Lucene 4.4 环境测试

package com.zsj.test;

import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.TokenStream;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

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

import org.apache.lucene.util.Version;

/**

* Lu

* @author hadoop

*

*/

public class FirstLucene {

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

/**

* 标准分析器是Lucene内置的分析器,会将语汇单元转成小写形式，

* 并去除停用词及标点符号，很明显也是不适合于中文环境

*/

Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);

TokenStream tokenStream = analyzer.tokenStream("",

"this is my first lucene");

CharTermAttribute charTermAttribute = tokenStream

.addAttribute(CharTermAttribute.class);

tokenStream.reset();

while (tokenStream.incrementToken()) {

System.out.println(charTermAttribute.toString());

}

tokenStream.end();

tokenStream.close();

}

}