MediaWiki  REL1_31
LanguageCrh.php
Go to the documentation of this file.
1 <?php
32  // Defines working character ranges
33  const WORD_BEGINS = '\r\s\"\'\‍(\‍)\-<>\[\]\/.,:;!?';
34  const WORD_ENDS = '\r\s\"\'\‍(\‍)\-<>\[\]\/.,:;!?';
35 
36  // Cyrillic
37  const C_UC = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'; # Crimean Tatar Cyrillic uppercase
38  const C_LC = 'абвгдеёжзийклмнопрстуфхцчшщъыьэюя'; # Crimean Tatar Cyrillic lowercase
39  const C_CONS_UC = 'БВГДЖЗЙКЛМНПРСТФХЦЧШЩCÑ'; # Crimean Tatar Cyrillic + CÑ uppercase consonants
40  const C_CONS_LC = 'бвгджзйклмнпрстфхцчшщcñ'; # Crimean Tatar Cyrillic + CÑ lowercase consonants
41  const C_M_CONS = 'бгкмпшcБГКМПШC'; # Crimean Tatar Cyrillic M-type consonants
42 
43  # Crimean Tatar Cyrillic + CÑ consonants
44  const C_CONS = 'бвгджзйклмнпрстфхцчшщcñБВГДЖЗЙКЛМНПРСТФХЦЧШЩCÑ';
45 
46  // Latin
47  const L_UC = 'AÂBCÇDEFGĞHIİJKLMNÑOÖPQRSŞTUÜVYZ'; # Crimean Tatar Latin uppercase
48  const L_LC = 'aâbcçdefgğhıijklmnñoöpqrsştuüvyz'; # Crimean Tatar Latin lowercase
49  const L_N_CONS_UC = 'ÇNRSTZ'; # Crimean Tatar Latin N-type upper case consonants
50  const L_N_CONS_LC = 'çnrstz'; # Crimean Tatar Latin N-type lower case consonants
51  const L_N_CONS = 'çnrstzÇNRSTZ'; # Crimean Tatar Latin N-type consonants
52  const L_M_CONS = 'bcgkmpşBCGKMPŞ'; # Crimean Tatar Latin M-type consonants
53  const L_CONS_UC = 'BCÇDFGHJKLMNÑPRSŞTVZ'; # Crimean Tatar Latin uppercase consonants
54  const L_CONS_LC = 'bcçdfghjklmnñprsştvz'; # Crimean Tatar Latin lowercase consonants
55  const L_CONS = 'bcçdfghjklmnñprsştvzBCÇDFGHJKLMNÑPRSŞTVZ'; # Crimean Tatar Latin consonants
56  const L_VOW_UC = 'AÂEIİOÖUÜ'; # Crimean Tatar Latin uppercase vowels
57  const L_VOW = 'aâeıioöuüAÂEIİOÖUÜ'; # Crimean Tatar Latin vowels
58  const L_F_UC = 'EİÖÜ'; # Crimean Tatar Latin uppercase front vowels
59  const L_F = 'eiöüEİÖÜ'; # Crimean Tatar Latin front vowels
60 
68  function __construct( $langobj, $maincode,
69  $variants = [],
70  $variantfallbacks = [],
71  $flags = [] ) {
72  parent::__construct( $langobj, $maincode,
73  $variants, $variantfallbacks, $flags );
74 
75  // No point delaying this since they're in code.
76  // Waiting until loadDefaultTables() means they never get loaded
77  // when the tables themselves are loaded from cache.
