//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testWithKeywordAttribute() throws java.io.IOException
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
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="BulgarianStemFilter"/>. </returns>
public override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new BulgarianStemFilter(result);
return(new TokenStreamComponents(source, result));
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testWithKeywordAttribute() throws java.io.IOException
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
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="BulgarianStemFilter"/>. </returns>
public override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new BulgarianStemFilter(result);
return new TokenStreamComponents(source, result);
}