SpringBoot 2.x整合IKAnalyzer中文分词

柔光的暖阳◎ 2023-06-11 04:22 37阅读 0赞

**废话不多说，直接上代码。**

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70]

### 1、pom.xml ###

<dependency>
                <groupId>com.janeluo</groupId>
                <artifactId>ikanalyzer</artifactId>
                <version>2012_u6</version>
     </dependency>

### 2、ik配置 ###

IKAnalyzer.cfg.xml

<?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
    <properties>
        <comment>IK Analyzer 扩展配置</comment>
        
        <entry key="ext_dict">local.dic;</entry>
        
        <entry key="ext_stopwords">stop.dic;</entry>
    </properties>

local.dic

中国太平
    中国太平洋

stop.dic

的
    好
    了

### 3、测试程序 ###

package com.example.ik;
    
    import org.wltea.analyzer.core.IKSegmenter;
    import org.wltea.analyzer.core.Lexeme;
    import java.io.IOException;
    import java.io.StringReader;
    import java.util.ArrayList;
    import java.util.List;
    
    public class IKAnalyzerUtil {
        
    
        public static List<String> cut(String msg) throws IOException {
        
            StringReader sr=new StringReader(msg);
            IKSegmenter ik=new IKSegmenter(sr, true);
            Lexeme lex=null;
            List<String> list=new ArrayList<>();
            while((lex=ik.next())!=null){
        
                list.add(lex.getLexemeText());
            }
            return list;
        }
        
        public static void main(String[] args) throws IOException {
        
            String text="中国太平成立九十周年了！";
            List<String> list=IKAnalyzerUtil.cut(text);
            System.out.println(list);
        }
    }

执行结果

加载扩展词典：local.dic
    加载扩展停止词典：stop.dic
    [中国太平, 成立, 九十周年]

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 1]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70]: /images/20230531/45e4a0c9735e4ae783ab6ee6118fd505.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 1]: /images/20230531/b6ee0d1d113f40e18f32768f2a24d3b4.png