Exemplos de org.apache.lucene.analysis.cjk CJKTokenizer em C# (CSharp)

Exemplo n.º 1

        protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
        {
            if (matchVersion.onOrAfter(Version.LUCENE_36))
            {
//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);
                // run the widthfilter first before bigramming, it sometimes combines characters.
                TokenStream result = new CJKWidthFilter(source);
                result = new LowerCaseFilter(matchVersion, result);
                result = new CJKBigramFilter(result);
                return(new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords)));
            }
            else
            {
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new CJKTokenizer(reader);
                Tokenizer source = new CJKTokenizer(reader);
                return(new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords)));
            }
        }

Exemplo n.º 2

Arquivo: CJKAnalyzer.cs Projeto: Cefa68000/lucenenet

	  protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
	  {
		if (matchVersion.onOrAfter(Version.LUCENE_36))
		{
//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);
		  // run the widthfilter first before bigramming, it sometimes combines characters.
		  TokenStream result = new CJKWidthFilter(source);
		  result = new LowerCaseFilter(matchVersion, result);
		  result = new CJKBigramFilter(result);
		  return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
		}
		else
		{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new CJKTokenizer(reader);
		  Tokenizer source = new CJKTokenizer(reader);
		  return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
		}
	  }