Examples of StopFilter

org.apache.lucene.analysis.StopFilter
Removes stop words from a token stream.
org.apache.lucene.analysis.core.StopFilter
Removes stop words from a token stream.
You must specify the required {@link Version}compatibility when creating StopFilter:
- As of 3.1, StopFilter correctly handles Unicode 4.0 supplementary characters in stopwords and position increments are preserved

uk.ac.ucl.panda.utility.parser.StopFilter
Removes stop words from a token stream.

Examples of org.apache.lucene.analysis.StopFilter

   * @return A {@link TokenStream} built from {@link CJKTokenizer}, filtered with
   *    {@link StopFilter}
   */
  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
    return new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                          new CJKTokenizer(reader), stopTable);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

    /* tokenStream() is final, no back compat issue */
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new CJKTokenizer(reader);
      streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                      streams.source, stopTable);
      setPreviousTokenStream(streams);
    } else {
      streams.source.reset(reader);
    }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

    else if (pattern == WHITESPACE_PATTERN) { // fast path
      stream = new FastStringTokenizer(text, false, toLowerCase, stopWords);
    }
    else {
      stream = new PatternTokenizer(text, pattern, toLowerCase);
      if (stopWords != null) stream = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion), stream, stopWords);
    }
    
    return stream;
  }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
                TokenStream result = new StandardTokenizer( matchVersion, reader );
    result = new LowerCaseFilter( result );
    result = new StandardFilter( result );
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                         result, stoptable );
    result = new BrazilianStemFilter( result, excltable );
    return result;
  }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

      if (streams == null) {
        streams = new SavedStreams();
        streams.source = new StandardTokenizer(matchVersion, reader);
        streams.result = new LowerCaseFilter(streams.source);
        streams.result = new StandardFilter(streams.result);
        streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                        streams.result, stoptable);
        streams.result = new BrazilianStemFilter(streams.result, excltable);
        setPreviousTokenStream(streams);
      } else {
        streams.source.reset(reader);

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

  @Override
  public final TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new ArabicLetterTokenizer( reader );
    result = new LowerCaseFilter(result);
    // the order here is important: the stopword list is not normalized!
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                             result, stoptable );
    result = new ArabicNormalizationFilter( result );
    result = new ArabicStemFilter( result );


    return result;

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new ArabicLetterTokenizer(reader);
      streams.result = new LowerCaseFilter(streams.source);
      // the order here is important: the stopword list is not normalized!
      streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                      streams.result, stoptable);
      streams.result = new ArabicNormalizationFilter(streams.result);
      streams.result = new ArabicStemFilter(streams.result);
      setPreviousTokenStream(streams);
    } else {

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

    @Override
    public TokenStream tokenStream(String fieldName, Reader reader)
    {
        TokenStream result = new StandardTokenizer(matchVersion, reader);
        result = new GreekLowerCaseFilter(result);
        result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                result, stopSet);
        return result;
    }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

      SavedStreams streams = (SavedStreams) getPreviousTokenStream();
      if (streams == null) {
        streams = new SavedStreams();
        streams.source = new StandardTokenizer(matchVersion, reader);
        streams.result = new GreekLowerCaseFilter(streams.source);
        streams.result = new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                        streams.result, stopSet);
        setPreviousTokenStream(streams);
      } else {
        streams.source.reset(reader);
      }

View Full Code Here

Examples of org.apache.lucene.analysis.StopFilter

  @Override
  public final TokenStream tokenStream( String fieldName, Reader reader ) {
                TokenStream result = new StandardTokenizer( matchVersion, reader );
    result = new StandardFilter( result );
    result = new LowerCaseFilter( result );
    result = new StopFilter( StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                                         result, stoptable );
    return result;
  }

View Full Code Here

0 1 2 3 4 5

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.