}

        propertyMap.put(key, value);
    }

    /**
     * Gets the map of parser features.
     *
     * @return the feature map
     */
    public Map<String, String> getFeatureMap() {
        return featureMap;
    }

    /**
     * Sets the map of parser features.
     *
     * @param featureMap the feature map to set
     */

 * </ol>
 * <p>
 * The class also provides methods for configuring features and properties of the
 * underlying DOM parser, as well as defining rules for extracting child URLs
 * from specific HTML tags and attributes.
 * </p>
 *
 * <p>
 * <b>Configuration:</b>
 * </p>
 * <ul>
 *   <li><b>featureMap:</b> A map of features to be set on the DOM parser.</li>

        {
            xpathTransformer = new XpathTransformer();
            xpathTransformer.setName("xpathTransformer");
            Map<String, String> featureMap = newHashMap();
            featureMap.put("http://xml.org/sax/features/namespaces", "false");
            xpathTransformer.setFeatureMap(featureMap);
            Map<String, String> propertyMap = newHashMap();
            xpathTransformer.setPropertyMap(propertyMap);

### Key Features

- **Multi-Protocol Support**: HTTP/HTTPS, File System, FTP, SMB/CIFS, Cloud Storage (MinIO, S3)
- **Comprehensive Content Extraction**: Office documents, PDFs, archives, images, audio/video files

 *
 * <p>The robots.txt protocol is implemented according to the standard specification,
 * 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>

 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:
 * <ul>
 *   <li>Text extraction from PDF pages</li>
 *   <li>Embedded document extraction</li>
 *   <li>Annotation extraction (file attachments)</li>
 *   <li>Metadata extraction</li>

        super.setUp();
        htmlTransformer = new HtmlTransformer();
        htmlTransformer.setName("htmlTransformer");
        Map<String, String> featureMap = newHashMap();
        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        htmlTransformer.setFeatureMap(featureMap);
        Map<String, String> propertyMap = newHashMap();
        htmlTransformer.setPropertyMap(propertyMap);

    @Override
    protected void setUp() throws Exception {
        super.setUp();

        final Map<String, String> featureMap = newHashMap();
        featureMap.put("http://xml.org/sax/features/namespaces", "false");
        final Map<String, String> propertyMap = newHashMap();
        final Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");

 *   <li>readTimeout - Read timeout in milliseconds (default: 10000)</li>
 * </ul>
 *
 * <p>The client supports URLs in the format: {@code storage://bucket-name/object-path}
 *
 * <p>Features:
 * <ul>
 *   <li>Automatic initialization of MinIO client</li>
 *   <li>Support for HEAD and GET operations</li>
 *   <li>Content length validation</li>
 *   <li>MIME type detection</li>

     */
    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<>();