elasticsearch 查询实践

最新推荐文章于 2024-07-25 11:30:48 发布
最新推荐文章于 2024-07-25 11:30:48 发布
阅读量536 收藏
点赞数
分类专栏： 中间件 文章标签： elasticsearch
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_38513424/article/details/106147417
版权 
GET _search
{
  "query": {
    "match_all": {}
  }
}

#查询所有
GET twitter/_search
{
  "query":{
    "match_all": {}
  }
}

PUT twitter/_doc/10
{
  "name":"test"
}

PUT twitter/article/10
{
  "name":"test"
}

#插入id自增
POST twitter/_doc
{
  "name":"test"
}

GET /

#插入
PUT oschinablog/_doc/1
{
  "title":"你还应该知道的哈希冲突解决策略",
  "url":"https://my.oschina.net/vivotech/blog/4268016",
  "author_url":"https://my.oschina.net/vivotech"
}

#通过title匹配查询
GET oschinablog/_search
{
  "query":{
    "match": {
      "title": "test"
    }
  }
}

#通过id查询返回指定字段
GET oschinablog/_doc/1?_source=title,url

#条件查询
GET _mget
{
  "docs":[
    {"_index":"twitter",
      "_id":1
    }
    ]
}

#查询ids中的document
GET twitter/_doc/_mget
{
  "ids": ["1", "2"]
}

#插入
GET oschinablog/_doc/1
{
  "url":"www.baidu.com"
}

#通过id获取
GET oschinablog/_doc/_mget
{
  "ids":["1"]
}

#更新部分字段
POST oschinablog/_update/1
{
  "doc":{
    "url":"www.baidu.com"
  }
}

#查询后进行更新
POST oschinablog/_update_by_query
{
  "query":{
    "match":{
      "title":"你还应该知道的哈希冲突解决策略"
    }
  },
  "script":{
    "source":"ctx._source.url=params.url;ctx._source.author_url=params.author_url;",
    "lang":"painless",
    "params":{
      "url":"www.google.com",
      "author_url":"www.github.com/forhj"
    }
  }
}

#对于中文字段的文档进行更新
POST edd/_update_by_query
{
  "query": {
    "match": {
      "姓名": "张彬"
    }
  },
  "script": {
    "source": "ctx._source[\"签到状态\"] = params[\"签到状态\"]",
    "lang": "painless",
    "params" : {
      "签到状态":"已签到"
    }
  }
}

#通过script更新，需要指定id
POST oschinablog/_update/1
{
  "script": {
    "source": "ctx._source.url=params.url"
    , "lang": "painless",
    "params": {
      "url":"www.baidu.com"
    }
  }
}

#插入或者更新
POST oschinablog/_update/1
{
  "doc": {
    "title":"test",
    "url":"www.google.com",
    "author_url":"www.immoc.com"
  },
  "doc_as_upsert":"true"
}

#检查一个文档是否存在
HEAD oschinablog/_doc/1

#删除一个文档
DELETE oschinablog/_doc/1

GET oschinablog/_search
{
  "query": {
    "match_all": {}
  }
}

#查询并删除 数组使用多个match
POST oschinablog/_delete_by_query
{
  "query":{
    "match":{
      "ids" : 
            "1"
    }
  }
}

#删除索引
DELETE twitter

#index批量插入，不要带空格用换行符分割，不管数据是否已经存在都会插入，有数据存在则进行覆盖
POST _bulk
{"index":{"_index":"me_blog1","_id":1}}
{"user":"aa","message":"is ok","date":"2020-5-16"}
{"index":{"_index":"me_blog1","_id":2}}
{"user":"bb","message":"is fine","date":"2020-5-17"}
{"index":{"_index":"me_blog1","_id":3}}
{"user":"cc","message":"is fucked","date":"2020-5-18"}

GET me_blog/_search
{
  "query":{
    "match_all": {}
  }
}

#查询数据总条数
GET me_blog/_count

#create批量插入，不能够覆盖已有的数据，如果已有数据存在则抛出异常，不存在则创建
POST _bulk
{"create":{"_index":"me_blog","_id":1}}
{"user":"aa","message":"is ok","date":"2020-5-16"}
{"create":{"_index":"me_blog","_id":2}}
{"user":"bb","message":"is fine","date":"2020-5-17"}
{"create":{"_index":"me_blog","_id":3}}
{"user":"cc","message":"is fucked","date":"2020-5-18"}

#使用_bulk删除
POST _bulk
{"delete":{"_index":"me_blog","_id":"1"}}

#使用_bulk更新
POST _bulk
{"update":{"_index":"me_blog","_id":"2"}}
{"doc":{"user":"bbb"}}

#查询
GET me_blog/_doc/2

#关闭索引
POST me_blog/_close

#开启索引
POST me_blog/_open

#冻结索引
POST me_blog/_freeze

#冻结后进行搜索需要加入ingore_throttled参数为false
GET me_blog/_search?ignore_throttled=false


#解冻索引
POST me_blog/_unfreeze

#统计
GET me_blog/_search
{
  "query":{
    "match": {
      "user": "bbb"
    }
  },
  "aggs":{
    "top_authors":{
      "field":"author"
    }
  }
}

