Examples of Tika

com.dotcms.repackage.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

Examples of org.apache.tika.Tika

    /**
     * Test case for TIKA-434 - Pushback buffer overflow in TagSoup
     */
    @Test
    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

Examples of org.apache.tika.Tika

    }


    // TIKA-1011
    @Test
    public void testUserDefinedCharset() throws Exception {
        String content = new Tika().parseToString(
                HtmlParserTest.class.getResourceAsStream("/test-documents/testUserDefinedCharset.mhtml"), new Metadata());
        assertNotNull(content);
    }

View Full Code Here

Examples of org.apache.tika.Tika

    }
    
    //TIKA-1001
    @Test
    public void testNoisyMetaCharsetHeaders() throws Exception {
       Tika tika = new Tika();
       String hit = "\u0623\u0639\u0631\u0628";


       for (int i = 1; i <=4; i++){
          String fileName = "/test-documents/testHTMLNoisyMetaEncoding_"+i+".html";
          String content = tika.parseToString(
                HtmlParserTest.class.getResourceAsStream(fileName));
          assertTrue("testing: " +fileName, content.contains(hit));
       }
    }

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

     *
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-346">TIKA-346</a>
     */
    @Test
    public void testUnsupportedZipCompressionMethod() throws Exception {
        String content = new Tika().parseToString(
                ZipParserTest.class.getResourceAsStream(
                        "/test-documents/moby.zip"));
        assertTrue(content.contains("README"));
    }

View Full Code Here

Examples of org.apache.tika.Tika

public class OOXMLContainerExtractionTest extends AbstractPOIContainerExtractionTest {
    private ContainerExtractor extractor;
    
    @Before
    public void setUp() {
        Tika tika = new Tika();
        extractor = new ParserContainerExtractor(
                tika.getParser(), tika.getDetector());
    }

View Full Code Here

Examples of org.apache.tika.Tika


    @Before
    public 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


  /* our log stream */
  private static final Logger LOG = LoggerFactory.getLogger(MimeUtil.class.getName());


  public MimeUtil(Configuration conf) {
    tika = new Tika();
    ObjectCache objectCache = ObjectCache.get(conf);
    MimeTypes mimeTypez = (MimeTypes) objectCache.getObject(MimeTypes.class
        .getName());
    if (mimeTypez == null) {
      try {

View Full Code Here

Examples of org.apache.tika.Tika

        URL aURL = new URL(newurl);
        String base = aURL.toString();
        int i = fname.lastIndexOf('.');
        if (i != -1) {
          // Trying to resolve the Mime-Type
          Tika tika = new Tika();
          String contentType = tika.detect(fname);
          try {
            Metadata metadata = new Metadata();
            metadata.set(Response.CONTENT_LENGTH, Long.toString(entry.getSize()));
            metadata.set(Response.CONTENT_TYPE, contentType);
            Content content = new Content(newurl, base, b, contentType, metadata, this.conf);

View Full Code Here

Examples of org.apache.tika.Tika

    this.base = url.toString();
    this.file = file;
    this.conf = conf;
    
    MIME = new MimeUtil(conf);
    tika = new Tika();


    if (!"file".equals(url.getProtocol()))
      throw new FileException("Not a file url:" + url);


    if (File.LOG.isTraceEnabled()) {

View Full Code Here

0 1 2 3 4 5

TOP

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.