diff options
Diffstat (limited to 'languages/classes/LanguageSr.php')
-rw-r--r-- | languages/classes/LanguageSr.php | 181 |
1 files changed, 181 insertions, 0 deletions
diff --git a/languages/classes/LanguageSr.php b/languages/classes/LanguageSr.php new file mode 100644 index 00000000..412463f8 --- /dev/null +++ b/languages/classes/LanguageSr.php @@ -0,0 +1,181 @@ +<?php +/** + * @package MediaWiki + * @subpackage Language + */ + +/* + There are two levels of conversion for Serbian: the script level + (Cyrillics <-> Latin), and the variant level (ekavian + <->iyekavian). The two are orthogonal. So we really only need two + dictionaries: one for Cyrillics and Latin, and one for ekavian and + iyekavian. +*/ +require_once( dirname(__FILE__).'/../LanguageConverter.php' ); +require_once( dirname(__FILE__).'/LanguageSr_ec.php' ); +require_once( dirname(__FILE__).'/LanguageSr_el.php' ); + +class SrConverter extends LanguageConverter { + var $mToLatin = array( + 'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', + 'ђ' => 'đ', 'е' => 'e', 'ж' => 'ž', 'з' => 'z', 'и' => 'i', + 'ј' => 'j', 'к' => 'k', 'л' => 'l', 'љ' => 'lj', 'м' => 'm', + 'н' => 'n', 'њ' => 'nj', 'о' => 'o', 'п' => 'p', 'р' => 'r', + 'с' => 's', 'т' => 't', 'ћ' => 'ć', 'у' => 'u', 'ф' => 'f', + 'х' => 'h', 'ц' => 'c', 'ч' => 'č', 'џ' => 'dž', 'ш' => 'š', + + 'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', + 'Ђ' => 'Đ', 'Е' => 'E', 'Ж' => 'Ž', 'З' => 'Z', 'И' => 'I', + 'Ј' => 'J', 'К' => 'K', 'Л' => 'L', 'Љ' => 'Lj', 'М' => 'M', + 'Н' => 'N', 'Њ' => 'Nj', 'О' => 'O', 'П' => 'P', 'Р' => 'R', + 'С' => 'S', 'Т' => 'T', 'Ћ' => 'Ć', 'У' => 'U', 'Ф' => 'F', + 'Х' => 'H', 'Ц' => 'C', 'Ч' => 'Č', 'Џ' => 'Dž', 'Ш' => 'Š', + ); + + var $mToCyrillics = array( + 'a' => 'а', 'b' => 'б', 'c' => 'ц', 'č' => 'ч', 'ć' => 'ћ', + 'd' => 'д', 'dž' => 'џ', 'đ' => 'ђ', 'e' => 'е', 'f' => 'ф', + 'g' => 'г', 'h' => 'х', 'i' => 'и', 'j' => 'ј', 'k' => 'к', + 'l' => 'л', 'lj' => 'љ', 'm' => 'м', 'n' => 'н', 'nj' => 'њ', + 'o' => 'о', 'p' => 'п', 'r' => 'р', 's' => 'с', 'š' => 'ш', + 't' => 'т', 'u' => 'у', 'v' => 'в', 'z' => 'з', 'ž' => 'ж', + + 'A' => 'А', 'B' => 'Б', 'C' => 'Ц', 'Č' => 'Ч', 'Ć' => 'Ћ', + 'D' => 'Д', 'Dž' => 'Џ', 'Đ' => 'Ђ', 'E' => 'Е', 'F' => 'Ф', + 'G' => 'Г', 'H' => 'Х', 'I' => 'И', 'J' => 'Ј', 'K' => 'К', + 'L' => 'Л', 'LJ' => 'Љ', 'M' => 'М', 'N' => 'Н', 'NJ' => 'Њ', + 'O' => 'О', 'P' => 'П', 'R' => 'Р', 'S' => 'С', 'Š' => 'Ш', + 'T' => 'Т', 'U' => 'У', 'V' => 'В', 'Z' => 'З', 'Ž' => 'Ж', + + 'DŽ' => 'Џ', 'd!ž' => 'дж', 'D!ž'=> 'Дж', 'D!Ž'=> 'ДЖ', + 'Lj' => 'Љ', 'l!j' => 'лј', 'L!j'=> 'Лј', 'L!J'=> 'ЛЈ', + 'Nj' => 'Њ', 'n!j' => 'нј', 'N!j'=> 'Нј', 'N!J'=> 'НЈ' + ); + + function loadDefaultTables() { + $this->mTables = array(); + $this->mTables['sr-ec'] = $this->mToCyrillics; + $this->mTables['sr-jc'] = $this->mToCyrillics; + $this->mTables['sr-el'] = $this->mToLatin; + $this->mTables['sr-jl'] = $this->mToLatin; + $this->mTables['sr'] = array(); + } + + /* rules should be defined as -{ekavian | iyekavian-} -or- + -{code:text | code:text | ...