public virtual void TestWithKeywordAttribute()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("строеве");
MockTokenizer tokenStream = new MockTokenizer(new StringReader("строевете строеве"), MockTokenizer.WHITESPACE, false);
BulgarianStemFilter filter = new BulgarianStemFilter(new SetKeywordMarkerFilter(tokenStream, set));
AssertTokenStreamContents(filter, new string[] { "строй", "строеве" });
}
/// <summary>
/// Creates a
/// <see cref="Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <see cref="TextReader"/>.
/// </summary>
/// <returns> A
/// <see cref="Analyzer.TokenStreamComponents"/>
/// built from an <see cref="StandardTokenizer"/> filtered with
/// <see cref="StandardFilter"/>, <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>,
/// <see cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <see cref="BulgarianStemFilter"/>. </returns>
protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(m_matchVersion, reader);
TokenStream result = new StandardFilter(m_matchVersion, source);
result = new LowerCaseFilter(m_matchVersion, result);
result = new StopFilter(m_matchVersion, result, m_stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new BulgarianStemFilter(result);
return(new TokenStreamComponents(source, result));
}
public virtual void TestWithKeywordAttribute()
{
CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("строеве");
MockTokenizer tokenStream = new MockTokenizer(new StringReader("строевете строеве"), MockTokenizer.WHITESPACE, false);
BulgarianStemFilter filter = new BulgarianStemFilter(new SetKeywordMarkerFilter(tokenStream, set));
AssertTokenStreamContents(filter, new string[] { "строй", "строеве" });
}
