Package org.apache.tika.parser

Examples of org.apache.tika.parser.AutoDetectParser

316
317
318
319
320
321
322
323
324
325
326
        InputStream input = ODFParserTest.class.getResourceAsStream(
            "/test-documents/testFooter.ods");
        try {
            Metadata metadata = new Metadata();
            ContentHandler handler = new BodyContentHandler();
            new AutoDetectParser().parse(input, handler, metadata);
 
            String content = handler.toString();
            assertContains("Here is a footer in the center area", content);
        } finally {
            input.close();
View Full Code Here
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
65
66
67
68
69
70
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
     * Test that we can extract information from
     *  a M4A MP4 Audio file
     */
    @Test
    public void testMP4ParsingAudio() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = MP4ParserTest.class.getResourceAsStream(
                "/test-documents/testMP4.m4a");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        // Check core properties
        assertEquals("audio/mp4", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE));
        assertEquals("Test Artist", metadata.get(TikaCoreProperties.CREATOR));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));
        assertEquals("2012-01-28T18:39:18Z", metadata.get(TikaCoreProperties.CREATED));
        assertEquals("2012-01-28T18:39:18Z", metadata.get(Metadata.CREATION_DATE));
        assertEquals("2012-01-28T18:40:25Z", metadata.get(TikaCoreProperties.MODIFIED));
        assertEquals("2012-01-28T18:40:25Z", metadata.get(Metadata.DATE));

        // Check the textual contents
        String content = handler.toString();
        assertTrue(content.contains("Test Title"));
        assertTrue(content.contains("Test Artist"));
        assertTrue(content.contains("Test Album"));
        assertTrue(content.contains("2008"));
        assertTrue(content.contains("Test Comment"));
        assertTrue(content.contains("Test Genre"));
       
        // Check XMPDM-typed audio properties
        assertEquals("Test Album", metadata.get(XMPDM.ALBUM));
        assertEquals("Test Artist", metadata.get(XMPDM.ARTIST));
        assertEquals("Test Composer", metadata.get(XMPDM.COMPOSER));
        assertEquals("2008", metadata.get(XMPDM.RELEASE_DATE));
        assertEquals("Test Genre", metadata.get(XMPDM.GENRE));
        assertEquals("Test Comments", metadata.get(XMPDM.LOG_COMMENT.getName()));
        assertEquals("1", metadata.get(XMPDM.TRACK_NUMBER));
       
        assertEquals("44100", metadata.get(XMPDM.AUDIO_SAMPLE_RATE));
        //assertEquals("Stereo", metadata.get(XMPDM.AUDIO_CHANNEL_TYPE)); // TODO Extract
        assertEquals("M4A", metadata.get(XMPDM.AUDIO_COMPRESSOR));
       
       
        // Check again by file, rather than stream
        TikaInputStream tstream = TikaInputStream.get(
              MP4ParserTest.class.getResourceAsStream("/test-documents/testMP4.m4a"));
        tstream.getFile();
        try {
           parser.parse(tstream, handler, metadata, new ParseContext());
        } finally {
           tstream.close();
        }
    }
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
     *  shouldn't break on these files either (TIKA-826) 
     */
    @Test
    public void testExcelXLSB() throws Exception {
       Detector detector = new DefaultDetector();
       AutoDetectParser parser = new AutoDetectParser();
      
       InputStream input = ExcelParserTest.class.getResourceAsStream(
             "/test-documents/testEXCEL.xlsb");
       Metadata m = new Metadata();
       m.add(Metadata.RESOURCE_NAME_KEY, "excel.xlsb");
      
       // Should be detected correctly
       MediaType type = null;
       try {
          type = detector.detect(input, m);
          assertEquals("application/vnd.ms-excel.sheet.binary.macroenabled.12", type.toString());
       } finally {
          input.close();
       }
      
       // OfficeParser won't handle it
       assertEquals(false, (new OfficeParser()).getSupportedTypes(new ParseContext()).contains(type));
      
       // OOXMLParser won't handle it
       assertEquals(false, (new OOXMLParser()).getSupportedTypes(new ParseContext()).contains(type));
      
       // AutoDetectParser doesn't break on it
       input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL.xlsb");

       try {
          ContentHandler handler = new BodyContentHandler(-1);
          ParseContext context = new ParseContext();
          context.set(Locale.class, Locale.US);
          parser.parse(input, handler, m, context);

          String content = handler.toString();
          assertEquals("", content);
       } finally {
          input.close();
View Full Code Here
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
     *  but we shouldn't break on these files either (TIKA-976) 
     */
    @Test
    public void testExcel95() throws Exception {
       Detector detector = new DefaultDetector();
       AutoDetectParser parser = new AutoDetectParser();
      
