spingboot + IKAnalyzer 实现中文分词

废话不多说，直接上代码。

1、pom.xml 文件

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

2、新建IKAnalyzer.cfg.xml文件，内容如下

<?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>
    <!--用户可以在这里配置自己的扩展字典 -->
    <entry key="ext_dict">local.dic;</entry>
    <!--用户可以在这里配置自己的扩展停止词字典 -->
    <entry key="ext_stopwords">stop.dic;</entry>
</properties>

3、新建local.dic 配置自己的扩展字典   和 stop.dic文件  配置自己的扩展停止词字典    内容举个例子

local.dic

正能量
微商

stop.dic

的
好
了

4、controller

public ReturnObject query(@RequestBody Map<String, Object> params) throws IOException {
        logger.info("queryLoveWord: params data ===> " + JSON.toJSONString(params));
        if (params.containsKey("keywords")) {
        	String keywords =     MyUtil.removeDuplicateLetters(params.get("keywords").toString());
        	List<String> fvs = new ArrayList<>();
        	if(keywords.length() > 1){        	
        		fvs = MyUtil.cutWord(keywords);
        	}
        	fvs.add(0, params.get("keywords").toString());
        	fvs = MyUtil.removeDuplicateKeepOrder(fvs);
        	params.put("fvs", fvs);
        }
		PageInfo<LoveWord> p = loveWordService.query(params);
        return new ReturnObject(ReturnCode.SUCCESS, p);
    }
    

5、util

// 整合IKAnalyzer中文分词
    public static List<String> cutWord(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;
    }
    
    // 字符串去重并且顺序不变
    public static String removeDuplicateLetters(String str){
    	if(StringUtils.isEmpty(str)){
    		return "";
    	}
    	StringBuffer sb = new StringBuffer();
    	for(int i = 0; i < str.length(); i++){
    		char everyword = str.charAt(i);
    		int firstIndex = str.indexOf(everyword);
    		int lastIndex = str.lastIndexOf(everyword);
    		if(lastIndex == firstIndex || firstIndex == i){
    			sb.append(everyword);
    		}
    	}
    	return sb.toString();
    }
    
    /**
     * 删除List中重复元素，并保持顺序
     * @param list 待去重的list
     * @return 去重后的list
     */
    public static <T> List<T> removeDuplicateKeepOrder(List<T> list){
        Set<T> set = new HashSet<T>();
        List<T> newList = new ArrayList<>();
        for (T element : list) {
            //set能添加进去就代表不是重复的元素
            if (set.add(element)){
            	newList.add(element);
            } 
        }
        list.clear();
        list.addAll(newList);
        return list;
    }

6、mybatis

<!-- 获取列表 -->
    <select id="query" parameterType="java.util.Map" resultType="com.hi.hailiaowenan.affair.bean.LoveWord">
    	select id, f_id as fId, f_id_name as fIdName, state, 
    	create_time as createTime, update_time as updateTime
    	from
    	<include refid="table_name"></include>
        <trim prefix="WHERE" prefixOverrides="AND | OR">
	    	<!-- 上架状态 -->        
	        <if test="state != null and state != '' or state == 0">
	    		and state = #{state}
	    	</if>
	    	<!-- 审核状态 -->        
	        <if test="active != null and active != '' or active == 0">
	    		and active = #{active}
	    	</if>
            <if test="content != null and content != ''">
		    	<!-- bind写法：预防SQL注入  匹配词语内容匹配 -->
		    	<bind name="pattern" value="'%'+content+'%'" />
                and content like #{pattern}
            </if>
            <if test="fIdName != null and fIdName != ''">
		    	<!-- bind写法：预防SQL注入  匹配词语标题匹配 -->
		    	<bind name="pattern" value="'%'+fIdName+'%'" />
                and f_id_name like #{pattern}
            </if>
	    	<if test="fvs != null and fvs.size > 0">
	    		and (
	            <foreach collection="fvs" open="(" close=")" separator="or" item="item">
	                content like CONCAT('%',#{item},'%') or f_id_name like CONCAT('%',#{item},'%') or title like CONCAT('%',#{item},'%')
	            </foreach>
	            )
	        </if>
        </trim>
    </select>

参考文章——

扫描二维码关注公众号，回复： 12900468 查看本文章

https://blog.csdn.net/tfstone/article/details/105785441

https://blog.csdn.net/chengyuqiang/article/details/102792839

拓展文章——IK Analyzer 热更新自定义词典

https://blog.csdn.net/litianxiang_kaola/article/details/103086088