/**
* Build a set of regular expressions matching URLs with the list of regex fragments.
* Returns an empty list if the input list is empty.
*
* @param array $lines list of fragments which will match in URLs
* @param BaseBlacklist $blacklist
* @param int $batchSize largest allowed batch regex;
* if 0, will produce one regex per line
* @return array
*/
static function buildRegexes($lines, BaseBlacklist $blacklist, $batchSize = 4096)
{
# Make regex
# It's faster using the S modifier even though it will usually only be run once
//$regex = 'https?://+[a-z0-9_\-.]*(' . implode( '|', $lines ) . ')';
//return '/' . str_replace( '/', '\/', preg_replace('|\\\*/|', '/', $regex) ) . '/Sim';
$regexes = array();
$regexStart = $blacklist->getRegexStart();
$regexEnd = $blacklist->getRegexEnd($batchSize);
$build = false;
foreach ($lines as $line) {
if (substr($line, -1, 1) == "\\") {
// Final \ will break silently on the batched regexes.
// Skip it here to avoid breaking the next line;
// warnings from getBadLines() will still trigger on
// edit to keep new ones from floating in.
continue;
}
// FIXME: not very robust size check, but should work. :)
if ($build === false) {
$build = $line;
} elseif (strlen($build) + strlen($line) > $batchSize) {
$regexes[] = $regexStart . str_replace('/', '\\/', preg_replace('|\\\\*/|u', '/', $build)) . $regexEnd;
$build = $line;
} else {
$build .= '|';
$build .= $line;
}
}
if ($build !== false) {
$regexes[] = $regexStart . str_replace('/', '\\/', preg_replace('|\\\\*/|u', '/', $build)) . $regexEnd;
}
return $regexes;
}
/**
* Returns the end of the regex for matches
*
* @param $batchSize
* @return string
*/
public function getRegexEnd($batchSize)
{
return ')' . parent::getRegexEnd($batchSize);
}