[
https://issues.apache.org/jira/browse/HIVE-15239?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xuefu Zhang updated HIVE-15239:
-------------------------------
Description:
env: hive on spark engine
reproduce step:
{code}
create table a1(KEHHAO string, START_DT string) partitioned by (END_DT string);
create table a2(KEHHAO string, START_DT string) partitioned by (END_DT string);
alter table a1 add partition(END_DT='20161020');
alter table a1 add partition(END_DT='20161021');
insert into table a1 partition(END_DT='20161020')
values('2000721360','20161001');
SELECT T1.KEHHAO,COUNT(1) FROM (
SELECT KEHHAO FROM a1 T
WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND T.END_DT-1
UNION ALL
SELECT KEHHAO FROM a2 T
WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND T.END_DT-1
) T1
GROUP BY T1.KEHHAO
HAVING COUNT(1)>1;
+-------------+------+--+
| t1.kehhao | _c1 |
+-------------+------+--+
| 2000721360 | 2 |
+-------------+------+--+
{code}
the result should be none record
was:
env: hive on spark engine
reproduce step:
create table a1(KEHHAO string, START_DT string) partitioned by (END_DT string);
create table a2(KEHHAO string, START_DT string) partitioned by (END_DT string);
alter table a1 add partition(END_DT='20161020');
alter table a1 add partition(END_DT='20161021');
insert into table a1 partition(END_DT='20161020')
values('2000721360','20161001');
SELECT T1.KEHHAO,COUNT(1) FROM (
SELECT KEHHAO FROM a1 T
WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND T.END_DT-1
UNION ALL
SELECT KEHHAO FROM a2 T
WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND T.END_DT-1
) T1
GROUP BY T1.KEHHAO
HAVING COUNT(1)>1;
+-------------+------+--+
| t1.kehhao | _c1 |
+-------------+------+--+
| 2000721360 | 2 |
+-------------+------+--+
the result should be none record
> hive on spark combine equivalentwork get wrong result because of tablescan
> operation compare
> ---------------------------------------------------------------------------------------------
>
> Key: HIVE-15239
> URL: https://issues.apache.org/jira/browse/HIVE-15239
> Project: Hive
> Issue Type: Bug
> Components: Spark
> Affects Versions: 1.2.0, 2.1.0
> Reporter: wangwenli
>
> env: hive on spark engine
> reproduce step:
> {code}
> create table a1(KEHHAO string, START_DT string) partitioned by (END_DT
> string);
> create table a2(KEHHAO string, START_DT string) partitioned by (END_DT
> string);
> alter table a1 add partition(END_DT='20161020');
> alter table a1 add partition(END_DT='20161021');
> insert into table a1 partition(END_DT='20161020')
> values('2000721360','20161001');
> SELECT T1.KEHHAO,COUNT(1) FROM (
> SELECT KEHHAO FROM a1 T
> WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND
> T.END_DT-1
> UNION ALL
> SELECT KEHHAO FROM a2 T
> WHERE T.KEHHAO = '2000721360' AND '20161018' BETWEEN T.START_DT AND
> T.END_DT-1
> ) T1
> GROUP BY T1.KEHHAO
> HAVING COUNT(1)>1;
> +-------------+------+--+
> | t1.kehhao | _c1 |
> +-------------+------+--+
> | 2000721360 | 2 |
> +-------------+------+--+
> {code}
> the result should be none record
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
