Kimahriman commented on a change in pull request #32338:
URL: https://github.com/apache/spark/pull/32338#discussion_r619881917
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala
##########
@@ -1686,6 +1686,61 @@ class ColumnExpressionSuite extends QueryTest with
SharedSparkSession {
StructType(Seq(StructField("a", IntegerType, nullable = true))))
}
+ test("SPARK-35213: chained withField operations should have correct schema
for new columns") {
+ val df = spark.createDataFrame(
+ sparkContext.parallelize(Row(null) :: Nil),
+ StructType(Seq(StructField("data", NullType))))
+
+ checkAnswer(
+ df.withColumn("data", struct()
+ .withField("a", struct())
+ .withField("b", struct())
+ .withField("a.aa", lit("aa1"))
+ .withField("b.ba", lit("ba1"))
+ .withField("a.ab", lit("ab1"))),
+ Row(Row(Row("aa1", "ab1"), Row("ba1"))) :: Nil,
+ StructType(Seq(
+ StructField("data", StructType(Seq(
+ StructField("a", StructType(Seq(
+ StructField("aa", StringType, nullable = false),
+ StructField("ab", StringType, nullable = false)
+ )), nullable = false),
+ StructField("b", StructType(Seq(
+ StructField("ba", StringType, nullable = false)
+ )), nullable = false)
+ )), nullable = false)
Review comment:
Yeah it's kinda verbose, but I feel like for complicated things the
objects are easier to understand than the DDL strings, especially with structs.
Wasn't sure if there was an easier way to not have to explicitly mark
everything as not nullable at least
--
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]
