es-07脚本查询

脚本查询

1. 概念

   Scripting是Elasticsearch支持的一种专门用于复杂场景下支持自定义编程的强大的脚本功能，ES支持多种脚本语言，如painless，其语法类似于Java,也有注释、关键字、类型、变量、函数等，其就要相对于其他脚本高出几倍的性能，并且安全可靠，可以用于内联和存储脚本。

# ES脚本
##语法：ctx._source.<field-name>
GET product/_search
GET product/_doc/2
POST product/_update/2
{
  "script": {
    "source": "ctx._source.price-=1"
  }
}
POST product/_update/2
{
  "script": {
    "source": "ctx._source.price-=ctx._version"
  }
}

#简写
POST product/_update/2
{
  "script": "ctx._source.price-=1"
}

2. 支持的语言

   1. groovy：ES 1.4.x-5.0的默认脚本语言

   2. painless：JavaEE使用java语言开发，.Net使用C#/F#语言开发，Flutter使用Dart语言开发，同样，ES 5.0+版本后的Scripting使用的语言默认就是painless，painless是一种专门用于Elasticsearch的简单,用于内联和存储脚本，是ES 5.0+的默认脚本语言，类似于Java,也有注释、关键字、类型、变量、函数等，是一种安全的脚本语言。并且是Elasticsearch的默认脚本语言。

   3. 其他：

      expression：每个文档的开销较低：表达式的作用更多，可以非常快速地执行，甚至比编写native脚本还要快，支持javascript语法的子集：单个表达式。缺点：只能访问数字，布尔值，日期和geo_point字段，存储的字段不可用

      mustache：提供模板参数化查询

3. 特点

   1. 语法简单，学习成本低
   2. 灵活度高，可编程能力强
   3. 性能相较于其他脚本语言很高
   4. 安全性好
   5. 独立语言，虽然易学但仍需单独学习
   6. 相较于DSL性能低
   7. 不适用于复杂的业务场景

4. 应用场景：各种复杂的应用场景，如自定义评分、自定义聚合查询等。

5. 正则:

   早先某些版本正则表达式默认情况下处于禁用模式，因为它绕过了painless的针对长时间运行和占用内存脚本的保护机制。而且有深度对战行为。如果需要开启正则，需要配置：script.painless.regex.enabled: true

   注意：通常正则的使用范围比较小，应用范围基本限制在数据量比较小和并发量比较小的应用场景下。

6. doc[‘field’].value和params[‘_source’][‘field’]：

   理解之间的区别是很重要的，doc[‘field’].value和params[‘_source’][‘field’]。首先，使用doc关键字，将导致该字段的条件被加载到内存（缓存），这将导致更快的执行，但更多的内存消耗。此外，doc[…]符号只允许简单类型（不能返回一个复杂类型(JSON对象或者nested类型)），只有在非分析或单个词条的基础上有意义。但是，doc如果可能，使用仍然是从文档访问值的推荐方式，因为_source每次使用时都必须加载并解析。使用_source非常缓慢

# Scripting的CRUD
POST _reindex
{
  "source": {
    "index": "product"
  },
  "dest": {
    "index": "product2"
  }
}
# 举个例子：小米10出了新款 新增了tag 叫做“无线充电”
POST product/_update/6
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.tags.add('无线充电')"
  }
}
GET product/_doc/6
GET product/_search
{
  "size": 20,
  "query": {
    "match": {
      "_id": 10
    }
  }
}
#delete
POST product/_update/10
{
  "script": {
    "lang": "painless",
    "source": "ctx.op='delete'"
  }
}
#upsert update + insert 
DELETE product/_doc/15
GET product/_doc/15
POST product/_update/15
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.price += 100"
  },
  "upsert": {
    "name" : "小米手机10",
    "desc" : "充电贼快掉电更快，超级无敌望远镜，高刷电竞屏",
    "price" : 1999
  }
}

#GET查询 painless expression
GET product/_search
{
  "script_fields": {
    "my_price": {
      "script": {
        "lang": "expression",
        "source": "doc['price'].value* 0.9"
      }
    }
  }
}
GET product/_search
{
  "script_fields": {
    "my_price": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value* 0.9"
      }
    }
  }
}
GET product/_doc/6
POST product/_update/6
{
  "doc": {
    "price": 5999
  }
}
#==========================================
#参数化
POST product/_update/6
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.tags.add(params.tag_name)",
    "params": {
      "tag_name":"无线秒充"
    }
  }
}

GET product/_search
{
  "script_fields": {
    "my_price": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value* params.num",
        "params": {
          "num": 9 
        }
      }
    }
  }
}

GET product/_search
{
  "script_fields": {
    "my_price": {
      "script": {
        "lang": "expression",
        "source": "doc['price']* num",
        "params": {
          "num": 9 
        }
      }
    }
  }
}

