Package org.apache.tika.parser

Examples of org.apache.tika.parser.Parser

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
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
   * Tests that the ParseContext parser is correctly fired for all the
   * embedded entries.
   */
    @Test
  public void testEmbedded() throws Exception {
    Parser parser = new AutoDetectParser(); // Should auto-detect!
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();

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

    assertEquals(1, tracker.filenames.size());
    assertEquals(1, tracker.mediatypes.size());

    assertEquals("testTXT.txt", tracker.filenames.get(0));

    for (String type : tracker.mediatypes) {
      assertNull(type);
    }

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

    assertEquals(1, tracker.filenames.size());
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
        for (int i=0; i<extensions.length; i++) {
            String extension = extensions[i];
            String filename = "testPPT." + extension;

            Parser parser = new AutoDetectParser();
            Metadata metadata = new Metadata();
            // TODO: should auto-detect without the resource name
            metadata.set(Metadata.RESOURCE_NAME_KEY, filename);
            ContentHandler handler = new BodyContentHandler();
            ParseContext context = new ParseContext();
   
            InputStream input = getTestDocument(filename);
            try {
                parser.parse(input, handler, metadata, context);
   
                assertEquals(
                        "Mime-type checking for " + filename,
                        mimeTypes[i],
                        metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
        for (int i=0; i<extensions.length; i++) {
            String extension = extensions[i];
            final String filename = "testPPT." + extension;

            Parser parser = new AutoDetectParser();
            final Metadata metadata = new Metadata();
            // TODO: should auto-detect without the resource name
            metadata.set(Metadata.RESOURCE_NAME_KEY, filename);

      // Allow the value to be access from the inner class
      final int currentI = i;
            ContentHandler handler = new BodyContentHandler()
    {
        public void startDocument ()
        {
      assertEquals(
             "Mime-type checking for " + filename,
             mimeTypes[currentI],
             metadata.get(Metadata.CONTENT_TYPE));
      assertEquals("Attachment Test", metadata.get(TikaCoreProperties.TITLE));
      assertEquals("Rajiv", metadata.get(TikaCoreProperties.CREATOR));
      assertEquals("Rajiv", metadata.get(Metadata.AUTHOR));

        }

    };
            ParseContext context = new ParseContext();
   
            InputStream input = getTestDocument(filename);
            try {
                parser.parse(input, handler, metadata, context);
            } finally {
                input.close();
            }
        }
    }
View Full Code Here
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
      
       for (int i=0; i<extensions.length; i++) {
          String extension = extensions[i];
          String filename = "testPPT." + extension;

          Parser parser = new AutoDetectParser();
          Metadata metadata = new Metadata();
          metadata.set(Metadata.RESOURCE_NAME_KEY, filename);
          ContentHandler handler = new BodyContentHandler();
          ParseContext context = new ParseContext();
 
          InputStream input = getTestDocument(filename);
          try {
              parser.parse(input, handler, metadata, context);

              // Should get the metadata
              assertEquals(
                    "Mime-type checking for " + filename,
                    mimeTypes[i],
View Full Code Here
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
    @Test
    public void testProtectedExcelSheets() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/protectedSheets.xlsx");

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

        try {
            parser.parse(input, handler, metadata, context);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
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
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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
*/
public class TarParserTest extends AbstractPkgTest {

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

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

        assertEquals("application/x-tar", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
     * Tests that the ParseContext parser is correctly
     *  fired for all the embedded entries.
     */
    @Test
    public void testEmbedded() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = ZipParserTest.class.getResourceAsStream(
               "/test-documents/test-documents.tar");
       try {
           parser.parse(stream, handler, metadata, trackingContext);
       } finally {
           stream.close();
       }
      
       // Should have found all 9 documents, but not the directory
View Full Code Here
TOP

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

  • bixo.parser.TikaCallableTest
  • com.baasbox.controllers.File
  • com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell
  • com.digitalpebble.behemoth.tika.TikaProcessor
  • com.findwise.hydra.stage.tika.SimpleFetchingTikaStageTest
  • 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
  • ipcress.Extraction
    • 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.