Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 133 |
|
0.00% |
0 / 1 |
CRAP | |
0.00% |
0 / 1 |
| GrammarTyv | |
0.00% |
0 / 133 |
|
0.00% |
0 / 1 |
4290 | |
0.00% |
0 / 1 |
| process | |
0.00% |
0 / 133 |
|
0.00% |
0 / 1 |
4290 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * @license GPL-2.0-or-later |
| 4 | * @file |
| 5 | */ |
| 6 | |
| 7 | namespace Wikimedia\Leximorph\Handler\Overrides\Grammar; |
| 8 | |
| 9 | use Wikimedia\Leximorph\Handler\Overrides\IGrammarTransformer; |
| 10 | |
| 11 | /** |
| 12 | * GrammarTyv |
| 13 | * |
| 14 | * Implements grammar transformations for Tuvan (tyv). |
| 15 | * |
| 16 | * These rules don't cover the whole grammar of the language. |
| 17 | * This logic was originally taken from MediaWiki Core. |
| 18 | * Thanks to all contributors. |
| 19 | * |
| 20 | * @since 1.45 |
| 21 | * @author Doğu Abaris (abaris@null.net) |
| 22 | * @license https://www.gnu.org/copyleft/gpl.html GPL-2.0-or-later |
| 23 | */ |
| 24 | class GrammarTyv implements IGrammarTransformer { |
| 25 | /** |
| 26 | * Applies Tuvan-specific grammatical transformations. |
| 27 | * |
| 28 | * @param string $word The word to process. |
| 29 | * @param string $case The grammatical case. |
| 30 | * |
| 31 | * @since 1.45 |
| 32 | * @return string The processed word. |
| 33 | */ |
| 34 | public function process( string $word, string $case ): string { |
| 35 | // Set up some constants... |
| 36 | $allVowels = [ "е", "и", "э", "ө", "ү", "а", "ё", "о", "у", "ы", "ю", "я", ]; |
| 37 | $frontVowels = [ "е", "и", "э", "ө", "ү", ]; |
| 38 | $backVowels = [ "а", "ё", "о", "у", "ы", "ю", "я", ]; |
| 39 | $unroundFrontVowels = [ "е", "и", "э", ]; |
| 40 | $roundFrontVowels = [ "ө", "ү", ]; |
| 41 | $unroundBackVowels = [ "а", "ы", "я", ]; |
| 42 | $roundBackVowels = [ "ё", "о", "у", "ю", ]; |
| 43 | $unvoicedPhonemes = [ "т", "п", "с", "ш", "к", "ч", "х", ]; |
| 44 | $directiveUnvoicedStems = [ "т", "п", "с", "ш", "к", "ч", "х", "л", "м", "н", "ң", ]; |
| 45 | $directiveVoicedStems = [ "д", "б", "з", "ж", "г", "р", "й", ]; |
| 46 | |
| 47 | // Put the word in a form we can play with since we're using UTF-8 |
| 48 | $ar = mb_str_split( $word, 1 ); |
| 49 | |
| 50 | // Here's the last letter in the word |
| 51 | $wordEnding = end( $ar ); |
| 52 | |
| 53 | // Find the last vowel in the word |
| 54 | $wordLastVowel = null; |
| 55 | for ( $i = count( $ar ); $i--; ) { |
| 56 | if ( in_array( $ar[$i], $allVowels, true ) ) { |
| 57 | $wordLastVowel = $ar[$i]; |
| 58 | break; |
| 59 | } |
| 60 | } |
| 61 | |
| 62 | // Now convert the word |
| 63 | switch ( $case ) { |
| 64 | case "genitive": |
| 65 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 66 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 67 | $word .= "түң"; |
| 68 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 69 | $word .= "тиң"; |
| 70 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 71 | $word .= "туң"; |
| 72 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 73 | $word .= "тың"; |
| 74 | } |
| 75 | } elseif ( $wordEnding === "л" ) { |
| 76 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 77 | $word .= "дүң"; |
| 78 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 79 | $word .= "диң"; |
| 80 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 81 | $word .= "дуң"; |
| 82 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 83 | $word .= "дың"; |
| 84 | } |
| 85 | } else { |
| 86 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 87 | $word .= "нүң"; |
| 88 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 89 | $word .= "ниң"; |
| 90 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 91 | $word .= "нуң"; |
| 92 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 93 | $word .= "ның"; |
| 94 | } |
| 95 | } |
| 96 | break; |
| 97 | |
| 98 | case "dative": |