GET .kibana_1/_search

#搜索文档并设定size
GET _search?size=1

#对多个索引进行搜索
POST /.kibana,.kibana_1/_search

#搜索所有文档
GET /_search

POST index1/_doc
{
  "val":1
}

POST _bulk
{"index":{"_index":"index2","_id":"2"}}
{"val":2}
{"index":{"_index":"index3","_id":"3"}}
{"val":3}

#查询多个index
POST /index1,index2,index3/_search

#查询以index开头的索引，排除index3
POST /index*,-index3/_search

#搜索
GET me_blog/_search?ignore_throttled=false

#分页搜索from代表那一页，下标从0开始
GET me_blog1/_search?size=1&from=0

#同上，另一种写法
GET me_blog1/_search
{
  "size": 1,
  "from": 0, 
  "query": {
    "match_all":{}
  }
}

#查询指定要输出的字段
GET me_blog1/_search?filter_path=hits.hits._source.user

#查询并指定返回的字段
GET oschinablog/_search
{
  "_source": ["title","author_url","url"],
  "query": {
    "match_all": {
      
    }
  }
}

#通配符匹配返回的字段
GET oschinablog/_search
{
  "_source":{
    "includes": [
      "tit*",
      "au*"
      ],
      "excludes":["*.lat"]
  },
  "query":{
    "match_all": {}
  }
}

#source为false时不会返回任何的字段
GET oschinablog/_search
{
  "_source": false,
  "query": {
    "match_all": {
      
    }
  }
}

#统计
GET oschinablog/_search
{
  "query": {
    "match_all": {}
  },
  "script_fields": {
    "test1": {
      "script": {
        "lang": "painless",
        "inline": "doc['title'].value"
      }
    }
  }
}

#获取满足条件的count
GET oschinablog/_count
{
  "query": {
    "match": {
      "title": "你还应该知道的哈希冲突解决策略*"
    }
  }
}

#获取所有索引
GET _cat/indices

#获取索引的配置
GET my_blog/_settings

#创建索引并配置索引
PUT test2
{
  "settings": {
    "number_of_replicas": 2
    , "number_of_shards": 2
  }
}



#配置index的mapping，当index插入数据后mapping不能够进行修改，需要重新创建然后预设值mapping
DELETE twitter
PUT twitter
{
  "settings": {
    "number_of_shards": 1,
    "number_of_replicas": 1
  }
}
 
PUT twitter/_mapping
{
  "properties": {
    "address": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    },
    "age": {
      "type": "long"
    },
    "city": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    },
    "country": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    },
    "location": {
      "type": "geo_point"
    },
    "message": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    },
    "province": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    },
    "uid": {
      "type": "long"
    },
    "user": {
      "type": "text",
      "fields": {
        "keyword": {
          "type": "keyword",
          "ignore_above": 256
        }
      }
    }
  }
}
POST _bulk
{ "index" : { "_index" : "twitter", "_id": 1} }
{"user":"双榆树-张三","message":"今儿天气不错啊，出去转转去","uid":2,"age":20,"city":"北京","province":"北京","country":"中国","address":"中国北京市海淀区","location":{"lat":"39.970718","lon":"116.325747"}}
{ "index" : { "_index" : "twitter", "_id": 2 }}
{"user":"东城区-老刘","message":"出发，下一站云南！","uid":3,"age":30,"city":"北京","province":"北京","country":"中国","address":"中国北京市东城区台基厂三条3号","location":{"lat":"39.904313","lon":"116.412754"}}
{ "index" : { "_index" : "twitter", "_id": 3} }
{"user":"东城区-李四","message":"happy birthday!","uid":4,"age":30,"city":"北京","province":"北京","country":"中国","address":"中国北京市东城区","location":{"lat":"39.893801","lon":"116.408986"}}
{ "index" : { "_index" : "twitter", "_id": 4} }
{"user":"朝阳区-老贾","message":"123,gogogo","uid":5,"age":35,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区建国门","location":{"lat":"39.718256","lon":"116.367910"}}
{ "index" : { "_index" : "twitter", "_id": 5} }
{"user":"朝阳区-老王","message":"Happy BirthDay My Friend!","uid":6,"age":50,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区国贸","location":{"lat":"39.918256","lon":"116.467910"}}
{ "index" : { "_index" : "twitter", "_id": 6} }
{"user":"虹桥-老吴","message":"好友来了都今天我生日，好友来了,什么 birthday happy 就成!","uid":7,"age":90,"city":"上海","province":"上海","country":"中国","address":"中国上海市闵行区","location":{"lat":"31.175927","lon":"121.383328"}}

GET twitter/_search
{
  "_source":false,
  "query":{
    "match": {
      "city": "北京"
    }
  }
}

#script条件查询
GET twitter/_search
{
  "query":{
    "script": {
      "source": "doc['city'].contains(params.name)", "lang": "painless",
      "params": {
        "name":"北京"
      }
    }
  }
}
#url查询
GET twitter/_search?q=city:("北京"^5 or "上海") AND user:"张三" AND age:[20 TO 30] &sort=age:desc&_source=user,age&size=2&from=0

#查询包含朝阳区老贾这些字中至少三个字的数据
#"user": "朝阳区-老贾", 等同于 
GET twitter/_search
{
  "query": {
    "match": {
      "user":{
        "query": "朝阳区-老贾",
      "operator":"or",
      "minimum_should_match":"3"
      }
    }
  }
}

