* governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

import java.io.Serializable;

/**
 * @author shinsuke
 *
 */
public interface Sitemap extends Serializable {

    String getLoc();

    String getLastmod();

<?xml version="1.0" encoding="UTF-8"?>
<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <sitemap>
      <loc>http://www.example.com/sitemap1.xml.gz</loc>
      <lastmod>2004-10-01T18:23:17+00:00</lastmod>
   </sitemap>
   <sitemap>
      <loc>http://www.example.com/sitemap2.xml.gz</loc>
      <lastmod>2005-01-01</lastmod>
   </sitemap>

        responseData.setResponseBody(file, false);
        return responseData;
    }

    private ResponseData getTestData3_OK() {
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("http://example.com/sitemap.txt");
        File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.txt");
        responseData.setResponseBody(file, false);
        return responseData;
    }

        assertEquals("http://www.example.com/sitemap2.xml.gz", sitemaps[1].getLoc());

    }

    public void test_parseXmlSitemapsIndexGz() {
        final InputStream in = ResourceUtil.getResourceAsStream("sitemaps/sitemap2.xml.gz");
        final SitemapSet sitemapSet = sitemapsHelper.parse(in);
        final Sitemap[] sitemaps = sitemapSet.getSitemaps();
        assertEquals(2, sitemaps.length);

 * @author shinsuke
 *
 */
public class SitemapFile implements Sitemap {

    private static final long serialVersionUID = 1L;

    /**
     * Identifies the location of the Sitemap. This location can be a Sitemap,
     * an Atom file, RSS file or a simple text file.
     */
    private String loc;

    /**
     * Identifies the time that the corresponding Sitemap file was modified. It

    public static final String INDEX = "Index";

    private final List<Sitemap> sitemapList = new ArrayList<>();

    private String type = URLSET;

    public void addSitemap(final Sitemap sitemap) {
        sitemapList.add(sitemap);
    }

    public void removeSitemap(final Sitemap sitemap) {
        sitemapList.remove(sitemap);
    }

    public Sitemap[] getSitemaps() {

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

			<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>

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

<?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>