HyukjinKwon commented on code in PR #38276:
URL: https://github.com/apache/spark/pull/38276#discussion_r1002828551
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -91,6 +93,37 @@ class SparkConnectPlanner(plan: proto.Relation, session:
SparkSession) {
transformRelation(rel.getInput))
}
+ private def transformDeduplicate(rel: proto.Deduplicate): LogicalPlan = {
+ if (!rel.hasInput) {
+ throw InvalidPlanInput("Deduplicate needs a plan input")
+ }
+ if (rel.getAllColumnsAsKeys && rel.getColumnNamesCount > 0) {
+ throw InvalidPlanInput("Cannot deduplicate on both all columns and a
subset of columns")
+ }
+ if (!rel.getAllColumnsAsKeys && rel.getColumnNamesCount == 0) {
Review Comment:
Why do we need `getAllColumnsAsKeys`? Seems like we can just tell when the
columns are not set.
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -91,6 +93,37 @@ class SparkConnectPlanner(plan: proto.Relation, session:
SparkSession) {
transformRelation(rel.getInput))
}
+ private def transformDeduplicate(rel: proto.Deduplicate): LogicalPlan = {
+ if (!rel.hasInput) {
+ throw InvalidPlanInput("Deduplicate needs a plan input")
+ }
+ if (rel.getAllColumnsAsKeys && rel.getColumnNamesCount > 0) {
+ throw InvalidPlanInput("Cannot deduplicate on both all columns and a
subset of columns")
+ }
+ if (!rel.getAllColumnsAsKeys && rel.getColumnNamesCount == 0) {
Review Comment:
and this is not matched with the logical 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]