#不需要score
GET twitter/_search
{"query": {
  "bool": {
    "filter": {
      "term": {
        "city.keyword":"北京"
      }
    }
  }
}
}

GET twitter/_search
{
  "query":{
    "match":{
      "user": "朝阳区-老贾"
    }
  }
}
#同上，可添加operator提高查询数据的精度
GET twitter/_search
{
  "query": {
    "match": {
      "user": {
        "query": "朝阳区-老贾",
        "operator": "and"
      }
    }
  }
}

#查询含有user,address和message的数据，对address包含朝阳的数据进行三倍加权
GET twitter/_search
{
  "query": {
    "multi_match": {
      "query": "朝阳",
      "fields": ["user","address^3","message"],
      "type": "best_fields"
    }
  }
}

#搜索对以朝为前缀开头的数据
GET twitter/_search
{
  "query": {
    "prefix": {
      "user": {
        "value": "朝"
      }
    }
  }
}

#精确匹配
GET twitter/_search
{
  "query": {
    "terms": {
      "user.keyword": [
        "双榆树-张三",
        "东城区-老刘"
        ]
    }
  }
}

GET twitter/_search
{
  "query": {
    "bool": {
      "must":
        {},
      "filter": 
        {},
      "must_not": 
        {},
      "should": 
        {},
      "minimum_should_match": 1,
      "boost": 1
    }
  }
}

#must：
#文档 必须匹配这些条件才能被包含进来。
#must_not:
#文档 必须不匹配这些条件才能被包含进来。 
#should：
#如果满足这些语句中的任意语句，将增加
#_score，否则，无任何影响。它们主要用于修正每个文
#档的相关性得分。 
#filter：
# 必须 匹配，但它以不评分、过滤模式来进行。这些语
#句对评分没有贡献，只是根据过滤标准来排除或包含文档
GET twitter/_search
{
  "query": {
    "bool": {
      "must":
        [
          {"match":{"city":"北京"}},
          {"match":{"age":"30"}}
        ],
        "must_not": [
          {"prefix": {
            "city": {
              "value": "上海"
            }
          }}
        ],
        "should": [
          {"match_phrase": {
            "message": "出发，下一站云南！"
          }}
        ],
        "filter": {
          "range": {
            "age": {
              "gte": 10,
              "lte": 50
            }
          }
        }
    }
  },
  "explain": false
}

#查询北京地址，在location位置为中心的3公里以内的所有文档
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "address": "北京"
        }}
      ]
    }
  },
  "post_filter": {
    "geo_distance": {
      "distance": "5km",
      "distance_type": "plane", 
      "location": {
        "lat":  39.920086,
        "lon": 116.454182
      }
    }
  },
  "sort": [
    {
      "_geo_distance": {
        "order": "asc",
        "location": "39.920086,116.454182",
        "unit": "km"
      }
    }
  ]
}

#另一种写法
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "address": "北京"
        }}
      ],
      "filter": {
         "geo_distance": {
         "distance": "5km",
         "distance_type": "plane", 
          "location": {
            "lat":  39.920086,
            "lon": 116.454182
          }   
        }
      }
    }
  },

  "sort": [
    {
      "_geo_distance": {
        "order": "asc",
        "location": "39.920086,116.454182",
        "unit": "km"
      }
    }
  ]
}

GET twitter/_search
{
  "query": {
  
  },
  "post_filter": {
    "geo_distance": {
      "distance": 100,
      "distance_unit": "km",
      "FIELD": {
        "lat": 40.73,
        "lon": -74.1
      }
    }
  },
  "sort": [
    {
      "_geo_distance": {
        "FIELD": {
          "lat": 40,
          "lon": -70
        },
        "order": "asc"
      }
    }
  ]
}

GET twitter/_search
{
  "query": {
  },
  "post_filter": {
    "geo_distance": {
      "distance": 100,
      "distance_unit": "km",
      "FIELD": {
        "lat": 40.73,
        "lon": -74.1
      }
    }
  },
  "sort": [
    {
      "_geo_distance": {
        "FIELD": {
          "lat": 40,
          "lon": -70
        },
        "order": "asc"
      }
    }
  ]
}

#查询三十到四十岁之间的document
GET twitter/_search
{
  "query": {
    "range": {
      "age": {
        "gte": 30,
        "lte": 40
      }
    }
  },
  "sort": [
    {
      "age": {
        "order": "desc"
      }
    }
  ]
}

PUT twitter/_doc/20
{
  "user" : "王二",
  "message" : "今儿天气不错啊，出去转转去",
  "uid" : 20,
  "age" : 40,
  "province" : "北京",
  "country" : "中国",
  "address" : "中国北京市海淀区",
  "location" : {
    "lat" : "39.970718",
    "lon" : "116.325747"
  }
}

#查询存在city这个字段的document
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"exists": {"field": "city"}}
      ]
    }
  }
}

#取反
GET twitter/_search
{
  "query": {
    "bool": {
      "must_not": [
        {"exists": {"field": "city"}}
      ]
    }
  }
}

#查询包含happy的文档，and条件查询
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "message": {
            "query": "happy birthday",
            "operator": "and"
          }
        }}
      ]
    }
  }
}

#or条件查询
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "message": "happy birthday"
        }}
      ]
    }
  }
}

#and条件查询 使用minimum_should_match 包含两个单词
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "message": {
            "query": "happy birthday",
            "minimum_should_match": 2
          }
        }}
      ]
    }
  }
}

