[
https://issues.apache.org/jira/browse/HIVE-10729?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Selina Zhang updated HIVE-10729:
--------------------------------
Description:
When map join happens, if projection columns from the small table are complex
data types, query will fail.
Steps to reproduce:
{code:sql}
hive> set hive.auto.convert.join;
hive.auto.convert.join=true
hive> desc foo;
a array<int>
hive> select * from foo;
[1,2]
hive> desc src_int;
key int
value string
hive> select * from src_int where key=2;
2 val_2
hive> select * from foo join src on src.key = foo.a[1];
{code}
Query will fail with stack trace
{noformat}
Caused by: java.lang.ClassCastException:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryArray cannot be cast to
[Ljava.lang.Object;
at
org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector.getList(StandardListObjectInspector.java:111)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serialize(LazySimpleSerDe.java:314)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serializeField(LazySimpleSerDe.java:262)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.doSerialize(LazySimpleSerDe.java:246)
at
org.apache.hadoop.hive.serde2.AbstractEncodingAwareSerDe.serialize(AbstractEncodingAwareSerDe.java:50)
at
org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:692)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
at
org.apache.hadoop.hive.ql.exec.SelectOperator.process(SelectOperator.java:88)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.internalForward(CommonJoinOperator.java:644)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.genAllOneUniqueJoinObject(CommonJoinOperator.java:676)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.checkAndGenObject(CommonJoinOperator.java:754)
at
org.apache.hadoop.hive.ql.exec.MapJoinOperator.process(MapJoinOperator.java:386)
... 23 more
{noformat}
Similar error when join on a map key:
{code:sql}
hive> CREATE TABLE test (a INT, b MAP<INT, STRING>) STORED AS ORC;
hive> INSERT OVERWRITE TABLE test SELECT 1, MAP(1, "val_1", 2, "val_2") FROM
src LIMIT 1;
hive> select * from src join test where src.value=test.b[2];
{code}
was:
Steps to reproduce:
{code:sql}
hive> set hive.auto.convert.join;
hive.auto.convert.join=true
hive> desc foo;
a array<int>
hive> select * from foo;
[1,2]
hive> desc src_int;
key int
value string
hive> select * from src_int where key=2;
2 val_2
hive> select * from foo join src on src.key = foo.a[1];
{code}
Query will fail with stack trace
{noformat}
Caused by: java.lang.ClassCastException:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryArray cannot be cast to
[Ljava.lang.Object;
at
org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector.getList(StandardListObjectInspector.java:111)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serialize(LazySimpleSerDe.java:314)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serializeField(LazySimpleSerDe.java:262)
at
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.doSerialize(LazySimpleSerDe.java:246)
at
org.apache.hadoop.hive.serde2.AbstractEncodingAwareSerDe.serialize(AbstractEncodingAwareSerDe.java:50)
at
org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:692)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
at
org.apache.hadoop.hive.ql.exec.SelectOperator.process(SelectOperator.java:88)
at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.internalForward(CommonJoinOperator.java:644)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.genAllOneUniqueJoinObject(CommonJoinOperator.java:676)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.checkAndGenObject(CommonJoinOperator.java:754)
at
org.apache.hadoop.hive.ql.exec.MapJoinOperator.process(MapJoinOperator.java:386)
... 23 more
{noformat}
Similar error when join on a map key:
{code:sql}
hive> CREATE TABLE test (a INT, b MAP<INT, STRING>) STORED AS ORC;
hive> INSERT OVERWRITE TABLE test SELECT 1, MAP(1, "val_1", 2, "val_2") FROM
src LIMIT 1;
hive> select * from src join test where src.value=test.b[2];
{code}
> Query failed when join table with complex types (tez map join only)
> -------------------------------------------------------------------
>
> Key: HIVE-10729
> URL: https://issues.apache.org/jira/browse/HIVE-10729
> Project: Hive
> Issue Type: Bug
> Components: Query Processor
> Affects Versions: 1.2.0
> Reporter: Selina Zhang
> Assignee: Selina Zhang
> Attachments: HIVE-10729.1.patch
>
>
> When map join happens, if projection columns from the small table are complex
> data types, query will fail.
> Steps to reproduce:
> {code:sql}
> hive> set hive.auto.convert.join;
> hive.auto.convert.join=true
> hive> desc foo;
> a array<int>
> hive> select * from foo;
> [1,2]
> hive> desc src_int;
> key int
> value string
> hive> select * from src_int where key=2;
> 2 val_2
> hive> select * from foo join src on src.key = foo.a[1];
> {code}
> Query will fail with stack trace
> {noformat}
> Caused by: java.lang.ClassCastException:
> org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryArray cannot be cast to
> [Ljava.lang.Object;
> at
> org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector.getList(StandardListObjectInspector.java:111)
> at
> org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serialize(LazySimpleSerDe.java:314)
> at
> org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.serializeField(LazySimpleSerDe.java:262)
> at
> org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.doSerialize(LazySimpleSerDe.java:246)
> at
> org.apache.hadoop.hive.serde2.AbstractEncodingAwareSerDe.serialize(AbstractEncodingAwareSerDe.java:50)
> at
> org.apache.hadoop.hive.ql.exec.FileSinkOperator.process(FileSinkOperator.java:692)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
> at
> org.apache.hadoop.hive.ql.exec.SelectOperator.process(SelectOperator.java:88)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:837)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.internalForward(CommonJoinOperator.java:644)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.genAllOneUniqueJoinObject(CommonJoinOperator.java:676)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.checkAndGenObject(CommonJoinOperator.java:754)
> at
> org.apache.hadoop.hive.ql.exec.MapJoinOperator.process(MapJoinOperator.java:386)
> ... 23 more
> {noformat}
> Similar error when join on a map key:
> {code:sql}
> hive> CREATE TABLE test (a INT, b MAP<INT, STRING>) STORED AS ORC;
> hive> INSERT OVERWRITE TABLE test SELECT 1, MAP(1, "val_1", 2, "val_2") FROM
> src LIMIT 1;
> hive> select * from src join test where src.value=test.b[2];
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
