Elasticsearch安装IK笔记

￡神魔★判官ぃ 2023-05-29 13:18 2阅读 0赞

## Elasticsearch6.3.1安装IK ##

1.下载插件

yum install unzip

2 下载elasticsearch-analysis-ik-6.3.1.zip  
https://github.com/medcl/elasticsearch-analysis-ik/releases  
3 拖入crt中  
4.在cd elasticsearch-6.3.1/plugins/下新建文件夹

mkdir ik

5 解压在相应位置

unzip elasticsearch-analysis-ik-6.3.1.zip -d elasticsearch-6.3.1/plugins/ik/

6 重启elasticsearch

su zpark
    cd /apps/elasticsearch-6.3.1/bin
    ./elasticsearch

7 启动kibana

[root@hdp-1 apps]# cd kibana-6.3.1-linux-x86_64
    [root@hdp-1 kibana-6.3.1-linux-x86_64]# cd bin/
    [root@hdp-1 bin]# ./kibana

8 上网查看喽  
http://hdp-1:5601/app/kibana

在kibana下的Dev Tools写

## 测试IK中文分词器的基本功能 ##

（1）ik\_smart  
（2）ik\_max\_word  
（3）新词  
输入

GET _analyze?pretty
    { 
      "analyzer": "ik_max_word",
      "text": "我是中国人"
    }
    GET _analyze?pretty
    { 
      "analyzer": "ik_smart",
      "text": "安徽省长江流域"
    }
    GET _analyze?pretty
    { 
      "analyzer": "ik_smart",
      "text": "王者荣耀"
    }

结果

{ 
      "tokens": [
        { 
          "token": "我",
          "start_offset": 0,
          "end_offset": 1,
          "type": "CN_CHAR",
          "position": 0
        },
        { 
          "token": "是",
          "start_offset": 1,
          "end_offset": 2,
          "type": "CN_CHAR",
          "position": 1
        },
        { 
          "token": "中国人",
          "start_offset": 2,
          "end_offset": 5,
          "type": "CN_WORD",
          "position": 2
        },
        { 
          "token": "中国",
          "start_offset": 2,
          "end_offset": 4,
          "type": "CN_WORD",
          "position": 3
        },
        { 
          "token": "国人",
          "start_offset": 3,
          "end_offset": 5,
          "type": "CN_WORD",
          "position": 4
        }
      ]
    }

{ 
      "tokens": [
        { 
          "token": "安徽省",
          "start_offset": 0,
          "end_offset": 3,
          "type": "CN_WORD",
          "position": 0
        },
        { 
          "token": "长江流域",
          "start_offset": 3,
          "end_offset": 7,
          "type": "CN_WORD",
          "position": 1
        }
      ]
    }
    
    
    { 
      "tokens": [
        { 
          "token": "王者",
          "start_offset": 0,
          "end_offset": 2,
          "type": "CN_WORD",
          "position": 0
        },
        { 
          "token": "荣耀",
          "start_offset": 2,
          "end_offset": 4,
          "type": "CN_WORD",
          "position": 1
        }
      ]
    }

## 4.4 扩展字典 ##

#### （1）查看已有词典 ####

[root@hdp-1 root]$ cd apps
    [root@hdp-1 apps]$ cd elasticsearch-6.3.1/
    [root@hdp-1 elasticsearch-6.3.1]$ cd plugins/
    [root@hdp-1 plugins]$ cd ik
    [root@hdp-1 ik]$ cd config/

#### （2）自定义词典 ####

在\[root@hdp-1 ik\]$ cd config/下新建文件  
mkdir newword.dic  
（vi newword.dic）  
cat newword.dic

老铁  
王者荣耀  
洪荒之力  
共有产权房  
一带一路

#### （3）更新配置 ####

在\[root@hdp-1 ik\]$ cd config/下  
vi 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">newword.dic</entry>
             
            <entry key="ext_stopwords"></entry>
            
            
            
            
    </properties>

#### （4）重启elasticsearch ####

之后检查是否加载了文档  
\[Dict Loading\] /root/apps/elasticsearch-6.3.1/plugins/ik/config/newword.dic

#### （5）重启Kibana ####

GET _analyze?pretty
    { 
      "analyzer": "ik_smart",
      "text": "王者荣耀"
    }

{ 
      "tokens": [
        { 
          "token": "王者荣耀",
          "start_offset": 0,
          "end_offset": 4,
          "type": "CN_WORD",
          "position": 0
        }
      ]
    }