PUT twitter/_doc/8
{
  "user": "朝阳区-老王",
  "message": "Happy",
  "uid": 6,
  "age": 50,
  "city": "北京",
  "province": "北京",
  "country": "中国",
  "address": "中国北京市朝阳区国贸",
  "location": {
    "lat": "39.918256",
    "lon": "116.467910"
  }
}

PUT twitter/_doc/5
{
  "user": "朝阳区-老王",
  "message": "BirthDay My Friend Happy !",
  "uid": 6,
  "age": 50,
  "city": "北京",
  "province": "北京",
  "country": "中国",
  "address": "中国北京市朝阳区国贸",
  "location": {
    "lat": "39.918256",
    "lon": "116.467910"
  }
}

#包含的单词按要求排序获取结果，且不区分大小写
GET twitter/_search
{
  "query": {
    "match_phrase": {
      "message": "happy birthday"
    }
  }
}

PUT twitter/_doc/5
{
  "user": "朝阳区-老王",
  "message": "Happy Good BirthDay My Friend!",
  "uid": 6,
  "age": 50,
  "city": "北京",
  "province": "北京",
  "country": "中国",
  "address": "中国北京市朝阳区国贸",
  "location": {
    "lat": "39.918256",
    "lon": "116.467910"
  }
}

#允许happy与birthday拥有一个tokend的差别
GET twitter/_search
{
  "query": {
    "match_phrase": {
      "message": {
        "query": "Happy birthday",
        "slop": 1
      }
    }
  },
  "highlight": {
    "fields": {
      "message": {}
    }
  }
}

GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match_all": {}
        }
      ]
    }
  }
}


#_name 字段名 ，当匹配到了_name后会将字段存入matched_queries中统一返回
GET twitter/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "city": {
            "query": "北京",
            "_name":"城市"
          }
        }},
        {
          "match": {
            "country": {
              "query": "中国",
              "_name":"国家"
            }
          }
        }
      ],
      "should": [
        {"match": {
          "_id":{
            "query": "1",
            "_name":"ID"
          }
        }}
      ]
    }
  }
}

#sql查询
GET /_sql?
{
  "query":"""
  select * from twitter where age =30
  """
}

#一次请求多次查询
GET twitter/_msearch
{"index":"twitter"}
{"query":{"match_all":{}},"from":0,"size":1}
{"index":"twitter"}
{"query":{"bool":{"filter":{"term":{"city.keyword":"北京"}}}},"size":1}
{"index":"twitter"}
{"query":{"match_all":{}}}

#查询多个索引
GET /twitter,twitter1/_search

#查询并返回额外的 搜索北京
GET twitter/_search
{
  "profile": "true",
  "query": {
    "term": {
      "city.keyword": {
        "value": "北京"
      }
    }
  }
}

#搜索北和京二字
GET twitter/_search
{
  "profile": "true",
  "query": {
    "match": {
      "city": "北京"
    }
  }
}

DELETE twitter
 
PUT twitter
{
  "mappings": {
    "properties": {
      "DOB": {
        "type": "date"
      },
      "address": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "age": {
        "type": "long"
      },
      "city": {
        "type": "keyword"
      },
      "country": {
        "type": "keyword"
      },
      "location": {
        "type": "geo_point"
      },
      "message": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "province": {
        "type": "keyword"
      },
      "uid": {
        "type": "long"
      },
      "user": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      }
    }
  }
}

POST _bulk
{"index":{"_index":"twitter","_id":1}}
{"user":"张三","message":"今儿天气不错啊，出去转转去","uid":2,"age":20,"city":"北京","province":"北京","country":"中国","address":"中国北京市海淀区","location":{"lat":"39.970718","lon":"116.325747"}, "DOB": "1999-04-01"}
{"index":{"_index":"twitter","_id":2}}
{"user":"老刘","message":"出发，下一站云南！","uid":3,"age":22,"city":"北京","province":"北京","country":"中国","address":"中国北京市东城区台基厂三条3号","location":{"lat":"39.904313","lon":"116.412754"}, "DOB": "1997-04-01"}
{"index":{"_index":"twitter","_id":3}}
{"user":"李四","message":"happy birthday!","uid":4,"age":25,"city":"北京","province":"北京","country":"中国","address":"中国北京市东城区","location":{"lat":"39.893801","lon":"116.408986"}, "DOB": "1994-04-01"}
{"index":{"_index":"twitter","_id":4}}
{"user":"老贾","message":"123,gogogo","uid":5,"age":30,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区建国门","location":{"lat":"39.718256","lon":"116.367910"}, "DOB": "1989-04-01"}
{"index":{"_index":"twitter","_id":5}}
{"user":"老王","message":"Happy BirthDay My Friend!","uid":6,"age":26,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区国贸","location":{"lat":"39.918256","lon":"116.467910"}, "DOB": "1993-04-01"}
{"index":{"_index":"twitter","_id":6}}
{"user":"老吴","message":"好友来了都今天我生日，好友来了,什么 birthday happy 就成!","uid":7,"age":28,"city":"上海","province":"上海","country":"中国","address":"中国上海市闵行区","location":{"lat":"31.175927","lon":"121.383328"}, "DOB": "1991-04-01"}


