cj-zhukov commented on code in PR #21021:
URL: https://github.com/apache/datafusion/pull/21021#discussion_r3130874501
##########
datafusion/core/src/dataframe/mod.rs:
##########
@@ -410,21 +426,128 @@ impl DataFrame {
expr_list: impl IntoIterator<Item = impl Into<SelectExpr>>,
) -> Result<DataFrame> {
let expr_list: Vec<SelectExpr> =
- expr_list.into_iter().map(|e| e.into()).collect::<Vec<_>>();
+ expr_list.into_iter().map(|e| e.into()).collect();
+ // Extract expressions
let expressions = expr_list.iter().filter_map(|e| match e {
SelectExpr::Expression(expr) => Some(expr),
_ => None,
});
- let window_func_exprs = find_window_exprs(expressions);
- let plan = if window_func_exprs.is_empty() {
+ // Apply window functions first
+ let window_func_exprs = find_window_exprs(expressions.clone());
+
+ let mut plan = if window_func_exprs.is_empty() {
self.plan
} else {
LogicalPlanBuilder::window_plan(self.plan, window_func_exprs)?
};
- let project_plan =
LogicalPlanBuilder::from(plan).project(expr_list)?.build()?;
+ // Collect aggregate expressions
+ let aggr_exprs = find_aggregate_exprs(expressions.clone());
+
+ // Check for non-aggregate expressions
+ let has_non_aggregate_expr = expr_list.iter().any(|e| match e {
+ SelectExpr::Expression(expr) => {
+ find_aggregate_exprs(std::iter::once(expr)).is_empty()
+ }
+ SelectExpr::Wildcard(_) | SelectExpr::QualifiedWildcard(_, _) =>
true,
+ });
+
+ if has_non_aggregate_expr && !aggr_exprs.is_empty() {
+ return plan_err!(
+ "Column in SELECT must be in GROUP BY or an aggregate function"
+ );
+ }
+
+ // Fallback to projection
+ if matches!(plan, LogicalPlan::Aggregate(_))
+ || has_non_aggregate_expr
+ || aggr_exprs.is_empty()
+ {
Review Comment:
Good questions - I agree the conditions are not very clear as written. I’ll
try simplifying this logic and see if we can reduce it to just checking for
aggregate expressions, and only keep additional conditions if they’re strictly
necessary.
--
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]
