SearchApi

ES支持两种基本方式检索

• 通过Rest request URI 发送搜索参数(uri + 检索参数)
• 通过Rest request body 发送 (uri + 请求体)

在kibana工具箱Dev Tools执行

GET /bank/_search?q=*&sort=account_number:asc

说明:

• /bank 查询bank索引下的数据
• _search 固定语法，查询
• q=* 查询所有
• sort=account_number:asc 排序规则，按照account_number字段升序排序

查询结果如下

{
  "took" : 121,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1000,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "0",
        "_score" : null,
        "_source" : {
          "account_number" : 0,
          "balance" : 16623,
          "firstname" : "Bradshaw",
          "lastname" : "Mckenzie",
          "age" : 29,
          "gender" : "F",
          "address" : "244 Columbus Place",
          "employer" : "Euron",
          "email" : "[email protected]",
          "city" : "Hobucken",
          "state" : "CO"
        },
        "sort" : [
          0
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "1",
        "_score" : null,
        "_source" : {
          "account_number" : 1,
          "balance" : 39225,
          "firstname" : "Amber",
          "lastname" : "Duke",
          "age" : 32,
          "gender" : "M",
          "address" : "880 Holmes Lane",
          "employer" : "Pyrami",
          "email" : "[email protected]",
          "city" : "Brogan",
          "state" : "IL"
        },
        "sort" : [
          1
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "2",
        "_score" : null,
        "_source" : {
          "account_number" : 2,
          "balance" : 28838,
          "firstname" : "Roberta",
          "lastname" : "Bender",
          "age" : 22,
          "gender" : "F",
          "address" : "560 Kingsway Place",
          "employer" : "Chillium",
          "email" : "[email protected]",
          "city" : "Bennett",
          "state" : "LA"
        },
        "sort" : [
          2
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "3",
        "_score" : null,
        "_source" : {
          "account_number" : 3,
          "balance" : 44947,
          "firstname" : "Levine",
          "lastname" : "Burks",
          "age" : 26,
          "gender" : "F",
          "address" : "328 Wilson Avenue",
          "employer" : "Amtap",
          "email" : "[email protected]",
          "city" : "Cochranville",
          "state" : "HI"
        },
        "sort" : [
          3
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "4",
        "_score" : null,
        "_source" : {
          "account_number" : 4,
          "balance" : 27658,
          "firstname" : "Rodriquez",
          "lastname" : "Flores",
          "age" : 31,
          "gender" : "F",
          "address" : "986 Wyckoff Avenue",
          "employer" : "Tourmania",
          "email" : "[email protected]",
          "city" : "Eastvale",
          "state" : "HI"
        },
        "sort" : [
          4
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "5",
        "_score" : null,
        "_source" : {
          "account_number" : 5,
          "balance" : 29342,
          "firstname" : "Leola",
          "lastname" : "Stewart",
          "age" : 30,
          "gender" : "F",
          "address" : "311 Elm Place",
          "employer" : "Diginetic",
          "email" : "[email protected]",
          "city" : "Fairview",
          "state" : "NJ"
        },
        "sort" : [
          5
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "6",
        "_score" : null,
        "_source" : {
          "account_number" : 6,
          "balance" : 5686,
          "firstname" : "Hattie",
          "lastname" : "Bond",
          "age" : 36,
          "gender" : "M",
          "address" : "671 Bristol Street",
          "employer" : "Netagy",
          "email" : "[email protected]",
          "city" : "Dante",
          "state" : "TN"
        },
        "sort" : [
          6
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "7",
        "_score" : null,
        "_source" : {
          "account_number" : 7,
          "balance" : 39121,
          "firstname" : "Levy",
          "lastname" : "Richard",
          "age" : 22,
          "gender" : "M",
          "address" : "820 Logan Street",
          "employer" : "Teraprene",
          "email" : "[email protected]",
          "city" : "Shrewsbury",
          "state" : "MO"
        },
        "sort" : [
          7
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "8",
        "_score" : null,
        "_source" : {
          "account_number" : 8,
          "balance" : 48868,
          "firstname" : "Jan",
          "lastname" : "Burns",
          "age" : 35,
          "gender" : "M",
          "address" : "699 Visitation Place",
          "employer" : "Glasstep",
          "email" : "[email protected]",
          "city" : "Wakulla",
          "state" : "AZ"
        },
        "sort" : [
          8
        ]
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "9",
        "_score" : null,
        "_source" : {
          "account_number" : 9,
          "balance" : 24776,
          "firstname" : "Opal",
          "lastname" : "Meadows",
          "age" : 39,
          "gender" : "M",
          "address" : "963 Neptune Avenue",
          "employer" : "Cedward",
          "email" : "[email protected]",
          "city" : "Olney",
          "state" : "OH"
        },
        "sort" : [
          9
        ]
      }
    ]
  }
}

