You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Rajkumar Singh (JIRA)" <ji...@apache.org> on 2016/06/13 11:33:20 UTC
[jira] [Created] (SPARK-15921) Spark unable to read partitioned
table in avro format and column name in upper case
Rajkumar Singh created SPARK-15921:
--------------------------------------
Summary: Spark unable to read partitioned table in avro format and column name in upper case
Key: SPARK-15921
URL: https://issues.apache.org/jira/browse/SPARK-15921
Project: Spark
Issue Type: Bug
Components: Spark Core, SQL
Affects Versions: 1.6.0
Environment: Centos 6.6
Spark 1.6
Reporter: Rajkumar Singh
Reproduce:
{code}
[root@sandbox ~]# cat file1.csv
rks,2016
[root@sandbox ~]# cat file2.csv
raj,2015
hive> CREATE TABLE `sample_table`(
> `name` string)
> PARTITIONED BY (
> `year` int)
> ROW FORMAT DELIMITED
> FIELDS TERMINATED BY ','
> STORED AS INPUTFORMAT
> 'org.apache.hadoop.mapred.TextInputFormat'
> OUTPUTFORMAT
> 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
> LOCATION
> 'hdfs://sandbox.hortonworks.com:8020/apps/hive/warehouse/sample_table'
> TBLPROPERTIES (
> 'transient_lastDdlTime'='1465816403')
> ;
load data local inpath '/root/file2.csv' overwrite into table sample_table partition(year='2015');
load data local inpath '/root/file1.csv' overwrite into table sample_table partition(year='2016');
hive> CREATE TABLE sample_table_uppercase
> PARTITIONeD BY ( YEAR INT)
> ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
> STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
> OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
> TBLPROPERTIES (
> 'avro.schema.literal'='{
> "namespace": "com.rishav.avro",
> "name": "student_marks",
> "type": "record",
> "fields": [ { "name":"NANME","type":"string"}]
> }');
INSERT OVERWRITE TABLE sample_table_uppercase partition(Year) select name,year from sample_table;
hive> select * from sample_table_uppercase;
OK
raj 2015
rks 2016
now using spark-shell
scala>val tbl = sqlContext.table("default.sample_table_uppercase");
scala>tbl.show
+----+----+
|name|year|
+----+----+
|null|2015|
|null|2016|
+----+----+
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org