Examples with SetKeywordMarkerFilter org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter used on opensource projects

Example 46 with SetKeywordMarkerFilter

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

the class TestNorwegianMinimalStemFilter method testKeyword.

public void testKeyword() throws IOException {
    final CharArraySet exclusionSet = new CharArraySet(asSet("sekretæren"), false);
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer source = new MockTokenizer(MockTokenizer.WHITESPACE, false);
            TokenStream sink = new SetKeywordMarkerFilter(source, exclusionSet);
            return new TokenStreamComponents(source, new NorwegianMinimalStemFilter(sink));
        }
    };
    checkOneTerm(a, "sekretæren", "sekretæren");
    a.close();
}

Example 47 with SetKeywordMarkerFilter

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

the class PolishAnalyzer 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 StempelFilter}.
   */
@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 StempelFilter(result, new StempelStemmer(stemTable));
    return new TokenStreamComponents(source, result);
}

Example 48 with SetKeywordMarkerFilter

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

the class SpanishAnalyzer 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 SpanishLightStemFilter}.
   */
@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 SpanishLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 49 with SetKeywordMarkerFilter

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

the class FinnishAnalyzer 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 FinnishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 50 with SetKeywordMarkerFilter

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

the class TurkishAnalyzer 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 TurkishLowerCaseFilter},
   *         {@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 ApostropheFilter(result);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    }
    result = new SnowballFilter(result, new TurkishStemmer());
    return new TokenStreamComponents(source, result);
}