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

Example 31 with StandardFilter

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

the class ASCIIEnglishAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ASCIIFoldingFilter(result);
    result = new EnglishPossessiveFilter(result);
    result = new WordDelimiterFilter(result, WordDelimiterFilter.ALPHA, null);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, EnglishAnalyzer.getDefaultStopSet());
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 32 with StandardFilter

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

the class MinimalAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(result);
    result = new EnglishPossessiveFilter(result);
    result = new StopFilter(result, stopwords);
    result = new WordDelimiterFilter(result, WordDelimiterFilter.ALPHA, null);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 33 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter in project ddf by codice.

the class CaseSensitiveContextualAnalyzer 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 StopFilter(enableStopPositionIncrements, streams.filteredTokenStream, stopSet);
    } else {
        streams.tokenStream.reset(reader);
    }
    return streams.filteredTokenStream;
}

Example 34 with StandardFilter

use of org.apache.lucene.analysis.standard.StandardFilter in project elasticsearch by elastic.

the class StandardHtmlStripAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final Tokenizer src = new StandardTokenizer();
    TokenStream tok = new StandardFilter(src);
    tok = new LowerCaseFilter(tok);
    if (!stopwords.isEmpty()) {
        tok = new StopFilter(tok, stopwords);
    }
    return new TokenStreamComponents(src, tok);
}

Example 35 with StandardFilter

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

the class SoraniAnalyzer 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 SoraniNormalizationFilter}, 
   *         {@link LowerCaseFilter}, {@link DecimalDigitFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SoraniStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new SoraniNormalizationFilter(result);
    result = new LowerCaseFilter(result);
    result = new DecimalDigitFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SoraniStemFilter(result);
    return new TokenStreamComponents(source, result);
}