java 庖丁解牛_“庖丁解牛” 分词器实现

import java.io.IOException;

import java.io.StringReader;

import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.Token;

import org.apache.lucene.analysis.TokenStream;

/**

* 类说明

*

* @author 曾修建

* @version 创建时间：2014-7-17 下午05:56:54

*/

public class Cld_Analyz {

private static String testString1 = "中华人湖发民共和国在1949年建立，从此開始了新中国的伟大篇章";

private static String testString2 = "乒乓球拍卖完了";

public static void Analyz() {

Analyzer analyzer = new PaodingAnalyzer();

String indexStr = testString2;

StringReader reader = new StringReader(indexStr);

TokenStream ts = analyzer.tokenStream(indexStr, reader);

Token t=null;

StringBuffer sb=new StringBuffer();

try {

t = ts.next();

int i=0;

while (t != null) {

if(i==0){

sb.append(t.termText());

}

else{

sb.append(" AND "+t.termText());

}

t = ts.next();

i++;

}

} catch (IOException e) {

e.printStackTrace();

}

System.out.println("结果是： "+sb );

analyzer.close();

}

public static void main(String[] args) {

Analyz();

}

}

执行结果：

    乒乓 AND 乒乓球 AND 球拍 AND 拍卖 AND 卖完 AND 完了