gengliangwang commented on code in PR #52831:
URL: https://github.com/apache/spark/pull/52831#discussion_r2492483625
##########
sql/pipelines/src/test/scala/org/apache/spark/sql/pipelines/utils/APITest.scala:
##########
@@ -542,6 +542,66 @@ trait APITest
}
}
+ test("Python Pipeline with cluster columns") {
+ val pipelineSpec =
+ TestPipelineSpec(include = Seq("transformations/**"))
+ val pipelineConfig = TestPipelineConfiguration(pipelineSpec)
+ val sources = Seq(
+ PipelineSourceFile(
+ name = "transformations/definition.py",
+ contents = """
+ |from pyspark import pipelines as dp
+ |from pyspark.sql import DataFrame, SparkSession
+ |from pyspark.sql.functions import col
+ |
+ |spark = SparkSession.active()
+ |
+ |@dp.materialized_view(cluster_by = ["cluster_col1"])
Review Comment:
let's also test non-existent columns
##########
sql/pipelines/src/test/scala/org/apache/spark/sql/pipelines/graph/MaterializeTablesSuite.scala:
##########
@@ -885,4 +886,228 @@ abstract class MaterializeTablesSuite extends
BaseCoreExecutionTest {
storageRoot = storageRoot
)
}
+
+ test("cluster columns with user schema") {
Review Comment:
let's also test non-existent columns
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
