/**
 * Represents a set of Sitemaps, which can be either a UrlSet or an Index.
 * This class provides methods to manage a list of Sitemap objects and determine the type of the SitemapSet.
 *
 */
public class SitemapSet implements Serializable {

    private static final long serialVersionUID = 1L;

    /** Constant for UrlSet type. */
    public static final String URLSET = "UrlSet";

    /** Constant for Index type. */

                + "<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">\n" + "  <url>\n" + "    <lastmod>2025-01-01</lastmod>\n"
                + "    <changefreq>daily</changefreq>\n" + "    <priority>0.8</priority>\n" + "  </url>\n" + "  <url>\n"
                + "    <loc>http://www.example.com/valid.html</loc>\n" + "    <lastmod>2025-01-02</lastmod>\n" + "  </url>\n" + "</urlset>";

            fail();
        } catch (final ChildUrlsException e) {
            final Set<RequestData> urlSet = e.getChildUrlList();
            assertEquals(1, urlSet.size());
            for (final RequestData requestData : urlSet.toArray(new RequestData[urlSet.size()])) {
                String url = requestData.getUrl();
                assertTrue(url.contains("dir1/test3.txt"));
            }

     */
    public void test_robotsTxtUrlSet() {
        Set<String> urlSet = crawlerContext.getRobotsTxtUrlSet();
        assertNotNull(urlSet);
        assertTrue(urlSet instanceof LruHashSet);
        assertTrue(urlSet.isEmpty());

        // Add URLs to default set
        urlSet.add("http://example.com/robots.txt");
        urlSet.add("http://test.com/robots.txt");

        try {
            fsClient.doGet("file://" + path);
            fail();
        } catch (final ChildUrlsException e) {
            final Set<RequestData> urlSet = e.getChildUrlList();
            for (final RequestData requestData : urlSet.toArray(new RequestData[urlSet.size()])) {
                String url = requestData.getUrl();
                if (url.indexOf(".svn") < 0) {

            final int depth, final String encoding) {
        // add url and filter
        final Set<String> urlSet = new HashSet<>();
        final List<UrlQueue<?>> childList = childUrlList.stream()
                .filter(d -> StringUtil.isNotBlank(d.getUrl()) && urlSet.add(d.getUrl()) && crawlerContext.getUrlFilter().match(d.getUrl()))
                .map(d -> {

            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');
            buf.append("<loc>http://localhost:7070/index.html</loc>").append('\n');

            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');
            buf.append("<loc>http://localhost:7070/index.html</loc>").append('\n');

        try {
            if (bis.read(bytes) == -1) {
                return false;
            }

            final String preloadDate = new String(bytes, Constants.UTF_8);
            if (preloadDate.indexOf("<urlset") >= 0 || preloadDate.indexOf("<sitemapindex") >= 0 || preloadDate.startsWith("http://")
                    || preloadDate.startsWith("https://")) {
                // XML Sitemaps
                return true;
            }

        }
        final Set<RequestData> urlSet = new HashSet<>(docList.size());
        for (final Map<String, Object> doc : docList) {
            final String url = DocumentUtil.getValue(doc, fessConfig.getIndexFieldUrl(), String.class);
            if (StringUtil.isNotBlank(url)) {
                urlSet.add(RequestDataBuilder.newRequestData().get().url(url).build());
            }
        }