MediaWiki  master
LanguageCrh.php
Go to the documentation of this file.
1 <?php
32  // Defines working character ranges
33 
34  // Cyrillic
35  const C_UC = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'; # Crimean Tatar Cyrillic uppercase
36  const C_LC = 'абвгдеёжзийклмнопрстуфхцчшщъыьэюя'; # Crimean Tatar Cyrillic lowercase
37  const C_CONS_UC = 'БВГДЖЗЙКЛМНПРСТФХЦЧШЩCÑ'; # Crimean Tatar Cyrillic + CÑ uppercase consonants
38  const C_CONS_LC = 'бвгджзйклмнпрстфхцчшщcñ'; # Crimean Tatar Cyrillic + CÑ lowercase consonants
39  const C_M_CONS = 'бгкмшcБГКМШC'; # Crimean Tatar Cyrillic M-type consonants
40 
41  // Crimean Tatar Cyrillic + CÑ consonants
42  const C_CONS = 'бвгджзйклмнпрстфхцчшщcñБВГДЖЗЙКЛМНПРСТФХЦЧШЩCÑ';
43 
44  // Latin
45  const L_UC = 'AÂBCÇDEFGĞHIİJKLMNÑOÖPQRSŞTUÜVYZ'; # Crimean Tatar Latin uppercase
46  const L_LC = 'aâbcçdefgğhıijklmnñoöpqrsştuüvyz'; # Crimean Tatar Latin lowercase
47  const L_N_CONS_UC = 'ÇNRSTZ'; # Crimean Tatar Latin N-type upper case consonants
48  const L_N_CONS_LC = 'çnrstz'; # Crimean Tatar Latin N-type lower case consonants
49  const L_N_CONS = 'çnrstzÇNRSTZ'; # Crimean Tatar Latin N-type consonants
50  const L_M_CONS = 'bcgkmpşBCGKMPŞ'; # Crimean Tatar Latin M-type consonants
51  const L_CONS_UC = 'BCÇDFGĞHJKLMNÑPQRSŞTVZ'; # Crimean Tatar Latin uppercase consonants
52  const L_CONS_LC = 'bcçdfgğhjklmnñpqrsştvz'; # Crimean Tatar Latin lowercase consonants
53  const L_CONS = 'bcçdfgğhjklmnñpqrsştvzBCÇDFGĞHJKLMNÑPQRSŞTVZ'; # Crimean Tatar Latin consonants
54  const L_VOW_UC = 'AÂEIİOÖUÜ'; # Crimean Tatar Latin uppercase vowels
55  const L_VOW = 'aâeıioöuüAÂEIİOÖUÜ'; # Crimean Tatar Latin vowels
56  const L_F_UC = 'EİÖÜ'; # Crimean Tatar Latin uppercase front vowels
57  const L_F = 'eiöüEİÖÜ'; # Crimean Tatar Latin front vowels
58 
66  function __construct( Language $langobj, $maincode,
67  $variants = [],
68  $variantfallbacks = [],
69  $flags = []
70  ) {
71  parent::__construct( $langobj, $maincode,
72  $variants, $variantfallbacks, $flags );
73 
74  // No point delaying this since they're in code.
75  // Waiting until loadDefaultTables() means they never get loaded
76  // when the tables themselves are loaded from cache.
