Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 2 |
|
0.00% |
0 / 2 |
CRAP | |
0.00% |
0 / 1 |
| LanguageJa | |
0.00% |
0 / 2 |
|
0.00% |
0 / 2 |
6 | |
0.00% |
0 / 1 |
| segmentByWord | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| emphasize | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| 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 | use MediaWiki\Language\Language; |
| 22 | |
| 23 | /** |
| 24 | * Japanese (日本語) |
| 25 | * |
| 26 | * @ingroup Languages |
| 27 | */ |
| 28 | class LanguageJa extends Language { |
| 29 | |
| 30 | /** Space string for hiragana - unicode range U3040-309f */ |
| 31 | private const WORD_SEG_HIRAGANA = '(?:\xe3(?:\x81[\x80-\xbf]|\x82[\x80-\x9f]))'; |
| 32 | |
| 33 | /** Space string for katakana - unicode range U30a0-30ff */ |
| 34 | private const WORD_SEG_KATAKANA = '(?:\xe3(?:\x82[\xa0-\xbf]|\x83[\x80-\xbf]))'; |
| 35 | |
| 36 | /** Space string for kanji - unicode range U3200-9999 = \xe3\x88\x80-\xe9\xa6\x99 */ |
| 37 | private const WORD_SEG_KANJI = |
| 38 | '(?:\xe3[\x88-\xbf][\x80-\xbf]|[\xe4-\xe8][\x80-\xbf]{2}|\xe9[\x80-\xa5][\x80-\xbf]|\xe9\xa6[\x80-\x99])'; |
| 39 | |
| 40 | private const WORD_SEGMENTATION_REGEX = |
| 41 | '/(' . self::WORD_SEG_HIRAGANA . '+|' . self::WORD_SEG_KATAKANA . '+|' . self::WORD_SEG_KANJI . '+)/'; |
| 42 | |
| 43 | public function segmentByWord( $string ) { |
| 44 | return self::insertSpace( $string, self::WORD_SEGMENTATION_REGEX ); |
| 45 | } |
| 46 | |
| 47 | /** |
| 48 | * Italic is not appropriate for Japanese script. |
| 49 | * Unfortunately, most browsers do not recognise this, and render `<em>` as italic. |
| 50 | * |
| 51 | * @param string $text |
| 52 | * @return string |
| 53 | */ |
| 54 | public function emphasize( $text ) { |
| 55 | return $text; |
| 56 | } |
| 57 | } |