Package org.apache.tika.metadata

Examples of org.apache.tika.metadata.Metadata

32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
    public void testExcel() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testEXCEL.xlsx");

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

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

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            assertTrue(content.contains("Sample Excel Worksheet"));
            assertTrue(content.contains("Numbers and their Squares"));
            assertTrue(content.contains("9"));
            assertFalse(content.contains("9.0"));
View Full Code Here
153
154
155
156
157
158
159
160
161
162
        ContentHandler handler = new BodyContentHandler() {
            public void ignorableWhitespace(char[] ch, int off, int len) {
                // Ignore the whitespace added by XHTMLContentHandler
            }
        };
        Metadata metadata = new Metadata();
        parser.parse(new ByteArrayInputStream(input), handler, metadata, new ParseContext());
        assertEquals("text/plain", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals(msg, expected, handler.toString());
    }
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-335">TIKA-335</a>
     */
    public void testRetainIncomingLanguage() throws Exception {
        final String test = "Simple Content";

        Metadata metadata = new Metadata();
        metadata.set(Metadata.LANGUAGE, "en");

        parser.parse(
                new ByteArrayInputStream(test.getBytes("UTF-8")),
                new BodyContentHandler(),  metadata, new ParseContext());

        assertEquals("en", metadata.get(Metadata.LANGUAGE));
    }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    public void testExcelFormats() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testEXCEL-formats.xlsx");

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

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

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));

            String content = handler.toString();

            // Number #,##0.00
            assertTrue(content.contains("1,599.99"));
View Full Code Here
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
    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));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            assertTrue(content.contains("Sample Powerpoint Slide"));
            assertTrue(content.contains("Powerpoint X for Mac"));
        } finally {
            input.close();
View Full Code Here
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
    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));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            assertTrue(handler.toString().contains("Sample Word Document"));
        } finally {
            input.close();
        }
    }
View Full Code Here
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
    public void testParseAscii() throws Exception {
        String path = "/test-documents/testHTML.html";
        final StringWriter href = new StringWriter();
        final StringWriter name = new StringWriter();
        ContentHandler body = new BodyContentHandler();
        Metadata metadata = new Metadata();
        InputStream stream = HtmlParserTest.class.getResourceAsStream(path);
        try {
            ContentHandler link = new DefaultHandler() {
                @Override
                public void startElement(
                        String u, String l, String n, Attributes a)
                        throws SAXException {
                    if ("a".equals(l)) {
                        if (a.getValue("href") != null) {
                            href.append(a.getValue("href"));
                        } else if (a.getValue("name") != null) {
                            name.append(a.getValue("name"));
                        }
                    }
                }
            };
            new HtmlParser().parse(
                    stream, new TeeContentHandler(body, link),
                    metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals(
                "Title : Test Indexation Html", metadata.get(Metadata.TITLE));
        assertEquals("Tika Developers", metadata.get("Author"));
        assertEquals("5", metadata.get("refresh"));

        assertEquals("http://www.apache.org/", href.toString());
        assertEquals("test-anchor", name.toString());

        String content = body.toString();
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
                content.contains("Indexation du fichier"));
    }

    public void XtestParseUTF8() throws IOException, SAXException, TikaException {
        String path = "/test-documents/testXHTML_utf8.html";
        Metadata metadata = new Metadata();
        String content = new Tika().parseToString(
                HtmlParserTest.class.getResourceAsStream(path), metadata);

        assertTrue("Did not contain expected text:"
                + "Title : Tilte with UTF-8 chars öäå", content
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
                .contains("åäö"));
    }

    public void testXhtmlParsing() throws Exception {
        String path = "/test-documents/testXHTML.html";
        Metadata metadata = new Metadata();
        String content = new Tika().parseToString(
                HtmlParserTest.class.getResourceAsStream(path), metadata);

        assertEquals("application/xhtml+xml", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("XHTML test document", metadata.get(Metadata.TITLE));

        assertEquals("Tika Developers", metadata.get("Author"));
        assertEquals("5", metadata.get("refresh"));
        assertTrue(content.contains("ability of Apache Tika"));
        assertTrue(content.contains("extract content"));
        assertTrue(content.contains("an XHTML document"));
    }
View Full Code Here
120
121
122
123
124
125
126
127
    public void testParseEmpty() throws Exception {
        ContentHandler handler = new BodyContentHandler();
        new HtmlParser().parse(
                new ByteArrayInputStream(new byte[0]),
                handler,  new Metadata(), new ParseContext());
        assertEquals("", handler.toString());
    }
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.