}

    /*
     * static class SynInfo { final String src; final int offset, length; final String[] synonyms; Mode mode; int count;
     * SynInfo(String src, int offset, int length, String[] synonyms){ this.src = src; this.offset = offset; this.length
     * = length; this.synonyms = synonyms; }
     *
     * static enum Mode { PREV, SYN, AFTER; } }
     */

    static class MyTokensComparator implements Comparator<MyToken> {

    /** The parent URL of the accessed resource. */
    protected String parentUrl;

    /** The status of the access result. */
    protected Integer status = Constants.OK_STATUS;

    /** The HTTP status code of the access result. */
    protected Integer httpStatusCode;

    /** The HTTP method used for the access. */
    protected String method;

    /** The MIME type of the accessed resource. */

import org.apache.logging.log4j.Logger;
import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.crawler.Constants;

import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.exception.InterruptedRuntimeException;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.io.FileUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;

 *   <li>Configure whether to use the filename for MIME type detection when the stream is octet-stream.</li>
 * </ul>
 *
 * <p>
 * The MIME type detection is based on the {@code tika-mimetypes.xml} resource, which is loaded during initialization.
 * </p>
 *
 * <p>
 * Usage:
 * </p>
 * <pre>
 * MimeTypeHelperImpl mimeTypeHelper = new MimeTypeHelperImpl();

import java.util.Map;

import org.apache.commons.io.output.DeferredFileOutputStream;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.beans.BeanDesc;
import org.codelibs.core.beans.PropertyDesc;
import org.codelibs.core.beans.factory.BeanDescFactory;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.crawler.Constants;

import org.codelibs.core.beans.BeanDesc;
import org.codelibs.core.beans.PropertyDesc;
import org.codelibs.core.beans.factory.BeanDescFactory;
import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.misc.Pair;
import org.codelibs.core.timer.TimeoutManager;
import org.codelibs.core.timer.TimeoutTask;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.core.io.InputStreamUtil;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.misc.Pair;
import org.codelibs.core.stream.StreamUtil;
import org.codelibs.fess.crawler.Constants;

/**

        try {
            final XPathNodes list = getXPathAPI().selectNodeList(document, "//BASE");
            if (list.size() > 0) {
                final Node node = list.get(0);
                final Node attrNode = node.getAttributes().getNamedItem("href");
                if (attrNode != null) {
                    String attrValue = attrNode.getNodeValue();