| 99 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 100 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 101 | $word .= "ке"; |
| 102 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 103 | $word .= "ка"; |
| 104 | } |
| 105 | } else { |
| 106 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 107 | $word .= "ге"; |
| 108 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 109 | $word .= "га"; |
| 110 | } |
| 111 | } |
| 112 | break; |
| 113 | |
| 114 | case "accusative": |
| 115 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 116 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 117 | $word .= "тү"; |
| 118 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 119 | $word .= "ти"; |
| 120 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 121 | $word .= "ту"; |
| 122 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 123 | $word .= "ты"; |
| 124 | } |
| 125 | } elseif ( $wordEnding === "л" ) { |
| 126 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 127 | $word .= "дү"; |
| 128 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 129 | $word .= "ди"; |
| 130 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 131 | $word .= "ду"; |
| 132 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 133 | $word .= "ды"; |
| 134 | } |
| 135 | } else { |
| 136 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 137 | $word .= "нү"; |
| 138 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 139 | $word .= "ни"; |
| 140 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 141 | $word .= "ну"; |
| 142 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 143 | $word .= "ны"; |
| 144 | } |
| 145 | } |
| 146 | break; |
| 147 | |
| 148 | case "locative": |
| 149 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 150 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 151 | $word .= "те"; |
| 152 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 153 | $word .= "та"; |
| 154 | } |
| 155 | } else { |
| 156 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 157 | $word .= "де"; |
| 158 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 159 | $word .= "да"; |
| 160 | } |
| 161 | } |
| 162 | break; |
| 163 | |
| 164 | case "ablative": |
| 165 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 166 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 167 | $word .= "тен"; |
| 168 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 169 | $word .= "тан"; |
| 170 | } |
| 171 | } else { |
| 172 | if ( in_array( $wordLastVowel, $frontVowels ) ) { |
| 173 | $word .= "ден"; |
| 174 | } elseif ( in_array( $wordLastVowel, $backVowels ) ) { |
| 175 | $word .= "дан"; |
| 176 | } |
| 177 | } |
| 178 | break; |
| 179 | |
| 180 | case "directive1": |
| 181 | if ( in_array( $wordEnding, $directiveVoicedStems ) ) { |
| 182 | $word .= "же"; |
| 183 | } elseif ( in_array( $wordEnding, $directiveUnvoicedStems ) ) { |
| 184 | $word .= "че"; |
| 185 | } |
| 186 | break; |
| 187 | |
| 188 | case "directive2": |
| 189 | if ( in_array( $wordEnding, $unvoicedPhonemes ) ) { |
| 190 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 191 | $word .= "түве"; |
| 192 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 193 | $word .= "тиве"; |
| 194 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 195 | $word .= "туве"; |
| 196 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 197 | $word .= "тыве"; |
| 198 | } |
| 199 | } else { |
| 200 | if ( in_array( $wordLastVowel, $roundFrontVowels ) ) { |
| 201 | $word .= "дүве"; |
| 202 | } elseif ( in_array( $wordLastVowel, $unroundFrontVowels ) ) { |
| 203 | $word .= "диве"; |
| 204 | } elseif ( in_array( $wordLastVowel, $roundBackVowels ) ) { |
| 205 | $word .= "дуве"; |
| 206 | } elseif ( in_array( $wordLastVowel, $unroundBackVowels ) ) { |
| 207 | $word .= "дыве"; |
| 208 | } |
| 209 | } |
| 210 | break; |
| 211 | |
| 212 | default: |
| 213 | break; |
| 214 | } |
| 215 | |
| 216 | return $word; |
| 217 | } |
| 218 | } |