import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * 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

     */
    @Resource
    protected DataService<AccessResult<?>> dataService;

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    @Resource
    protected RuleManager ruleManager;

    /**
     * Container for managing crawler components.

import java.io.Serializable;

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

/**
 * The Rule interface defines the contract for implementing rules that can be applied to
 * response data in a web crawler. Implementations of this interface should provide logic
 * to determine if a given response data matches the rule, retrieve the rule's identifier,

 *   <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;

/**
 * {@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.
     */

import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * Implementation of the {@link RuleManager} interface.
 * Manages a list of rules for the crawler.
 * Provides methods to add, remove, check, and retrieve rules.
 *
 */
public class RuleManagerImpl implements RuleManager {

    /** The list of rules managed by this rule manager. */
    protected final List<Rule> ruleList = new ArrayList<>();

    /**

        StatefulTransformer transformer = new StatefulTransformer("statefulTransformer");

        // Process multiple URLs
        String[] urls = { "http://example1.com", "http://example2.com", "http://example3.com" };

        for (String url : urls) {
            ResponseData responseData = new ResponseData();
            responseData.setUrl(url);

        }
    }

    /**
     * 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);

     */
    void addIncludeUrlFilter(String sessionId, String url);

    /**
     * Adds a list of URLs to the include filter for a given session.
     *
     * @param sessionId the ID of the session for which the URLs should be included
     * @param urlList the list of URLs to be added to the include filter
     */
    void addIncludeUrlFilter(String sessionId, List<String> urlList);

    /**

import jakarta.annotation.Resource;

/**
 * Abstract base class for implementing {@link Rule} interfaces.
 * Provides common functionality and properties for crawler rules.
 *
 * <p>
 * This class handles the registration of rules with the {@link RuleManager}
 * and provides getter and setter methods for common properties such as
 * {@code ruleId} and {@code responseProcessor}.
 * </p>
 *
 * <p>