| [ Index ] |
PHP Cross Reference of MediaWiki-1.24.0 |
[Summary view] [Print] [Text view]
1 <?php 2 /** 3 * Kazakh (Қазақша) specific code. 4 * 5 * This program is free software; you can redistribute it and/or modify 6 * it under the terms of the GNU General Public License as published by 7 * the Free Software Foundation; either version 2 of the License, or 8 * (at your option) any later version. 9 * 10 * This program is distributed in the hope that it will be useful, 11 * but WITHOUT ANY WARRANTY; without even the implied warranty of 12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 * GNU General Public License for more details. 14 * 15 * You should have received a copy of the GNU General Public License along 16 * with this program; if not, write to the Free Software Foundation, Inc., 17 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. 18 * http://www.gnu.org/copyleft/gpl.html 19 * 20 * @file 21 * @ingroup Language 22 */ 23 24 require_once __DIR__ . '/../LanguageConverter.php'; 25 require_once __DIR__ . '/LanguageKk_cyrl.php'; 26 27 define( 'KK_C_UC', 'АӘБВГҒДЕЁЖЗИЙКҚЛМНҢОӨПРСТУҰҮФХҺЦЧШЩЪЫІЬЭЮЯ' ); # Kazakh Cyrillic uppercase 28 define( 'KK_C_LC', 'аәбвгғдеёжзийкқлмнңоөпрстуұүфхһцчшщъыіьэюя' ); # Kazakh Cyrillic lowercase 29 define( 'KK_L_UC', 'AÄBCÇDEÉFGĞHIİÏJKLMNÑOÖPQRSŞTUÜVWXYÝZ' ); # Kazakh Latin uppercase 30 define( 'KK_L_LC', 'aäbcçdeéfgğhıiïjklmnñoöpqrsştuüvwxyýz' ); # Kazakh Latin lowercase 31 // define( 'KK_A', 'ٴابپتجحدرزسشعفقكلمنڭەوۇۋۆىيچھ' ); # Kazakh Arabic 32 define( 'H_HAMZA', 'ٴ' ); # U+0674 ARABIC LETTER HIGH HAMZA 33 // define( 'ZWNJ', '' ); # U+200C ZERO WIDTH NON-JOINER 34 35 /** 36 * Kazakh (Қазақша) converter routines 37 * 38 * @ingroup Language 39 */ 40 class KkConverter extends LanguageConverter { 41 protected $mCyrl2Latn, $mLatn2Cyrl, $mCyLa2Arab; 42 43 /** 44 * @param Language $langobj 45 * @param string $maincode 46 * @param array $variants 47 * @param array $variantfallbacks 48 * @param array $flags 49 */ 50 function __construct( $langobj, $maincode, 51 $variants = array(), 52 $variantfallbacks = array(), 53 $flags = array() ) { 54 parent::__construct( $langobj, $maincode, 55 $variants, $variantfallbacks, $flags ); 56 57 // No point delaying this since they're in code. 58 // Waiting until loadDefaultTables() means they never get loaded 59 // when the tables themselves are loaded from cache. 60 $this->loadRegs(); 61 } 62 63 function loadDefaultTables() { 64 // require __DIR__."