Examples of ToXMLContentHandler

org.apache.jackrabbit.commons.xml.ToXmlContentHandler
Simple XML serializer. This content handler serializes the received SAX events as XML to a given {@link Writer} or {@link OutputStream}. The serialization assumes that the incoming SAX events are well-formed, i.e. that all elements are properly nested, that element and attribute names are valid and that no invalid XML characters are included. Assuming these preconditions are met, the result will be a well-formed XML stream.
This serializer does not have any special support for namespaces. For example, namespace prefixes are declared in the resulting XML stream if and only if the corresponding "xmlns" attributes are explicitly included in the {@link Attributes} instances passed in{@link #startElement(String,String,String,Attributes)} calls.
As a convenience this class inherits the {@link DefaultHandler} classinstead of just the {@link ContentHandler} interface. This makes iteasier to pass instances of this class to methods like {@link javax.xml.parsers.SAXParser#parse(String,DefaultHandler)} thatexpect a DefaultHandler instance instead of a ContentHandler.
org.apache.tika.sax.ToXMLContentHandler
SAX event handler that serializes the XML document to a character stream. The incoming SAX events are expected to be well-formed (properly nested, etc.) and to explicitly include namespace declaration attributes and corresponding namespace prefixes in element and attribute names. @since Apache Tika 0.10

Examples of org.apache.tika.sax.ToXMLContentHandler

    protected XMLResult getXML(InputStream input, Parser parser, Metadata metadata) throws Exception {
      ParseContext context = new ParseContext();
      context.set(Parser.class, parser);


      try {
          ContentHandler handler = new ToXMLContentHandler();
          parser.parse(input, handler, metadata, context);
          return new XMLResult(handler.toString(), metadata);
      } finally {
          input.close();
      }
  }

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler

        config.setExtractUniqueInlineImagesOnly(false);
        context.set(org.apache.tika.parser.pdf.PDFParserConfig.class, config);




        Metadata metadata = new Metadata();
        ContentHandler handler = new ToXMLContentHandler();
        String path = "/test-documents/testPDF_childAttachments.pdf";
        InputStream stream = null;
        try {
            stream = TikaInputStream.get(this.getClass().getResource(path));
            parser.parse(stream, handler, metadata, context);
        } finally {
            IOUtils.closeQuietly(stream);
        }


        String xml = handler.toString();
        //regular attachment
        assertContains("<div class=\"embedded\" id=\"Unit10.doc\" />", xml);
        //inline image
        assertContains("<img src=\"embedded:image1.tif\" alt=\"image1.tif\" />", xml);

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler


    /**
     * Example of extracting the contents as HTML, as a string.
     */
    public String parseToHTML() throws IOException, SAXException, TikaException {
        ContentHandler handler = new ToXMLContentHandler();
        
        InputStream stream = ContentHandlerExample.class.getResourceAsStream("test.doc");
        AutoDetectParser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        try {
            parser.parse(stream, handler, metadata);
            return handler.toString();
        } finally {
            stream.close();
        }
    }

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler

     * Example of extracting just the body as HTML, without the
     *  head part, as a string
     */
    public String parseBodyToHTML() throws IOException, SAXException, TikaException {
        ContentHandler handler = new BodyContentHandler(
                new ToXMLContentHandler());
        
        InputStream stream = ContentHandlerExample.class.getResourceAsStream("test.doc");
        AutoDetectParser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        try {

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler

        // Only get things under html -> body -> div (class=header)
        XPathParser xhtmlParser = new XPathParser("xhtml", XHTMLContentHandler.XHTML);
        Matcher divContentMatcher = xhtmlParser.parse(
                "/xhtml:html/xhtml:body/xhtml:div/descendant::node()");        
        ContentHandler handler = new MatchingContentHandler(
                new ToXMLContentHandler(), divContentMatcher);
        
        InputStream stream = ContentHandlerExample.class.getResourceAsStream("test2.doc");
        AutoDetectParser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        try {

