$taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_remote_job_publisher_task_class');
$handlerInstance->registerTask('crawler_remote_job_publisher', $taskInstance);
+ // 5) MIME sniffer
+ $taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_mime_sniffer_task_class');
+ $handlerInstance->registerTask('crawler_mime_sniffer', $taskInstance);
+
+ // 6) Document parser (converts document to meta format)
+ $taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_document_parser_task_class');
+ $handlerInstance->registerTask('crawler_document_parser', $taskInstance);
+
+ // 7) Document structure analyzer
+ $taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_structure_analyzer_task_class');
+ $handlerInstance->registerTask('crawler_structure_analyzer', $taskInstance);
+
+ // 8) Snippet extractor
+ $taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_snippet_extractor_task_class');
+ $handlerInstance->registerTask('crawler_snippet_extractor', $taskInstance);
+
+ // 9) Node ping
+ $taskInstance = ObjectFactory::createObjectByConfiguredName('crawler_ping_task_class');
+ $handlerInstance->registerTask('crawler_ping', $taskInstance);
+
// Put the task handler in registry
Registry::getRegistry()->addInstance('task_handler', $handlerInstance);
}