Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/21745#discussion_r202242420
--- Diff: sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
---
@@ -2387,4 +2387,25 @@ class DataFrameSuite extends QueryTest with
SharedSQLContext {
val mapWithBinaryKey = map(lit(Array[Byte](1.toByte)), lit(1))
checkAnswer(spark.range(1).select(mapWithBinaryKey.getItem(Array[Byte](1.toByte))),
Row(1))
}
+
+ test("SPARK-24781: Using a reference from Dataset in Filter/Sort might
not work") {
+ val df = Seq(("test1", 0), ("test2", 1)).toDF("name", "id")
+ val filter1 = df.select(df("name")).filter(df("id") === 0)
+ val filter2 = df.select(col("name")).filter(col("id") === 0)
+ checkAnswer(filter1, filter2.collect())
+
+ val sort1 = df.select(df("name")).orderBy(df("id"))
+ val sort2 = df.select(col("name")).orderBy(col("id"))
+ checkAnswer(sort1, sort2.collect())
+
+ withSQLConf(SQLConf.DATAFRAME_RETAIN_GROUP_COLUMNS.key -> "false") {
--- End diff --
Will update it in next commit.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
