087a9f70c5
Doxygen documentation update: * Changed alls @addtogroup to @ingroup. @addtogroup adds the comment to the group description, but doesn't add the file, class, function, ... to the group like @ingroup does. See for example http://svn.wikimedia.org/doc/group__SpecialPage.html where it's impossible to see related files, classes, ... that should belong to that group. * Added @file to file description, it seems that it should be explicitely decalred for file descriptions, otherwise doxygen will think that the comment document the first class, variabled, function, ... that is in that file. * Removed some empty comments * Removed some ?> Added following groups: * ExternalStorage * JobQueue * MaintenanceLanguage One more thing: there are still a lot of warnings when generating the doc.
40 lines
1.3 KiB
PHP
40 lines
1.3 KiB
PHP
<?php
|
|
|
|
/**
|
|
* Japanese (日本語)
|
|
*
|
|
* @ingroup Language
|
|
*/
|
|
class LanguageJa extends Language {
|
|
function stripForSearch( $string ) {
|
|
# MySQL fulltext index doesn't grok utf-8, so we
|
|
# need to fold cases and convert to hex
|
|
$s = $string;
|
|
|
|
# Strip known punctuation ?
|
|
#$s = preg_replace( '/\xe3\x80[\x80-\xbf]/', '', $s ); # U3000-303f
|
|
|
|
# Space strings of like hiragana/katakana/kanji
|
|
$hiragana = '(?:\xe3(?:\x81[\x80-\xbf]|\x82[\x80-\x9f]))'; # U3040-309f
|
|
$katakana = '(?:\xe3(?:\x82[\xa0-\xbf]|\x83[\x80-\xbf]))'; # U30a0-30ff
|
|
$kanji = '(?:\xe3[\x88-\xbf][\x80-\xbf]'
|
|
. '|[\xe4-\xe8][\x80-\xbf]{2}'
|
|
. '|\xe9[\x80-\xa5][\x80-\xbf]'
|
|
. '|\xe9\xa6[\x80-\x99])';
|
|
# U3200-9999 = \xe3\x88\x80-\xe9\xa6\x99
|
|
$s = preg_replace( "/({$hiragana}+|{$katakana}+|{$kanji}+)/", ' $1 ', $s );
|
|
|
|
# Double-width roman characters: ff00-ff5f ~= 0020-007f
|
|
$s = preg_replace( '/\xef\xbc([\x80-\xbf])/e', 'chr((ord("$1") & 0x3f) + 0x20)', $s );
|
|
$s = preg_replace( '/\xef\xbd([\x80-\x99])/e', 'chr((ord("$1") & 0x3f) + 0x60)', $s );
|
|
|
|
# Do general case folding and UTF-8 armoring
|
|
return parent::stripForSearch( $s );
|
|
}
|
|
|
|
# Italic is not appropriate for Japanese script
|
|
# Unfortunately most browsers do not recognise this, and render <em> as italic
|
|
function emphasize( $text ) {
|
|
return $text;
|
|
}
|
|
}
|