#统计查询格式

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

GET twitter/_search
{
  "size": 0,
  "aggs": {
    "age":{
      "range": {
        "field": "age",
        "ranges": [
          {
            "from": 20,
            "to": 30
          },{
            "from": 30,
            "to":40
          },{
            "from": 40,
            "to":50
          }
        ]
      }
    }
  }
}

#对日期进行统计
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "birth_range": {
      "date_range": {
        "field": "DOB",
        "format": "yyyy-MM-dd", 
        "ranges": [
          {
            "from": "1989-01-01",
            "to": "1990-01-01"
          },
          {
            "from": "1991-01-01",
            "to": "1992-01-01"
          }
        ]
      }
    }
  }
}

#trems类似于group对结果进行分组统计
GET twitter/_search
{
  "query": {
    "match": {
      "message": "happy birthday"
    }
  },
  "size": 0,
  "aggs": {
    "city": {
      "terms": {
        "field": "city",
        "size": 10
      }
    }
  }
}

GET twitter/_search
{
  "size": 0,
  "aggs": {
    "birth_year": {
      "terms": {
        "script": {
          "source": "2020 - doc['age'].value"
        },
        "size": 10
      }
    }
  }
}

#根据值动态构建文档中中间隔为interval的桶
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "age": {
      "histogram": {
        "field": "age",
        "interval": 1
      }
    }
  }
}

GET twitter/_search
{
  "size": 0,
  "aggs": {
    "year": {
      "date_histogram": {
        "field": "DOB",
        "interval": "year"
      }
    }
  }
}

#聚合统计city的数量，但是失效了
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "city_count": {
      "cardinality": {
        "field": "city.keyword"
      }
    }
  }
}


GET twitter/_search
{
  "size": 0,
  "aggs": {
    "age_group": {
      "range": {
        "field": "age",
        "ranges": [
          {
            "from": 20,
            "to": 24
          },
          {
            "from": 24,
            "to": 26
          },
          {
            "from": 26
            , "to": 28
          }
        ]
      }
    }
  }
}

GET twitter/_search
{
  "size": 0,
  "aggs": {
    "city": {
      "terms": {
        "field": "city",
        "size": 10
      }
    }
  }
}

GET  twitter/_search
{
  "size": 0,
  "aggs": {
    "age": {
      "histogram": {
        "field": "age",
        "interval": 2
      }
    }
  }
}

#根据DOB的值动态根据year分割并存储进桶
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "date": {
      "date_histogram": {
        "field": "DOB",
        "interval": "year"
      }
    }
  }
}

#获取平均年龄
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "age_average": {
      "avg": {
        "field": "age"
      }
    }
  }
}

#查询city为上海的用户的平均年龄
GET twitter/_search
{
  "size": 0,
  "query": {
    "match": {
      "city": {
        "query": "北京",
        "operator": "and"
      }
    }
  }, 
  "aggs": {
    "average_age_beijin": {
      "avg": {
        "field": "age"
      }
    }
  }
}

#global针对所有文档进行计算平均值
GET twitter/_search
{
  "size": 0
  , 
  "query": {
    "match": {
      "city": "北京"
    }
  }, 
  "aggs": {
    "average_age": {
      "avg": {
        "field": "age"
      }
    },
    "average_age_all":{
      "global": {}
      ,"aggs": {
        "age_global_avg": {
          "avg": {
            "field": "age"
          }
        }
      }
    }
  }
}

#获取age的统计数据
GET twitter/_search
{
  "size": 0,
  "aggs": {
    "age_stats": {
      "stats": {
        "field": "age"
      }
    }
  }
}

#取age的最大值
GET twitter/_search
{
  "size": 0
  , "aggs": {
    "age_max": {
      "max": {
        "field": "age"
      }
    }
  }
}

#对统计的age平均值进行乘以1.5倍的处理
GET twitter/_search
{
  "size": 0
  , "aggs": {
    "avg_age_1.5": {
      "avg": {
        "field": "age"
        , "script": {
          "source": "_value * params.correction"
          , "params": {
            "correction":1.5
          }
        }
      }
    }
  }
}

#使用script的doc来形成聚合
GET twitter/_search
{
  
   "size": 0
   , "aggs": {
     "age_avg_time": {
       "avg": {"script": {
          "source": "doc['age'].value * params.times"
          , "params": {
            "times":2
          }
        }
         
       }
     }
   }
}


#百分比聚合
GET twitter/_search
{
  "size": 0
  , "aggs": {
    "age_quartiles": {
      "percentiles": {
        "field": "age",
        "percents": [
          25,
          50,
          75,
          100
        ]
      }
    }
  }
}

GET twitter/_search
{
  "size": 0
  , "aggs": {
    "age_quartiles": {
      "percentiles": {
        "field": "age",
        "percents": [
          1,
          5,
          25,
          50,
          75,
          95,
          99
        ]
      }
    }
  }
}

GET twitter/_search
{
  "size": 0
  , "aggs": {
    "age_avg": {
      "avg": {
        "field": "age"
      }
    }
  }
}

#首先生成每个城市的聚合，然后再对这个聚合进行计算平均年龄
GET twitter/_search
{
  "size": 0
  , "aggs": {
    "cities": {
      "terms": {
        "field": "city",
        "size": 10,
        "order": {
          "age_avg": "desc"
        }
      },
      "aggs": {
        "age_avg": {
          "avg": {
            "field": "age"
          }
        }
      }
    }
  }
}

