/** Flag indicating if the thread is still running. */
    protected AtomicBoolean running = new AtomicBoolean();

    /**
     * Constructs an AccessTimeoutTarget with the specified thread.
     * @param thread The thread to monitor.
     */
    public AccessTimeoutTarget(final Thread thread) {
        runningThread = thread;
        running.set(true);
    }

    /**
     * {@inheritDoc}
     *

         *
         * @param url the URL string to be set
         * @return the current RequestDataContext instance for method chaining
         */
        public RequestDataContext url(final String url) {
            data.setUrl(url);
            return this;
        }

        /**
         * Sets the weight for the request data.
         *
         * @param weight the weight to set

        }
        return c;
    }

    /**
     * Merges two characters, handling voiced and semi-voiced sound marks.
     * @param c1 The first character.
     * @param c2 The second character.
     * @return The merged character.
     */
    public static char mergeChar(final char c1, final char c2) {
        if (c2 == 'ﾞ') {

 *
 */
public class UnsupportedExtractException extends ExtractException {

    private static final long serialVersionUID = 1L;

    /**
     * Constructor.
     * @param message The error message.
     */
    public UnsupportedExtractException(final String message) {
        super(message, false, false);
    }

 * obtained during a crawling process.
 */
public interface ResponseProcessor {

    /**
     * Processes the given response data.
     *
     * @param responseData the response data to be processed
     */
    void process(ResponseData responseData);

 */
public class ICUNormalizer implements Normalizer {
    /** The transliterator used for normalization. */
    protected Transliterator transliterator;

    /**
     * Constructor for ICUNormalizer.
     * @param transliteratorId The ID of the transliterator to use.
     */
    public ICUNormalizer(final String transliteratorId) {
        transliterator = Transliterator.getInstance(transliteratorId);
    }

    @Override

     * Valid URL characters include:
     * - Lowercase letters (a-z)
     * - Uppercase letters (A-Z)
     * - Digits (0-9)
     * - Special characters: . - * _ : / + % = & ? # [ ] @ ~ ! $ ' ( ) , ;
     *
     * @param c the character to check
     * @return {@code true} if the character is a valid URL character, {@code false} otherwise
     */
    public static boolean isUrlChar(final char c) {
        if (c >= 'a' && c <= 'z' //

        rule.addCondition("url", "https://example\\.com/\\?param=.*");

        ResponseData responseData1 = new ResponseData();
        responseData1.setUrl("https://example.com/?param=value");
        assertTrue(rule.match(responseData1));

        ResponseData responseData2 = new ResponseData();
        responseData2.setUrl("https://exampleXcom/?param=value");
        assertFalse(rule.match(responseData2));
    }

    int NO_URL_IN_QUEUE = 4;

    /** Constant indicating that the crawler is waiting for new URLs. */
    int WAIT_NEW_URL = 8;

    /**
     * Introduces a delay based on the specified type.
     *
     * @param type the type of delay to be introduced
     */
    void delay(int type);

     */
    protected List<Throwable> failures = Collections.synchronizedList(new ArrayList<>());

    /**
     * Adds a Throwable to the list of failures.
     *
     * @param t the Throwable to add
     */
    public void addFailure(final Throwable t) {
        failures.add(t);
    }

    /**
     * Checks if there are any failures recorded.
     *