_Join datatype 父子关系数据建模

　　nested object的建模，有个不好的地方，就是采取的是类似冗余数据的方式，将多个数据都放在一起了，维护成本比较高　

　　ES 提供了类似关系型数据库中 Join 的实现。使用 Join 数据类型实现，可以通过 Parent / Child 的关系，从而分离两个对象

• 父文档和子文档是两个独立的文档
• 更新父文档无需重新索引整个子文档。子文档被新增，更改和删除也不会影响到父文档和其他子文档。

PUT my_blogs
{
  "mappings": {
    "properties": {
      "blog_comments_relation":{
        "type":"join",
        "relations":{  //父子关系
          "blog"(父节点):"comment"（子节点）
        }
      },
      "content":{
        "type":"text"
      },
      "title":{
        "type":"keyword"
      }
    }
  }
}

　　创建父节点

#索引父文档
PUT my_blogs/_doc/blog1
{
  "title":"Learning Elasticsearch",
  "content":"learning ELK @ geektime",
  "blog_comments_relation":{
    "name":"blog"
  }
}

#索引父文档
PUT my_blogs/_doc/blog2
{
  "title":"Learning Hadoop",
  "content":"learning Hadoop",
    "blog_comments_relation":{
    "name":"blog"
  }
}

索引子文档

　　父文档和子文档必须存在相同的分片上：确保查询 join 的性能

　　当指定文档时候，必须指定它的父文档 ID：使用 route 参数来保证，分配到相同的分片

　　

#索引子文档
PUT my_blogs/_doc/comment1?routing=blog1     //指定routing确保父子节点索引到相同的分片
{
  "comment":"I am learning ELK",
  "username":"Jack",
  "blog_comments_relation":{
    "name":"comment",
    "parent":"blog1"    //父文档ID
  }
}

#索引子文档
PUT my_blogs/_doc/comment2?routing=blog2
{
  "comment":"I like Hadoop!!!!!",
  "username":"Jack",
  "blog_comments_relation":{
    "name":"comment",
    "parent":"blog2"
  }
}

#索引子文档
PUT my_blogs/_doc/comment3?routing=blog2
{
  "comment":"Hello Hadoop",
  "username":"Bob",
  "blog_comments_relation":{
    "name":"comment",
    "parent":"blog2"
  }
}

　　查询

//查询父节点
GET /my_blogs/_doc/blog2

//parent_id查询
POST /my_blogs/_search
{
  "query":{
    "parent_id":{
      "type":"comment",
      "id":"blog2"
    }
  }
}

---------------------结果-------------------------

{
  "took" : 15,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 0.5389965,
    "hits" : [
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "comment2",
        "_score" : 0.5389965,
        "_routing" : "blog2",
        "_source" : {
          "comment" : "I like Hadoop!!!!!",
          "username" : "Jack",
          "blog_comments_relation" : {
            "name" : "comment",
            "parent" : "blog2"
          }
        }
      },
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "comment3",
        "_score" : 0.5389965,
        "_routing" : "blog2",
        "_source" : {
          "comment" : "Hello Hadoop",
          "username" : "Bob",
          "blog_comments_relation" : {
            "name" : "comment",
            "parent" : "blog2"
          }
        }
      }
    ]
  }
}

------------结果--------------------
{
  "took" : 70,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "blog1",
        "_score" : 1.0,
        "_source" : {
          "title" : "Learning Elasticsearch",
          "content" : "learning ELK @ geektime",
          "blog_comments_relation" : {
            "name" : "blog"
          }
        }
      },
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "blog2",
        "_score" : 1.0,
        "_source" : {
          "title" : "Learning Hadoop",
          "content" : "learning Hadoop",
          "blog_comments_relation" : {
            "name" : "blog"
          }
        }
      }
    ]
  }
}

POST my_blogs/_search
{
  "query": {
    "has_parent": {
      "parent_type": "blog",
      "query": {
         "match":{
           "title":"Learning Hadoop"
         }
      }
    }
  }
}

-------------------结果-------------------

{
  "took" : 5,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "comment2",
        "_score" : 1.0,
        "_routing" : "blog2",
        "_source" : {
          "comment" : "I like Hadoop!!!!!",
          "username" : "Jack",
          "blog_comments_relation" : {
            "name" : "comment",
            "parent" : "blog2"
          }
        }
      },
      {
        "_index" : "my_blogs",
        "_type" : "_doc",
        "_id" : "comment3",
        "_score" : 1.0,
        "_routing" : "blog2",
        "_source" : {
          "comment" : "Hello Hadoop",
          "username" : "Bob",
          "blog_comments_relation" : {
            "name" : "comment",
            "parent" : "blog2"
          }
        }
      }
    ]
  }
}

#通过ID和routing ，访问子文档
GET my_blogs/_doc/comment3?routing=blog2

--------------------结果-------------------------
{
  "_index" : "my_blogs",
  "_type" : "_doc",
  "_id" : "comment3",
  "_version" : 1,
  "_seq_no" : 4,
  "_primary_term" : 1,
  "_routing" : "blog2",
  "found" : true,
  "_source" : {
    "comment" : "Hello Hadoop",
    "username" : "Bob",
    "blog_comments_relation" : {
      "name" : "comment",
      "parent" : "blog2"
    }
  }
}

Join类型约束
　　每个索引只允许一个Join类型Mapping定义；
　　父文档和子文档必须在同一个分片上编入索引；这意味着，当进行删除、更新、查找子文档时候需要提供相同的路由值。
　　一个文档可以有多个子文档，但只能有一个父文档。
　　可以为已经存在的Join类型添加新的关系。
　　当一个文档已经成为父文档后，可以为该文档添加子文档。
全量检索

GET my_blogs/_search
{
  "query":{
    "match_all": {}
  },
  "sort":["_id"]
}