languages/classes/LanguageSr.php

   1 <?php
   2 /**
   3   * @package MediaWiki
   4   * @subpackage Language
   5   */
   6
   7 /*
   8         There are two levels of conversion for Serbian: the script level
   9         (Cyrillics <-> Latin), and the variant level (ekavian
  10         <->iyekavian). The two are orthogonal. So we really only need two
  11         dictionaries: one for Cyrillics and Latin, and one for ekavian and
  12         iyekavian.
  13 */
  14 require_once( dirname(__FILE__).'/../LanguageConverter.php' );
  15 require_once( dirname(__FILE__).'/LanguageSr_ec.php' );
  16 require_once( dirname(__FILE__).'/LanguageSr_el.php' );
  17
  18 class SrConverter extends LanguageConverter {
  19         var $mToLatin = array(
  20                 'а' => 'a', 'б' => 'b',  'в' => 'v', 'г' => 'g',  'д' => 'd',
  21                 'ђ' => 'đ', 'е' => 'e',  'ж' => 'ž', 'з' => 'z',  'и' => 'i',
  22                 'ј' => 'j', 'к' => 'k',  'л' => 'l', 'љ' => 'lj', 'м' => 'm',
  23                 'н' => 'n', 'њ' => 'nj', 'о' => 'o', 'п' => 'p',  'р' => 'r',
  24                 'с' => 's', 'т' => 't',  'ћ' => 'ć', 'у' => 'u',  'ф' => 'f',
  25                 'х' => 'h', 'ц' => 'c',  'ч' => 'č', 'џ' => 'dž', 'ш' => 'š',
  26
  27                 'А' => 'A', 'Б' => 'B',  'В' => 'V', 'Г' => 'G',  'Д' => 'D',
  28                 'Ђ' => 'Đ', 'Е' => 'E',  'Ж' => 'Ž', 'З' => 'Z',  'И' => 'I',
  29                 'Ј' => 'J', 'К' => 'K',  'Л' => 'L', 'Љ' => 'Lj', 'М' => 'M',
  30                 'Н' => 'N', 'Њ' => 'Nj', 'О' => 'O', 'П' => 'P',  'Р' => 'R',
  31                 'С' => 'S', 'Т' => 'T',  'Ћ' => 'Ć', 'У' => 'U',  'Ф' => 'F',
  32                 'Х' => 'H', 'Ц' => 'C',  'Ч' => 'Č', 'Џ' => 'Dž', 'Ш' => 'Š',
  33         );
  34
  35         var $mToCyrillics = array(
  36                 'a' => 'а', 'b'  => 'б', 'c' => 'ц', 'č' => 'ч', 'ć'  => 'ћ',
  37                 'd' => 'д', 'dž' => 'џ', 'đ' => 'ђ', 'e' => 'е', 'f'  => 'ф',
  38                 'g' => 'г', 'h'  => 'х', 'i' => 'и', 'j' => 'ј', 'k'  => 'к',
  39                 'l' => 'л', 'lj' => 'љ', 'm' => 'м', 'n' => 'н', 'nj' => 'њ',
  40                 'o' => 'о', 'p'  => 'п', 'r' => 'р', 's' => 'с', 'š'  => 'ш',
  41                 't' => 'т', 'u'  => 'у', 'v' => 'в', 'z' => 'з', 'ž'  => 'ж',
  42
  43                 'A' => 'А', 'B'  => 'Б', 'C' => 'Ц', 'Č' => 'Ч', 'Ć'  => 'Ћ',
  44                 'D' => 'Д', 'Dž' => 'Џ', 'Đ' => 'Ђ', 'E' => 'Е', 'F'  => 'Ф',
  45                 'G' => 'Г', 'H'  => 'Х', 'I' => 'И', 'J' => 'Ј', 'K'  => 'К',
  46                 'L' => 'Л', 'LJ' => 'Љ', 'M' => 'М', 'N' => 'Н', 'NJ' => 'Њ',
  47                 'O' => 'О', 'P'  => 'П', 'R' => 'Р', 'S' => 'С', 'Š'  => 'Ш',
  48                 'T' => 'Т', 'U'  => 'У', 'V' => 'В', 'Z' => 'З', 'Ž'  => 'Ж',
  49
  50                 'DŽ' => 'Џ', 'd!ž' => 'дж', 'D!ž'=> 'Дж', 'D!Ž'=> 'ДЖ',
  51                 'Lj' => 'Љ', 'l!j' => 'лј', 'L!j'=> 'Лј', 'L!J'=> 'ЛЈ',
  52                 'Nj' => 'Њ', 'n!j' => 'нј', 'N!j'=> 'Нј', 'N!J'=> 'НЈ'
  53         );
  54
  55         var $mParsingContent=false;
  56
  57         function loadDefaultTables() {
  58                 $this->mTables = array(
  59                         'sr-ec' => new ReplacementArray( $this->mToCyrillics ),
  60                         'sr-jc' => new ReplacementArray( $this->mToCyrillics),
  61                         'sr-el' => new ReplacementArray( $this->mToLatin),
  62                         'sr-jl' => new ReplacementArray( $this->mToLatin),
  63                         'sr'    => new ReplacementArray()
  64                 );
  65         }
  66
  67         /* rules should be defined as -{ekavian | iyekavian-} -or-
  68                 -{code:text | code:text | ...}-
  69                 update: delete all rule parsing because it's not used
  70                         currently, and just produces a couple of bugs
  71         */
  72         function parseManualRule($rule, $flags=array()) {
  73                 // ignore all formatting
  74                 foreach($this->mVariants as $v) {
  75                                 $carray[$v] = $rule;
  76                         }
  77
  78                 return $carray;
  79         }
  80
  81         // Set a flag when parsing content, this is used to prevent
  82         // conversion of content within talk pages
  83         function parserConvert( $text, &$parser ){
  84                 $this->mParsingContent = true;
  85                 $output = parent::parserConvert($text, $parser );
  86                 $this->mParsingContent = false;
  87                 return $output;
  88
  89         }
  90
  91         /*
  92          * Override function from LanguageConvertor
