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

    /** Map of parser features. */
    protected Map<String, String> featureMap = new HashMap<>();

    /** Map of parser properties. */
    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression for extracting content from the document body. */
    protected String contentXpath = "//BODY";

    }

    /** The suggest settings. */
    protected SuggestSettings settings;
    /** The suggest settings builder. */
    protected SuggestSettingsBuilder settingsBuilder;
    /** The reading converter. */
    protected ReadingConverter readingConverter;
    /** The contents reading converter. */
    protected ReadingConverter contentsReadingConverter;
    /** The normalizer. */
    protected Normalizer normalizer;
    /** The analyzer. */

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */
    protected static final ByteOrderMark BOM_UTF_7 = new ByteOrderMark("UTF-7", 0x2B, 0x2F, 0x76);

    /**
     * HTML4 unescape translator.
     */

    protected IDTYPE id;

    /** The session ID associated with the access result. */
    protected String sessionId;

    /** The rule ID that matched the accessed resource. */
    protected String ruleId;

    /** The URL of the accessed resource. */
    protected String url;

    /** The parent URL of the accessed resource. */
    protected String parentUrl;

    /** User agent string */
    protected String userAgent = "Crawler";

    /** HTTP client context for requests */
    protected HttpClientContext httpClientContext = HttpClientContext.create();

    /** Proxy host name */
    protected String proxyHost;

    /** Proxy port number */
    protected Integer proxyPort;

    /** Proxy authentication scheme */
    protected AuthScheme proxyAuthScheme = new BasicScheme();

    protected boolean includeAware;

    /**
     * A map of attributes.
     */
    protected final Map<String, Object> attributeMap = new HashMap<>();

    /**
     * A map of features.
     */
    protected final Map<String, String> featureMap = new HashMap<>();

    /**
     * A map of field rules.
     */
    protected Map<String, String> fieldRuleMap = new LinkedHashMap<>();

     * Field name for ID.
     */
    protected static final String ID = "id";

    /**
     * Field name for session ID.
     */
    protected static final String SESSION_ID = "sessionId";

    /**
     * Field name for URL.
     */
    protected static final String URL = "url";

    /**
     * Field name for last modified timestamp.
     */
    protected static final String LAST_MODIFIED = "lastModified";

    /** The index name. */
    protected final String index;

    /** The time taken in milliseconds. */
    protected final long tookMs;

    /** The list of suggested words. */
    protected final List<String> words;

    /** The number of suggested words. */
    protected final int num;

    /** The total number of hits. */
    protected final long total;

    /** The list of suggested items. */

    protected Map<String, String> propertyMap = new HashMap<>();

    /** XPath expression to select target nodes for text extraction. */
    protected String targetNodePath = "//HTML/BODY | //@alt | //@title";

    /** Cache for XPathAPI instances to improve performance. */
    protected LoadingCache<String, XPathAPI> xpathAPICache;

    /** Cache duration in minutes for XPathAPI instances. */
    protected long cacheDuration = 10; // min

     */
    @Resource
    protected UrlQueueService<UrlQueue<?>> urlQueueService;

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

    /**
     * Container for managing crawler components.
     */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /**