Examples of org.apache.tika.extractor.ContainerExtractor.extract()

Class org.apache.tika.extractor.ContainerExtractor

Examples of org.apache.tika.extractor.ContainerExtractor.extract()

org.apache.tika.extractor.ContainerExtractor.extract()
Processes a container file, and extracts all the embedded resources from within it.
The {@link EmbeddedResourceHandler} you supply willbe called for each embedded resource in the container. It is up to you whether you process the contents of the resource or not.
The given document stream is consumed but not closed by this method. The responsibility to close the stream remains on the caller.
If required, nested containers (such as a .docx within a .zip) can automatically be recursed into, and processed inline. If no recurseExtractor is given, the nested containers will be treated as with any other embedded resources. @since Apache Tika 0.8 @param stream the document stream (input) @param recurseExtractor the extractor to use on any embedded containers @param handler handler for the embedded files (output) @throws IOException if the document stream could not be read @throws TikaException if the container could not be parsed


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


            // Process it
            AbstractPOIContainerExtractionTest.TrackingHandler handler = new AbstractPOIContainerExtractionTest.TrackingHandler();
            extractor.extract(stream, null, handler);


            assertEquals(2, handler.filenames.size());
        } finally {
            input.close();
        }

View Full Code Here

       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 {
          stream.close();
       }
       assertEquals(true, ex.isSupported(tis));
       assertEquals(3, tracker.filenames.size());

View Full Code Here

        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();
            }
        }

View Full Code Here

       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 {
          stream.close();
       }
       assertEquals(true, ex.isSupported(tis));
       assertEquals(3, tracker.filenames.size());

View Full Code Here

        TikaInputStream tis = null;
        try {
            ContainerExtractor ex = new ParserContainerExtractor();
            tis = TikaInputStream.get(getResourceAsStream("/test-documents/testBinControlWord.rtf"));
            assertEquals(true, ex.isSupported(tis));
            ex.extract(tis, ex, embHandler);            
        } finally {
            tis.close();
        }
        assertEquals(1, embHandler.bytes.size());

View Full Code Here

        TikaInputStream tis = null;
        try {
            ContainerExtractor ex = new ParserContainerExtractor();
            tis = TikaInputStream.get(getResourceAsStream("/test-documents/testRTFEmbeddedFiles.rtf"));
            assertEquals(true, ex.isSupported(tis));
            ex.extract(tis, ex, tracker);


        } finally {
            tis.close();
        }

View Full Code Here

        tis = null;
        try {
            ContainerExtractor ex = new ParserContainerExtractor();
            tis = TikaInputStream.get(getResourceAsStream("/test-documents/testRTFEmbeddedFiles.rtf"));
            assertEquals(true, ex.isSupported(tis));
            ex.extract(tis, ex, tracker);


        } finally {
            tis.close();
        }
        assertEquals(47, tracker.filenames.size());

View Full Code Here

        TikaInputStream tis = null;
        try {
            ContainerExtractor ex = new ParserContainerExtractor();
            tis = TikaInputStream.get(getResourceAsStream("/test-documents/testRTFEmbeddedLink.rtf"));
            assertEquals(true, ex.isSupported(tis));
            ex.extract(tis, ex, tracker);


        } finally {
            tis.close();
        }
        //should gracefully skip link and not throw NPE, IOEx, etc

View Full Code Here

        tis = null;
        try {
            ContainerExtractor ex = new ParserContainerExtractor();
            tis = TikaInputStream.get(getResourceAsStream("/test-documents/testRTFEmbeddedLink.rtf"));
            assertEquals(true, ex.isSupported(tis));
            ex.extract(tis, ex, tracker);
        } finally {
            tis.close();
        }
        //should gracefully skip link and not throw NPE, IOEx, etc
        assertEquals(2, tracker.filenames.size());

View Full Code Here


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


            // Process it
            AbstractPOIContainerExtractionTest.TrackingHandler handler = new AbstractPOIContainerExtractionTest.TrackingHandler();
            extractor.extract(stream, null, handler);


            assertEquals(2, handler.filenames.size());
        } finally {
            input.close();
        }

View Full Code Here

0 1

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.