Examples of org.apache.tika.sax.BodyContentHandler

org.apache.tika.sax.BodyContentHandler
Content handler decorator that only passes everything inside the XHTML <body/> tag to the underlying handler. Note that the <body/> tag itself is not passed on.

        String test =
            "<html><head><title>\u017d</title></head><body></body></html>";
        Metadata metadata = new Metadata();
        new HtmlParser().parse (
                new ByteArrayInputStream(test.getBytes("UTF-8")),
                new BodyContentHandler(),  metadata, new ParseContext());
        assertEquals("\u017d", metadata.get(TikaCoreProperties.TITLE));
    }

View Full Code Here

     *  details from id3v2
     */
    @Test
    public void testMp3ParsingID3v1v2() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();


        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v1_v2.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }


        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE));
        assertEquals("Test Artist", metadata.get(TikaCoreProperties.CREATOR));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));


        String content = handler.toString();
        assertTrue(content.contains("Test Title"));
        assertTrue(content.contains("Test Artist"));
        assertTrue(content.contains("Test Album"));
        assertTrue(content.contains("2008"));
        assertTrue(content.contains("Test Comment"));

View Full Code Here

     *  set of information out.
     */
    @Test
    public void testMp3ParsingID3v24() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();


        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3id3v24.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }


        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE));
        assertEquals("Test Artist", metadata.get(TikaCoreProperties.CREATOR));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));


        String content = handler.toString();
        assertTrue(content.contains("Test Title"));
        assertTrue(content.contains("Test Artist"));
        assertTrue(content.contains("Test Album"));
        assertTrue(content.contains("2008"));
        assertTrue(content.contains("Test Comment"));

View Full Code Here

     *  range is correctly handled
     */
    @Test
    public void testMp3ParsingID3i18n() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();


       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testMP3i18n.mp3");
       try {

View Full Code Here

     *  ID3v2 tags gets both extracted correctly
     */
    @Test
    public void testMp3ParsingLyrics() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();


        // Note - our test file has a lyrics tag, but lacks any
        //  lyrics in the tags, so we can't test that bit
        // TODO Find a better sample file
        
        InputStream stream = Mp3ParserTest.class.getResourceAsStream(
                "/test-documents/testMP3lyrics.mp3");
        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }


        assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE));
        assertEquals("Test Artist", metadata.get(TikaCoreProperties.CREATOR));
        assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));


        String content = handler.toString();
        assertTrue(content.contains("Test Title"));
        assertTrue(content.contains("Test Artist"));
        assertTrue(content.contains("Test Album"));
        assertTrue(content.contains("2008"));
        assertTrue(content.contains("Test Comment"));

View Full Code Here

public class ArParserTest extends AbstractPkgTest {
    @Test
  public void testArParsing() throws Exception {
    Parser parser = new AutoDetectParser();


    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();


    InputStream stream = ArParserTest.class
        .getResourceAsStream("/test-documents/testARofText.ar");
    try {
      parser.parse(stream, handler, metadata, recursingContext);
    } finally {
      stream.close();
    }


    assertEquals("application/x-archive",
        metadata.get(Metadata.CONTENT_TYPE));
    String content = handler.toString();
    assertTrue(content.contains("testTXT.txt"));
    assertTrue(content.contains("Test d'indexation de Txt"));
    assertTrue(content.contains("http://www.apache.org"));


    stream = ArParserTest.class
        .getResourceAsStream("/test-documents/testARofSND.ar");
    try {
      parser.parse(stream, handler, metadata, recursingContext);
    } finally {
      stream.close();
    }


    assertEquals("application/x-archive",
        metadata.get(Metadata.CONTENT_TYPE));
    content = handler.toString();
    assertTrue(content.contains("testAU.au"));
  }

View Full Code Here

     *  tags.
     */
    @Test
    public void testTIKA424() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();


       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/test2.mp3");
       if(stream == null) {
          // You haven't downloaded the file
          // Skip the test
          return;
       }
       
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }


       assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
       assertEquals("Plus loin vers l'ouest", metadata.get(TikaCoreProperties.TITLE));
       assertEquals("Merzhin", metadata.get(TikaCoreProperties.CREATOR));
       assertEquals("Merzhin", metadata.get(Metadata.AUTHOR));


       String content = handler.toString();
       assertTrue(content.contains("Plus loin vers l'ouest"));
       
       assertEquals("MPEG 3 Layer III Version 1", metadata.get("version"));
       assertEquals("44100", metadata.get("samplerate"));
       assertEquals("2", metadata.get("channels"));

View Full Code Here

   * embedded entries.
   */
    @Test
  public void testEmbedded() throws Exception {
    Parser parser = new AutoDetectParser(); // Should auto-detect!
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();


    InputStream stream = ArParserTest.class
        .getResourceAsStream("/test-documents/testARofText.ar");
    try {

View Full Code Here

     *  is trunacted before the end of the JPEG bit of the ID3 frame.
     */
    @Test
    public void testTIKA474() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();


       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testMP3truncated.mp3");
       
       
       try {
           parser.parse(stream, handler, metadata, new ParseContext());
       } finally {
           stream.close();
       }


       // Check we could get the headers from the start
       assertEquals("audio/mpeg", metadata.get(Metadata.CONTENT_TYPE));
       assertEquals("Girl you have no faith in medicine", metadata.get(TikaCoreProperties.TITLE));
       assertEquals("The White Stripes", metadata.get(TikaCoreProperties.CREATOR));
       assertEquals("The White Stripes", metadata.get(Metadata.AUTHOR));


       String content = handler.toString();
       assertTrue(content.contains("Girl you have no faith in medicine"));
       assertTrue(content.contains("The White Stripes"));
       assertTrue(content.contains("Elephant"));
       assertTrue(content.contains("2003"));

View Full Code Here


    // TIKA-1024
    @Test
    public void testNakedUTF16BOM() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();


       InputStream stream = Mp3ParserTest.class.getResourceAsStream(
               "/test-documents/testNakedUTF16BOM.mp3");

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.tika.sax.BodyContentHandler

com.nidhinova.tika.server.TikaService

com.tamingtext.tika.TikaTest

cx.fbn.nevernote.threads.IndexRunner

org.apache.droids.tika.TikaDocumentParser

org.apache.oodt.cas.protocol.imaps.ImapsProtocol

org.apache.stanbol.enhancer.engines.tika.TikaEngine

org.apache.tika.bundle.BundleIT

org.apache.tika.embedder.ExternalEmbedderTest

org.apache.tika.example.ContentHandlerExample

org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor

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.