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

Example 26 with LowerCaseFilter

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

the class ClassicAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final ClassicTokenizer src = new ClassicTokenizer();
    src.setMaxTokenLength(maxTokenLength);
    TokenStream tok = new ClassicFilter(src);
    tok = new LowerCaseFilter(tok);
    tok = new StopFilter(tok, stopwords);
    return new TokenStreamComponents(src, tok) {

        @Override
        protected void setReader(final Reader reader) {
            src.setMaxTokenLength(ClassicAnalyzer.this.maxTokenLength);
            super.setReader(reader);
        }
    };
}

Example 27 with LowerCaseFilter

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

the class ThaiAnalyzer method normalize.

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

Example 28 with LowerCaseFilter

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

the class CJKAnalyzer method normalize.

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

Example 29 with LowerCaseFilter

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

the class CJKAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    // run the widthfilter first before bigramming, it sometimes combines characters.
    TokenStream result = new CJKWidthFilter(source);
    result = new LowerCaseFilter(result);
    result = new CJKBigramFilter(result);
    return new TokenStreamComponents(source, new StopFilter(result, stopwords));
}

Example 30 with LowerCaseFilter

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

the class ArabicAnalyzer 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 LowerCaseFilter}, {@link DecimalDigitFilter}, {@link StopFilter},
   *         {@link ArabicNormalizationFilter}, {@link SetKeywordMarkerFilter}
   *         if a stem exclusion set is provided and {@link ArabicStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new DecimalDigitFilter(result);
    // the order here is important: the stopword list is not normalized!
    result = new StopFilter(result, stopwords);
    // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
    result = new ArabicNormalizationFilter(result);
    if (!stemExclusionSet.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    }
    return new TokenStreamComponents(source, new ArabicStemFilter(result));
}