You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@drill.apache.org by "Rahul Challapalli (JIRA)" <ji...@apache.org> on 2015/11/13 01:14:10 UTC

[jira] [Commented] (DRILL-4084) HIVE_DEFAULT_PARTITION : Ambiguity in how drill and hive interpret a filter on this column

    [ https://issues.apache.org/jira/browse/DRILL-4084?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15003271#comment-15003271 ] 

Rahul Challapalli commented on DRILL-4084:
------------------------------------------

Data :
{code}
1|dhfawriuueiq dshfjklhfiue eiufhwelfhleiruhj ejfwekjlf hsjdkgfhsdjk  hjd hdfkh sdhg dkj hsdhg jds gsdlgd sd hjk sdjhkjdhgsdhg
2|jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
3|dfg
4|sdjklhkhjdfgjhdfgkjhdfkjldfsgjdsfkjhdfmnb,cv
5|dfg
6|
7|jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
8|?
9|
10|?
11| a
12|a
{code}

Hive DDL :
{code}
DROP TABLE IF EXISTS empty_lengthy;
CREATE EXTERNAL TABLE empty_lengthy (
    int_col INT,
    varchar_col STRING
   )
ROW FORMAT DELIMITED FIELDS TERMINATED BY "|"
STORED AS TEXTFILE LOCATION "/drill/testdata/partition_pruning/hive/empty_lengthy_partitions.tbl";

DROP TABLE IF EXISTS empty_lengthy_p1;
CREATE TABLE empty_lengthy_p1 (
    int_col INT
   )
PARTITIONED BY (varchar_col STRING)
ROW FORMAT DELIMITED FIELDS TERMINATED BY "|"
STORED AS TEXTFILE LOCATION "/drill/testdata/partition_pruning/hive/empty_lengthy_partitions_p1";

SET hive.exec.dynamic.partition.mode=true;

insert overwrite table empty_lengthy_p1 partition (varchar_col)
select int_col, case when varchar_col='dfg' then null else varchar_col END from empty_lengthy;

DROP TABLE IF EXISTS empty_lengthy_p2;
CREATE TABLE empty_lengthy_p2 (
    int_col INT
   )
PARTITIONED BY (varchar_col STRING)
ROW FORMAT DELIMITED FIELDS TERMINATED BY "|"
STORED AS TEXTFILE LOCATION "/drill/testdata/partition_pruning/hive/empty_lengthy_partitions_p2"
TBLPROPERTIES ("serialization.null.format"="?");

SET hive.exec.dynamic.partition.mode=true;

insert overwrite table empty_lengthy_p2 partition (varchar_col)
select int_col, varchar_col from empty_lengthy;
{code}

> HIVE_DEFAULT_PARTITION : Ambiguity in how drill and hive interpret a filter on this column
> ------------------------------------------------------------------------------------------
>
>                 Key: DRILL-4084
>                 URL: https://issues.apache.org/jira/browse/DRILL-4084
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Storage - Hive
>    Affects Versions: 1.3.0
>            Reporter: Rahul Challapalli
>            Priority: Critical
>
> git.commit.id.abbrev=e78e286
> Query : 
> {code}
> select * from hive.empty_lengthy_p2 d2, hive.empty_lengthy_p1 d1 where d2.varchar_col = d1.varchar_col and length(d2.varchar_col)>10;
> {code}
> Drill Output :
> {code}
> | 1 | dhfawriuueiq dshfjklhfiue eiufhwelfhleiruhj ejfwekjlf hsjdkgfhsdjk  hjd hdfkh sdhg dkj hsdhg jds gsdlgd sd hjk sdjhkjdhgsdhg  | 1 | dhfawriuueiq dshfjklhfiue eiufhwelfhleiruhj ejfwekjlf hsjdkgfhsdjk  hjd hdfkh sdhg dkj hsdhg jds gsdlgd sd hjk sdjhkjdhgsdhg  |
> | 2 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd | 2 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd |
> | 7 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd | 2 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd |
> | 2 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd | 7 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd |
> | 7 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd | 7 | jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd |
> | 4 | sdjklhkhjdfgjhdfgkjhdfkjldfsgjdsfkjhdfmnb,cv | 4 | sdjklhkhjdfgjhdfgkjhdfkjldfsgjdsfkjhdfmnb,cv |
> {code}
> Hive Output :
> {code}
> 6	__HIVE_DEFAULT_PARTITION__	3	__HIVE_DEFAULT_PARTITION__
> 6	__HIVE_DEFAULT_PARTITION__	5	__HIVE_DEFAULT_PARTITION__
> 6	__HIVE_DEFAULT_PARTITION__	6	__HIVE_DEFAULT_PARTITION__
> 1	dhfawriuueiq dshfjklhfiue eiufhwelfhleiruhj ejfwekjlf hsjdkgfhsdjk  hjd hdfkh sdhg dkj hsdhg jds gsdlgd sd hjk sdjhkjdhgsdhg 	1	dhfawriuueiq dshfjklhfiue eiufhwelfhleiruhj ejfwekjlf hsjdkgfhsdjk  hjd hdfkh sdhg dkj hsdhg jds gsdlgd sd hjk sdjhkjdhgsdhg 
> 2	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd	2	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
> 7	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd	2	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
> 2	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd	7	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
> 7	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd	7	jkdshgf jhg sdgj dlsg jsdgjg    jkdhgiergergd fgjgioug8945u irjfoiej0930j pofkqpgogogj dogj09g djvkldsjgjgirewoie dkflvsd vkdvskgjiwegjwe;sdkvjsdgfdgksdjgkdjkdjgksjg sdkjgdsjg skdjggj;sdgjd sk;gjsd
> 4	sdjklhkhjdfgjhdfgkjhdfkjldfsgjdsfkjhdfmnb,cv	4	sdjklhkhjdfgjhdfgkjhdfkjldfsgjdsfkjhdfmnb,cv
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)