This is an automated email from the ASF dual-hosted git repository.
jeffreyvo 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 198846dcde Add RunEndEncoded array comparator (#9368)
198846dcde is described below
commit 198846dcdea2fbea74f103580258375ff938352b
Author: Yan Tingwang <[email protected]>
AuthorDate: Tue Feb 10 09:06:57 2026 +0800
Add RunEndEncoded array comparator (#9368)
# 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 #9360 .
# 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.
-->
# 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.
-->
# 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)?
-->
YES
# 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.
-->
make_comparator now accepts RunEndEncoded arrays
---------
Co-authored-by: Jeffrey Vo <[email protected]>
---
arrow-ord/src/ord.rs | 229 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 229 insertions(+)
diff --git a/arrow-ord/src/ord.rs b/arrow-ord/src/ord.rs
index f120ae6e8d..5951a58788 100644
--- a/arrow-ord/src/ord.rs
+++ b/arrow-ord/src/ord.rs
@@ -24,6 +24,28 @@ use arrow_buffer::{ArrowNativeType, NullBuffer};
use arrow_schema::{ArrowError, DataType, SortOptions};
use std::{cmp::Ordering, collections::HashMap};
+fn compare_run_end_encoded<R: RunEndIndexType>(
+ left: &dyn Array,
+ right: &dyn Array,
+ opts: SortOptions,
+) -> Result<DynComparator, ArrowError> {
+ let left = left.as_run::<R>();
+ let right = right.as_run::<R>();
+
+ let c_opts = child_opts(opts);
+ let cmp = make_comparator(left.values().as_ref(), right.values().as_ref(),
c_opts)?;
+
+ let l_run_ends = left.run_ends().clone();
+ let r_run_ends = right.run_ends().clone();
+
+ let f = compare(left, right, opts, move |i, j| {
+ let l_physical = l_run_ends.get_physical_index(i);
+ let r_physical = r_run_ends.get_physical_index(j);
+ cmp(l_physical, r_physical)
+ });
+ Ok(f)
+}
+
/// Compare the values at two arbitrary indices in two arrays.
pub type DynComparator = Box<dyn Fn(usize, usize) -> Ordering + Send + Sync>;
@@ -521,6 +543,21 @@ pub fn make_comparator(
_ => unreachable!()
}
},
+ (RunEndEncoded(l_run_ends, _), RunEndEncoded(r_run_ends, _)) => {
+ macro_rules! run_end_helper {
+ ($t:ty, $left:expr, $right:expr, $opts:expr) => {
+ compare_run_end_encoded::<$t>($left, $right, $opts)
+ };
+ }
+ downcast_run_end_index! {
+ l_run_ends.data_type(), r_run_ends.data_type() =>
(run_end_helper, left, right, opts),
+ _ => Err(ArrowError::InvalidArgumentError(format!(
+ "Cannot compare RunEndEncoded arrays with different run
ends types: left={:?}, right={:?}",
+ l_run_ends.data_type(),
+ r_run_ends.data_type()
+ )))
+ }
+ },
(Map(_, _), Map(_, _)) => compare_map(left, right, opts),
(Null, Null) => Ok(Box::new(|_, _| Ordering::Equal)),
(Union(_, _), Union(_, _)) => compare_union(left, right, opts),
@@ -1690,4 +1727,196 @@ mod tests {
assert_eq!(cmp(0, 1), Ordering::Equal);
assert_eq!(cmp(2, 0), Ordering::Equal);
}
+
+ #[test]
+ fn test_run_end_encoded_int32() {
+ // Create RunEndEncoded arrays:
+ // array1: [1, 1, 2, 2, 2, 3]
+ // run_ends1: [2, 5, 6], values1: [1, 2, 3]
+ let run_ends1 = Int32Array::from(vec![2, 5, 6]);
+ let values1 = Int32Array::from(vec![1, 2, 3]);
+ let array1 = RunArray::<Int32Type>::try_new(&run_ends1,
&values1).unwrap();
+
+ // array2: [1, 2, 2, 3, 3, 3]
+ // run_ends2: [1, 3, 6], values2: [1, 2, 3]
+ let run_ends2 = Int32Array::from(vec![1, 3, 6]);
+ let values2 = Int32Array::from(vec![1, 2, 3]);
+ let array2 = RunArray::<Int32Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let cmp = make_comparator(&array1, &array2,
SortOptions::default()).unwrap();
+
+ // array1[0] = 1, array2[0] = 1
+ assert_eq!(cmp(0, 0), Ordering::Equal);
+ // array1[0] = 1, array2[1] = 2
+ assert_eq!(cmp(0, 1), Ordering::Less);
+ // array1[2] = 2, array2[1] = 2
+ assert_eq!(cmp(2, 1), Ordering::Equal);
+ // array1[5] = 3, array2[5] = 3
+ assert_eq!(cmp(5, 5), Ordering::Equal);
+ // array1[1] = 1, array2[2] = 2
