/**
* Converts some characters for MySQL's indexing to grok it correctly,
* and pads short words to overcome limitations.
* @return mixed|string
*/
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;
}
