mhtml - Code Search

fess-crawler/src/main/resources/org/codelibs/fess/crawler/mime/tika-mimetypes.xml

  <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"/>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Mar 13 08:18:01 UTC 2025

- 320.1K bytes

- Viewed (2)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/impl/MimeTypeHelperImplTest.java

        assertContentType("text/plain", null, "hoge.txt");
        assertContentType("text/html", "html/test1.html", "hoge.html");
        assertContentType("text/html", "html/test1.html", "hoge.htm");
        assertContentType("text/html", "html/test1.shtml", "hoge.shtml");

        assertContentType("application/msword", "test/text1.txt", "hoge.doc");

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 11.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformer.java

    /**
     * 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;

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 28.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/client/ftp/FtpAuthenticationTest.java

        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

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 3.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/HtmlTransformerTest.java

        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));

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 13.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/TextTransformerTest.java

        final byte[] data = new String("<html><body>xyz</body></html>").getBytes();
        final ResponseData responseData = new ResponseData();
        responseData.setUrl("file:/test.html");
        responseData.setCharSet(Constants.UTF_8);
        responseData.setResponseBody(data);
        responseData.setMimeType("text/html");
        final ResultData resultData = textTransformer.transform(responseData);

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 4.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/UrlConvertHelperTest.java

        String url;

        url = "http://hoge.com/http/fuga.html";
        assertEquals("http://hoge.com/http/fuga.html", urlConvertHelper.convert(url));

        url = "tp://hoge.com/http/fuga.html";
        assertEquals("tp://hoge.com/http/fuga.html", urlConvertHelper.convert(url));

        urlConvertHelper.add("^tp:", "http:");

        url = "http://hoge.com/http/fuga.html";

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 2.4K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            assertTrue(robotsTxt.allows("/private/index.html", userAgent));
            assertTrue(robotsTxt.allows("/help/", userAgent));
            assertTrue(robotsTxt.allows("/help.html", userAgent));
            assertTrue(robotsTxt.allows("/help/faq.html", userAgent));
            assertTrue(robotsTxt.allows("/foo/bar/", userAgent));
            assertTrue(robotsTxt.allows("/foo/bar/index.html", userAgent));

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 5.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

            buf.append("<url>").append('\n');
            buf.append("<loc>http://localhost:7070/index.html</loc>").append('\n');
            buf.append("<loc>http://localhost:7070/file").append(count).append("-1.html").append("</loc>").append('\n');
            buf.append("</url>").append('\n');
            buf.append("</urlset>").append('\n');

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 6.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

        final File indexFile = new File(dir, "index.html");
        indexFile.deleteOnExit();
        FileUtil.writeBytes(indexFile.getAbsolutePath(), content.getBytes("UTF-8"));

        for (int i = 1; i <= 10; i++) {
            final File file = new File(dir, "file" + count + "-" + i + ".html");
            file.deleteOnExit();

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 5K bytes

- Viewed (0)

Search Options