function docreader_get_description($doc)
{
if (preg_match('|<meta name="description" content="([^"]*?)" />|is', $doc, $regs)) {
return preg_replace('|[\\r\\n\\t ]+|s', ' ', trim(strip_tags($regs[1])));
}
return substr(docreader_get_body($doc), 0, 255) . '...';
}
// get content type (ie. if pdf, don't parse as an html file)
$finfo = pathinfo($f);
$fext = strtolower($finfo['extension']);
if (in_array($fext, array('html', 'htm'))) {
// parse file
$doc = docreader_get_data($f);
if (!$doc) {
continue;
}
$title = docreader_get_title($doc);
if (!$title) {
$title = 'Untitled';
}
$description = docreader_get_description($doc);
$keywords = docreader_get_keywords($doc);
$body = extractor_run(docreader_get_body($doc), 'HTML');
unset($doc);
} else {
$body = extractor_run($f);
if (!$body) {
$body = '';
}
$description = '';
$keywords = '';
$title = basename($f);
}
$data = array('title' => $title, 'url' => $url, 'description' => $description, 'keywords' => $keywords, 'body' => $body, 'access' => 'public', 'status' => 'approved', 'team' => 'none', 'ctype' => $ctype, 'mtime' => (string) $mtime, 'domain' => $domain);
// add file to index
$counts[$ctype]++;
$res = $search->addDocument($data);
if (!$res) {
