crawlerContext.setIntervalController(new TestIntervalController());

        // Start crawling
        crawlerContext.setStatus(CrawlerStatus.RUNNING);
        crawlerContext.setActiveThreadCount(5);

        // Simulate crawling progress
        for (int i = 0; i < 100; i++) {
            crawlerContext.incrementAndGetAccessCount();

     * @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
     */

/**
 * Helper class for managing duplicate host configurations in the Fess search system.
 * This class handles URL conversion based on duplicate host rules, allowing multiple
 * hostnames or URLs to be treated as equivalent for crawling and indexing purposes.
 * It maintains a list of DuplicateHost rules and applies them to URLs.
 *
 */
public class DuplicateHostHelper {

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * The class CrawlerSystemException is a runtime exception that is thrown when a system error occurs during crawling.
 * It extends the RuntimeException class and provides constructors for creating exceptions with a message, a cause, or both.

 * This can help Google index your videos and display them in Google Video search results.
 * </p>
 *
 * @see <a href="https://developers.google.com/search/docs/crawling-indexing/sitemaps/video-sitemaps">Video Sitemaps</a>
 */
public class SitemapVideo implements Serializable {

    private static final long serialVersionUID = 1L;

    /**

errors.design_file_name_is_invalid = Der Dateiname ist ungültig.
errors.design_file_is_unsupported_type = Dieser Dateityp wird nicht unterstützt.
errors.failed_to_create_crawling_config_at_wizard = Fehler beim Erstellen einer Crawling-Konfiguration in einem Assistenten.
errors.design_editor_disabled = Diese Funktion ist deaktiviert.
errors.not_found_on_file_system = Nicht gefunden. Ursache: {0}

import jakarta.validation.constraints.Min;
import jakarta.validation.constraints.Size;

/**
 * Form class for creating data store configurations.
 * Data configs allow administrators to set up crawling of various data sources
 * including databases, CSV files, and other structured data sources.
 */
public class CreateForm {

    /**
     * Creates a new CreateForm instance.
     */
    public CreateForm() {

 * This can help Google index your images and display them in Google Images search results.
 * </p>
 *
 * @see <a href="https://developers.google.com/search/docs/crawling-indexing/sitemaps/image-sitemaps">Google Image Sitemaps</a>
 */
public class SitemapImage implements Serializable {

    private static final long serialVersionUID = 1L;

    /**
     * The URL of the image.

import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.container.CrawlerContainer;

import jakarta.annotation.Resource;

/**
 * Creates and manages crawler clients for web crawling operations.
 * This class handles the registration and loading of crawler client factories and their associated clients.
 * <p>
 * The class maintains a mapping between regular expressions and component names, and manages a list

import jakarta.annotation.Resource;

/**
 * API action for admin job log management.
 * Provides RESTful API endpoints for viewing and managing job execution logs in the Fess search engine.
 * Job logs contain information about crawling jobs, indexing tasks, and system maintenance operations.
 *
 */
public class ApiAdminJoblogAction extends FessApiAdminAction {

    private static final Logger logger = LogManager.getLogger(ApiAdminJoblogAction.class);