fqaiser94 commented on a change in pull request #27066:
URL: https://github.com/apache/spark/pull/27066#discussion_r448588256
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala
##########
@@ -923,4 +923,501 @@ class ColumnExpressionSuite extends QueryTest with
SharedSparkSession {
val inSet = InSet(Literal("a"), Set("a", "b").map(UTF8String.fromString))
assert(inSet.sql === "('a' IN ('a', 'b'))")
}
+
+ def checkAnswerAndSchema(
+ df: => DataFrame,
+ expectedAnswer: Seq[Row],
+ expectedSchema: StructType): Unit = {
+
+ checkAnswer(df, expectedAnswer)
+ assert(df.schema == expectedSchema)
+ }
+
+ private lazy val structType = StructType(Seq(
+ StructField("a", IntegerType, nullable = false),
+ StructField("b", IntegerType, nullable = true),
+ StructField("c", IntegerType, nullable = false)))
+
+ private lazy val structLevel1: DataFrame = spark.createDataFrame(
+ sparkContext.parallelize(Row(Row(1, null, 3)) :: Nil),
+ StructType(Seq(StructField("a", structType, nullable = false))))
+
+ private lazy val nullStructLevel1: DataFrame = spark.createDataFrame(
+ sparkContext.parallelize(Row(null) :: Nil),
+ StructType(Seq(StructField("a", structType, nullable = true))))
+
+ private lazy val structLevel2: DataFrame = spark.createDataFrame(
+ sparkContext.parallelize(Row(Row(Row(1, null, 3))) :: Nil),
+ StructType(Seq(
+ StructField("a", StructType(Seq(
+ StructField("a", structType, nullable = false))),
+ nullable = false))))
+
+ private lazy val nullStructLevel2: DataFrame = spark.createDataFrame(
+ sparkContext.parallelize(Row(Row(null)) :: Nil),
+ StructType(Seq(
+ StructField("a", StructType(Seq(
+ StructField("a", structType, nullable = true))),
+ nullable = false))))
+
+ private lazy val structLevel3: DataFrame = spark.createDataFrame(
+ sparkContext.parallelize(Row(Row(Row(Row(1, null, 3)))) :: Nil),
+ StructType(Seq(
+ StructField("a", StructType(Seq(
+ StructField("a", StructType(Seq(
+ StructField("a", structType, nullable = false))),
+ nullable = false))),
+ nullable = false))))
+
+ test("withField should throw an exception if called on a non-StructType
column") {
+ intercept[AnalysisException] {
+ testData.withColumn("key", $"key".withField("a", lit(2)))
+ }.getMessage should include("struct argument should be struct type, got:
int")
+ }
+
+ test("withField should throw an exception if either fieldName or col
argument are null") {
+ an[java.lang.NullPointerException] should be thrownBy {
Review comment:
I was trying to stick to `Dataset.withColumn` behaviour which throws NPE
in similar scenarios but I agree with you so I've changed it to throw
`IllegalArgumentException` with a clear error message.
----------------------------------------------------------------
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]
