robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');
            buf.append("<url>").append('\n');

    }

    /**
     * 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

        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() {

 * and processing of Sitemap data.
 * </p>
 *
 * <p>
 * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
 * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers
 * to incrementally fetch sitemaps that have been updated since a certain date.
 * </p>
 *
 * <p>

 * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
 * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
 * If any exception occurs during the sitemap validation, it logs the error and returns false.
 *
 */
public class SitemapsRule extends RegexRule {
    /**

<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
      <loc>http://www.example.com/</loc>
      <lastmod>2005-01-01</lastmod>
      <changefreq>monthly</changefreq>
      <priority>0.8</priority>
   </url>
   <url>
      <loc>http://www.example.com/catalog?item=12&amp;desc=vacation_hawaii</loc>
      <changefreq>weekly</changefreq>
   </url>
   <url>

    }

    /**
     * Adds sitemaps from robots.txt to the crawling queue.
     * @param urlQueue The URL queue to add sitemaps to.
     */
    protected void addSitemapsFromRobotsTxt(final UrlQueue<?> urlQueue) {
        final String[] sitemaps = crawlerContext.removeSitemaps();
        if (sitemaps != null) {
            for (final String childUrl : sitemaps) {
                try {

	<include path="crawler/extractor.xml"/>
	<include path="crawler/mimetype.xml"/>
	<include path="crawler/encoding.xml"/>
	<include path="crawler/urlconverter.xml"/>
	<include path="crawler/log.xml"/>
	<include path="crawler/sitemaps.xml"/>

	<!-- Crawler -->
	<component name="crawler" class="org.codelibs.fess.crawler.Crawler" instance="prototype" >
	</component>

	<!-- Crawler Thread -->

    }

    /**
     * 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
     */

    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>
    <include path="crawler/sitemaps.xml"/>

    <include path="crawler/opensearch.xml"/>

	<!-- Crawler -->
	<component name="crawler" class="org.codelibs.fess.crawler.Crawler" instance="prototype" >
	</component>

	<!-- Crawler Thread -->