30彻底掌握IK中文分词_上机动手实战IK中文分词器的安装和使用

之前大家会发现，字段全部是用英文

其实我们用来进行搜索的，绝大多数，都是中文应用，很少做英文的 默认分词器standard：没有办法对中文进行合理分词的，只是将每个中文字符一个一个的切割开来，比如说中国人 --> 中 国 人

在搜索引擎领域，比较成熟和流行的中文分词起，就是ik分词器

中国人很喜欢吃油条

standard：中 国 人 很 喜 欢 吃 油 条 ik：中国人 很 喜欢 吃 油条

1、在elasticsearch中安装ik中文分词器

因为使用es的版本是5.6.0

（1）git clone https://github.com/medcl/elasticsearch-analysis-ik （2）git checkout tags/v5.6.0 （3）mvn package

或者直接访问https://github.com/medcl/elasticsearch-analysis-ik/releases/tag/v5.6.0去下载

（4）将target/releases/elasticsearch-analysis-ik-5.6.0.zip拷贝到es/plugins/ik目录下

（5）在es/plugins/ik下对elasticsearch-analysis-ik-5.6.0.zip进行解压缩

（6）删掉压缩包，重启es

2、ik分词器基础知识

两种analyzer：ik_max_word、ik_smart，你根据自己的需要自己选，但是一般是选用ik_max_word

ik_max_word: 会将文本做最细粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,中华人民,中华,华人,人民共和国,人民,人,民,共和国,共和,和,国国,国歌”，会穷尽各种可能的组合；

ik_smart: 会做最粗粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,国歌”。

ik_smart搜索共和国 --> 中华人民共和国和国歌，就搜不到了

3、ik分词器的使用

删除索引my_index

DELETE /my_index 

创建索引，设置text使用ik_max_word

PUT /my_index 
{
  "mappings": {
    "my_type": {
      "properties": {
        "text": {
          "type": "text",
          "analyzer": "ik_max_word"
        }
      }
    }
  }
}

增加数据

POST /my_index/my_type/_bulk
{ "index": { "_id": "1"} }
{ "text": "男子偷上万元发红包求交女友 被抓获时仍然单身" }
{ "index": { "_id": "2"} }
{ "text": "16岁少女为结婚“变”22岁 7年后想离婚被法院拒绝" }
{ "index": { "_id": "3"} }
{ "text": "深圳女孩骑车逆行撞奔驰 遭索赔被吓哭(图)" }
{ "index": { "_id": "4"} }
{ "text": "女人对护肤品比对男票好？网友神怼" }
{ "index": { "_id": "5"} }
{ "text": "为什么国内的街道招牌用的都是红黄配？" }

响应结果

{
  "took": 61,
  "errors": false,
  "items": [
    {
      "index": {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "1",
        "_version": 1,
        "result": "created",
        "_shards": {
          "total": 2,
          "successful": 1,
          "failed": 0
        },
        "created": true,
        "status": 201
      }
    },
    {
      "index": {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "2",
        "_version": 1,
        "result": "created",
        "_shards": {
          "total": 2,
          "successful": 1,
          "failed": 0
        },
        "created": true,
        "status": 201
      }
    },
    {
      "index": {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "3",
        "_version": 1,
        "result": "created",
        "_shards": {
          "total": 2,
          "successful": 1,
          "failed": 0
        },
        "created": true,
        "status": 201
      }
    },
    {
      "index": {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "4",
        "_version": 1,
        "result": "created",
        "_shards": {
          "total": 2,
          "successful": 1,
          "failed": 0
        },
        "created": true,
        "status": 201
      }
    },
    {
      "index": {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "5",
        "_version": 1,
        "result": "created",
        "_shards": {
          "total": 2,
          "successful": 1,
          "failed": 0
        },
        "created": true,
        "status": 201
      }
    }
  ]
}

测试分词器

GET /my_index/_analyze
{
  "text": "男子偷上万元发红包求交女友 被抓获时仍然单身",
  "analyzer": "ik_max_word"
}

响应结果

{
  "tokens": [
    {
      "token": "男子",
      "start_offset": 0,
      "end_offset": 2,
      "type": "CN_WORD",
      "position": 0
    },
    {
      "token": "偷上",
      "start_offset": 2,
      "end_offset": 4,
      "type": "CN_WORD",
      "position": 1
    },
    {
      "token": "上万",
      "start_offset": 3,
      "end_offset": 5,
      "type": "CN_WORD",
      "position": 2
    },
    {
      "token": "万元",
      "start_offset": 4,
      "end_offset": 6,
      "type": "CN_WORD",
      "position": 3
    },
    {
      "token": "万",
      "start_offset": 4,
      "end_offset": 5,
      "type": "TYPE_CNUM",
      "position": 4
    },
    {
      "token": "元",
      "start_offset": 5,
      "end_offset": 6,
      "type": "COUNT",
      "position": 5
    },
    {
      "token": "发红包",
      "start_offset": 6,
      "end_offset": 9,
      "type": "CN_WORD",
      "position": 6
    },
    {
      "token": "发红",
      "start_offset": 6,
      "end_offset": 8,
      "type": "CN_WORD",
      "position": 7
    },
    {
      "token": "红包",
      "start_offset": 7,
      "end_offset": 9,
      "type": "CN_WORD",
      "position": 8
    },
    {
      "token": "求",
      "start_offset": 9,
      "end_offset": 10,
      "type": "CN_CHAR",
      "position": 9
    },
    {
      "token": "交",
      "start_offset": 10,
      "end_offset": 11,
      "type": "CN_CHAR",
      "position": 10
    },
    {
      "token": "女友",
      "start_offset": 11,
      "end_offset": 13,
      "type": "CN_WORD",
      "position": 11
    },
    {
      "token": "被",
      "start_offset": 14,
      "end_offset": 15,
      "type": "CN_CHAR",
      "position": 12
    },
    {
      "token": "抓获",
      "start_offset": 15,
      "end_offset": 17,
      "type": "CN_WORD",
      "position": 13
    },
    {
      "token": "时",
      "start_offset": 17,
      "end_offset": 18,
      "type": "CN_CHAR",
      "position": 14
    },
    {
      "token": "仍然",
      "start_offset": 18,
      "end_offset": 20,
      "type": "CN_WORD",
      "position": 15
    },
    {
      "token": "单身",
      "start_offset": 20,
      "end_offset": 22,
      "type": "CN_WORD",
      "position": 16
    }
  ]
}

查询

GET /my_index/my_type/_search 
{
  "query": {
    "match": {
      "text": "16岁少女结婚好还是单身好？"
    }
  }
}

响应结果

{
  "took": 6,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": 3,
    "max_score": 2.6093416,
    "hits": [
      {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "2",
        "_score": 2.6093416,
        "_source": {
          "text": "16岁少女为结婚“变”22岁 7年后想离婚被法院拒绝"
        }
      },
      {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "4",
        "_score": 1.3300087,
        "_source": {
          "text": "女人对护肤品比对男票好？网友神怼"
        }
      },
      {
        "_index": "my_index",
        "_type": "my_type",
        "_id": "1",
        "_score": 0.26301134,
        "_source": {
          "text": "男子偷上万元发红包求交女友 被抓获时仍然单身"
        }
      }
    ]
  }
}