elasticsearch系统学习笔记5-中文分词器

elasticsearch系统学习笔记5-中文分词器

IK

https://github.com/medcl/elasticsearch-analysis-ik

• Analyzer: ik_smart , ik_max_word
• Tokenizer: ik_smart , ik_max_word

1. 下载

下载地址 https://github.com/medcl/elasticsearch-analysis-ik/releases

本机下载 elasticsearch-analysis-ik-6.3.2.zip

2. 解压

目录名改为 analysis-ik

// 3. 将文件夹 analysis-ik/config 文件夹下的内容移动到 {ES_HOME}/config 目录下

4. 将解压后的目录移动到 {ES_HOME}/plugins 目录下

5. 重启 ES 服务

启动窗口加载日志会多出一些加载插件的信息：[YABPFPe] loaded plugin [analysis-ik]

---

测试：

GET /_analyze
{
  "text": "中华人民共和国国歌",
  "analyzer": "ik_smart"
}

{
  "tokens": [
    {
      "token": "中华人民共和国",
      "start_offset": 0,
      "end_offset": 7,
      "type": "CN_WORD",
      "position": 0
    },
    {
      "token": "国歌",
      "start_offset": 7,
      "end_offset": 9,
      "type": "CN_WORD",
      "position": 1
    }
  ]
}

GET /_analyze
{
  "text": "中华人民共和国国歌",
  "analyzer": "ik_max_word"
}

{
  "tokens": [
    {
      "token": "中华人民共和国",
      "start_offset": 0,
      "end_offset": 7,
      "type": "CN_WORD",
      "position": 0
    },
    {
      "token": "中华人民",
      "start_offset": 0,
      "end_offset": 4,
      "type": "CN_WORD",
      "position": 1
    },
    {
      "token": "中华",
      "start_offset": 0,
      "end_offset": 2,
      "type": "CN_WORD",
      "position": 2
    },
    {
      "token": "华人",
      "start_offset": 1,
      "end_offset": 3,
      "type": "CN_WORD",
      "position": 3
    },
    {
      "token": "人民共和国",
      "start_offset": 2,
      "end_offset": 7,
      "type": "CN_WORD",
      "position": 4
    },
    {
      "token": "人民",
      "start_offset": 2,
      "end_offset": 4,
      "type": "CN_WORD",
      "position": 5
    },
    {
      "token": "共和国",
      "start_offset": 4,
      "end_offset": 7,
      "type": "CN_WORD",
      "position": 6
    },
    {
      "token": "共和",
      "start_offset": 4,
      "end_offset": 6,
      "type": "CN_WORD",
      "position": 7
    },
    {
      "token": "国",
      "start_offset": 6,
      "end_offset": 7,
      "type": "CN_CHAR",
      "position": 8
    },
    {
      "token": "国歌",
      "start_offset": 7,
      "end_offset": 9,
      "type": "CN_WORD",
      "position": 9
    }
  ]
}