#对年龄进行生成桶聚合，然后在计算平均年龄
GET twitter/_search
{
  "size": 0
  , "aggs": {
    "age_range": {
      "range": {
        "field": "age",
        "ranges": [
          {
            "from": 20,
            "to": 24
          },
          {
            "from": 24
            , "to": 28
          },
          {
            "from": 28,
            "to":30
          }
        ]
      },
      "aggs": {
        "avg_age": {
          "avg": {
            "field": "age"
          }
        }
      }
    }
  }
}

PUT sports
{
  "mappings": {
    "properties": {
      "birthdate": {
        "type": "date",
        "format": "dateOptionalTime"
      },
      "location": {
        "type": "geo_point"
      },
      "name": {
        "type": "keyword"
      },
      "rating": {
        "type": "integer"
      },
      "sport": {
        "type": "keyword"
      }
    }
  }
}

POST _bulk/
{"index":{"_index":"sports"}}
{"name":"Michael","birthdate":"1989-10-1","sport":"Baseball","rating":["5","4"],"location":"46.22,-68.45"}
{"index":{"_index":"sports"}}
{"name":"Bob","birthdate":"1989-11-2","sport":"Baseball","rating":["3","4"],"location":"45.21,-68.35"}
{"index":{"_index":"sports"}}
{"name":"Jim","birthdate":"1988-10-3","sport":"Baseball","rating":["3","2"],"location":"45.16,-63.58"}
{"index":{"_index":"sports"}}
{"name":"Joe","birthdate":"1992-5-20","sport":"Baseball","rating":["4","3"],"location":"45.22,-68.53"}
{"index":{"_index":"sports"}}
{"name":"Tim","birthdate":"1992-2-28","sport":"Baseball","rating":["3","3"],"location":"46.22,-68.85"}
{"index":{"_index":"sports"}}
{"name":"Alfred","birthdate":"1990-9-9","sport":"Baseball","rating":["2","2"],"location":"45.12,-68.35"}
{"index":{"_index":"sports"}}
{"name":"Jeff","birthdate":"1990-4-1","sport":"Baseball","rating":["2","3"],"location":"46.12,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Will","birthdate":"1988-3-1","sport":"Baseball","rating":["4","4"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Mick","birthdate":"1989-10-1","sport":"Baseball","rating":["3","4"],"location":"46.22,-68.45"}
{"index":{"_index":"sports"}}
{"name":"Pong","birthdate":"1989-11-2","sport":"Baseball","rating":["1","3"],"location":"45.21,-68.35"}
{"index":{"_index":"sports"}}
{"name":"Ray","birthdate":"1988-10-3","sport":"Baseball","rating":["2","2"],"location":"45.16,-63.58"}
{"index":{"_index":"sports"}}
{"name":"Ping","birthdate":"1992-5-20","sport":"Baseball","rating":["4","3"],"location":"45.22,-68.53"}
{"index":{"_index":"sports"}}
{"name":"Duke","birthdate":"1992-2-28","sport":"Baseball","rating":["5","2"],"location":"46.22,-68.85"}
{"index":{"_index":"sports"}}
{"name":"Hal","birthdate":"1990-9-9","sport":"Baseball","rating":["4","2"],"location":"45.12,-68.35"}
{"index":{"_index":"sports"}}
{"name":"Charge","birthdate":"1990-4-1","sport":"Baseball","rating":["3","2"],"location":"46.12,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Barry","birthdate":"1988-3-1","sport":"Baseball","rating":["5","2"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Bank","birthdate":"1988-3-1","sport":"Golf","rating":["6","4"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Bingo","birthdate":"1988-3-1","sport":"Golf","rating":["10","7"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"James","birthdate":"1988-3-1","sport":"Basketball","rating":["10","8"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Wayne","birthdate":"1988-3-1","sport":"Hockey","rating":["10","10"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Brady","birthdate":"1988-3-1","sport":"Football","rating":["10","10"],"location":"46.25,-68.55"}
{"index":{"_index":"sports"}}
{"name":"Lewis","birthdate":"1988-3-1","sport":"Football","rating":["10","10"],"location":"46.25,-68.55"}

GET sports/_count

GET sports/_search
{
  "size":0,
  "aggs": {
    "NAME": {
      "terms": {
        "field": "name",
        "size": 10
        , "order": {
          "rating_avg": "desc"
        }
      },
      "aggs": {
        "rating_avg": {
          "avg": {
            "field": "rating"
          }
        }
      }
    }
  }
}

GET sports/_search
{
  "size": 0,
  "aggs": {
    "age_range": {
      "range": {
        "script": {
          "source": """
            ZonedDateTime dob = doc['birthdate'].value;
            return params.now - dob.getYear()
          """
          , "params": {
            "now":2020
          }
        },
        "ranges": [
          {
            "from": 30,
            "to": 31
          }
        ]
      }
    }
  }
}

#计数生成聚合桶
GET sports/_search
{
  "size": 0
  , "aggs": {
    "sports_count": {
      "value_count": {
        "field": "sport"
      }
    }
  }
}

#统计运动的类型生成聚合桶
GET sports/_search
{
  "size": 0
  , "aggs": {
    "sport": {
      "terms": {
        "field": "sport",
        "size": 10
      }
    }
  }
}

