This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/main by this push:
new b19aa6538e fix(REE): check upfront if sorting empty array or 0 limit
(#10293)
b19aa6538e is described below
commit b19aa6538e7b3eac3f177f5dde4c3bc3615a1d1c
Author: Jeffrey Vo <[email protected]>
AuthorDate: Fri Jul 10 23:56:29 2026 +0900
fix(REE): check upfront if sorting empty array or 0 limit (#10293)
# 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.
-->
- Closes #10285
# Rationale for this change
<!--
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.
-->
See issue.
# What changes are included in this PR?
<!--
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.
-->
Check upfront for our public sort methods if we're sorting an empty
array or sorting with 0 limit, to immediately return an empty array.
# Are these changes 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)?
If this PR claims a performance improvement, please include evidence
such as benchmark results.
-->
Added tests.
# Are there any user-facing changes?
<!--
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 call them out.
-->
No.
---
arrow-ord/src/sort.rs | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/arrow-ord/src/sort.rs b/arrow-ord/src/sort.rs
index 55e517c54e..e64c1dac22 100644
--- a/arrow-ord/src/sort.rs
+++ b/arrow-ord/src/sort.rs
@@ -55,6 +55,9 @@ pub use arrow_schema::SortOptions;
/// assert_eq!(sorted_array.as_ref(), &Int32Array::from(vec![1, 2, 3, 4, 5]));
/// ```
pub fn sort(values: &dyn Array, options: Option<SortOptions>) ->
Result<ArrayRef, ArrowError> {
+ if values.is_empty() {
+ return Ok(new_empty_array(values.data_type()));
+ }
downcast_primitive_array!(
values => sort_native_type(values, options),
DataType::RunEndEncoded(_, _) => sort_run(values, options, None),
@@ -158,6 +161,9 @@ pub fn sort_limit(
options: Option<SortOptions>,
limit: Option<usize>,
) -> Result<ArrayRef, ArrowError> {
+ if values.is_empty() || limit == Some(0) {
+ return Ok(new_empty_array(values.data_type()));
+ }
if let DataType::RunEndEncoded(_, _) = values.data_type() {
return sort_run(values, options, limit);
}
@@ -273,6 +279,10 @@ pub fn sort_to_indices(
options: Option<SortOptions>,
limit: Option<usize>,
) -> Result<UInt32Array, ArrowError> {
+ if array.is_empty() || limit == Some(0) {
+ return Ok(UInt32Array::from(Vec::<u32>::new()));
+ }
+
let options = options.unwrap_or_default();
let (v, n) = partition_validity(array);
@@ -5407,4 +5417,25 @@ mod tests {
assert_eq!(sorted_strings, expected);
assert_eq!(sorted_strings.len(), limit);
}
+
+ #[test]
+ fn test_empty_run() {
+ let run = RunArray::try_new(
+ &Int16Array::from(vec![1, 2, 3]),
+ &Int32Array::from(vec![1, 5, 2]),
+ )
+ .unwrap();
+
+ let sorted = sort(&run.slice(1, 0), None).unwrap();
+ assert!(sorted.is_empty());
+ // ensure output run array upholds safety invariants
+ sorted.into_data().validate_full().unwrap();
+
+ let sorted = sort_limit(&run, None, Some(0)).unwrap();
+ assert!(sorted.is_empty());
+ sorted.into_data().validate_full().unwrap();
+
+ let indices = sort_to_indices(&run, None, Some(0)).unwrap();
+ assert!(indices.is_empty());
+ }
}
