
/* We need UTF-8 encoding of numbers to encode the weights if
* we are using wcsxfrm. However, we aren't encoding Unicode
* characters, so we can't simply use g_unichar_to_utf8.
*
* The following routine is taken (with modification) from GNU
* libc's strxfrm routine:
*
* Copyright (C) 1995-1999,2000,2001 Free Software Foundation, Inc.
* Written by Ulrich Drepper <drepper@cygnus.com>, 1995.
*/
static inline int
utf8_encode (char *buf, wchar_t val)
{
int retval;
if (val < 0x80)
{
if (buf)
*buf++ = (char) val;
retval = 1;
}
else
{
int step;
for (step = 2; step < 6; ++step)
if ((val & (~(guint32)0 << (5 * step + 1))) == 0)
break;
retval = step;
if (buf)
{
*buf = (unsigned char) (~0xff >> step);
--step;
do
{
buf[step] = 0x80 | (val & 0x3f);
val >>= 6;
}
while (--step > 0);
*buf |= val;
}
}
return retval;
}
#endif /* __STDC_ISO_10646__ */
/**
* g_utf8_collate_key:
* @str: a UTF-8 encoded string.
*
* Converts a string into a collation key that can be compared
* with other collation keys using strcmp(). The results of
* comparing the collation keys of two strings with strcmp()
* will always be the same as comparing the two original
* keys with g_utf8_collate().
*
* Return value: a newly allocated string. This string should
* be freed with g_free when you are done with it.
**/
gchar *
g_utf8_collate_key (const gchar *str)
{
gchar *result;
size_t len;
#ifdef __STDC_ISO_10646__
gunichar *str_norm = _g_utf8_normalize_wc (str, G_NORMALIZE_ALL_COMPOSE);
wchar_t *result_wc;
size_t i;
size_t result_len = 0;
setlocale (LC_COLLATE, "");
len = wcsxfrm (NULL, (wchar_t *)str_norm, 0);
result_wc = g_new (wchar_t, len + 1);
wcsxfrm (result_wc, (wchar_t *)str_norm, len + 1);
for (i=0; i < len; i++)
result_len += utf8_encode (NULL, result_wc[i]);
result = g_malloc (result_len + 1);
result_len = 0;
for (i=0; i < len; i++)
result_len += utf8_encode (result + result_len, result_wc[i]);
result[result_len] = '\0';
g_free (result_wc);
g_free (str_norm);
return result;
#else /* !__STDC_ISO_10646__ */
const gchar *charset;
gchar *str_norm = g_utf8_normalize (str, G_NORMALIZE_ALL_COMPOSE);
if (g_get_charset (&charset))
{
len = strxfrm (NULL, str_norm, 0);
result = g_malloc (len + 1);
strxfrm (result, str_norm, len + 1);
}
else
{
gchar *str_locale = g_convert (str_norm, -1, "UTF-8", charset, NULL, NULL, NULL);
if (str_locale)
{
len = strxfrm (NULL, str_locale, 0);
result = g_malloc (len + 2);
result[0] = 'A';
strxfrm (result + 1, str_locale, len + 1);
g_free (str_locale);
}
else
{
len = strlen (str_norm);
result = g_malloc (len + 2);
result[0] = 'B';
memcpy (result + 1, str_norm, len);
result[len+1] = '\0';
}
}
g_free (str_norm);
#endif /* __STDC_ISO_10646__ */
return result;
}
|
