cloud-fan commented on code in PR #44162:
URL: https://github.com/apache/spark/pull/44162#discussion_r1414764985
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala:
##########
@@ -3469,6 +3470,52 @@ class Analyzer(override val catalogManager:
CatalogManager) extends RuleExecutor
}
}
+ /**
+ * Rewrite [[UnresolvedWithColumns]] into a [[Project]].
+ *
+ * `withColumns` can both update an existing columns and add new columns.
+ */
+ object RewriteWithColumns extends Rule[LogicalPlan] {
+ override def apply(plan: LogicalPlan): LogicalPlan =
plan.resolveOperatorsWithPruning(
+ _.containsPattern(UNRESOLVED_WITH_COLUMNS), ruleId) {
+ case UnresolvedWithColumns(projectList, child) if child.resolved =>
+ SchemaUtils.checkColumnNameDuplication(
+ projectList.map(_.name),
+ resolver)
+ val usedProjectListIndices = mutable.Set.empty[Int]
+ val outputProjectListBuilder = Seq.newBuilder[NamedExpression]
+ val lookup = {
Review Comment:
shall we simplify the code a bit? Basically we only need two list
```
val updatedProjectList = ...
val extraProjectList = ...
child.output.foreach { col =>
if (need to replace)
updatedProjectList += newExpr
else
updatedProjectList += col
extraProjectList += newExpr
}
Project(updatedProjectList ++ extraProjectList, ...)
```
--
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: reviews-unsubscr...@spark.apache.org
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
