Examples of org.apache.tika.Tika.detect()

org.apache.tika.Tika.detect()
Detects the media type of the given document. The type detection is based on the content of the given document stream and any given document metadata. The document stream can be null, in which case only the given document metadata is used for type detection.
If the document stream supports the {@link InputStream#markSupported() mark feature}, then the stream is marked and reset to the original position before this method returns. Only a limited number of bytes are read from the stream.
The given document stream is not closed by this method.
Unlike in the {@link #parse(InputStream,Metadata)} method, thegiven document metadata is not modified by this method. @param stream the document stream, or null @param metadata document metadata @return detected media type @throws IOException if the stream can not be read

        // requested a specific resource
        String file = StringUtils.getLastPathElement(requestedPath);
        try {
          // query Tika for the content type
          Tika tika = new Tika();
          String contentType = tika.detect(file);


          if (contentType == null) {
            // ask the container for the content type
            contentType = context.getMimeType(requestedPath);

View Full Code Here

    @Test
    public void testBundleDetection(BundleContext bc) throws Exception {
        Tika tika = new Tika();


        // Simple type detection
        assertEquals("text/plain", tika.detect("test.txt"));
        assertEquals("application/pdf", tika.detect("test.pdf"));
    }


    @Ignore // TODO Fix this test
    @Test

View Full Code Here

    public void testBundleDetection(BundleContext bc) throws Exception {
        Tika tika = new Tika();


        // Simple type detection
        assertEquals("text/plain", tika.detect("test.txt"));
        assertEquals("application/pdf", tika.detect("test.pdf"));
    }


    @Ignore // TODO Fix this test
    @Test
    public void testBundleSimpleText(BundleContext bc) throws Exception {

View Full Code Here

      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern
      try {
        TikaConfig tikaConfig = TikaConfig.getDefaultConfig();
        Tika tika = new Tika(tikaConfig);
        retType = tika.detect(url) != null ? tika.detect(url) : null;
      } catch (Exception e) {
        String message = "Problem loading default Tika configuration";
        LOG.error(message, e);
        throw new RuntimeException(e);
      }

View Full Code Here

      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern
      try {
        TikaConfig tikaConfig = TikaConfig.getDefaultConfig();
        Tika tika = new Tika(tikaConfig);
        retType = tika.detect(url) != null ? tika.detect(url) : null;
      } catch (Exception e) {
        String message = "Problem loading default Tika configuration";
        LOG.error(message, e);
        throw new RuntimeException(e);
      }

View Full Code Here

    // if magic is enabled use mime magic to guess if the mime type returned
    // from the magic guess is different than the one that's already set so far
    // if it is, and it's not the default mime type, then go with the mime type
    // returned by the magic
    if (this.mimeMagic) {
      magicType = tika.detect(data);


      // Deprecated in Tika 1.0 See https://issues.apache.org/jira/browse/NUTCH-1230
      //MimeType magicType = this.mimeTypes.getMimeType(data);
      if (magicType != null && !magicType.equals(MimeTypes.OCTET_STREAM)
          && !magicType.equals(MimeTypes.PLAIN_TEXT)

View Full Code Here

    public void validateImageFormat(byte[] bytes) throws ImageFormatException {
        Validate.notNull(bytes, "Incoming byte array cannot be null");
        Tika tika = new Tika();
        InputStream input = new ByteArrayInputStream(bytes);
        try {
            String type = tika.detect(input);
            if (!VALID_IMAGE_TYPES.contains(type)) {
                LOGGER.debug("Wrong file extension. May be only {}", VALID_IMAGE_EXTENSIONS);
                throw new ImageFormatException(VALID_IMAGE_EXTENSIONS);
            }
        } catch (IOException e) {

View Full Code Here

    public BufferedImage convertByteArrayToImage(byte[] bytes) throws ImageProcessException {
        BufferedImage result;
        BufferedInputStream bis = new BufferedInputStream(new ByteArrayInputStream(bytes));
        Tika tika = new Tika();
        try {
            String type = tika.detect(bis);
            if (type.contains(ImageService.ICO_TYPE)) {
                result = ICODecoder.read(bis).get(0);
            } else {
                result = ImageIO.read(bis);
            }

View Full Code Here

    @Test
    public void testTikaBundle(BundleContext bc) throws Exception {
        Tika tika = new Tika();


        // Simple type detection
        assertEquals("text/plain", tika.detect("test.txt"));
        assertEquals("application/pdf", tika.detect("test.pdf"));


        // Simple text extraction
        String xml = tika.parseToString(new File("pom.xml"));
        assertTrue(xml.contains("tika-bundle"));

View Full Code Here

    public void testTikaBundle(BundleContext bc) throws Exception {
        Tika tika = new Tika();


        // Simple type detection
        assertEquals("text/plain", tika.detect("test.txt"));
        assertEquals("application/pdf", tika.detect("test.pdf"));


        // Simple text extraction
        String xml = tika.parseToString(new File("pom.xml"));
        assertTrue(xml.contains("tika-bundle"));

View Full Code Here

0 1 2

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.