  93          * Additional checks:
  94          *  - There should be no conversion for Talk pages
  95          */
  96         function getPreferredVariant( $fromUser=true ){
  97                 global $wgTitle;
  98                 if(is_object($wgTitle) && $wgTitle->isTalkPage() && $this->mParsingContent){
  99                         return $this->mMainLanguageCode;
 100                 }
 101                 return parent::getPreferredVariant($fromUser);
 102         }
 103
 104
 105         /*
 106          * A function wrapper:
 107          *   - if there is no selected variant, leave the link
 108          *     names as they were
 109          *   - do not try to find variants for usernames
 110          */
 111         function findVariantLink( &$link, &$nt ) {
 112                 // check for user namespace
 113                 if(is_object($nt)){
 114                         $ns = $nt->getNamespace();
 115                         if($ns==NS_USER || $ns==NS_USER_TALK)
 116                                 return;
 117                 }
 118
 119                 $oldlink=$link;
 120                 parent::findVariantLink($link,$nt);
 121                 if($this->getPreferredVariant()==$this->mMainLanguageCode)
 122                         $link=$oldlink;
 123         }
 124
 125         /*
 126          * We want our external link captions to be converted in variants,
 127          * so we return the original text instead -{$text}-, except for URLs
 128          */
 129         function markNoConversion($text, $noParse=false) {
 130                 if($noParse || preg_match("/^https?:\/\/|ftp:\/\/|irc:\/\//",$text))
 131                         return parent::markNoConversion($text);
 132                 return $text;
 133         }
 134
 135         /*
 136          * An ugly function wrapper for parsing Image titles
 137          * (to prevent image name conversion)
 138          */
 139         function autoConvert($text, $toVariant=false) {
 140                 global $wgTitle;
 141                 if(is_object($wgTitle) && $wgTitle->getNameSpace()==NS_IMAGE){
 142                         $imagename = $wgTitle->getNsText();
 143                         if(preg_match("/^$imagename:/",$text)) return $text;
 144                 }
 145                 return parent::autoConvert($text,$toVariant);
 146         }
 147
 148         /**
 149          *  It translates text into variant, specials:
 150          *    - ommiting roman numbers
 151          */
 152         function translate($text, $toVariant){
 153                 $breaks = '[^\w\x80-\xff]';
 154
 155                 // regexp for roman numbers
 156                 $roman = 'M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})';
 157
 158                 $reg = '/^'.$roman.'$|^'.$roman.$breaks.'|'.$breaks.$roman.'$|'.$breaks.$roman.$breaks.'/';
 159
 160                 $matches = preg_split($reg, $text, -1, PREG_SPLIT_OFFSET_CAPTURE);
 161
 162                 $m = array_shift($matches);
 163                 $ret = $this->mTables[$toVariant]->replace( $m[0] );
 164                 $mstart = $m[1]+strlen($m[0]);
 165                 foreach($matches as $m) {
 166                         $ret .= substr($text, $mstart, $m[1]-$mstart);
 167                         $ret .= parent::translate($m[0], $toVariant);
 168                         $mstart = $m[1] + strlen($m[0]);
 169                 }
 170
 171                 return $ret;
 172         }
 173
 174         function armourMath($text){
 175                 return parent::markNoConversion($text);
 176         }
 177
 178 }
 179
 180 class LanguageSr extends LanguageSr_ec {
 181         function __construct() {
 182                 global $wgHooks;
 183
 184                 parent::__construct();
 185
 186                 // these variants are currently UNUSED:
 187                 // 'sr-jc', 'sr-jl'
 188                 $variants = array('sr', 'sr-ec', 'sr-el');
 189                 $variantfallbacks = array(
 190                         'sr'    => 'sr-ec',
 191                         'sr-ec' => 'sr-ec',
 192                         'sr-el' => 'sr-el',
 193                         );
 194
 195
 196                 $marker = array();//don't mess with these, leave them as they are
 197                 $flags = array(
 198                         'S' => 'S', 'писмо' => 'S', 'pismo' => 'S',
 199                         'W' => 'W', 'реч'   => 'W', 'reč'   => 'W', 'ријеч' => 'W', 'riječ' => 'W'
 200                 );
 201                 $this->mConverter = new SrConverter($this, 'sr', $variants, $variantfallbacks, $marker, $flags);
 202                 $wgHooks['ArticleSaveComplete'][] = $this->mConverter;
 203         }
 204 }
 205 ?>