3 * Chinese specific code.
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
15 * You should have received a copy of the GNU General Public License along
16 * with this program; if not, write to the Free Software Foundation, Inc.,
17 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
18 * http://www.gnu.org/copyleft/gpl.html
24 require_once( __DIR__
. '/../LanguageConverter.php' );
25 require_once( __DIR__
. '/LanguageZh_hans.php' );
30 class ZhConverter
extends LanguageConverter
{
33 * @param $langobj Language
34 * @param $maincode string
35 * @param $variants array
36 * @param $variantfallbacks array
38 * @param $manualLevel array
40 function __construct( $langobj, $maincode,
42 $variantfallbacks = array(),
44 $manualLevel = array() ) {
45 $this->mDescCodeSep
= ':';
46 $this->mDescVarSep
= ';';
47 parent
::__construct( $langobj, $maincode,
63 $this->mVariantNames
= array_merge( $this->mVariantNames
, $names );
66 function loadDefaultTables() {
67 require( __DIR__
. "/../../includes/ZhConversion.php" );
68 $this->mTables
= array(
69 'zh-hans' => new ReplacementArray( $zh2Hans ),
70 'zh-hant' => new ReplacementArray( $zh2Hant ),
71 'zh-cn' => new ReplacementArray( array_merge( $zh2Hans, $zh2CN ) ),
72 'zh-hk' => new ReplacementArray( array_merge( $zh2Hant, $zh2HK ) ),
73 'zh-mo' => new ReplacementArray( array_merge( $zh2Hant, $zh2HK ) ),
74 'zh-my' => new ReplacementArray( array_merge( $zh2Hans, $zh2SG ) ),
75 'zh-sg' => new ReplacementArray( array_merge( $zh2Hans, $zh2SG ) ),
76 'zh-tw' => new ReplacementArray( array_merge( $zh2Hant, $zh2TW ) ),
77 'zh' => new ReplacementArray
81 function postLoadTables() {
82 $this->mTables
['zh-cn']->merge( $this->mTables
['zh-hans'] );
83 $this->mTables
['zh-hk']->merge( $this->mTables
['zh-hant'] );
84 $this->mTables
['zh-mo']->merge( $this->mTables
['zh-hant'] );
85 $this->mTables
['zh-my']->merge( $this->mTables
['zh-hans'] );
86 $this->mTables
['zh-sg']->merge( $this->mTables
['zh-hans'] );
87 $this->mTables
['zh-tw']->merge( $this->mTables
['zh-hant'] );
91 * there shouldn't be any latin text in Chinese conversion, so no need
93 * $noParse is there for compatibility with LanguageConvert::markNoConversion
96 * @param $noParse bool
100 function markNoConversion( $text, $noParse = false ) {
108 function convertCategoryKey( $key ) {
109 return $this->autoConvert( $key, 'zh' );
114 * class that handles both Traditional and Simplified Chinese
115 * right now it only distinguish zh_hans, zh_hant, zh_cn, zh_tw, zh_sg and zh_hk.
119 class LanguageZh
extends LanguageZh_hans
{
121 function __construct() {
123 parent
::__construct();
125 $variants = array( 'zh', 'zh-hans', 'zh-hant', 'zh-cn', 'zh-hk', 'zh-mo', 'zh-my', 'zh-sg', 'zh-tw' );
127 $variantfallbacks = array(
128 'zh' => array( 'zh-hans', 'zh-hant', 'zh-cn', 'zh-tw', 'zh-hk', 'zh-sg', 'zh-mo', 'zh-my' ),
129 'zh-hans' => array( 'zh-cn', 'zh-sg', 'zh-my' ),
130 'zh-hant' => array( 'zh-tw', 'zh-hk', 'zh-mo' ),
131 'zh-cn' => array( 'zh-hans', 'zh-sg', 'zh-my' ),
132 'zh-sg' => array( 'zh-hans', 'zh-cn', 'zh-my' ),
133 'zh-my' => array( 'zh-hans', 'zh-sg', 'zh-cn' ),
134 'zh-tw' => array( 'zh-hant', 'zh-hk', 'zh-mo' ),
135 'zh-hk' => array( 'zh-hant', 'zh-mo', 'zh-tw' ),
136 'zh-mo' => array( 'zh-hant', 'zh-hk', 'zh-tw' ),
140 'zh-hans' => 'unidirectional',
141 'zh-hant' => 'unidirectional',
144 $this->mConverter
= new ZhConverter( $this, 'zh',
145 $variants, $variantfallbacks,
149 $wgHooks['PageContentSaveComplete'][] = $this->mConverter
;
153 * this should give much better diff info
155 * @param $text string
158 function segmentForDiff( $text ) {
160 "/([\\xc0-\\xff][\\x80-\\xbf]*)/e",
161 "' ' .\"$1\"", $text );
165 * @param $text string
168 function unsegmentForDiff( $text ) {
170 "/ ([\\xc0-\\xff][\\x80-\\xbf]*)/e",
175 * auto convert to zh-hans and normalize special characters.
177 * @param $string String
178 * @param $autoVariant String, default to 'zh-hans'
181 function normalizeForSearch( $string, $autoVariant = 'zh-hans' ) {
182 wfProfileIn( __METHOD__
);
184 // always convert to zh-hans before indexing. it should be
185 // better to use zh-hans for search, since conversion from
186 // Traditional to Simplified is less ambiguous than the
188 $s = $this->mConverter
->autoConvert( $string, $autoVariant );
189 // LanguageZh_hans::normalizeForSearch
190 $s = parent
::normalizeForSearch( $s );
191 wfProfileOut( __METHOD__
);
197 * @param $termsArray array
200 function convertForSearchResult( $termsArray ) {
201 $terms = implode( '|', $termsArray );
202 $terms = self
::convertDoubleWidth( $terms );
203 $terms = implode( '|', $this->mConverter
->autoConvertToAllVariants( $terms ) );
204 $ret = array_unique( explode( '|', $terms ) );