Examples of org.apache.tika.io.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

    private void assertType(String file, String byData, String byNameAndData) throws Exception {
       assertTypeByData(file, byData);
       assertTypeByNameAndData(file, byNameAndData);
    }
    private void assertTypeByNameAndData(String dataFile, String name, String type) throws Exception {
       TikaInputStream stream = TikaInputStream.get(
               TestContainerAwareDetector.class.getResource(
                       "/test-documents/" + dataFile));
       try {
           Metadata m = new Metadata();
           if (name != null)
              m.add(Metadata.RESOURCE_NAME_KEY, name);
           
           assertEquals(
                   MediaType.parse(type),
                   detector.detect(stream, m));
       } finally {
           stream.close();
       }
    }

View Full Code Here


    }


    @Test
    public void testOpenContainer() throws Exception {
        TikaInputStream stream = TikaInputStream.get(
                TestContainerAwareDetector.class.getResource(
                        "/test-documents/testPPT.ppt"));
        try {
            assertNull(stream.getOpenContainer());
            assertEquals(
                    MediaType.parse("application/vnd.ms-powerpoint"),
                    detector.detect(stream, new Metadata()));
            assertTrue(stream.getOpenContainer() instanceof NPOIFSFileSystem);
        } finally {
            stream.close();
        }
    }

View Full Code Here

    }


    private void assertRemovalTempfiles(String fileName) throws Exception {
        int numberOfTempFiles = countTemporaryFiles();


        TikaInputStream stream = TikaInputStream.get(
                TestContainerAwareDetector.class.getResource(
                        "/test-documents/" + fileName));
        try {
            detector.detect(stream, new Metadata());
        } finally {
            stream.close();
        }


        assertEquals(numberOfTempFiles, countTemporaryFiles());
    }

View Full Code Here

    @Test
    public void testTruncatedFiles() throws Exception {
        // First up a truncated OOXML (zip) file
       
        // With only the data supplied, the best we can do is the container
        TikaInputStream xlsx = getTruncatedFile("testEXCEL.xlsx", 300);
        Metadata m = new Metadata();
        try {
            assertEquals(
                    MediaType.application("x-tika-ooxml"),
                    detector.detect(xlsx, m));
        } finally {
            xlsx.close();
        }
        
        // With truncated data + filename, we can use the filename to specialise
        xlsx = getTruncatedFile("testEXCEL.xlsx", 300);
        m = new Metadata();
        m.add(Metadata.RESOURCE_NAME_KEY, "testEXCEL.xlsx");
        try {
            assertEquals(
                    MediaType.application("vnd.openxmlformats-officedocument.spreadsheetml.sheet"),
                    detector.detect(xlsx, m));
        } finally {
            xlsx.close();
        }
        


        // Now a truncated OLE2 file 
        TikaInputStream xls = getTruncatedFile("testEXCEL.xls", 400);
        m = new Metadata();
        try {
            assertEquals(
                    MediaType.application("x-tika-msoffice"),
                    detector.detect(xls, m));
        } finally {
            xls.close();
        }
        
        // Finally a truncated OLE2 file, with a filename available
        xls = getTruncatedFile("testEXCEL.xls", 400);
        m = new Metadata();
        m.add(Metadata.RESOURCE_NAME_KEY, "testEXCEL.xls");
        try {
            assertEquals(
                    MediaType.application("vnd.ms-excel"),
                    detector.detect(xls, m));
        } finally {
            xls.close();
        }
   }

View Full Code Here

    public void testAdobeFontMetricParsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();
        TikaInputStream stream = TikaInputStream.get(
                AdobeFontMetricParserTest.class.getResource(
                        "/test-documents/testAFM.afm"));


        try {
            parser.parse(stream, handler, metadata, context);
        } finally {
            stream.close();
        }


        assertEquals("application/x-font-adobe-metric", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("TestFullName", metadata.get(TikaCoreProperties.TITLE));
        assertEquals("Fri Jul 15 17:50:51 2011", metadata.get(Metadata.CREATION_DATE));

View Full Code Here

    public static final MediaType TYPE_PNG = MediaType.image("png");
    public static final MediaType TYPE_EMF = MediaType.application("x-emf");
    public static final MediaType TYPE_WMF = MediaType.application("x-msmetafile");


    protected TrackingHandler process(String filename, ContainerExtractor extractor, boolean recurse) throws Exception {
        TikaInputStream stream = getTestFile(filename);
        try {
            assertEquals(true, extractor.isSupported(stream));


            // Process it
            TrackingHandler handler = new TrackingHandler();
            if(recurse) {
                extractor.extract(stream, extractor, handler);
            } else {
                extractor.extract(stream, null, handler);
            }


