blob: d5f3e76085a670bee3c84a168c81dc7d7e9d257f (
plain)
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
|
<?php
/**
* Cantonese (粵語) specific code.
*
* This program 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.
*
* This program 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 this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
* @ingroup Language
*/
/**
* Cantonese (粵語)
*
* @ingroup Language
*/
class LanguageYue extends Language {
/**
* @return bool
*/
function hasWordBreaks() {
return false;
}
/**
* Eventually this should be a word segmentation;
* for now just treat each character as a word.
* @todo FIXME: Only do this for Han characters...
*
* @param string $string
* @return string
*/
function segmentByWord( $string ) {
$reg = "/([\\xc0-\\xff][\\x80-\\xbf]*)/";
$s = self::insertSpace( $string, $reg );
return $s;
}
/**
* @param string $string
* @return string
*/
function normalizeForSearch( $string ) {
// Double-width roman characters
$s = self::convertDoubleWidth( $string );
$s = trim( $s );
$s = parent::normalizeForSearch( $s );
return $s;
}
}
|
