// Test handling of duplicate URLs in sitemap
        ResponseData responseData = new ResponseData();
        byte[] content = "<sitemap></sitemap>".getBytes();
        responseData.setResponseBody(content);

        SitemapUrl sitemap1 = new SitemapUrl();
        sitemap1.setLoc("https://example.com/duplicate");

        SitemapUrl sitemap2 = new SitemapUrl();
        sitemap2.setLoc("https://example.com/duplicate");

                        + "  </sitemap>\n" + "  <sitemap>\n" + "    <lastmod>2025-01-02</lastmod>\n" + "  </sitemap>\n" + "  <sitemap>\n"
                        + "    <loc>http://www.example.com/sitemap2.xml</loc>\n" + "  </sitemap>\n" + "</sitemapindex>";
        final InputStream in = new ByteArrayInputStream(xml.getBytes());
        final SitemapSet sitemapSet = sitemapsHelper.parse(in);
        final Sitemap[] sitemaps = sitemapSet.getSitemaps();

        robotsTxt.addSitemap("https://example.com/sitemap.xml");
        robotsTxt.addSitemap("https://example.com/sitemap2.xml");

        String[] sitemaps = robotsTxt.getSitemaps();
        assertEquals(2, sitemaps.length);
        assertEquals("https://example.com/sitemap.xml", sitemaps[0]);
        assertEquals("https://example.com/sitemap2.xml", sitemaps[1]);
    }

    public void test_addSitemapNoDuplicates() {

/**
 * Helper class for parsing and validating sitemaps.
 * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
 * and can handle GZIP compressed sitemaps.
 * The class provides methods to check if an input stream is a valid sitemap,
 * and to parse an input stream into a {@link SitemapSet} object.
 * It uses SAX parser for XML sitemaps and XML sitemap indexes,
 * and handles potential exceptions during parsing.

    }

    /**
     * Test sitemaps add and remove operations
     */
    public void test_sitemaps() {
        // Initial state
        assertNull(crawlerContext.removeSitemaps());

        // Add sitemaps
        String[] sitemaps = new String[] { "http://example.com/sitemap.xml", "http://test.com/sitemap.xml" };
        crawlerContext.addSitemaps(sitemaps);

        // Remove and verify

    }

    /**
     * Adds a sitemap URL to the list of sitemaps.
     *
     * @param url The URL of the sitemap to be added
     */
    public void addSitemap(final String url) {
        if (!sitemapList.contains(url)) {
            sitemapList.add(url);
        }
    }

    /**
     * Returns an array of sitemap URLs.
     *
     * @return an array of sitemap URLs
     */

    protected static final Pattern CRAWL_DELAY_RECORD = Pattern.compile("^crawl-delay:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for Sitemap record.
     */
    protected static final Pattern SITEMAP_RECORD = Pattern.compile("^sitemap:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Whether robots.txt processing is enabled. */
    protected boolean enabled = true;

    /**

    controller.setDefaultIntervalTime(1000);
});
```

### Sitemap Support

```java
// Enable sitemap processing
container.singleton("sitemapsRule", SitemapsRule.class, rule -> {
    rule.addRule("url", ".*sitemap.*");
});

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

## Data Access and Storage

### Accessing Crawled Data

```java

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

        assertFalse(robotsTxt.allows("/ddd", "Hoge Crawler"));

        String[] sitemaps = robotsTxt.getSitemaps();
        assertEquals(2, sitemaps.length);
        assertEquals("http://www.example.com/sitmap.xml", sitemaps[0]);
        assertEquals("http://www.example.net/sitmap.xml", sitemaps[1]);

    }

    public void testParse_disable() {