elasticsearch使用进阶

小码哥
2023-03-25 18:30:24
杂项
es

head插件安装及其使用安装流程：安装nodejs
安装grunt 安装head：https://github.com/mobz/elasticsearch-head npm run start http://localhost:9100 测试数据

POST /products/_bulk
{ "index": {"_id":1}}
  {"title":"iphone12 pro","price":8999,"created_at":"2020-10-23","description":"iPhone 12 Pro采用超瓷晶面板和亚光质感玻璃背板，搭配不锈钢边框，有银色、石墨色、金色、海蓝色四种颜色。宽度:71.5毫米，高度:146.7毫米，厚度:7.4毫米，重量：187克"}
{ "index": {"_id":2}}
  {"title":"iphone12","price":4999,"created_at":"2020-10-23","description":"iPhone 12 高度：146.7毫米；宽度：71.5毫米；厚度：7.4毫米；重量：162克（5.73盎司） [5]  。iPhone 12设计采用了离子玻璃，以及7000系列铝金属外壳。"}
{ "index": {"_id":3}}
  {"title":"iphone13","price":6000,"created_at":"2021-09-15","description":"iPhone 13屏幕采用6.1英寸OLED屏幕；高度约146.7毫米，宽度约71.5毫米，厚度约7.65毫米，重量约173克。"}
{ "index": {"_id":4}}
  {"title":"iphone13 pro","price":8999,"created_at":"2021-09-15","description":"iPhone 13Pro搭载A15 Bionic芯片，拥有四种配色，支持5G。有128G、256G、512G、1T可选，售价为999美元起。"}
{ "index": {"_id":5}}
  {"title":"iphone14 pro","price":8999,"created_at":"2021-09-15","description":"iPhone 13Pro搭载A16 Bionic芯片，拥有四种配色，支持5G。有128G、256G、512G、1T可选，售价为999美元起。"}
{ "index": {"_id":6}}
  {"title":"iphone14 pro max","price":9999,"created_at":"2021-09-15","description":"iPhone 14ProMax搭载A16 Bionic芯片，拥有四种配色，支持5G。有128G、256G、512G、1T可选，售价为999美元起。"}
{ "index": {"_id":7}}
  {"title":"iphone12","price":6499,"created_at":"2020-10-23","description":"iPhone 12 采用超瓷晶面板和亚光质感玻璃背板，搭配不锈钢边框，有银色、石墨色、金色、海蓝色四种颜色。宽度:71.5毫米，高:146.7毫米，厚度:7.4毫米，重量：187克"}

2. DSL之常见的Query

查询所有[match_all]

match_all关键字: 返回索引中的全部文档

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

###关键词查询(term) term 关键字: 用来使用关键词查询 Keyword integer double 不分词 text类型会进行分词，默认是es标准分词器

GET /products/_search
{
 "query": {
   "term": {
     "price": {
       "value": 4999
     }
   }
 }
}

注意:

通过使用term查询得知ES中默认使用分词器为标准分词器(StandardAnalyzer),标准分词器对于英文单词分词,对于中文单字分词。
通过使用term查询得知,在ES的Mapping Type 中 keyword , date ,integer, long , double , boolean or ip 这些类型不分词，只有text类型分词。

范围查询[range]

range 关键字: 用来指定查询指定范围内的文档

GET /products/_search
{
  "query": {
    "range": {
      "price": {
        "gte": 1400,
        "lte": 9999
      }
    }
  }
}

###前缀查询[prefix] prefix 关键字: 用来检索含有指定前缀的关键词的相关文档

GET /products/_search
{
  "query": {
    "prefix": {
      "title": {
        "value": "ipho"
      }
    }
  }
}

通配符查询[wildcard]

wildcard 关键字: 通配符查询 ? 用来匹配一个任意字符 * 用来匹配多个任意字符

GET /products/_search
{
  "query": {
    "wildcard": {
      "description": {
        "value": "iphon*"
      }
    }
  }
}

###多id查询[ids] ids 关键字 : 值为数组类型,用来根据一组id获取多个对应的文档

GET /products/_search
{
  "query": {
    "ids": {
      "values": ["1","2"]
    }
  }
}

###模糊查询[fuzzy] fuzzy 关键字: 用来模糊查询含有指定关键字的文档

GET /products/_search
{
  "query": {
    "fuzzy": {
      "description": "iphooone"
    }
  }
}

注意: fuzzy 模糊查询最大模糊错误必须在0-2之间

搜索关键词长度为 2 不允许存在模糊
搜索关键词长度为3-5 允许一次模糊
搜索关键词长度大于5 允许最大2模糊

###布尔查询[bool] bool 关键字: 用来组合多个条件实现复杂查询 must: 相当于&& 同时成立 should: 相当于|| 成立一个就行 must_not: 相当于! 不能满足任何一个

GET /products/_search
{
  "query": {
    "bool": {
      "must": [
        {"term": {
          "price": {
            "value": 4999
          }
        }}
      ]
    }
  }
}

多字段查询[multi_match]

GET /products/_search
{
  "query": {
    "multi_match": {
      "query": "iphone13 毫",
      "fields": ["title","description"]
    }
  }
}

