cloud-fan commented on a change in pull request #32448:
URL: https://github.com/apache/spark/pull/32448#discussion_r632017258
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameSetOperationsSuite.scala
##########
@@ -707,32 +710,63 @@ class DataFrameSetOperationsSuite extends QueryTest with
SharedSparkSession {
val df2 = Seq((1, UnionClass1c(1, 2L, UnionClass4(2, 3L)))).toDF("id",
"a")
var unionDf = df1.unionByName(df2, true)
- checkAnswer(unionDf,
- Row(0, Row(0, 1, Row(null, 1, null, "2"))) ::
- Row(1, Row(1, 2, Row(2, null, 3L, null))) :: Nil)
assert(unionDf.schema.toDDL ==
"`id` INT,`a` STRUCT<`a`: INT, `b`: BIGINT, " +
- "`nested`: STRUCT<`A`: INT, `a`: INT, `b`: BIGINT, `c`: STRING>>")
+ "`nested`: STRUCT<`a`: INT, `c`: STRING, `A`: INT, `b`: BIGINT>>")
+ checkAnswer(unionDf,
+ Row(0, Row(0, 1, Row(1, "2", null, null))) ::
+ Row(1, Row(1, 2, Row(null, null, 2, 3L))) :: Nil)
unionDf = df2.unionByName(df1, true)
- checkAnswer(unionDf,
- Row(1, Row(1, 2, Row(2, null, 3L, null))) ::
- Row(0, Row(0, 1, Row(null, 1, null, "2"))) :: Nil)
assert(unionDf.schema.toDDL ==
"`id` INT,`a` STRUCT<`a`: INT, `b`: BIGINT, " +
- "`nested`: STRUCT<`A`: INT, `a`: INT, `b`: BIGINT, `c`: STRING>>")
+ "`nested`: STRUCT<`A`: INT, `b`: BIGINT, `a`: INT, `c`: STRING>>")
+ checkAnswer(unionDf,
+ Row(1, Row(1, 2, Row(2, 3L, null, null))) ::
+ Row(0, Row(0, 1, Row(null, null, 1, "2"))) :: Nil)
val df3 = Seq((2, UnionClass1b(2, 3L, UnionClass3(4, 5L)))).toDF("id",
"a")
unionDf = df2.unionByName(df3, true)
- checkAnswer(unionDf,
- Row(1, Row(1, 2, Row(2, null, 3L))) ::
- Row(2, Row(2, 3, Row(null, 4, 5L))) :: Nil)
assert(unionDf.schema.toDDL ==
"`id` INT,`a` STRUCT<`a`: INT, `b`: BIGINT, " +
- "`nested`: STRUCT<`A`: INT, `a`: INT, `b`: BIGINT>>")
+ "`nested`: STRUCT<`A`: INT, `b`: BIGINT, `a`: INT>>")
+ checkAnswer(unionDf,
+ Row(1, Row(1, 2, Row(2, 3L, null))) ::
+ Row(2, Row(2, 3, Row(null, 5L, 4))) :: Nil)
}
}
+ test("SPARK-32376: Make unionByName null-filling behavior work with struct
columns" +
+ " - case-insensitive cases") {
Review comment:
From PR description
```
Certain nested structs would cause unionByName with null filling to error
out due to
part of the logic for rewriting the expression tree to sort the structs.
```
Does this test fail before this PR?
--
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
