Package org.apache.tika.parser

Examples of org.apache.tika.parser.AutoDetectParser

177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
     * Test that with only ID3v2 tags, of version 2.4, we get the full
     *  set of information out.
     */
    @Test
    public void testMp3ParsingID3v24() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v24.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
          @Context UriInfo info,
          boolean saveAll
  ) throws Exception {
    Metadata metadata = new Metadata();

    AutoDetectParser parser = TikaResource.createParser();

    TikaResource.fillMetadata(parser, metadata, httpHeaders.getRequestHeaders());
    TikaResource.logRequest(logger, info, metadata);

    ContentHandler ch;
    ByteArrayOutputStream text = new ByteArrayOutputStream();

    if (saveAll) {
      ch = new BodyContentHandler(new RichTextContentHandler(new OutputStreamWriter(text, "UTF-8")));
    } else {
      ch = new DefaultHandler();
    }

    ParseContext pc = new ParseContext();

    Map<String, byte[]> files = new HashMap<String, byte[]>();
    MutableInt count = new MutableInt();

    pc.set(EmbeddedDocumentExtractor.class, new MyEmbeddedDocumentExtractor(count, files));

    try {
      parser.parse(is, ch, metadata, pc);
    } catch (TikaException ex) {
      logger.warn(String.format(
              "%s: Unpacker failed",
              info.getPath()
      ), ex);
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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
     * Tests that a file with characters not in the ISO 8859-1
     *  range is correctly handled
     */
    @Test
    public void testMp3ParsingID3i18n() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testMP3i18n.mp3");
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }

       assertEquals("audio/mpeg", 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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
     * Tests that a file with both lyrics and
     *  ID3v2 tags gets both extracted correctly
     */
    @Test
    public void testMp3ParsingLyrics() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        // Note - our test file has a lyrics tag, but lacks any
        //  lyrics in the tags, so we can't test that bit
        // TODO Find a better sample file
       
        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3lyrics.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
     * This test will check for the complicated set of ID3v2.4
     *  tags.
     */
    @Test
    public void testTIKA424() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/test2.mp3");
       if(stream == null) {
          // You haven't downloaded the file
          // Skip the test
          return;
       }
      
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }

       assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
     * In this case, it is a file with JPEG data in the ID3, which
     *  is trunacted before the end of the JPEG bit of the ID3 frame.
     */
    @Test
    public void testTIKA474() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testMP3truncated.mp3");
      
      
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }

       // Check we could get the headers from the start
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.