//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testDecomposed3() throws Exception
public virtual void testDecomposed3()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0049\u0307"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] { "i" });
}
/// <summary>
/// Test decomposed forms with additional accents
/// In this example, U+0049 + U+0316 + U+0307 is canonically equivalent
/// to U+0130 + U+0316, and is lowercased the same way.
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testDecomposed2() throws Exception
public virtual void testDecomposed2()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0049\u0316\u0307STANBUL \u0049\u0307ZM\u0049\u0307R I\u0316SPARTA"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] { "i\u0316stanbul", "izmir", "\u0131\u0316sparta" });
}
/// <summary>
/// Test composed forms
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testTurkishLowerCaseFilter() throws Exception
public virtual void testTurkishLowerCaseFilter()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0130STANBUL \u0130ZM\u0130R ISPARTA"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] { "istanbul", "izmir", "\u0131sparta" });
}
/// <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="TurkishLowerCaseFilter"/>,
/// <seealso cref="StopFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> if a stem
/// exclusion set is provided and <seealso cref="SnowballFilter"/>. </returns>
protected internal 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);
if (matchVersion.onOrAfter(Version.LUCENE_48))
{
result = new ApostropheFilter(result);
}
result = new TurkishLowerCaseFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new TurkishStemmer());
return(new TokenStreamComponents(source, result));
}
/// <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="TurkishLowerCaseFilter"/>,
/// <seealso cref="StopFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> if a stem
/// exclusion set is provided and <seealso cref="SnowballFilter"/>. </returns>
protected internal 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);
if (matchVersion.onOrAfter(Version.LUCENE_48))
{
result = new ApostropheFilter(result);
}
result = new TurkishLowerCaseFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new TurkishStemmer());
return new TokenStreamComponents(source, result);
}
/// <summary>
/// Test composed forms
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testTurkishLowerCaseFilter() throws Exception
public virtual void testTurkishLowerCaseFilter()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0130STANBUL \u0130ZM\u0130R ISPARTA"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] {"istanbul", "izmir", "\u0131sparta"});
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testDecomposed3() throws Exception
public virtual void testDecomposed3()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0049\u0307"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] {"i"});
}
/// <summary>
/// Test decomposed forms with additional accents
/// In this example, U+0049 + U+0316 + U+0307 is canonically equivalent
/// to U+0130 + U+0316, and is lowercased the same way.
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testDecomposed2() throws Exception
public virtual void testDecomposed2()
{
TokenStream stream = new MockTokenizer(new StringReader("\u0049\u0316\u0307STANBUL \u0049\u0307ZM\u0049\u0307R I\u0316SPARTA"), MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilter filter = new TurkishLowerCaseFilter(stream);
assertTokenStreamContents(filter, new string[] {"i\u0316stanbul", "izmir", "\u0131\u0316sparta"});
}