【Elasticsearch 系列】 文档的基本 CRUD 和批量操作

前言

以下操作均在 kibana 下进行，提前需要安装 kinana。

CRUD

Index 操作

# 文档不存在，创建一个新的文档，索引名为 my_indexs ,type 默认为 doc, 文档 id = 1
put my_indexs/_doc/1 
{
    "name":"joyxj",
    "age":2
}

# 执行结果
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 1,
  "result" : "created",
  "_shards" : {
    "total" : 2,
    "successful" : 1,
    "failed" : 0
  },
  "_seq_no" : 0,
  "_primary_term" : 1
}

# 再执行一次，文档存在，删除现有的文档，再创建新的文档，版本加1
put my_indexs/_doc/1 
{
    "name":"joyxj.com",
    "age":21
}

# 执行结果
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 2,
  "result" : "updated",
  "_shards" : {
    "total" : 2,
    "successful" : 1,
    "failed" : 0
  },
  "_seq_no" : 1,
  "_primary_term" : 1
}

# 查询文档的内容
get my_indexs/_doc/1

# 执行结果，从_source可以看出，只有一个值了。所以不是更新操作，而是新删除，后创建
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 2,
  "_seq_no" : 1,
  "_primary_term" : 1,
  "found" : true,
  "_source" : {
    "name" : "joyxj.com"
  }
}

对于 Index 操作，如果 ID 不存在的话，则创建新的文档。否则会删除旧的文档，再创建新的文档，同时版本号加 1.

Create 操作

指定 ID 的 Create 操作，type 默认为 _doc。

# 指定ID，type 默认为 _doc,如果 ID 存在会报错
put my_indexs/_create/1 
{
    "name":"joyxj.com",
    "age":21
}

# 执行结果
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 1,
  "result" : "created",
  "_shards" : {
    "total" : 2,
    "successful" : 1,
    "failed" : 0
  },
  "_seq_no" : 0,
  "_primary_term" : 1
}

如果不指定 ID 的话，ES 会自动生成 ID

# 不指定ID , ES 自动生成 ID
POST my_indexs/_doc
{
    "name":"joyxj.com",
    "age":21
}

对于指定 ID 情况下的 Create 操作，如果 ID 存在，会报错。

{
  "error": {
    "root_cause": [
      {
        "type": "version_conflict_engine_exception",
        "reason": "[1]: version conflict, document already exists (current version [1])",
        "index_uuid": "VSRfGESYRgmsOwMj5HZPxw",
        "shard": "0",
        "index": "my_indexs"
      }
    ],
    "type": "version_conflict_engine_exception",
    "reason": "[1]: version conflict, document already exists (current version [1])",
    "index_uuid": "VSRfGESYRgmsOwMj5HZPxw",
    "shard": "0",
    "index": "my_indexs"
  },
  "status": 409
}

Read 操作

# 语法 get {index}/{type}/{id}
get my_indexs/_doc/1

# 执行结果，其包含 index 、type 、 id 、 version 等信息。 _source 下的 json 内容是我们的查询的本身内容
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 1,
  "_seq_no" : 0,
  "_primary_term" : 1,
  "found" : true,
  "_source" : {
    "name" : "joyxj.com",
    "age" : 21
  }
}

Update 操作

对于 Update 操作，文档必须存在，更新操作只会对相应的字段做增量更新，其它字段不会被修改

# 更新操作
POST my_indexs/_update/1 
{
  "doc" : {
    "city" : "shenzhen",
    "name": "blog.joyxj.com"
  }
}

# 查询下结果
get my_indexs/_doc/1
{
  "_index" : "my_indexs",
  "_type" : "_doc",
  "_id" : "1",
  "_version" : 2,
  "_seq_no" : 2,
  "_primary_term" : 1,
  "found" : true,
  "_source" : {
    "name" : "blog.joyxj.com",
    "age" : 21,
    "city" : "shenzhen"
  }
}

删除操作

可以是删除文档，也可以删除 index。

# 删除文档
delete my_indexs/_doc/1

# 删除 index
delete my_indexs

Bulk API

• 支持在一个 API 中对多个 index 进行操作
• 支持以下 4 种操作
  • Index
  • Create
  • Delete
  • Update
• 操作中单条失败，不会影响到其它操作
• 返回结果包含了每一条操作的结果

执行命令

POST _bulk
{ "index" : { "_index" : "test", "_id" : "1" } }
{ "field1" : "value1" }
{ "delete" : { "_index" : "test", "_id" : "2" } }
{ "create" : { "_index" : "test", "_id" : "3" } }
{ "field1" : "value3" }
{ "update" : {"_id" : "1", "_index" : "test"} }
{ "doc" : {"field2" : "value2"} }

返回结果

{
  "took" : 272,
  "errors" : false,
  "items" : [
    {
      "index" : {
        "_index" : "test",
        "_type" : "_doc",
        "_id" : "1",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 0,
        "_primary_term" : 1,
        "status" : 201
      }
    },
    {
      "delete" : {
        "_index" : "test",
        "_type" : "_doc",
        "_id" : "2",
        "_version" : 1,
        "result" : "not_found",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 1,
        "_primary_term" : 1,
        "status" : 404
      }
    },
    {
      "create" : {
        "_index" : "test",
        "_type" : "_doc",
        "_id" : "3",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 2,
        "_primary_term" : 1,
        "status" : 201
      }
    },
    {
      "update" : {
        "_index" : "test",
        "_type" : "_doc",
        "_id" : "1",
        "_version" : 2,
        "result" : "updated",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 3,
        "_primary_term" : 1,
        "status" : 200
      }
    }
  ]
}

mget 批量读取

get _mget 
{
  "docs":[
    {
      "index":"my_indexs",
      "id":"1"
    },
    {
      "index":"test",
      "id":"1"
    }
  ]
}

执行结果

{
  "docs" : [
    {
      "_index" : "my_indexs",
      "_type" : "_doc",
      "_id" : "1",
      "_version" : 1,
      "_seq_no" : 0,
      "_primary_term" : 1,
      "found" : true,
      "_source" : {
        "name" : "joyxj.com",
        "age" : 21
      }
    },
    {
      "_index" : "test",
      "_type" : "_doc",
      "_id" : "1",
      "_version" : 2,
      "_seq_no" : 3,
      "_primary_term" : 1,
      "found" : true,
      "_source" : {
        "field1" : "value1",
        "field2" : "value2"
      }
    }
  ]
}

msearch 批量查询

# 下面的语句执行需要去除注释
GET twitter/_msearch
# 未指定index 
{}
{"query" : {"match_all" : {}}, "from" : 0, "size" : 10}
{}
{"query" : {"match_all" : {}}}
# 指定index
{"index" : "twitter2"}
{"query" : {"match_all" : {}}}

上面的查询包含三条查询，其中前二条未指定 index, 其 index 为默认的 twitter。第三条指定了 index 为 twitter2。