}- + update: delete all rule parsing because it's not used + currently, and just produces a couple of bugs + */ + function parseManualRule($rule, $flags=array()) { + // ignore all formatting + foreach($this->mVariants as $v) { + $carray[$v] = $rule; + } + + return $carray; + } + + /* + * Override function from LanguageConvertor + * Additional checks: + * - There should be no conversion for Talk pages + */ + function getPreferredVariant(){ + global $wgTitle; + if($wgTitle!=NULL && $wgTitle->isTalkPage()){ + return $this->mMainLanguageCode; + } + return parent::getPreferredVariant(); + } + + + /* + * A function wrapper, if there is no selected variant, + * leave the link names as they were + */ + function findVariantLink( &$link, &$nt ) { + $oldlink=$link; + parent::findVariantLink($link,$nt); + if($this->getPreferredVariant()==$this->mMainLanguageCode) + $link=$oldlink; + } + + + /* + * We want our external link captions to be converted in variants, + * so we return the original text instead -{$text}-, except for URLs + */ + function markNoConversion($text, $noParse=false) { + if($noParse || preg_match("/^https?:\/\/|ftp:\/\/|irc:\/\//",$text)) + return parent::markNoConversion($text); + return $text; + } + + /* + * An ugly function wrapper for parsing Image titles + * (to prevent image name conversion) + */ + function autoConvert($text, $toVariant=false) { + global $wgTitle; + if($wgTitle->getNameSpace()==NS_IMAGE){ + $imagename = $wgTitle->getNsText(); + if(preg_match("/^$imagename:/",$text)) return $text; + } + return parent::autoConvert($text,$toVariant); + } + + /** + * It translates text into variant, specials: + * - ommiting roman numbers + */ + function translate($text, $toVariant){ + $breaks = '[^\w\x80-\xff]'; + + // regexp for roman numbers + $roman = 'M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})'; + + $reg = '/^'.$roman.'$|^'.$roman.$breaks.'|'.$breaks.$roman.'$|'.$breaks.$roman.$breaks.'/'; + + $matches = preg_split($reg, $text, -1, PREG_SPLIT_OFFSET_CAPTURE); + + $m = array_shift($matches); + $ret = strtr($m[0], $this->mTables[$toVariant]); + $mstart = $m[1]+strlen($m[0]); + foreach($matches as $m) { + $ret .= substr($text, $mstart, $m[1]-$mstart); + $ret .= parent::translate($m[0], $toVariant); + $mstart = $m[1] + strlen($m[0]); + } + + return $ret; + } + + +} + +class LanguageSr extends LanguageSr_ec { + function __construct() { + global $wgHooks; + + parent::__construct(); + + // these variants are currently UNUSED: + // 'sr-jc', 'sr-jl' + $variants = array('sr', 'sr-ec', 'sr-el'); + $variantfallbacks = array( + 'sr' => 'sr-ec', + 'sr-ec' => 'sr-ec', + 'sr-el' => 'sr-el', + ); + + + $marker = array();//don't mess with these, leave them as they are + $flags = array( + 'S' => 'S', 'писмо' => 'S', 'pismo' => 'S', + 'W' => 'W', 'реч' => 'W', 'reč' => 'W', 'ријеч' => 'W', 'riječ' => 'W' + ); + $this->mConverter = new SrConverter($this, 'sr', $variants, $variantfallbacks, $marker, $flags); + $wgHooks['ArticleSaveComplete'][] = $this->mConverter; + } +} +?> |