summaryrefslogtreecommitdiff
path: root/languages/classes/LanguageSr.php
blob: 412463f88b89d51eb26b15d88d61e392c9c60f94 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
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;
	}
}
?>