77  $this->loadExceptions();
78  }
79 
80  public $mCyrillicToLatin = [
81 
82  ## these are independent of location in the word, but have
83  ## to go first so other transforms don't bleed them
84  'гъ' => 'ğ', 'Гъ' => 'Ğ', 'ГЪ' => 'Ğ',
85  'къ' => 'q', 'Къ' => 'Q', 'КЪ' => 'Q',
86  'нъ' => 'ñ', 'Нъ' => 'Ñ', 'НЪ' => 'Ñ',
87  'дж' => 'c', 'Дж' => 'C', 'ДЖ' => 'C',
88 
89  'А' => 'A', 'а' => 'a', 'Б' => 'B', 'б' => 'b',
90  'В' => 'V', 'в' => 'v', 'Г' => 'G', 'г' => 'g',
91  'Д' => 'D', 'д' => 'd', 'Ж' => 'J', 'ж' => 'j',
92  'З' => 'Z', 'з' => 'z', 'И' => 'İ', 'и' => 'i',
93  'Й' => 'Y', 'й' => 'y', 'К' => 'K', 'к' => 'k',
94  'Л' => 'L', 'л' => 'l', 'М' => 'M', 'м' => 'm',
95  'Н' => 'N', 'н' => 'n', 'П' => 'P', 'п' => 'p',
96  'Р' => 'R', 'р' => 'r', 'С' => 'S', 'с' => 's',
97  'Т' => 'T', 'т' => 't', 'Ф' => 'F', 'ф' => 'f',
98  'Х' => 'H', 'х' => 'h', 'Ч' => 'Ç', 'ч' => 'ç',
99  'Ш' => 'Ş', 'ш' => 'ş', 'Ы' => 'I', 'ы' => 'ı',
100  'Э' => 'E', 'э' => 'e', 'Е' => 'E', 'е' => 'e',
101  'Я' => 'Â', 'я' => 'â', 'У' => 'U', 'у' => 'u',
102  'О' => 'O', 'о' => 'o',
103 
104  'Ё' => 'Yo', 'ё' => 'yo', 'Ю' => 'Yu', 'ю' => 'yu',
105  'Ц' => 'Ts', 'ц' => 'ts', 'Щ' => 'Şç', 'щ' => 'şç',
106  'Ь' => '', 'ь' => '', 'Ъ' => '', 'ъ' => '',
107 
108  ];
109 
110  public $mLatinToCyrillic = [
111  'Â' => 'Я', 'â' => 'я', 'B' => 'Б', 'b' => 'б',
112  'Ç' => 'Ч', 'ç' => 'ч', 'D' => 'Д', 'd' => 'д',
113  'F' => 'Ф', 'f' => 'ф', 'G' => 'Г', 'g' => 'г',
114  'H' => 'Х', 'h' => 'х', 'I' => 'Ы', 'ı' => 'ы',
115  'İ' => 'И', 'i' => 'и', 'J' => 'Ж', 'j' => 'ж',
116  'K' => 'К', 'k' => 'к', 'L' => 'Л', 'l' => 'л',
117  'M' => 'М', 'm' => 'м', 'N' => 'Н', 'n' => 'н',
118  'O' => 'О', 'o' => 'о', 'P' => 'П', 'p' => 'п',
119  'R' => 'Р', 'r' => 'р', 'S' => 'С', 's' => 'с',
120  'Ş' => 'Ш', 'ş' => 'ш', 'T' => 'Т', 't' => 'т',
121  'V' => 'В', 'v' => 'в', 'Z' => 'З', 'z' => 'з',
122 
123  'ya' => 'я', 'Ya' => 'Я', 'YA' => 'Я',
124  'ye' => 'е', 'YE' => 'Е', 'Ye' => 'Е',
125 
126  // hack, hack, hack
127  'A' => 'А', 'a' => 'а', 'E' => 'Е', 'e' => 'е',
128  'Ö' => 'Ё', 'ö' => 'ё', 'U' => 'У', 'u' => 'у',
129  'Ü' => 'Ю', 'ü' => 'ю', 'Y' => 'Й', 'y' => 'й',
130  'C' => 'Дж', 'c' => 'дж', 'Ğ' => 'Гъ', 'ğ' => 'гъ',
131  'Ñ' => 'Нъ', 'ñ' => 'нъ', 'Q' => 'Къ', 'q' => 'къ',
132 
133  ];
134 
135  public $mCyrl2LatnExceptions = [];
136  public $mLatn2CyrlExceptions = [];
137 
