Package org.apache.tika.extractor

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

378
379
380
381
382
383
384
385
386
387
388
        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
473
474
475
476
477
478
479
480
481
482
483
        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
501
502
503
504
505
506
507
508
509
510
511
        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
559
560
561
562
563
564
565
566
567
568
569
        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
573
574
575
576
577
578
579
580
581
582
583
        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
56
57
58
59
60
61
62
63
64
65
66
            assertEquals(true, extractor.isSupported(stream));

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

            assertEquals(2, handler.filenames.size());
        } finally {
            input.close();
        }
View Full Code Here
525
526
527
528
529
530
531
532
533
534
535
       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
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
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.