/**
         * Gets the parsed sitemap set.
         * @return the sitemap set
         */
        public SitemapSet getSitemapSet() {
            return sitemapSet;
        }

    }

    /**
     * Parses an XML sitemap index from the given input stream.
     * @param in the input stream to parse
     * @return the parsed sitemap set
     */

     * Processes allowed SIDs (Security Identifiers) and adds them to the SID set.
     * If the SID is a group, it recursively processes all group members.
     *
     * @param file the SMB1 file
     * @param sid the SID to process
     * @param sidSet the set of SIDs to add to
     */
    protected void processAllowedSIDs(final SmbFile file, final SID sid, final Set<SID> sidSet) {
        if (logger.isDebugEnabled()) {

 *
 * ESSourceReader reader = new ESSourceReader(client, settings, indexName);
 * reader.setScrollSize(1000); // Set the scroll size
 * reader.setLimitOfDocumentSize(1024 * 1024); // Limit document size to 1MB
 * reader.setQuery(QueryBuilders.termQuery("field", "value")); // Set a query
 *
 * Map<String, Object> document;
 * while ((document = reader.read()) != null) {
 *     // Process the document

        if (StringUtil.isNotEmpty(resourceName)) {
            metadata.set(ExtractData.RESOURCE_NAME_KEY, resourceName);
        }
        if (StringUtil.isNotBlank(contentType)) {
            metadata.set(ExtractData.CONTENT_TYPE, contentType);
        }
        if (StringUtil.isNotBlank(contentEncoding)) {
            metadata.set(ExtractData.CONTENT_ENCODING, contentEncoding);
        }
        if (pdfPassword != null) {

     */
    public Map<String, String> getFieldRuleMap() {
        return fieldRuleMap;
    }

    /**
     * Sets the fieldRuleMap.
     *
     * @param fieldRuleMap the fieldRuleMap to set
     */
    public void setFieldRuleMap(final Map<String, String> fieldRuleMap) {
        this.fieldRuleMap = fieldRuleMap;
    }

    /**
     * Returns the trimSpace.
     *

    }

    /**
     * Gets the character set of the response.
     *
     * @return the character set, or null if not specified
     */
    public String getCharSet() {
        return charSet;
    }

    /**
     * Sets the character set of the response.
     *
     * @param charSet the character set to set
     */
    public void setCharSet(final String charSet) {

        // Initial state
        assertNull(testRule.getRuleId());

        // Set rule ID
        testRule.setRuleId("testRule1");
        assertEquals("testRule1", testRule.getRuleId());

        // Change rule ID
        testRule.setRuleId("changedRule");
        assertEquals("changedRule", testRule.getRuleId());

        // Set null rule ID
        testRule.setRuleId(null);
        assertNull(testRule.getRuleId());

     */
    public HtmlXpathExtractor() {
        super();
    }

    /**
     * Initializes the XPathAPI cache with a specified cache duration.
     * This method is called to set up the cache for XPathAPI instances.
     */
    @Resource
    public void init() {
        xpathAPICache =

     * @param objs the log objects (should contain UrlQueue and Set of RequestData)
     */
    protected void processProcessChildUrlsByException(final Object... objs) {
        // CrawlerContext crawlerContext = (CrawlerContext) objs[0];
        final UrlQueue<?> urlQueue = (UrlQueue<?>) objs[1];
        @SuppressWarnings("unchecked")
        final Set<RequestData> requestDataSet = (Set<RequestData>) objs[2];
        if (logger.isDebugEnabled()) {

     *
     * @param maxDuplicatedPath the maximum duplicated path count to set
     */
    public void setMaxDuplicatedPath(final int maxDuplicatedPath) {
        this.maxDuplicatedPath = maxDuplicatedPath;
    }

    /**
     * Gets the character set name used for encoding file paths.
     *
     * @return the character set name
     */
    public String getCharsetName() {
        return charsetName;