maropu commented on a change in pull request #28560:
URL: https://github.com/apache/spark/pull/28560#discussion_r428666366
##########
File path:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasingSuite.scala
##########
@@ -341,6 +341,78 @@ class NestedColumnAliasingSuite extends SchemaPruningTest {
.analyze
comparePlans(optimized, expected)
}
+
+ test("Nested field pruning for Aggregate") {
+ val query1 =
contact.groupBy($"id")(first($"name.first").as("first")).analyze
+ val optimized1 = Optimize.execute(query1)
+ val aliases1 = collectGeneratedAliases(optimized1)
+
+ val expected1 = contact
+ .select($"id", 'name.getField("first").as(aliases1(0)))
+ .groupBy($"id")(first($"${aliases1(0)}").as("first")).analyze
+ comparePlans(optimized1, expected1)
+
+ val query2 =
contact.groupBy($"name.last")(first($"name.first").as("first")).analyze
+ val optimized2 = Optimize.execute(query2)
+ val aliases2 = collectGeneratedAliases(optimized2)
+
+ val expected2 = contact
+ .select('name.getField("last").as(aliases2(0)),
'name.getField("first").as(aliases2(1)))
+ .groupBy($"${aliases2(0)}")(first($"${aliases2(1)}").as("first")).analyze
+ comparePlans(optimized2, expected2)
+
+ val query3 = contact.groupBy($"id")(first($"name"),
first($"name.first").as("first")).analyze
+ val optimized3 = Optimize.execute(query3)
+ val expected3 = contact.select($"id", $"name")
+ .groupBy($"id")(first($"name"), first($"name.first").as("first")).analyze
+ comparePlans(optimized3, expected3)
+ }
+
+ test("Nested field pruning for Expand") {
+ val query1 = Expand(
+ Seq(
+ Seq($"name.first", $"name.middle"),
+ Seq(ConcatWs(Seq($"name.first", $"name.middle")),
+ ConcatWs(Seq($"name.middle", $"name.first")))
+ ),
+ Seq('a.string, 'b.string),
+ contact
Review comment:
ditto; https://github.com/apache/spark/pull/28560#discussion_r428665197
----------------------------------------------------------------
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]
