*
 * <p>The extractor supports two types of password management:
 * <ul>
 *   <li>Static passwords configured via {@link #addPassword(String, String)}</li>
 *   <li>Dynamic passwords provided through extraction parameters</li>
 * </ul>
 *
 * <p>Passwords are matched against URLs or resource names using regular expression patterns.

     */
    boolean match(String url);

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**

import org.codelibs.fess.crawler.entity.ResponseData;

/**
 * RegexRule is a rule implementation that uses regular expressions to match against the ResponseData.
 * It allows defining multiple regular expressions for different fields of the ResponseData.
 * The rule can be configured to require all regular expressions to match (allRequired = true) or
 * only one of them (allRequired = false). It also supports a default rule that always matches.

        }
    }

    /**
     * Adds a client with a regular expression pattern.
     * @param regex The regular expression to match URLs.
     * @param client The CrawlerClient instance.
     */
    public void addClient(final String regex, final CrawlerClient client) {
        if (StringUtil.isBlank(regex)) {
            throw new CrawlerSystemException("A regular expression is null.");
        }
        if (client == null) {

     * @return a list of compiled regular expression patterns representing the URLs to include
     */
    List<Pattern> getIncludeUrlPatternList(String sessionId);

    /**
     * Retrieves a list of URL patterns to be excluded for a given session.
     *
     * @param sessionId the identifier of the session for which to retrieve the exclude URL patterns

            clientFactoryList.remove(0);
        }
    }

    /**
     * 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.
     */

     * @param regex The regular expression for the client.
     * @param client The CrawlerClient instance.
     */
    @Override
    public void addClient(final String regex, final CrawlerClient client) {
        factory.addClient(regex, client);
    }

    /**
     * Adds a client to the wrapped factory at a specific position.
     * @param regex The regular expression for the client.

     */
    @Override
    public void close() {
        clientFactory.close();
    }

    /**
     * Adds an include filter for URLs.
     * Only URLs matching this regular expression will be crawled.
     * @param regexp The regular expression for the include filter.
     */
    public void addIncludeFilter(final String regexp) {
        if (StringUtil.isNotBlank(regexp)) {
            urlFilter.addInclude(regexp);

 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**
     * Regular expression pattern to match the charset attribute in the meta tag of HTML documents.

     * (java.lang.String)
     */
    /**
     * Retrieves a list of URL patterns to be excluded for a given session.
     * @param sessionId The ID of the session.
     * @return A list of compiled regular expression patterns.
     */
    @Override
    public List<Pattern> getExcludeUrlPatternList(final String sessionId) {
        return dataHelper.getExcludeUrlPatternList(sessionId);
    }