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

import java.util.Map;

import org.codelibs.core.lang.ThreadUtil;

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.service;

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.
 *

        assertFalse(robotsTxt.allows("/aaa", "Crawler"));
        assertTrue(robotsTxt.allows("/bbb", "Crawler"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler"));
        assertTrue(robotsTxt.allows("/ddd", "Crawler"));
        assertTrue(robotsTxt.allows("/aaa", "Crawler/1.0"));
        assertFalse(robotsTxt.allows("/bbb", "Crawler/1.0"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler/1.0"));

     *
     * @see org.codelibs.fess.crawler.entity.AccessResult#getAccessResultDataAsOne()
     */
    @Override
    public AccessResultData<IDTYPE> getAccessResultData() {
        return accessResultData;
    }

    /*
     * (non-Javadoc)
     *
     * @see
     * org.codelibs.fess.crawler.entity.AccessResult#setAccessResultDataAsOne(org.codelibs.fess.crawler.db.exentity.AccessResultData)
     */

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

import java.util.HashMap;
import java.util.Map;

import org.codelibs.fess.crawler.client.fs.FileSystemClient;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.crawler.client.storage.StorageClient;

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

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

import java.io.UnsupportedEncodingException;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * Implementation of the {@link AccessResultData} interface.
 *
 * @param <IDTYPE> the type of the identifier
 */

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

 */
package org.codelibs.fess.crawler.filter.impl;

import java.util.LinkedHashSet;
import java.util.List;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

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

import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.helper.RobotsTxtHelper;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.codelibs.fess.crawler.service.impl.UrlFilterServiceImpl;
import org.codelibs.fess.crawler.util.CrawlerWebServer;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;