frankyin-factual commented on a change in pull request #28898:
URL: https://github.com/apache/spark/pull/28898#discussion_r454033847
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/SchemaPruningSuite.scala
##########
@@ -460,6 +460,67 @@ abstract class SchemaPruningSuite
checkAnswer(query4, Row(2, null) :: Row(2, 4) :: Nil)
}
+ testSchemaPruning("select nested field in window function") {
+ val windowSql =
+ """
+ |with contact_rank as (
+ | select row_number() over (partition by address order by id desc) as
rank,
+ | contacts.*
+ | from contacts
+ |)
+ |select name.first, rank from contact_rank
+ |where name.first = 'Jane' AND rank = 1
+ |""".stripMargin
+ val query = sql(windowSql)
+ checkScan(query, "struct<id:int,name:struct<first:string>,address:string>")
+ checkAnswer(query, Row("Jane", 1) :: Nil)
+ }
+
+ testSchemaPruning("select nested field in window function and then order
by") {
+ val windowSql =
+ """
+ |with contact_rank as (
+ | select row_number() over (partition by address order by id desc) as
rank,
+ | contacts.*
+ | from contacts
+ | order by name.last, name.first
+ |)
+ |select name.first, rank from contact_rank
+ |""".stripMargin
+ val query = sql(windowSql)
+ checkScan(query,
"struct<id:int,name:struct<first:string,last:string>,address:string>")
+ checkAnswer(query,
+ Row("Jane", 1) ::
+ Row("John", 1) ::
+ Row("Janet", 1) ::
+ Row("Jim", 1) :: Nil)
+ }
+
+ testSchemaPruning("select nested field in Sort") {
+ val query1 = sql("select name.first, name.last from contacts order by
name.first, name.last")
+ checkScan(query1, "struct<name:struct<first:string,last:string>>")
+ checkAnswer(query1,
+ Row("Jane", "Doe") ::
+ Row("Janet", "Jones") ::
+ Row("Jim", "Jones") ::
+ Row("John", "Doe") :: Nil)
+
+ // Create a repartitioned view because `SORT BY` is a local sort
+ sql("select * from
contacts").repartition(1).createOrReplaceTempView("tmp_contacts")
+ val sortBySql =
Review comment:
Updated. Thanks.
----------------------------------------------------------------
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]
