Package org.apache.tika.extractor

Examples of org.apache.tika.extractor.ParserContainerExtractor$RecursiveParser

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
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
       assertTrue(needle > -1);
       assertTrue(needle > pdfHaystack && pdfHaystack > outerHaystack);
      
       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());
       assertEquals(3, tracker.mediaTypes.size());
       assertEquals("image1.emf", tracker.filenames.get(0));
       assertNull(tracker.filenames.get(1));
       assertEquals("Test.docx", tracker.filenames.get(2));
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
     * Check the Rtf and Attachments are returned
     *  as expected
     */
   @Test
    public void testBodyAndAttachments() throws Exception {
       ContainerExtractor extractor = new ParserContainerExtractor();
      
       // Process it with recursing
       // Will have the message body RTF and the attachments
       TrackingHandler handler = process(file, extractor, true);
       assertEquals(6, handler.filenames.size());
View Full Code Here
TOP

Related Classes of org.apache.tika.extractor.ParserContainerExtractor$RecursiveParser

  • org.apache.tika.detect.DefaultDetector
  • org.apache.tika.io.TemporaryFiles
  • org.apache.tika.io.TemporaryResources
  • org.apache.tika.io.TikaInputStream
  • org.apache.tika.metadata.Metadata
  • org.apache.tika.mime.MediaType
  • org.apache.tika.parser.AutoDetectParser
  • org.apache.tika.parser.microsoft.ooxml.OOXMLContainerExtractionTest
  • org.apache.tika.parser.microsoft.POIContainerExtractionTest
  • org.apache.tika.parser.microsoft.TNEFParserTest
    • 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.