/../../includes/KkConversion.php"; 65 // Placeholder for future implementing. Remove variables declarations 66 // after generating KkConversion.php 67 $kk2Cyrl = array(); 68 $kk2Latn = array(); 69 $kk2Arab = array(); 70 $kk2KZ = array(); 71 $kk2TR = array(); 72 $kk2CN = array(); 73 74 $this->mTables = array( 75 'kk-cyrl' => new ReplacementArray( $kk2Cyrl ), 76 'kk-latn' => new ReplacementArray( $kk2Latn ), 77 'kk-arab' => new ReplacementArray( $kk2Arab ), 78 'kk-kz' => new ReplacementArray( array_merge( $kk2Cyrl, $kk2KZ ) ), 79 'kk-tr' => new ReplacementArray( array_merge( $kk2Latn, $kk2TR ) ), 80 'kk-cn' => new ReplacementArray( array_merge( $kk2Arab, $kk2CN ) ), 81 'kk' => new ReplacementArray() 82 ); 83 } 84 85 function postLoadTables() { 86 $this->mTables['kk-kz']->merge( $this->mTables['kk-cyrl'] ); 87 $this->mTables['kk-tr']->merge( $this->mTables['kk-latn'] ); 88 $this->mTables['kk-cn']->merge( $this->mTables['kk-arab'] ); 89 } 90 91 function loadRegs() { 92 93 $this->mCyrl2Latn = array( 94 # # Punctuation 95 '/№/u' => 'No.', 96 # # Е after vowels 97 '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])Е/u' => '$1YE', 98 '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])е/ui' => '$1ye', 99 # # leading ЁЮЯЩ 100 '/^Ё([' . KK_C_UC . ']|$)/u' => 'YO$1', '/^Ё([' . KK_C_LC . ']|$)/u' => 'Yo$1', 101 '/^Ю([' . KK_C_UC . ']|$)/u' => 'YU$1', '/^Ю([' . KK_C_LC . ']|$)/u' => 'Yu$1', 102 '/^Я([' . KK_C_UC . ']|$)/u' => 'YA$1', '/^Я([' . KK_C_LC . ']|$)/u' => 'Ya$1', 103 '/^Щ([' . KK_C_UC . ']|$)/u' => 'ŞÇ$1', '/^Щ([' . KK_C_LC . ']|$)/u' => 'Şç$1', 104 # # other ЁЮЯ 105 '/Ё/u' => 'YO', '/ё/u' => 'yo', 106 '/Ю/u' => 'YU', '/ю/u' => 'yu', 107 '/Я/u' => 'YA', '/я/u' => 'ya', 108 '/Щ/u' => 'ŞÇ', '/щ/u' => 'şç', 109 # # soft and hard signs 110 '/[ъЪ]/u' => 'ʺ', '/[ьЬ]/u' => 'ʹ', 111 # # other characters 112 '/А/u' => 'A', '/а/u' => 'a', '/Ә/u' => 'Ä', '/ә/u' => 'ä', 113 '/Б/u' => 'B', '/б/u' => 'b', '/В/u' => 'V', '/в/u' => 'v', 114 '/Г/u' => 'G', '/г/u' => 'g', '/Ғ/u' => 'Ğ', '/ғ/u' => 'ğ', 115 '/Д/u' => 'D', '/д/u' => 'd', '/Е/u' => 'E', '/е/u' => 'e', 116 '/Ж/u' => 'J', '/ж/u' => 'j', '/З/u' => 'Z', '/з/u' => 'z', 117 '/И/u' => 'Ï', '/и/u' => 'ï', '/Й/u' => 'Ý', '/й/u' => 'ý', 118 '/К/u' => 'K', '/к/u' => 'k', '/Қ/u' => 'Q', '/қ/u' => 'q', 119 '/Л/u' => 'L', '/л/u' => 'l', '/М/u' => 'M', '/м/u' => 'm', 120 '/Н/u' => 'N', '/н/u' => 'n', '/Ң/u' => 'Ñ', '/ң/u' => 'ñ', 121 '/О/u' => 'O', '/о/u' => 'o', '/Ө/u' => 'Ö', '/ө/u' => 'ö', 122 '/П/u' => 'P', '/п/u' => 'p', '/Р/u' => 'R', '/р/u' => 'r', 123 '/С/u' => 'S', '/с/u' => 's', '/Т/u' => 'T', '/т/u' => 't', 124 '/У/u' => 'W', '/у/u' => 'w', '/Ұ/u' => 'U', '/ұ/u' => 'u', 125 '/Ү/u' => 'Ü', '/ү/u' => 'ü', '/Ф/u' => 'F', '/ф/u' => 'f', 126 '/Х/u' => 'X', '/х/u' => 'x', '/Һ/u' => 'H', '/һ/u' => 'h', 127 '/Ц/u' => 'C', '/ц/u' => 'c', '/Ч/u' => 'Ç', '/ч/u' => 'ç', 128 '/Ш/u' => 'Ş', '/ш/u' => 