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
|
<?php
/**
* Serbian (Српски / Srpski) specific code.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
* @ingroup 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.
*
* @ingroup Language
*/
class SrConverter extends LanguageConverter {
public $mToLatin = [
'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',
];
public $mToCyrillics = [
'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'
];
/**
* @param Language $langobj
*/
public function __construct( $langobj ) {
$variants = [ 'sr', 'sr-ec', 'sr-el' ];
$variantfallbacks = [
'sr' => 'sr-ec',
'sr-ec' => 'sr',
'sr-el' => 'sr',
];
$flags = [
'S' => 'S', 'писмо' => 'S', 'pismo' => 'S',
'W' => 'W', 'реч' => 'W', 'reč' => 'W', 'ријеч' => 'W', 'riječ' => 'W'
];
parent::__construct( $langobj, 'sr', $variants, $variantfallbacks, $flags );
}
protected function loadDefaultTables() {
$this->mTables = [
'sr-ec' => new ReplacementArray( $this->mToCyrillics ),
'sr-el' => new ReplacementArray( $this->mToLatin ),
'sr' => new ReplacementArray()
];
}
/**
* A function wrapper:
* - if there is no selected variant, leave the link
* names as they were
* - do not try to find variants for usernames
*
* @param string &$link
* @param Title &$nt
* @param bool $ignoreOtherCond
*/
public function findVariantLink( &$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;
}
}
/**
* It translates text into variant, specials:
* - ommiting roman numbers
*
* @param string $text
* @param string $toVariant
*
* @throws MWException
* @return string
*/
public function translate( $text, $toVariant ) {
$breaks = '[^\w\x80-\xff]';
// regexp for roman numbers
// Lookahead assertion ensures $roman doesn't match the empty string
$roman = '(?=[MDCLXVI])M{0,4}(C[DM]|D?C{0,3})(X[LC]|L?X{0,3})(I[VX]|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 );
$this->loadTables();
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;
}
/**
* Guess if a text is written in Cyrillic or Latin.
* Overrides LanguageConverter::guessVariant()
*
* @param string $text The text to be checked
* @param string $variant Language code of the variant to be checked for
* @return bool True if $text appears to be written in $variant
*
* @author Nikola Smolenski <smolensk@eunet.rs>
* @since 1.19
*/
public function guessVariant( $text, $variant ) {
$numCyrillic = preg_match_all( "/[шђчћжШЂЧЋЖ]/u", $text, $dummy );
$numLatin = preg_match_all( "/[šđč枊ĐČĆŽ]/u", $text, $dummy );
if ( $variant == 'sr-ec' ) {
return $numCyrillic > $numLatin;
} elseif ( $variant == 'sr-el' ) {
return $numLatin > $numCyrillic;
} else {
return false;
}
}
}
|