参数说明

• took – Elasticsearch运行查询所需的时间（以毫秒为单位）

• timed_out –搜索请求是否超时

• _shards –搜索了多少个分片，以及成功，失败或跳过了多少个分片。

• max_score –找到的最相关文件的分数

• hits.total.value -找到了多少个匹配的文档

• hits.sort -文档的排序位置（不按相关性得分排序时）

• hits._score-文档的相关性得分（使用时不适用match_all）

  在本示例 相应hits.total.value为1000，但发现记录里只有10条记录，这是因为
  默认情况下，hits响应部分包括符合搜索条件的前10个文档，类似于Mysql数据库的分页。Mysql分页使用limt

select *from user limt 5;  //返回结果集的前5行记录
select * from user limt 5,5  //从第6行开始，返回5行记录，也就是6, 7, 8, 9，10，这里的行索引是从0开始的

es也有类似的语法，可以使用 from 和 size 两个参数

GET /bank/_search?q=*&sort=account_number:asc&from=10&size=1

结果如下

{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1000,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "10",
        "_score" : null,
        "_source" : {
          "account_number" : 10,
          "balance" : 46170,
          "firstname" : "Dominique",
          "lastname" : "Park",
          "age" : 37,
          "gender" : "F",
          "address" : "100 Gatling Place",
          "employer" : "Conjurica",
          "email" : "[email protected]",
          "city" : "Omar",
          "state" : "NJ"
        },
        "sort" : [
          10
        ]
      }
    ]
  }
}

Query DSL

语法格式

elasticsearch提供了一个可以执行查询的Json风格的DSL(domain-specific-language领域特定语言)，这个称为 Query DSL。

Query DSL 基本使用

GET /bank/_search
{
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "account_number": "asc"
    },
    {
      "balance": {
        "order": "desc"
      }
    }
  ],
  "from": 10,
  "size": 10,
  "_source": ["account_number","balance"]
}

先按照 account_number 升序排序，再按照 balance 降序排序

• query —查询条件
• sort — 排序条件( “account_number”: "asc"为简写方式)
• match_all – 匹配所有
• _source —可以指定返回哪些字段，类似于Mysql中的 select name,age from user

match【匹配查询】

• 基本类型(非字符串)，精确匹配

查询 1号用户的数据文档

GET /bank/_search
{
  "query": {
    "match": {
      "account_number": 1
    }
  }
}

kibana查询结果如下

{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "account_number" : 1,
          "balance" : 39225,
          "firstname" : "Amber",
          "lastname" : "Duke",
          "age" : 32,
          "gender" : "M",
          "address" : "880 Holmes Lane",
          "employer" : "Pyrami",
          "email" : "[email protected]",
          "city" : "Brogan",
          "state" : "IL"
        }
      }
    ]
  }
}

使用match匹配查询，会有 max_score 以及 _score 得分情况,es会根据这个得分排序返回，得分越高越靠前

match也可以模糊匹配，匹配字段是字符串， es会将 字段匹配值进行分词，查询

GET /bank/_search
{
  "query": {
    "match": {
      "address": "Kings"
    }
  }
}

