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

Example 56 with LowerCaseFilter

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

the class SoraniAnalyzer method normalize.

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

Example 57 with LowerCaseFilter

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

the class TestGermanStemFilter method setUp.

@Override
public void setUp() throws Exception {
    super.setUp();
    analyzer = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer t = new MockTokenizer(MockTokenizer.KEYWORD, false);
            return new TokenStreamComponents(t, new GermanStemFilter(new LowerCaseFilter(t)));
        }
    };
}

Example 58 with LowerCaseFilter

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

the class TestTeeSinkTokenFilter method testMultipleSources.

public void testMultipleSources() throws Exception {
    final TeeSinkTokenFilter tee1 = new TeeSinkTokenFilter(whitespaceMockTokenizer(buffer1.toString()));
    final TokenStream source1 = new CachingTokenFilter(tee1);
    tee1.addAttribute(CheckClearAttributesAttribute.class);
    MockTokenizer tokenizer = new MockTokenizer(tee1.getAttributeFactory(), MockTokenizer.WHITESPACE, false);
    tokenizer.setReader(new StringReader(buffer2.toString()));
    final TeeSinkTokenFilter tee2 = new TeeSinkTokenFilter(tokenizer);
    final TokenStream source2 = tee2;
    assertTokenStreamContents(source1, tokens1);
    assertTokenStreamContents(source2, tokens2);
    TokenStream lowerCasing = new LowerCaseFilter(source1);
    String[] lowerCaseTokens = new String[tokens1.length];
    for (int i = 0; i < tokens1.length; i++) lowerCaseTokens[i] = tokens1[i].toLowerCase(Locale.ROOT);
    assertTokenStreamContents(lowerCasing, lowerCaseTokens);
}

Example 59 with LowerCaseFilter

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

the class FrenchAnalyzer 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 ElisionFilter},
   *         {@link LowerCaseFilter}, {@link StopFilter},
   *         {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided, and {@link FrenchLightStemFilter}
   */
@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 (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
    result = new FrenchLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 60 with LowerCaseFilter

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

the class FrenchAnalyzer method normalize.

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