jieba分词

1.引入依赖

?

1 2 3 4 5

<dependency>     <groupId>com.huaban</groupId>     <artifactId>jieba-analysis</artifactId>     <version>1.0.2</version> </dependency>

2.分词工具类

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33

package com.itcast.utils;   import com.huaban.analysis.jieba.JiebaSegmenter; import com.huaban.analysis.jieba.SegToken; import com.huaban.analysis.jieba.WordDictionary; import java.io.*; import java.nio.file.*; import java.util.ArrayList; import java.util.List;   public class JiebaAnalyzerUtil {       /*     *对语句进行分词     *@Param text 语句     *@return 分词后的集合     *@throws IOException     */     public List segment(String text) throws IOException {         List<Object> strings = new ArrayList<>();         //dict.txt 自定义词典         String path = getClass().getClassLoader().getResource("dict.txt").getPath();         Path upath = Paths.get(new File(path).getAbsolutePath());         WordDictionary.getInstance().loadUserDict(upath);         JiebaSegmenter jiebaSegmenter = new JiebaSegmenter();         List<SegToken> process = jiebaSegmenter.process(text, JiebaSegmenter.SegMode.SEARCH);         for (SegToken segToken : process) {             String word = segToken.word;             strings.add(word);         }         return strings;     } }

　3.测试

?

1 2	public static void main(String[] args) throws IOException {         String str= "亲爱的请帮忙推荐一个稳健型-理财基金1期封闭式净值型产品";<br> 　　　　List<String > segment = new JiebaAnalyzerUtil().segment(str); System.out.println(segment); }

4.未指定分词效果

?

1	[亲爱, 的, 请, 帮忙, 推荐, 一个, 稳健, 型, -, 理财, 基金, 1, 期, 封闭式, 净值, 型, 产品]

5.指定分词：

dict.txt中输入：

?

1 2 3 4

亲爱的 3 n 稳健型 3 n 理财基金1期 3 n 净值型产品  3 n

6.指定分词效果：

[亲爱的, 请, 帮忙, 推荐, 一个, 稳健型, -, 理财基金1期, 封闭式, 净值型产品]