1. LanguageConverter enabled for LanguageGan, per the request from Gan Wikipedia.

2. Update the Chinese conversion tables.
This commit is contained in:
Philip Tzou 2009-03-12 05:04:19 +00:00
parent fc1f87ca77
commit b8b9e1e477
12 changed files with 4489 additions and 2123 deletions

View file

@ -2546,7 +2546,7 @@ $zh2Hant = array(
'龟' => '龜',
'𡒄' => '壈',
'𨱏' => '鎝',
'<EFBFBD><EFBFBD><EFBFBD>' => '鱇',
'𩾌' => '鱇',
'' => '棡',
'0多只' => '0多隻',
'0天后' => '0天後',
@ -3922,6 +3922,7 @@ $zh2Hant = array(
'多占' => '多佔',
'多划' => '多劃',
'多只是' => '多只是',
'多只需' => '多只需',
'多天后' => '多天後',
'多于' => '多於',
'多冲' => '多衝',
@ -5483,7 +5484,6 @@ $zh2Hant = array(
'乐于' => '樂於',
'樊于期' => '樊於期',
'梁上' => '樑上',
'梁书' => '樑書',
'梁柱' => '樑柱',
'标志着' => '標志著',
'标杆' => '標杆',
@ -10985,7 +10985,7 @@ $zh2Hans = array(
'鰾' => '鳔',
'鱂' => '鳉',
'鱅' => '鳙',
'鱇' => '<EFBFBD><EFBFBD><EFBFBD>',
'鱇' => '𩾌',
'鱈' => '鳕',
'鱉' => '鳖',
'鱒' => '鳟',
@ -11726,6 +11726,7 @@ $zh2Hans = array(
'尋著者' => '寻著者',
'尋著述' => '寻著述',
'將軍抽車' => '将军抽車',
'尼乾陀' => '尼乾陀',
'展著' => '展着',
'展著書' => '展著书',
'展著作' => '展著作',
@ -12192,6 +12193,7 @@ $zh2Hans = array(
'於夫罗' => '於夫罗',
'於夫羅' => '於夫罗',
'於姓' => '於姓',
'於崇文' => '於崇文',
'於戲' => '於戏',
'於梨華' => '於梨华',
'於梨华' => '於梨华',

View file

@ -101,8 +101,8 @@ def GetManualTable( dest ):
elem = elem.strip('|')
if elem:
temp2 = elem.split( '|', 1 )
from_char = temp2[0][-1:]
to_chars = [code[-1:] for code in temp2[1].split('|')]
from_char = chr( int( temp2[0][2:7], 16 ) )
to_chars = [chr( int( code[2:7], 16 ) ) for code in temp2[1].split('|')]
char_table[from_char] = to_chars
return char_table

View file

@ -205,7 +205,7 @@ U+08d5e赞|U+08d0a贊|U+08b9a讚|
U+0E82D|U+068E1棡|
U+29F8C𩾌|U+09C47鱇|
U+070BC炼|U+07149煉|U+0934A鍊|
U+0432A个|U+0500B個|U+07B87箇|
U+04E2A个|U+0500B個|U+07B87箇|
U+094F2铲|U+093DF鏟|U+05277剷|
U+05EB5庵|U+05EB5庵|U+083F4菴|
U+05F69彩|U+05F69彩|U+07DB5綵|

View file

@ -2032,4 +2032,7 @@
因著《
因著〈
李泽钜
於祥玉
於祥玉
於崇文
尼乾陀
於崇文

View file

@ -66,7 +66,7 @@ U+07E34縴|U+07EA4纤|
U+07E94纔|U+0624D才|
U+08591薑|U+059DC姜|
U+0884A衊|U+08511蔑|
U+08A17託|U+06258托|U+8BAC讬|
U+08A17託|U+06258托|U+08BAC讬|
U+08B8E讎|U+04EC7仇|
U+08B9A讚|U+08D5E赞|
U+08FF4迴|U+056DE回|
@ -104,7 +104,7 @@ U+08986覆|U+08986覆|U+0590D复|
U+085C9藉|U+085C9藉|U+0501F借|
U+05138儸|U+03469㑩|U+07F57罗|
U+06FDB濛|U+06FDB濛|U+08499蒙|
U+07B87箇|U+0432A个|
U+07B87箇|U+04E2A个|
U+05277剷|U+094F2铲|
U+05690嚐|U+05C1D尝|
U+055AB喫|U+05403吃|

