languages/classes/LanguageSr.php

   1 <?php
   2 /**
   3  * Serbian (Српски / Srpski) specific code.
   4  *
   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.
   9  *
  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.
  14  *
  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
  19  *
  20  * @file
  21  * @ingroup Language
  22  */
  23
  24 /**
  25  * There are two levels of conversion for Serbian: the script level
  26  * (Cyrillics <-> Latin), and the variant level (ekavian
  27  * <->iyekavian). The two are orthogonal. So we really only need two
  28  * dictionaries: one for Cyrillics and Latin, and one for ekavian and
  29  * iyekavian.
  30  *
  31  * @ingroup Language
  32  */
  33 class SrConverter extends LanguageConverter {
  34         public $mToLatin = [
  35                 'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd',
  36                 'ђ' => 'đ', 'е' => 'e', 'ж' => 'ž', 'з' => 'z', 'и' => 'i',
  37                 'ј' => 'j', 'к' => 'k', 'л' => 'l', 'љ' => 'lj', 'м' => 'm',
  38                 'н' => 'n', 'њ' => 'nj', 'о' => 'o', 'п' => 'p', 'р' => 'r',
  39                 'с' => 's', 'т' => 't', 'ћ' => 'ć', 'у' => 'u', 'ф' => 'f',
  40                 'х' => 'h', 'ц' => 'c', 'ч' => 'č', 'џ' => 'dž', 'ш' => 'š',
  41
  42                 'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D',
  43                 'Ђ' => 'Đ', 'Е' => 'E', 'Ж' => 'Ž', 'З' => 'Z', 'И' => 'I',
  44                 'Ј' => 'J', 'К' => 'K', 'Л' => 'L', 'Љ' => 'Lj', 'М' => 'M',
  45                 'Н' => 'N', 'Њ' => 'Nj', 'О' => 'O', 'П' => 'P', 'Р' => 'R',
  46                 'С' => 'S', 'Т' => 'T', 'Ћ' => 'Ć', 'У' => 'U', 'Ф' => 'F',
  47                 'Х' => 'H', 'Ц' => 'C', 'Ч' => 'Č', 'Џ' => 'Dž', 'Ш' => 'Š',
  48         ];
  49
  50         public $mToCyrillics = [
  51                 'a' => 'а', 'b' => 'б', 'c' => 'ц', 'č' => 'ч', 'ć' => 'ћ',
  52                 'd' => 'д', 'dž' => 'џ', 'đ' => 'ђ', 'e' => 'е', 'f' => 'ф',
  53                 'g' => 'г', 'h' => 'х', 'i' => 'и', 'j' => 'ј', 'k' => 'к',
  54                 'l' => 'л', 'lj' => 'љ', 'm' => 'м', 'n' => 'н', 'nj' => 'њ',
  55                 'o' => 'о', 'p' => 'п', 'r' => 'р', 's' => 'с', 'š' => 'ш',
  56                 't' => 'т', 'u' => 'у', 'v' => 'в', 'z' => 'з', 'ž' => 'ж',
  57
  58                 'A' => 'А', 'B' => 'Б', 'C' => 'Ц', 'Č' => 'Ч', 'Ć' => 'Ћ',
  59                 'D' => 'Д', 'Dž' => 'Џ', 'Đ' => 'Ђ', 'E' => 'Е', 'F' => 'Ф',
  60                 'G' => 'Г', 'H' => 'Х', 'I' => 'И', 'J' => 'Ј', 'K' => 'К',
  61                 'L' => 'Л', 'LJ' => 'Љ', 'M' => 'М', 'N' => 'Н', 'NJ' => 'Њ',
  62                 'O' => 'О', 'P' => 'П', 'R' => 'Р', 'S' => 'С', 'Š' => 'Ш',
  63                 'T' => 'Т', 'U' => 'У', 'V' => 'В', 'Z' => 'З', 'Ž' => 'Ж',
  64
  65                 'DŽ' => 'Џ', 'd!ž' => 'дж', 'D!ž' => 'Дж', 'D!Ž' => 'ДЖ',
  66                 'Lj' => 'Љ', 'l!j' => 'лј', 'L!j' => 'Лј', 'L!J' => 'ЛЈ',
  67                 'Nj' => 'Њ', 'n!j' => 'нј', 'N!j' => 'Нј', 'N!J' => 'НЈ'
  68         ];
  69
  70         function loadDefaultTables() {
  71                 $this->mTables = [
  72                         'sr-ec' => new ReplacementArray( $this->mToCyrillics ),
  73                         'sr-el' => new ReplacementArray( $this->mToLatin ),
  74                         'sr' => new ReplacementArray()
  75                 ];
  76         }
  77
  78         /**
  79          * rules should be defined as -{ekavian | iyekavian-} -or-
  80          * -{code:text | code:text | ...}-
  81          *
  82          * update: delete all rule parsing because it's not used
  83          * currently, and just produces a couple of bugs
  84          *
  85          * @param string $rule
  86          * @param array $flags
  87          * @return array
  88          */
  89         function parseManualRule( $rule, $flags = [] ) {
  90                 if ( in_array( 'T', $flags ) ) {
  91                         return parent::parseManualRule( $rule, $flags );
  92                 }
  93
  94                 $carray = [];
  95                 // otherwise ignore all formatting
  96                 foreach ( $this->mVariants as $v ) {
  97                         $carray[$v] = $rule;
  98                 }
  99
 100                 return $carray;
 101         }
 102
 103         /**
 104          * A function wrapper:
 105          *   - if there is no selected variant, leave the link
 106          *     names as they were
