Skip to content

fix: reject groups accumulator for bit_xor(DISTINCT) #24989

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jackylee-ch wants to merge 2 commits into
base: main
Choose a base branch
from
+32 −2
Open

fix: reject groups accumulator for bit_xor(DISTINCT) #24989

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c779379
fix: reject groups accumulator for distinct bitwise aggregates
jackylee-ch Sep 6, 2026
4230781
fix: limit the groups accumulator rejection to bit_xor(DISTINCT)
jackylee-ch Sep 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions datafusion/functions-aggregate/src/bit_and_or_xor.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,8 +290,9 @@ impl AggregateUDFImpl for BitwiseOperation {
}
}

fn groups_accumulator_supported(&self, _args: AccumulatorArgs) -> bool {
true
fn groups_accumulator_supported(&self, args: AccumulatorArgs) -> bool {
// DISTINCT only changes the result of XOR; AND and OR are idempotent
!(args.is_distinct && self.operation == BitwiseOperationType::Xor)
}

fn create_groups_accumulator(
Expand Down
29 changes: 29 additions & 0 deletions datafusion/sqllogictest/test_files/aggregate.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5123,6 +5123,35 @@ ORDER BY tag
33 11 NULL 33 11 NULL 33 11 NULL B


# bit_xor(DISTINCT) with GROUP BY must not use the non-distinct groups
# accumulator: for tag A, 5 ^ 5 ^ 9 = 9 but 5 ^ 9 = 12. AND and OR are
# idempotent, so they keep the groups accumulator.
statement ok
create table bit_distinct (c SMALLINT, tag varchar) as values
(5, 'A'), (5, 'A'), (9, 'A'), (33, 'B'), (33, 'B');

query IIT
SELECT bit_xor(DISTINCT c), count(c), tag FROM bit_distinct GROUP BY tag ORDER BY tag;
----
12 3 A
33 2 B

query IT
SELECT bit_xor(DISTINCT c) FILTER (WHERE c > 4), tag FROM bit_distinct GROUP BY tag ORDER BY tag;
----
12 A
33 B

query IIIT
SELECT bit_and(DISTINCT c), bit_or(DISTINCT c), count(c), tag FROM bit_distinct GROUP BY tag ORDER BY tag;
----
1 13 3 A
33 33 2 B

statement ok
drop table bit_distinct;


# bit_and_i32
statement ok
create table t (c int) as values (4), (7), (15);
Expand Down
Loading