Skip to content

Fix ScalarValue::List comparison when the compared lists have different lengths #15856

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

Merged
jayzhan211 merged 1 commit into from
Apr 25, 2025
Merged

Fix ScalarValue::List comparison when the compared lists have different lengths #15856

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
61 changes: 58 additions & 3 deletions datafusion/common/src/scalar/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -597,8 +597,12 @@ fn partial_cmp_list(arr1: &dyn Array, arr2: &dyn Array) -> Option<Ordering> {
let arr1 = first_array_for_list(arr1);
let arr2 = first_array_for_list(arr2);

let lt_res = arrow::compute::kernels::cmp::lt(&arr1, &arr2).ok()?;
let eq_res = arrow::compute::kernels::cmp::eq(&arr1, &arr2).ok()?;
let min_length = arr1.len().min(arr2.len());
let arr1_trimmed = arr1.slice(0, min_length);
let arr2_trimmed = arr2.slice(0, min_length);

let lt_res = arrow::compute::kernels::cmp::lt(&arr1_trimmed, &arr2_trimmed).ok()?;
let eq_res = arrow::compute::kernels::cmp::eq(&arr1_trimmed, &arr2_trimmed).ok()?;

for j in 0..lt_res.len() {
if lt_res.is_valid(j) && lt_res.value(j) {
Expand All @@ -609,7 +613,7 @@ fn partial_cmp_list(arr1: &dyn Array, arr2: &dyn Array) -> Option<Ordering> {
}
}

Some(Ordering::Equal)
Some(arr1.len().cmp(&arr2.len()))
}

fn partial_cmp_struct(s1: &Arc<StructArray>, s2: &Arc<StructArray>) -> Option<Ordering> {
Expand Down Expand Up @@ -4752,6 +4756,57 @@ mod tests {
])]),
));
assert_eq!(a.partial_cmp(&b), Some(Ordering::Less));

let a =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(1),
Some(2),
Some(3),
])]),
));
let b =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(2),
Some(3),
])]),
));
assert_eq!(a.partial_cmp(&b), Some(Ordering::Less));

let a =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(2),
Some(3),
Some(4),
])]),
));
let b =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(1),
Some(2),
])]),
));
assert_eq!(a.partial_cmp(&b), Some(Ordering::Greater));

let a =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(1),
Some(2),
Some(3),
])]),
));
let b =
ScalarValue::List(Arc::new(
ListArray::from_iter_primitive::<Int64Type, _, _>(vec![Some(vec![
Some(1),
Some(2),
])]),
));
assert_eq!(a.partial_cmp(&b), Some(Ordering::Greater));
}

#[test]
Expand Down