/**
     * Constructs a new {@code CrawlerSystemException} with the specified detail message and cause.
     *
     * @param message the detail message (which is saved for later retrieval by the {@link #getMessage()} method).
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */
public class DefaultIntervalController extends AbstractIntervalController {

    /** Delay in milliseconds after processing a URL */
    protected long delayMillisAfterProcessing = 0L;

 *
 * <p>
 * This class defines the contract for delaying the crawling process at various points, such as:
 * </p>
 * <ul>
 *   <li>Before processing a URL ({@link #delayBeforeProcessing()})</li>
 *   <li>After processing a URL ({@link #delayAfterProcessing()})</li>
 *   <li>When there are no URLs in the queue ({@link #delayAtNoUrlInQueue()})</li>

        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"));

        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) {

        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");

 * </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());
    }