Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/22944#discussion_r232941317
--- Diff: sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
---
@@ -1556,6 +1556,20 @@ class DatasetSuite extends QueryTest with
SharedSQLContext {
df.where($"city".contains(new java.lang.Character('A'))),
Seq(Row("Amsterdam")))
}
+
+ test("SPARK-25942: typed aggregation on primitive type") {
+ val ds = Seq(1, 2, 3).toDS()
+
+ val agg = ds.groupByKey(_ >= 2)
+ .agg(sum("value").as[Long], sum($"value" + 1).as[Long])
+ assert(agg.collect() === Seq((false, 1, 2), (true, 5, 7)))
+ }
+
+ test("SPARK-25942: typed aggregation on product type") {
+ val ds = Seq((1, 2), (2, 3), (3, 4)).toDS()
+ val agg = ds.groupByKey(x => x).agg(sum("_1").as[Long], sum($"_2" +
1).as[Long])
+ assert(agg.collect().sorted === Seq(((1, 2), 1, 3), ((2, 3), 2, 4),
((3, 4), 3, 5)))
--- End diff --
can you try `((1, 2), 1L, 3L)` instead of `((1, 2), 1, 3)`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
