Examples with LowerCaseFilter org.apache.lucene.analysis.LowerCaseFilter used on opensource projects

Example 91 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter 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);
}

Example 92 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project epadd by ePADD.

the class EnglishNumberAnalyzer method createComponents.

/*
 * Creates a {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} which
 * tokenizes all the text in the reader that is set after the instantiation of this analyzer .
 *
 * @return A {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} built from an {@link StandardTokenizer} filtered with {@link StandardFilter}, {@link EnglishPossessiveFilter}, {@link LowerCaseFilter}, {@link StopFilter} , {@link SetKeywordMarkerFilter} if a stem exclusion set is
 *         provided and {@link PorterStemFilter}.
 **/
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardNumberTokenizer();
    TokenStream result = new StandardFilter(source);
    // @TODO document what each of these filters do
    result = new EnglishPossessiveFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, this.stopwords);
    if (!this.stemExclusionSet.isEmpty()) {
        result = new SetKeywordMarkerFilter((TokenStream) result, this.stemExclusionSet);
    }
    result = new PorterStemFilter((TokenStream) result);
    return new TokenStreamComponents(source, result);
}

Example 93 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter in project crate by crate.

the class StandardHtmlStripAnalyzer method createComponents.

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

Example 94 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter 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 95 with LowerCaseFilter

use of org.apache.lucene.analysis.LowerCaseFilter 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;
}