hudi-bot opened a new issue, #16823:
URL: https://github.com/apache/hudi/issues/16823
{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}
## JIRA info
- Link: https://issues.apache.org/jira/browse/HUDI-8956
- Type: Bug
- Fix version(s):
- 1.1.0
---
## Comments
11/Feb/25 08:23;ktblsva;but why column dt should be in schema if you use
this property?
hoodie.datasource.write.drop.partition.columns = 'true';;;
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
