zoukankan      html  css  js  c++  java
  • Elasticsearch系统学习(四)-简单查询及聚合函数

    一、ES简单查询

    查询主要有如下几种:

    1、query string search
    2、query DSL
    3、query filter
    4、full-text search
    5、phrase search
    6、highlight search

    1.1、query string search

    适用于临时的在命令行使用一些工具,比如curl,快速的发出请求,来检索想要的信息;但是如果查询请求很复杂,是很难去构建的。在生产环境中,几乎很少使用query string search

    搜索全部商品:GET /ecommerce/product/_search

    GET /ecommerce/product/_search
    
    {
      "took": 3,    #耗费了几毫秒
      "timed_out": false,   #是否超时,这里是没有
      "_shards": {    #数据拆成了5个分片,所以对于搜索请求,会打到所有的primary shard(或者是它的某个replica shard也可以)
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,   #查询结果的数量,4个document
        "max_score": 1,   #score的含义,就是document对于一个search的相关度的匹配分数,越相关,就越匹配,分数也高
        "hits": [    #包含了匹配搜索的document的详细数据
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1_update",
            "_score": 1,
            "_source": {
              "doc": {
                "name": "jiaqiangban gaolujie yaogao"
              }
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": 1,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 1,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 1,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            }
          }
        ]
      }
    }
    

    搜索商品名称中包含yagao的商品,而且按照售价降序序:GET /ecommerce/product/_searchq=name:yagao&sort=price:desc

    GET /ecommerce/product/_search?q=name:yagao&sort=price:desc
    
    {
      "took": 11,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 3,
        "max_score": null,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": null,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            },
            "sort": [
              40
            ]
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": null,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            },
            "sort": [
              30
            ]
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": null,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            },
            "sort": [
              25
            ]
          }
        ]
      }
    }

    1.2、query DSL

    DSL:Domain Specified Language,特定领域的语言
    http request body:请求体,可以用json的格式来构建查询语法,比较方便,可以构建各种复杂的语法,比query string search肯定强大多了

    更加适合生产环境的使用,可以构建复杂的查询

    1)查询所有的商品

    GET /ecommerce/product/_search
    {
      "query": {"match_all": {}}  #使用match_all
    }
    
    {
      "took": 4,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 3,
        "max_score": 1,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": 1,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 1,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 1,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            }
          }
        ]
      }
    }

    2)查询名称包含yagao的商品,同时按照价格降序排序

    GET /ecommerce/product/_search
    {
      "query": {
        "match": {
          "name": "yagao"
        }
      },
      "sort": [
        {"price": "desc"}  
      ]
    }
    
    
    {
      "took": 7,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 3,
        "max_score": null,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": null,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            },
            "sort": [
              40
            ]
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": null,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            },
            "sort": [
              30
            ]
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": null,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            },
            "sort": [
              25
            ]
          }
        ]
      }
    }

    3)分页查询商品

    总共3条商品,假设每页就显示1条商品,现在显示第2页,所以就查出来第2个商品

    GET /ecommerce/product/_search
    {
      "query": {"match_all": {}},
      "from": 1,   #从第几个开始查询
      "size": 1    #查询几个
    }
    
    {
      "took": 2,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 3,
        "max_score": 1,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 1,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            }
          }
        ]
      }
    }

    4)指定要查询出来商品的名称和价格

    GET /ecommerce/product/_search
    {
      "query": {"match_all": {}},
      "_source": ["name","price"]
    }
    
    
    {
      "took": 13,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 3,
        "max_score": 1,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": 1,
            "_source": {
              "price": 25,
              "name": "jiajieshi yagao"
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 1,
            "_source": {
              "price": 30,
              "name": "gaolujie yagao"
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 1,
            "_source": {
              "price": 40,
              "name": "zhonghua yagao"
            }
          }
        ]
      }
    }

    1.3、query filter

    搜索商品名称包含yagao,而且售价大于25元的商品

    GET /ecommerce/product/_search
    {
      "query": {
        "bool": {
          "must": {
            "match": {
              "name":"yagao"
            }
          },
          "filter": {
            "range": {
            "price": {"gt": 25}
            }
          }
        }
      }
    }
    
    
    {
      "took": 7,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 2,
        "max_score": 0.25811607,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 0.25811607,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 0.25811607,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            }
          }
        ]
      }
    }

    1.4、full-text search(全文检索)

    全文检索图解:

    什么是全文检索

    新增条数据:

    put /ecommerce/product/4
    {
      "name": "special yagao",
      "desc": "special meibai",
      "price": 50,
      "producer": "special yagao producer",
      "tags": ["meibai"]
    }

    查看所有数据:

    GET /ecommerce/product/_search
    {
      "query": {
        "match_all": {}
      }
    }

    全文检索:查询producer字段带有”yagao producer”的商品

    GET /ecommerce/product/_search
    {
      "query": {
        "match": {
          "producer": "yagao producer"
        }
      }
    }
    
