Package org.apache.tika.extractor

Examples of org.apache.tika.extractor.ContainerExtractor

106
107
108
109
110
111
112
113
114
115
116
     *       -> powerpoint
     *       -> excel
     *           -> image
     */
    public void testEmbeddedOfficeFiles() throws Exception {
       ContainerExtractor extractor = new ParserContainerExtractor();
       TrackingHandler handler;
      
      
       // Excel with a word doc and a powerpoint doc, both of which have images in them
       // Without recursion, should see both documents + the images
View Full Code Here
375
376
377
378
379
380
381
382
383
384
385
386
387
388
    @Test
    public void testBinControlWord() throws Exception {
        ByteCopyingHandler embHandler = new ByteCopyingHandler();
        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
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
        trueTypes.add("image/jpeg");
       
        TrackingHandler tracker = new TrackingHandler(skipTypes);
        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();
        }

        assertEquals(trueNames.size(), tracker.filenames.size());
        assertEquals(trueTypes.size(), tracker.mediaTypes.size());
        for (int i = 0; i < tracker.filenames.size(); i++) {
            String expectedName = trueNames.get(i);
            if (expectedName == null) {
                assertNull(tracker.filenames.get(i));
            } else {
                assertNotNull(tracker.filenames.get(i));
                //necessary to getName() because MSOffice extractor includes
                //directory: _1457338524/HW.txt
                assertEquals("filename equals ",
                        expectedName, FilenameUtils.getName(tracker.filenames.get(i)));
            }
            assertEquals(trueTypes.get(i), tracker.mediaTypes.get(i).toString());
        }
       
        tracker = new TrackingHandler();
        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
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
        skipTypes.add(MediaType.parse("application/x-msmetafile"));

        TrackingHandler tracker = new TrackingHandler(skipTypes);
        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
        assertEquals(0, tracker.filenames.size());

        tracker = new TrackingHandler();
        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
35
36
37
38
39
40
41
42
43
44
45
    /**
     * For office files which don't have anything embedded in them
     */
    @Test
    public void testWithoutEmbedded() throws Exception {
       ContainerExtractor extractor = new ParserContainerExtractor();
      
       String[] files = new String[] {
             "testEXCEL.xls", "testWORD.doc", "testPPT.ppt",
             "testVISIO.vsd", "test-outlook.msg"
       };
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
     * Office files with embedded images, but no other
     *  office files in them
     */
    @Test
    public void testEmbeddedImages() throws Exception {
       ContainerExtractor extractor = new ParserContainerExtractor();
       TrackingHandler handler;
      
       // Excel with 1 image
       handler = process("testEXCEL_1img.xls", extractor, false);
       assertEquals(1, handler.filenames.size());
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
     *       -> excel
     *           -> image
     */
    @Test
    public void testEmbeddedOfficeFiles() throws Exception {
       ContainerExtractor extractor = new ParserContainerExtractor();
       TrackingHandler handler;
      
      
       // Excel with a word doc and a powerpoint doc, both of which have images in them
       // Without recursion, should see both documents + the images
View Full Code Here
324
325
326
327
328
329
330
331
332
333
334
       assertEquals(TYPE_PDF, handler.mediaTypes.get(1));
    }

    @Test
    public void testEmbeddedOfficeFilesXML() throws Exception {
        ContainerExtractor extractor = new ParserContainerExtractor();
        TrackingHandler handler;

        handler = process("EmbeddedDocument.docx", extractor, false);
        assertTrue(handler.filenames.contains("Microsoft_Office_Excel_97-2003_Worksheet1.bin"));
        assertEquals(2, handler.filenames.size());
View Full Code Here
334
335
336
337
338
339
340
341
342
343
344
        assertEquals(2, handler.filenames.size());
    }

    @Test
    public void testPowerpointImages() throws Exception {
        ContainerExtractor extractor = new ParserContainerExtractor();
        TrackingHandler handler;

        handler = process("pictures.ppt", extractor, false);
        assertTrue(handler.mediaTypes.contains(new MediaType("image", "jpeg")));
        assertTrue(handler.mediaTypes.contains(new MediaType("image", "png")));
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
    @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
            TrackingHandler handler = new TrackingHandler();
            extractor.extract(stream, null, handler);

            assertEquals(2, handler.filenames.size());
        } finally {
            input.close();
        }
View Full Code Here
TOP

Related Classes of org.apache.tika.extractor.ContainerExtractor

  • org.apache.tika.parser.microsoft.POIContainerExtractionTest
  • org.apache.tika.parser.microsoft.TNEFParserTest
  • org.apache.tika.parser.pdf.PDFParserTest
  • org.apache.tika.parser.rtf.RTFParserTest
  • org.apache.tika.parser.xml.FictionBookParserTest
    • Copyright © 2018 www.massapicom. 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.