Examples with StopFilter org.apache.lucene.analysis.StopFilter used on opensource projects

Example 51 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.

the class FinnishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 52 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.

the class ThaiAnalyzer method createComponents.

/**
   * Creates
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * used to tokenize all the text in the provided {@link Reader}.
   * 
   * @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from a {@link ThaiTokenizer} filtered with
   *         {@link LowerCaseFilter}, {@link DecimalDigitFilter} and {@link StopFilter}
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new ThaiTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new DecimalDigitFilter(result);
    result = new StopFilter(result, stopwords);
    return new TokenStreamComponents(source, result);
}

Example 53 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.

the class TurkishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link TurkishLowerCaseFilter},
   *         {@link StopFilter}, {@link SetKeywordMarkerFilter} if a stem
   *         exclusion set is provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ApostropheFilter(result);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    }
    result = new SnowballFilter(result, new TurkishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 54 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.

the class UAX29URLEmailAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer();
    src.setMaxTokenLength(maxTokenLength);
    TokenStream tok = new StandardFilter(src);
    tok = new LowerCaseFilter(tok);
    tok = new StopFilter(tok, stopwords);
    return new TokenStreamComponents(src, tok) {

        @Override
        protected void setReader(final Reader reader) {
            // So that if maxTokenLength was changed, the change takes
            // effect next time tokenStream is called:
            src.setMaxTokenLength(UAX29URLEmailAnalyzer.this.maxTokenLength);
            super.setReader(reader);
        }
    };
}

Example 55 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.

the class SwedishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SwedishStemmer());
    return new TokenStreamComponents(source, result);
}