Examples of org.apache.tika.Tika.parseToString()

org.apache.tika.Tika.parseToString()
Parses the given document and returns the extracted text content. The given input stream is closed by this method.
To avoid unpredictable excess memory use, the returned string contains only up to {@link #getMaxStringLength()} first characters extractedfrom the input document. Use the {@link #setMaxStringLength(int)}method to adjust this limitation. @param stream the document to be parsed @param metadata document metadata @return extracted text content @throws IOException if the document can not be read @throws TikaException if the document can not be parsed

  public String getText() {
    if (text == null || lastTextUpdate < getFile().lastModified()) {
      try {
        Tika tika = new Tika();
        tika.setMaxStringLength(-1);
        text = tika.parseToString(getFile()).replaceAll("\n\\s*\n+","\n\n");
      } catch (TikaException e) {
        text = "";
      } catch (IOException e) {
        text = "";
      } finally {

View Full Code Here

        // Simple type detection
        assertEquals("text/plain", tika.detect("test.txt"));
        assertEquals("application/pdf", tika.detect("test.pdf"));


        // Simple text extraction
        String xml = tika.parseToString(new File("pom.xml"));
        assertTrue(xml.contains("tika-bundle"));


        // Package extraction
        ContentHandler handler = new BodyContentHandler();

View Full Code Here

        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:

View Full Code Here

        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);

View Full Code Here

        //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

       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

        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:

View Full Code Here

        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);

View Full Code Here

        //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

            // extract met from prod using tika
            LOG.fine("Invoking tika extractor on file ["
                    + file.getAbsolutePath() + "]");
            Tika tika = new Tika();
            tika.parse(is, tikaMet); // extract metadata
            tikaMet.add("content", tika.parseToString(file)); // extract content


            LOG.fine("Number of captured tika metadata keys: ["
                    + tikaMet.names().length + "]");


            // copy tika met into oodt met

View Full Code Here

0 1 2

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.