View file

@ -35,6 +35,7 @@
萬隻
億隻
多只是
多只需
最多只
多隻
0多隻

View file

@ -248,6 +248,7 @@
公裡
箇中
樑子
樑書
讚成
讚同
鐘表店

View file

@ -99,7 +99,9 @@
'fy' => 'Frysk', # Frisian
'ga' => 'Gaeilge', # Irish
'gag' => 'Gagauz', # Gagauz
'gan' => '贛語', # Gan
'gan' => '贛語', # Gan-hant
'gan-hans' => '赣语(简体)', # Gan-hans
'gan-hant' => '贛語(繁體)', # Gan-hant
'gd' => 'Gàidhlig', # Scots Gaelic
'gl' => 'Galego', # Galician
'glk' => 'گیلکی', # Gilaki

View file

@ -0,0 +1,168 @@
<?php
require_once( dirname(__FILE__).'/../LanguageConverter.php' );
require_once( dirname(__FILE__).'/LanguageZh.php' );
/**
* @ingroup Language
*/
class GanConverter extends LanguageConverter {
function __construct($langobj, $maincode,
$variants=array(),
$variantfallbacks=array(),
$markup=array(),
$flags = array(),
$manualLevel = array() ) {
$this->mDescCodeSep = '';
$this->mDescVarSep = '';
parent::__construct($langobj, $maincode,
$variants,
$variantfallbacks,
$markup,
$flags,
$manualLevel);
$names = array(
'gan' => '原文',
'gan-hans' => '简体',
'gan-hant' => '繁體',
);
$this->mVariantNames = array_merge($this->mVariantNames,$names);
$this->loadNamespaceTables();
}
function loadNamespaceTables() {
global $wgMetaNamespace;
$nsproject = $wgMetaNamespace;
$projecttable = array(
'Wikipedia' => '维基百科',
'Wikisource' => '维基文库',
'Wikinews' => '维基新闻',
'Wiktionary' => '维基词典',
'Wikibooks' => '维基教科书',
'Wikiquote' => '维基语录',
);
$this->mNamespaceTables['gan-hans'] = array(
'Media' => '媒体',
'Special' => '特殊',
'Talk' => '談詑',
'User' => '用户',
'User talk' => '用户談詑',
$nsproject
=> isset($projecttable[$nsproject]) ?
$projecttable[$nsproject] : $nsproject,
$nsproject . ' talk'
=> isset($projecttable[$nsproject]) ?
$projecttable[$nsproject] . '談詑' : $nsproject . '談詑',
'File' => '文件',
'File talk' => '文件談詑',
'MediaWiki' => 'MediaWiki',
'MediaWiki talk' => 'MediaWiki談詑',
'Template' => '模板',
'Template talk' => '模板談詑',
'Help' => '帮助',
'Help talk' => '帮助談詑',
'Category' => '分类',
'Category talk' => '分类談詑',
);
$this->mNamespaceTables['gan-hant'] = array_merge($this->mNamespaceTables['gan-hans']);
$this->mNamespaceTables['gan-hant']['File'] = '檔案';
$this->mNamespaceTables['gan-hant']['File talk'] = '檔案談詑';
$this->mNamespaceTables['gan'] = array_merge($this->mNamespaceTables['gan-hans']);
}
function loadDefaultTables() {
require( dirname(__FILE__)."/../../includes/ZhConversion.php" );
$this->mTables = array(
'gan-hans' => new ReplacementArray( $zh2Hans ),
'gan-hant' => new ReplacementArray( $zh2Hant ),
'gan' => new ReplacementArray
);
}
/* 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, 'gan' );
}
}
/**
* class that handles both Traditional and Simplified Chinese
* right now it only distinguish gan_hans, gan_hant.
*
* @ingroup Language
*/
class LanguageGan extends LanguageZh {
function __construct() {
global $wgHooks;
parent::__construct();
$variants = array('gan','gan-hans','gan-hant');
$variantfallbacks = array(
'gan' => array('gan-hans','gan-hant'),
'gan-hans' => array('gan'),
'gan-hant' => array('gan'),
);
$ml=array(
'gan' => 'disable',
);
$this->mConverter = new GanConverter( $this, 'gan',
$variants, $variantfallbacks,
array(),array(),
$ml);
$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 ) {
wfProfileIn( __METHOD__ );
// eventually this should be a word segmentation
// for now just treat each character as a word
// @fixme only do this for Han characters...
$t = preg_replace(
"/([\\xc0-\\xff][\\x80-\\xbf]*)/",
" $1", $string);
//always convert to gan-hans before indexing. it should be
//better to use gan-hans for search, since conversion from
//Traditional to Simplified is less ambiguous than the
//other way around
$t = $this->mConverter->autoConvert($t, 'gan-hans');
$t = parent::stripForSearch( $t );
wfProfileOut( __METHOD__ );
return $t;
}
function convertForSearchResult( $termsArray ) {
$terms = implode( '|', $termsArray );
$terms = implode( '|', $this->mConverter->autoConvertToAllVariants( $terms ) );
$ret = array_unique( explode('|', $terms) );
return $ret;
}
}

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff