Package org.apache.tika.parser

Examples of org.apache.tika.parser.Parser

33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
*/
public class Bzip2ParserTest extends AbstractPkgTest {

    @Test
    public void testBzip2Parsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = Bzip2ParserTest.class.getResourceAsStream(
                "/test-documents/test-documents.tbz2");
        try {
            parser.parse(stream, handler, metadata, recursingContext);
        } finally {
            stream.close();
        }

        assertEquals("application/x-bzip2", 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.tbz2");
       try {
           parser.parse(stream, handler, metadata, trackingContext);
       } finally {
           stream.close();
       }
      
       // Should find a single entry, for the (compressed) tar file
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
*/
public class GzipParserTest extends AbstractPkgTest {

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

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

        assertEquals("application/x-gzip", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
     * 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.tgz");
       try {
           parser.parse(stream, handler, metadata, trackingContext);
       } finally {
           stream.close();
       }
      
       // Should find a single entry, for the (compressed) tar file
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
       assertEquals("test-documents/", new String(tracker.lastSeenStart, 0, 15, "ASCII"));
    }
   
    @Test
    public void testSvgzParsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

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

        assertEquals("application/x-gzip", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
*/
public class ZipParserTest extends AbstractPkgTest {

    @Test
    public void testZipParsing() 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.zip");
        try {
            parser.parse(stream, handler, metadata, recursingContext);
        } finally {
            stream.close();
        }

        assertEquals("application/zip", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
     * 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.zip");
       try {
           parser.parse(stream, handler, metadata, trackingContext);
       } finally {
           stream.close();
       }
      
       // Should have found all 9 documents
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
        assertContains("<div class=\"embedded\" id=\"test1.txt\" />", xml);
        assertContains("<div class=\"embedded\" id=\"test2.txt\" />", xml);

        // Also make sure EMBEDDED_RELATIONSHIP_ID was
        // passed when parsing the embedded docs:
        Parser parser = new AutoDetectParser();
        ParseContext context = new ParseContext();
        context.set(Parser.class, parser);
        GatherRelIDsDocumentExtractor relIDs = new GatherRelIDsDocumentExtractor();
        context.set(EmbeddedDocumentExtractor.class, relIDs);
        InputStream input = getResourceAsStream("/test-documents/testEmbedded.zip");
        try {
          parser.parse(input,
                       new BodyContentHandler(),
                       new Metadata(),
                       context);
        } 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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
            // Embed the metadata into a copy of the original output stream
            embedder.embed(metadataToEmbed, sourceInputStream, tempFileOutputStream, null);

            ParseContext context = new ParseContext();
            Parser parser = getParser();
            context.set(Parser.class, parser);

            // Setup the extracting content handler
            ByteArrayOutputStream result = new ByteArrayOutputStream();
            OutputStreamWriter outputWriter = new OutputStreamWriter(result,DEFAULT_CHARSET);
            ContentHandler handler = new BodyContentHandler(outputWriter);

            // Create a new metadata object to read the new metadata into
            Metadata embeddedMetadata = new Metadata();

            // Setup a re-read of the now embeded temp file
            FileInputStream embeddedFileInputStream = new FileInputStream(tempOutputFile);

            parser.parse(embeddedFileInputStream, handler, embeddedMetadata,
                    context);

            tmp.dispose();

            String outputString = null;
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.