Examples of org.apache.lucene.analysis.StopFilter

org.apache.lucene.analysis.StopFilter
Removes stop words from a token stream.

   *       {@link StopFilter}, {@link LowerCaseFilter}, {@link ArabicNormalizationFilter}
   *            and {@link ArabicStemFilter}.
   */
  public final TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new ArabicLetterTokenizer( reader );
    result = new StopFilter( result, stoptable );
    result = new LowerCaseFilter(result);
    result = new ArabicNormalizationFilter( result );
    result = new ArabicStemFilter( result );


    return result;

View Full Code Here

      throws IOException {
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new ArabicLetterTokenizer(reader);
      streams.result = new StopFilter(streams.source, stoptable);
      streams.result = new LowerCaseFilter(streams.result);
      streams.result = new ArabicNormalizationFilter(streams.result);
      streams.result = new ArabicStemFilter(streams.result);
      setPreviousTokenStream(streams);
    } else {

View Full Code Here

    if (fieldName == null) throw new IllegalArgumentException("fieldName must not be null");
    if (reader == null) throw new IllegalArgumentException("reader must not be null");


    TokenStream result = new StandardTokenizer(reader);
    result = new StandardFilter(result);
    result = new StopFilter(result, stoptable);
    result = new FrenchStemFilter(result, excltable);
    // Convert to lowercase after stemming!
    result = new LowerCaseFilter(result);
    return result;
  }

View Full Code Here

    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new StandardTokenizer(reader);
      streams.result = new StandardFilter(streams.source);
      streams.result = new StopFilter(streams.result, stoptable);
      streams.result = new FrenchStemFilter(streams.result, excltable);
      // Convert to lowercase after stemming!
      streams.result = new LowerCaseFilter(streams.result);
      setPreviousTokenStream(streams);
    } else {

View Full Code Here

   */
  public final TokenStream tokenStream( String fieldName, Reader reader ) {
    TokenStream result = new StandardTokenizer( reader );
    result = new StandardFilter( result );
    result = new LowerCaseFilter( result );
    result = new StopFilter( result, stoptable );
    return result;
  }

View Full Code Here

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

View Full Code Here

   */
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(reader);
    result = new StandardFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopSet);
    result = new GermanStemFilter(result, exclusionSet);
    return result;
  }

View Full Code Here

    if (streams == null) {
      streams = new SavedStreams();
      streams.source = new StandardTokenizer(reader);
      streams.result = new StandardFilter(streams.source);
      streams.result = new LowerCaseFilter(streams.result);
      streams.result = new StopFilter(streams.result, stopSet);
      streams.result = new GermanStemFilter(streams.result, exclusionSet);
      setPreviousTokenStream(streams);
    } else {
      streams.source.reset(reader);
    }

View Full Code Here

  
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream ts = new StandardTokenizer(reader);
    ts = new StandardFilter(ts);
    ts = new ThaiWordFilter(ts);
    ts = new StopFilter(ts, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
    return ts;
  }

View Full Code Here

    } catch (IOException e) {
      result = delegate.tokenStream(fieldName, reader);
    }
    HashSet stopWords = (HashSet) stopWordsPerField.get(fieldName);
    if (stopWords != null) {
      result = new StopFilter(result, stopWords);
    }
    return result;
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.analysis.StopFilter

BugAnalyzer.PorterStemAnalyzer

com.gentics.cr.lucene.analysis.CustomPatternAnalyzer

com.gentics.cr.lucene.autocomplete.AutocompleteAnalyzer

com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer$EnglishSpecialAnalyzer

com.infoclinika.mssharing.search.NoStopWordsAnalyzer

com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer

com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer

edu.wiki.index.WikipediaAnalyzer

ivory.core.tokenize.LuceneArabicAnalyzer

ivory.core.tokenize.LuceneSpanishAnalyzer

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.