cloud-fan commented on a change in pull request #26593: [SPARK-29890][SQL]
DataFrameNaFunctions.fill should handle duplicate columns
URL: https://github.com/apache/spark/pull/26593#discussion_r349552595
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameNaFunctionsSuite.scala
##########
@@ -266,6 +267,32 @@ class DataFrameNaFunctionsSuite extends QueryTest with
SharedSparkSession {
assert(message.contains("Reference 'f2' is ambiguous"))
}
+ test("fill with col(*)") {
+ val df = createDF()
+ // If columns are specified with "*", they are ignored.
+ checkAnswer(df.na.fill("new name", Seq("*")), df.collect())
+ }
+
+ test("fill with nested columns") {
+ val schema = new StructType()
+ .add("c1", new StructType()
+ .add("c1-1", StringType)
+ .add("c1-2", StringType))
+
+ val data = Seq(
+ Row(Row(null, "a2")),
+ Row(Row("b1", "b2")))
+
+ val df = spark.createDataFrame(
+ spark.sparkContext.parallelize(data), schema)
+
+ checkAnswer(df.select("c1.c1-1"),
+ Row(null) :: Row("b1") :: Nil)
+
+ // Nested columns are ignored for fill().
+ checkAnswer(df.na.fill("a1", Seq("c1.c1-1")), data)
Review comment:
We can expose the bug if the data is
```
val data = Seq(
Row(Row(null, "a2")),
Row(Row("b1", "b2")),
Row(null))
```
----------------------------------------------------------------
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]
