use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.
the class SpanishAnalyzer 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 SpanishLightStemFilter}.
*/
@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 SpanishLightStemFilter(result);
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.
the class SpanishAnalyzer method normalize.
@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
TokenStream result = new StandardFilter(in);
result = new LowerCaseFilter(result);
return result;
}
use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.
the class PersianAnalyzer 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 StandardTokenizer} filtered with
* {@link LowerCaseFilter}, {@link DecimalDigitFilter}, {@link ArabicNormalizationFilter},
* {@link PersianNormalizationFilter} and Persian Stop words
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final Tokenizer source = new StandardTokenizer();
TokenStream result = new LowerCaseFilter(source);
result = new DecimalDigitFilter(result);
result = new ArabicNormalizationFilter(result);
/* additional persian-specific normalization */
result = new PersianNormalizationFilter(result);
/*
* the order here is important: the stopword list is normalized with the
* above!
*/
return new TokenStreamComponents(source, new StopFilter(result, stopwords));
}
use of org.apache.lucene.analysis.LowerCaseFilter in project lucene-solr by apache.
the class FinnishAnalyzer method normalize.
@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
TokenStream result = new StandardFilter(in);
result = new LowerCaseFilter(result);
return result;
}
use of org.apache.lucene.analysis.LowerCaseFilter 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);
}
Aggregations