*
 * <p>Example usage:
 * <pre>
 *   Crawler crawler = new Crawler();
 *   crawler.addUrl("http://example.com/");
 *   crawler.execute();
 *   crawler.close();
 * </pre>
 */
public class Crawler implements Runnable, AutoCloseable {

    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /**
     * Service for managing URL queues during crawling.
     */

 * </pre>
 */
public class Crawler {

    /**
     * Creates a new instance of Crawler.
     */
    public Crawler() {
        // Default constructor
    }

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /** Thread name for web and file system crawling process. */

    OkHttpClient client = new OkHttpClient.Builder()
        .cache(cache)
        .callTimeout(5, TimeUnit.SECONDS)
        .build();

    Crawler crawler = new Crawler(client, queueLimit, hostLimit);
    crawler.queue.add(HttpUrl.get(args[1]));
    crawler.parallelDrainQueue(threadCount);
  }

        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";
        options.fileConfigIds = "file1";

        int result = crawler.doCrawl(options);
        assertEquals(Constants.EXIT_OK, result);
    }

    public void test_doCrawl_withDataConfigIds() {
        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";

 */
package org.codelibs.fess.crawler;

import java.io.File;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.transformer.impl.FileTransformer;
import org.codelibs.fess.crawler.util.CrawlerWebServer;
import org.codelibs.opensearch.runner.OpenSearchRunner;
import org.dbflute.utflute.lastadi.LastaDiTestCase;

 */
package org.codelibs.fess.crawler.rule.impl;

import java.util.ArrayList;
import java.util.List;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

     *
     * @see org.codelibs.fess.crawler.entity.AccessResult#getAccessResultDataAsOne()
     */
    @Override
    public AccessResultData<IDTYPE> getAccessResultData() {
        return accessResultData;
    }

    /*
     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.entity.AccessResult#setAccessResultDataAsOne(org.codelibs.fess.crawler.db.exentity.AccessResultData)
     */

import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlQueueService} interface.