Package org.apache.tika.metadata

Examples of org.apache.tika.metadata.Metadata

104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
     *  details from id3v2
     */
    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);
        } 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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
    }

    private void decompress(InputStream stream, XHTMLContentHandler xhtml)
            throws IOException, SAXException, TikaException {
        try {
            Metadata entrydata = new Metadata();
            String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
            if (name != null) {
                if (name.endsWith(".tbz")) {
                    name = name.substring(0, name.length() - 4) + ".tar";
                } else if (name.endsWith(".tbz2")) {
                    name = name.substring(0, name.length() - 5) + ".tar";
                } else if (name.endsWith(".bz")) {
                    name = name.substring(0, name.length() - 3);
                } else if (name.endsWith(".bz2")) {
                    name = name.substring(0, name.length() - 4);
                } else if (name.length() > 0) {
                    name = GzipUtils.getUncompressedFilename(name);
                }
                entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
            }
            // Use the delegate parser to parse the compressed document
            parser.parse(
                    new CloseShieldInputStream(stream),
                    new EmbeddedContentHandler(
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
165
166
167
        try {
            ArchiveEntry entry = archive.getNextEntry();
            while (entry != null) {
                if (!entry.isDirectory()) {
                    xhtml.startElement("div", "class", "package-entry");
                    Metadata entrydata = new Metadata();
                    String name = entry.getName();
                    if (name != null && name.length() > 0) {
                        entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
                        xhtml.element("h1", name);
                    }
                    try {
                        // Use the delegate parser to parse this entry
                        parser.parse(
View Full Code Here
127
128
129
130
131
132
133
     * @param stream the document stream
     * @return detected media type
     * @throws IOException if the stream can not be read
     */
    public String detect(InputStream stream) throws IOException {
        return detect(stream, new Metadata());
    }
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
     * @param url the URL of the resource
     * @return detected media type
     * @throws IOException if the resource can not be read
     */
    public String detect(URL url) throws IOException {
        Metadata metadata = new Metadata();
        InputStream stream = MetadataHelper.getInputStream(url, metadata);
        try {
            return detect(stream, metadata);
        } finally {
            stream.close();
View Full Code Here
178
179
180
181
182
183
184
185
186
187
188
189
     *
     * @param name the file name of the document
     * @return detected media type
     */
    public String detect(String name) {
        Metadata metadata = new Metadata();
        metadata.set(Metadata.RESOURCE_NAME_KEY, name);
        try {
            return detect(null, metadata);
        } catch (IOException e) {
            throw new IllegalStateException("Unexpected IOException", e);
        }
View Full Code Here
212
213
214
215
216
217
218
     * @param stream the document to be parsed
     * @return extracted text content
     * @throws IOException if the document can not be read or parsed
     */
    public Reader parse(InputStream stream) throws IOException {
        return parse(stream, new Metadata());
    }
View Full Code Here
235
236
237
238
239
240
241
242
243
     * @param url the URL of the resource to be parsed
     * @return extracted text content
     * @throws IOException if the resource can not be read or parsed
     */
    public Reader parse(URL url) throws IOException {
        Metadata metadata = new Metadata();
        InputStream stream = MetadataHelper.getInputStream(url, metadata);
        return parse(stream, metadata);
    }
View Full Code Here
291
292
293
294
295
296
297
     * @throws IOException if the document can not be read
     * @throws TikaException if the document can not be parsed
     */
    public String parseToString(InputStream stream)
            throws IOException, TikaException {
        return parseToString(stream, new Metadata());
    }
View Full Code Here
326
327
328
329
330
331
332
333
334
     * @return extracted text content
     * @throws IOException if the resource can not be read
     * @throws TikaException if the resource can not be parsed
     */
    public String parseToString(URL url) throws IOException, TikaException {
        Metadata metadata = new Metadata();
        InputStream stream = MetadataHelper.getInputStream(url, metadata);
        return parseToString(stream, metadata);
    }
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.