stream2000 commented on code in PR #7366:
URL: https://github.com/apache/hudi/pull/7366#discussion_r1045379908
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/procedure/TestClusteringProcedure.scala:
##########
@@ -602,6 +603,46 @@ class TestClusteringProcedure extends
HoodieSparkProcedureTestBase {
}
}
+ test("Test Call run_clustering with partition selected config") {
+ withTempDir { tmp =>
+ val tableName = generateTableName
+ val basePath = s"${tmp.getCanonicalPath}/$tableName"
+ spark.sql(
+ s"""
+ |create table $tableName (
+ | id int,
+ | name string,
+ | price double,
+ | ts long
+ |) using hudi
+ | options (
+ | primaryKey ='id',
+ | type = 'cow',
+ | preCombineField = 'ts'
+ | )
+ | partitioned by(ts)
+ | location '$basePath'
+ """.stripMargin)
+
+ spark.sql(s"insert into $tableName values(1, 'a1', 10, 1010)")
+ spark.sql(s"insert into $tableName values(2, 'a2', 10, 1010)")
+ spark.sql(s"insert into $tableName values(3, 'a3', 10, 1011)")
+ spark.sql(s"set
${HoodieClusteringConfig.PARTITION_SELECTED.key()}=ts=1010")
Review Comment:
Good suggestion. I will add more selected partitions as another test case
below. This case is to test that when PARTITION_SELECTED is set, we don't need
to list all partitions and use the partitions designated in config so I choose
only a part of all partitions to schedule clustering.
--
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]
