planga82 commented on a change in pull request #28351:
URL: https://github.com/apache/spark/pull/28351#discussion_r418441567
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
##########
@@ -530,6 +530,26 @@ class DataFrameAggregateSuite extends QueryTest
)
}
+ test("SPARK-31500: collect_set() of BinaryType returns duplicate elements") {
+ val bytesTest1 = "test1".getBytes
+ val bytesTest2 = "test2".getBytes
+ val df = Seq(bytesTest1, bytesTest1, bytesTest2).toDF("a")
+ val ret = df.select(collect_set($"a")).collect()
+ .map(r => r.getAs[Seq[_]](0)).head
+ assert(ret.length == 2)
+
+ val a = "aa".getBytes
+ val b = "bb".getBytes
+ val c = "cc".getBytes
+ val d = "dd".getBytes
+ val df1 = Seq((a, b), (a, b), (c, d))
+ .toDF("x", "y")
+ .select(struct($"x", $"y").as("a"))
+ val ret1 = df1.select(collect_set($"a")).collect()
+ .map(r => r.getAs[Seq[_]](0)).head
+ assert(ret1.length == 2)
Review comment:
shorter way to compare, good idea!
----------------------------------------------------------------
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
