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

/**
 * Configuration class for OpenSearch crawler settings.
 * This class provides configuration for index names, shards, and replicas
 * for the queue, data, and filter indices used by the crawler.
 */
public class OpenSearchCrawlerConfig {
    /**
     * Constructs a new OpenSearchCrawlerConfig.
     */

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

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

/**
 * The ResponseProcessor interface defines a contract for processing response data.
 * Implementations of this interface are responsible for handling the response data

import java.util.regex.Pattern;

import javax.xml.xpath.XPathNodes;

import org.codelibs.core.lang.StringUtil;
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.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;

        if (artifactType != ArtifactType.CRAWLER) {
            return false;
        }

        if ("fess-crawler".equals(name)//
                || "fess-crawler-db".equals(name)//
                || "fess-crawler-db-h2".equals(name)//
                || "fess-crawler-db-mysql".equals(name)//
                || "fess-crawler-es".equals(name)//
                || "fess-crawler-opensearch".equals(name)//

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

                                        <la:errors property="crawler"/>
                                        <div class="form-check">
                                            <la:checkbox styleId="crawler" styleClass="form-check-input" property="crawler"/>
                                            <label for="crawler" class="form-check-label">

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

import java.util.LinkedHashMap;
import java.util.Map;

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

/**
 * Helper class for converting URLs based on a set of predefined rules.
 *

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

import java.util.ArrayList;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.Queue;
import java.util.regex.Pattern;

import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;

/**

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

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

/**

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

import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;