Search API和Aggregations

最新推荐文章于 2024-10-18 19:12:03 发布

weixin_34402090

最新推荐文章于 2024-10-18 19:12:03 发布

阅读量94

点赞数

文章标签：大数据 python

原文链接：https://my.oschina.net/grittan/blog/3018128

版权

2019独角兽企业重金招聘Python工程师标准>>>

Search API和Aggregations

搜索方式

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

Aggregations

7.嵌套聚合下钻分析聚合分析

1.query string search

GET /sport-shop-item-info/public/_search
GET /sport-shop-item-info/public/_search?q=shop_id:2896280279

2.query DSL

GET /sport-shop-item-info/public/_search
{
    "query": {
        "match_all": {}
    }
}

查询所有标题含有“运动鞋”的商品，并按照价格进行降序排序

GET /sport-shop-item-info/public/_search
{
    "size" : 10,
    "query": {
        "match": {
           "title": "运动鞋"
        }
    },
    "sort": [
       {
          "sale_price_a": {
             "order": "desc"
          }
       }
    ]
}

分页

GET /sport-shop-item-info/public/_search
{   "from": 0, 
    "size" : 10,
    "query": {
        "match": {
           "title": "运动鞋"
        }
    },
    "sort": [
       {
          "sale_price_a": {
             "order": "desc"
          }
       }
    ]
}

3.query filter

格式

GET /sport-shop-item-info/public/_search
{
  "query": {
    "bool": {
      //多个查询条件，也可以嵌套bool
    }
    
  }
}

例子

GET /sport-shop-item-info/public/_search
{
    "query": {
        "bool": {
            "must": [
               {
                   "term": {
                      "shop_id": {
                         "value": "3362038456"
                      }
                   }
               },
               {
               "term": {
                  "platform_id": {
                     "value": "1"
                  }
               }
               },
               {
                   "match": {
                      "title": "运动鞋"
                   }
               }
            ]
        }
    }
}

4.full-text search

producer这个字段，会先被拆解，建立倒排索引	

special		4
yagao		4
producer	1,2,3,4
gaolujie	1
zhognhua	3
jiajieshi	2

PUT /ecommerce/product/4
{
  "name" : "special yagao",
  "desc" : "texiao fangzhu",
  "price" : 50,
  "producer" : "yagao producer",
  "tags" : ["fangzhu"]
}

GET /ecommerce/product/_search
{
  "query": {
    "match": {
      "producer": "yagao producer"
    }
  }
}

5.phrase search

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": 19,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 1,
    "max_score": 0.7854939,
    "hits": [
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "4",
        "_score": 0.7854939,
        "_source": {
          "name": "special yagao",
          "desc": "texiao fangzhu",
          "price": 50,
          "producer": "yagao producer",
          "tags": [
            "fangzhu"
          ]
        }
      }
    ]
  }
}

6.highlight search

高亮搜索结果

GET /ecommerce/product/_search
{
  "query": {
    "match": {
      "producer": "producer"
    }
  },
  "highlight": {
    "fields": {
      "producer": {}
    }
  }
}

结果如下

{
  "took": 42,
  "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>"
          ]
        }
      },
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "3",
        "_score": 0.25811607,
        "_source": {
          "name": "zhonghua yagao",
          "desc": "caoben zhiwu",
          "price": 40,
          "producer": "zhonghua producer",
          "tags": [
            "qinxin"
          ]
        },
        "highlight": {
          "producer": [
            "zhonghua <em>producer</em>"
          ]
        }
      },
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "2",
        "_score": 0.16358379,
        "_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": 0.16358379,
        "_source": {
          "name": "special yagao",
          "desc": "texiao fangzhu",
          "price": 50,
          "producer": "yagao producer",
          "tags": [
            "fangzhu"
          ]
        },
        "highlight": {
          "producer": [
            "yagao <em>producer</em>"
          ]
        }
      }
    ]
  }
}

7.嵌套聚合下钻分析聚合分析

size: 0 设置为对进行分组的数据不显示出来

GET /sport-shop-item-info/public/_search
{   "size": 0, 
    "query": {
        "bool": {
            "must": [
               {
                   "term": {
                      "shop_id": {
                         "value": "3362038456"
                      }
                   }
               },
               {
               "term": {
                  "platform_id": {
                     "value": "1"
                  }
               }
               },
               {
                  "range": {
                     "crawl_time": {
                        "from": "2017-10-01",
                        "to": "2017-10-31",
                        "include_upper": true, 
                        "include_lower": true
                     }
                  }
               }
            ]
        }
    },
    "aggs":{
    "groupByItemId" : {
        "terms":{
            "field": "item_id"
        }
     }
    }
}

聚合分析的需求：先分组，再算每组的平均值

GET /sport-shop-item-info/public/_search
{   "size": 0, 
    "query": {
        "bool": {
            "must": [
               {
                   "term": {
                      "shop_id": {
                         "value": "3362038456"
                      }
                   }
               },
               {
               "term": {
                  "platform_id": {
                     "value": "1"
                  }
               }
               },
               {
                  "range": {
                     "crawl_time": {
                        "from": "2017-10-01",
                        "to": "2017-10-31",
                        "include_upper": true, 
                        "include_lower": true
                     }
                  }
               }
            ]
        }
    },
    "aggregations":{
     "groupByItemId" : {
        "terms":{
            "field": "item_id",
			"size" : 0,
            "shard_size" : 0
        },
        "aggregations":{
            "avgPrice":{
                "avg":{
                    "field":"sale_price"
                }
            }
        }
        }
    }
}

数据分析需求：计算店铺下的商品的平均价格，并且按照平均价格降序排序

GET /sport-shop-item-info/public/_search
{
  "size" : 0,
  "query" : {
    "bool" : {
      "must" : [ {
        "term" : {
          "platform_id" : "1"
        }
      }, {
        "term" : {
          "shop_id" : "353571709"
        }
      } ],
      "must_not" : [ {
        "term" : {
          "shelve_change" : 0
        }
      }, {
        "term" : {
          "sale" : 0
        }
      } ],
      "should" : {
        "bool" : {
          "must" : [ {
            "term" : {
              "platform_id" : "1"
            }
          }, {
            "term" : {
              "shop_id" : "353571709"
            }
          } ]
        }
      }
    }
  },
  "aggregations" : {
    "groupByItem" : {
      "terms" : {
        "field" : "item_id",
        "order" : {
          "avgPrice" : "desc"
        }
      },
      "aggregations" : {
        "avgPrice" : {
          "avg" : {
            "field" : "sale_price"
          }
        }
      }
    }
  }
}

参考官方文档：

https://www.elastic.co/guide/en/elasticsearch/reference/5.2/index.html

转载于:https://my.oschina.net/grittan/blog/3018128