amaliujia commented on code in PR #38166:
URL: https://github.com/apache/spark/pull/38166#discussion_r992654735
##########
connector/connect/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala:
##########
@@ -81,6 +81,31 @@ class SparkConnectProtoSuite extends PlanTest with
SparkConnectPlanTest {
}
}
+ test("Test union, except, intersect") {
+ for (isAll <- Seq(true, false)) {
+ val connectPlan = {
+ import org.apache.spark.sql.connect.dsl.plans._
+ transform(connectTestRelation.except(connectTestRelation, isAll))
+ }
+ val sparkPlan = sparkTestRelation.except(sparkTestRelation, isAll)
+ comparePlans(connectPlan.analyze, sparkPlan.analyze, false)
+
+ val connectPlan2 = {
+ import org.apache.spark.sql.connect.dsl.plans._
+ transform(connectTestRelation.intersect(connectTestRelation, isAll))
+ }
+ val sparkPlan2 = sparkTestRelation.intersect(sparkTestRelation, isAll)
+ comparePlans(connectPlan2.analyze, sparkPlan2.analyze, false)
+ }
+
+ val connectPlan3 = {
+ import org.apache.spark.sql.connect.dsl.plans._
+ transform(connectTestRelation.union(connectTestRelation))
Review Comment:
I am fine on the proposal as long as it does not prevent the clients being
compatible with existing data frame API. Any extra functionality is fine.
For example we still support `df.union().distinct()` meaning
`DISTINCT(UNION)` to be, at least one of the options for `UNION(isAll=false)`
then I am good.
Thanks @cloud-fan for you summary. Let me change 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.
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]
