/** The transliterator for Hiragana-Katakana conversion. */
    protected final Transliterator transliterator = Transliterator.getInstance("Hiragana-Katakana");

    /** Flag indicating if the converter is initialized. */
    protected volatile boolean initialized = false;

    /** Tokenizer factory. */
    protected TokenizerFactory tokenizerFactory = null;

    /**
     * Default constructor.
     */

        super();
    }

    /**
     * Pattern for XML encoding.
     */
    protected Pattern xmlEncodingPattern =
            Pattern.compile("<\\?xml.*encoding\\s*=\\s*['\"]([\\w\\d\\-_]*)['\"]\\s*\\?>", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for XML tags.
     */
    protected Pattern xmlTagPattern = Pattern.compile("<[^>]+>");

    /**
     * Returns the encoding pattern.

     */
    protected AtomicLong accessCount = new AtomicLong(0);

    /**
     * Current status of the crawler.
     */
    protected volatile CrawlerStatus status = CrawlerStatus.INITIALIZING;

    /**
     * Filter for URLs to control which URLs are processed.
     */
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.
     */
    protected RuleManager ruleManager;

 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */
    protected int preloadSize = 512;

    /**
     * Creates a new SitemapsHelper instance.
     */
    public SitemapsHelper() {
        // Default constructor
    }

    /**

    /**
     * Cache for include filters.
     */
    protected LoadingCache<String, List<Pattern>> includeFilterCache;

    /**
     * Cache for exclude filters.
     */
    protected LoadingCache<String, List<Pattern>> excludeFilterCache;

    /**
     * The expiration time for the filter cache in seconds.
     */
    protected int filterCacheExpireAfterWrite = 10; // 10sec

    /**

    /** The unique identifier for the access result data. */
    protected IDTYPE id;

    /** The name of the transformer associated with this access result data. */
    protected String transformerName;

    /** The data as a byte array. */
    protected byte[] data;

    /** The encoding used for the access result data. */
    protected String encoding;

    /**
     * Constructs a new AccessResultDataImpl instance.

    private static final int MAX_LOOP_COUNT = 10;

    /** The thread being monitored. */
    protected Thread runningThread;

    /** Flag indicating if the thread is still running. */
    protected AtomicBoolean running = new AtomicBoolean();

    /**
     * Constructs an AccessTimeoutTarget with the specified thread.
     * @param thread The thread to monitor.

    @Resource
    protected CrawlerContainer crawlerContainer;

    /** The initialization parameter map. */
    protected Map<String, Object> initParamMap;

    /** The maximum cached content size in bytes. Default is 1MB. */
    protected long maxCachedContentSize = 1024L * 1024L; // 1MB

    /** The access timeout in seconds. Default is null (no timeout). */
    protected Integer accessTimeout = null; // seconds

     * @param deferred The Deferred object to resolve or reject the response.
     */
    protected abstract void processRequest(Client client, Deferred<T> deferred);

    /**
     * Returns a validation error message, or null if there are no errors.
     * @return A validation error message, or null.
     */
    protected abstract String getValidationError();

 * methods, leveraging the helper methods provided by this abstract class.
 * </p>
 *
 */
public abstract class AbstractExtractor implements Extractor {

    /** The crawler container. */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**
     * Constructs a new AbstractExtractor.
     */
    public AbstractExtractor() {
        // NOP
    }

    /**