package cn.lucene;

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.analysis.util.CharArraySet;

public class test1 {

	public static final String[] china_stop = {"着", "的", "之", "式"};

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

		//把数组赋值到CharArraySet里

		CharArraySet cnstop=new CharArraySet(china_stop.length, true);

	    for(String value : china_stop) {

	    	cnstop.add(value);

	    }

	    //并把StandardAnalyzer默认的停用词加进来

	    cnstop.addAll(StandardAnalyzer.STOP_WORDS_SET);

	    System.out.println(cnstop);		

		Analyzer analyzer = new StandardAnalyzer(cnstop);

		TokenStream stream=  analyzer.tokenStream("", "中秋be之夜，享受着月华的孤独，享受着爆炸式的思维跃迁");

		//获取每个单词信息,获取词元文本属性

		CharTermAttribute cta = stream.addAttribute(CharTermAttribute.class);

		stream.reset();

        while(stream.incrementToken()){

            System.out.print("[" + cta + "]");

        }

        System.out.println();

		analyzer.close();

	}

}