结果如下

{
  "took" : 5,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 5.9908285,
    "hits" : [
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "20",
        "_score" : 5.9908285,
        "_source" : {
          "account_number" : 20,
          "balance" : 16418,
          "firstname" : "Elinor",
          "lastname" : "Ratliff",
          "age" : 36,
          "gender" : "M",
          "address" : "282 Kings Place",
          "employer" : "Scentric",
          "email" : "[email protected]",
          "city" : "Ribera",
          "state" : "WA"
        }
      },
      {
        "_index" : "bank",
        "_type" : "account",
        "_id" : "722",
        "_score" : 5.9908285,
        "_source" : {
          "account_number" : 722,
          "balance" : 27256,
          "firstname" : "Roberts",
          "lastname" : "Beasley",
          "age" : 34,
          "gender" : "F",
          "address" : "305 Kings Hwy",
          "employer" : "Quintity",
          "email" : "[email protected]",
          "city" : "Hayden",
          "state" : "PA"
        }
      }
    ]
  }
}

match_phrase【短语匹配】

将需要匹配的值当成一个整体单词(不会被分词)，进行检索
例如: “address”: “mill road”
如果使用match查询，es会将mill road分词成 mill 和road,只要address字段含有mill，road其一就会被检索出来,并给出相关性得分。
如果使用match_phrase，只有address含有 mill road这个短语的才会被检索出来，例如：
xxx mill road xxx会被检索出来， mill xxx road就不会被检索出来

GET /bank/_search
{
  "query": {
    "match_phrase": {
      "address": "mill road"
    }
  }
}

multi_match【多字段匹配】

示例: 查询 addrss 或 status 包含 mill的文档数据

GET /bank/_search
{
  "query": {
    "multi_match": {
      "query": "mill",
      "fields": ["address","state"]
    }
  }
}

类似于Mysql中 address like ‘%mill%’ or status like '%mill%'

注意:
multi_match 也会进行分词查询

GET /bank/_search
{
  "query": {
    "multi_match": {
      "query": "mill movico",
      "fields": ["address","city"]
    }
  }
}

address字段包含 mill 或 movico
city字段包含 mill 或 movico
都会被检索出来

bool 【复合查询】

在复合查询中，会使用must,must_not以及should组合来查询

• must 必须满足
• must_not 必须不满足
• should 应该，可以满足，也可以不满足，满足最好(相关性得分会高)

GET /bank/_search
{
  "query": {
    "bool": {
      "must": [
        { "match": { "gender": "F" } },
        {"match":{"address":"mill"}}
      ]
    }
  }
}

• must 必须满足
  含义: 查询 gender包含F的，同时，address包含mill的

除了有 must 还有一个 must_not（必须不是）

GET /bank/_search
{
  "query": {
    "bool": {
      "must": [
        { "match": { "gender": "F" } },
        {"match":{"address":"mill"}}
      ],
      "must_not": [
        {"match":{"age":"38"}}
      ]
    }
  }
}

说明:
查询 age 不是 38的数据

查看官方文档可知，must 和 should 会贡献相关性得分，换言之，must 和 should 匹配成功的话，相关性得分会高

filter【结果过滤】

filter会把不满足 fiter定义规则的给过滤掉，同时，filter不会贡献相关性得分

GET /bank/_search
{
  "query": {
    "bool": {
      "filter": {
        "range": {
          "balance": {
            "gte": 20000,
            "lte": 30000
          }
        }
      }
    }
  }
}

term 查询

term级别查询将按照存储在倒排索引中的确切字词进行操作，这些查询通常用于数字，日期和枚举等结构化数据，而不是全文本字段。 或者，它们允许您制作低级查询，并在分析过程之前进行。
term是代表完全匹配，也就是精确查询，搜索前不会再对搜索词进行分词，所以我们的搜索词必须是文档分词集合中的一个。

所以: 查询数字，日期这种的可以使用term，查询文本类型的使用match

总结: 精确匹配的几种方式
方式一: match_phrase

GET /bank/_search
{
  "query": {
    "match_phrase": {
      "address": "Madison Street"
    }
  }
}

方式二: match + 字段.keyword

GET /bank/_search
{
  "query": {
    "match": {
      "address.keyword": "Madison Street"
    }
  }
}

那么二者的区别是什么?
“match_phrase”: {
“address”: “Madison Street”
}
类似于Mysql中的 address like ‘%Madison Street%’

“match”: {
“address.keyword”: “Madison Street”
}
类似于Mysql中的 address = ‘Madison Street’

aggregations【执行聚合】

聚合提供了从数据中分组和提取数据的能力，最简单的聚合类似于 SQL GROUP BY和聚合函数

聚合简单的结构如下:

