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
|
<?php
/**
* @addtogroup Language
*/
require_once( dirname(__FILE__).'/../LanguageConverter.php' );
require_once( dirname(__FILE__).'/LanguageZh_cn.php' );
class ZhConverter extends LanguageConverter {
function loadDefaultTables() {
require( dirname(__FILE__)."/../../includes/ZhConversion.php" );
$this->mTables = array(
'zh-cn' => new ReplacementArray( $zh2CN ),
'zh-tw' => new ReplacementArray( $zh2TW ),
'zh-sg' => new ReplacementArray( array_merge($zh2CN, $zh2SG) ),
'zh-hk' => new ReplacementArray( array_merge($zh2TW, $zh2HK) ),
'zh' => new ReplacementArray
);
}
function postLoadTables() {
$this->mTables['zh-sg']->merge( $this->mTables['zh-cn'] );
$this->mTables['zh-hk']->merge( $this->mTables['zh-tw'] );
}
/* there shouldn't be any latin text in Chinese conversion, so no need
to mark anything.
$noParse is there for compatibility with LanguageConvert::markNoConversion
*/
function markNoConversion($text, $noParse = false) {
return $text;
}
function convertCategoryKey( $key ) {
return $this->autoConvert( $key, 'zh-cn' );
}
}
/* class that handles both Traditional and Simplified Chinese
right now it only distinguish zh_cn, zh_tw, zh_sg and zh_hk.
*/
class LanguageZh extends LanguageZh_cn {
function __construct() {
global $wgHooks;
parent::__construct();
$this->mConverter = new ZhConverter($this, 'zh',
array('zh', 'zh-cn', 'zh-tw', 'zh-sg', 'zh-hk'),
array('zh'=>'zh-cn',
'zh-cn'=>'zh-sg',
'zh-sg'=>'zh-cn',
'zh-tw'=>'zh-hk',
'zh-hk'=>'zh-tw'));
$wgHooks['ArticleSaveComplete'][] = $this->mConverter;
}
# this should give much better diff info
function segmentForDiff( $text ) {
return preg_replace(
"/([\\xc0-\\xff][\\x80-\\xbf]*)/e",
"' ' .\"$1\"", $text);
}
function unsegmentForDiff( $text ) {
return preg_replace(
"/ ([\\xc0-\\xff][\\x80-\\xbf]*)/e",
"\"$1\"", $text);
}
// word segmentation
function stripForSearch( $string ) {
$fname="LanguageZh::stripForSearch";
wfProfileIn( $fname );
// eventually this should be a word segmentation
// for now just treat each character as a word
$t = preg_replace(
"/([\\xc0-\\xff][\\x80-\\xbf]*)/e",
"' ' .\"$1\"", $string);
//always convert to zh-cn before indexing. it should be
//better to use zh-cn for search, since conversion from
//Traditional to Simplified is less ambiguous than the
//other way around
$t = $this->mConverter->autoConvert($t, 'zh-cn');
$t = parent::stripForSearch( $t );
wfProfileOut( $fname );
return $t;
}
function convertForSearchResult( $termsArray ) {
$terms = implode( '|', $termsArray );
$terms = implode( '|', $this->mConverter->autoConvertToAllVariants( $terms ) );
$ret = array_unique( explode('|', $terms) );
return $ret;
}
}
|
