urlFilter.init(sessionId);

        // Add conflicting patterns
        urlFilter.addInclude("https://example.com/.*");
        urlFilter.addExclude("https://example.com/.*");

        // Exclude should take precedence
        assertFalse(urlFilter.match("https://example.com/page"));
    }

    /**
     * Test URL normalization scenarios
     */
    public void test_urlNormalization() {

        assertEquals(150L, merged.getQueryFreq()); // Sum of frequencies
        assertEquals(75L, merged.getDocFreq()); // Sum of frequencies
        assertEquals(1.5f, merged.getUserBoost(), 0.001f); // Takes item2's boost

        // Check merged arrays contain both items' values
        assertTrue(merged.getTags().length >= 2);
        assertTrue(merged.getRoles().length >= 2);

     *
     * @param client the OpenSearch client used to clear the scroll context
     * @param scrollId the ID of the scroll context to be deleted; if null, no action is taken
     */
    public static void deleteScrollContext(final Client client, final String scrollId) {
        if (scrollId != null) {

 * </p>
 *
 * <p>
 * The class uses a cache for XPathAPI objects to improve performance. The cache duration is configurable.
 * </p>
 *
 * <p>
 * The transform method takes a ResponseData object containing the XML content and returns a ResultData object with the extracted and formatted data.
 * </p>
 *
 * <p>

 *       invalid URLs.</li>
 * </ul>
 *
 * <p>
 * <b>Usage:</b>
 * </p>
 * <p>
 * The {@code transform} method is the main entry point for transforming an HTML
 * response. It takes a {@link ResponseData} object as input and returns a
 * {@link ResultData} object containing the extracted data and child URLs.
 * </p>
 */
public class HtmlTransformer extends AbstractTransformer {