gengliangwang commented on code in PR #39040:
URL: https://github.com/apache/spark/pull/39040#discussion_r1050336921
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveLateralColumnAliasReference.scala:
##########
@@ -129,6 +163,45 @@ object ResolveLateralColumnAliasReference extends
Rule[LogicalPlan] {
child = Project(innerProjectList.toSeq, child)
)
}
+
+ case agg @ Aggregate(groupingExpressions, aggregateExpressions, _) if
agg.resolved
+ &&
aggregateExpressions.exists(_.containsPattern(LATERAL_COLUMN_ALIAS_REFERENCE))
=>
+
+ val newAggExprs = collection.mutable.Set.empty[NamedExpression]
+ val expressionMap =
collection.mutable.LinkedHashMap.empty[Expression, NamedExpression]
+ val projectExprs = aggregateExpressions.map { exp =>
+ exp.transformDown {
+ case aggExpr: AggregateExpression =>
+ // Doesn't support referencing a lateral alias in aggregate
function
+ if (aggExpr.containsPattern(LATERAL_COLUMN_ALIAS_REFERENCE)) {
+ aggExpr.collectFirst {
+ case lcaRef: LateralColumnAliasReference =>
+ throw
QueryCompilationErrors.lateralColumnAliasInAggFuncUnsupportedError(
+ lcaRef.nameParts, aggExpr)
+ }
+ }
+ val ne = expressionMap.getOrElseUpdate(aggExpr.canonicalized,
assignAlias(aggExpr))
+ newAggExprs += ne
Review Comment:
So for the following query
```
create table table_1(a int, b int, c int);
select a as x, x+1, sum(b)+sum(c) from table_1 group by a;
```
Do we need to extract `sum(b)` and `sum(c)` and put them separately in the
new aggregation expressions?
--
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]
