Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
37.50% |
3 / 8 |
|
50.00% |
2 / 4 |
CRAP | |
0.00% |
0 / 1 |
| LanguageZh | |
37.50% |
3 / 8 |
|
50.00% |
2 / 4 |
7.91 | |
0.00% |
0 / 1 |
| segmentForDiff | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| unsegmentForDiff | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getSearchIndexVariant | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| convertForSearchResult | |
0.00% |
0 / 4 |
|
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 | /** |
| 22 | * Chinese-specific code. |
| 23 | * |
| 24 | * This handles both Traditional and Simplified Chinese. |
| 25 | * Right now, we distinguish `zh_hans`, `zh_hant`, `zh_cn`, `zh_tw`, `zh_sg`, |
| 26 | * and `zh_hk`. |
| 27 | * |
| 28 | * @ingroup Languages |
| 29 | */ |
| 30 | class LanguageZh extends LanguageZh_hans { |
| 31 | /** |
| 32 | * Add a formfeed character between each non-ASCII character, so that |
| 33 | * "word-level" diffs will effectively operate on a character level. The FF |
| 34 | * characters are stripped out by unsegmentForDiff(). |
| 35 | * |
| 36 | * We use FF because it is the least used character that is matched by |
| 37 | * PCRE's \s class. |
| 38 | * |
| 39 | * In the unlikely event that an FF character appears in the input, it will |
| 40 | * be displayed in the diff as a replacement character. |
| 41 | * |
| 42 | * @param string $text |
| 43 | * @return string |
| 44 | */ |
| 45 | public function segmentForDiff( $text ) { |
| 46 | $text = str_replace( "\x0c", "\u{FFFD}", $text ); |
| 47 | return preg_replace( '/[\xc0-\xff][\x80-\xbf]*/', "\x0c$0", $text ); |
| 48 | } |
| 49 | |
| 50 | public function unsegmentForDiff( $text ) { |
| 51 | return str_replace( "\x0c", '', $text ); |
| 52 | } |
| 53 | |
| 54 | protected function getSearchIndexVariant() { |
| 55 | return 'zh-hans'; |
| 56 | } |
| 57 | |
| 58 | public function convertForSearchResult( $termsArray ) { |
| 59 | $terms = implode( '|', $termsArray ); |
| 60 | $terms = self::convertDoubleWidth( $terms ); |
| 61 | $terms = implode( '|', $this->getConverterInternal()->autoConvertToAllVariants( $terms ) ); |
| 62 | return array_unique( explode( '|', $terms ) ); |
| 63 | } |
| 64 | } |