13、自定义Analyzer实现字长过滤

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u013115157/article/details/53690632

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.miscellaneous.LengthFilter;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import java.io.IOException;

/**
 * Created by kangz on 2016/12/16.
 * 自定义Analyzer实现扩展停用词
 */
public class MyAnalzerlen extends Analyzer {

    public MyAnalzerlen(int len) {
        this.len = len;
    }

    private int len;  //过虑的长度

    public int getLen() {
        return len;
    }

    public void setLen(int len) {
        this.len = len;
    }


    @Override
    protected TokenStreamComponents createComponents(String s) {
        Tokenizer source = new WhitespaceTokenizer();
        TokenStream tokenStream = new LengthFilter(source, len, 6);//  分词器 最小长度开区间  最大长度闭区间
        return new TokenStreamComponents(source, tokenStream);
        //return new TokenStreamComponents(source, new StopFilter(source, stopWordSet));
    }
    public static void main(String[] args) throws Exception {

        //把长度小于2的过滤掉，开区间
        Analyzer analyzer = new MyAnalzerlen(2);
        String words = "I am a java coder ! jjjuje !";
        TokenStream stream = analyzer.tokenStream("myfield", words);
        try {
            stream.reset();
            CharTermAttribute offsetAtt = stream.addAttribute(CharTermAttribute.class);
            while (stream.incrementToken()) {
                System.out.println(offsetAtt.toString());
            }
            stream.end();
            stream.close();
        } catch (IOException e) {
        }
    }
}

TokenStream tokenStream = new LengthFilter(source, len, 6);// 分词器 最小长度开区间 最大长度闭区间 重点的一句话

下面是小编的微信转帐二维码，小编再次谢谢读者的支持，小编会更努力的

----请看下方↓↓↓↓↓↓↓

百度搜索 Drools从入门到精通：可下载开源全套Drools教程

深度Drools教程不段更新中：

更多Drools实战陆续发布中………

扫描下方二维码关注公众号 ↓↓↓↓↓↓↓↓↓↓