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
|
/*
* Copyright (c) 2012 Giovanni Campagna <scampa.giovanni@gmail.com>
*
* The Control Center is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*
* The Control Center 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 General Public License
* for more details.
*
* You should have received a copy of the GNU General Public License along
* with the Control Center; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
*/
#include "config.h"
#include <string.h>
#include "cc-util.h"
/* Combining diacritical mark?
* Basic range: [0x0300,0x036F]
* Supplement: [0x1DC0,0x1DFF]
* For Symbols: [0x20D0,0x20FF]
* Half marks: [0xFE20,0xFE2F]
*/
#define IS_CDM_UCS4(c) (((c) >= 0x0300 && (c) <= 0x036F) || \
((c) >= 0x1DC0 && (c) <= 0x1DFF) || \
((c) >= 0x20D0 && (c) <= 0x20FF) || \
((c) >= 0xFE20 && (c) <= 0xFE2F))
/* Copied from tracker/src/libtracker-fts/tracker-parser-glib.c under the GPL
* And then from gnome-shell/src/shell-util.c
*
* Originally written by Aleksander Morgado <aleksander@gnu.org>
*/
char *
cc_util_normalize_casefold_and_unaccent (const char *str)
{
char *normalized, *tmp;
int i = 0, j = 0, ilen;
if (str == NULL)
return NULL;
normalized = g_utf8_normalize (str, -1, G_NORMALIZE_NFKD);
tmp = g_utf8_casefold (normalized, -1);
g_free (normalized);
ilen = strlen (tmp);
while (i < ilen)
{
gunichar unichar;
gchar *next_utf8;
gint utf8_len;
/* Get next character of the word as UCS4 */
unichar = g_utf8_get_char_validated (&tmp[i], -1);
/* Invalid UTF-8 character or end of original string. */
if (unichar == (gunichar) -1 ||
unichar == (gunichar) -2)
{
break;
}
/* Find next UTF-8 character */
next_utf8 = g_utf8_next_char (&tmp[i]);
utf8_len = next_utf8 - &tmp[i];
if (IS_CDM_UCS4 ((guint32) unichar))
{
/* If the given unichar is a combining diacritical mark,
* just update the original index, not the output one */
i += utf8_len;
continue;
}
/* If already found a previous combining
* diacritical mark, indexes are different so
* need to copy characters. As output and input
* buffers may overlap, need to use memmove
* instead of memcpy */
if (i != j)
{
memmove (&tmp[j], &tmp[i], utf8_len);
}
/* Update both indexes */
i += utf8_len;
j += utf8_len;
}
/* Force proper string end */
tmp[j] = '\0';
return tmp;
}
|
