C/C++教程

Elasticsearch06-脚本和写入原理

本文主要是介绍Elasticsearch06-脚本和写入原理,对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!

 

Script

-- 使用painless脚本

# 数量减一, 安全的

POST produce/_update/1
{
  "script": {
    "source": "ctx._source.price-=1"
  }
}


# 数量减一, 安全的<简写>
POST produce/_update/1
{"script":  "ctx._source.price-=1"}

 

 

 

查询所有的价格

GET produce/_search
{
  "script_fields": {
    "test_field": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value"
      }
    }
  }
}

 

 

 

给数组中添加元素

POST product/_update/2
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.tags.add('无线充电')"
  }
}

 

 

传参的方式,给数组中添加元素

POST product/_update/2
{
  "script": {
    "lang": "painless",
    "source": "ctx._source.tags.add(params.tag_name)",
    "params": {
      "tag_name": "新增"
    }
  }
}

 

 

删除数据

POST product/_update/3
{
  "script": {
    "lang": "painless",
    "source": "ctx.op='delete'"
  }
}

 

 

如果数据存在,执行部分update操作,如果数据不存在,那么执行create操作

POST produce/_update/2
{
  "script": {
    "source": "ctx._source.price += params.paraml",
    "lang": "painless",
    "params": {
      "paraml": 100
    }
  },
  "upsert": {
    "name": "xiaoke",
    "price": 2000
  }
}

 

 

_bulk更新

POST _bulk
{ "update" : { "_id" : "5", "_index" : "produce", "retry_on_conflict" : 3} }
{ "script" : { "source": "ctx._source.price += params.param1", "lang" : "painless", "params" : {"param1" : 100}}, "upsert" : {"price" : 1999}}

 

 

 

打8折价格

GET produce/_search
{
  "script_fields": {
    "discount_price": {
      "script": {
        "lang": "painless",
        "source": "doc['price'].value * params.discount",
        "params": {
          "discount" : 0.8
        }
      }
    }
  }
}


GET produce/_search
{
  "script_fields": {
    "discount_price": {
      "script": {
        "lang": "painless",
        "source": "doc.price.value * params.discount",
        "params": {
          "discount": 0.8
        }
      }
    }
  }
}

 

 

 

 

原始价格 和 多个打折价格

GET produce/_search
{
  "script_fields": {
    "init_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
        }
      }
    }
  }
}

 

 

 

 

 

缓存方式查询

# /_scripts/{id}  类似存储过程  计算折扣 作用域为整个集群
# 默认缓存大小是100MB  没有过期时间 可以手工设置过期时间script.cache.expire 通过script.cache.max_size设置缓存大小 脚本最大64MB



创建
POST _scripts/calculate-discount
{
  "script": {
    "lang": "painless",
    "source": "doc['price'].value * params.discount"
  }
}

查看
GET _scripts/calculate-discount

使用
GET produce/_search
{
  "script_fields": {
    "discount_price": {
      "script": {
        "id":"calculate-discount",
        "params": {
          "discount": 0.8
        }
      }
    }
  }
}


删除
DELETE _scripts/calculate-discount

 

 

 

 

Date

PUT /one/_doc/2
{
  "name": "xiaoke",
  "createtime": "2021-09-06"
}


# year、month、dayOfMonth、dayOfWeek、dayOfYear、hour、minute、second、nano
GET one/_search
{
  "script_fields": {
    "test_year": {
      "script": {
        "source": "doc.createtime.value.year"
      }
    }
  }
}

 

 

复杂操作,多个column更新

POST produce/_update/1
{
  "script": {
    "lang": "painless",
    "source": """
      ctx._source.name += params.name;
      ctx._source.price -= 1
    """,
    "params": {
      "name": "无线充电",
      "price": "1"
    }
  }
}

 

 

 

正则匹配, 开启: script.painless.regex.enabled: true

POST produce/_update/1
{
  "script": {
    "lang": "painless",
    "source": """
      if (ctx._source.name =~ /[\s\S]*phone[\s\S]*/) {
        ctx._source.name += "***|";
      } else {
        ctx.op = "noop";
      }
    """
  }
}


POST one/_update/1
{
  "script": {
    "lang": "painless",
    "source": """
      if (ctx._source.createtime ==~ /[0-9]{4}-[0-9]{2}-[0-9]{2}/) {
        ctx._source.name += "|***";
      } else {
        ctx.op = "noop";
      }
    """
  }
}

 

 

统计所有小于1000商品tag的 数量 不考虑去重

GET /produce/_search
{
  "query": {
    "bool": {
      "filter": [
        {
          "range": {
            "price": {
              "lt": 1000
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "tag_agg_group": {
      "sum": {
        "script": {
          "lang": "painless",
          "source": """
            int total = 0;
            for (int i = 0; i < doc['tags'].length; i++)
            {
               total++
            }
            return total;
          """
        }
      }
    }
  },
  "size": 0
}

 

 

 

练习题

测试数据:
PUT /test_indexc/_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"}]}

求: 所有案件中男性的数量
GET /test_index1/_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;
          """
        }
      }
    }
  },
  "size": 0
}

 

 

 

 

 

ES写入原理

写入步骤  
1.client请求    
2. a.内存Buffer b.持久化到translog文件 1.只是负责写入,很快会写入index segment file中 2.通过refresh写入到segment中 refresh  
3.index segment 1.用来增删改查的缓存 flush、a.刷到os cache b.触发commit  
4.OS cache fsync  
5.OS disk    

 

 

 

 

 

 

 

 

refresh

1.将内存Buffer中导数据刷新到segment中
2.自动刷新
PUT /index
{"settings":{"refresh_interval": "10s"}}
3.手动刷新
POST /index/refresh

 

 

流程

refresh行为会立即把缓存中的文档写入segment中,但是此时新创建的segment是写在文件系统的缓存中的,如果出现断电等异常,name这部分数据就会丢失。所以es会定期执行flush操作,将缓存中segment全部写入磁盘并确保写入成功,同时创建一个commit point,整个过程就是一个完整的commit过程。
 

 


flush

1.手动执行
 POST /index/_flush
 
2.自动执行
触发flush:当文件大小达到阈值或者一定时间(默认30分钟)
    a.将数据刷到os cache
    b.同步创建commit
    c.fsync
    d.清空translog
    e.如果d之前出现了关机,内存数据丢失,会从translog文件加载
​
segment删除步骤
1.选择相似segment合并
2.flush操作
3.创建新的commit piont标记新的segment,删除旧的标记
4.将新的segment搜索状态打开
5.删除旧的segment文件

 


 

 

 

这篇关于Elasticsearch06-脚本和写入原理的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!