java 使用Lucene+Paoding中文分词

百度云盘下载地址：

https://pan.baidu.com/s/1tnDXvQs9rBVSqnbMpxN3DQ

提取码：q9fh

1.引入jar包

• lucene-core-3.3.0.jar
• commons-logging.jar
• paoding.jar

2.加入字典

•  src/paoding/dic   下的所有文件
• src/paoding-dic-home.properties  来配置 指向字典目录 

#values are "system-env" or "this";
#if value is "this" , using the paoding.dic.home as dicHome if configed!
#paoding.dic.home.config-first=system-env
paoding.dic.home.config-first=this

#dictionary home (directory)
#"classpath:xxx" means dictionary home is in classpath.
#e.g "classpath:dic" means dictionaries are in "classes/dic" directory or any other classpath directory
paoding.dic.home=D:\\qiyulin\\workspace\\myapi\\src\\paoding\\dic

#seconds for dic modification detection
#paoding.dic.detector.interval=60

3.测试代码

import com.google.gson.Gson;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;

/***
 * @author qiyulin 实现分词
 * */
public class Fenci {

    public static Object [] start(String text){
       try {
           List<String> list = new ArrayList<String>();
           Analyzer analyzer = new PaodingAnalyzer();
           TokenStream tokenizer = analyzer.tokenStream("text", new StringReader(text));
           tokenizer.reset();
           CharTermAttribute offAtt = (CharTermAttribute) tokenizer.addAttribute(CharTermAttribute.class);
           while (tokenizer.incrementToken()) {
               list.add(offAtt.toString());
           }
           tokenizer.close();
           return list.toArray();
       }catch (Exception e){
           e.printStackTrace();
       }
       return new String[]{text};
    }

    public static void main(String args []){
        Object arr[]=start("这些沙糖桔怎么回事？");
        System.out.println(new Gson().toJson(arr));
    }
}

4.运行结果