Examples of org.apache.lucene.analysis.TokenStream.incrementToken()

Class org.apache.lucene.analysis.TokenStream

Examples of org.apache.lucene.analysis.TokenStream.incrementToken()

org.apache.lucene.analysis.TokenStream.incrementToken()
Consumers (i.e., {@link IndexWriter}) use this method to advance the stream to the next token. Implementing classes must implement this method and update the appropriate {@link AttributeImpl}s with the attributes of the next token.
The producer must make no assumptions about the attributes after the method has been returned: the caller may arbitrarily change it. If the producer needs to preserve the state for subsequent calls, it can use {@link #captureState} to create a copy of the current attribute state.
This method is called for every token of a document, so an efficient implementation is crucial for good performance. To avoid calls to {@link #addAttribute(Class)} and {@link #getAttribute(Class)}, references to all {@link AttributeImpl}s that this stream uses should be retrieved during instantiation.
To ensure that filters and consumers know which attributes are available, the attributes must be added during instantiation. Filters and consumers are not required to check for availability of attributes in {@link #incrementToken()}. @return false for end of stream; true otherwise

      TokenStream ts = analyzer.tokenStream("text", new StringReader("the big brown fox jumped on the wood"));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
      TypeAttribute typeAttr = ts.addAttribute(TypeAttribute.class);
      PositionIncrementAttribute posAtt = ts.addAttribute(PositionIncrementAttribute.class);
      while (ts.incrementToken()) {
        assertNotNull(offsetAtt);
        assertNotNull(termAtt);
        assertNotNull(posAtt);
        assertNotNull(typeAttr);
        System.out.println("token '" + termAtt.toString() + "' has type " + typeAttr.type());

View Full Code Here

  public void baseUIMAPayloadsAnalyzerStreamTest() {
    try {
      TokenStream ts = analyzer.tokenStream("text", new StringReader("the big brown fox jumped on the wood"));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      PayloadAttribute payloadAttribute = ts.addAttribute(PayloadAttribute.class);
      while (ts.incrementToken()) {
        assertNotNull(termAtt);
        assertNotNull(payloadAttribute);
        System.out.println("token '" + termAtt.toString() + "' has payload " + new String(payloadAttribute.getPayload().getData()));
      }
    } catch (Exception e) {

View Full Code Here

      TokenStream ts = analyzer.tokenStream("text", new StringReader(app
              .getString(inputText, "text")));
      app.removeAll(resultsList);
      ts.reset();


      while (ts.incrementToken()) {
        Object row = app.create("item");
        app.setString(row, "text", ((CharTermAttribute)ts.getAttribute(CharTermAttribute.class)).toString());
        app.add(resultsList, row);
        app.putProperty(row, "state", ts.cloneAttributes());
      }

View Full Code Here

        try {
            TokenStream stream = _analyzer.tokenStream("content", new StringReader(contentText));
            CharTermAttribute termAtt = (CharTermAttribute) stream.addAttribute(CharTermAttribute.class);


            stream.reset();
            while (stream.incrementToken()) {
                if (termAtt.length() > 0) {
                    String term = termAtt.toString();
                        result.add(term);
                }
            }

View Full Code Here

    StringReader reader = new StringReader( source );
    TokenStream ts = loadTokenizer(tokFactory, reader);
    List<String> tokList = new ArrayList<String>();
    try {
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      while (ts.incrementToken()){
        if( termAtt.length() > 0 )
          tokList.add( termAtt.toString() );
      }
    } catch (IOException e) {
      throw new RuntimeException(e);

View Full Code Here

    final Set<String> tokens = new HashSet<String>();
    final TokenStream tokenStream = analyzer.tokenStream("", new StringReader(query));
    final CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
    try {
      tokenStream.reset();
      while (tokenStream.incrementToken()) {
        tokens.add(termAtt.toString());
      }
    } catch (IOException ioe) {
      throw new RuntimeException("Error occured while iterating over tokenstream", ioe);
    }

View Full Code Here

          FlagsAttribute flagsAtt = stream.addAttribute(FlagsAttribute.class);
          TypeAttribute typeAtt = stream.addAttribute(TypeAttribute.class);
          PayloadAttribute payloadAtt = stream.addAttribute(PayloadAttribute.class);
          PositionIncrementAttribute posIncAtt = stream.addAttribute(PositionIncrementAttribute.class);
          stream.reset();
          while (stream.incrementToken()) {
            Token token = new Token();
            token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
            token.setStartOffset(matcher.start());
            token.setEndOffset(matcher.end());
            token.setFlags(flagsAtt.getFlags());

View Full Code Here

    TypeAttribute typeAtt = ts.addAttribute(TypeAttribute.class);
    FlagsAttribute flagsAtt = ts.addAttribute(FlagsAttribute.class);
    PayloadAttribute payloadAtt = ts.addAttribute(PayloadAttribute.class);
    PositionIncrementAttribute posIncAtt = ts.addAttribute(PositionIncrementAttribute.class);
    
    while (ts.incrementToken()){
      Token token = new Token();
      token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
      token.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
      token.setType(typeAtt.type());
      token.setFlags(flagsAtt.getFlags());

View Full Code Here

    StringReader sr = new StringReader(s);
//    Analyzer analyzer =new StandardAnalyzer((Version) Enum.valueOf((Class) Class.forName("org.apache.lucene.util.Version"),  Version.LUCENE_35.name()));
    Analyzer analyzer = schema.getAnalyzer();//JobIndexPublic.setAnalyzer(conf);
    TokenStream tk=analyzer.tokenStream("rawquery", sr);


    boolean hasnext = tk.incrementToken();


    while(hasnext){


      TermAttribute ta = tk.getAttribute(TermAttribute.class);

View Full Code Here


      TermAttribute ta = tk.getAttribute(TermAttribute.class);


      System.out.println(ta.term());


      hasnext = tk.incrementToken();


    }
  }


    protected void cleanup(Context context) throws IOException,  InterruptedException {

View Full Code Here

0 1 2 3 4 5 6 7 8 9

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.