wiki.techinc.nl/includes/languages/LanguageYue.php
Timo Tijhof 939700e8ff language: Continue doc Languages subgroup for msg files and subclasses
Follows-up I301f471f86ba2.

For ease of navigation, move Converter subclasses to a group called
"Languages", which for documentation purposes is a subgroup of
"Language". The next commit does the same for Messages* files,
and Language subclasses (done separately for ease of review).

Change-Id: If1cef9aa15f536ebaedd4477ad7453426e7f3b85
2022-06-29 00:13:45 +00:00

61 lines
1.5 KiB
PHP

<?php
/**
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
*/
/**
* Cantonese (粵語)
*
* @ingroup Languages
*/
class LanguageYue extends Language {
/**
* @return bool
*/
public function hasWordBreaks() {
return false;
}
/**
* Eventually this should be a word segmentation;
* for now just treat each character as a word.
* @todo FIXME: Only do this for Han characters...
*
* @param string $string
* @return string
*/
public function segmentByWord( $string ) {
$reg = "/([\\xc0-\\xff][\\x80-\\xbf]*)/";
$s = self::insertSpace( $string, $reg );
return $s;
}
/**
* @param string $string
* @return string
*/
public function normalizeForSearch( $string ) {
// Double-width roman characters
$s = self::convertDoubleWidth( $string );
$s = trim( $s );
$s = parent::normalizeForSearch( $s );
return $s;
}
}