Ingest Pipeline & Painless Script

DELETE tech_blogs

#Blog数据，包含3个字段，tags用逗号间隔
PUT tech_blogs/_doc/1
{
  "title":"Introducing big data......",
  "tags":"hadoop,elasticsearch,spark",
  "content":"You know ,for big data"
}

#测试split tags
POST _ingest/pipeline/_simulate
{
  "pipeline": {
    "description": "to split blog tags",
    "processors": [
      {
        "split": {
          "field": "tags",
          "separator": ","
        }
      }
    ]
  },
  "docs": [
    {
      "_index":"index",
      "_id":"id",
      "_source":{
        "title":"Introducing big data......",
        "tags":"hadoop,elasticsearch,spark",
        "content":"You know, for big data"
      }
    },
    {
      "_index":"index",
      "_id":"idxx",
      "_source":{
        "title":"Introducing cloud computering",
        "tags":"openstack,k8s",
        "content":"You know, for cloud"
      }
    }
  ]
}

#同时为文档，增加一个字段。blog查看量
POST _ingest/pipeline/_simulate
{
  "pipeline": {
    "description": "to split blog tags",
    "processors": [
      {
        "split": {
          "field": "tags",
          "separator": ","
        }
      },
      {
        "set": {
          "field": "views", 
          "value": "0"
        }
      }
    ]
  },
  "docs": [
    {
      "_index":"index",
      "_id":"id",
      "_source":{
        "title":"Introducing big data......",
        "tags":"hadoop,elasticsearch,spark",
        "content":"You know, for big data"
      }
    },
    {
      "_index":"index",
      "_id":"idxx",
      "_source":{
        "title":"Introducing cloud computering",
        "tags":"openstack,k8s",
        "content":"You know, for cloud"
      }
    }
  ]
}

#为ES添加一个Pipeline
PUT _ingest/pipeline/blog_pipeline
{
  "description": "a blog pipeline",
  "processors": [
    { "split": {
      "field": "tags",
      "separator": ","
      }
    },
    {
      "set": {
        "field": "views",
        "value": "0"
      }
    }
  ]
}

#查看Pipeline
GET _ingest/pipeline/blog_pipeline

#测试pipeline
POST _ingest/pipeline/blog_pipeline/_simulate
{
  "docs": [
    {
      "_source":{
        "title":"Introducing cloud computering",
        "tags":"openstack,k8s",
        "content":"You know, for cloud"
      }
    }
  ]
}

DELETE tech_blogs
#不使用pipeline更新数据
PUT tech_blogs/_doc/1
{
  "title":"Introducing big data......",
  "tags":"hadoop,elasticsearch,spark",
  "content":"You know ,for big data"
}

#使用pipeline更新数据
PUT tech_blogs/_doc/2?pipeline=blog_pipeline
{
        "title":"Introducing cloud computering",
        "tags":"openstack,k8s",
        "content":"You know, for cloud"
}

#查看两条数据，一条被处理，一条未被处理
POST tech_blogs/_search
{}

#update_by_query 会导致错误
POST tech_blogs/_update_by_query?pipeline=blog_pipeline
{}

#增加update_by_query的条件
POST tech_blogs/_update_by_query?pipeline=blog_pipeline
{
  "query": {
    "bool": {
      "must_not": [
        {
          "exists": {
            "field": "views"
          }
        }
      ]
    }
  }
}

POST tech_blogs/_search

#############Demo for Painless#############
#增加一个script processor
POST _ingest/pipeline/_simulate
{
  "pipeline": {
    "description": "to split blog tags",
    "processors": [
      {
        "split": {
          "field": "tags",
          "separator": ","
        }
      },
      {
        "script": {
          "source": """
          if(ctx.containsKey("content")){
            ctx.content_length = ctx.content.length();
          }else{
            ctx.content_length=0;
          }
          
          """
        }
      },
      {
        "set": {
          "field": "views",
          "value": "0"
        }
      }
    ]
  },
  "docs": [
    {
      "_index":"index",
      "_id":"id",
      "_source":{
          "title":"Introducing big data......",
  "tags":"hadoop,elasticsearch,spark",
  "content":"You know ,for big data"  
      }
    },
    {
     "_index":"index",
      "_id":"idxx",  
      "_source":{
              "title":"Introducing cloud computering",
        "tags":"openstack,k8s",
        "content":"You know, for cloud"  
      }
    }
  ]
}

DELETE tech_blogs
PUT tech_blogs/_doc/1
{
  "title":"Introducing big data......",
  "tags":"hadoop,elasticsearch,spark",
  "content":"You know ,for big data",
  "views":0
}

POST tech_blogs/_update/1
{
  "script": {
    "source": "ctx._source.views += params.new_views",
    "params": {
      "new_views":100
    }
  }
}

#查看views计数
POST tech_blogs/_search
{}

#保存脚本在 Cluster State
POST _scripts/update_views
{
  "script":{
    "lang":"painless",
    "source": "ctx._source.views += params.new_views"
  }
}

POST tech_blogs/_update/1
{
  "script": {
    "id":"update_views",
    "params": {
      "new_views":1000
    }
  }
}

POST tech_blogs/_search
{}

GET tech_blogs/_search
{
  "script_fields": {
    "rnd_views": {
      "script": {
        "lang": "painless",
        "source": """
          java.util.Random rnd = new Random();
          doc['views'].value+rnd.nextInt(1000);
        """
      }
    }
  },
  "query": {
    "match_all": {}
  }
}