Examples of parseToString()


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

        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

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

        //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.parseToString()

        // 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

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

        // Simple text extrction
        byte[] data = "Hello, World!".getBytes("UTF-8");
        Assert.assertEquals(
                "Hello, World!",
                tika.parseToString(new ByteArrayInputStream(data)).trim());
    }

}
View Full Code Here

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

        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

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

        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

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

        //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.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

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

     */
    public String parseToStringExample() throws IOException, SAXException, TikaException {
        InputStream stream = ParsingExample.class.getResourceAsStream("test.doc");
        Tika tika = new Tika();
        try {
            return tika.parseToString(stream);
        } finally {
            stream.close();
        }
    }

View Full Code Here

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

       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
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.