Examples with StandardFilter org.apache.lucene.analysis.standard.StandardFilter used on opensource projects

Example 71 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter 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;
}

Example 72 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter 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;
}

Example 73 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter 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;
}

Example 74 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter in project cogcomp-nlp by CogComp.

the class CharacterShingleAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new CharacterShingleTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(result);
    result = new ShingleFilter(result, 3);
    return new TokenStreamComponents(source, result);
}

Example 75 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter in project cogcomp-nlp by CogComp.

the class WikiURLAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final Tokenizer source = new KeywordTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new CharacterFilter(result);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(result);
    return new TokenStreamComponents(source, result);
}