Package org.apache.tika.parser

Examples of org.apache.tika.parser.AutoDetectParser

510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
     * See TIKA-437.
     */
    @Test
    public void testProtectedExcelFile() throws Exception {

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();

        InputStream input = getTestDocument("protectedFile.xlsx");
        try {
            parser.parse(input, handler, metadata, context);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));

View Full Code Here
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
    }

    // TIKA-1024
    @Test
    public void testNakedUTF16BOM() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testNakedUTF16BOM.mp3");
      
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }
       assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
       assertEquals("", metadata.get(XMPDM.GENRE));
View Full Code Here
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
     * Test docx without headers
     * TIKA-633
     */
    @Test
    public void testNullHeaders() throws Exception {
        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();

        InputStream input = getTestDocument("NullHeader.docx");
        try {
            parser.parse(input, handler, metadata, context);
            assertFalse(handler.toString().length()==0);
        } finally {
            input.close();
        }
    }
View Full Code Here
48
49
50
51
52
53
54
55
56
   public void setUp() throws Exception {
      tracker = new EmbeddedTrackingParser();
      trackingContext = new ParseContext();
      trackingContext.set(Parser.class, tracker);
     
      autoDetectParser = new AutoDetectParser();
      recursingContext = new ParseContext();
      recursingContext.set(Parser.class, autoDetectParser);
   }
View Full Code Here
560
561
562
563
564
565
566
567
568
569
570
        Metadata metadata = new Metadata();

        InputStream stream = OOXMLParserTest.class.getResourceAsStream(
                "/test-documents/testWORD_various.docx");
        try {
            new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        String content = handler.toString();
View Full Code Here
632
633
634
635
636
637
638
639
640
641
642
        Metadata metadata = new Metadata();

        InputStream stream = OOXMLParserTest.class.getResourceAsStream(
                "/test-documents/testPPT_various.pptx");
        try {
            new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        String content = handler.toString();
View Full Code Here
67
68
69
70
71
72
73
         mediatypes.clear();
      }
     
      public Set<MediaType> getSupportedTypes(ParseContext context) {
         // Cheat!
         return (new AutoDetectParser()).getSupportedTypes(context);
      }
View Full Code Here
704
705
706
707
708
709
710
711
712
713
714
        Metadata metadata = new Metadata();

        InputStream stream = OOXMLParserTest.class.getResourceAsStream(
                "/test-documents/testPPT_masterFooter.pptx");
        try {
            new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        String content = handler.toString();
View Full Code Here
759
760
761
762
763
764
765
766
767
768
769
        Metadata metadata = new Metadata();

        InputStream stream = OOXMLParserTest.class.getResourceAsStream(
                "/test-documents/testWordArt.pptx");
        try {
            new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }
        String content = handler.toString();
        assertContains("Here is some red word Art", content);
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
import org.xml.sax.ContentHandler;

public class ArParserTest extends AbstractPkgTest {
    @Test
  public void testArParsing() throws Exception {
    Parser parser = new AutoDetectParser();

    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();

    InputStream stream = ArParserTest.class
        .getResourceAsStream("/test-documents/testARofText.ar");
    try {
      parser.parse(stream, handler, metadata, recursingContext);
    } finally {
      stream.close();
    }

    assertEquals("application/x-archive",
        metadata.get(Metadata.CONTENT_TYPE));
    String content = handler.toString();
    assertTrue(content.contains("testTXT.txt"));
    assertTrue(content.contains("Test d'indexation de Txt"));
    assertTrue(content.contains("http://www.apache.org"));

    stream = ArParserTest.class
        .getResourceAsStream("/test-documents/testARofSND.ar");
    try {
      parser.parse(stream, handler, metadata, recursingContext);
    } finally {
      stream.close();
    }

    assertEquals("application/x-archive",
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.AutoDetectParser

  • bixo.parser.SimpleParser
  • com.baasbox.controllers.File
  • com.findwise.utils.tika.InputStreamParser
  • com.ikanow.infinit.e.harvest.extraction.document.file.FileHarvester
  • com.ikanow.infinit.e.harvest.extraction.text.legacy.TextExtractorTika
  • com.nidhinova.tika.server.TikaService
  • com.tamingtext.tika.TikaTest
  • edu.isi.karma.rdf.GenericRDFGenerator
  • fr.inra.lipm.jezlucene.Main
  • fr.inra.lipm.jezlucene.parser.Parser
    • 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.