[branch-52] Fix duplicate group keys after hash aggregation spill (#20724) (#20858) (#20917)

- Part of #20855
- Closes #20724 on branch-52

This PR:
- Backports #20858 from
@gboucher90 to the branch-52 line

Co-authored-by: gboucher90 <gboucher90@users.noreply.github.com>

Author: alamb

datafusion/physical-plan/src/aggregates/row_hash.rs

@@ -1233,6 +1233,18 @@ impl GroupedHashAggregateStream {
             // on the grouping columns.
             self.group_ordering = GroupOrdering::Full(GroupOrderingFull::new());
 
+            // Recreate group_values to use streaming mode (GroupValuesColumn<true>
+            // with scalarized_intern) which preserves input row order, as required
+            // by GroupOrderingFull. This is only needed for multi-column group by,
+            // since single-column uses GroupValuesPrimitive which is always safe.
+            let group_schema = self
+                .spill_state
+                .merging_group_by
+                .group_schema(&self.spill_state.spill_schema)?;
+            if group_schema.fields().len() > 1 {
+                self.group_values = new_group_values(group_schema, &self.group_ordering)?;
+            }
+
             // Use `OutOfMemoryMode::ReportError` from this point on
             // to ensure we don't spill the spilled data to disk again.
             self.oom_mode = OutOfMemoryMode::ReportError;