 107          *   - do not try to find variants for usernames
 108          *
 109          * @param string &$link
 110          * @param Title &$nt
 111          * @param bool $ignoreOtherCond
 112          */
 113         function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) {
 114                 // check for user namespace
 115                 if ( is_object( $nt ) ) {
 116                         $ns = $nt->getNamespace();
 117                         if ( $ns == NS_USER || $ns == NS_USER_TALK ) {
 118                                 return;
 119                         }
 120                 }
 121
 122                 $oldlink = $link;
 123                 parent::findVariantLink( $link, $nt, $ignoreOtherCond );
 124                 if ( $this->getPreferredVariant() == $this->mMainLanguageCode ) {
 125                         $link = $oldlink;
 126                 }
 127         }
 128
 129         /**
 130          *  It translates text into variant, specials:
 131          *    - ommiting roman numbers
 132          *
 133          * @param string $text
 134          * @param string $toVariant
 135          *
 136          * @throws MWException
 137          * @return string
 138          */
 139         function translate( $text, $toVariant ) {
 140                 $breaks = '[^\w\x80-\xff]';
 141
 142                 // regexp for roman numbers
 143                 $roman = 'M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})';
 144
 145                 $reg = '/^' . $roman . '$|^' . $roman . $breaks . '|' . $breaks
 146                         . $roman . '$|' . $breaks . $roman . $breaks . '/';
 147
 148                 $matches = preg_split( $reg, $text, -1, PREG_SPLIT_OFFSET_CAPTURE );
 149
 150                 $m = array_shift( $matches );
 151                 $this->loadTables();
 152                 if ( !isset( $this->mTables[$toVariant] ) ) {
 153                         throw new MWException( "Broken variant table: "
 154                                 . implode( ',', array_keys( $this->mTables ) ) );
 155                 }
 156                 $ret = $this->mTables[$toVariant]->replace( $m[0] );
 157                 $mstart = $m[1] + strlen( $m[0] );
 158                 foreach ( $matches as $m ) {
 159                         $ret .= substr( $text, $mstart, $m[1] -$mstart );
 160                         $ret .= parent::translate( $m[0], $toVariant );
 161                         $mstart = $m[1] + strlen( $m[0] );
 162                 }
 163
 164                 return $ret;
 165         }
 166
 167         /**
 168          * Guess if a text is written in Cyrillic or Latin.
 169          * Overrides LanguageConverter::guessVariant()
 170          *
 171          * @param string $text The text to be checked
 172          * @param string $variant Language code of the variant to be checked for
 173          * @return bool True if $text appears to be written in $variant
 174          *
 175          * @author Nikola Smolenski <smolensk@eunet.rs>
 176          * @since 1.19
 177          */
 178         public function guessVariant( $text, $variant ) {
 179                 $numCyrillic = preg_match_all( "/[шђчћжШЂЧЋЖ]/u", $text, $dummy );
 180                 $numLatin = preg_match_all( "/[šđčćžŠĐČĆŽ]/u", $text, $dummy );
 181
 182                 if ( $variant == 'sr-ec' ) {
 183                         return $numCyrillic > $numLatin;
 184                 } elseif ( $variant == 'sr-el' ) {
 185                         return $numLatin > $numCyrillic;
 186                 } else {
 187                         return false;
 188                 }
 189         }
 190
 191 }
 192
 193 /**
 194  * Serbian (Српски / Srpski)
 195  *
 196  * @ingroup Language
 197  */
 198 class LanguageSr extends Language {
 199         function __construct() {
 200                 parent::__construct();
 201
 202                 $variants = [ 'sr', 'sr-ec', 'sr-el' ];
 203                 $variantfallbacks = [
 204                         'sr' => 'sr-ec',
 205                         'sr-ec' => 'sr',
 206                         'sr-el' => 'sr',
 207                 ];
 208
 209                 $flags = [
 210                         'S' => 'S', 'писмо' => 'S', 'pismo' => 'S',
 211                         'W' => 'W', 'реч' => 'W', 'reč' => 'W', 'ријеч' => 'W', 'riječ' => 'W'
 212                 ];
 213                 $this->mConverter = new SrConverter( $this, 'sr', $variants, $variantfallbacks, $flags );
 214         }
 215 }