private void button2_Click(object sender, EventArgs e) { Analyzer analyzer = new CJKAnalyzer(); TokenStream tokenStream = analyzer.TokenStream("", new StringReader("北京,Hi欢迎你们大家")); Lucene.Net.Analysis.Token token = null; while ((token = tokenStream.Next()) != null) { Console.WriteLine(token.TermText()); } }
private void button2_Click(object sender, EventArgs e) { Analyzer analyzer = new CJKAnalyzer(Version.LUCENE_30); TokenStream tokenStream = analyzer.TokenStream("", new StringReader("北京,欢迎你们所有人")); //var cta = tokenStream.AddAttribute<TermAttribute>(); while (tokenStream.IncrementToken()) { var str = tokenStream.GetAttribute <ITermAttribute>(); Console.WriteLine(str.Term); } }
protected void btnGetSegmentation_Click(object sender, EventArgs e) { string words = txtWords.Text; if (string.IsNullOrEmpty(words)) { return; } Analyzer analyzer = new CJKAnalyzer(); // CJK分词 → 二元分词 TokenStream tokenStream = analyzer.TokenStream("", new StringReader(words)); Token token = null; while ((token = tokenStream.Next()) != null) // 只要还有词,就不返回null { string word = token.TermText(); // token.TermText() 取得当前分词 Response.Write(word + " | "); } }