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"));

        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");

});

// Configure URL filtering
container.singleton("urlFilter", UrlFilterImpl.class, filter -> {
    filter.addInclude("https://example.com/.*");
    filter.addExclude(".*\\.(css|js|png|jpg|gif)$");
});

// Configure content extraction
container.singleton("tikaExtractor", TikaExtractor.class);
container.singleton("extractorFactory", ExtractorFactory.class, factory -> {

        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);

      <match value="0x0000000C6A5020200D0A870A" type="string" offset="0">
        <match value="0x6a706d20" type="string" offset="20"/>
      </match>
    </magic>
    <glob pattern="*.jpm"/>
    <glob pattern="*.jpgm"/>
  </mime-type>

  <mime-type type="image/jpx">
    <sub-class-of type="image/x-jp2-container" />
    <acronym>JP2</acronym>
    <_comment>JPEG 2000 Part 2 (JPX)</_comment>
    <magic priority="50">