Examples of org.apache.tika.Tika

org.apache.tika.Tika
Facade class for accessing Tika functionality. This class hides much of the underlying complexity of the lower level Tika classes and provides simple methods for many common parsing and type detection operations. @since Apache Tika 0.5 @see Parser @see Detector

        out.println("    ports you specify as one or more arguments.");
        out.println();
    }


    private void version() {
        System.out.println(new Tika().toString());
    }

View Full Code Here

    }


    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
                .contains("Title : Tilte with UTF-8 chars öäå"));

View Full Code Here

    }


    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(TikaCoreProperties.TITLE));

View Full Code Here

     * Test case for TIKA-210
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-210">TIKA-210</a>
     */
    public void testCharactersDirectlyUnderBodyElement() throws Exception {
        String test = "<html><body>test</body></html>";
        String content = new Tika().parseToString(
                new ByteArrayInputStream(test.getBytes("UTF-8")));
        assertEquals("test", content);
    }

View Full Code Here

     * @see <a href="https://issues.apache.org/jira/browse/TIKA-268">TIKA-268</a>
     */
    public void testWhitespaceBetweenTableCells() throws Exception {
        String test =
            "<html><body><table><tr><td>a</td><td>b</td></table></body></html>";
        String content = new Tika().parseToString(
                new ByteArrayInputStream(test.getBytes("UTF-8")));
        assertTrue(content.contains("a"));
        assertTrue(content.contains("b"));
        assertFalse(content.contains("ab"));
    }

View Full Code Here

     *
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-343">TIKA-343</a>
     */
    public void testLineBreak() throws Exception {
        String test = "<html><body><div>foo<br>bar</div>baz</body></html>";
        String text = new Tika().parseToString(
                new ByteArrayInputStream(test.getBytes("US-ASCII")));
        String[] parts = text.trim().split("\\s+");
        assertEquals(3, parts.length);
        assertEquals("foo", parts[0]);
        assertEquals("bar", parts[1]);

View Full Code Here


    /**
     * Test case for TIKA-434 - Pushback buffer overflow in TagSoup
     */
    public void testPushback() throws IOException, TikaException {
        String content = new Tika().parseToString(
                HtmlParserTest.class.getResourceAsStream("/test-documents/tika434.html"), new Metadata());




        assertNotNull(content);
    }

View Full Code Here

        File file = getResourceAsFile("/test-documents/testRTFJapanese.rtf");
        Metadata metadata = new Metadata();
        InputStream stream = TikaInputStream.get(file, metadata);


        // Test w/ default limit:
        Tika localTika = new Tika();
        String content = localTika.parseToString(stream, metadata);
        // parseToString closes for convenience:
        //stream.close();
        assertTrue(content.length() > 500);


        // Test setting max length on the instance:
        localTika.setMaxStringLength(200);
        stream = TikaInputStream.get(file, metadata);
        content = localTika.parseToString(stream, metadata);
        
        // parseToString closes for convenience:
        //stream.close();
        assertTrue(content.length() <= 200);
        
        // Test setting max length per-call:
        stream = TikaInputStream.get(file, metadata);
        content = localTika.parseToString(stream, metadata, 100);
        // parseToString closes for convenience:
        //stream.close();
        assertTrue(content.length() <= 100);
    }

View Full Code Here

    private static final File f = new File("/a/b/c/x.pdf");


    protected void setUp() throws Exception{
        TikaConfig config = TikaConfig.getDefaultConfig();
        repo = config.getMimeRepository();
        tika = new Tika(config);
        u = new URL("http://mydomain.com/x.pdf?x=y");
    }

View Full Code Here

     * @throws MimeTypeException if the type can't be detected
     * @throws IOException if the file can't be read
     */
    public MimeType getMimeType(File file)
            throws MimeTypeException, IOException {
        return forName(new Tika(this).detect(file));
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.tika.Tika

ch.entwine.weblounge.kernel.site.SiteServlet

com.digitalpebble.storm.crawler.bolt.ParserBolt

com.gentics.cr.file.ResolvableFileBean

com.gitblit.servlet.RawServlet

com.ikanow.infinit.e.harvest.extraction.document.file.FileHarvester

com.ikanow.infinit.e.harvest.extraction.text.boilerpipe.TextExtractorBoilerpipe

com.ikanow.infinit.e.harvest.extraction.text.legacy.TextExtractorTika

com.javajing.webjar.FileUploadServlet

com.trsst.Command

com.trsst.ui.AppServlet

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.