/** * Gets the description, count of summaries, and number of partitions of the * summaries store in the supplied directory. If the file * arc_description.txt exists, this is viewed as a dummy index archive for * the sole purpose of allowing conversions of downloaded data such as arc * files into Yioop! format. * * @param string $dir_name path to a directory containing a summaries * WebArchiveBundle * @return array summary of the given archive */ static function getArchiveInfo($dir_name) { if (file_exists($dir_name . "/arc_description.txt")) { $crawl = array(); $info = array(); $crawl['DESCRIPTION'] = substr(file_get_contents($dir_name . "/arc_description.txt"), 0, 256); $crawl['ARCFILE'] = true; $info['VISITED_URLS_COUNT'] = 0; $info['COUNT'] = 0; $info['NUM_DOCS_PER_PARTITION'] = 0; $info['WRITE_PARTITION'] = 0; $info['DESCRIPTION'] = serialize($crawl); return $info; } return WebArchiveBundle::getArchiveInfo($dir_name . "/summaries"); }