6 class LanguageZh_hans
extends Language
{
7 function hasWordBreaks() {
11 function stripForSearch( $string ) {
12 // Eventually this should be a word segmentation;
13 // for now just treat each character as a word.
15 // Note we put a space on both sides to cover cases
16 // where a number or Latin char follows a Han char.
18 // @fixme only do this for Han characters...
20 "/([\\xc0-\\xff][\\x80-\\xbf]*)/",
22 $t = preg_replace( '/ +/', ' ', $t );
24 return parent
::stripForSearch( $t );