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

Example 31 with StopFilter

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

the class TestCJKAnalyzer method testSingleChar2.

public void testSingleChar2() throws Exception {
    Analyzer analyzer = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
            TokenFilter filter = new FakeStandardTokenizer(tokenizer);
            filter = new StopFilter(filter, CharArraySet.EMPTY_SET);
            filter = new CJKBigramFilter(filter);
            return new TokenStreamComponents(tokenizer, filter);
        }
    };
    assertAnalyzesTo(analyzer, "一", new String[] { "一" }, new int[] { 0 }, new int[] { 1 }, new String[] { "<SINGLE>" }, new int[] { 1 });
    analyzer.close();
}

Example 32 with StopFilter

use of org.apache.lucene.analysis.StopFilter 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 33 with StopFilter

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

the class IrishAnalyzer 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 IrishLowerCaseFilter}, {@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 StopFilter(result, HYPHENATIONS);
    result = new ElisionFilter(result, DEFAULT_ARTICLES);
    result = new IrishLowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new IrishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 34 with StopFilter

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

the class HungarianAnalyzer 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 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 HungarianStemmer());
    return new TokenStreamComponents(source, result);
}

Example 35 with StopFilter

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

the class ArmenianAnalyzer 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 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 ArmenianStemmer());
    return new TokenStreamComponents(source, result);
}