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

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

View Full Code Here

         stream.close();
     }
   }
   
   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

    private void handleEmbeddedOLE(PackagePart part, ContentHandler handler)
            throws IOException, SAXException {
        POIFSFileSystem fs = new POIFSFileSystem(part.getInputStream());
        try {
            Metadata metadata = new Metadata();
            TikaInputStream stream = null;


            DirectoryNode root = fs.getRoot();
            POIFSDocumentType type = POIFSDocumentType.detectType(root);
            
            if (root.hasEntry("CONTENTS")

View Full Code Here

            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream tis = TikaInputStream.get(stream, tmp);
            new ImageMetadataExtractor(metadata).parseJpeg(tis.getFile());
            new JempboxExtractor(metadata).parse(tis);
        } finally {
            tmp.dispose();
        }

View Full Code Here

    }


    public void openFile(File file) {
        try {
            Metadata metadata = new Metadata();
            TikaInputStream stream = TikaInputStream.get(file, metadata);
            try {
                handleStream(stream, metadata);
            } finally {
                stream.close();
            }
        } catch (Throwable t) {
            handleError(file.getPath(), t);
        }
    }

View Full Code Here

    }


    public void openURL(URL url) {
        try {
            Metadata metadata = new Metadata();
            TikaInputStream stream = TikaInputStream.get(url, metadata);
            try {
                handleStream(stream, metadata);
            } finally {
                stream.close();
            }
        } catch (Throwable t) {
            handleError(url.toString(), t);
        }
    }

View Full Code Here

        boolean hasMetadataCommandArguments =
                (metadataCommandArguments != null && !metadataCommandArguments.isEmpty());
        boolean serializeMetadataCommandArgumentsToken = false;
        boolean replacedMetadataCommandArgumentsToken = false;


        TikaInputStream tikaInputStream = TikaInputStream.get(inputStream);
        File tempOutputFile = null;


        List<String> commandMetadataSegments = null;
        if (hasMetadataCommandArguments) {
            commandMetadataSegments = getCommandMetadataSegments(metadata);
        }


        // Build our command
        List<String> origCmd = Arrays.asList(command);
        List<String> cmd = new ArrayList<String>();
        for (String commandSegment : origCmd) {
            if (commandSegment.indexOf(ExternalParser.INPUT_FILE_TOKEN) != -1) {
                commandSegment = commandSegment.replace(
                        ExternalParser.INPUT_FILE_TOKEN,
                        tikaInputStream.getFile().toString());
                inputToStdIn = false;
            }
            if (commandSegment.indexOf(ExternalParser.OUTPUT_FILE_TOKEN) != -1) {
                tempOutputFile = tmp.createTemporaryFile();
                commandSegment = commandSegment.replace(

View Full Code Here

            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata, context);
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
            TaggedContentHandler taggedHandler = 
                handler != null ? new TaggedContentHandler(handler) : null;
      metadata.add("X-Parsed-By", parser.getClass().getName());
            try {
                parser.parse(taggedStream, taggedHandler, metadata, context);
            } catch (RuntimeException e) {
                throw new TikaException(
                        "Unexpected RuntimeException from " + parser, e);
            } catch (IOException e) {
                taggedStream.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-198: Illegal IOException from " + parser, e);
            } catch (SAXException e) {
                if (taggedHandler != null) taggedHandler.throwIfCauseOf(e);
                throw new TikaException(

View Full Code Here

            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream tis = TikaInputStream.get(stream, tmp);


            // Automatically detect the MIME type of the document
            MediaType type = detector.detect(tis, metadata);
            metadata.set(Metadata.CONTENT_TYPE, type.toString());

View Full Code Here

        // Open the Zip stream
        // Use a File if we can, and an already open zip is even better
        ZipFile zipFile = null;
        ZipInputStream zipStream = null;
        if (stream instanceof TikaInputStream) {
            TikaInputStream tis = (TikaInputStream) stream;
            Object container = ((TikaInputStream) stream).getOpenContainer();
            if (container instanceof ZipFile) {
                zipFile = (ZipFile) container;
            } else if (tis.hasFile()) {
                zipFile = new ZipFile(tis.getFile());                
            }
        } else {
            zipStream = new ZipInputStream(stream);
        }

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.