    #原理说明:
    producer这个字段,会先被拆解,建立倒排索引,yagao producer ---> yagao和producer
    
    special		4
    yagao		4
    producer	1,2,3,4
    gaolujie	1
    zhognhua	3
    jiajieshi	2
    
    
    {
      "took": 14,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0.70293105,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "4",
            "_score": 0.70293105,  #相关度得分最高
            "_source": {
              "name": "special yagao",
              "desc": "special meibai",
              "price": 50,
              "producer": "special yagao producer",
              "tags": [
                "meibai"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 0.25811607,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 0.25811607,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": 0.1805489,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            }
          }
        ]
      }
    }

    1.5、phrase search(短语搜索)

    跟全文检索相对应,相反,全文检索会将输入的搜索串拆解开来,去倒排索引里面去一一匹配,只要能匹配上任意一个拆解后的单词,就可以作为结果返回
    phrase search,要求输入的搜索串,必须在指定的字段文本中,完全包含一模一样的,才可以算匹配,才能作为结果返回

    GET /ecommerce/product/_search
    {
      "query": {
        "match_phrase": {
          "producer": "yagao producer"
        }
      }
    }
    
    {
      "took": 18,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 1,
        "max_score": 0.70293105,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "4",
            "_score": 0.70293105,
            "_source": {
              "name": "special yagao",
              "desc": "special meibai",
              "price": 50,
              "producer": "special yagao producer",
              "tags": [
                "meibai"
              ]
            }
          }
        ]
      }
    }

    1.6、highlight search(高亮搜索结果)

    image

    GET /ecommerce/product/_search
    {
      "query": {
        "match": {
          "producer":"producer"
        }
      },
      "highlight": {
        "fields": {
          "producer": {}
        }
      }
    }
    
    
    {
      "took": 37,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0.25811607,
        "hits": [
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "1",
            "_score": 0.25811607,
            "_source": {
              "name": "gaolujie yagao",
              "desc": "gaoxiao meibai",
              "price": 30,
              "producer": "gaolujie producer",
              "tags": [
                "meibai",
                "fangzhu"
              ]
            },
            "highlight": {
              "producer": [
                "gaolujie <em>producer</em>"    #高亮显示<em>标签
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "3",
            "_score": 0.25811607,
            "_source": {
              "name": "zhonghua yagao",
              "desc": "caoben zhiwu",
              "price": 40,
              "producer": "zhonghua producer",
              "tags": [
                "qingxin"
              ]
            },
            "highlight": {
              "producer": [
                "zhonghua <em>producer</em>"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "2",
            "_score": 0.1805489,
            "_source": {
              "name": "jiajieshi yagao",
              "desc": "youxiao fangzhu",
              "price": 25,
              "producer": "jiajieshi producer",
              "tags": [
                "fangzhu"
              ]
            },
            "highlight": {
              "producer": [
                "jiajieshi <em>producer</em>"
              ]
            }
          },
          {
            "_index": "ecommerce",
            "_type": "product",
            "_id": "4",
            "_score": 0.14638957,
            "_source": {
              "name": "special yagao",
              "desc": "special meibai",
              "price": 50,
              "producer": "special yagao producer",
              "tags": [
                "meibai"
              ]
            },
            "highlight": {
              "producer": [
                "special yagao <em>producer</em>"
              ]
            }
          }
        ]
      }
    }

    二、聚合函数

    聚合函数有:avg,groupby,sort等

    1)计算每个tag下的商品数量

    GET /ecommerce/product/_search
    {
      "aggs": {
        "group_by_tags": {   #通过标签进行分组,名称可以自己定义
          "terms": {
            "field": "tags"
          }
        }
      }
    }
    
    #报错
    "Fielddata is disabled on text fields by default. Set fielddata=true on [tags] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory."
    
    #解决方法:将文本field的fielddata属性设置为true
    PUT /ecommerce/_mapping/product
    {
      "properties": {
        "tags": {
          "type": "text",
          "fielddata": true
        }
      }
    }
    
    #再次查询
    GET /ecommerce/product/_search
    {
      "size": 0,   #不显示原始数据
      "aggs": {
        "all_tags": {
          "terms": { "field": "tags" }
        }
      }
    }
    
    
    {
      "took": 20,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0,
        "hits": []
      },
      "aggregations": {
        "group_by_tags": {
          "doc_count_error_upper_bound": 0,
          "sum_other_doc_count": 0,
          "buckets": [
            {
              "key": "fangzhu",
              "doc_count": 2
            },
            {
              "key": "meibai",
              "doc_count": 2
            },
            {
              "key": "qingxin",
              "doc_count": 1
            }
          ]
        }
      }
    }

    2)对名称中包含yagao的商品,计算每个tag下的商品数量

    GET /ecommerce/product/_search
    {
      "size": 0,
      "query": {
        "match": {
          "name": "yagao"
        }
      },
      "aggs": {
        "all_tags": {
          "terms": {
            "field": "tags"
          }
        }
      }
    }
    