78  $this->loadExceptions();
79  }
80 
81  public $mCyrillicToLatin = [
82 
83  ## these are independent of location in the word, but have
84  ## to go first so other transforms don't bleed them
85  'гъ' => 'ğ', 'Гъ' => 'Ğ', 'ГЪ' => 'Ğ',
86  'къ' => 'q', 'Къ' => 'Q', 'КЪ' => 'Q',
87  'нъ' => 'ñ', 'Нъ' => 'Ñ', 'НЪ' => 'Ñ',
88  'дж' => 'c', 'Дж' => 'C', 'ДЖ' => 'C',
89 
90  'А' => 'A', 'а' => 'a', 'Б' => 'B', 'б' => 'b',
91  'В' => 'V', 'в' => 'v', 'Г' => 'G', 'г' => 'g',
92  'Д' => 'D', 'д' => 'd', 'Ж' => 'J', 'ж' => 'j',
93  'З' => 'Z', 'з' => 'z', 'И' => 'İ', 'и' => 'i',
94  'Й' => 'Y', 'й' => 'y', 'К' => 'K', 'к' => 'k',
95  'Л' => 'L', 'л' => 'l', 'М' => 'M', 'м' => 'm',
96  'Н' => 'N', 'н' => 'n', 'П' => 'P', 'п' => 'p',
97  'Р' => 'R', 'р' => 'r', 'С' => 'S', 'с' => 's',
98  'Т' => 'T', 'т' => 't', 'Ф' => 'F', 'ф' => 'f',
99  'Х' => 'H', 'х' => 'h', 'Ч' => 'Ç', 'ч' => 'ç',
100  'Ш' => 'Ş', 'ш' => 'ş', 'Ы' => 'I', 'ы' => 'ı',
101  'Э' => 'E', 'э' => 'e', 'Е' => 'E', 'е' => 'e',
102  'Я' => 'Â', 'я' => 'â', 'У' => 'U', 'у' => 'u',
103  'О' => 'O', 'о' => 'o',
104 
105  'Ё' => 'Yo', 'ё' => 'yo', 'Ю' => 'Yu', 'ю' => 'yu',
106  'Ц' => 'Ts', 'ц' => 'ts', 'Щ' => 'Şç', 'щ' => 'şç',
107  'Ь' => '', 'ь' => '', 'Ъ' => '', 'ъ' => '',
108 
109  ];
110 
111  public $mLatinToCyrillic = [
112  'Â' => 'Я', 'â' => 'я', 'B' => 'Б', 'b' => 'б',
113  'Ç' => 'Ч', 'ç' => 'ч', 'D' => 'Д', 'd' => 'д',
114  'F' => 'Ф', 'f' => 'ф', 'G' => 'Г', 'g' => 'г',
115  'H' => 'Х', 'h' => 'х', 'I' => 'Ы', 'ı' => 'ы',
116  'İ' => 'И', 'i' => 'и', 'J' => 'Ж', 'j' => 'ж',
117  'K' => 'К', 'k' => 'к', 'L' => 'Л', 'l' => 'л',
118  'M' => 'М', 'm' => 'м', 'N' => 'Н', 'n' => 'н',
119  'O' => 'О', 'o' => 'о', 'P' => 'П', 'p' => 'п',
120  'R' => 'Р', 'r' => 'р', 'S' => 'С', 's' => 'с',
121  'Ş' => 'Ш', 'ş' => 'ш', 'T' => 'Т', 't' => 'т',
122  'V' => 'В', 'v' => 'в', 'Z' => 'З', 'z' => 'з',
123 
124  'ya' => 'я', 'Ya' => 'Я', 'YA' => 'Я',
125  'ye' => 'е', 'YE' => 'Е', 'Ye' => 'Е',
126 
127  // hack, hack, hack
128  'A' => 'А', 'a' => 'а', 'E' => 'Е', 'e' => 'е',
129  'Ö' => 'Ё', 'ö' => 'ё', 'U' => 'У', 'u' => 'у',
130  'Ü' => 'Ю', 'ü' => 'ю', 'Y' => 'Й', 'y' => 'й',
131  'C' => 'Дж', 'c' => 'дж', 'Ğ' => 'Гъ', 'ğ' => 'гъ',
132  'Ñ' => 'Нъ', 'ñ' => 'нъ', 'Q' => 'Къ', 'q' => 'къ',
133 
134  ];
135 
136  public $mExceptions = [];
137  public $mCyrl2LatnPatterns = [];
138  public $mLatn2CyrlPatterns = [];
139  public $mCyrlCleanUpRegexes = [];
140 
141  public $mExceptionsLoaded = false;
142 
143  function loadDefaultTables() {
144  $this->mTables = [
145  'crh-latn' => new ReplacementArray( $this->mCyrillicToLatin ),
146  'crh-cyrl' => new ReplacementArray( $this->mLatinToCyrillic ),
147  'crh' => new ReplacementArray()
148  ];
149  }
150 
151  function loadExceptions() {
152  if ( $this->mExceptionsLoaded ) {
153  return;
154  }
155 
156  $this->mExceptionsLoaded = true;
157  $crhExceptions = new MediaWiki\Languages\Data\CrhExceptions();
158  list( $this->mExceptions, $this->mCyrl2LatnPatterns, $this->mLatn2CyrlPatterns,
159  $this->mCyrlCleanUpRegexes ) = $crhExceptions->loadExceptions( self::L_LC . self::C_LC,
160  self::L_UC . self::C_UC );
161  }
162 
173  function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) {
174  // check for user namespace
175  if ( is_object( $nt ) ) {
176  $ns = $nt->getNamespace();
177  if ( $ns == NS_USER || $ns == NS_USER_TALK ) {
178  return;
179  }
180  }
181 
182  $oldlink = $link;
183  parent::findVariantLink( $link, $nt, $ignoreOtherCond );
184  if ( $this->getPreferredVariant() == $this->mMainLanguageCode ) {
185  $link = $oldlink;
186  }
187  }
188 
199  function translate( $text, $toVariant ) {
200  $letters = '';
201  switch ( $toVariant ) {
202  case 'crh-cyrl':
203  $letters = self::L_UC . self::L_LC . "\'";
204  break;
205  case 'crh-latn':
206  $letters = self::C_UC . self::C_LC . "";
207  break;
208  default:
209  return $text;
210  break;
211  }
212 
213  if ( !$this->mTablesLoaded ) {
214  $this->loadTables();
215  }
216 
217  if ( !isset( $this->mTables[$toVariant] ) ) {
218  throw new MWException( "Broken variant table: " . implode( ',', array_keys( $this->mTables ) ) );
219  }
220 
221  // check for roman numbers like VII, XIX...
