use of org.apache.lucene.analysis.StopFilter in project lucene-solr by apache.
the class PortugueseAnalyzer 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 PortugueseLightStemFilter}.
*/
@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 PortugueseLightStemFilter(result);
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.StopFilter in project ddf by codice.
the class ContextualAnalyzer method reusableTokenStream.
@Override
public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
if (overridesTokenStreamMethod) {
// tokenStream but not reusableTokenStream
return tokenStream(fieldName, reader);
}
SavedStreams streams = (SavedStreams) getPreviousTokenStream();
if (streams == null) {
streams = new SavedStreams();
setPreviousTokenStream(streams);
streams.tokenStream = new ContextualTokenizer(reader);
streams.filteredTokenStream = new StandardFilter(streams.tokenStream);
streams.filteredTokenStream = new LowerCaseFilter(streams.filteredTokenStream);
streams.filteredTokenStream = new StopFilter(enableStopPositionIncrements, streams.filteredTokenStream, stopSet);
} else {
streams.tokenStream.reset(reader);
}
return streams.filteredTokenStream;
}
use of org.apache.lucene.analysis.StopFilter in project ddf by codice.
the class ContextualAnalyzer method tokenStream.
/**
* Constructs a {@link org.apache.lucene.analysis.standard.StandardTokenizer} filtered by a {@link StandardFilter}, a
* {@link LowerCaseFilter} and a {@link StopFilter}.
*/
@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
ContextualTokenizer tokenStream = new ContextualTokenizer(reader);
TokenStream result = new StandardFilter(tokenStream);
result = new LowerCaseFilter(result);
result = new StopFilter(enableStopPositionIncrements, result, stopSet);
return result;
}
use of org.apache.lucene.analysis.StopFilter in project ddf by codice.
the class CaseSensitiveContextualAnalyzer method tokenStream.
/**
* Constructs a {@link org.apache.lucene.analysis.standard.StandardTokenizer} filtered by a {@link StandardFilter}, a
* {@link LowerCaseFilter} and a {@link StopFilter}.
*/
@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
ContextualTokenizer tokenStream = new ContextualTokenizer(reader);
TokenStream result = new StandardFilter(tokenStream);
result = new StopFilter(enableStopPositionIncrements, result, stopSet);
return result;
}
Aggregations