} catch (final ChildUrlsException e) {
            String[] urls = e.getChildUrlList().stream().map(r -> r.getUrl()).sorted().toArray(String[]::new);
            assertEquals(3, urls.length);
            assertEquals(baseUrl + "dir1/", urls[0]);
            assertEquals(baseUrl + "dir3/", urls[1]);
            assertEquals(baseUrl + "file1.txt", urls[2]);
        }
        try {
            smbClient.doGet(baseUrl + "dir1/");

 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL
 * from each sitemap, and creates a new {@link RequestData} object for each URL.

            url = url.substring(0, idx);
        }

        url = url.replace("/./", "/");

        idx = url.indexOf(";jsessionid");
        if (idx >= 0) {
            url = url.replaceFirst(";jsessionid=[a-zA-Z0-9\\.]*", "");
        }

        if (url.indexOf(' ') >= 0) {
            url = url.replace(" ", "%20");
        }

        String oldUrl = null;

 * 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;

    /** Delay in milliseconds when no URL is in the queue */

                }
            }
        }
    }

    /**
     * Generate a path from a url.
     *
     * @param url URL
     * @return path File path
     */
    protected String getFilePath(final String url) {
        return url.replaceAll("/+", "/")
                .replace("./", "")
                .replace("../", "")
                .replaceAll("/$", "/index.html")

     * @param url the URL to be excluded
     */
    void addExcludeUrlFilter(String sessionId, String url);

    /**
     * Adds a list of URLs to be excluded from crawling for a specific session.
     *
     * @param sessionId the ID of the session for which the URLs should be excluded
     * @param urlList the list of URLs to be excluded
     */

/**
 * {@link ChildUrlsException} is thrown when child URLs are found during crawling.
 * It extends {@link CrawlerSystemException} and holds a set of {@link RequestData}
 * representing the child URLs that caused the exception.
 *
 */
public class ChildUrlsException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**
     * The list of child URLs.
     */

 *   <li>{@code POST_PROCESSING} - Represents the post-processing state.</li>
 *   <li>{@code NO_URL_IN_QUEUE} - Indicates that there are no URLs in the queue.</li>
 *   <li>{@code WAIT_NEW_URL} - Indicates that the crawler is waiting for new URLs.</li>
 * </ul>
 */
public interface IntervalController {
    /** Constant representing the pre-processing state. */
    int PRE_PROCESSING = 1;

        this.data = data;
    }

    /**
     * Add a child URL.
     * @param url the request data to add to the child URL set
     */
    public void addUrl(final RequestData url) {
        childUrlSet.add(url);
    }

    /**
     * Add child URLs.
     * @param c the collection of request data to add to the child URL set
     */
    public void addAllUrl(final Collection<RequestData> c) {

        }
    }

    /**
     * Registers a client component with a regular expression.
     * The component will be loaded into all registered CrawlerClientFactories.
     * @param regex The regular expression to match URLs.
     * @param componentName The name of the component to register.
     */
    public synchronized void register(final String regex, final String componentName) {
        clientMap.put(regex, componentName);