summaryrefslogtreecommitdiff
path: root/languages/classes/LanguageSr.php
blob: b26a2543894b0af3df2517aa9115684a100a4eab (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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
<?php

require_once( dirname( __FILE__ ) . '/../LanguageConverter.php' );
require_once( dirname( __FILE__ ) . '/LanguageSr_ec.php' );
require_once( dirname( __FILE__ ) . '/LanguageSr_el.php' );

/**
 * 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.
 *
 * @ingroup Language
 */
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(
			'sr-ec' => new ReplacementArray( $this->mToCyrillics ),
			'sr-el' => new ReplacementArray( $this->mToLatin ),
			'sr'    => new ReplacementArray()
		);
	}

	/**
	 * 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
	 *
	 * @param $rule string
	 * @param $flags array
	 * @return array
	 */
	function parseManualRule( $rule, $flags = array() ) {
		if ( in_array( 'T', $flags ) ) {
			return parent::parseManualRule( $rule, $flags );
		}

		$carray = array();
		// otherwise ignore all formatting
		foreach ( $this->mVariants as $v ) {
			$carray[$v] = $rule;
		}

		return $carray;
	}

	/**
	 * A function wrapper:
	 *   - if there is no selected variant, leave the link
	 *     names as they were
	 *   - do not try to find variants for usernames
	 *
	 * @param $link string
	 * @param $nt Title
	 * @param $ignoreOtherCond bool
	 */
	function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) {
		// check for user namespace
		if ( is_object( $nt ) ) {
			$ns = $nt->getNamespace();
			if ( $ns == NS_USER || $ns == NS_USER_TALK )
				return;
		}

		$oldlink = $link;
		parent::findVariantLink( $link, $nt, $ignoreOtherCond );
		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
	 *
	 * @param $text string
	 * @param $noParse bool
	 *
	 * @return string
	 */
	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)
	 *
	 * @param $text string
	 * @param $toVariant bool
	 *
	 * @return string
	 */
	function autoConvert( $text, $toVariant = false ) {
		global $wgTitle;
		if ( is_object( $wgTitle ) && $wgTitle->getNameSpace() == NS_FILE ) {
			$imagename = $wgTitle->getNsText();
			if ( preg_match( "/^$imagename:/", $text ) ) return $text;
		}
		return parent::autoConvert( $text, $toVariant );
	}

	/**
	 *  It translates text into variant, specials:
	 *    - ommiting roman numbers
	 *
	 * @param $text string
	 * @param $toVariant string
	 *
	 * @return string
	 */
	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 );
		if ( !isset( $this->mTables[$toVariant] ) ) {
			throw new MWException( "Broken variant table: " . implode( ',', array_keys( $this->mTables ) ) );
		}
		$ret = $this->mTables[$toVariant]->replace( $m[0] );
		$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;
	}
}

/**
 * Serbian (Српски / Srpski)
 *
 * @ingroup Language
 */
class LanguageSr extends LanguageSr_ec {
	function __construct() {
		global $wgHooks;

		parent::__construct();

		$variants = array( 'sr', 'sr-ec', 'sr-el' );
		$variantfallbacks = array(
			'sr'    => 'sr-ec',
			'sr-ec' => 'sr',
			'sr-el' => 'sr',
		);

		$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, $flags );
		$wgHooks['ArticleSaveComplete'][] = $this->mConverter;
	}

	/**
	 * @param $count int
	 * @param $forms array
	 *
	 * @return string
	 */
	function convertPlural( $count, $forms ) {
		if ( !count( $forms ) ) {
			return '';
		}

		// if no number with word, then use $form[0] for singular and $form[1] for plural or zero
		if ( count( $forms ) === 2 ) {
			return $count == 1 ? $forms[0] : $forms[1];
		}

		// @todo FIXME: CLDR defines 4 plural forms. Form with decimals missing.
		// See http://unicode.org/repos/cldr-tmp/trunk/diff/supplemental/language_plural_rules.html#ru
		$forms = $this->preConvertPlural( $forms, 3 );

		if ( $count > 10 && floor( ( $count % 100 ) / 10 ) == 1 ) {
			return $forms[2];
		} else {
			switch ( $count % 10 ) {
				case 1:  return $forms[0];
				case 2:
				case 3:
				case 4:  return $forms[1];
				default: return $forms[2];
			}
		}
	}
}