138  public $mCyrl2LatnPatterns = [];
139  public $mLatn2CyrlPatterns = [];
140 
141  public $mCyrlCleanUpRegexes = [];
142 
143  public $mExceptionsLoaded = false;
144 
145  function loadDefaultTables() {
146  $this->mTables = [
147  'crh-latn' => new ReplacementArray( $this->mCyrillicToLatin ),
148  'crh-cyrl' => new ReplacementArray( $this->mLatinToCyrillic ),
149  'crh' => new ReplacementArray()
150  ];
151  }
152 
153  function loadExceptions() {
154  if ( $this->mExceptionsLoaded ) {
155  return;
156  }
157 
158  $this->mExceptionsLoaded = true;
159  $crhExceptions = new MediaWiki\Languages\Data\CrhExceptions();
160  list( $this->mCyrl2LatnExceptions, $this->mLatn2CyrlExceptions,
161  $this->mCyrl2LatnPatterns, $this->mLatn2CyrlPatterns, $this->mCyrlCleanUpRegexes ) =
162  $crhExceptions->loadExceptions( self::L_LC . self::C_LC, self::L_UC . self::C_UC );
163  }
164 
175  function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) {
176  // check for user namespace
177  if ( is_object( $nt ) ) {
178  $ns = $nt->getNamespace();
179  if ( $ns == NS_USER || $ns == NS_USER_TALK ) {
180  return;
181  }
182  }
183 
184  $oldlink = $link;
185  parent::findVariantLink( $link, $nt, $ignoreOtherCond );
186  if ( $this->getPreferredVariant() == $this->mMainLanguageCode ) {
187  $link = $oldlink;
188  }
189  }
190 
201  function translate( $text, $toVariant ) {
202  switch ( $toVariant ) {
203  case 'crh-cyrl':
204  case 'crh-latn':
205  break;
206  default:
207  return $text;
208  }
209 
210  if ( !$this->mTablesLoaded ) {
211  $this->loadTables();
212  }
213 
214  if ( !isset( $this->mTables[$toVariant] ) ) {
215  throw new MWException( "Broken variant table: " . implode( ',', array_keys( $this->mTables ) ) );
216  }
217 
218  switch ( $toVariant ) {
219  case 'crh-cyrl':
220  /* Check for roman numbers like VII, XIX...
221  * Only need to split on Roman numerals when converting to Cyrillic
222  * Lookahead assertion ensures $roman doesn't match the empty string, and
223  * non-period after first "Roman" character allows initials to be converted
224  */
225  $roman = '(?=[MDCLXVI]([^.]|$))M{0,4}(C[DM]|D?C{0,3})(X[LC]|L?X{0,3})(I[VX]|V?I{0,3})';
226 
227  $breaks = '([^\w\x80-\xff])';
228 
229  // allow for multiple Roman numerals in a row; rare but it happens
230  $romanRegex = '/^' . $roman . '$|^(' . $roman . $breaks . ')+|(' . $breaks . $roman . ')+$|' .
