[
https://issues.apache.org/jira/browse/HIVE-5850?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Shengjun Xin updated HIVE-5850:
-------------------------------
Attachment: schema.tar.gz
part.tar.gz
partsupp.tar.gz
> Multiple table join error for avro
> -----------------------------------
>
> Key: HIVE-5850
> URL: https://issues.apache.org/jira/browse/HIVE-5850
> Project: Hive
> Issue Type: Bug
> Affects Versions: 0.11.0
> Reporter: Shengjun Xin
> Attachments: part.tar.gz, partsupp.tar.gz, schema.tar.gz
>
>
> Reproduce step:
> {code}
> -- Create table Part.
> CREATE EXTERNAL TABLE part
> 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'
> LOCATION 'hdfs://<hostname>/user/hadoop/tpc-h/data/part'
> TBLPROPERTIES
> ('avro.schema.url'='hdfs://<hostname>/user/hadoop/tpc-h/schema/part.avsc');
> -- Create table Part Supplier.
> CREATE EXTERNAL TABLE partsupp
> 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'
> LOCATION 'hdfs://<hostname>/user/hadoop/tpc-h/data/partsupp'
> TBLPROPERTIES
> ('avro.schema.url'='hdfs://<hostname>/user/hadoop/tpc-h/schema/partsupp.avsc');
> --- Query
> select * from partsupp ps join part p on ps.ps_partkey = p.p_partkey where
> p.p_partkey=1;
> {code}
> {code}
> Error message is:
> Error: java.io.IOException: java.io.IOException:
> org.apache.avro.AvroTypeException: Found {
> "type" : "record",
> "name" : "partsupp",
> "namespace" : "com.gs.sdst.pl.avro.tpch",
> "fields" : [ {
> "name" : "ps_partkey",
> "type" : "long"
> }, {
> "name" : "ps_suppkey",
> "type" : "long"
> }, {
> "name" : "ps_availqty",
> "type" : "long"
> }, {
> "name" : "ps_supplycost",
> "type" : "double"
> }, {
> "name" : "ps_comment",
> "type" : "string"
> }, {
> "name" : "systimestamp",
> "type" : "long"
> } ]
> }, expecting {
> "type" : "record",
> "name" : "part",
> "namespace" : "com.gs.sdst.pl.avro.tpch",
> "fields" : [ {
> "name" : "p_partkey",
> "type" : "long"
> }, {
> "name" : "p_name",
> "type" : "string"
> }, {
> "name" : "p_mfgr",
> "type" : "string"
> }, {
> "name" : "p_brand",
> "type" : "string"
> }, {
> "name" : "p_type",
> "type" : "string"
> }, {
> "name" : "p_size",
> "type" : "int"
> }, {
> "name" : "p_container",
> "type" : "string"
> }, {
> "name" : "p_retailprice",
> "type" : "double"
> }, {
> "name" : "p_comment",
> "type" : "string"
> }, {
> "name" : "systimestamp",
> "type" : "long"
> } ]
> }
> at
> org.apache.hadoop.hive.io.HiveIOExceptionHandlerChain.handleRecordReaderNextException(HiveIOExceptionHandlerChain.java:121)
> at
> org.apache.hadoop.hive.io.HiveIOExceptionHandlerUtil.handleRecordReaderNextException(HiveIOExceptionHandlerUtil.java:77)
> at
> org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.doNextWithExceptionHandler(HadoopShimsSecure.java:302)
> at
> org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.next(HadoopShimsSecure.java:218)
> at
> org.apache.hadoop.mapred.MapTask$TrackedRecordReader.moveToNext(MapTask.java:197)
> at
> org.apache.hadoop.mapred.MapTask$TrackedRecordReader.next(MapTask.java:183)
> at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:52)
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:429)
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
> at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:158)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1478)
> at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:153)
> {code}
--
This message was sent by Atlassian JIRA
(v6.1#6144)