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

Example 41 with SetKeywordMarkerFilter

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

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

Example 42 with SetKeywordMarkerFilter

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

the class TestMorfologikAnalyzer method testKeywordAttrTokens.

/** */
public final void testKeywordAttrTokens() throws IOException {
    Analyzer a = new MorfologikAnalyzer() {

        @Override
        protected TokenStreamComponents createComponents(String field) {
            final CharArraySet keywords = new CharArraySet(1, false);
            keywords.add("liście");
            final Tokenizer src = new StandardTokenizer();
            TokenStream result = new StandardFilter(src);
            result = new SetKeywordMarkerFilter(result, keywords);
            result = new MorfologikFilter(result);
            return new TokenStreamComponents(src, result);
        }
    };
    assertAnalyzesTo(a, "liście danych", new String[] { "liście", "dany", "dana", "dane", "dać" }, new int[] { 0, 7, 7, 7, 7 }, new int[] { 6, 13, 13, 13, 13 }, new int[] { 1, 1, 0, 0, 0 });
    a.close();
}

Example 43 with SetKeywordMarkerFilter

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

the class TestHunspellStemFilter method testKeywordAttribute.

/** Simple test for KeywordAttribute */
public void testKeywordAttribute() throws IOException {
    MockTokenizer tokenizer = whitespaceMockTokenizer("lucene is awesome");
    tokenizer.setEnableChecks(true);
    HunspellStemFilter filter = new HunspellStemFilter(tokenizer, dictionary);
    assertTokenStreamContents(filter, new String[] { "lucene", "lucen", "is", "awesome" }, new int[] { 1, 0, 1, 1 });
    // assert with keyword marker
    tokenizer = whitespaceMockTokenizer("lucene is awesome");
    CharArraySet set = new CharArraySet(Arrays.asList("Lucene"), true);
    filter = new HunspellStemFilter(new SetKeywordMarkerFilter(tokenizer, set), dictionary);
    assertTokenStreamContents(filter, new String[] { "lucene", "is", "awesome" }, new int[] { 1, 1, 1 });
}

Example 44 with SetKeywordMarkerFilter

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

the class TestHungarianLightStemFilter method testKeyword.

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

Example 45 with SetKeywordMarkerFilter

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

the class TestGalicianMinimalStemFilter method testKeyword.

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