/**
     * Determines the content type of the given input stream using the provided parameters.
     * @param is the input stream to analyze
     * @param params the parameters containing additional information like filename
     * @return the detected content type
     */
    String getContentType(InputStream is, Map<String, String> params);

 * Provides common functionality such as access to CrawlerContainer components
 * and registration with the ExtractorFactory.
 *
 * <p>
 * This class handles the retrieval of essential crawler components like
 * {@link MimeTypeHelper} and {@link ExtractorFactory} from the
 * {@link CrawlerContainer}. It also provides a convenient method for
 * registering the extractor with the {@link ExtractorFactory}.
 * </p>
 *
 * <p>

 * result and storing it. Unsuccessful responses are logged for debugging purposes.
 * </p>
 *
 * <p>
 * The class uses {@link CrawlerContainer} to access components like {@link AccessResult}
 * and {@link UrlQueue}. It also uses {@link CrawlingParameterUtil} to access services
 * like {@link UrlQueueService} and DataService, as well as the {@link CrawlerContext}.
 * </p>
 *
 * <p>

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

/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**

ve/media/ico_verified-1407009642236.png" width="16" height="16" style="width:15px;height:15px;display:inline;margin:0;padding:0;display:block;-ms-interpolation-mode:bicubic;border:none;outline:none;display:inline-block;vertical-align:top;" class="inline-image" />&nbsp;<a href="https://twitter.com/i/redirect?url=https%3A%2F%2Ftwitter.com%2Ftokyo_bousai%3Ft%3D1%26cn%3DZmxleGlibGVfcmVjc18y%26sig%3D469e0de8684fdb4a9be152419cb6a5c173720fed%26al%3D1%26refsrc%3Demail%26iid%3D7c2e8db7f2e0464eb1fb51f268e...

ueued--,n.queue(a,"fx").length||h.empty.fire()})})),1===a.nodeType&&("height"in b||"width"in b)&&(c.overflow=[o.overflow,o.overflowX,o.overflowY],j=n.css(a,"display"),k="none"===j?L.get(a,"olddisplay")||tb(a.nodeName):j,"inline"===k&&"none"===n.css(a,"float")&&(o.display="inline-block")),c.overflow&&(o.overflow="hidden",l.always(function(){o.overflow=c.overflow[0],o.overflowX=c.overflow[1],o.overflowY=c.overflow[2]}));for(d in b)if(e=b[d],Nb.exec(e)){if(delete b[d],f=f||"toggle"===e,e===(p?"hide...

    <glob pattern="*.dif"/>
    <sub-class-of type="application/xml"/>
  </mime-type>

  <mime-type type="application/onix-message+xml">
    <_comment>ONline Information eXchange (ONIX) for books</_comment>
    <!-- see https://www.loc.gov/preservation/digital/formats/fdd/fdd000488.shtml -->
    <root-XML localName="ONIXMessage" namespaceURI="http://ns.editeur.org/onix/3.0/reference"/>