Package org.apache.lucene.analysis.standard

Examples of org.apache.lucene.analysis.standard.StandardFilter


   */
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new TurkishStemmer());
View Full Code Here


   */
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new DanishStemmer());
View Full Code Here

  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    result = new StandardFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(excltable != null && !excltable.isEmpty())
      result = new SetKeywordMarkerFilter(result, excltable);
    return new TokenStreamComponents(source, new BrazilianStemFilter(result));
  }
View Full Code Here

   */
  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new LatvianStemFilter(result);
View Full Code Here

  protected TokenStreamComponents createComponents(final String field, final Reader reader) {
    final Tokenizer src = new StandardTokenizer(this.version, reader);
   
    return new TokenStreamComponents(
        src,
        new MorfologikFilter(new StandardFilter(this.version, src), this.version));
  }
View Full Code Here

   * @return  A TokenStream build from a StandardTokenizer filtered with
   *       StandardFilter, LowerCaseFilter, and StopFilter
   */
  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 (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

   *         provided and {@link SoraniStemFilter}.
   */
  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new SoraniNormalizationFilter(result);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
View Full Code Here

     * Constructs a {@link StandardTokenizer} filtered by a {@link
     * StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}.
     */
    public TokenStream tokenStream(String fieldName, Reader reader) {
        TokenStream result = new StandardTokenizer(reader);
        result = new StandardFilter(result);
        result = new StopFilter(result, stopSet);
        return result;
    }
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

TOP

Related Classes of org.apache.lucene.analysis.standard.StandardFilter

Copyright © 2018 www.massapicom. All rights reserved.
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.