*
 * <p>Example usage:
 * <pre>
 *   Crawler crawler = new Crawler();
 *   crawler.addUrl("http://example.com/");
 *   crawler.execute();
 *   crawler.close();
 * </pre>
 */
public class Crawler implements Runnable, AutoCloseable {

    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /**
     * Service for managing URL queues during crawling.
     */

    <glob pattern="*.wspolicy"/>
  </mime-type>
  
  <mime-type type="image/x-tga">
     <alias type="image/x-targa"/>
     <!-- trailer bytes: 54 52 55 45 56 49 53 49 4F 4E 2D 58 46 49 4C 45 2E 00
          trailer as string: TRUEVISION-XFILE\\x2E\\x00
          Some .tga files may be conflicting with application/x-123 recognition, 

        NameTrackingTransformer tracker = new NameTrackingTransformer();
        ResponseData responseData = new ResponseData();

        // Transform with different names
        tracker.setName("name1");
        tracker.transform(responseData);

        tracker.setName("name2");
        tracker.transform(responseData);

        tracker.setName("name3");
        tracker.transform(responseData);

<components namespace="fessCrawler">
    <include path="crawler/container.xml"/>
    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>
    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>

        return id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#setId(IDTYPE)
     */
    @Override
    public void setId(final IDTYPE id) {
        this.id = id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#getSessionId()
     */
    @Override
    public String getSessionId() {

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

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

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

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**

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.extractor.impl;

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

import org.codelibs.core.io.InputStreamUtil;
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;

/**

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

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.IOException;

import org.apache.commons.io.IOUtils;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;