/**
 * Helper class for converting URLs based on a set of predefined rules.
 *
 * <p>This class provides functionality to convert URLs by replacing parts of the URL
 * based on a map of target strings and their corresponding replacements. It allows
 * adding new conversion rules, setting the entire conversion map, and converting
 * URLs using these rules.</p>
 *

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.
 * It uses a {@link UrlFilterService} to manage the URL filtering rules.
 * The class supports caching of include and exclude patterns for scenarios where a session ID is not available.

    }

    /**
     * Returns the set of robots.txt URLs.
     * @return The set of robots.txt URLs.
     */
    public Set<String> getRobotsTxtUrlSet() {
        return robotsTxtUrlSet;
    }

    /**
     * Sets the set of robots.txt URLs.
     * @param robotsTxtUrlSet The set of robots.txt URLs.
     */
    public void setRobotsTxtUrlSet(final Set<String> robotsTxtUrlSet) {

 */
package org.codelibs.fess.crawler.rule;

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

/**
 * The RuleManager interface provides methods to manage rules for processing response data.
 * It allows adding, retrieving, and removing rules, as well as checking for their existence.
 */
public interface RuleManager {

    /**
     * Retrieves the rule associated with the given response data.
     *

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

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<>();

    /**

        }
    }

    /**
     * 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);