ik分词 java_Java实现使用IK Analyzer实现中文分词

lucene-core-3.6.0.jar

什么都不用改

示例代码如下(使用IK Analyzer):

[java] view plaincopy

package com.haha.test;

import java.io.IOException;

import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.TokenStream;

import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import org.wltea.analyzer.lucene.IKAnalyzer;

public class Test2 {

public static void main(String[] args) throws IOException {

String text="基于java语言开发的轻量级的中文分词工具包";

//创建分词对象

Analyzer anal=new IKAnalyzer(true);

StringReader reader=new StringReader(text);

//分词

TokenStream ts=anal.tokenStream("", reader);

CharTermAttribute term=ts.getAttribute(CharTermAttribute.class);

//遍历分词数据

while(ts.incrementToken()){

System.out.print(term.toString()+"|");

}

reader.close();

System.out.println();

}

}