'ş', '/Ы/u' => 'I', '/ы/u' => 'ı', 129 '/І/u' => 'İ', '/і/u' => 'i', '/Э/u' => 'É', '/э/u' => 'é', 130 ); 131 132 $this->mLatn2Cyrl = array( 133 # # Punctuation 134 '/#|No\./' => '№', 135 # # Şç 136 '/ŞÇʹ/u' => 'ЩЬ', '/Şçʹ/u' => 'Щь', 137 '/Ş[Çç]/u' => 'Щ', '/şç/u' => 'щ', 138 # # soft and hard signs 139 '/([' . KK_L_UC . '])ʺ([' . KK_L_UC . '])/u' => '$1Ъ$2', 140 '/ʺ([' . KK_L_LC . '])/u' => 'ъ$1', 141 '/([' . KK_L_UC . '])ʹ([' . KK_L_UC . '])/u' => '$1Ь$2', 142 '/ʹ([' . KK_L_LC . '])/u' => 'ь$1', 143 '/ʺ/u' => 'ъ', 144 '/ʹ/u' => 'ь', 145 # # Ye Yo Yu Ya. 146 '/Y[Ee]/u' => 'Е', '/ye/u' => 'е', 147 '/Y[Oo]/u' => 'Ё', '/yo/u' => 'ё', 148 '/Y[UWuw]/u' => 'Ю', '/y[uw]/u' => 'ю', 149 '/Y[Aa]/u' => 'Я', '/ya/u' => 'я', 150 # # other characters 151 '/A/u' => 'А', '/a/u' => 'а', '/Ä/u' => 'Ә', '/ä/u' => 'ә', 152 '/B/u' => 'Б', '/b/u' => 'б', '/C/u' => 'Ц', '/c/u' => 'ц', 153 '/Ç/u' => 'Ч', '/ç/u' => 'ч', '/D/u' => 'Д', '/d/u' => 'д', 154 '/E/u' => 'Е', '/e/u' => 'е', '/É/u' => 'Э', '/é/u' => 'э', 155 '/F/u' => 'Ф', '/f/u' => 'ф', '/G/u' => 'Г', '/g/u' => 'г', 156 '/Ğ/u' => 'Ғ', '/ğ/u' => 'ғ', '/H/u' => 'Һ', '/h/u' => 'һ', 157 '/I/u' => 'Ы', '/ı/u' => 'ы', '/İ/u' => 'І', '/i/u' => 'і', 158 '/Ï/u' => 'И', '/ï/u' => 'и', '/J/u' => 'Ж', '/j/u' => 'ж', 159 '/K/u' => 'К', '/k/u' => 'к', '/L/u' => 'Л', '/l/u' => 'л', 160 '/M/u' => 'М', '/m/u' => 'м', '/N/u' => 'Н', '/n/u' => 'н', 161 '/Ñ/u' => 'Ң', '/ñ/u' => 'ң', '/O/u' => 'О', '/o/u' => 'о', 162 '/Ö/u' => 'Ө', '/ö/u' => 'ө', '/P/u' => 'П', '/p/u' => 'п', 163 '/Q/u' => 'Қ', '/q/u' => 'қ', '/R/u' => 'Р', '/r/u' => 'р', 164 '/S/u' => 'С', '/s/u' => 'с', '/Ş/u' => 'Ш', '/ş/u' => 'ш', 165 '/T/u' => 'Т', '/t/u' => 'т', '/U/u' => 'Ұ', '/u/u' => 'ұ', 166 '/Ü/u' => 'Ү', '/ü/u' => 'ү', '/V/u' => 'В', '/v/u' => 'в', 167 '/W/u' => 'У', '/w/u' => 'у', '/Ý/u' => 'Й', '/ý/u' => 'й', 168 '/X/u' => 'Х', '/x/u' => 'х', '/Z/u' => 'З', '/z/u' => 'з', 169 ); 170 171 $this->mCyLa2Arab = array( 172 # # Punctuation -> Arabic 173 '/#|№|No\./u' => '', # ؀ 174 '/\,/' => '،', # ، 175 '/;/' => '؛', # ؛ 176 '/\?/' => '؟', # ؟ 177 '/%/' => '٪', # ٪ 178 '/\*/' => '٭', # ٭ 179 # # Digits -> Arabic 180 '/0/' => '۰', # ۰ 181 '/1/' => '۱', # ۱ 182 '/2/' => '۲', # ۲ 183 '/3/' => '۳', # ۳ 184 '/4/' => '۴', # ۴ 185 '/5/' => '۵', # ۵ 186 '/6/' => '۶', # ۶ 187 '/7/' => '۷', # ۷ 188 '/8/' => '۸', # ۸ 189 '/9/' => '۹', # ۹ 190 # # Cyrillic -> Arabic 191 '/Аллаһ/ui' => 'ﷲ', 192 '/([АӘЕЁИОӨҰҮЭЮЯЪЬ])е/ui' => '$1يە', 193 '/[еэ]/ui' => 'ە', '/[ъь]/ui' => '', 194 '/[аә]/ui' => 'ا', '/[оө]/ui' => 'و', '/[ұү]/ui' => 'ۇ', '/[ыі]/ui' => 'ى', 195 '/[и]/ui' => 'ىي', '/ё/ui' => 'يو', '/ю/ui' => 'يۋ', '/я/ui' => 'يا', '/[й]/ui' => 'ي', 