Package org.apache.tika.parser

Examples of org.apache.tika.parser.AutoDetectParser

143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
    public void testPowerPoint() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testPPT.pptx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testPPT.pptx");
        ContentHandler handler = new BodyContentHandler();

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

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
    public void testWord() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testWORD.docx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testWORD.docx");
        ContentHandler handler = new BodyContentHandler();

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

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
    public void testProtectedExcel() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/protected.xlsx");

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

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

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
303
304
305
306
307
308
309
310
311
312
313
    private boolean prettyPrint;
   
    public TikaCLI() throws Exception {
        context = new ParseContext();
        detector = new DefaultDetector();
        parser = new AutoDetectParser(detector);
        context.set(Parser.class, parser);
        context.set(PasswordProvider.class, new PasswordProvider() {
            public String getPassword(Metadata metadata) {
                return password;
            }
View Full Code Here
604
605
606
607
608
609
610
611
612
613
614
615
616
    /**
     * Prints all the known media types, aliases and matching parser classes.
     */
    private void displaySupportedTypes() {
        AutoDetectParser parser = new AutoDetectParser();
        MediaTypeRegistry registry = parser.getMediaTypeRegistry();
        Map<MediaType, Parser> parsers = parser.getParsers();

        for (MediaType type : registry.getTypes()) {
            System.out.println(type);
            for (MediaType alias : registry.getAliases(type)) {
                System.out.println("  alias:     " + alias);
View Full Code Here
83
84
85
86
87
88
89
            this.metadata = metadata;
        }
    }

    protected XMLResult getXML(String filePath) throws Exception {
        return getXML(getResourceAsStream("/test-documents/" + filePath), new AutoDetectParser(), new Metadata());
    }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
*/
public class AdobeFontMetricParserTest {
 
    @Test
    public void testAdobeFontMetricParsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();
        TikaInputStream stream = TikaInputStream.get(
                AdobeFontMetricParserTest.class.getResource(
                        "/test-documents/testAFM.afm"));

        try {
            parser.parse(stream, handler, metadata, context);
        } finally {
            stream.close();
        }

        assertEquals("application/x-font-adobe-metric", metadata.get(Metadata.CONTENT_TYPE));
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
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.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.