注意: 将query的字段类型进行分词,将分词之后词进行查询该字段如果该字段不分词就会将查询条件作为整体进行查询 ###默认字段分词查询[query_string]

GET /products/_search
{
  "query": {
    "query_string": {
      "default_field": "description",
      "query": "屏幕真的非常不错"
    }
  }
}

注意: 查询字段分词就将查询条件分词查询查询字段不分词将查询条件不分词查询 ###高亮查询[highlight] highlight 关键字: 可以让符合条件的文档中的关键词高亮

GET /products/_search
{
  "query": {
    "term": {
      "description": {
        "value": "iphone"
      }
    }
  },
  "highlight": {
    "fields": {
      "*":{}
    }
  }
}

自定义高亮html标签: 可以在highlight中使用pre_tags和post_tags

GET /products/_search
{
  "query": {
    "term": {
      "description": {
        "value": "iphone"
      }
    }
  },
  "highlight": {
    "post_tags": ["</span>"], 
    "pre_tags": ["<span style='color:red'>"],
    "fields": {
      "*":{}
    }
  }
}

多字段高亮使用require_field_match开启多个字段高亮

GET /products/_search
{
  "query": {
    "term": {
      "description": {
        "value": "iphone"
      }
    }
  },
  "highlight": {
    "require_field_match": "false",
    "post_tags": ["</span>"], 
    "pre_tags": ["<span style='color:red'>"],
    "fields": {
      "*":{}
    }
  }
}

###返回指定条数[size] size 关键字: 指定查询结果中返回指定条数。默认返回值10条

GET /products/_search
{
  "query": {
    "match_all": {}
  },
  "size": 5
}

###分页查询[from] from 关键字: 用来指定起始返回位置，和size关键字连用可实现分页效果

GET /products/_search
{
  "query": {
    "match_all": {}
  },
  "size": 5,
  "from": 0
}

###指定字段排序[sort]

GET /products/_search
{
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "price": {
        "order": "desc"
      }
    }
  ]
}

###返回指定字段[_source] _source 关键字: 是一个数组,在数组中用来指定展示那些字段

GET /products/_search
{
  "query": {
    "match_all": {}
  },
  "_source": ["title","description"]
}

###部分更新[_update]

POST /products/_update/1
{
    "doc": {
        "price": 8888
    }
}

###查询更新[_update_by_query]

POST /products/_update_by_query
{
    "query": {
        "match": {
            "_id": 1
        }
    },
    "script": {
        "source": "ctx._source.price = 8899"
    }
}

###批量操作[bulk]

POST _bulk
{"index":{"_index":"products", "_id":3}}
{"title":"iphone12 pro","price":89990,"created_at":"2020-10-23","description":"iPhone 12 Pro采用超瓷晶面板和亚光质感玻璃背板，搭配不锈钢边框，有银色、石墨色、金色、海蓝色四种颜色。宽度:71.5毫米，高度:146.7毫米，厚度:7.4毫米，重量：187克"}

###批量删除

POST _bulk
{"delete":{"_index":"products", "_id":3}}
{"delete":{"_index":"products", "_id":4}}

###批量创建

POST _bulk
{"create":{"_index":"products", "_id":3}} 
{"title":"iphone12 pro","price":8999,"created_at":"2020-10-23","description":"iPhone 12 Pro采用超瓷晶面板和亚光质感玻璃背板，搭配不锈钢边框，有银色、石墨色、金色、海蓝色四种颜色。宽度:71.5毫米，高度:146.7毫米，厚度:7.4毫米，重量：187克"}

主键重复会报错

###批量局部更新

POST _bulk
{"update":{"_index":"products","_id":4}}
{"doc": {"title":"iphone12 pro","price":8999}}

##3. 聚合查询

聚合：英文为Aggregation，是es除搜索功能外提供的针对es数据做统计分析的功能。聚合有助于根据搜索查询提供聚合数据。聚合查询是数据库中重要的功能特性，ES作为搜索引擎兼数据库，同样提供了强大的聚合分析能力。它基于查询条件来对数据进行分桶、计算的方法。有点类似于 SQL 中的 group by 再加一些函数方法的操作。注意事项：text类型是不支持聚合的。测试数据创建索引 index 和映射 mapping

PUT /fruit
{
  "mappings": {
    "properties": {
      "title":{
        "type": "keyword"
      },
      "price":{
        "type":"double"
      },
      "description":{
        "type": "text",
        "analyzer": "ik_max_word"
      }
    }
  }
}

POST /fruit/_bulk
{"index":{}}
{"title":"面包","price":19.9,"description":"小面包非常好吃"}
{"index":{}}
{"title":"旺仔牛奶","price":29.9,"description":"非常好喝"}
{"index":{}}
{"title":"豆本豆","price":19.9,"description":"豆本豆非常好吃"}
{"index":{}}
{"title":"小馒头","price":19.9,"description":"小馒头非常好吃"}
{"index":{}}
{"title":"大辣片","price":39.9,"description":"大辣片非常好吃"}
{"index":{}}
{"title":"王老吉","price":9.9,"description":"透心凉非常好喝"}
{"index":{}}
{"title":"小浣熊","price":19.9,"description":"童年的味道"}
{"index":{}}
{"title":"海苔","price":19.9,"description":"海的味道"}

