/**
     * 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="*.sse"/>
  </mime-type>
  <mime-type type="application/vnd.liberty-request+xml"/>
  <mime-type type="application/vnd.llamagraphics.life-balance.desktop">
    <glob pattern="*.lbd"/>
  </mime-type>
  <mime-type type="application/vnd.llamagraphics.life-balance.exchange+xml">
    <glob pattern="*.lbe"/>
  </mime-type>
  
  <mime-type type="application/vnd.lotus-1-2-3">

    }

    /**
     * Strips comments from a line (everything after '#' character).
     * @param line the line to strip comments from
     * @return the line without comments
     */
    protected String stripComment(final String line) {
        final int commentIndex = line.indexOf('#');
        if (commentIndex != -1) {
            return line.substring(0, commentIndex);
        }
        return line;
    }

                Thread.currentThread().getContextClassLoader().getResourceAsStream("suggest_settings/default-badwords.txt")))) {

            String line;
            while ((line = br.readLine()) != null) {
                if (line.length() > 0 && !line.startsWith("#")) {
                    list.add(line.trim());
                }
            }
        } catch (final Exception e) {

<!--<![endif]-->
<tbody>
<tr>
<td width="50" style="width:50px;padding:0;margin:0;line-height:1px;font-size:1px;" class="margins"></td>
<td align="center" style="padding:0;margin:0;line-height:1px;font-size:1px;">
<table width="100%" align="left" cellpadding="0" cellspacing="0" border="0" class="collapse" style="padding:0;margin:0;line-height:1px;font-size:1px;">
<tbody>

            final List<String> rules = Analysis.parseWordList(env, settings, "synonyms", s -> s);
            final StringBuilder sb = new StringBuilder();
            for (final String line : rules) {
                sb.append(line).append(System.getProperty("line.separator"));
            }
            reader = new StringReader(sb.toString());
        } else if (settings.get("synonyms_path") != null) {

                this.getClass().getClassLoader().getResourceAsStream("suggest_indices/suggest/mappings-default.json")))) {

            String line;
            while ((line = br.readLine()) != null) {
                mappingSource.append(line);
            }
        }
        return mappingSource.toString();
    }

    private String getDefaultIndexSettings() throws IOException {