[ 
https://issues.apache.org/jira/browse/HUDI-8956?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17925891#comment-17925891
 ] 

Ekaterina Belousova commented on HUDI-8956:
-------------------------------------------

but why column dt should be in schema if you use this property?
hoodie.datasource.write.drop.partition.columns = 'true'

> insert with static partition config leads to wrong schema being written
> -----------------------------------------------------------------------
>
>                 Key: HUDI-8956
>                 URL: https://issues.apache.org/jira/browse/HUDI-8956
>             Project: Apache Hudi
>          Issue Type: Bug
>            Reporter: Davis Zhang
>            Priority: Major
>             Fix For: 1.0.2
>
>
>  
> {code:java}
> test("Test enable hoodie.datasource.write.drop.partition.columns when write") 
> {
>   withSQLConf("hoodie.sql.bulk.insert.enable" -> "false") {
>     Seq("cow").foreach { tableType =>
>       withRecordType()(withTempDir { tmp =>
>         val tableName = generateTableName
>         spark.sql(
>           s"""
>              | create table $tableName (
>              |  id int,
>              |  name string,
>              |  price double,
>              |  ts long,
>              |  dt string
>              | ) using hudi
>              | partitioned by (dt)
>              | location '${tmp.getCanonicalPath}/$tableName'
>              | tblproperties (
>              |  primaryKey = 'id',
>              |  preCombineField = 'ts',
>              |  type = '$tableType',
>              |  hoodie.datasource.write.drop.partition.columns = 'true'
>              | )
>      """.stripMargin)
>         spark.sql(s"insert into $tableName partition(dt='2021-12-25') values 
> (1, 'a1', 10, 1000)")
>         spark.sql(s"insert into $tableName partition(dt='2021-12-25') values 
> (2, 'a2', 20, 1000)")
>         checkAnswer(s"select id, name, price, ts, dt from $tableName")(
>           Seq(1, "a1", 10, 1000, "2021-12-25"),
>           Seq(2, "a2", 20, 1000, "2021-12-25")
>         )
>       })
>     }
>   }
> } {code}
> extra commit metadata does not contain the partition column `dt`
> {code:java}
>   "schema": 
> "{\"type\":\"record\",\"name\":\"h2_record\",\"namespace\":\"hoodie.h2\",\"fields\":[{\"name\":\"id\",\"type\":[\"null\",\"int\"],\"default\":null},{\"name\":\"name\",\"type\":[\"null\",\"string\"],\"default\":null},{\"name\":\"price\",\"type\":[\"null\",\"double\"],\"default\":null},{\"name\":\"ts\",\"type\":[\"null\",\"long\"],\"default\":null}]}"{code}



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to