.NET中文分词

 这两天因为需要就研究了.net环境下的中文分词，发现在目前的最高2.3.1Lucene.net版本下中文分词效果不好，他自带了一些分词器，均没有什么效果，出来单词切分，连JCK二分法都不提供，更谈不上基于词典的分词了。

        下面我发俩段代码，前一段是我通过写一个二分法类来实现双字切分，后一段是通过调用肖波的分词器，自己又写了一个.net环境接口来实现基于词典的分词，以供大家学习之用……

代码段一

using System; using System.Collections.Generic; using System.Linq; using System.Text; using Lucene.Net.Analysis.Standard; using Lucene.Net.Analysis; using System.IO; using System.Net; using System.Collections; namespace erfenfa { private class filter { public static void main(string [ ]arg) { string str="我们都是好孩子，即使你不同意，但又能如何，是不？"; TextReader tr = new StringReader(str ); CJKAnalyzer wa = new CJKAnalyzer(); TokenStream ts = wa.TokenStream("*",tr); Token t = null; while ((t = ts.Next()) != null) { messagebox.show(t.TermText().ToString());//实现循环输出 } } } public class CJKAnalyzer:Analyzer { public static string[] STOP_WORDS = { "a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "s", "such", "t", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with", "", "www" }; private Hashtable stopTable; public CJKAnalyzer() { stopTable = StopFilter.MakeStopSet(STOP_WORDS); } public CJKAnalyzer(string[] stopWords) { stopTable = StopFilter.MakeStopSet(stopWords); } public override To