[jira] [Created] (HIVE-5456) Queries fail on avro backed table with empty partition

["Prasad Mujumdar (JIRA)" <ji...@apache.org>]

Prasad Mujumdar created HIVE-5456:
-------------------------------------

             Summary: Queries fail on avro backed table with empty partition 
                 Key: HIVE-5456
                 URL: https://issues.apache.org/jira/browse/HIVE-5456
             Project: Hive
          Issue Type: Bug
          Components: Query Processor
    Affects Versions: 0.11.0
            Reporter: Prasad Mujumdar


The following query fails
{noformat}
DROP TABLE IF EXISTS episodes_partitioned;
CREATE TABLE episodes_partitioned
PARTITIONED BY (doctor_pt 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": "testing.hive.avro.serde",
  "name": "episodes",
  "type": "record",
  "fields": [
    {
      "name":"title",
      "type":"string",
      "doc":"episode title"
    },
    {
      "name":"air_date",
      "type":"string",
      "doc":"initial date"
    },
    {
      "name":"doctor",
      "type":"int",
      "doc":"main actor playing the Doctor in episode"
    }
  ]
}');

ALTER TABLE episodes_partitioned ADD PARTITION (doctor_pt=4);
ALTER TABLE episodes_partitioned ADD PARTITION (doctor_pt=5);
SELECT COUNT(*) FROM episodes_partitioned;
{noformat}

with following exception 

{noformat}
java.io.IOException: org.apache.hadoop.hive.serde2.avro.AvroSerdeException: Neither avro.schema.literal nor avro.schema.url specified, can't determine table schema
        at org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat.getHiveRecordWriter(AvroContainerOutputFormat.java:61)
        at org.apache.hadoop.hive.ql.exec.Utilities.createEmptyFile(Utilities.java:2869)
        at org.apache.hadoop.hive.ql.exec.Utilities.createDummyFileForEmptyPartition(Utilities.java:2901)
        at org.apache.hadoop.hive.ql.exec.Utilities.getInputPaths(Utilities.java:2825)
        at org.apache.hadoop.hive.ql.exec.mr.ExecDriver.execute(ExecDriver.java:381)
        at org.apache.hadoop.hive.ql.exec.mr.MapRedTask.execute(MapRedTask.java:136)
        at org.apache.hadoop.hive.ql.exec.Task.executeTask(Task.java:151)
        at org.apache.hadoop.hive.ql.exec.TaskRunner.runSequential(TaskRunner.java:65)
        at org.apache.hadoop.hive.ql.Driver.launchTask(Driver.java:1409)
        at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1187)
        at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1015)
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:883)
        at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:259)
        at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:216)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:413)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:348)
        at org.apache.hadoop.hive.cli.CliDriver.processReader(CliDriver.java:446)
        at org.apache.hadoop.hive.cli.CliDriver.processFile(CliDriver.java:456)
        at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:737)
        at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:675)
        at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:614)
{noformat}



--
This message was sent by Atlassian JIRA
(v6.1#6144)