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

  public void map(Text key, Text value,
                  OutputCollector<Text,StringTuple> output, Reporter reporter) throws IOException {
    TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
    StringTuple document = new StringTuple();
    while (stream.incrementToken()) {
      if (termAtt.termLength() > 0) {
        document.add(new String(termAtt.termBuffer(), 0, termAtt.termLength()));
      }
    }
    output.collect(key, document);

View Full Code Here

            stream.reset();


            int poz = 0;
            boolean hasFulltextToken = false;
            StringBuilder token = new StringBuilder();
            while (stream.incrementToken()) {
                String term = termAtt.toString();
                int start = offsetAtt.startOffset();
                int end = offsetAtt.endOffset();
                if (start > poz) {
                    for (int i = poz; i < start; i++) {

View Full Code Here

        {
            TokenStream ts = nexusAnalyzer.reusableTokenStream( indexerField.getKey(), new StringReader( query ) );


            int result = 0;


            while ( ts.incrementToken() )
            {
                result++;
            }


            return result;

View Full Code Here

        CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
        PositionIncrementAttribute posIncr = stream
                .addAttribute(PositionIncrementAttribute.class);


        int position = 0;
        while (stream.incrementToken()) {


            int increment = posIncr.getPositionIncrement();
            if (increment > 0) {
                position = position + increment;
                System.out.println();

View Full Code Here

        OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
        TypeAttribute type = stream.addAttribute(TypeAttribute.class);
        PayloadAttribute payload = stream.addAttribute(PayloadAttribute.class);


        int position = 0;
        while (stream.incrementToken()) {


            int increment = posIncr.getPositionIncrement();
            if (increment > 0) {
                position = position + increment;
                System.out.println();

View Full Code Here

    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
    
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);


    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
    
    assertEquals("Second Token did not match!", "Text", t2);

View Full Code Here

    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);


    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
    
    assertEquals("Second Token did not match!", "Text", t2);
    assertEquals("Third Token did not match!", "Whitespaces", t3);

View Full Code Here

    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
    
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);


    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
    
    assertEquals("Second Token did not match!", "text", t2);

View Full Code Here

    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);


    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
    
    assertEquals("Second Token did not match!", "text", t2);
    assertEquals("Third Token did not match!", "whitespaces", t3);

View Full Code Here

    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
    
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);


    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
    
    assertEquals("Second Token did not match!", "text", t2);

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.