222  // Lookahead assertion ensures $roman doesn't match the empty string
223  $roman = '/^(?=[MDCLXVI])M{0,4}(C[DM]|D?C{0,3})(X[LC]|L?X{0,3})(I[VX]|V?I{0,3})$/u';
224 
225  # match any sub-string of the relevant letters and convert it
226  $matches = preg_split( '/(\b|^)[^' . $letters . ']+(\b|$)/u',
227  $text, -1, PREG_SPLIT_OFFSET_CAPTURE );
228  $mstart = 0;
229  $ret = '';
230  foreach ( $matches as $m ) {
231  # copy over the non-matching bit
232  $ret .= substr( $text, $mstart, $m[1] - $mstart );
233  # skip certain classes of strings
234 
235  if ( array_key_exists( $m[0], $this->mExceptions ) ) {
236  # if it's an exception, just copy down the right answer
237  $ret .= $this->mExceptions[$m[0]];
238  } elseif ( ! $m[0] || # empty strings
239  preg_match( $roman, $m[0] ) || # roman numerals
240  preg_match( '/[^' . $letters . ']/', $m[0] ) # mixed orthography
241  ) {
242  $ret .= $m[0];
243  } else {
244  # convert according to the rules
245  $token = $this->regsConverter( $m[0], $toVariant );
246  $ret .= parent::translate( $token, $toVariant );
247  }
248  $mstart = $m[1] + strlen( $m[0] );
249  }
250 
251  # pick up stray quote marks
252  switch ( $toVariant ) {
253  case 'crh-cyrl':
254  $ret = strtr( $ret, [ '“' => '«', '”' => '»', ] );
255  $ret = $this->regsConverter( $ret, 'cyrl-cleanup' );
256  break;
257  case 'crh-latn':
258  $ret = strtr( $ret, [ '«' => '"', '»' => '"', ] );
259  break;
260  }
261 
262  return $ret;
263  }
264 
265  private function regsConverter( $text, $toVariant ) {
266  if ( $text == '' ) return $text;
267 
268  $pat = [];
269  $rep = [];
270  switch ( $toVariant ) {
271  case 'crh-latn':
272  foreach ( $this->mCyrl2LatnPatterns as $pat => $rep ) {
273  $text = preg_replace( $pat, $rep, $text );
274  }
275  return $text;
276  case 'crh-cyrl':
277  foreach ( $this->mLatn2CyrlPatterns as $pat => $rep ) {
278  $text = preg_replace( $pat, $rep, $text );
279  }
280  return $text;
281  case 'cyrl-cleanup':
282  foreach ( $this->mCyrlCleanUpRegexes as $pat => $rep ) {
283  $text = preg_replace( $pat, $rep, $text );
284  }
285  return $text;
286  default:
287  return $text;
288  }
289  }
290 
291 }
292 
298 class LanguageCrh extends Language {
299 
300  function __construct() {
301  parent::__construct();
302 
303  $variants = [ 'crh', 'crh-cyrl', 'crh-latn' ];
304  $variantfallbacks = [
305  'crh' => 'crh-latn',
306  'crh-cyrl' => 'crh-latn',
307  'crh-latn' => 'crh-cyrl',
308  ];
309 
310  $this->mConverter = new CrhConverter( $this, 'crh', $variants, $variantfallbacks );
311  }
312 }
strings
it sets a lot of them automatically from query strings
Definition: design.txt:93
type
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 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:30
MediaWiki\Languages\Data\CrhExceptions
Definition: CrhExceptions.php:14
CrhConverter\L_N_CONS
const L_N_CONS
Definition: LanguageCrh.php:51
LanguageCrh
Crimean Tatar (Qırımtatarca)
Definition: LanguageCrh.php:298
CrhConverter\loadExceptions
loadExceptions()
Definition: LanguageCrh.php:151
$ret
null means default in associative array with keys and values unescaped Should be merged with default with a value of false meaning to suppress the attribute in associative array with keys and values unescaped noclasses & $ret
Definition: hooks.txt:2005
CrhConverter\C_M_CONS
const C_M_CONS
Definition: LanguageCrh.php:41
CrhConverter\L_CONS_LC
const L_CONS_LC
Definition: LanguageCrh.php:54
CrhConverter\$mLatinToCyrillic
$mLatinToCyrillic
Definition: LanguageCrh.php:111
CrhConverter\loadDefaultTables
loadDefaultTables()
Load default conversion tables.
