Examples of Tika


Examples of org.apache.tika.Tika

    }

    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

Examples of org.apache.tika.Tika

    }

    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));
View Full Code Here

Examples of org.apache.tika.Tika

     * 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

Examples of org.apache.tika.Tika

     * @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

Examples of org.apache.tika.Tika

     *
     * @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

Examples of org.apache.tika.Tika

    public void testFLV() throws Exception {
        String path = "/test-documents/testFLV.flv";
        Metadata metadata = new Metadata();

        String content = new Tika().parseToString(
                FLVParserTest.class.getResourceAsStream(path), metadata);

        assertEquals("", content);
        assertEquals("video/x-flv", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("true", metadata.get("hasVideo"));
View Full Code Here

Examples of org.apache.tika.Tika

    } catch (IOException e) {
      throw new RuntimeException(e);
    }

    logger.info("Starting Tikaserver "+properties.getProperty("tikaserver.version"));
    logger.info("Starting Tika Server " + new Tika().toString());

    try {
      Options options = getOptions();

      CommandLineParser cliParser = new GnuParser();
View Full Code Here

Examples of org.apache.tika.Tika

    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

Examples of org.apache.tika.Tika

        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

Examples of org.apache.tika.Tika

    }

    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
TOP
Copyright © 2018 www.massapi.com. 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.