viirya commented on a change in pull request #27499: [SPARK-30590][SQL] Untyped
select API cannot take typed column expression
URL: https://github.com/apache/spark/pull/27499#discussion_r377752050
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DatasetAggregatorSuite.scala
##########
@@ -394,4 +403,21 @@ class DatasetAggregatorSuite extends QueryTest with
SharedSparkSession {
checkAnswer(group, Row("bob", Row(true, 3)) :: Nil)
checkDataset(group.as[OptionBooleanIntData], OptionBooleanIntData("bob",
Some((true, 3))))
}
+
+ test("SPARK-30590: select multiple typed column expressions") {
+ val df = Seq((1, 2, 3, 4, 5, 6)).toDF("a", "b", "c", "d", "e", "f")
+ val fooAgg = (i: Int) => FooAgg(i).toColumn.name(s"foo_agg_$i")
+
+ val agg1 = df.select(fooAgg(1), fooAgg(2), fooAgg(3), fooAgg(4), fooAgg(5))
+ checkDataset(agg1, (3, 5, 7, 9, 11))
+
+ val agg2 = df.selectUntyped(fooAgg(1), fooAgg(2), fooAgg(3), fooAgg(4),
fooAgg(5), fooAgg(6))
+ .asInstanceOf[Dataset[(Int, Int, Int, Int, Int, Int)]]
+ checkDataset(agg2, (3, 5, 7, 9, 11, 13))
+
+ val err = intercept[AnalysisException] {
+ df.select(fooAgg(1), fooAgg(2), fooAgg(3), fooAgg(4), fooAgg(5),
fooAgg(6))
Review comment:
I think we can do it like @HyukjinKwon suggested
https://github.com/apache/spark/pull/27499#discussion_r377444876, the result is
we will lose typed info from typed 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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
