}return h<b.length&&g.push({elem:this,handlers:b.slice(h)}),g},props:"altKey bubbles cancelable ctrlKey currentTarget eventPhase metaKey relatedTarget shiftKey target timeStamp view which".split(" "),fixHooks:{},keyHooks:{props:"char charCode key keyCode".split(" "),filter:function(a,b){return null==a.which&&(a.which=null!=b.charCode?b.charCode:b.keyCode),a}},mouseHooks:{props:"button buttons clientX clientY offsetX offsetY pageX pageY screenX screenY toElement".split(" "),filter:function(a,b){var...

    /**
     * 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;

    /**

            this.spaceChars = spaceChars;
            return this;
        }
    }

    /**
     * Normalizes the text from the given Reader.
     *
     * @param reader the Reader from which to read the text to be normalized
     * @return a TextNormalizeContext containing the normalized text
     */
    public static TextNormalizeContext normalizeText(final Reader reader) {

     * @param prefix The prefix string to be used in generating the file's name.
     * @param suffix The suffix string to be used in generating the file's name.
     * @param directory The directory in which the file is to be created, or null if the default temporary-file directory is to be used.
     * @return The created temporary file.
     */

     * values range from 0.0 to 1.0. This value does not affect how your pages
     * are compared to pages on other sites—it only lets the search engines know
     * which pages you deem most important for the crawlers.
     *
     * The default priority of a page is 0.5.
     *
     * Please note that the priority you assign to a page is not likely to

    }

    /**
     * Returns the most specific directive matching the given user agent.
     * The method finds the longest matching user agent pattern in the directives,
     * excluding the general "*" pattern which matches all bots.
     *
     * @param userAgent the user agent string to match against directives,
     *                 can be null (treated as empty string)

 * to ensure visibility of changes across threads.
 *
 * <p>The class also provides methods to manage URL patterns for inclusion and exclusion, which
 * are stored as {@code Pattern} objects.
 */
public class MemoryDataHelper {
    /** Map of session IDs to URL queues for managing crawling queues. */

 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.
 * The default value for {@code targetNodePath} is "//HTML/BODY | //@alt | //@title", which selects the body of the HTML document,
 * as well as the alt and title attributes.
 * </p>
 * <p>
 * The class uses {@link DOMParser} to parse HTML documents and {@link XPathAPI} to execute XPath queries.

    /**
     * Service for managing access result data.
     */
    @Resource
    protected DataService<AccessResult<?>> dataService;

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource
    protected UrlFilter urlFilter;

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

     * The charset name for the output.
     */
    protected String charsetName = Constants.UTF_8;

    /**
     * Class type to be returned by the {@link #getData(AccessResultData)} method. Defaults to null, which returns XML content
     * as a String.
     */
    protected Class<?> dataClass = null;

    @Override
    protected void storeData(final ResponseData responseData, final ResultData resultData) {