Package org.apache.tika.metadata

Examples of org.apache.tika.metadata.Metadata

140
141
142
143
144
145
146
147
148
149
150
151
152
153
        "application/vnd.ms-excel");
        assertEquals(s1, s2);
        assertTrue("Text does not contain '" + expected + "'", s1
                .contains(expected));
        Parser parser = tc.getParser("application/vnd.ms-excel");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
    }
View Full Code Here
169
170
171
172
173
174
175
176
177
178
179
            throws TikaException, IOException {
        try {
            Parser parser = config.getParser(mimeType);
            StringWriter writer = new StringWriter();
            parser.parse(
                    stream, new WriteOutContentHandler(writer), new Metadata());
            return writer.toString();
        } catch (SAXException e) {
            throw new TikaException("Unexpected SAX error", e);
        }
    }
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
            type = TEXT;
        } else if (arg.equals("-m") || arg.equals("--metadata")) {
            type = METADATA;
        } else {
            pipeMode = false;
            metadata = new Metadata();
            if (arg.equals("-")) {
                parser.parse(
                        System.in, type.getContentHandler(),
                        metadata, context);
            } else {
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
            fail("Could not open stream from specified resource: "
                    + tp.resourceRealName);
        }

        try {
            Metadata metadata = new Metadata();
            metadata.set(Metadata.RESOURCE_NAME_KEY, tp.resourceStatedName);
            metadata.set(Metadata.CONTENT_TYPE, tp.statedType);
            ContentHandler handler = new BodyContentHandler();
            new AutoDetectParser().parse(input, handler, metadata);

            assertEquals("Bad content type: " + tp,
                    tp.realType, metadata.get(Metadata.CONTENT_TYPE));

            assertTrue("Expected content not found: " + tp,
                    handler.toString().contains(tp.expectedContentFragment));
        } finally {
            input.close();
View Full Code Here
178
179
180
181
182
183
184
185
186
187
188
     */
    public void testZipBombPrevention() throws Exception {
        InputStream tgz = AutoDetectParserTest.class.getResourceAsStream(
                "/test-documents/TIKA-216.tgz");
        try {
            Metadata metadata = new Metadata();
            ContentHandler handler = new BodyContentHandler(-1);
            new AutoDetectParser().parse(tgz, handler, metadata);
            fail("Zip bomb was not detected");
        } catch (TikaException e) {
            // expected
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
        String s1 = ParseUtils.getStringContent(file, tc);
        String s2 = ParseUtils.getStringContent(file, tc,
                "application/vnd.ms-powerpoint");
        assertEquals(s1, s2);
        Parser parser = tc.getParser("application/vnd.ms-powerpoint");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
    }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
103
104
105
        File file = getResourceAsFile("/test-documents/testWORD.doc");
        String s1 = ParseUtils.getStringContent(file, tc);
        String s2 = ParseUtils.getStringContent(file, tc, "application/msword");
        assertEquals(s1, s2);
        Parser parser = tc.getParser("application/msword");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
    }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
                "application/vnd.ms-excel");
        assertEquals(s1, s2);
        assertTrue("Text does not contain '" + expected + "'", s1
                .contains(expected));
        Parser parser = tc.getParser("application/vnd.ms-excel");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
    }
View Full Code Here
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
65
66
     * Test that with only ID3v1 tags, we get some information out  
     */
    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);
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(Metadata.TITLE));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));

        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("Rock"));
       
        assertEquals("MPEG 3 Layer III Version 1", metadata.get("version"));
        assertEquals("44100", metadata.get("samplerate"));
        assertEquals("2", metadata.get("channels"));
    }
View Full Code Here
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
100
     *  set of information out.
     */
    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);
        } finally {
            stream.close();
        }

        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(Metadata.TITLE));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));

        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("Rock"));
       
        assertEquals("MPEG 3 Layer III Version 1", metadata.get("version"));
        assertEquals("44100", metadata.get("samplerate"));
        assertEquals("2", metadata.get("channels"));
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.metadata.Metadata

  • bixo.parser.TikaCallableTest
  • com.tamingtext.tika.TikaTest
  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.any23.mime.TikaMIMETypeDetector
  • org.apache.chemistry.opencmis.client.parser.MetadataParserTika
  • org.apache.cxf.jaxrs.ext.search.tika.TikaContentExtractor
  • org.apache.jackrabbit.core.query.lucene.NodeIndexer
  • org.apache.jackrabbit.oak.plugins.index.lucene.LuceneIndexEditor
  • org.apache.jackrabbit.server.io.DefaultHandler
  • org.apache.jackrabbit.server.io.ImportContextImpl
    • 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.