Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 43 |
|
0.00% |
0 / 6 |
CRAP | |
0.00% |
0 / 1 |
| EnConverter | |
0.00% |
0 / 43 |
|
0.00% |
0 / 6 |
132 | |
0.00% |
0 / 1 |
| getMainCode | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| getLanguageVariants | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| getVariantsFallbacks | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| loadDefaultTables | |
0.00% |
0 / 4 |
|
0.00% |
0 / 1 |
2 | |||
| translate | |
0.00% |
0 / 25 |
|
0.00% |
0 / 1 |
20 | |||
| pigLatin | |
0.00% |
0 / 11 |
|
0.00% |
0 / 1 |
12 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * This program is free software; you can redistribute it and/or modify |
| 4 | * it under the terms of the GNU General Public License as published by |
| 5 | * the Free Software Foundation; either version 2 of the License, or |
| 6 | * (at your option) any later version. |
| 7 | * |
| 8 | * This program is distributed in the hope that it will be useful, |
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | * GNU General Public License for more details. |
| 12 | * |
| 13 | * You should have received a copy of the GNU General Public License along |
| 14 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 15 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 16 | * http://www.gnu.org/copyleft/gpl.html |
| 17 | * |
| 18 | * @file |
| 19 | */ |
| 20 | |
| 21 | /** |
| 22 | * English specific converter routines. |
| 23 | * |
| 24 | * @ingroup Languages |
| 25 | */ |
| 26 | class EnConverter extends LanguageConverter { |
| 27 | |
| 28 | public function getMainCode(): string { |
| 29 | return 'en'; |
| 30 | } |
| 31 | |
| 32 | public function getLanguageVariants(): array { |
| 33 | return [ 'en', 'en-x-piglatin' ]; |
| 34 | } |
| 35 | |
| 36 | public function getVariantsFallbacks(): array { |
| 37 | return []; |
| 38 | } |
| 39 | |
| 40 | protected function loadDefaultTables(): array { |
| 41 | return [ |
| 42 | 'en' => new ReplacementArray(), |
| 43 | 'en-x-piglatin' => new ReplacementArray(), |
| 44 | ]; |
| 45 | } |
| 46 | |
| 47 | /** |
| 48 | * Translates text into Pig Latin. This allows developers to test the language variants |
| 49 | * functionality and user interface without having to switch wiki language away from default. |
| 50 | * This method also processes custom conversion rules to allow testing these parts of the |
| 51 | * language converter as well. |
| 52 | * |
| 53 | * @param string $text |
| 54 | * @param string $toVariant |
| 55 | * @return string |
| 56 | */ |
| 57 | public function translate( $text, $toVariant ) { |
| 58 | if ( $toVariant !== 'en-x-piglatin' ) { |
| 59 | return $text; |
| 60 | } |
| 61 | // Apply any custom rules. (Primarily for testing.) |
| 62 | $this->loadTables(); |
| 63 | $customRules = $this->mTables[$toVariant]; |
| 64 | |
| 65 | if ( !$customRules->getArray() ) { |
| 66 | return self::pigLatin( $text ); |
| 67 | } |
| 68 | |
| 69 | // Split on the matches from custom rules, so that we only apply |
| 70 | // the Pig Latin transformation on output. which is not from a |
| 71 | // custom rule; this avoids double-conversion. |
| 72 | // (See SrConverter for similar split-and-process code.) |
| 73 | $re = '(' . |
| 74 | implode( |
| 75 | '|', |
| 76 | array_map( |
| 77 | 'preg_quote', |
| 78 | // "Original" texts from the ReplacementArray rules |
| 79 | array_keys( $customRules->getArray() ) |
| 80 | ) |
| 81 | ) . ')'; |
| 82 | |
| 83 | $matches = preg_split( $re, $text, -1, PREG_SPLIT_OFFSET_CAPTURE ); |
| 84 | $m = array_shift( $matches ); |
| 85 | |
| 86 | // Apply Pig Latin transformation to the initial "non-matching" section. |
| 87 | $ret = self::pigLatin( $m[0] ); |
| 88 | $mstart = (int)$m[1] + strlen( $m[0] ); |
| 89 | foreach ( $matches as $m ) { |
| 90 | // Use the ReplacementArray rules to transform any matching sections |
| 91 | $ret .= $customRules->replace( |
| 92 | substr( $text, $mstart, (int)$m[1] - $mstart ) |
| 93 | ); |
| 94 | // And Pig Latin transformation on the non-matching sections. |
| 95 | $ret .= self::pigLatin( $m[0] ); |
| 96 | $mstart = (int)$m[1] + strlen( $m[0] ); |
| 97 | } |
| 98 | // $mstart will always equal strlen($text) here. |
| 99 | |
| 100 | return $ret; |
| 101 | } |
| 102 | |
| 103 | /** |
| 104 | * Translates words into Pig Latin. |
| 105 | * |
| 106 | * @param string $text |
| 107 | * @return string |
| 108 | */ |
| 109 | private static function pigLatin( string $text ): string { |
| 110 | // Only process words composed of standard English alphabet, leave the rest unchanged. |
| 111 | // This skips some English words like 'naïve' or 'résumé', but we can live with that. |
| 112 | // Ignore single letters and words which aren't lowercase or uppercase-first. |
| 113 | return preg_replace_callback( '/[A-Za-z][a-z\']+/', static function ( $matches ) { |
| 114 | $word = $matches[0]; |
| 115 | if ( preg_match( '/^[aeiou]/i', $word ) ) { |
| 116 | return $word . 'way'; |
| 117 | } |
| 118 | |
| 119 | return preg_replace_callback( '/^(s?qu|[^aeiou][^aeiouy]*)(.*)$/i', static function ( $m ) { |
| 120 | $ucfirst = strtoupper( $m[1][0] ) === $m[1][0]; |
| 121 | if ( $ucfirst ) { |
| 122 | return ucfirst( $m[2] ) . lcfirst( $m[1] ) . 'ay'; |
| 123 | } |
| 124 | |
| 125 | return $m[2] . $m[1] . 'ay'; |
| 126 | }, $word ); |
| 127 | }, $text ); |
| 128 | } |
| 129 | } |