Examples of TikaInputStream

org.apache.tika.io.TikaInputStream
Input stream with extended capabilities. The purpose of this class is to allow files and other resources and information to be associated with the {@link InputStream} instance passed through the{@link org.apache.tika.parser.Parser} interface and other similar APIs.
TikaInputStream instances can be created using the various static get() factory methods. Most of these methods take an optional {@link Metadata} argument that is then filled with the available inputmetadata from the given resource. The created TikaInputStream instance keeps track of the original resource used to create it, while behaving otherwise just like a normal, buffered {@link InputStream}. A TikaInputStream instance is also guaranteed to support the {@link #mark(int)} feature.
Code that wants to access the underlying file or other resources associated with a TikaInputStream should first use the {@link #get(InputStream)} factory method to cast or wrap a given{@link InputStream} into a TikaInputStream instance. @since Apache Tika 0.8

Examples of org.apache.tika.io.TikaInputStream

        zout.put(finalName, data);


        count.increment();
      } else {
        if (inputStream instanceof TikaInputStream) {
          TikaInputStream tin = (TikaInputStream)  inputStream;


          if (tin.getOpenContainer()!=null && tin.getOpenContainer() instanceof DirectoryEntry) {
            POIFSFileSystem fs = new POIFSFileSystem();
            copy((DirectoryEntry) tin.getOpenContainer(), fs.getRoot());
            ByteArrayOutputStream bos2 = new ByteArrayOutputStream();
            fs.writeFilesystem(bos2);
            bos2.close();


            zout.put(finalName, bos2.toByteArray());

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

       assertTrue(needle > -1);
       assertTrue(needle > pdfHaystack && pdfHaystack > outerHaystack);
       
       //plagiarized from POIContainerExtractionTest.  Thank you!
       TrackingHandler tracker = new TrackingHandler();
       TikaInputStream tis;
       ContainerExtractor ex = new ParserContainerExtractor();
       try{
          tis= TikaInputStream.get(getResourceAsStream("/test-documents/testPDFEmbeddingAndEmbedded.docx"));
          ex.extract(tis, ex, tracker);
       } finally {

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

        String xml = getXML("/testPDF_childAttachments.pdf").xml;
        //"regressiveness" exists only in Unit10.doc not in the container pdf document
        assertTrue(xml.contains("regressiveness"));


        TrackingHandler tracker = new TrackingHandler();
        TikaInputStream tis = null;
        ContainerExtractor ex = new ParserContainerExtractor();
        try{
            tis= TikaInputStream.get(
                getResourceAsStream("/test-documents/testPDF_childAttachments.pdf"));
            ex.extract(tis, ex, tracker);
        } finally {
            if (tis != null){
                tis.close();
            }
        }
        assertEquals(2, tracker.filenames.size());
        assertEquals(2, tracker.mediaTypes.size());
        assertEquals("Press Quality(1).joboptions", tracker.filenames.get(0));

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

public class TNEFParserTest extends AbstractPOIContainerExtractionTest {
   private static final String file = "testWINMAIL.dat";
   
   @Test
   public void testBasics() throws Exception {
      TikaInputStream stream = getTestFile(file);
      Detector detector = new DefaultDetector();
      try {
         assertEquals(
                 MediaType.application("vnd.ms-tnef"),
                 detector.detect(stream, new Metadata()));
     } finally {
         stream.close();
     }
   }

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

     }
   }
   
   @Test
   public void testMetadata() throws Exception {
      TikaInputStream stream = getTestFile(file);
      
      Metadata metadata = new Metadata();
      ContentHandler handler = new BodyContentHandler();
      
      TNEFParser tnef = new TNEFParser();

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

                       break;
                    default:
                       mimeType =  "image/unknown";
                       break;
                    }
                    TikaInputStream stream = TikaInputStream.get(blip.getPicturedata());
                    
                    // Handle the embeded resource
                    extractor.handleEmbeddedResource(
                          stream, null, mimeType,
                          handler, true

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

       xhtml.endElement("img");


       // Have we already output this one?
       // (Only expose each individual image once) 
       if(! pictures.hasOutput(picture)) {
          TikaInputStream stream = TikaInputStream.get(picture.getContent());
          handleEmbeddedResource(stream, filename, mimeType, xhtml, false);
          pictures.recordOutput(picture);
       }
    }

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

    protected TrackingHandler process(String filename, ContainerExtractor extractor, boolean recurse) throws Exception {
        InputStream input = AbstractPOIContainerExtractionTest.class.getResourceAsStream(
             "/test-documents/" + filename);
        assertNotNull(filename + " not found", input);
        
        TikaInputStream stream = TikaInputStream.get(input);
        assertNotNull(stream);
        
        assertEquals(true, extractor.isSupported(stream));
        
        // Process it

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        TrueTypeFont font;
        TikaInputStream tis = TikaInputStream.get(stream);
        TTFParser parser = new TTFParser();
        if (tis.hasFile()) {
            font = parser.parseTTF(tis.getFile());
        } else {
            font = parser.parseTTF(stream);
        }


        metadata.set(Metadata.CONTENT_TYPE, TYPE.toString());

View Full Code Here

Examples of org.apache.tika.io.TikaInputStream

       // Is it an embedded OLE2 document, or an embedded OOXML document?
       try {
          Entry ooxml = dir.getEntry("Package");


          // It's OOXML
          TikaInputStream ooxmlStream = TikaInputStream.get(
                new DocumentInputStream((DocumentEntry)ooxml)
          );
          ZipContainerDetector detector = new ZipContainerDetector();
          MediaType type = detector.detect(ooxmlStream, new Metadata());
          handleEmbeddedResource(ooxmlStream, null, type.toString(), xhtml, true);
          return;
       } catch(FileNotFoundException e) {
          // It's regular OLE2
       }


       // Need to dump the directory out to a new temp file, so
       //  it's stand along
       POIFSFileSystem newFS = new POIFSFileSystem();
       copy(dir, newFS.getRoot());


       File tmpFile = File.createTempFile("tika", ".ole2");
       try {
           FileOutputStream out = new FileOutputStream(tmpFile);
           newFS.writeFilesystem(out);
           out.close();


           // What kind of document is it?
           Metadata metadata = new Metadata();
           POIFSDocumentType type = POIFSDocumentType.detectType(dir);
           metadata.set(Metadata.CONTENT_TYPE, type.getType().toString());


           // Trigger for the document itself 
           TikaInputStream embedded = TikaInputStream.get(tmpFile);
           try {
               if (extractor.shouldParseEmbedded(metadata)) {
                   extractor.parseEmbedded(embedded, xhtml, metadata, true);
               }
           } finally {
               embedded.close();
           }
       } finally {
           tmpFile.delete();
       }
    }

View Full Code Here

0 1 2 3 4 5

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.