assertEquals("application/pdf", mimeMap.getMimeType("pdf"));
            assertEquals("application/msword", mimeMap.getMimeType("doc"));
            assertEquals("application/vnd.ms-excel", mimeMap.getMimeType("xls"));
            assertEquals("text/html", mimeMap.getMimeType("html"));
            assertEquals("text/html", mimeMap.getMimeType("htm"));
            assertEquals("image/jpeg", mimeMap.getMimeType("jpg"));

            final Set<RequestData> requestDataSet = new LinkedHashSet<>();
            for (final Sitemap sitemap : sitemapSet.getSitemaps()) {
                if (sitemap != null) {
                    requestDataSet.add(RequestDataBuilder.newRequestData().get().url(sitemap.getLoc()).build()); // TODO priority
                }
            }

package org.codelibs.fess.crawler.entity;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a Sitemap file entry, conforming to the Sitemap XML format.
 * This class holds information about a single Sitemap, including its location and last modification timestamp.
 * It implements the {@link Sitemap} interface.
 *
 * <p>
 * A Sitemap file provides search engines with a list of URLs available for crawling.

			<component class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>"http[s]?:.*sitemap[^/]*\.xml.*|http[s]?:.*sitemap[^/]*\.gz.*|http[s]?:.*sitemap[^/]*\.txt.*"</arg>
		</postConstruct>
	</component>

	<component name="webHtmlRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule" >
		<property name="ruleId">"webHtmlRule"</property>

     *
     * @param in Input stream for a sitemap
     * @return a sitemap set
     */
    public SitemapSet parse(final InputStream in) {
        return parse(in, true);
    }

    /**
     * Parses a sitemap from the given input stream.
     * @param in the input stream to parse
     * @param recursive whether to recursively parse compressed files
     * @return the parsed sitemap set
     */

 * 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 {
    /**

import java.io.ByteArrayInputStream;
import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.Sitemap;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.entity.SitemapUrl;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.dbflute.utflute.core.PlainTestCase;

      throws Exception {
    File fileA = newFile("file-a");
    File dir1 = newDir("dir-1");
    newFile("dir-1/file-b");
    newFile("dir-1/dir-2");

    assertThat(Iterables.limit(Files.fileTraverser().breadthFirst(rootDir), 3))
        .containsExactly(rootDir, fileA, dir1);
  }

  public void testFileTraverser_multipleDirectoryLayers_traversalReturnsAll() throws Exception {
    File fileA = newFile("file-a");

Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

User-agent: Crawler/2.0
Disallow: /ccc

User-agent: Hoge Crawler
Disallow: /ddd

sitemap: http://www.example.com/sitmap.xml

    /**
     * Adds sitemaps to the thread-local storage.
     * @param sitemaps An array of sitemap URLs.
     */
    public void addSitemaps(final String[] sitemaps) {
        sitemapsLocal.set(sitemaps);
    }

    /**
     * Removes sitemaps from the thread-local storage and returns them.
     * @return An array of sitemap URLs, or null if none were present.
     */
    public String[] removeSitemaps() {