import org.mortbay.jetty.handler.DefaultHandler;
import org.mortbay.jetty.handler.HandlerList;
import org.mortbay.jetty.handler.ResourceHandler;
import org.mortbay.log.Log;

/**
 * @author shinsuke
 *
 */
public class CrawlerWebServer {
    private final File docRoot;

    private final Server server;

    private boolean tempDocRoot = false;

    public CrawlerWebServer(final int port) {
        this(port, createDocRoot(3));

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

import java.util.ArrayList;

/**
 * OpenSearchResultList is a list of OpenSearch results.
 *
 * @param <E> The type of elements in this list.
 */
public class OpenSearchResultList<E> extends ArrayList<E> {
    /**
     * Constructs a new OpenSearchResultList.
     */
    public OpenSearchResultList() {
        super();
    }

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from .xls file.
 *
 * @author shinsuke
 *
 */
public class MsExcelExtractor extends AbstractExtractor {

    /**
     * Creates a new MsExcelExtractor instance.
     */
    public MsExcelExtractor() {
        super();
    }

    /**

import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

import jakarta.annotation.Resource;

/**
 * The Crawler class is the main class for web crawling. It manages the crawling process,
 * including adding URLs to the queue, filtering URLs, managing crawler threads,
 * and handling the overall crawling lifecycle.
 *

 * This exception holds an array of Throwable objects representing the individual causes.
 * It extends CrawlingAccessException and provides methods to print the stack traces of all causes.
 *
 */
public class MultipleCrawlingAccessException extends CrawlingAccessException {

    private static final long serialVersionUID = 1L;

    /**
     * The array of throwables that caused this exception.
     */

import org.apache.http.impl.auth.NTLMEngine;
import org.apache.http.impl.auth.NTLMEngineException;

/**
 * SmbjEngine is a NTLM Engine implementation based on smbj.
 *
 * @author shinsuke
 *
 */
public class SmbjEngine implements NTLMEngine {

    /**
     * Creates a new SmbjEngine instance.
     */
    public SmbjEngine() {
        super();
    }

    /**
     * Generates a Type 1 NTLM message.

/**
 * @author shinsuke
 *
 */
public class MimeTypeHelperImplTest extends PlainTestCase {

    private StandardCrawlerContainer container;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        container = new StandardCrawlerContainer().singleton("mimeTypeHelper", MimeTypeHelperImpl.class);
    }

                return func.apply(this).actionGet(connTimeout, TimeUnit.MILLISECONDS);
            } catch (final IndexNotFoundException | VersionConflictEngineException e) {
                logger.debug("{} occurs.", e.getClass().getName(), e);
                throw e;
            } catch (final Exception e) {
                if (retryCount > maxRetryCount) {
                    throw e;
                }

 * {@link ResultData} object containing the extracted data and child URLs.
 * </p>
 */
public class HtmlTransformer extends AbstractTransformer {

    /** Logger instance for this class */
    private static final Logger logger = LogManager.getLogger(HtmlTransformer.class);

    /**
     * Constructs a new HtmlTransformer.
     */
    public HtmlTransformer() {
        // Default constructor

 * 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.
 *
 * <p>
 * The class uses a map of field names to Pattern objects to store the regular expressions.
 * The match method extracts the values of the specified fields from the ResponseData and
 * applies the corresponding regular expressions.
 * </p>
 *