Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 204 |
|
0.00% |
0 / 5 |
CRAP | |
0.00% |
0 / 1 |
| GrammarKk_cyrl | |
0.00% |
0 / 204 |
|
0.00% |
0 / 5 |
14042 | |
0.00% |
0 / 1 |
| process | |
0.00% |
0 / 175 |
|
0.00% |
0 / 1 |
11556 | |||
| lastLetter | |
0.00% |
0 / 15 |
|
0.00% |
0 / 1 |
12 | |||
| lc | |
0.00% |
0 / 3 |
|
0.00% |
0 / 1 |
12 | |||
| lcfirst | |
0.00% |
0 / 10 |
|
0.00% |
0 / 1 |
20 | |||
| isMultibyte | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * @license GPL-2.0-or-later |
| 4 | * @file |
| 5 | */ |
| 6 | |
| 7 | // phpcs:ignoreFile Squiz.Classes.ValidClassName.NotCamelCaps |
| 8 | namespace Wikimedia\Leximorph\Handler\Overrides\Grammar; |
| 9 | |
| 10 | use Wikimedia\Leximorph\Handler\Overrides\IGrammarTransformer; |
| 11 | |
| 12 | /** |
| 13 | * GrammarKk_cyrl |
| 14 | * |
| 15 | * Implements grammar transformations for Kazakh using the Cyrillic script. |
| 16 | * |
| 17 | * These rules don't cover the whole grammar of the language. |
| 18 | * This logic was originally taken from MediaWiki Core. |
| 19 | * Thanks to all contributors. |
| 20 | * |
| 21 | * @since 1.45 |
| 22 | * @author Doğu Abaris (abaris@null.net) |
| 23 | * @license https://www.gnu.org/copyleft/gpl.html GPL-2.0-or-later |
| 24 | */ |
| 25 | class GrammarKk_cyrl implements IGrammarTransformer { |
| 26 | /** |
| 27 | * Applies Cyrillic Kazakh-specific grammatical transformations. |
| 28 | * |
| 29 | * Convert from the nominative form of a noun to some other case |
| 30 | * Invoked with {{GRAMMAR:case|word}} |
| 31 | * |
| 32 | * Cases: genitive, dative, accusative, locative, ablative, comitative + possessive forms |
| 33 | * |
| 34 | * @param string $word The word to process. |
| 35 | * @param string $case The grammatical case. |
| 36 | * |
| 37 | * @since 1.45 |
| 38 | * @return string The processed word. |
| 39 | */ |
| 40 | public function process( string $word, string $case ): string { |
| 41 | // Set up some constants... |
| 42 | // Vowels in last syllable |
| 43 | $frontVowels = [ "е", "ө", "ү", "і", "ә", "э", "я", "ё", "и", ]; |
| 44 | $backVowels = [ "а", "о", "ұ", "ы", ]; |
| 45 | $allVowels = [ "е", "ө", "ү", "і", "ә", "э", "а", "о", "ұ", "ы", "я", "ё", "и", ]; |
| 46 | // Preceding letters |
| 47 | $Nasals = [ "м", "н", "ң", ]; |
| 48 | $Sonants = [ "и", "й", "л", "р", "у", "ю", ]; |
| 49 | $Consonants = [ "п", "ф", "к", "қ", "т", "ш", "с", "х", "ц", "ч", "щ", "б", "в", "г", "д", ]; |
| 50 | $Sibilants = [ "ж", "з", ]; |
| 51 | $Sonorants = [ "и", "й", "л", "р", "у", "ю", "м", "н", "ң", "ж", "з", ]; |
| 52 | |
| 53 | // Possessives |
| 54 | // 1st singular, 2nd informal |
| 55 | $firstPerson = [ "м", "ң", ]; |
| 56 | // 1st plural, 2nd formal |
| 57 | $secondPerson = [ "з" ]; |
| 58 | // 3rd |
| 59 | $thirdPerson = [ "ы", "і", ]; |
| 60 | |
| 61 | [ |
| 62 | $wordEnding, |
| 63 | $wordLastVowel, |
| 64 | ] = $this->lastLetter( $word, $allVowels ); |
| 65 | |
| 66 | // Now convert the word |
| 67 | switch ( $case ) { |
| 68 | case "dc1": |
| 69 | # ilik |
| 70 | case "genitive": |
| 71 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 72 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 73 | $word .= "тің"; |
| 74 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 75 | $word .= "тың"; |
| 76 | } |
| 77 | } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Nasals ) ) { |
| 78 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 79 | $word .= "нің"; |
| 80 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 81 | $word .= "ның"; |
| 82 | } |
| 83 | } elseif ( in_array( $wordEnding, $Sonants ) || in_array( $wordEnding, $Sibilants ) ) { |
| 84 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 85 | $word .= "дің"; |
| 86 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 87 | $word .= "дың"; |
| 88 | } |
| 89 | } |
| 90 | break; |
| 91 | |
| 92 | case "dc2": |
| 93 | # barıs |
| 94 | case "dative": |
| 95 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 96 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 97 | $word .= "ке"; |
| 98 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 99 | $word .= "қа"; |
| 100 | } |
| 101 | } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { |
| 102 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 103 | $word .= "ге"; |
| 104 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 105 | $word .= "ға"; |
| 106 | } |
| 107 | } |
