assertContentType("application/vnd.openxmlformats-officedocument.presentationml.presentation", "extractor/msoffice/test.pptx",
                "hoge.pptx");

        assertContentType("image/jpeg", null, "hoge.jpg");
        assertContentType("image/gif", null, "hoge.gif");

        assertContentType("application/pdf", "extractor/test.pdf", "hoge.pdf");

#### Office Documents
- Microsoft Office (Word, Excel, PowerPoint)
- OpenOffice/LibreOffice documents
- RTF, WordPerfect

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

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

#### Web and Markup

				"video/h261",
				"video/h263",
				"video/h263-1998",
				"video/h263-2000",
				"video/h264",
				"video/jpeg",
				"video/jpeg2000",
				"video/mj2",
				"video/mp1s",
				"video/mp2p",
				"video/mp2t",
				"video/mp4",
				"video/mp4v-es",
				"video/mpeg",
				"video/mpeg4-generic",
				"video/mpv",
				"video/nv",
				"video/ogg",
				"video/daala",

    <tika:uti>public.jpeg</tika:uti>
    <magic priority="50">
      <!-- FFD8 is the SOI (Start Of Image) marker.              -->
      <!-- It is followed by another marker that starts with FF. -->
      <match value="0xffd8ff" type="string" offset="0"/>
    </magic>
    <glob pattern="*.jpg"/>
    <glob pattern="*.jpeg"/>
    <glob pattern="*.jpe"/>
    <glob pattern="*.jif"/>

test.jpg...

e8db7f2e0464eb1fb51f268eeba54&amp;uid=131239501&amp;nid=244+124" target="blank" style="text-decoration:none;border-style:none;border:0;padding:0;margin:0;"><img src="https://pbs.twimg.com/profile_images/570533738933547008/bdtDCTFo_reasonably_small.jpeg" class="avatar_med" width="32" height="32" style="margin:0;padding:0;display:block;-ms-interpolation-mode:bicubic;border:none;outline:none;padding:0px;margin:0px;border-radius:5px;-moz-border-radius:5px;-webkit-border-radius:5px;width:32;height:32;"...

        urlFilter.init(sessionId);

        urlFilter.addExclude(".*\\.(jpg|png|gif)$");

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertTrue(urlFilter.match("https://example.com/document.pdf"));
        assertFalse(urlFilter.match("https://example.com/image.jpg"));
        assertFalse(urlFilter.match("https://example.com/photo.png"));

        logger.info(content);
        assertTrue(content.contains("Test"));
    }

    public void test_getTika_jpg() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/image/test.jpg");
        final ExtractData extractData = tikaExtractor.getText(in, null);
        final String content = extractData.getContent();
        CloseableUtil.closeQuietly(in);
        logger.info(content);