#计算范围内的运动员数量生成聚合桶
GET sports/_search
{
  "size": 0
  , "aggs": {
    "baseball_player_ring": {
      "geo_distance": {
        "field": "location",
        "origin": {
          "lat": 46.12,
          "lon": -68.55
        },
        "ranges": [
          {
            "from": 0,
            "to": 20
          }
        ]
      }
    }
  }
}

GET sports/_search
{
"_source": ["name","rating"]
}


GET sports/_search
{
  "size": 0
  , "aggs": {
    "sports_count": {
      "range": {
        "field": "",
        "ranges": [
          {
            "from": 50,
            "to": 100
          }
        ]
      }
    }
  }
}

GET sports/_search
{
  "size": 0
  , "aggs": {
    "baseball_player_ring": {
      "geo_distance": {
        "field": "location",
        "origin": {
          "lat": 46.12,
          "lon": -68.55
        },
        "ranges": [
          {
            "from": 0,
            "to": 20
          }
        ]
      }
    }
  }
}


PUT users
{
  "mappings": {
    "properties": {
      "age": {
        "type": "long"
      },
      "category": {
        "type": "keyword"
      },
      "country": {
        "type": "keyword"
      },
      "user": {
        "type": "keyword"
      }
    }
  }
}

POST _bulk
{ "index" : { "_index" : "users", "_id": 1} }
{"user":"bill", "age": 30, "country": "FR", "category": "A"}
{ "index" : { "_index" : "users", "_id": 2} }
{"user":"Marie", "age": 32, "country": "US", "category": "A"}
{ "index" : { "_index" : "users", "_id": 3} }
{"user":"Clarie", "age": 32, "country": "US", "category": "A"}
{ "index" : { "_index" : "users", "_id": 4} }
{"user":"Tom", "age": 44, "country": "DE", "category": "B"}
{ "index" : { "_index" : "users", "_id": 5} }
{"user":"John", "age": 40, "country": "US", "category": "B"}
{ "index" : { "_index" : "users", "_id": 6} }
{"user":"Emma", "age": 26, "country": "US", "category": "B"}

GET users/_search
{
  "size": 0,
  "aggs": {
    "category_terms": {
      "terms": {
        "field": "category",
        "size": 10
      },
      "aggs": {
        "country_terms": {
          "terms": {
            "field": "country",
            "size": 10
          },"aggs": {
            "avg_age": {
              "avg": {
                "field": "age"
              }
            }
          }
        }
      }
    }
  }
}

