*/
    @Override
    protected Pattern getEncodingPattern() {
        return xmlEncodingPattern;
    }

    /**
     * Returns the precompiled {@link Pattern} used to match XML tags within the content.
     * This pattern is utilized by the extractor to identify and process XML elements.
     *
     * @return the {@link Pattern} instance for XML tag matching
     */
    @Override

/**
 * The Response interface serves as a marker interface for all response types
 * in the suggestion system. Implementations of this interface are used to
 * encapsulate the results of various operations and queries within the system.
 *
 * <p>Classes implementing this interface should provide specific details and
 * data relevant to the type of response they represent.</p>
 */
public interface Response {

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

import org.codelibs.core.lang.StringUtil;

/**
 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,
 * check availability, and destroy the container. Additionally, it provides
 * a default method to initialize the container with specific protocol handlers.
 *
 */

import java.util.List;

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

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *
 * @param <QUEUE> the type of URL queue
 */
public interface UrlQueueService<QUEUE extends UrlQueue<?>> {

    /**
     * Updates the session ID.
     *

import jp.gr.java_conf.dangan.util.lha.LhaFile;
import jp.gr.java_conf.dangan.util.lha.LhaHeader;

/**
 * Extractor implementation for LHA (LZH) archive files.
 * This extractor can extract text content from files within LHA archives
 * by using appropriate extractors for each contained file type.
 *
 * @author shinsuke
 */
public class LhaExtractor extends AbstractExtractor {
    /** Logger for this class. */

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

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a URL entry within a sitemap.
 *
 * <p>
 * This class encapsulates the properties of a URL as defined in the sitemap XML format,
 * including its location, last modification date, change frequency, and priority.

 * </ul>
 *
 * <p>
 * The class uses synchronization to ensure thread safety when accessing and modifying the URL queue.
 * It also checks for duplicate URLs before adding them to the queue,
 * both within the queue itself and against previously accessed URLs stored in the {@link MemoryDataHelper}.
 * </p>
 *
 */
/**
 * This class is an implementation of {@link UrlQueueService}.
 */