You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@hive.apache.org by "Skye Wanderman-Milne (JIRA)" <ji...@apache.org> on 2013/03/16 01:46:12 UTC

[jira] [Created] (HIVE-4195) Avro SerDe causes incorrect behavior in unrelated tables

Skye Wanderman-Milne created HIVE-4195:
------------------------------------------

             Summary: Avro SerDe causes incorrect behavior in unrelated tables
                 Key: HIVE-4195
                 URL: https://issues.apache.org/jira/browse/HIVE-4195
             Project: Hive
          Issue Type: Bug
            Reporter: Skye Wanderman-Milne


When I run a file that first creates an Avro table using the Avro SerDe, then immediately creates an LZO text table and inserts data into the LZO table, the resulting LZO table contain Avro data files. When I remove the Avro CREATE TABLE statement, the LZO table contains .lzo files as expected.

{noformat}
DROP TABLE IF EXISTS avro_table;
CREATE EXTERNAL TABLE avro_table
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": "testing.hive.avro.serde",
"name": "test_record",
"type": "record",
"fields": [
{"name":"int1", "type":"long"},
{"name":"string1", "type":"string"}
]
}');

DROP TABLE IF EXISTS lzo_table;
CREATE EXTERNAL TABLE lzo_table (
id int,
bool_col boolean,
tinyint_col tinyint,
smallint_col smallint,
int_col int,
bigint_col bigint,
float_col float,
double_col double,
date_string_col string,
string_col string,
timestamp_col timestamp)
STORED AS 
INPUTFORMAT 'com.hadoop.mapred.DeprecatedLzoTextInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
;

SET hive.exec.compress.output=true;
SET mapred.output.compression.type=BLOCK;
SET mapred.output.compression.codec=com.hadoop.compression.lzo.LzopCodec;
SET hive.exec.dynamic.partition.mode=nonstrict;
SET hive.exec.dynamic.partition=true;
SET mapred.max.split.size=256000000;
SET hive.input.format=org.apache.hadoop.hive.ql.io.CombineHiveInputFormat;
insert overwrite table lzo_table SELECT id, bool_col, tinyint_col, smallint_col, int_col, bigint_col, float_col, double_col, date_string_col, string_col, timestamp_col FROM src_table;
{noformat}

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira