Elasticsearch 之（11）mapping引入

核心的数据类型

string

byte，short，integer，long

float，double

boolean

date

dynamic mapping （动态生成mapping）

true or false --> boolean

123 --> long

123.45 --> double

2017-01-01 --> date

"hello world" --> string/text

查看mapping

GET /index/_mapping/type

如何建立索引

analyzed

not_analyzed

no

修改mapping

只能创建index时手动建立mapping，或者新增field mapping，但是不能update field mapping

创建mapping

PUT /website
{
  "mappings": {
    "article": {
      "properties": {
        "author_id": {
          "type": "long"
        },
        "title": {
          "type": "text",
          "analyzer": "english"
        },
        "content": {
          "type": "text"
        },
        "post_date": {
          "type": "date"
        },
        "publisher_id": {
          "type": "text",
          "index": "not_analyzed"
        }
      }
    }
  }
}

只能新增不能修改，即创建后，无法修改

PUT /website
{
  "mappings": {
    "article": {
      "properties": {
        "author_id": {
          "type": "text"
        }
      }
    }
  }
}

{
  "error": {
    "root_cause": [
      {
        "type": "index_already_exists_exception",
        "reason": "index [website/co1dgJ-uTYGBEEOOL8GsQQ] already exists",
        "index_uuid": "co1dgJ-uTYGBEEOOL8GsQQ",
        "index": "website"
      }
    ],
    "type": "index_already_exists_exception",
    "reason": "index [website/co1dgJ-uTYGBEEOOL8GsQQ] already exists",
    "index_uuid": "co1dgJ-uTYGBEEOOL8GsQQ",
    "index": "website"
  },
  "status": 400
}

PUT /website/_mapping/article
{
  "properties" : {
    "new_field" : {
      "type" :    "string",
      "index":    "not_analyzed"
    }
  }
}

测试mapping

GET /website/_analyze
{
  "field": "content",
  "text": "my-dogs" 
}

GET website/_analyze
{
  "field": "new_field",
  "text": "my dogs"
}

{
  "error": {
    "root_cause": [
      {
        "type": "remote_transport_exception",
        "reason": "[4onsTYV][127.0.0.1:9300][indices:admin/analyze[s]]"
      }
    ],
    "type": "illegal_argument_exception",
    "reason": "Can't process field [new_field], Analysis requests are only supported on tokenized fields"
  },
  "status": 400
}

multivalue field

{ "tags": [ "tag1", "tag2" ]}

建立索引时与string是一样的，数据类型不能混

empty field

null，[]，[null]

object field

PUT /company/employee/1
{
  "address": {
    "country": "china",
    "province": "guangdong",
    "city": "guangzhou"
  },
  "name": "jack",
  "age": 27,
  "join_date": "2017-01-01"
}

address：object类型

{
  "company": {
    "mappings": {
      "employee": {
        "properties": {
          "address": {
            "properties": {
              "city": {
                "type": "text",
                "fields": {
                  "keyword": {
                    "type": "keyword",
                    "ignore_above": 256
                  }
                }
              },
              "country": {
                "type": "text",
                "fields": {
                  "keyword": {
                    "type": "keyword",
                    "ignore_above": 256
                  }
                }
              },
              "province": {
                "type": "text",
                "fields": {
                  "keyword": {
                    "type": "keyword",
                    "ignore_above": 256
                  }
                }
              }
            }
          },
          "age": {
            "type": "long"
          },
          "join_date": {
            "type": "date"
          },
          "name": {
            "type": "text",
            "fields": {
              "keyword": {
                "type": "keyword",
                "ignore_above": 256
              }
            }
          }
        }
      }
    }
  }
}

存储格式

{
  "address": {
    "country": "china",
    "province": "guangdong",
    "city": "guangzhou"
  },
  "name": "jack",
  "age": 27,
  "join_date": "2017-01-01"
}

{
    "name":            [jack],
    "age":          [27],
    "join_date":      [2017-01-01],
    "address.country":         [china],
    "address.province":   [guangdong],
    "address.city":  [guangzhou]
}

{
    "authors": [
        { "age": 26, "name": "Jack White"},
        { "age": 55, "name": "Tom Jones"},
        { "age": 39, "name": "Kitty Smith"}
    ]
}

{
    "authors.age":    [26, 55, 39],
    "authors.name":   [jack, white, tom, jones, kitty, smith]
}

root object

就是某个type对应的mapping json，包括了properties，metadata（_id，_source，_type），settings（analyzer），其他settings（比如include_in_all）

PUT /my_index
{
  "mappings": {
    "my_type": {
      "properties": {}
    }
  }
}

properties

type，index，analyzer

PUT /my_index/_mapping/my_type
{
  "properties": {
    "title": {
      "type": "text",
      "index": true,
      "analyzer": "standard"
    }
  }
}

_source

（1）查询的时候，直接可以拿到完整的document，不需要先拿document id，再发送一次请求拿document

（2）partial update基于_source实现

（3）reindex时，直接基于_source实现，不需要从数据库（或者其他外部存储）查询数据再修改

（4）可以基于_source定制返回field

（5）debug query更容易，因为可以直接看到_source

如果不需要上述，可以禁用_source

PUT /my_index/_mapping/my_type2
{
  "_source": {"enabled": false}
}

_all

将所有field打包在一起，作为一个_all field，建立索引。没指定任何field进行搜索时，就是使用_all field在搜索。

PUT /my_index/_mapping/my_type3
{
  "_all": {"enabled": false}
}

也可以在field级别设置include_in_all field，设置是否要将field的值包含在_all field中

PUT /my_index/_mapping/my_type4
{
  "properties": {
    "my_field": {
      "type": "text",
      "include_in_all": false
    }
  }
}

标识性metadata

_index，_type，_id

定制dynamic策略

true：遇到陌生字段，就进行dynamic mapping

false：遇到陌生字段，就忽略

strict：遇到陌生字段，就报错

PUT /my_index
{
  "mappings": {
    "my_type": {
      "dynamic": "strict",
      "properties": {
        "title": {
          "type": "text"
        },
        "address": {
          "type": "object",
          "dynamic": "true"
        }
      }
    }
  }
}

PUT /my_index/my_type/1
{
  "title": "my article",
  "content": "this is my article",
  "address": {
    "province": "guangdong",
    "city": "guangzhou"
  }
}

{
  "error": {
    "root_cause": [
      {
        "type": "strict_dynamic_mapping_exception",
        "reason": "mapping set to strict, dynamic introduction of [content] within [my_type] is not allowed"
      }
    ],
    "type": "strict_dynamic_mapping_exception",
    "reason": "mapping set to strict, dynamic introduction of [content] within [my_type] is not allowed"
  },
  "status": 400
}

PUT /my_index/my_type/1
{
  "title": "my article",
  "address": {
    "province": "guangdong",
    "city": "guangzhou"
  }
}

GET /my_index/_mapping/my_type

{
  "my_index": {
    "mappings": {
      "my_type": {
        "dynamic": "strict",
        "properties": {
          "address": {
            "dynamic": "true",
            "properties": {
              "city": {
                "type": "text",
                "fields": {
                  "keyword": {
                    "type": "keyword",
                    "ignore_above": 256
                  }
                }
              },
              "province": {
                "type": "text",
                "fields": {
                  "keyword": {
                    "type": "keyword",
                    "ignore_above": 256
                  }
                }
              }
            }
          },
          "title": {
            "type": "text"
          }
        }
      }
    }
  }
}

定制dynamic mapping策略

（1）date_detection

默认会按照一定格式识别date，比如yyyy-MM-dd。但是如果某个field先过来一个2017-01-01的值，就会被自动dynamic mapping成date，后面如果再来一个"hello world"之类的值，就会报错。可以手动关闭某个type的date_detection，如果有需要，自己手动指定某个field为date类型。

PUT /my_index/_mapping/my_type
{
    "date_detection": false
}

（2）定制自己的dynamic mapping template（type level）

PUT /my_index
{
    "mappings": {
        "my_type": {
            "dynamic_templates": [
                { "en": {
                      "match":              "*_en", 
                      "match_mapping_type": "string",
                      "mapping": {
                          "type":           "string",
                          "analyzer":       "english"
                      }
                }}
            ]
}}}

PUT /my_index/my_type/1
{
  "title": "this is my first article"
}

PUT /my_index/my_type/2
{
  "title_en": "this is my first article"
}

title没有匹配到任何的dynamic模板，默认就是standard分词器，不会过滤停用词，is会进入倒排索引，用is来搜索是可以搜索到的

title_en匹配到了dynamic模板，就是english分词器，会过滤停用词，is这种停用词就会被过滤掉，用is来搜索就搜索不到了

（3）定制自己的default mapping template（index level）

PUT /my_index
{
    "mappings": {
        "_default_": {
            "_all": { "enabled":  false }
        },
        "blog": {
            "_all": { "enabled":  true  }
        }
    }
}