            // So they can check what happened
            return handler;
        } finally {
            stream.close();
        }
    }

View Full Code Here

        //assertEquals("Stereo", metadata.get(XMPDM.AUDIO_CHANNEL_TYPE)); // TODO Extract
        assertEquals("M4A", metadata.get(XMPDM.AUDIO_COMPRESSOR));
        
        
        // Check again by file, rather than stream
        TikaInputStream tstream = TikaInputStream.get(
              MP4ParserTest.class.getResourceAsStream("/test-documents/testMP4.m4a"));
        tstream.getFile();
        try {
           parser.parse(tstream, handler, metadata, new ParseContext());
        } finally {
           tstream.close();
        }
    }

View Full Code Here

    @Test
    public void testEmbedded() throws Exception {
        InputStream input = FictionBookParserTest.class.getResourceAsStream("/test-documents/test.fb2");
        try {
            ContainerExtractor extractor = new ParserContainerExtractor();
            TikaInputStream stream = TikaInputStream.get(input);


            assertEquals(true, extractor.isSupported(stream));


            // Process it
            AbstractPOIContainerExtractionTest.TrackingHandler handler = new AbstractPOIContainerExtractionTest.TrackingHandler();

View Full Code Here

      public void write(OutputStream outputStream) throws IOException, WebApplicationException {
        Writer writer = new OutputStreamWriter(outputStream, "UTF-8");


        BodyContentHandler body = new BodyContentHandler(new RichTextContentHandler(writer));


        TikaInputStream tis = TikaInputStream.get(is);


        try {
            parser.parse(tis, body, metadata);
        } catch (SAXException e) {
          throw new WebApplicationException(e);
        } catch (EncryptedDocumentException e) {
          logger.warn(String.format(
                  "%s: Encrypted document",
                  info.getPath()
          ), e);


          throw new WebApplicationException(e, Response.status(422).build());
        } catch (TikaException e) {
          logger.warn(String.format(
            "%s: Text extraction failed",
            info.getPath()
          ), e);


          if (e.getCause()!=null && e.getCause() instanceof WebApplicationException) {
            throw (WebApplicationException) e.getCause();
          }


          if (e.getCause()!=null && e.getCause() instanceof IllegalStateException) {
            throw new WebApplicationException(Response.status(422).build());
          }


          if (e.getCause()!=null && e.getCause() instanceof OldWordFileFormatException) {
            throw new WebApplicationException(Response.status(422).build());
          }


          throw new WebApplicationException(Response.Status.INTERNAL_SERVER_ERROR);
        } finally {
          tis.close();
        }
      }
    };
  }

View Full Code Here

        }
        catch ( TransformerConfigurationException e ) {
          throw new WebApplicationException( e );
        }


        TikaInputStream tis = TikaInputStream.get(is);


        try {
          parser.parse(tis, content, metadata);
        }
        catch (SAXException e) {
          throw new WebApplicationException(e);
        }
        catch (EncryptedDocumentException e) {
          logger.warn(String.format(
            "%s: Encrypted document",
            info.getPath()
          ), e);
          throw new WebApplicationException(e, Response.status(422).build());
        }
        catch (TikaException e) {
          logger.warn(String.format(
            "%s: Text extraction failed",
            info.getPath()
          ), e);


          if (e.getCause()!=null && e.getCause() instanceof WebApplicationException)
            throw (WebApplicationException) e.getCause();


          if (e.getCause()!=null && e.getCause() instanceof IllegalStateException)
            throw new WebApplicationException(Response.status(422).build());


          if (e.getCause()!=null && e.getCause() instanceof OldWordFileFormatException)
            throw new WebApplicationException(Response.status(422).build());


          throw new WebApplicationException(Response.Status.INTERNAL_SERVER_ERROR);
        }
        finally {
          tis.close();
        }
      }
    };
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.tika.io.TikaInputStream

com.cloudera.cdk.morphline.tika.decompress.EmbeddedExtractor

com.cloudera.cdk.morphline.tika.decompress.UnpackBuilder$Unpack

com.gentics.cr.lucene.indexer.transformer.tika.TikaParserTransformer

org.apache.tika.cli.TikaCLI$FileEmbeddedDocumentExtractor

org.apache.tika.detect.POIFSContainerDetector

org.apache.tika.detect.TestContainerAwareDetector

org.apache.tika.embedder.ExternalEmbedder

org.apache.tika.extractor.ParserContainerExtractor$RecursiveParser

org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor

org.apache.tika.gui.TikaGUI

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.