196 '/ц/ui' => 'تس', '/щ/ui' => 'شش', 197 '/һ/ui' => 'ح', '/ч/ui' => 'تش', 198 # '/һ/ui' => 'ھ', '/ч/ui' => 'چ', 199 '/б/ui' => 'ب', '/в/ui' => 'ۆ', '/г/ui' => 'گ', '/ғ/ui' => 'ع', 200 '/д/ui' => 'د', '/ж/ui' => 'ج', '/з/ui' => 'ز', '/к/ui' => 'ك', 201 '/қ/ui' => 'ق', '/л/ui' => 'ل', '/м/ui' => 'م', '/н/ui' => 'ن', 202 '/ң/ui' => 'ڭ', '/п/ui' => 'پ', '/р/ui' => 'ر', '/с/ui' => 'س', 203 '/т/ui' => 'ت', '/у/ui' => 'ۋ', '/ф/ui' => 'ف', '/х/ui' => 'ح', 204 '/ш/ui' => 'ش', 205 # # Latin -> Arabic // commented for now... 206 /*'/Allah/ui' => 'ﷲ', 207 '/[eé]/ui' => 'ە', '/[yý]/ui' => 'ي', '/[ʺʹ]/ui' => '', 208 '/[aä]/ui' => 'ا', '/[oö]/ui' => 'و', '/[uü]/ui' => 'ۇ', 209 '/[ï]/ui' => 'ىي', '/[ıIiİ]/u' => 'ى', 210 '/c/ui' => 'تس', 211 '/ç/ui' => 'تش', '/h/ui' => 'ح', 212 #'/ç/ui' => 'چ', '/h/ui' => 'ھ', 213 '/b/ui' => 'ب','/d/ui' => 'د', 214 '/f/ui' => 'ف', '/g/ui' => 'گ', '/ğ/ui' => 'ع', 215 '/j/ui' => 'ج', '/k/ui' => 'ك', '/l/ui' => 'ل', '/m/ui' => 'م', 216 '/n/ui' => 'ن', '/ñ/ui' => 'ڭ', '/p/ui' => 'پ', '/q/ui' => 'ق', 217 '/r/ui' => 'ر', '/s/ui' => 'س', '/ş/ui' => 'ش', '/t/ui' => 'ت', 218 '/v/ui' => 'ۆ', '/w/ui' => 'ۋ', '/x/ui' => 'ح', '/z/ui' => 'ز',*/ 219 ); 220 } 221 222 /** 223 * rules should be defined as -{ekavian | iyekavian-} -or- 224 * -{code:text | code:text | ...}- 225 * 226 * update: delete all rule parsing because it's not used 227 * currently, and just produces a couple of bugs 228 * 229 * @param string $rule 230 * @param array $flags 231 * @return array 232 */ 233 function parseManualRule( $rule, $flags = array() ) { 234 if ( in_array( 'T', $flags ) ) { 235 return parent::parseManualRule( $rule, $flags ); 236 } 237 238 $carray = array(); 239 // otherwise ignore all formatting 240 foreach ( $this->mVariants as $v ) { 241 $carray[$v] = $rule; 242 } 243 244 return $carray; 245 } 246 247 /** 248 * A function wrapper: 249 * - if there is no selected variant, leave the link 250 * names as they were 251 * - do not try to find variants for usernames 252 * 253 * @param string &$link 254 * @param Title &$nt 255 * @param bool $ignoreOtherCond 256 */ 257 function findVariantLink( &$link, &$nt, $ignoreOtherCond = false ) { 258 // check for user namespace 259 if ( is_object( $nt ) ) { 260 $ns = $nt->getNamespace(); 261 if ( $ns == NS_USER || $ns == NS_USER_TALK ) { 262 return; 263 } 264 } 265 266 $oldlink = $link; 267 parent::findVariantLink( $link, $nt, $ignoreOtherCond ); 268 if ( $this->getPreferredVariant() == $this->mMainLanguageCode ) { 269 $link = $oldlink; 270 } 271 } 272 273 /** 274 * It translates text into variant 275 * 276 * @param string $text 277 * @param string $toVariant 278 * 279 * @return string 280 */ 281 function translate( $text, $toVariant ) { 282 global $wgLanguageCode; 283 $text = parent::translate( $text, $toVariant ); 284 285 switch ( $toVariant ) { 286 case 'kk-cyrl': 287 case 'kk-kz': 288 $letters = KK_L_UC . KK_L_LC . 