Examples of org.apache.tika.parser.html.HtmlParser$HtmlParserMapper

org.apache.tika.parser.html.HtmlParser
Adapter class that maintains backwards compatibility with the protected HtmlParser methods. Making HtmlParser implement HtmlMapper directly would require those methods to be public, which would break backwards compatibility with subclasses. @deprecated Use the {@link HtmlMapper} mechanism to customizethe HTML mapping. This class will be removed in Tika 1.0.

                 data = ((ByteChunk)htmlChunk).getValue();
              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)), 
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;

View Full Code Here


  public static AutoDetectParser createParser() {
    final AutoDetectParser parser = new AutoDetectParser();


    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);


    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);

View Full Code Here

              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                  // nocommit same problem here?
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)), 
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;

View Full Code Here


  public static AutoDetectParser createParser() {
    final AutoDetectParser parser = new AutoDetectParser();


    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);


    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);

View Full Code Here

     */
    private String extract(byte[][] byteObject) {// throws IOException
        StringBuilder wBuf = new StringBuilder();
        InputStream stream = null;
        Metadata metadata = new Metadata();
        HtmlParser htmlParser = new HtmlParser();
        BodyContentHandler handler = new BodyContentHandler(-1);// -1
        ParseContext parser = new ParseContext();
        try {
            for (int i = 0; i < byteObject.length; i++) {
                stream = new ByteArrayInputStream(byteObject[i]);
                try {
                    htmlParser.parse(stream, handler, metadata, parser);
                } catch (TikaException e) {
                    wBuf.append(new String(byteObject[i]));
//                    System.err.println("\n"
//                            + CHMDocumentInformation.class.getName()
//                            + " extract " + e.getMessage());

View Full Code Here

  @SuppressWarnings("serial")
  public static AutoDetectParser createParser(TikaConfig tikaConfig) {
    final AutoDetectParser parser = new AutoDetectParser(tikaConfig);


    Map<MediaType,Parser> parsers = parser.getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    parser.setParsers(parsers);


    parser.setFallback(new Parser() {
      public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
        return parser.getSupportedTypes(parseContext);

View Full Code Here

                 data = ((ByteChunk)htmlChunk).getValue();
              } else if(htmlChunk instanceof StringChunk) {
                 data = ((StringChunk)htmlChunk).getRawValue();
              }
              if(data != null) {
                 HtmlParser htmlParser = new HtmlParser();
                 htmlParser.parse(
                       new ByteArrayInputStream(data),
                       new EmbeddedContentHandler(new BodyContentHandler(xhtml)), 
                       new Metadata(), new ParseContext()
                 );
                 doneBody = true;

View Full Code Here

     */
    private String extract(byte[] byteObject) throws TikaException {// throws IOException
        StringBuilder wBuf = new StringBuilder();
        InputStream stream = null;
        Metadata metadata = new Metadata();
        HtmlParser htmlParser = new HtmlParser();
        BodyContentHandler handler = new BodyContentHandler(-1);// -1
        ParseContext parser = new ParseContext();
        try {
            stream = new ByteArrayInputStream(byteObject);
            htmlParser.parse(stream, handler, metadata, parser);
            wBuf.append(handler.toString()
                    + System.getProperty("line.separator"));
        } catch (SAXException e) {
            throw new RuntimeException(e);
        } catch (IOException e) {

View Full Code Here

0 1 2

TOP

Related Classes of org.apache.tika.parser.html.HtmlParser$HtmlParserMapper

bixo.examples.webmining.DemoWebMiningTool

com.scaleunlimited.helpful.operations.ParseModMboxPageFunction

com.tamingtext.tika.TikaTest

edu.uci.ics.crawler4j.parser.Parser

org.apache.commons.io.input.CloseShieldInputStream

org.apache.jackrabbit.core.query.lucene.JackrabbitParser

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

org.apache.oodt.cas.pushpull.protocol.http.HttpClient

org.apache.oodt.cas.pushpull.protocol.imaps.ImapsClient

org.apache.tika.detect.AutoDetectReader

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.