public static final MediaType XHTML_UTF_8 = createConstantUtf8(APPLICATION_TYPE, "xhtml+xml");

  /**
   * Extensible Resource Descriptors. This is not yet registered with the IANA, but it is specified
   * by OASIS in the <a href="http://docs.oasis-open.org/xri/xrd/v1.0/cd02/xrd-1.0-cd02.html">XRD
   * definition</a> and implemented in projects such as <a

  public static final MediaType XHTML_UTF_8 = createConstantUtf8(APPLICATION_TYPE, "xhtml+xml");

  /**
   * Extensible Resource Descriptors. This is not yet registered with the IANA, but it is specified
   * by OASIS in the <a href="http://docs.oasis-open.org/xri/xrd/v1.0/cd02/xrd-1.0-cd02.html">XRD
   * definition</a> and implemented in projects such as <a

                        + "    <loc>http://www.example.com/page.html</loc>\n"
                        + "    <xhtml:link rel=\"alternate\" hreflang=\"en\" href=\"http://www.example.com/en/page.html\" />\n"
                        + "    <xhtml:link rel=\"alternate\" hreflang=\"ja\" href=\"http://www.example.com/ja/page.html\" />\n"

    /**
     * Checks if the response data represents HTML content.
     *
     * @param responseData the response data to check
     * @return true if the content is HTML, false otherwise
     */
    protected boolean isHtml(final ResponseData responseData) {
        final String mimeType = responseData.getMimeType();
        if ("text/html".equals(mimeType) || "application/xhtml+xml".equals(mimeType)) {
            return true;

gc.ca

// cat : https://www.iana.org/domains/root/db/cat.html
cat

// cc : https://www.iana.org/domains/root/db/cc.html
cc

// cd : https://www.iana.org/domains/root/db/cd.html
// see also: https://www.nic.cd/domain/insertDomain_2.jsp?act=1
cd
gov.cd

// cf : https://www.iana.org/domains/root/db/cf.html
cf

// cg : https://www.iana.org/domains/root/db/cg.html
cg

  <mime-type type="text/html">
    <_comment>HyperText Markup Language</_comment>
    <acronym>HTML</acronym>
    <tika:uti>public.html</tika:uti>
     <!-- TIKA-327: if you encounter tags in the HTML
          with no declared namespace, it's not XHTML, it's just
          bad HTML, unfortunately.
     -->
    <root-XML localName="html"/>
    <root-XML localName="HTML"/>

- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

        assertEquals("http://hoge/index.html", htmlTransformer.normalizeUrl(url));

        url = "http://hoge/index.html;jsessionid=hoge?a=1";
        assertEquals("http://hoge/index.html?a=1", htmlTransformer.normalizeUrl(url));

        url = "http://hoge/index.html;jsessionid=hoge.fuga?a=1";
        assertEquals("http://hoge/index.html?a=1", htmlTransformer.normalizeUrl(url));

        assertTrue(auth.matches("ftp://otherhost:21/test/aaa.html"));

        // Test with IP address
        auth.setServer("192.168.1.1");
        assertTrue(auth.matches("ftp://192.168.1.1:21/test/aaa.html"));
        assertTrue(auth.matches("ftp://192.168.1.1/test/aaa.html"));
        assertFalse(auth.matches("ftp://hostname/test/aaa.html"));

        // Test with more complex paths

    HtmlNext path_Error_NotFoundJsp = new HtmlNext("/error/notFound.jsp");

    /** The path of the HTML: /error/redirect.jsp */
    HtmlNext path_Error_RedirectJsp = new HtmlNext("/error/redirect.jsp");

    /** The path of the HTML: /error/system.jsp */
    HtmlNext path_Error_SystemJsp = new HtmlNext("/error/system.jsp");

    /** The path of the HTML: /footer.jsp */