'ʺʹ#0123456789'; 289 $wgLanguageCode = 'kk'; 290 break; 291 case 'kk-latn': 292 case 'kk-tr': 293 $letters = KK_C_UC . KK_C_LC . '№0123456789'; 294 $wgLanguageCode = 'kk-Latn'; 295 break; 296 case 'kk-arab': 297 case 'kk-cn': 298 $letters = KK_C_UC . KK_C_LC . /*KK_L_UC.KK_L_LC.'ʺʹ'.*/',;\?%\*№0123456789'; 299 $wgLanguageCode = 'kk-Arab'; 300 break; 301 default: 302 $wgLanguageCode = 'kk'; 303 return $text; 304 } 305 // disable conversion variables like $1, $2... 306 $varsfix = '\$[0-9]'; 307 308 $matches = preg_split( 309 '/' . $varsfix . '[^' . $letters . ']+/u', 310 $text, 311 -1, 312 PREG_SPLIT_OFFSET_CAPTURE 313 ); 314 315 $mstart = 0; 316 $ret = ''; 317 318 foreach ( $matches as $m ) { 319 $ret .= substr( $text, $mstart, $m[1] -$mstart ); 320 $ret .= $this->regsConverter( $m[0], $toVariant ); 321 $mstart = $m[1] + strlen( $m[0] ); 322 } 323 324 return $ret; 325 } 326 327 /** 328 * @param string $text 329 * @param string $toVariant 330 * @return mixed|string 331 */ 332 function regsConverter( $text, $toVariant ) { 333 if ( $text == '' ) { 334 return $text; 335 } 336 337 switch ( $toVariant ) { 338 case 'kk-arab': 339 case 'kk-cn': 340 $letters = KK_C_LC . KK_C_UC; /*.KK_L_LC.KK_L_UC*/ 341 $front = 'әөүіӘӨҮІ'; /*.'äöüiÄÖÜİ'*/ 342 $excludes = 'еэгғкқЕЭГҒКҚ'; /*.'eégğkqEÉGĞKQ'*/ 343 // split text to words 344 $matches = preg_split( '/[\b\s\-\.:]+/', $text, -1, PREG_SPLIT_OFFSET_CAPTURE ); 345 $mstart = 0; 346 $ret = ''; 347 foreach ( $matches as $m ) { 348 $ret .= substr( $text, $mstart, $m[1] - $mstart ); 349 // is matched the word to front vowels? 350 // exclude a words matched to е, э, г, к, к, қ, 351 // them should be without hamza 352 if ( preg_match( '/[' . $front . ']/u', $m[0] ) 353 && !preg_match( '/[' . $excludes . ']/u', $m[0] ) 354 ) { 355 $ret .= preg_replace( '/[' . $letters . ']+/u', H_HAMZA . '$0', $m[0] ); 356 } else { 357 $ret .= $m[0]; 358 } 359 $mstart = $m[1] + strlen( $m[0] ); 360 } 361 $text =& $ret; 362 foreach ( $this->mCyLa2Arab as $pat => $rep ) { 363 $text = preg_replace( $pat, $rep, $text ); 364 } 365 return $text; 366 break; 367 case 'kk-latn': 368 case 'kk-tr': 369 foreach ( $this->mCyrl2Latn as $pat => $rep ) { 370 $text = preg_replace( $pat, $rep, $text ); 371 } 372 return $text; 373 break; 374 case 'kk-cyrl': 375 case 'kk-kz': 376 foreach ( $this->mLatn2Cyrl as $pat => $rep ) { 377 $text = preg_replace( $pat, $rep, $text ); 378 } 379 return $text; 380 break; 381 default: 