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler

    if (System.getProperty("java.version").startsWith("1.5")) {
      return;
    }


    Parser parser = new EnviHeaderParser();
    ToXMLContentHandler handler = new ToXMLContentHandler();
    Metadata metadata = new Metadata();


    InputStream stream = EnviHeaderParser.class
        .getResourceAsStream("/test-documents/envi_test_header.hdr");
    assertNotNull("Test ENVI file not found", stream);
    try {
      parser.parse(stream, handler, metadata, new ParseContext());
    } finally {
      stream.close();
    }


    // Check content of test file
    String content = handler.toString();
        assertTrue(content.contains("<body><p>ENVI</p>"));
    assertTrue(content.contains("<p>samples = 2400</p>"));
    assertTrue(content.contains("<p>lines   = 2400</p>"));
    assertTrue(content.contains("<p>map info = {Sinusoidal, 1.5000, 1.5000, -10007091.3643, 5559289.2856, 4.6331271653e+02, 4.6331271653e+02, , units=Meters}</p>"));
    assertTrue(content.contains("content=\"application/envi.hdr\""));

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler


    @Test
    public void testParser() throws Exception {


        AutoDetectParser parser = new AutoDetectParser();
        ToXMLContentHandler handler = new ToXMLContentHandler();
        Metadata metadata = new Metadata();
        String path = "/test-documents/breidamerkurjokull_radar_profiles_2009.mat";


        InputStream stream = MatParser.class.getResourceAsStream(path);


        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }


        //Check Metadata
        assertEquals("PCWIN64", metadata.get("platform"));
        assertEquals("MATLAB 5.0 MAT-file", metadata.get("fileType"));
        assertEquals("IM", metadata.get("endian"));
        assertEquals("Thu Feb 21 15:52:49 2013", metadata.get("createdOn"));


        //Check Content
        String content = handler.toString();


        assertTrue(content.contains("<li>[1x909  double array]</li>"));
        assertTrue(content.contains("<p>c1:[1x1  struct array]</p>"));
        assertTrue(content.contains("<li>[1024x1  double array]</li>"));
        assertTrue(content.contains("<p>b1:[1x1  struct array]</p>"));

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler


    @Test
    public void testParserForText() throws Exception {


        Parser parser = new MatParser();
        ToXMLContentHandler handler = new ToXMLContentHandler();
        Metadata metadata = new Metadata();
        String path = "/test-documents/test_mat_text.mat";


        InputStream stream = MatParser.class.getResourceAsStream(path);


        try {
            parser.parse(stream, handler, metadata, new ParseContext());
        } finally {
            stream.close();
        }


        //Check Content
        String content = handler.toString();
        assertTrue(content.contains("<p>double:[2x2  double array]</p>"));
    }

View Full Code Here

Examples of org.apache.tika.sax.ToXMLContentHandler

                    "writing the text/plain version of the parsed content",e);
            }
            final Writer plainTextWriter = new OutputStreamWriter(plainTextSink.getOutputStream(), UTF8);
            final ContentHandler textHandler = new BodyContentHandler( //only the Body
                new PlainTextHandler(plainTextWriter, false,skipLinebreaks)); //skip ignoreable
            final ToXMLContentHandler xhtmlHandler;
            final ContentHandler mainHandler;
            ContentSink xhtmlSink = null;
            try {
                if(!plainMediaType.equals(XHTML)){ //do not parse XHTML from XHTML
                    try {
                        xhtmlSink = ciFactory.createContentSink(XHTML +"; charset="+UTF8.name());
                    } catch (IOException e) {
                        throw new EngineException("Error while initialising Blob for" +
                                "writing the application/xhtml+xml version of the parsed content",e);
                    }
                    try {
                        xhtmlHandler = new ToXMLContentHandler(xhtmlSink.getOutputStream(),UTF8.name());
                    } catch (UnsupportedEncodingException e) {
                        throw new EngineException("This system does not support the encoding "+UTF8,e);
                    }
                    mainHandler = new MultiHandler(textHandler,xhtmlHandler);
                } else {

View Full Code Here

0 1 2 3 4

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.