【elasticsearch】13、结构化搜索

结构化数据

• 结构化搜索（structured search）是指对结构化数据的搜索
  • 日期，布尔类型和数字都是结构化的
• 文本也可以是结构化的
  • 如彩色笔可以有离散的集合：红，绿，蓝
  • 一个博客可能被标记了标签，例如，分布式 distributed，搜索search
  • 电商网站上的商品都有UPCs（universal product codes）或者其他的唯一标识，它们都需要遵从严格规定的，结构化的格式

ex中的结构化搜索

• buer，时间，日期和数字这类结构化数据：有精确的格式，我们可以对这些格式进行逻辑操作。包括比较数字或者时间的范围，或者判定两个值的大小
• 结构化的文本可做精确匹配或者部分匹配
  • term查询/prefix前缀查询
• 结构化结果只有“是”或“否 ”两个值
  • 根据场景需要，而已决定结构化搜索是否需要打分

日期range

• date math expressions
  • 2020-01-01 00:00:))||+1M

字母	时间
y	年
M	月
w	周
d	天
H/h	小时
m	分钟
s	秒

image.png

包含不是相等

• 解决方案：增加一个genre_count字段进行计数。会在组合 bool
  query 给出解决方法

image.png
image.png

回顾

• 结构化数据 & 结构化搜索
  • 如果不需要算分，可以通过constant score，将查询转为filtering
• 范围查询和date math
• 使用exist查询处理非空null值
• 精确值&多值字段的精确查找
  • term查询是包含，不是完全相等，针对多值字段查询尤其要注意

#结构化搜索，精确匹配
DELETE products
POST /products/_bulk
{ "index": { "_id": 1 }}
{ "price" : 10,"avaliable":true,"date":"2018-01-01", "productID" : "XHDK-A-1293-#fJ3" }
{ "index": { "_id": 2 }}
{ "price" : 20,"avaliable":true,"date":"2019-01-01", "productID" : "KDKE-B-9947-#kL5" }
{ "index": { "_id": 3 }}
{ "price" : 30,"avaliable":true, "productID" : "JODL-X-1937-#pV7" }
{ "index": { "_id": 4 }}
{ "price" : 30,"avaliable":false, "productID" : "QQPX-R-3956-#aD8" }

GET products/_mapping



#对布尔值 match 查询，有算分
POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "term": {
      "avaliable": true
    }
  }
}



#对布尔值，通过constant score 转成 filtering，没有算分
POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "avaliable": true
        }
      }
    }
  }
}


#数字类型 Term
POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "term": {
      "price": 30
    }
  }
}

#数字类型 terms
POST products/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "terms": {
          "price": [
            "20",
            "30"
          ]
        }
      }
    }
  }
}

#数字 Range 查询
GET products/_search
{
    "query" : {
        "constant_score" : {
            "filter" : {
                "range" : {
                    "price" : {
                        "gte" : 20,
                        "lte"  : 30
                    }
                }
            }
        }
    }
}


# 日期 range
POST products/_search
{
    "query" : {
        "constant_score" : {
            "filter" : {
                "range" : {
                    "date" : {
                      "gte" : "now-1y"
                    }
                }
            }
        }
    }
}



#exists查询
POST products/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "exists": {
          "field": "date"
        }
      }
    }
  }
}

#处理多值字段
POST /movies/_bulk
{ "index": { "_id": 1 }}
{ "title" : "Father of the Bridge Part II","year":1995, "genre":"Comedy"}
{ "index": { "_id": 2 }}
{ "title" : "Dave","year":1993,"genre":["Comedy","Romance"] }


#处理多值字段，term 查询是包含，而不是等于
POST movies/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "genre.keyword": "Comedy"
        }
      }
    }
  }
}


#字符类型 terms
POST products/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "terms": {
          "productID.keyword": [
            "QQPX-R-3956-#aD8",
            "JODL-X-1937-#pV7"
          ]
        }
      }
    }
  }
}



POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "match": {
      "price": 30
    }
  }
}


POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "term": {
      "date": "2019-01-01"
    }
  }
}

POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "match": {
      "date": "2019-01-01"
    }
  }
}




POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "productID.keyword": "XHDK-A-1293-#fJ3"
        }
      }
    }
  }
}

POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "term": {
      "productID.keyword": "XHDK-A-1293-#fJ3"
    }
  }
}

#对布尔数值
POST products/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "avaliable": "false"
        }
      }
    }
  }
}

POST products/_search
{
  "query": {
    "term": {
      "avaliable": {
        "value": "false"
      }
    }
  }
}

POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "term": {
      "price": {
        "value": "20"
      }
    }
  }
}

POST products/_search
{
  "profile": "true",
  "explain": true,
  "query": {
    "match": {
      "price": "20"
    }
    }
  }
}


POST products/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "bool": {
          "must_not": {
            "exists": {
              "field": "date"
            }
          }
        }
      }
    }
  }
}