Package org.apache.tika

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


    @Test
    public void testBundleSimpleText(BundleContext bc) throws Exception {
        Tika tika = new Tika();
       
        // Simple text extraction
        String xml = tika.parseToString(new File("pom.xml"));
        assertTrue(xml.contains("tika-bundle"));
    }
   
    @Ignore // TODO Fix this test
    @Test
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

        // 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

        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

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.