/**
* This is the function that should be called to get the queue_server
* to start. Calls init to handle the command line arguments then enters
* the queue_server's main loop
*/
function start()
{
global $argv;
if (isset($argv[1]) && $argv[1] == "start") {
if (isset($argv[2]) && in_array($argv[2], array(self::INDEXER, self::SCHEDULER))) {
$argv[3] = $argv[2];
$argv[2] = "none";
// 3 indicates force start
CrawlDaemon::init($argv, "queue_server", 3);
} else {
$argv[2] = "none";
$argv[3] = self::INDEXER;
CrawlDaemon::init($argv, "queue_server", 0);
$argv[2] = "none";
$argv[3] = self::SCHEDULER;
CrawlDaemon::init($argv, "queue_server", 2);
}
} else {
CrawlDaemon::init($argv, "queue_server");
}
crawlLog("\n\nInitialize logger..", "queue_server", true);
$this->server_name = "IndexerAndScheduler";
if (isset($argv[3]) && $argv[1] == "child" && in_array($argv[3], array(self::INDEXER, self::SCHEDULER))) {
$this->server_type = $argv[3];
$this->server_name = $argv[3];
crawlLog($argv[3] . " logging started.");
}
$remove = false;
$old_message_names = array("queue_server_messages.txt", "scheduler_messages.txt", "crawl_status.txt", "schedule_status.txt");
foreach ($old_message_names as $name) {
if (file_exists(CRAWL_DIR . "/schedules/{$name}")) {
@unlink(CRAWL_DIR . "/schedules/{$name}");
$remove = true;
}
}
if ($remove == true) {
crawlLog("Remove old messages..", "queue_server");
}
$this->loop();
}
/**
* This is the function that should be called to get the fetcher to start
* fetching. Calls init to handle the command-line arguments then enters
* the fetcher's main loop
*/
function start()
{
global $argv;
if (isset($argv[2])) {
$this->fetcher_num = intval($argv[2]);
} else {
$this->fetcher_num = 0;
$argv[2] = "0";
}
CrawlDaemon::init($argv, "fetcher");
crawlLog("\n\nInitialize logger..", $this->fetcher_num . "-fetcher", true);
$this->loop();
}
/**
* This is the function that should be called to get the
* classifier_trainer to start training a logistic regression instance for
* a particular classifier. The class label corresponding to the
* classifier to be finalized should be passed as the second command-line
* argument.
*/
function start()
{
global $argv;
CrawlDaemon::init($argv, "classifier_trainer");
$label = $argv[2];
crawlLog("Initializing classifier trainer log..", $label . '-classifier_trainer', true);
$classifier = Classifier::getClassifier($label);
$classifier->prepareToFinalize();
$classifier->finalize();
Classifier::setClassifier($classifier);
crawlLog("Training complete.\n");
CrawlDaemon::stop('classifier_trainer', $label);
}
/**
* This is the function that should be called to get the mirror to start
* syncing. Calls init to handle the command line arguments then enters
* the syncer's main loop
*/
function start()
{
global $argv;
CrawlDaemon::init($argv, "mirror");
crawlLog("\n\nInitialize logger..", "mirror", true);
$this->loop();
}
/**
* This is the function that should be called to get the newsupdater to
* start to start updating. Calls init to handle the command-line
* arguments then enters news_updaters main loop
*/
function start()
{
global $argv;
CrawlDaemon::init($argv, "news_updater");
crawlLog("\n\nInitialize logger..", "news_updater", true);
$this->sourceModel = new SourceModel();
$this->loop();
}
