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

Example 6 with StopFilter

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

the class UkrainianMorfologikAnalyzer 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 MorfologikFilter} on the Ukrainian dictionary.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (stemExclusionSet.isEmpty() == false) {
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    }
    result = new MorfologikFilter(result, getDictionary());
    return new TokenStreamComponents(source, result);
}

Example 7 with StopFilter

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

the class DutchAnalyzer method createComponents.

/**
   * Returns a (possibly reused) {@link TokenStream} which tokenizes all the 
   * text in the provided {@link Reader}.
   *
   * @return A {@link TokenStream} built from a {@link StandardTokenizer}
   *   filtered with {@link StandardFilter}, {@link LowerCaseFilter}, 
   *   {@link StopFilter}, {@link SetKeywordMarkerFilter} if a stem exclusion set is provided,
   *   {@link StemmerOverrideFilter}, 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, stoptable);
    if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
    if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);
    result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
    return new TokenStreamComponents(source, result);
}

Example 8 with StopFilter

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

the class NorwegianAnalyzer 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 NorwegianStemmer());
    return new TokenStreamComponents(source, result);
}

Example 9 with StopFilter

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

the class QueryAutoStopWordAnalyzer method wrapComponents.

@Override
protected TokenStreamComponents wrapComponents(String fieldName, TokenStreamComponents components) {
    Set<String> stopWords = stopWordsPerField.get(fieldName);
    if (stopWords == null) {
        return components;
    }
    StopFilter stopFilter = new StopFilter(components.getTokenStream(), new CharArraySet(stopWords, false));
    return new TokenStreamComponents(components.getTokenizer(), stopFilter);
}

Example 10 with StopFilter

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

the class RomanianAnalyzer 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 RomanianStemmer());
    return new TokenStreamComponents(source, result);
}