###根据某个字段进行分组统计数量比如统计“好吃” 好评的数量

GET /fruit/_search
{
  "query": {
    "term": {
      "description": {
        "value": "好吃"
      }
    }
  }, 
  "aggs": {
    "price_group": {
      "terms": {
        "field": "price"
      }
    }
  }
}

###求最大值

GET /fruit/_search
{
  "aggs": {
    "price_max": {
      "max": {
        "field": "price"
      }
    }
  }
}

###求最小值

GET /fruit/_search
{
  "aggs": {
    "price_min": {
      "min": {
        "field": "price"
      }
    }
  }
}

###求平均值

GET /fruit/_search { "aggs": { "price_agv": { "avg": { "field": "price" } } } }

###求和

GET /fruit/_search
{
  "aggs": {
    "price_sum": {
      "sum": {
        "field": "price"
      }
    }
  }
}

准备案例数据 Mappings

PUT /cars
{
    "mappings": {
        "properties": {
            "price": {
                "type": "long"
            },
            "color": {
                "type": "keyword"
            },
            "brand": {
                "type": "keyword"
            },
            "model": {
                "type": "keyword"
            },
            "sold_date": {
                "type": "date",
                "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis"
            },
            "remark": {
                "type": "text",
                "analyzer": "ik_max_word"
            }
        }
    }
}

bluck插入数据

POST /cars/_bulk
{"index":{}}
{"price":258000,"color":"金色","brand":"大众","model":"大众迈腾","sold_date":"2021-10-22","remark":"大众中档车"}
{"index":{}}
{"price":123000,"color":"金色","brand":"大众","model":"大众速腾","sold_date":"2021-11-05","remark":"大众神车"}
{"index":{}}
{"price":239800,"color":"白色","brand":"标志","model":"标志508","sold_date":"2021-05-18","remark":"标志品牌全球上市车型"}
{"index":{}}
{"price":148800,"color":"白色","brand":"标志","model":"标志408","sold_date":"2021-07-02","remark":"比较大的紧凑型车"}
{"index":{}}
{"price":1998000,"color":"黑色","brand":"大众","model":"大众辉腾","sold_date":"2021-08-19","remark":"大众最让人肝疼的车"}
{"index":{}}
{"price":218000,"color":"红色","brand":"奥迪","model":"奥迪A4","sold_date":"2021-11-06","remark":"小资车型"}
{"index":{}}
{"price":489000,"color":"黑色","brand":"奥迪","model":"奥迪A6","sold_date":"2022-01-01","remark":"政府专用？"}
{"index":{}}
{"price":1899000,"color":"黑色","brand":"奥迪","model":"奥迪A8","sold_date":"2022-02-12","remark":"很贵的大A6。。。"}

###统计某个维度平均价格

GET cars/_search
{
    "size":0,
    "aggs": {
        "group_by_color": {
            "terms": {
                "field": "color",
                "order": {
                    "avg_by_price": "asc"
                }
            },
            "aggs": {
                "avg_by_price": {
                    "avg": {
                        "field": "price"
                    }
                }
            }
        }
    }
}

设置size为0，不返回原始数据

###统计某个维度最大和最小价格、总价

```json
GET cars/_search
{
  "aggs": {
    "group_by_color": {
      "terms": {
        "field": "color"
      },
      "aggs": {
        "max_price": {
          "max": {
            "field": "price"
          }
        },
        "min_price": {
          "min": {
            "field": "price"
          }
        },
        "sum_price": {
          "sum": {
            "field": "price"
          }
        }
      }
    }
  }
}

###根据某个维度统计销售（月季年）

GET cars/_search
{
   "size" : 0,
   "aggs": {
      "sales": {
         "date_histogram": {
            "field": "sold_date",
            "calendar_interval": "month", //按月划分 year quarter day  34d
            "format": "yyyy-MM-dd",
            "min_doc_count" : 0,
            "extended_bounds" : {    //时间限制
                "min" : "2021-01-01",
                "max" : "2023-12-31"
            }
         },
         "aggs": {
            "per_brand_sum": {
               "terms": {
                  "field": "brand"
               },
               "aggs": {
                  "sum_price": {
                     "sum": { "field": "price" } 
                  }
               }
            },
            "total_sum": {
               "sum": { "field": "price" } 
            }
         }
      }
   }
}

上一篇： laravel接入websocket
下一篇： Redis基本使用

如果您喜欢我的文章，请点击下面按钮随意打赏，您的支持是我最大的动力。

打赏

elasticsearch使用进阶

2. DSL之常见的Query

查询所有[match_all]

范围查询[range]

通配符查询[wildcard]

多字段查询[multi_match]

热门标签

最新评论

友情链接

elasticsearch使用进阶

2. DSL之常见的Query

查询所有[match_all]

范围查询[range]

通配符查询[wildcard]

多字段查询[multi_match]

热门标签

置顶推荐

最新评论

友情链接