if (m.matches() && m.groupCount() > 0) {
            return m.group(1);
        }
        return null;
    }

    /**
     * Strips comments from a line (everything after '#' character).
     * @param line the line to strip comments from
     * @return the line without comments
     */
    protected String stripComment(final String line) {

 * </p>
 *
 * <p>
 * The class uses temporary files for processing large input streams and ensures that these files are deleted after
 * processing.
 * </p>
 *
 */
public class TikaExtractor extends PasswordBasedExtractor {

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

    /**

     */
    public ApiExtractor() {
        // NOP
    }

    /**
     * Initializes the API extractor, setting up the HTTP client and configuration.
     * This method is called after construction to initialize the HTTP client with
     * configured timeouts, authentication, and request headers.
     */
    @PostConstruct
    public void init() {
        if (logger.isDebugEnabled()) {

                try {
                    dateStr = getDateString(v);
                    final Date receivedDate = new MailDateFormat().parse(dateStr);
                    if (!receivedDate.after(today)) {
                        return receivedDate;
                    }
                } catch (final ParseException e) {
                    // ignore
                }
            }
        }

      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");

 * and handling the overall crawling lifecycle.
 *
 * <p>It implements the Runnable interface to be executed in a separate thread,
 * and the AutoCloseable interface to ensure resources are properly released after use.
 *
 * <p>The crawler uses several services and components, such as UrlQueueService, DataService,
 * UrlFilter, RuleManager, CrawlerContainer, IntervalController, and CrawlerClientFactory,
 * to perform its tasks.
 *

        /**
         * The class of the component to instantiate.
         */
        protected Class<T> cls;

        /**
         * The initializer function to be called after component creation.
         */
        protected Consumer<T> initializer;

        /**
         * The container instance.
         */
        protected StandardCrawlerContainer container;

        /**

        // Reset and verify
        transformer.reset();
        assertEquals(0, transformer.getTransformCallCount());
        assertNull(transformer.getLastResponseData());

        // Name should persist after reset
        assertEquals("workflowTransformer", transformer.getName());
    }

        // Should not match with conditions
        assertFalse(rule.match(responseData));

        // Clear conditions
        rule.clearConditions();

        // Should match after clearing conditions
        assertTrue(rule.match(responseData));
    }

    /**
     * Test rule matching with various ResponseData states
     */
    public void test_matchWithVariousResponseDataStates() {

        assertEquals(2, removedSitemaps.length);
        assertEquals("http://example.com/sitemap.xml", removedSitemaps[0]);
        assertEquals("http://test.com/sitemap.xml", removedSitemaps[1]);

        // Should be null after removal
        assertNull(crawlerContext.removeSitemaps());

        // Test with null
        crawlerContext.addSitemaps(null);
        assertNull(crawlerContext.removeSitemaps());