Exemple #1
0
        public IList <string> TestClassicTokenizerReturnDelimiterTrue(string text)
        {
            var            tokenizer = new ClassicTokenizer(true);
            IList <string> tokens    = tokenizer.Tokenize(text);

            return(tokens);
        }
Exemple #2
0
        private static void SentenceSegmentation()
        {
            var               paragraph = "Prof. Dr. Ahmet Bey 1.6 oranında artış var dedi 2. kez. E-posta adresi [email protected] imiş! Doğru mu?";
            ITokenizer        tokenizer = new ClassicTokenizer(true);
            SentenceSegmenter segmenter = new TokenBasedSentenceSegmenter(tokenizer);
            var               sentences = segmenter.GetSentences(paragraph);

            foreach (string sentence in sentences)
            {
                Console.WriteLine(sentence);
            }
        }
 public TokenStreamComponentsAnonymousInnerClassHelper(ClassicAnalyzer outerInstance, ClassicTokenizer src, TokenStream tok, Reader reader)
     : base(src, tok)
 {
     this.outerInstance = outerInstance;
     this.reader = reader;
     this.src = src;
 }
 public override TokenStreamComponents CreateComponents(string fieldName, Reader reader)
 {
     var src = new ClassicTokenizer(matchVersion, reader);
     src.MaxTokenLength = maxTokenLength;
     TokenStream tok = new ClassicFilter(src);
     tok = new LowerCaseFilter(matchVersion, tok);
     tok = new StopFilter(matchVersion, tok, stopwords);
     return new TokenStreamComponentsAnonymousInnerClassHelper(this, src, tok, reader);
 }
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
//ORIGINAL LINE: @Override protected TokenStreamComponents createComponents(final String fieldName, final java.io.Reader reader)
	  protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
	  {
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final ClassicTokenizer src = new ClassicTokenizer(matchVersion, reader);
		ClassicTokenizer src = new ClassicTokenizer(matchVersion, reader);
		src.MaxTokenLength = maxTokenLength;
		TokenStream tok = new ClassicFilter(src);
		tok = new LowerCaseFilter(matchVersion, tok);
		tok = new StopFilter(matchVersion, tok, stopwords);
		return new TokenStreamComponentsAnonymousInnerClassHelper(this, src, tok, reader);
	  }
 public override ClassicTokenizer create(AttributeFactory factory, Reader input)
 {
     ClassicTokenizer tokenizer = new ClassicTokenizer(luceneMatchVersion, factory, input);
     tokenizer.MaxTokenLength = maxTokenLength;
     return tokenizer;
 }