assertTrue(urlFilter.match("https://example.com/page"));
        assertFalse(urlFilter.match("https://other.com/page"));

        // Clear the filter
        urlFilter.clear();

        // After clear, all URLs should match (no filters applied)
        assertTrue(urlFilter.match("https://example.com/page"));
        assertTrue(urlFilter.match("https://other.com/page"));

        assertSame(testRule, rules.get(0));
        assertSame(testRule, rules.get(1));
        assertSame(testRule, rules.get(2));
    }

    /**
     * Test property changes after registration
     */
    public void test_propertyChangesAfterRegistration() {
        TestResponseProcessor processor1 = new TestResponseProcessor();
        testRule.setRuleId("originalId");

                queue.add(new MyToken(word, synonym.startOffset, synonym.endOffset, posInc, i + 1));
                if (!expand) {
                    break;
                }
            }

            // enqueue after-synonym
            afterSynonymProduced =
                    processAfterSynonym(synonym.endOffset, idx < synonyms.size() - 1 ? synonyms.get(idx + 1).startOffset : block.length());

            nextStart = synonym.endOffset;

 * </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
                }
            }
        }

        // 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() {

 * 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;

        /**