[jira] [Closed] (HUDI-2234) MERGE INTO works only ON primary key

["Raymond Xu (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/HUDI-2234?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Raymond Xu closed HUDI-2234.
----------------------------

> MERGE INTO works only ON primary key
> ------------------------------------
>
>                 Key: HUDI-2234
>                 URL: https://issues.apache.org/jira/browse/HUDI-2234
>             Project: Apache Hudi
>          Issue Type: Sub-task
>          Components: Spark Integration
>            Reporter: Sagar Sumit
>            Assignee: Yann Byron
>            Priority: Blocker
>             Fix For: 0.10.0
>
>
> {code:sql}
> drop table if exists hudi_gh_ext_fixed;
> create table hudi_gh_ext_fixed (id int, name string, price double, ts long) using hudi options(primaryKey = 'id', precombineField = 'ts') location 'file:///tmp/hudi-h4-fixed';
> insert into hudi_gh_ext_fixed values(3, 'AMZN', 300, 120);
> insert into hudi_gh_ext_fixed values(2, 'UBER', 300, 120);
> insert into hudi_gh_ext_fixed values(4, 'GOOG', 300, 120);
> update hudi_gh_ext_fixed set price = 150.0 where name = 'UBER';
> drop table if exists hudi_fixed;
> create table hudi_fixed (id int, name string, price double, ts long) using hudi options(primaryKey = 'id', precombineField = 'ts') partitioned by (ts) location 'file:///tmp/hudi-h4-part-fixed';
> insert into hudi_fixed values(2, 'UBER', 200, 120);
> MERGE INTO hudi_fixed 
> USING (select id, name, price, ts from hudi_gh_ext_fixed) updates
> ON hudi_fixed.name = updates.name
> WHEN MATCHED THEN
>   UPDATE SET *
> WHEN NOT MATCHED
>   THEN INSERT *;
> -- java.lang.IllegalArgumentException: Merge Key[name] is not Equal to the defined primary key[id] in table hudi_fixed
> -- 	at org.apache.spark.sql.hudi.command.MergeIntoHoodieTableCommand.buildMergeIntoConfig(MergeIntoHoodieTableCommand.scala:425)
> -- 	at org.apache.spark.sql.hudi.command.MergeIntoHoodieTableCommand.run(MergeIntoHoodieTableCommand.scala:146)
> -- 	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
> -- 	at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
> -- 	at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
> -- 	at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:229)
> {code}



--
This message was sent by Atlassian Jira
(v8.20.1#820001)