CrawlingParameterUtil.setUrlQueue(urlQueue);

        // Verify it can be retrieved
        UrlQueue<?> retrieved = CrawlingParameterUtil.getUrlQueue();
        assertNotNull(retrieved);
        assertEquals("test-session", retrieved.getSessionId());
        assertEquals("http://example.com", retrieved.getUrl());
    }

    public void test_urlQueue_setNull() {
        // Set a UrlQueue first

        Directive retrieved = robotsTxt.getDirective("OtherBot");
        assertNull(retrieved);
    }

    public void test_getDirectiveWithNull() {
        // Test getDirective with null user agent
        RobotsTxt robotsTxt = new RobotsTxt();

        Directive retrieved = robotsTxt.getDirective(null);
        assertNull(retrieved);
    }

        String[] retrieved = data.getValues("empty");
        assertNotNull(retrieved);
        assertEquals(0, retrieved.length);
    }

    public void test_nullValues() {
        // Test with null values
        ExtractData data = new ExtractData();

        data.putValue("key", null);

        String[] retrieved = data.getValues("key");
        assertNotNull(retrieved);

 *   <li>{@code done} - Flag indicating whether the file has been retrieved.</li>
 * </ul>
 *
 * <p>Constructors:</p>
 * <ul>
 *   <li>{@code ContentOutputStream(int threshold, File tmpDir)} - Constructs a ContentOutputStream with a specified threshold and temporary directory.</li>
 * </ul>
 *
 * <p>Methods:</p>
 * <ul>
 *   <li>{@code getFile()} - Marks the file as retrieved and returns the file.</li>

                .setSize(0)
                .execute()
                .actionGet()
                .getHits()
                .getTotalHits()
                .value() > 0);

        // Verify pattern can be retrieved
        final List<Pattern> patterns = urlFilterService.getIncludeUrlPatternList(sessionId);
        assertEquals(1, patterns.size());
        assertTrue(patterns.get(0).matcher("http://example.com/page1").matches());

 * without processing the actual file content. The input stream is validated but not
 * read - only the filename from the parameters is used as the extracted content.</p>
 *
 * <p>The filename is retrieved from the {@link ExtractData#RESOURCE_NAME_KEY} parameter.
 * If this parameter is not present, an empty string is returned as the content.</p>
 */
public class FilenameExtractor extends AbstractExtractor {

    /**

    /**
     * The container that provides crawler components.
     */
    protected CrawlerContainer crawlerContainer;

    /**
     * The name of the component to be retrieved from the CrawlerContainer.
     */
    protected String componentName;

    /**
     * The listener that is called when a pooled object is destroyed.
     */
    protected OnDestroyListener<T> onDestroyListener;

     * When enabled, users can save favorite search results.
     */
    @Size(max = 10)
    public String userFavorite;

    /**
     * Enable or disable JSON Web API.
     * When enabled, search results can be retrieved via JSON API.
     */
    @Size(max = 10)
    public String webApiJson;

    /**
     * Application-specific value for custom configurations.
     * This field can be used to store custom application settings.

    }

    /**
     * Retrieves a single document from the OpenSearch index by session ID and URL.
     *
     * @param <T> The type of the object to retrieve.
     * @param clazz The class of the object to retrieve.
     * @param sessionId The session ID of the document.
     * @param url The URL of the document.
     * @return The retrieved object, or null if not found.

    /**
     * Processes an FTP request to retrieve data from the specified URI.
     * This method handles the complete FTP request lifecycle including timeout management,
     * connection setup, and data retrieval.
     *
     * @param uri The URI to retrieve data from
     * @param includeContent Whether to include the actual content in the response
     * @return The response data containing the retrieved information