}

    // Test run method with null DataService
    @Test
    public void test_run_nullDataService() {
        indexUpdater.dataService = null;
        try {
            indexUpdater.run();
            fail("Should throw FessSystemException");
        } catch (FessSystemException e) {
            assertEquals("DataService is null. IndexUpdater cannot proceed without a DataService instance.", e.getMessage());
        }
    }

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

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

    /**
     * Filter for URLs to control which URLs are crawled.
     */
    @Resource
    protected UrlFilter urlFilter;

    /**
     * Manager for crawling rules and configurations.

import jakarta.annotation.Resource;

public class CrawlerTest extends LastaDiTestCase {

    @Resource
    private Crawler crawler;

    @Resource
    private DataService dataService;

    @Resource
    private UrlQueueService urlQueueService;

    @Resource
    private FileTransformer fileTransformer;

    @Resource
    private CrawlerContainer crawlerContainer;

     * if too many empty results are encountered or if a system shutdown is requested.
     */
    @Override
    public void run() {
        if (dataService == null) {
            throw new FessSystemException("DataService is null. IndexUpdater cannot proceed without a DataService instance.");
        }

        if (logger.isDebugEnabled()) {
            logger.debug("Starting indexUpdater.");
        }

     */
    @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;

    /**

crawler.addUrl("https://example.com/sitemap.xml");
```

## Data Access and Storage

### Accessing Crawled Data

```java
// Get data service
DataService dataService = container.getComponent("dataService");

// Iterate through crawled data
dataService.iterate(sessionId, accessResult -> {
    System.out.println("URL: " + accessResult.getUrl());
    System.out.println("Status: " + accessResult.getHttpStatusCode());

import org.opensearch.search.SearchHits;

import jakarta.annotation.PostConstruct;

/**
 * OpenSearchDataService is an implementation of {@link DataService} for OpenSearch.
 */
public class OpenSearchDataService extends AbstractCrawlerService implements DataService<OpenSearchAccessResult> {

    /**
     * Fields to fetch for access result list without data.
     */

        dataService.delete("id1");

        assertNull(dataService.getAccessResult("id1", "http://www.id1.com/"));
        assertNotNull(dataService.getAccessResult("id2", "http://www.id2.com/"));

        dataService.store(accessResult1);
        assertNotNull(dataService.getAccessResult("id1", "http://www.id1.com/"));

        dataService.deleteAll();

    private static final Logger logger = LogManager.getLogger(OpenSearchUrlQueueService.class);

    /**
     * Data service for checking access results.
     */
    @Resource
    protected OpenSearchDataService dataService;

    /**
     * Cache for session queues.
     */
    protected Map<String, QueueHolder> sessionCache = new ConcurrentHashMap<>();

    /**
     * The number of URLs to fetch when polling.
     */

        final OpenSearchUrlQueueService urlQueueService = ComponentUtil.getComponent(OpenSearchUrlQueueService.class);
        final OpenSearchDataService dataService = ComponentUtil.getComponent(OpenSearchDataService.class);

        try {
            // clear url filter
            urlFilterService.delete(sid);
        } catch (final Exception e) {