Definition: LanguageCrh.php:143
CrhConverter\L_N_CONS_UC
const L_N_CONS_UC
Definition: LanguageCrh.php:49
php
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:37
MWException
MediaWiki exception.
Definition: MWException.php:26
CrhConverter\$mExceptions
$mExceptions
Definition: LanguageCrh.php:136
CrhConverter\L_CONS_UC
const L_CONS_UC
Definition: LanguageCrh.php:53
CrhConverter\L_CONS
const L_CONS
Definition: LanguageCrh.php:55
$matches
$matches
Definition: NoLocalSettings.php:24
CrhConverter\WORD_ENDS
const WORD_ENDS
Definition: LanguageCrh.php:34
CrhConverter\L_F_UC
const L_F_UC
Definition: LanguageCrh.php:58
CrhConverter\L_VOW_UC
const L_VOW_UC
Definition: LanguageCrh.php:56
CrhConverter\findVariantLink
findVariantLink(&$link, &$nt, $ignoreOtherCond=false)
A function wrapper:
Definition: LanguageCrh.php:173
CrhConverter\regsConverter
regsConverter( $text, $toVariant)
Definition: LanguageCrh.php:265
$link
usually copyright or history_copyright This message must be in HTML not wikitext & $link
Definition: hooks.txt:3021
CrhConverter\C_CONS_UC
const C_CONS_UC
Definition: LanguageCrh.php:39
CrhConverter\$mCyrillicToLatin
$mCyrillicToLatin
Definition: LanguageCrh.php:81
list
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
CrhConverter\C_LC
const C_LC
Definition: LanguageCrh.php:38
CrhConverter\$mCyrl2LatnPatterns
$mCyrl2LatnPatterns
Definition: LanguageCrh.php:137
NS_USER_TALK
const NS_USER_TALK
Definition: Defines.php:77
ReplacementArray
Wrapper around strtr() that holds replacements.
Definition: ReplacementArray.php:24
CrhConverter\L_VOW
const L_VOW
Definition: LanguageCrh.php:57
CrhConverter\C_CONS_LC
const C_CONS_LC
Definition: LanguageCrh.php:40
CrhConverter\C_CONS
const C_CONS
Definition: LanguageCrh.php:44
LanguageConverter\getPreferredVariant
getPreferredVariant()
Get preferred language variant.
Definition: LanguageConverter.php:161
CrhConverter\L_N_CONS_LC
const L_N_CONS_LC
Definition: LanguageCrh.php:50
CrhConverter
Crimean Tatar (Qırımtatarca) converter routines.
Definition: LanguageCrh.php:31
LanguageConverter\loadTables
loadTables( $fromCache=true)
Load conversion tables either from the cache or the disk.
Definition: LanguageConverter.php:913
CrhConverter\L_LC
const L_LC
Definition: LanguageCrh.php:48
CrhConverter\$mExceptionsLoaded
$mExceptionsLoaded
Definition: LanguageCrh.php:141
CrhConverter\L_M_CONS
const L_M_CONS
Definition: LanguageCrh.php:52
CrhConverter\translate
translate( $text, $toVariant)
It translates text into variant, specials:
Definition: LanguageCrh.php:199
CrhConverter\$mCyrlCleanUpRegexes
$mCyrlCleanUpRegexes
Definition: LanguageCrh.php:139
CrhConverter\$mLatn2CyrlPatterns
$mLatn2CyrlPatterns
Definition: LanguageCrh.php:138
Makefile.translate
def translate(text, conv_table)
Definition: Makefile.py:235
as
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:22
CrhConverter\__construct
__construct( $langobj, $maincode, $variants=[], $variantfallbacks=[], $flags=[])
Definition: LanguageCrh.php:68
LanguageCrh\__construct
__construct()
Definition: LanguageCrh.php:300
NS_USER
const NS_USER
Definition: Defines.php:76
CrhConverter\L_UC
const L_UC
Definition: LanguageCrh.php:47
LanguageConverter
Base class for language conversion.
Definition: LanguageConverter.php:34
Language
Internationalisation code.
Definition: Language.php:35
CrhConverter\C_UC
const C_UC
Definition: LanguageCrh.php:37
CrhConverter\WORD_BEGINS
const WORD_BEGINS
Definition: LanguageCrh.php:33
CrhConverter\L_F
const L_F
Definition: LanguageCrh.php:59