[
https://issues.apache.org/jira/browse/HIVE-25404?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zoltan Haindrich updated HIVE-25404:
------------------------------------
Description:
{code}
drop table u;drop table t;
create table t(value string default 'def') partitioned by (id integer);
create table u(id integer);
{code}
right now it causes an exception like:
{code}
See ./ql/target/tmp/log/hive.log or ./itests/qtest/target/tmp/log/hive.log, or
check ./ql/target/surefire-reports or ./itests/qtest/target/surefire-reports/
for specific test cases logs.
org.apache.hadoop.hive.ql.parse.SemanticException: Encountered parse error
while parsing rewritten merge/update or delete query
at
org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.parseRewrittenQuery(RewriteSemanticAnalyzer.java:277)
at
org.apache.hadoop.hive.ql.parse.MergeSemanticAnalyzer.analyzeMerge(MergeSemanticAnalyzer.java:272)
at
org.apache.hadoop.hive.ql.parse.MergeSemanticAnalyzer.analyze(MergeSemanticAnalyzer.java:63)
at
org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.analyzeInternal(RewriteSemanticAnalyzer.java:72)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:317)
at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:223)
[...]
Caused by: org.apache.hadoop.hive.ql.parse.ParseException: line 6:34 cannot
recognize input near 'partition' '(' 'id' in select clause
at
org.apache.hadoop.hive.ql.parse.ParseDriver.parse(ParseDriver.java:125)
at org.apache.hadoop.hive.ql.parse.ParseUtils.parse(ParseUtils.java:93)
at org.apache.hadoop.hive.ql.parse.ParseUtils.parse(ParseUtils.java:85)
at
org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.parseRewrittenQuery(RewriteSemanticAnalyzer.java:275)
{code}
because the query is rewritten to
#1 id&value specified
rewritten
{code}
FROM
`default`.`t`
RIGHT OUTER JOIN
`default`.`u`
ON `t`.`id`=`u`.`id`
INSERT INTO `default`.`t` (`id`,`value`) partition (`id`) -- insert clause
SELECT `u`.`id`,'x'
WHERE `t`.`id` IS NULL
{code}
#2 when values is not specified
{code}
merge into t using u on t.id=u.id when not matched then insert (id) values
(u.id);
{code}
rewritten query:
{code}
FROM
`default`.`t`
RIGHT OUTER JOIN
`default`.`u`
ON `t`.`id`=`u`.`id`
INSERT INTO `default`.`t` (`id`) partition (`id`) -- insert clause
SELECT `u`.`id`
WHERE `t`.`id` IS NULL
{code}
was:
{code}
drop table u;drop table t;
create table t(value string default 'def') partitioned by (id integer);
create table u(id integer);
{code}
#1 id&value specified
rewritten
{code}
FROM
`default`.`t`
RIGHT OUTER JOIN
`default`.`u`
ON `t`.`id`=`u`.`id`
INSERT INTO `default`.`t` (`id`,`value`) partition (`id`) -- insert clause
SELECT `u`.`id`,'x'
WHERE `t`.`id` IS NULL
{code}
#2 when values is not specified
{code}
merge into t using u on t.id=u.id when not matched then insert (id) values
(u.id);
{code}
rewritten query:
{code}
FROM
`default`.`t`
RIGHT OUTER JOIN
`default`.`u`
ON `t`.`id`=`u`.`id`
INSERT INTO `default`.`t` (`id`) partition (`id`) -- insert clause
SELECT `u`.`id`
WHERE `t`.`id` IS NULL
{code}
> Inserts inside merge statements are rewritten incorrectly for partitioned
> tables
> --------------------------------------------------------------------------------
>
> Key: HIVE-25404
> URL: https://issues.apache.org/jira/browse/HIVE-25404
> Project: Hive
> Issue Type: Bug
> Reporter: Zoltan Haindrich
> Assignee: Zoltan Haindrich
> Priority: Major
> Labels: pull-request-available
> Time Spent: 50m
> Remaining Estimate: 0h
>
> {code}
> drop table u;drop table t;
> create table t(value string default 'def') partitioned by (id integer);
> create table u(id integer);
> {code}
> right now it causes an exception like:
> {code}
> See ./ql/target/tmp/log/hive.log or ./itests/qtest/target/tmp/log/hive.log,
> or check ./ql/target/surefire-reports or
> ./itests/qtest/target/surefire-reports/ for specific test cases logs.
> org.apache.hadoop.hive.ql.parse.SemanticException: Encountered parse error
> while parsing rewritten merge/update or delete query
> at
> org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.parseRewrittenQuery(RewriteSemanticAnalyzer.java:277)
> at
> org.apache.hadoop.hive.ql.parse.MergeSemanticAnalyzer.analyzeMerge(MergeSemanticAnalyzer.java:272)
> at
> org.apache.hadoop.hive.ql.parse.MergeSemanticAnalyzer.analyze(MergeSemanticAnalyzer.java:63)
> at
> org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.analyzeInternal(RewriteSemanticAnalyzer.java:72)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:317)
> at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:223)
> [...]
> Caused by: org.apache.hadoop.hive.ql.parse.ParseException: line 6:34 cannot
> recognize input near 'partition' '(' 'id' in select clause
> at
> org.apache.hadoop.hive.ql.parse.ParseDriver.parse(ParseDriver.java:125)
> at org.apache.hadoop.hive.ql.parse.ParseUtils.parse(ParseUtils.java:93)
> at org.apache.hadoop.hive.ql.parse.ParseUtils.parse(ParseUtils.java:85)
> at
> org.apache.hadoop.hive.ql.parse.RewriteSemanticAnalyzer.parseRewrittenQuery(RewriteSemanticAnalyzer.java:275)
> {code}
> because the query is rewritten to
> #1 id&value specified
> rewritten
> {code}
> FROM
> `default`.`t`
> RIGHT OUTER JOIN
> `default`.`u`
> ON `t`.`id`=`u`.`id`
> INSERT INTO `default`.`t` (`id`,`value`) partition (`id`) -- insert clause
> SELECT `u`.`id`,'x'
> WHERE `t`.`id` IS NULL
> {code}
> #2 when values is not specified
> {code}
> merge into t using u on t.id=u.id when not matched then insert (id) values
> (u.id);
> {code}
> rewritten query:
> {code}
> FROM
> `default`.`t`
> RIGHT OUTER JOIN
> `default`.`u`
> ON `t`.`id`=`u`.`id`
> INSERT INTO `default`.`t` (`id`) partition (`id`) -- insert clause
> SELECT `u`.`id`
> WHERE `t`.`id` IS NULL
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
