throw e;
        } catch (final Exception e) {
            throw new CrawlingAccessException("Could not parse Sitemaps: " + preloadDate, e);
        }
    }

    /**
     * Parses a text-based sitemap from the given input stream.
     * @param in the input stream to parse
     * @return the parsed sitemap set
     */
    protected SitemapSet parseTextSitemaps(final InputStream in) {

                return new String[0];
            }
        }
        return keywords.toArray(new String[keywords.size()]);
    }

    /**
     * Extracts keywords from the given query string based on the specified fields.
     *
     * @param q the query string to parse and extract keywords from
     * @param fields the fields to consider when extracting keywords

 *
 * <p>This class uses various utilities such as ReadingConverter, Normalizer, and SuggestAnalyzer
 * to process and analyze the input data.</p>
 *
 * <p>It also handles the exclusion of search words based on certain criteria and manages the
 * maximum length of analyzed content.</p>
 *
 * <p>Methods in this class may throw SuggesterException in case of failures during the parsing process.</p>
 *
 * <p>Usage example:</p>

/**
 * 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 {

    /**
     * Logger for this class.
     */

        assertEquals(0, CrawlerStatus.RUNNING.compareTo(CrawlerStatus.RUNNING));
        assertEquals(0, CrawlerStatus.DONE.compareTo(CrawlerStatus.DONE));

        // INITIALIZING < RUNNING < DONE (based on ordinal)
        assertTrue(CrawlerStatus.INITIALIZING.compareTo(CrawlerStatus.RUNNING) < 0);
        assertTrue(CrawlerStatus.INITIALIZING.compareTo(CrawlerStatus.DONE) < 0);

 *
 * <p>
 * It provides methods to set and retrieve the server address, port, username,
 * password, and domain. Additionally, it offers a method to construct a path
 * prefix for SMB1 URLs based on the configured server and port.
 * </p>
 *
 * <p>
 * The path prefix is in the format "smb1://server:port/", where the port is
 * included only if it's greater than 0. If the server is not set, the path

 * supporting pattern matching for user agents, path-based access control, and crawl delay settings.</p>
 *
 * <p>Key features:</p>
 * <ul>
 *   <li>Supports multiple user-agent directives with pattern matching</li>
 *   <li>Handles Allow and Disallow rules for path-based access control</li>
 *   <li>Manages crawl delay settings per user agent</li>

                    return true;
                }
            }
        }
        return ret;
    }

    /**
     * Generates URL queue entries for a new session based on access results from a previous session.
     *
     * @param previousSessionId The previous session ID.
     * @param sessionId The new session ID.
     */
    @Override

            }
            setId(bean, id);
            return bean;
        }
        return null;
    }

    /**
     * Retrieves a list of documents from the OpenSearch index based on the specified criteria.
     *
     * @param <T> The type of objects to retrieve.
     * @param clazz The class of the objects to retrieve.
     * @param sessionId The session ID to filter by (optional).

      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes