-2

我试图在配置单元中加载这个 json 数据

{
    "id": "0001",
    "type": "donut",
     "name": "Cake",
     "ppu": 0.55,
     "batters":
         {
             "batter":
                 [
                     { "id": "1001", "type": "Regular" },
                     { "id": "1002", "type": "Chocolate" },
                    { "id": "1003", "type": "Blueberry" },
                    { "id": "1004", "type": "Devil's Food" }
                ]
        },
    "topping":
        [
            { "id": "5001", "type": "None" },
            { "id": "5002", "type": "Glazed" },
            { "id": "5005", "type": "Sugar" },
            { "id": "5007", "type": "Powdered Sugar" },
            { "id": "5006", "type": "Chocolate with Sprinkles" },
            { "id": "5003", "type": "Chocolate" },
            { "id": "5004", "type": "Maple" }
        ]
}

使用 DDL 命令

ADD JAR /home/cloudera/Downloads/json-serde-1.3.6-SNAPSHOT-jar-with-dependencies.jar;

CREATE EXTERNAL TABLE format.json_serde (
  `id` string,
  `type` string,
  `name` string,
 `ppu` float,       
  batters` struct < `batter`:array < struct <`bid`:string, `btype`:string >>>,
  `topping`:array < struct<`tid`:int, `ttype`:string>>
)
ROW FORMAT SERDE 'org.openx.data.jsonserde.JsonSerDe';

正在向我抛出错误

FAILED: ParseException line 7:11 cannot recognize input near ':' 'array' '<' in column type </b>
4

2 回答 2

0

当我删除顶部附近的分号时，它起作用了。谢谢


创建外部表格式.json_serde（
id字符串，
type字符串，
name字符串，
ppu浮点数，

battersstruct< batter:array< struct< bid:string, btype:string >>>,


topping数组< struct< tid:string, ttype:string>> )

于 2017-04-27T01:47:11.340 回答
0

  1. 你有错别字
    ttype`:string应该是ttype:string
    beatsstruct应该是beats struct
    topping:array应该是topping array

  2. JSON SerDe 映射是按名称完成的。
    您的结构字段名称应与实际名称匹配，例如idand not bidor tid，否则您将获得这些字段的 NULL 值。

  3. 已经有一个 JSON SerDe，它是 Hive 安装的一部分。 https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL#LanguageManualDDL-RowFormats&SerDe

create external table json_serde 
( 
    id      string
   ,type    string 
   ,name    string 
   ,ppu     float
   ,batters struct<batter:array<struct<id:string,type:string>>>
   ,topping array<struct<id:string,type:string>>
) 
row format serde 
'org.apache.hive.hcatalog.data.JsonSerDe' 
stored as textfile
;

select * from json_serde
;

+------+-------+------+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|  id  | type  | name |        ppu        |                                                                     batters                                                                      |                                                                                                                  topping                                                                                                                  |
+------+-------+------+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| 0001 | donut | Cake | 0.550000011920929 | {"batter":[{"id":"1001","type":"Regular"},{"id":"1002","type":"Chocolate"},{"id":"1003","type":"Blueberry"},{"id":"1004","type":"Devil'sFood"}]} | [{"id":"5001","type":"None"},{"id":"5002","type":"Glazed"},{"id":"5005","type":"Sugar"},{"id":"5007","type":"PowderedSugar"},{"id":"5006","type":"ChocolatewithSprinkles"},{"id":"5003","type":"Chocolate"},{"id":"5004","type":"Maple"}] |
+------+-------+------+-------------------+--------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
于 2017-04-26T05:50:03.320 回答