/// <summary> Creates a TokenStream which tokenizes all the text in the provided Reader.
///
/// </summary>
/// <returns> A TokenStream build from a RussianLetterTokenizer filtered with
/// RussianLowerCaseFilter, StopFilter, and RussianStemFilter
/// </returns>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new RussianLetterTokenizer(reader, charset);
result = new RussianLowerCaseFilter(result, charset);
result = new StopFilter(result, stopSet);
result = new RussianStemFilter(result, charset);
return(result);
}
/// <summary> Creates a TokenStream which tokenizes all the text in the provided Reader.
///
/// </summary>
/// <returns> A TokenStream build from a StandardTokenizer filtered with
/// StandardFilter, LowerCaseFilter, StopFilter, GermanStemFilter
/// </returns>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
result = new StopFilter(result, stopSet);
result = new GermanStemFilter(result, exclusionSet);
return(result);
}
/// <summary> Creates a TokenStream which tokenizes all the text in the provided Reader.
///
/// </summary>
/// <returns> A TokenStream build from a StandardTokenizer filtered with
/// StandardFilter, LowerCaseFilter, StopFilter, GermanStemFilter
/// </returns>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
result = new StopFilter(result, stopSet);
result = new GermanStemFilter(result, exclusionSet);
return result;
}
/// <summary> Creates a TokenStream which tokenizes all the text in the provided Reader.
///
/// </summary>
/// <returns> A TokenStream build from a RussianLetterTokenizer filtered with
/// RussianLowerCaseFilter, StopFilter, and RussianStemFilter
/// </returns>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new RussianLetterTokenizer(reader, charset);
result = new RussianLowerCaseFilter(result, charset);
result = new StopFilter(result, stopSet);
result = new RussianStemFilter(result, charset);
return result;
}
/// <summary> Builds an exclusionlist from an array of Strings.</summary>
public virtual void SetStemExclusionTable(System.String[] exclusionlist)
{
exclusionSet = StopFilter.MakeStopSet(exclusionlist);
}
/// <summary> Builds an analyzer with the given stop words.</summary>
public GermanAnalyzer(System.String[] stopwords)
{
stopSet = StopFilter.MakeStopSet(stopwords);
}
/// <summary> Builds an analyzer.</summary>
public GermanAnalyzer()
{
stopSet = StopFilter.MakeStopSet(GERMAN_STOP_WORDS);
}
/// <summary> Builds an analyzer with the given stop words.</summary>
public RussianAnalyzer(char[] charset, System.String[] stopwords)
{
this.charset = charset;
stopSet = StopFilter.MakeStopSet(stopwords);
}
/// <summary> Builds an analyzer.</summary>
public RussianAnalyzer(char[] charset)
{
this.charset = charset;
stopSet = StopFilter.MakeStopSet(makeStopWords(charset));
}
public RussianAnalyzer()
{
charset = RussianCharsets.UnicodeRussian;
stopSet = StopFilter.MakeStopSet(makeStopWords(RussianCharsets.UnicodeRussian));
}