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

Example 21 with LowerCaseFilter

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

the class IndonesianAnalyzer 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 an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter},
   *         {@link StopFilter}, {@link SetKeywordMarkerFilter}
   *         if a stem exclusion set is provided and {@link IndonesianStemFilter}.
   */
@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);
    }
    return new TokenStreamComponents(source, new IndonesianStemFilter(result));
}

Example 22 with LowerCaseFilter

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

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

Example 23 with LowerCaseFilter

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

the class SwedishAnalyzer method normalize.

@Override
protected TokenStream normalize(String fieldName, TokenStream in) {
    TokenStream result = new StandardFilter(in);
    result = new LowerCaseFilter(result);
    return result;
}

Example 24 with LowerCaseFilter

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

the class SynonymFilterFactory method inform.

@Override
public void inform(ResourceLoader loader) throws IOException {
    final TokenizerFactory factory = tokenizerFactory == null ? null : loadTokenizerFactory(loader, tokenizerFactory);
    Analyzer analyzer;
    if (analyzerName != null) {
        analyzer = loadAnalyzer(loader, analyzerName);
    } else {
        analyzer = new Analyzer() {

            @Override
            protected TokenStreamComponents createComponents(String fieldName) {
                Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer() : factory.create();
                TokenStream stream = ignoreCase ? new LowerCaseFilter(tokenizer) : tokenizer;
                return new TokenStreamComponents(tokenizer, stream);
            }
        };
    }
    try (Analyzer a = analyzer) {
        String formatClass = format;
        if (format == null || format.equals("solr")) {
            formatClass = SolrSynonymParser.class.getName();
        } else if (format.equals("wordnet")) {
            formatClass = WordnetSynonymParser.class.getName();
        }
        // TODO: expose dedup as a parameter?
        map = loadSynonyms(loader, formatClass, true, a);
    } catch (ParseException e) {
        throw new IOException("Error parsing synonyms file:", e);
    }
}

Example 25 with LowerCaseFilter

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

the class RussianAnalyzer 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 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 org.tartarus.snowball.ext.RussianStemmer());
    return new TokenStreamComponents(source, result);
}