GET sports/_search
{
  "size": 0
  , "aggs": {
    "defender_filter": {
      "filter": {
        "term": {
          "sport": "Baseball"
        }
      },"aggs": {
        "avg_goals": {
          "avg": {
            "field": "rating"
          }
        }
      }
    }
  }
}
带文豪的云烟
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
Elasticsearch分页实践&方式汇总
空山新雨后，天气晚来秋
12-01 3593
Elasticsearch大数据量分页最佳实践
elasticsearch es调优实践经验总结
yonggeit的博客
10-15 2740
概述 大多数操作系统都尽可能多地为文件系统缓存使用内存,并切换出未使用的应用程序 内存。这可能导致部分 JVM 堆被交换到磁盘上。 对于性能和节点的稳定性来说,这种交换是非常糟糕的,应该不惜一切代价避免。它 可能导致垃圾收集持续几分钟而不是几毫秒,这可能导致节点响应缓慢,甚至脱离集 群。 可以通过三种方式来禁用 swapping: 禁用所有的 swap 文件 配置 swappiness 禁用swapping 启用 bootstrap.memory_lock 禁用 swapping。 1.1 禁用所有的
ElasticSearch查询实践与优化
silverBlack
12-25 728
1、背景 近期项目组需要对机器人服务进行升级改造，需要基于用户的信息匹配不同的机器人和评论文案。需求可抽象为：每个用户有n个标签，每个机器人有m个标签，每条评论文案有q个标签，需要为每个用户找到前k个最匹配的机器人和评论文案。 2、方案 机器人的量级在100w左右，评论文案的量级在1w条左右，机器人和评论文案都存在多个标签。刚开始我们想基于map来给每个用户匹配机器人和评论文案：把每种标签对...
ElasticSearch最佳实践
Talk is cheap，show me the code.
02-15 1031
es 第一是准实时的，数据写入 1 秒后可以搜索到；可能会丢失数据的。有 5 秒的数据，停留在 buffer、translog os cache、segment file os cache 中，而不在磁盘上，此时如果宕机，会导致 5 秒的数据丢失。 归根结底，你要让 es 性能要好，最佳的情况下，就是你的机器的内存，至少可以容纳你的总数据量的一半。 根据我们自己的生产环境实践经验，最佳的情况下...
elasticsearch之多条件查询
Java领域优秀创作者
04-02 2535
总体来说，KQL的语法相对简单，但可以通过组合运算符、通配符、括号和常量等元素来构建复杂的查询。
Elastic Search最佳实践
canfengli的博客
09-23 491
ES最佳实践(6.x) 按天生成index，支撑每天10亿级日志量入库。 ES日志采用按天生成index方法，查询先确定索引位置，如log_20190801，log_20190802。再去ES中查找 动态模板与指定字段类型配合使用，优先采用指定类型，字段类型指定为keyword，不分词。 针对精确查询：使用term/terms + filter可完整查询字段并缓存结果。 针对模糊查询，使用w...
Elasticsearch高级查询Query DSL
Charge8的博客
06-19 2977
Elasticsearch高级查询Query DSL
Elasticsearch 原理与实践
BXA
06-08 1801
Elasticsearch 是一个基于 Lucene 的开源分布式搜索引擎，可以用于全文搜索、结构化搜索和分析等应用领域。它最初是由 Shay Banon 开发的在 Apache 开源许可证下发布。Elasticsearch 能够快速地将各种数据存储在多个节点的集群中，并且能够提供一个统一的接口进行检索和查询。在 Elasticsearch 中索引是指一个具有类型映射的容器，可以保存多个文档。每个文档都有独立的 ID 以及相应的类型和属性。
Elasticsearch之join关联查询
星空的风fly
11-19 1万+
Elasticsearch提供了类似于SQL JOIN的关联查询，通过has_child/has_parent可以实现一对多关系的父子表数据查询。但是其损耗也是比较大的，在使用的时候要根据分片数量的多少和预估数量量级的大小，提前做好性能测试
ES性能优化最佳实践- 检索性能提升30倍！
热门推荐
Angus
10-26 91万+
虽然Elasticsearch是一款强大的搜索引擎技术，但在超大规模数据检索中，尤其是在处理大量检索关键词（150个以上）、对多个字段执行检索并使用脚本排序时，可能会面临严重的性能问题。 在我们实际的业务中，检索的时间可能到达300秒，无法满足实时交互需求。本文带你打开一个新思路。在未添加任何资源的情况下，我把性能提升了30倍，请求时间控制在10s内。多数请求能在3秒5秒内完成。一起来看看我是如何做到的叭。
elasticSearch查询语句DSL
06-27
在这篇资源中，我们将详细介绍如何使用DSL...最后，我们将分享一些实用技巧和最佳实践，帮助您充分发挥DSL在Elasticsearch中的优势。我们将探讨性能优化、查询调试和索引优化等关键主题，以提升查询效率和搜索准确性。
elasticsearch运维实践
08-12
"elasticsearch运维实践" Elasticsearch是一个功能强大且灵活的搜索引擎，可以满足复杂的搜索需求。以下是Elasticsearch运维实践中的重要知识点： 1. Elasticsearch的架构 Elasticsearch的架构主要由三个部分组成...
滴滴Elasticsearch多集群架构实践
02-24
Elasticsearch是基于Lucene实现的...Elasticsearch在滴滴有着非常丰富的使用场景，例如线上核心的打车地图搜索，客服、运营的多维度查询，滴滴日志服务等近千个平台用户。超大的规模和丰富的场景给滴滴Elasticsear
01-微盟 Elasticsearch 运维实践
12-22
【微盟 Elasticsearch 运维实践】深入探讨了在企业级应用中如何高效、稳定地运行 Elasticsearch，这在数据检索、大数据分析及日志处理中扮演着关键角色。微盟作为使用者，分享了他们在运维过程中积累的经验和建议。 ...
git命令使用详细介绍
有勇气的牛排博客
07-24 1687
Git 的master分支并不是一个特殊分支。之所以几乎每一个仓库都有 master 分支，是因为git init 命令默认创建它，并且大多数人都懒得去改动它。如果当前本地仓库不是从远程仓库克隆，而是本地创建的仓库，并且仓库中存在文件，此时再从远程仓库拉取文件的时候会报错（fatal: refusing to merge unrelated histories ）：.git隐藏文件夹的目录就是工作目录，主要用于存放开发的代码。：包含.git文件夹的目录就是工作目录，主要存放开发的代码。
【Python】基础学习&技能提升&代码样例1：简单句式
Code_LT的博客
07-24 1177
可迭代对象的例子包括所有序列类型（如 list, str 和 tuple 等）以及某些非序列类型如 dict, 文件对象 以及任何定义了。如果传入了额外的 iterables 参数，则 function 必须接受相同个数的参数并被用于到从所有可迭代对象中并行获取的项。map() 和 starmap() 之间的区别类似于 function(a,b) 和 function(*c) 之间的差异。返回一个将 function 应用于 iterable 的每一项，并产生其结果的迭代器。时，它会返回该对象的迭代器。
ElasticSearch学习篇15_《检索技术核心20讲》进阶篇之TopK检索
最新发布
xiaosi的博客
07-25 685
学习极客实践课程《检索技术核心20讲》，文档形式记录笔记。
Docker 部署常用中间件(redis,rabbitMQ,mysql8,es,kibana,nginx等)亲测成功~~~
m0_64787068的博客
07-24 857
设置elasticsearch的地址，因为kibana已经与elasticsearch在一个网络，因此可以用容器名直接访问elasticsearch。就OK了，主要我们开放的端口是3307，所以连接的时候要使用3307端口，如果还是连不上有可能是被墙了。创建/usr/local/server/redis目录，将上面配置Docker 部署常用中间件(redis,rabbitMQ,mysql8,es,kibana,nginx等)亲自成功~~~
百度Elasticsearch大数据分析实践
"百度Elasticsearch实践" 在本文中，我们将探讨百度如何实践Elasticsearch，并分享在大数据分析实践中遇到的问题和经验。Elasticsearch（简称ES）是一款基于Lucene的开源搜索引擎，支持全文搜索、结构化数据分析和...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值