use of org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter 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);
}
Aggregations