| 108 | break; |
| 109 | |
| 110 | case "dc21": |
| 111 | # täweldık + barıs |
| 112 | case "possessive dative": |
| 113 | if ( in_array( $wordEnding, $firstPerson ) ) { |
| 114 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 115 | $word .= "е"; |
| 116 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 117 | $word .= "а"; |
| 118 | } |
| 119 | } elseif ( in_array( $wordEnding, $secondPerson ) ) { |
| 120 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 121 | $word .= "ге"; |
| 122 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 123 | $word .= "ға"; |
| 124 | } |
| 125 | } elseif ( in_array( $wordEnding, $thirdPerson ) ) { |
| 126 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 127 | $word .= "не"; |
| 128 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 129 | $word .= "на"; |
| 130 | } |
| 131 | } |
| 132 | break; |
| 133 | |
| 134 | case "dc3": |
| 135 | # tabıs |
| 136 | case "accusative": |
| 137 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 138 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 139 | $word .= "ті"; |
| 140 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 141 | $word .= "ты"; |
| 142 | } |
| 143 | } elseif ( in_array( $wordEnding, $allVowels ) ) { |
| 144 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 145 | $word .= "ні"; |
| 146 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 147 | $word .= "ны"; |
| 148 | } |
| 149 | } elseif ( in_array( $wordEnding, $Sonorants ) ) { |
| 150 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 151 | $word .= "ді"; |
| 152 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 153 | $word .= "ды"; |
| 154 | } |
| 155 | } |
| 156 | break; |
| 157 | |
| 158 | case "dc31": |
| 159 | # täweldık + tabıs |
| 160 | case "possessive accusative": |
| 161 | if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { |
| 162 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 163 | $word .= "ді"; |
| 164 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 165 | $word .= "ды"; |
| 166 | } |
| 167 | } elseif ( in_array( $wordEnding, $thirdPerson ) ) { |
| 168 | $word .= "н"; |
| 169 | } |
| 170 | break; |
| 171 | |
| 172 | case "dc4": |
| 173 | # jatıs |
| 174 | case "locative": |
| 175 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 176 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 177 | $word .= "те"; |
| 178 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 179 | $word .= "та"; |
| 180 | } |
| 181 | } elseif ( in_array( $wordEnding, $allVowels ) || in_array( $wordEnding, $Sonorants ) ) { |
| 182 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 183 | $word .= "де"; |
| 184 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 185 | $word .= "да"; |
| 186 | } |
| 187 | } |
| 188 | break; |
| 189 | |
| 190 | case "dc41": |
| 191 | # täweldık + jatıs |
| 192 | case "possessive locative": |
| 193 | if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $secondPerson ) ) { |
| 194 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 195 | $word .= "де"; |
| 196 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 197 | $word .= "да"; |
| 198 | } |
| 199 | } elseif ( in_array( $wordEnding, $thirdPerson ) ) { |
| 200 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 201 | $word .= "нде"; |
| 202 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 203 | $word .= "нда"; |
| 204 | } |
| 205 | } |
| 206 | break; |
| 207 | |
| 208 | case "dc5": |
| 209 | # şığıs |
| 210 | case "ablative": |
| 211 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 212 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 213 | $word .= "тен"; |
| 214 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 215 | $word .= "тан"; |
| 216 | } |
| 217 | } elseif ( |
| 218 | in_array( $wordEnding, $allVowels ) || |
| 219 | in_array( $wordEnding, $Sonants ) || |
| 220 | in_array( $wordEnding, $Sibilants ) |
| 221 | ) { |
| 222 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 223 | $word .= "ден"; |
| 224 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 225 | $word .= "дан"; |
| 226 | } |
| 227 | } elseif ( in_array( $wordEnding, $Nasals ) ) { |
| 228 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 229 | $word .= "нен"; |
| 230 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 231 | $word .= "нан"; |
| 232 | } |
| 233 | } |
| 234 | break; |
| 235 | |
| 236 | case "dc51": |
| 237 | # täweldık + şığıs |
