cloud-fan commented on code in PR #52557:
URL: https://github.com/apache/spark/pull/52557#discussion_r2443583458
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala:
##########
@@ -755,10 +763,72 @@ class ParquetIOSuite extends QueryTest with ParquetTest
with SharedSparkSession
.add("_4", LongType, nullable = true),
nullable = true)
+ val expectedAnswer = if (!returnNullStructIfAllFieldsMissing) {
+ Row(Row(null, null)) :: Row(Row(null, null)) :: Row(null) :: Nil
+ } else {
+ Row(null) :: Row(null) :: Row(null) :: Nil
+ }
+
withParquetFile(data) { file =>
- checkAnswer(spark.read.schema(readSchema).parquet(file),
- Row(null) :: Row(null) :: Row(null) :: Nil
- )
+ val df = spark.read.schema(readSchema).parquet(file)
+ val scanNode = df.queryExecution.executedPlan.collectLeaves().head
+ VerifyNoAdditionalScanOutputExec(scanNode).execute().first()
Review Comment:
shall we use the existing `ColumnarToRowExec` and then verify the rows? But
I'm also fine with this custom physical plan.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