#案例： 打8折
GET product/_search
{
  "script_fields": {
    "price": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value"
      }
    },
    "discount_price": {
      "script": {
        "lang": "painless",
        "source": "[doc['price'].value* params.discount_8,doc['price'].value* params.discount_7,doc['price'].value* params.discount_6,doc['price'].value* params.discount_5]",
        "params": {
          "discount_8": 0.8,
          "discount_7": 0.7,
          "discount_6": 0.6,
          "discount_5": 0.5
        }
      }
    }
  }
}

# Stored scripts   scripts模板
# /_scripts/{id}
POST _scripts/calculate_discount
{
  "script": {
    "lang": "painless",
    "source": "doc.price.value * params.discount"
  }
}
#查看
GET _scripts/calculate_discount
GET product/_search
{
  "script_fields": {
    "price": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value"
      }
    },
    "discount_fields": {
      "script": {
        "id": "calculate_discount",
        "params": {
          "discount":0.8
        }
      }
    }
  }
}

#Scripting的函数式编程
GET product/_search
GET product/_doc/1
POST product/_update/1
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.tags.add(params.tag_name)",
    "params": {
      "tag_name":"无线秒充"
    }
  }
}

POST product/_update/1
{
  "script": {
    "lang": "painless",
    "source": """
      ctx._source.tags.add(params.tag_name);
      ctx._source.price-=100;
    """,
    "params": {
      "tag_name":"无线秒充1"
    }
  }
}
GET product/_doc/1
GET product/_search
#正则like %小米% /[\s\S]*小米[\s\S]*/
POST product/_update/3
{
  "script": {
    "lang": "painless",
    "source": """
      if(ctx._source.name ==~ /[\s\S]*小米[\s\S]*/) {
        ctx._source.name+="***|"
      }else{
        ctx.op="noop"
      }
    """
  }
}
#/\d{4}-\d{2}-\d{2}[\s\S]*/
GET product/_doc/1
POST product/_update/1
{
  "script": {
    "lang": "painless",
    "source": """
      if(ctx._source.createtime ==~ /\d{4}-\d{2}-\d{2}[\s\S]*/) {
        ctx._source.name+="|***"
      }else{
        ctx.op="noop"
      }
    """
  }
}
GET product/_search
#统计所有价格小于1000的商品的tag的数量 不考虑重复的情况
GET product/_mapping
GET product/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "price": {
            "lte": 1000
          }
        }
      }
    }
  },
  "aggs": {
    "tag_agg": {
      "sum": {
        "script": {
          "lang": "painless",
          "source": """
            int total = 0;
            for(int i = 0; i <doc['tags.keyword'].length; i++){
              total++;
            }
            return total;
          """
        }
      }
    }
  }
}

#================================================
#本章小结 && 知识点补充.

# 对于一些早期版本 script.painless.regex.enabled: true
# doc['field'].value 和 params['_source']['field']

#以下为案件的嫌疑人信息
PUT test_index/_bulk?refresh
{"index":{"_id":1}}
{"ajbh": "12345","ajmc": "立案案件","lasj": "2020/05/21 13:25:23","jsbax_sjjh2_xz_ryjbxx_cleaning": [{"XM": "张三","NL": "30","SF": "男"},{"XM": "李四","NL": "31","SF": "男"},{"XM": "王五","NL": "30","SF": "女"},{"XM": "赵六","NL": 23,"SF": "男"}]}
{"index":{"_id":2}}
{"ajbh": "563245","ajmc": "结案案件","lasj": "2020/05/21 13:25:23","jsbax_sjjh2_xz_ryjbxx_cleaning": [{"XM": "张三2","NL": "30","SF": "男"},{"XM": "李四2","NL": "31","SF": "男"},{"XM": "王五2","NL": "30","SF": "女"},{"XM": "赵六2","NL": "23","SF": "女"}]}
{"index":{"_id":3}}
{"ajbh": "12345","ajmc": "立案案件","lasj": "2020/05/21 13:25:23","jsbax_sjjh2_xz_ryjbxx_cleaning": [{"XM": "张三3","NL": "30","SF": "男"},{"XM": "李四3","NL": "31","SF": "男"},{"XM": "王五3","NL": "30","SF": "女"},{"XM": "赵六3","NL": "23","SF": "男"}]}

#统计男性嫌疑人的数量
GET test_index/_search
GET product/_search
#Object Nested
GET /test_index/_search
{
  "aggs": {
    "sum_person": {
      "sum": {
        "script": {
          "lang": "painless",
          "source": """
            int total = 0;
            for(int i = 0;i< params['_source']['jsbax_sjjh2_xz_ryjbxx_cleaning'].length;i++){
              if(params['_source']['jsbax_sjjh2_xz_ryjbxx_cleaning'][i]['SF']=='男'){
                total+=1;
              }
            }
            return total;
          """
        }
      }
    }
  }
}