System.out.println("Usage: Crawler <cache dir> <root>");
      return;
    }

    int threadCount = 20;
    long cacheByteCount = 1024L * 1024L * 100L;

    Cache cache = new Cache(new File(args[0]), cacheByteCount);
    OkHttpClient client = new OkHttpClient.Builder()
        .cache(cache)
        .build();

    Crawler crawler = new Crawler(client);
    crawler.queue.add(HttpUrl.get(args[1]));

            if (logger.isDebugEnabled()) {
                logger.debug("Crawler is stopped.", e);
            } else if (logger.isInfoEnabled()) {
                logger.info("Crawler is stopped.");
            }
            exitCode = Constants.EXIT_FAIL;
        } catch (final Throwable t) {
            logger.error("Crawler does not work correctly.", t);
            exitCode = Constants.EXIT_FAIL;
        } finally {

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.EsAccessResult;
import org.codelibs.fess.crawler.entity.EsUrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;

    /** The key of the configuration. e.g. 500ms */
    String CRAWLER_HOTTHREAD_INTERVAL = "crawler.hotthread.interval";

    /** The key of the configuration. e.g. 10 */
    String CRAWLER_HOTTHREAD_SNAPSHOTS = "crawler.hotthread.snapshots";

    /** The key of the configuration. e.g. 3 */
    String CRAWLER_HOTTHREAD_THREADS = "crawler.hotthread.threads";

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.LogHelperImpl;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.es.config.exentity.CrawlingConfig;

            ThreadUtil.sleep(500);
            count++;
            final Map<String, Object> scheduler = getSchedulerItem(namePrefix);
            assertTrue(scheduler.containsKey("running"));
            isRunning = (Boolean) scheduler.get("running");
        }
        if (300 <= count) {
            logger.info("Time out: Failed to start crawler)");
            fail(); // Time Out

   * exception is propagated to the caller exactly as-is. If, on the other hand, the time limit is
   * reached, the proxy will attempt to abort the call to the target, and will throw an {@link
   * UncheckedTimeoutException} to the caller.
   *
   * <p>It is important to note that the primary purpose of the proxy object is to return control to

 *
 * <p>{@code ByteSink} provides two kinds of methods:
 *
 * <ul>
 *   <li><b>Methods that return a stream:</b> These methods should return a <i>new</i>, independent
 *       instance each time they are called. The caller is responsible for ensuring that the
 *       returned stream is closed.
 *   <li><b>Convenience methods:</b> These are implementations of common operations that are

 *
 * <p>Generally, implementations don't support {@link #put} and {@link #putAll} because there is no
 * way to check an object at runtime to be an instance of a {@link TypeToken}. Instead, caller
 * should use the type safe {@link #putInstance}.
 *
 * <p>Also, if caller suppresses unchecked warnings and passes in an {@code Iterable<String>} for
 * type {@code Iterable<Integer>}, the map won't be able to detect and throw type error.
 *