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;

    @Override

        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();

import org.codelibs.fess.crawler.util.CrawlerWebServer;
import org.dbflute.utflute.core.PlainTestCase;

public class CrawlerTest extends PlainTestCase {

    public Crawler crawler;

    public DataService dataService;

    public UrlQueueService urlQueueService;

    public FileTransformer fileTransformer;

    private StandardCrawlerContainer container;

    @Override
    protected void setUp() throws Exception {

    public void test_dataService_setAndGet() {
        // Initially should be null
        assertNull(CrawlingParameterUtil.getDataService());

        // Create a mock DataService
        DataService<AccessResult<?>> service = new DataService<AccessResult<?>>() {
            @Override
            public void store(AccessResult<?> accessResult) {
            }

            @Override

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());

     * 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;

    /**

context.setMaxDepth(3);           // Max depth (-1 = unlimited)
context.setNumOfThread(10);       // Concurrent threads
```

### Accessing Results

```java
DataService ds = container.getComponent("dataService");

// Count
int count = ds.getCount(sessionId);

// Get by URL
AccessResult result = ds.getAccessResult(sessionId, url);

// Iterate all
ds.iterate(sessionId, accessResult -> {

    private CrawlerThread crawlerThread;
    private CrawlerContext crawlerContext;
    private UrlQueueService<UrlQueue<?>> urlQueueService;
    private DataService dataService;
    private CrawlerContainer crawlerContainer;
    private LogHelper logHelper;
    private CrawlerClientFactory clientFactory;
    private UrlFilter urlFilter;
    private RuleManager ruleManager;

    @Override
    @SuppressWarnings("unchecked")

    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.
     */