231  $breaks . '(' . $roman . $breaks . ')+/';
232 
233  $matches = preg_split( $romanRegex, $text, -1, PREG_SPLIT_OFFSET_CAPTURE );
234  $mstart = 0;
235  $ret = '';
236  foreach ( $matches as $m ) {
237  // copy over Roman numerals
238  $ret .= substr( $text, $mstart, $m[1] - $mstart );
239 
240  // process everything else
241  if ( $m[0] !== '' ) {
242  $ret .= $this->regsConverter( $m[0], $toVariant );
243  }
244 
245  $mstart = $m[1] + strlen( $m[0] );
246  }
247 
248  return $ret;
249  default:
250  // Just process the whole string in one go
251  return $this->regsConverter( $text, $toVariant );
252  }
253  }
254 
255  private function regsConverter( $text, $toVariant ) {
256  if ( $text == '' ) return $text;
257 
258  $pat = [];
259  $rep = [];
260  switch ( $toVariant ) {
261  case 'crh-latn':
262  $text = strtr( $text, $this->mCyrl2LatnExceptions );
263  foreach ( $this->mCyrl2LatnPatterns as $pat => $rep ) {
264  $text = preg_replace( $pat, $rep, $text );
265  }
266  $text = parent::translate( $text, $toVariant );
267  $text = strtr( $text, [ '«' => '"', '»' => '"', ] );
268  return $text;
269  case 'crh-cyrl':
270  $text = strtr( $text, $this->mLatn2CyrlExceptions );
271  foreach ( $this->mLatn2CyrlPatterns as $pat => $rep ) {
272  $text = preg_replace( $pat, $rep, $text );
273  }
274  $text = parent::translate( $text, $toVariant );
275  $text = strtr( $text, [ '“' => '«', '”' => '»', ] );
276  foreach ( $this->mCyrlCleanUpRegexes as $pat => $rep ) {
277  $text = preg_replace( $pat, $rep, $text );
278  }
279  return $text;
280  default:
281  return $text;
282  }
283  }
284 
285 }
286 
292 class LanguageCrh extends Language {
293 
294  function __construct() {
295  parent::__construct();
296 
297  $variants = [ 'crh', 'crh-cyrl', 'crh-latn' ];
298  $variantfallbacks = [
299  'crh' => 'crh-latn',
300  'crh-cyrl' => 'crh-latn',
301  'crh-latn' => 'crh-cyrl',
302  ];
303 
304  $this->mConverter = new CrhConverter( $this, 'crh', $variants, $variantfallbacks );
305  }
306 }
Wrapper around strtr() that holds replacements.
deferred txt A few of the database updates required by various functions here can be deferred until after the result page is displayed to the user For updating the view updating the linked to tables after a etc PHP does not yet have any way to tell the server to actually return and disconnect while still running these but it might have such a feature in the future We handle these by creating a deferred update object and putting those objects on a global list
Definition: deferred.txt:11
default $toVariant
foreach( $matches as $m) return $ret
const L_CONS_LC
Definition: LanguageCrh.php:52
Crimean Tatar (Qırımtatarca)
const L_CONS_UC
Definition: LanguageCrh.php:51
__construct(Language $langobj, $maincode, $variants=[], $variantfallbacks=[], $flags=[])
Definition: LanguageCrh.php:66
const L_VOW_UC
Definition: LanguageCrh.php:54
usually copyright or history_copyright This message must be in HTML not wikitext & $link
Definition: hooks.txt:3050
const C_M_CONS
Definition: LanguageCrh.php:39
const L_N_CONS_LC
Definition: LanguageCrh.php:48
findVariantLink(&$link, &$nt, $ignoreOtherCond=false)
If a language supports multiple variants, it is possible that non-existing link in one variant actual...
const L_N_CONS_UC
Definition: LanguageCrh.php:47
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:9
translate( $text, $variant)
Translate a string to a variant.
regsConverter( $text, $toVariant)
const C_CONS_UC
Definition: LanguageCrh.php:37
def translate(text, conv_table)
Definition: Makefile.py:235
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:35
This document describes the state of Postgres support in and is fairly well maintained The main code is very well while extensions are very hit and miss it is probably the most supported database after MySQL Much of the work in making MediaWiki database agnostic came about through the work of creating Postgres as and are nearing end of but without copying over all the usage comments General notes on the but these can almost always be programmed around *Although Postgres has a true BOOLEAN type
Definition: postgres.txt:22
const C_CONS_LC
Definition: LanguageCrh.php:38
Crimean Tatar (Qırımtatarca) converter routines.
Definition: LanguageCrh.php:31
const NS_USER_TALK
Definition: Defines.php:63
const L_M_CONS
Definition: LanguageCrh.php:50
getPreferredVariant()
Get preferred language variant.
const L_N_CONS
Definition: LanguageCrh.php:49
loadDefaultTables()
Load default conversion tables.
loadTables( $fromCache=true)
Load conversion tables either from the cache or the disk.