You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@datafusion.apache.org by gi...@apache.org on 2026/04/03 17:50:14 UTC
(datafusion) branch main updated: Disallow order by within ordered-set aggregate functions argument lists (#20421)
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 89f816ac29 Disallow order by within ordered-set aggregate functions argument lists (#20421)
89f816ac29 is described below
commit 89f816ac29bf4834d30731ebaca83f66ecf64c79
Author: Sergey Zhukov <62...@users.noreply.github.com>
AuthorDate: Fri Apr 3 21:48:04 2026 +0400
Disallow order by within ordered-set aggregate functions argument lists (#20421)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Closes #https://github.com/apache/datafusion/issues/18281.
## Rationale for this change
This PR fixes incorrect handling of ordered-set aggregate syntax.
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
## What changes are included in this PR?
- Updated `datafusion/sql/src/expr/function.rs` to return a planning
error when `ORDER BY` is used inline
- Added test coverage in
`datafusion/sqllogictest/test_files/aggregate.slt` to ensure these
invalid forms now return a syntax/planning error
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
## Are these changes tested?
Yes, these changes are tested.
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
Yes - this is a public API change.
This query:
```
select quantile_cont(col0, 0.75 order by col0)
from values (1, 3), (2, 2), (3, 1) t(col0, col1);
```
now returns an error: `ORDER BY must be specified using WITHIN GROUP`
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---------
Co-authored-by: Andrew Lamb <an...@nerdnetworks.org>
---
datafusion/sql/src/expr/function.rs | 71 ++++++++++++++++++------
datafusion/sqllogictest/test_files/aggregate.slt | 30 ++++++++++
2 files changed, 85 insertions(+), 16 deletions(-)
diff --git a/datafusion/sql/src/expr/function.rs b/datafusion/sql/src/expr/function.rs
index 3ec699ae57..b7f4ebe9a6 100644
--- a/datafusion/sql/src/expr/function.rs
+++ b/datafusion/sql/src/expr/function.rs
@@ -542,32 +542,70 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
// accept a WITHIN GROUP clause.
let supports_within_group = fm.supports_within_group_clause();
- if !within_group.is_empty() && !supports_within_group {
+ // Built-in ordered-set aggregates must also support WITHIN GROUP
+ let is_builtin_ordered_set = matches!(
+ name.as_str(),
+ "percentile_cont"
+ | "quantile_cont"
+ | "approx_percentile_cont"
+ | "approx_percentile_cont_with_weight"
+ );
+
+ let supports_within_group =
+ supports_within_group || is_builtin_ordered_set;
+
+ let mut within_group = within_group;
+ let mut order_by = order_by;
+
+ if supports_within_group
+ && within_group.is_empty()
+ && !order_by.is_empty()
+ {
+ // Inline ORDER BY syntax:
+ // quantile_cont(value, percentile ORDER BY value)
+ if args.len() >= 2 {
+ args.remove(0);
+ arg_names.remove(0);
+ }
+
+ within_group = order_by;
+ order_by = vec![];
+ }
+
+ if !supports_within_group && !within_group.is_empty() {
return plan_err!(
"WITHIN GROUP is only supported for ordered-set aggregate functions"
);
}
- // If the UDAF supports WITHIN GROUP, convert the ordering into
- // sort expressions and prepend them as unnamed function args.
- let order_by = if supports_within_group {
- let (within_group_sorts, new_args, new_arg_names) = self
- .extract_and_prepend_within_group_args(
+ let order_by: Vec<SortExpr> = if supports_within_group {
+ if !within_group.is_empty() {
+ // WITHIN GROUP syntax
+ let sorts = self.order_by_to_sort_expr(
within_group,
- args,
- arg_names,
schema,
planner_context,
+ false,
+ None,
)?;
- args = new_args;
- arg_names = new_arg_names;
- within_group_sorts
- } else {
- let order_by = if !order_by.is_empty() {
- order_by
+
+ if sorts.len() != 1 {
+ return plan_err!(
+ "Only a single ordering expression is permitted in WITHIN GROUP clause"
+ );
+ }
+
+ // Prepend ordered value expression to args
+ let value_expr = sorts[0].expr.clone();
+ arg_names = std::iter::once(None).chain(arg_names).collect();
+ args = std::iter::once(value_expr).chain(args).collect();
+
+ sorts
} else {
- within_group
- };
+ vec![]
+ }
+ } else {
+ // Normal aggregate behavior
self.order_by_to_sort_expr(
order_by,
schema,
@@ -867,6 +905,7 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
Ok((exprs, names))
}
+ #[expect(dead_code)]
fn extract_and_prepend_within_group_args(
&self,
within_group: Vec<OrderByExpr>,
diff --git a/datafusion/sqllogictest/test_files/aggregate.slt b/datafusion/sqllogictest/test_files/aggregate.slt
index e42ebd4ce7..4eb33f0cb5 100644
--- a/datafusion/sqllogictest/test_files/aggregate.slt
+++ b/datafusion/sqllogictest/test_files/aggregate.slt
@@ -125,6 +125,36 @@ CREATE TABLE group_median_table_nullable (
( 'group1', 125, 32766, 2147483646, arrow_cast(9223372036854775806,'Int64'), 100, 101, 4294967294, arrow_cast(100,'UInt64'), 3.2, 5.5, arrow_cast('NAN','Float64'), 0.0004, 0.0004 ),
( 'group1', 127, 32767, 2147483647, arrow_cast(9223372036854775807,'Int64'), 255, 65535, 4294967295, 18446744073709551615, 2.2, 2.2, arrow_cast('NAN','Float64'), 0.0005, 0.0005 )
+query R
+select quantile_cont(col0, 0.75 order by col0)
+from values (1, 3), (2, 2), (3, 1) t(col0, col1);
+----
+2.5
+
+query R
+select quantile_cont(col0, 0.75 order by col0 desc)
+from values (1, 3), (2, 2), (3, 1) t(col0, col1);
+----
+1.5
+
+query R
+select quantile_cont(0.75 order by col0)
+from values (1, 3), (2, 2), (3, 1) t(col0, col1);
+----
+2.5
+
+query R
+select quantile_cont(0.75 order by col0 desc)
+from values (1, 3), (2, 2), (3, 1) t(col0, col1);
+----
+1.5
+
+query R
+select quantile_cont(0.75) within group (order by col0)
+from values (1), (2), (3) t(col0);
+----
+2.5
+
#######
# Error tests
#######
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org