    {
      "took": 2,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0,
        "hits": []
      },
      "aggregations": {
        "all_tags": {
          "doc_count_error_upper_bound": 0,
          "sum_other_doc_count": 0,
          "buckets": [
            {
              "key": "fangzhu",
              "doc_count": 2
            },
            {
              "key": "meibai",
              "doc_count": 2
            },
            {
              "key": "qingxin",
              "doc_count": 1
            }
          ]
        }
      }
    }

    3)先分组,再算每组的平均值,计算每个tag下的商品的平均价格

    GET /ecommerce/product/_search
    {
      "size": 0,
      "aggs": {
        "group_by_tags": {
          "terms": {
            "field": "tags"
          },
          "aggs": {
            "avg_price": {
              "avg": {
                "field": "price"
              }
            }
          }
        }
      }
    }
    
    {
      "took": 21,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0,
        "hits": []
      },
      "aggregations": {
        "group_by_tags": {
          "doc_count_error_upper_bound": 0,
          "sum_other_doc_count": 0,
          "buckets": [
            {
              "key": "fangzhu",
              "doc_count": 2,
              "avg_price": {
                "value": 27.5
              }
            },
            {
              "key": "meibai",
              "doc_count": 2,
              "avg_price": {
                "value": 40
              }
            },
            {
              "key": "qingxin",
              "doc_count": 1,
              "avg_price": {
                "value": 40
              }
            }
          ]
        }
      }
    }

    4)计算每个tag下的商品的平均价格,并且按照平均价格降序排序

    GET /ecommerce/product/_search
    {
      "size": 0,
      "aggs": {
        "all_tags": {
          "terms": {
            "field": "tags",
            "order": {
              "avg_price": "desc"
            }
          },
          "aggs": {
            "avg_price": {
              "avg": {
                "field": "price"
              }
            }
          }
        }
      }
    }
    
    
    {
      "took": 10,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0,
        "hits": []
      },
      "aggregations": {
        "all_tags": {
          "doc_count_error_upper_bound": 0,
          "sum_other_doc_count": 0,
          "buckets": [
            {
              "key": "meibai",
              "doc_count": 2,
              "avg_price": {
                "value": 40
              }
            },
            {
              "key": "qingxin",
              "doc_count": 1,
              "avg_price": {
                "value": 40
              }
            },
            {
              "key": "fangzhu",
              "doc_count": 2,
              "avg_price": {
                "value": 27.5
              }
            }
          ]
        }
      }
    }

    5)按照指定的价格范围区间进行分组,然后在每组内再按照tag进行分组,最后再计算每组的平均价格

    GET /ecommerce/product/_search
    {
      "size": 0,
      "aggs": {
        "group_by_price": {
          "range": {
            "field": "price",
            "ranges": [
              {
                "from": 0,
                "to": 20
              },
              {
                "from": 20,
                "to": 40
              },
              {
                "from": 40,
                "to": 50
              }
            ]
          },
          "aggs": {
            "group_by_tags": {
              "terms": {
                "field": "tags"
              },
              "aggs": {
                "avg_price": {
                  "avg": {
                    "field": "price"
                  }
                }
              }
            }
          }
        }
      }
    }
    
    
    {
      "took": 22,
      "timed_out": false,
      "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
      },
      "hits": {
        "total": 4,
        "max_score": 0,
        "hits": []
      },
      "aggregations": {
        "group_by_price": {
          "buckets": [
            {
              "key": "0.0-20.0",
              "from": 0,
              "to": 20,
              "doc_count": 0,
              "group_by_tags": {
                "doc_count_error_upper_bound": 0,
                "sum_other_doc_count": 0,
                "buckets": []
              }
            },
            {
              "key": "20.0-40.0",
              "from": 20,
              "to": 40,
              "doc_count": 2,
              "group_by_tags": {
                "doc_count_error_upper_bound": 0,
                "sum_other_doc_count": 0,
                "buckets": [
                  {
                    "key": "fangzhu",
                    "doc_count": 2,
                    "avg_price": {
                      "value": 27.5
                    }
                  },
                  {
                    "key": "meibai",
                    "doc_count": 1,
                    "avg_price": {
                      "value": 30
                    }
                  }
                ]
              }
            },
            {
              "key": "40.0-50.0",
              "from": 40,
              "to": 50,
              "doc_count": 1,
              "group_by_tags": {
                "doc_count_error_upper_bound": 0,
                "sum_other_doc_count": 0,
                "buckets": [
                  {
                    "key": "qingxin",
                    "doc_count": 1,
                    "avg_price": {
                      "value": 40
                    }
                  }
                ]
              }
            }
          ]
        }
      }
    }
  • 相关阅读:
    KBEngine:记录
    h5游戏研讨
    Django部署方法
    JQuery Advanced
    Web从入门到放弃<7>
    Web从入门到放弃<6>
    Web从入门到放弃<5>
    Web从入门到放弃<4>
    Web从入门到放弃<3>
    Web从入门到放弃<2>
  • 原文地址:https://www.cnblogs.com/hujinzhong/p/11444934.html
Copyright © 2011-2022 走看看