import org.codelibs.core.io.FileUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
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.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;

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

import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;
import org.slf4j.Logger;

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

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;

import java.util.stream.Collectors;

import javax.annotation.PostConstruct;

import org.codelibs.fess.crawler.entity.EsUrlFilter;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.service.UrlFilterService;
import org.codelibs.fess.crawler.util.EsCrawlerConfig;
import org.opensearch.action.DocWriteRequest.OpType;
import org.opensearch.index.query.QueryBuilders;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.EsUrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.EsAccessException;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.util.EsCrawlerConfig;

            ThreadUtil.sleep(500);
            count++;
            final Map<String, Object> scheduler = getSchedulerItem(namePrefix);
            assertTrue(scheduler.containsKey("running"));
            isRunning = (Boolean) scheduler.get("running");
        }
        if (300 <= count) {
            logger.info("Time out: Failed to start crawler)");
            fail(); // Time Out

 * 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;

/**
 * @author shinsuke
 *
 */
public interface ResponseProcessor {

    void process(ResponseData responseData);

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.SitemapFile;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.SitemapsException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

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

import java.io.ByteArrayInputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import javax.xml.XMLConstants;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

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

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

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;