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

Example 11 with SetKeywordMarkerFilter

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

the class TestGermanLightStemFilter method testKeyword.

public void testKeyword() throws IOException {
    final CharArraySet exclusionSet = new CharArraySet(asSet("sängerinnen"), 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 GermanLightStemFilter(sink));
        }
    };
    checkOneTerm(a, "sängerinnen", "sängerinnen");
    a.close();
}

Example 12 with SetKeywordMarkerFilter

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

the class TestCzechStemmer method testWithKeywordAttribute.

public void testWithKeywordAttribute() throws IOException {
    CharArraySet set = new CharArraySet(1, true);
    set.add("hole");
    final MockTokenizer in = new MockTokenizer(MockTokenizer.WHITESPACE, false);
    in.setReader(new StringReader("hole desek"));
    CzechStemFilter filter = new CzechStemFilter(new SetKeywordMarkerFilter(in, set));
    assertTokenStreamContents(filter, new String[] { "hole", "desk" });
}

Example 13 with SetKeywordMarkerFilter

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

the class DutchAnalyzer method createComponents.

/**
   * Returns a (possibly reused) {@link TokenStream} which tokenizes all the 
   * text in the provided {@link Reader}.
   *
   * @return A {@link TokenStream} built from a {@link StandardTokenizer}
   *   filtered with {@link StandardFilter}, {@link LowerCaseFilter}, 
   *   {@link StopFilter}, {@link SetKeywordMarkerFilter} if a stem exclusion set is provided,
   *   {@link StemmerOverrideFilter}, 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, stoptable);
    if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
    if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);
    result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
    return new TokenStreamComponents(source, result);
}

Example 14 with SetKeywordMarkerFilter

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

the class NorwegianAnalyzer 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 NorwegianStemmer());
    return new TokenStreamComponents(source, result);
}

Example 15 with SetKeywordMarkerFilter

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

the class RomanianAnalyzer 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 RomanianStemmer());
    return new TokenStreamComponents(source, result);
}