/**
* Get a normalized string representation of a title suitable for
* including in a search index
*
* @param SearchEngine $search
* @return string A stripped-down title string ready for the search index
*/
private function getNormalizedTitle(SearchEngine $search)
{
global $wgContLang;
$ns = $this->title->getNamespace();
$title = $this->title->getText();
$lc = $search->legalSearchChars() . '&#;';
$t = $wgContLang->normalizeForSearch($title);
$t = preg_replace("/[^{$lc}]+/", ' ', $t);
$t = $wgContLang->lc($t);
# Handle 's, s'
$t = preg_replace("/([{$lc}]+)'s( |\$)/", "\\1 \\1's ", $t);
$t = preg_replace("/([{$lc}]+)s'( |\$)/", "\\1s ", $t);
$t = preg_replace("/\\s+/", ' ', $t);
if ($ns == NS_FILE) {
$t = preg_replace("/ (png|gif|jpg|jpeg|ogg)\$/", "", $t);
}
return $search->normalizeText(trim($t));
}
/**
* Converts some characters for MySQL's indexing to grok it correctly,
* and pads short words to overcome limitations.
*/
function normalizeText($string)
{
global $wgContLang;
wfProfileIn(__METHOD__);
$out = parent::normalizeText($string);
// MySQL fulltext index doesn't grok utf-8, so we
// need to fold cases and convert to hex
$out = preg_replace_callback("/([\\xc0-\\xff][\\x80-\\xbf]*)/", array($this, 'stripForSearchCallback'), $wgContLang->lc($out));
// And to add insult to injury, the default indexing
// ignores short words... Pad them so we can pass them
// through without reconfiguring the server...
$minLength = $this->minSearchLength();
if ($minLength > 1) {
$n = $minLength - 1;
$out = preg_replace("/\\b(\\w{1,{$n}})\\b/", "\$1u800", $out);
}
// Periods within things like hostnames and IP addresses
// are also important -- we want a search for "example.com"
// or "192.168.1.1" to work sanely.
//
// MySQL's search seems to ignore them, so you'd match on
// "example.wikipedia.com" and "192.168.83.1" as well.
$out = preg_replace("/(\\w)\\.(\\w|\\*)/u", "\$1u82e\$2", $out);
wfProfileOut(__METHOD__);
return $out;
}