"aggregations" : {
    "<aggregation_name>" : {
        "<aggregation_type>" : {
            <aggregation_body>
        }
        [,"meta" : {  [<meta_data_body>] } ]?
        [,"aggregations" : { [<sub_aggregation>]+ } ]?
    }
    [,"<aggregation_name_2>" : { ... } ]*
}

• 需求: 搜索address中包含mill的所有人的年龄分布以及平均年龄
  
  

• 需求2 按照年龄聚合，并且求各个年龄段的平均工资

GET bank/_search
{
  "query": {
   "match_all": {}
  },
  "aggs": {
    "ageAgg": {
      "terms": {
        "field": "age",
        "size": 100
      },
      "aggs": {
        "aggAvg": {
          "avg": {
            "field": "balance"
          }
        }
      }
    }
  }
}

• 需求3 查出所有年龄分布，这些年龄段中性别为M的平均薪资和性别为F的平均薪资，以及这个年龄段的总体平均薪资

GET bank/_search
{
  "query": {
   "match_all": {}
  },
  "aggs": {
    "ageAgg": {
      "terms": {
        "field": "age",
        "size": 100
      },
      "aggs": {
        "genderAgg": {
          "terms": {
            "field": "gender.keyword",
            "size": 10
          },
          "aggs": {
            "balanceAvg": {
              "avg": {
                "field": "balance"
              }
            }
          }
        },
        "balanceAvg":{
          "avg": {
            "field": "balance"
          }
        }
      }     
    }
  }
}

结果如下

更多内容请参考官方文档

mapping

mapping是类似于数据库中的表结构定义。
用来定义一个文档（document）,以及它所包含的属性(field)是如何存储和索引的。
比如: 使用mapping用来定义

• 哪些字符串属性应该被看作全文本属性(full text field)
• 哪些属性包含数字、日期或地理位置
• 文档中的属性是否能被索引(_all 配置)
• 日期的格式
• 自定义映射规则来执行动态添加属性

注意

在es8版本将移除(type)，所以以后可以将文档直接存储在某一个索引下面。

查询mapping 信息

GET bank/_mapping

结果如下:

{
  "bank" : {
    "mappings" : {
      "properties" : {
        "account_number" : {
          "type" : "long"
        },
        "address" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "age" : {
          "type" : "long"
        },
        "balance" : {
          "type" : "long"
        },
        "city" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "email" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "employer" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "firstname" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "gender" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "lastname" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "state" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        }
      }
    }
  }
}

创建索引并指定映射规则

PUT /my-index
{
  "mappings": {
    "properties": {
      "age":    { "type": "integer" },  
      "email":  { "type": "keyword"  }, 
      "name":   { "type": "text"  }     
    }
  }
}

注意: type 为 text 的会被分词检索，keyword不会被分词检索，当成关键字整体匹配。

添加新的字段映射

PUT /my-index/_mapping
{
  "properties": {
    "employee-id": {
      "type": "keyword",
      "index": false
    }
  }
}

index 为false，表示该字段不需要被索引，
index默认为true

更新映射

对于已经存在的字段映射，不能直接更新。可以创建新的索引，将数据迁移过去。

需求: 创建新的索引 new bank，修改之前字段的mapping映射，将bank数据迁移过去

PUT /newbank
{
  "mappings": {
    "properties": {
    "account_number" : {
          "type" : "long"
        },
        "address" : {
          "type" : "text"
        },
        "age" : {
          "type" : "integer"
        },
        "balance" : {
          "type" : "long"
        },
        "city" : {
          "type" : "keyword"
        },
        "email" : {
          "type" : "keyword"
        },
        "employer" : {
          "type" : "keyword"
        },
        "firstname" : {
          "type" : "text"
        },
        "gender" : {
          "type" : "keyword"
        },
        "lastname" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "state" : {
          "type" : "keyword"
        }
  }
  }
}

数据迁移

POST _reindex
{
  "source": {
    "index": "bank",
    "type": "account"
  },
  "dest": {
    "index": "newbank"
  }
}

注意:
将source下的数据迁移到dest下
如果旧索引下有 type,在source下写type，如果没有type就不用写