       InputStream input = ExcelParserTest.class.getResourceAsStream(
             "/test-documents/testEXCEL_95.xls");
       Metadata m = new Metadata();
       m.add(Metadata.RESOURCE_NAME_KEY, "excel_95.xls");
      
       // Should be detected correctly
       MediaType type = null;
       try {
          type = detector.detect(input, m);
          assertEquals("application/vnd.ms-excel", type.toString());
       } finally {
          input.close();
       }
      
       // OfficeParser will claim to handle it
       assertEquals(true, (new OfficeParser()).getSupportedTypes(new ParseContext()).contains(type));
      
       // OOXMLParser won't handle it
       assertEquals(false, (new OOXMLParser()).getSupportedTypes(new ParseContext()).contains(type));
      
       // AutoDetectParser doesn't break on it
       input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL_95.xls");

       try {
          ContentHandler handler = new BodyContentHandler(-1);
          ParseContext context = new ParseContext();
          context.set(Locale.class, Locale.US);
          parser.parse(input, handler, m, context);

          String content = handler.toString();
          assertEquals("", content);
       } finally {
          input.close();
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
    return GREETING;
  }

  @SuppressWarnings("serial")
  public static AutoDetectParser createParser() {
    final AutoDetectParser parser = new AutoDetectParser();

    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);

    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);
      }

      public void parse(InputStream inputStream, ContentHandler contentHandler, Metadata metadata, ParseContext parseContext) {
        throw new WebApplicationException(Response.Status.UNSUPPORTED_MEDIA_TYPE);
      }
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
  @Produces("text/plain")
  public StreamingOutput getText(final InputStream is, @Context HttpHeaders httpHeaders, @Context final UriInfo info) {
    return produceText(is, httpHeaders.getRequestHeaders(), info);
  }
  public StreamingOutput produceText(final InputStream is, MultivaluedMap<String, String> httpHeaders, final UriInfo info) {   
    final AutoDetectParser parser = createParser();
    final Metadata metadata = new Metadata();

    fillMetadata(parser, metadata, httpHeaders);

    logRequest(logger, info, metadata);

    return new StreamingOutput() {
      public void write(OutputStream outputStream) throws IOException, WebApplicationException {
        Writer writer = new OutputStreamWriter(outputStream, "UTF-8");

        BodyContentHandler body = new BodyContentHandler(new RichTextContentHandler(writer));

        TikaInputStream tis = TikaInputStream.get(is);

        try {
            parser.parse(tis, body, metadata);
        } catch (SAXException e) {
          throw new WebApplicationException(e);
        } catch (EncryptedDocumentException e) {
          logger.warn(String.format(
                  "%s: Encrypted document",
View Full Code Here
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
295
296
297
298
    return produceOutput(is, httpHeaders.getRequestHeaders(), info, "xml");
  }
 
  private StreamingOutput produceOutput(final InputStream is, final MultivaluedMap<String, String> httpHeaders,
        final UriInfo info, final String format) {
    final AutoDetectParser parser = createParser();
    final Metadata metadata = new Metadata();

    fillMetadata(parser, metadata, httpHeaders);

    logRequest(logger, info, metadata);

    return new StreamingOutput() {
      public void write(OutputStream outputStream)
        throws IOException, WebApplicationException {
        Writer writer = new OutputStreamWriter(outputStream, "UTF-8");
        ContentHandler content;

        try {
          SAXTransformerFactory factory = (SAXTransformerFactory)SAXTransformerFactory.newInstance( );
          TransformerHandler handler = factory.newTransformerHandler( );
          handler.getTransformer().setOutputProperty(OutputKeys.METHOD, format);
          handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
          handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "UTF-8");
          handler.setResult(new StreamResult(writer));
          content = new ExpandedTitleContentHandler( handler );
        }
        catch ( TransformerConfigurationException e ) {
          throw new WebApplicationException( e );
        }

        TikaInputStream tis = TikaInputStream.get(is);

        try {
          parser.parse(tis, content, metadata);
        }
        catch (SAXException e) {
          throw new WebApplicationException(e);
        }
        catch (EncryptedDocumentException e) {
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
    /**
     * Test that with only ID3v1 tags, we get some information out  
     */
    @Test
    public void testMp3ParsingID3v1() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v1.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
     * Test that with only ID3v2 tags, we get the full
     *  set of information out.
     */
    @Test
    public void testMp3ParsingID3v2() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v2.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        // Check core properties
View Full Code Here
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
     * Test that with both id3v2 and id3v1, we prefer the
     *  details from id3v2
     */
    @Test
    public void testMp3ParsingID3v1v2() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v1_v2.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
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.