maropu commented on a change in pull request #28266:
URL: https://github.com/apache/spark/pull/28266#discussion_r411061846
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameNaFunctionsSuite.scala
##########
@@ -275,33 +285,35 @@ class DataFrameNaFunctionsSuite extends QueryTest with
SharedSparkSession {
assert(message.contains("Reference 'f2' is ambiguous"))
}
- test("fill/drop with col(*)") {
+ test("fill with col(*)") {
val df = createDF()
// If columns are specified with "*", they are ignored.
checkAnswer(df.na.fill("new name", Seq("*")), df.collect())
- checkAnswer(df.na.drop("any", Seq("*")), df.collect())
}
- test("fill/drop with nested columns") {
- val schema = new StructType()
- .add("c1", new StructType()
- .add("c1-1", StringType)
- .add("c1-2", StringType))
+ test("drop with col(*)") {
+ val df = createDF()
+ val exception = intercept[AnalysisException] {
+ df.na.drop("any", Seq("*"))
+ }
+ assert(exception.getMessage.contains("Cannot resolve column name \"*\""))
+ }
- val data = Seq(
- Row(Row(null, "a2")),
- Row(Row("b1", "b2")),
- Row(null))
+ test("fill with nested columns") {
+ val df = createDFWithNestedColumns
- val df = spark.createDataFrame(
- spark.sparkContext.parallelize(data), schema)
+ // Nested columns are ignored for fill().
+ checkAnswer(df.na.fill("a1", Seq("c1.c1-1")), df)
+ }
- checkAnswer(df.select("c1.c1-1"),
- Row(null) :: Row("b1") :: Row(null) :: Nil)
+ test("drop with nested columns") {
Review comment:
nvm, a bit late...
----------------------------------------------------------------
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]
