* It uses Log4j2 for logging.
 *
 * <p>
 * The class contains methods for logging different types of events, such as:
 * </p>
 * <ul>
 *   <li>Starting and finishing threads</li>
 *   <li>Starting and cleaning up crawling</li>
 *   <li>Handling unsupported URLs</li>
 *   <li>Checking last modified dates</li>
 *   <li>Getting content</li>
 *   <li>Handling redirects</li>

      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise

        // Add entries
        statusMap.put(CrawlerStatus.INITIALIZING, "Starting up");
        statusMap.put(CrawlerStatus.RUNNING, "In progress");
        statusMap.put(CrawlerStatus.DONE, "Completed");

        // Verify entries
        assertEquals(3, statusMap.size());
        assertEquals("Starting up", statusMap.get(CrawlerStatus.INITIALIZING));

      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise

        extensionMap.put("otg", "svg");

        extractorMap.put("pdf", new PdfExtractor());
        extractorMap.put("svg", new XmlExtractor());
    }

    /**
     * Initializes the extractor by starting the office manager.
     *
     * @throws CrawlerSystemException if the office manager is null or fails to start
     */
    @PostConstruct
    public void init() {
        if (officeManager == null) {

 * exceptions during retries.</p>
 *
 * <p>Key features:</p>
 * <ul>
 *   <li>Configurable maximum retry attempts</li>
 *   <li>Adjustable interval between retries</li>
 *   <li>Exception tracking and aggregation</li>
 *   <li>Request lifecycle monitoring through listener</li>
 * </ul>
 *
 * <p>By default, it will:</p>
 * <ul>
 *   <li>Retry up to 5 times</li>
 *   <li>Wait 500ms between retries</li>

                        .forPath("/minio/health/ready")//
                        .forPort(port)//
                        .withStartupTimeout(Duration.ofSeconds(30)));
        logger.info("Starting {}", IMAGE_NAME);
        minioServer.start();
        logger.info("Started {}", IMAGE_NAME);

        String bucketName = "fess";
        Integer mappedPort = minioServer.getFirstMappedPort();

    /**
     * Lock object for synchronizing access to active thread count.
     */
    protected Object activeThreadCountLock = new Object();

    /**
     * Atomic counter for tracking the number of accesses made.
     */
    protected AtomicLong accessCount = new AtomicLong(0);

    /**
     * Current status of the crawler.
     */

                        "-s", "testuser2 private share;/testuser2;no;no;no;testuser2", //
                        "-g", "log level = 3");
        logger.info("Starting Samba container with image {}", IMAGE_NAME);
        sambaServer.start();
        logger.info("Samba container started");

        String host = sambaServer.getContainerIpAddress();

        }
        return null;
    }

    /**
     * Extracts a date string from the received header text.
     *
     * @param text the received header text
     * @return the date string starting from the day of week, or null if not found
     */
    private static String getDateString(final String text) {
        for (final String dow : DAY_OF_WEEK) {
            final int i = text.lastIndexOf(dow);