Hive Table Error loading json data - json

Question

json file:
{
"DocId":"ABC",
"User":{
"Id":1234,
"Username":"sam1234",
"Name":"Sam",
"ShippingAddress":{
"Address1":"123 Main St.",
"Address2":null,
"City":"Durham",
"State":"NC"
},
"Orders":[{
"ItemId":6789,
"OrderDate":"11/11/2012"
},
{
"ItemId":4352,
"OrderDate":"12/12/2012"
}
]
}
}}
schema:
create external table sample_json(DocId string,User struct<Id:int,Username:string,Name:string,ShippingAddress:struct<Address1:string,Address2:string,City:string,State:string>,Orders:array<struct<ItemId:int,OrderDate:string>>>)ROW FORMAT SERDE 'com.cloudera.hive.serde.JSONSerDe' location '/user/babu/sample_json';
--loading data to the hive table
load data inpath '/user/samplejson/samplejson.json' into table sample_json;
Error:
when I am firing the select query like
select * from sample_json;
Exception:
Failed with exception
java.io.IOException:org.apache.hadoop.hive.serde2.SerDeException:
org.codehaus.jackson.JsonParseException: Unexpected end-of-input:
expected close marker for OBJECT (from [Source:
java.io.StringReader#8c3770; line: 1, column: 0]) at [Source:
java.io.StringReader#8c3770; line: 1, column: 3]

Answer 1

First please ensure that json file is valid through http://jsonlint.com and then remove any newline characters or unwanted spaces in the json file before loading the file into the hive table. Also please drop the table and create a new table if you have already loaded json files having newline characters into the table.
Following is the input you can try
{"DocId":"ABC",
"User":{"Id":1234,
"Username":"sam1234",
"Name":"Sam",
"ShippingAddress":{"Address1":"123 Main St.","Address2":null,"City":"Durham","State":"NC"},
"Orders":[{"ItemId":6789,"OrderDate":"11/11/2012"},
{"ItemId":4352,"OrderDate":"12/12/2012"}
]
}
}

Answer 2

remove the newline from the json file.
{"DocId": "ABC", "Userdetails": {"Id": 1234, "Username": "sam1234", "Name": "Sam", "ShippingAddress": {"Address1": "123 Main St.", "Address2": null, "City": "Durham", "State": "NC" }, "Orders":[{"ItemId": 6789, "OrderDate": "11/11/2012"}, {"ItemId": 4352, "OrderDate": "12/12/2012"}]}}
change User to userdetails as it's a identifier check the error which I got.
3.either use location or load data inpath. because both does the same work. Location does not create a folder in HDFS while load inpath does create folder.
following are the commands :
hive>
create external table sample_json(DocId string, userdetails struct< Id:int , Username:string,Name:string,ShippingAddress:struct,Orders:array< struct< ItemId:int, OrderDate:string>>>)ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe' location '/user/admin';
OK
Time taken: 0.13 seconds
hive>
select * from sample_json;
OK
sample_json.docid sample_json.userdetails
ABC {"id":1234,"username":"sam1234","name":"Sam","shippingaddress":{"address1":"123 Main St.","address2":null,"city":"Durham","state":"NC"},"orders":[{"itemid":6789,"orderdate":"11/11/2012"},{"itemid":4352,"orderdate":"12/12/2012"}]}
Time taken: 0.106 seconds, Fetched: 1 row(s)