382 return $text; 383 } 384 } 385 386 /** 387 * @param string $key 388 * @return string 389 */ 390 function convertCategoryKey( $key ) { 391 return $this->autoConvert( $key, 'kk' ); 392 } 393 } 394 395 /** 396 * class that handles Cyrillic, Latin and Arabic scripts for Kazakh 397 * right now it only distinguish kk_cyrl, kk_latn, kk_arab and kk_kz, kk_tr, kk_cn. 398 * 399 * @ingroup Language 400 */ 401 class LanguageKk extends LanguageKk_cyrl { 402 function __construct() { 403 global $wgHooks; 404 parent::__construct(); 405 406 $variants = array( 'kk', 'kk-cyrl', 'kk-latn', 'kk-arab', 'kk-kz', 'kk-tr', 'kk-cn' ); 407 $variantfallbacks = array( 408 'kk' => 'kk-cyrl', 409 'kk-cyrl' => 'kk', 410 'kk-latn' => 'kk', 411 'kk-arab' => 'kk', 412 'kk-kz' => 'kk-cyrl', 413 'kk-tr' => 'kk-latn', 414 'kk-cn' => 'kk-arab' 415 ); 416 417 $this->mConverter = new KkConverter( $this, 'kk', $variants, $variantfallbacks ); 418 419 $wgHooks['PageContentSaveComplete'][] = $this->mConverter; 420 } 421 422 /** 423 * It fixes issue with ucfirst for transforming 'i' to 'İ' 424 * 425 * @param string $string 426 * 427 * @return string 428 */ 429 function ucfirst( $string ) { 430 $variant = $this->getPreferredVariant(); 431 if ( ( $variant == 'kk-latn' || $variant == 'kk-tr' ) && $string[0] == 'i' ) { 432 $string = 'İ' . substr( $string, 1 ); 433 } else { 434 $string = parent::ucfirst( $string ); 435 } 436 return $string; 437 } 438 439 /** 440 * It fixes issue with lcfirst for transforming 'I' to 'ı' 441 * 442 * @param string $string 443 * 444 * @return string 445 */ 446 function lcfirst( $string ) { 447 $variant = $this->getPreferredVariant(); 448 if ( ( $variant == 'kk-latn' || $variant == 'kk-tr' ) && $string[0] == 'I' ) { 449 $string = 'ı' . substr( $string, 1 ); 450 } else { 451 $string = parent::lcfirst( $string ); 452 } 453 return $string; 454 } 455 456 /** 457 * @param string $word 458 * @param string $case 459 * @return string 460 */ 461 function convertGrammar( $word, $case ) { 462 wfProfileIn( __METHOD__ ); 463 464 $variant = $this->getPreferredVariant(); 465 switch ( $variant ) { 466 case 'kk-arab': 467 case 'kk-cn': 468 $word = parent::convertGrammarKk_arab( $word, $case ); 469 break; 470 case 'kk-latn': 471 case 'kk-tr': 472 $word = parent::convertGrammarKk_latn( $word, $case ); 473 break; 474 case 'kk-cyrl': 475 case 'kk-kz': 476 case 'kk': 477 default: 478 $word = parent::convertGrammarKk_cyrl( $word, $case ); 479 } 480 481 wfProfileOut( __METHOD__ ); 482 return $word; 483 } 484 }
title
Description
Body
title
Description
Body
title
Description
Body
title
Body
| Generated: Fri Nov 28 14:03:12 2014 | Cross-referenced by PHPXref 0.7.1 |