| 238 | case "possessive ablative": |
| 239 | if ( in_array( $wordEnding, $firstPerson ) || in_array( $wordEnding, $thirdPerson ) ) { |
| 240 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 241 | $word .= "нен"; |
| 242 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 243 | $word .= "нан"; |
| 244 | } |
| 245 | } elseif ( in_array( $wordEnding, $secondPerson ) ) { |
| 246 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 247 | $word .= "ден"; |
| 248 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 249 | $word .= "дан"; |
| 250 | } |
| 251 | } |
| 252 | break; |
| 253 | |
| 254 | case "dc6": |
| 255 | # kömektes |
| 256 | case "comitative": |
| 257 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 258 | $word .= "пен"; |
| 259 | } elseif ( |
| 260 | in_array( $wordEnding, $allVowels ) || |
| 261 | in_array( $wordEnding, $Nasals ) || |
| 262 | in_array( $wordEnding, $Sonants ) |
| 263 | ) { |
| 264 | $word .= "мен"; |
| 265 | } elseif ( in_array( $wordEnding, $Sibilants ) ) { |
| 266 | $word .= "бен"; |
| 267 | } |
| 268 | break; |
| 269 | case "dc61": |
| 270 | # täweldık + kömektes |
| 271 | case "possessive comitative": |
| 272 | if ( in_array( $wordEnding, $Consonants ) ) { |
| 273 | $word .= "пенен"; |
| 274 | } elseif ( |
| 275 | in_array( $wordEnding, $allVowels ) || |
| 276 | in_array( $wordEnding, $Nasals ) || |
| 277 | in_array( $wordEnding, $Sonants ) |
| 278 | ) { |
| 279 | $word .= "менен"; |
| 280 | } elseif ( in_array( $wordEnding, $Sibilants ) ) { |
| 281 | $word .= "бенен"; |
| 282 | } |
| 283 | break; |
| 284 | |
| 285 | # dc0 #nominative #ataw |
| 286 | default: |
| 287 | break; |
| 288 | } |
| 289 | |
| 290 | return $word; |
| 291 | } |
| 292 | |
| 293 | /** |
| 294 | * @param string $word |
| 295 | * @param string[] $allVowels |
| 296 | * |
| 297 | * @return array{0: string, 1: string|null} |
| 298 | */ |
| 299 | private function lastLetter( string $word, array $allVowels ): array { |
| 300 | // Convert the word to lowercase safely for UTF-8 handling |
| 301 | $lowered = $this->lc( $word ); |
| 302 | $ar = mb_str_split( $lowered, 1 ); |
| 303 | |
| 304 | // Get the last letter using array_key_last to ensure a string |
| 305 | $lastKey = array_key_last( $ar ); |
| 306 | $lastLetter = $ar[$lastKey] ?? ''; |
| 307 | |
| 308 | // Find the last vowel in the word |
| 309 | for ( $i = count( $ar ); $i--; ) { |
| 310 | $letter = $ar[$i]; |
| 311 | if ( in_array( $letter, $allVowels, true ) ) { |
| 312 | return [ |
| 313 | $lastLetter, |
| 314 | $letter, |
| 315 | ]; |
| 316 | } |
| 317 | } |
| 318 | |
| 319 | return [ |
| 320 | $lastLetter, |
| 321 | null, |
| 322 | ]; |
| 323 | } |
| 324 | |
| 325 | /** |
| 326 | * @param string $str |
| 327 | * @param bool $first Whether to lowercase only the first character |
| 328 | * |
| 329 | * @return string The string with lowercase conversion applied |
| 330 | */ |
| 331 | public function lc( string $str, bool $first = false ): string { |
| 332 | if ( $first ) { |
| 333 | return $this->lcfirst( $str ); |
| 334 | } else { |
| 335 | return $this->isMultibyte( $str ) ? mb_strtolower( $str ) : strtolower( $str ); |
| 336 | } |
| 337 | } |
| 338 | |
| 339 | /** |
| 340 | * @param string $str |
| 341 | * |
| 342 | * @return string The string with lowercase conversion applied to the first character |
| 343 | */ |
| 344 | public function lcfirst( string $str ): string { |
| 345 | $octetCode = ord( $str ); |
| 346 | // See https://en.wikipedia.org/wiki/ASCII#Printable_characters |
| 347 | if ( $octetCode < 96 ) { |
| 348 | // Assume this is an uppercase/uncased ASCII character |
| 349 | return lcfirst( $str ); |
| 350 | } elseif ( $octetCode < 128 ) { |
| 351 | // Assume this is a lowercase/uncased ASCII character |
| 352 | return $str; |
| 353 | } |
| 354 | |
| 355 | return $this->isMultibyte( $str ) |
| 356 | // Assume this is a multibyte character and mb_internal_encoding() is appropriate |
| 357 | ? mb_strtolower( mb_substr( $str, 0, 1 ) ) . mb_substr( $str, 1 ) |
| 358 | // Assume this is a non-multibyte character and LC_CASE is appropriate |
| 359 | : lcfirst( $str ); |
| 360 | } |
| 361 | |
| 362 | /** |
| 363 | * @param string $str |
| 364 | * |
| 365 | * @return bool |
| 366 | */ |
| 367 | private function isMultibyte( string $str ): bool { |
| 368 | return strlen( $str ) !== mb_strlen( $str ); |
| 369 | } |
| 370 | } |