* and handles potential exceptions during parsing.
 * The class also includes inner classes for handling XML sitemap and sitemap index parsing.
 */
public class SitemapsHelper {
    private static final Logger logger = LogManager.getLogger(SitemapsHelper.class);

    /** The size of the preload buffer for checking file format. */
    protected int preloadSize = 512;

    /** Enable validation of sitemap entries. */

        SitemapSet sitemapSet = new SitemapSet();
        sitemapSet.addSitemap(sitemap);

        when(crawlerContainer.getComponent("sitemapsHelper")).thenReturn(sitemapsHelper);
        try {
            when(sitemapsHelper.parse(any(InputStream.class))).thenReturn(sitemapSet);
        } catch (Exception e) {
            fail("Should not throw exception in test setup");
        }

     */
    @Override
    public void process(final ResponseData responseData) {
        final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");
        try (final InputStream responseBody = responseData.getResponseBody()) {
            final SitemapSet sitemapSet = sitemapsHelper.parse(responseBody);
            final Set<RequestData> requestDataSet = new LinkedHashSet<>();

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("sitemapsHelper", SitemapsHelper.class)//
                .singleton("sitemapsRule", SitemapsRule.class);
        sitemapsRule = container.getComponent("sitemapsRule");
    }

    public void test_match() {
        assertMatchTrue(getTestData1_OK());

        assertFalse(sitemapsHelper.isValidPriority("-0.1"));
        assertFalse(sitemapsHelper.isValidPriority("1.1"));
        assertFalse(sitemapsHelper.isValidPriority("abc"));

        // Valid changefreq
        assertTrue(sitemapsHelper.isValidChangefreq("always"));
        assertTrue(sitemapsHelper.isValidChangefreq("hourly"));
        assertTrue(sitemapsHelper.isValidChangefreq("daily"));

        if (super.match(responseData)) {
            try (final InputStream is = responseData.getResponseBody()) {
                final SitemapsHelper sitemapsHelper = crawlerContainer.getComponent("sitemapsHelper");
                return sitemapsHelper.isValid(is);
            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {

    public RuleManager ruleManager;

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

        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("sitemapsHelper", SitemapsHelper.class)//
                .singleton("sitemapsRule", SitemapsRule.class)//
                .singleton("fileRule", RegexRule.class)//
                .singleton("ruleManager", RuleManagerImpl.class);

                .singleton("urlConvertHelper", UrlConvertHelper.class)
                .singleton("intervalController", DefaultIntervalController.class)
                .singleton("sitemapsHelper", SitemapsHelper.class)
                .singleton("logHelper", LogHelperImpl.class)
                .singleton("encodingHelper", EncodingHelper.class)
                .singleton("contentLengthHelper", ContentLengthHelper.class)

extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps
**SitemapsHelper**: Sitemap XML parsing, index handling
**MimeTypeHelper**: MIME detection via Tika
**EncodingHelper**: Charset detection with BOM
**UrlConvertHelper**: URL normalization

---

## Development Workflow