/**
     * 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 {

    /**

    <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"/>