+ assert_eq!(cmp(1, 2), Ordering::Less);
+ // array1[4] = 2, array2[4] = 3
+ assert_eq!(cmp(4, 4), Ordering::Less);
+ }
+
+ #[test]
+ fn test_run_end_encoded_with_nulls() {
+ // Create RunEndEncoded arrays with nulls:
+ // array1: [1, 1, null, null, 2]
+ // run_ends1: [2, 4, 5], values1: [1, null, 2]
+ let run_ends1 = Int32Array::from(vec![2, 4, 5]);
+ let values1 = Int32Array::from(vec![Some(1), None, Some(2)]);
+ let array1 = RunArray::<Int32Type>::try_new(&run_ends1,
&values1).unwrap();
+
+ // array2: [null, 1, 1, 2, null]
+ // run_ends2: [1, 3, 4, 5], values2: [null, 1, 2, null]
+ let run_ends2 = Int32Array::from(vec![1, 3, 4, 5]);
+ let values2 = Int32Array::from(vec![None, Some(1), Some(2), None]);
+ let array2 = RunArray::<Int32Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let opts = SortOptions::default();
+ let cmp = make_comparator(&array1, &array2, opts).unwrap();
+
+ // array1[0] = 1, array2[1] = 1
+ assert_eq!(cmp(0, 1), Ordering::Equal);
+ // array1[2] = null, array2[0] = null
+ assert_eq!(cmp(2, 0), Ordering::Equal);
+ // array1[0] = 1, array2[0] = null (nulls first by default)
+ assert_eq!(cmp(0, 0), Ordering::Greater);
+ // array1[2] = null, array2[1] = 1
+ assert_eq!(cmp(2, 1), Ordering::Less);
+ }
+
+ #[test]
+ fn test_run_end_encoded_int16() {
+ // Test with Int16 run ends
+ let run_ends1 = Int16Array::from(vec![3_i16, 5, 6]);
+ let values1 = StringArray::from(vec!["a", "b", "c"]);
+ let array1 = RunArray::<Int16Type>::try_new(&run_ends1,
&values1).unwrap();
+
+ let run_ends2 = Int16Array::from(vec![2_i16, 4, 6]);
+ let values2 = StringArray::from(vec!["a", "b", "c"]);
+ let array2 = RunArray::<Int16Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let cmp = make_comparator(&array1, &array2,
SortOptions::default()).unwrap();
+
+ // array1: [a, a, a, b, b, c]
+ // array2: [a, a, b, b, c, c]
+ assert_eq!(cmp(0, 0), Ordering::Equal); // a vs a
+ assert_eq!(cmp(2, 2), Ordering::Less); // a vs b
+ assert_eq!(cmp(3, 2), Ordering::Equal); // b vs b
+ assert_eq!(cmp(5, 4), Ordering::Equal); // c vs c
+ }
+
+ #[test]
+ fn test_run_end_encoded_int64() {
+ // Test with Int64 run ends
+ let run_ends1 = Int64Array::from(vec![2_i64, 4, 6]);
+ let values1 = Int64Array::from(vec![10_i64, 20, 30]);
+ let array1 = RunArray::<Int64Type>::try_new(&run_ends1,
&values1).unwrap();
+
+ let run_ends2 = Int64Array::from(vec![3_i64, 5, 6]);
+ let values2 = Int64Array::from(vec![10_i64, 20, 30]);
+ let array2 = RunArray::<Int64Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let cmp = make_comparator(&array1, &array2,
SortOptions::default()).unwrap();
+
+ // array1: [10, 10, 20, 20, 30, 30]
+ // array2: [10, 10, 10, 20, 20, 30]
+ assert_eq!(cmp(0, 0), Ordering::Equal); // 10 vs 10
+ assert_eq!(cmp(1, 2), Ordering::Equal); // 10 vs 10
+ assert_eq!(cmp(2, 3), Ordering::Equal); // 20 vs 20
+ assert_eq!(cmp(4, 4), Ordering::Greater); // 30 vs 20
+ }
+
+ #[test]
+ fn test_run_end_encoded_sliced() {
+ // Create a RunEndEncoded array and slice it:
+ // original: [1, 1, 2, 2, 2, 3, 3, 4]
+ // run_ends: [2, 5, 7, 8], values: [1, 2, 3, 4]
+ let run_ends = Int32Array::from(vec![2, 5, 7, 8]);
+ let values = Int32Array::from(vec![1, 2, 3, 4]);
+ let array = RunArray::<Int32Type>::try_new(&run_ends,
&values).unwrap();
+
+ // slice1 = array[1..5] => [1, 2, 2, 2]
+ let slice1 = array.slice(1, 4);
+ // slice2 = array[3..7] => [2, 2, 3, 3]
+ let slice2 = array.slice(3, 4);
+
+ let cmp = make_comparator(&slice1, &slice2,
SortOptions::default()).unwrap();
+
+ // slice1[0]=1, slice2[0]=2
+ assert_eq!(cmp(0, 0), Ordering::Less);
+ // slice1[1]=2, slice2[0]=2
+ assert_eq!(cmp(1, 0), Ordering::Equal);
+ // slice1[3]=2, slice2[2]=3
+ assert_eq!(cmp(3, 2), Ordering::Less);
+ // slice1[1]=2, slice2[3]=3
+ assert_eq!(cmp(1, 3), Ordering::Less);
+
+ // Compare a sliced array with an unsliced array
+ let run_ends2 = Int32Array::from(vec![2, 4]);
+ let values2 = Int32Array::from(vec![1, 2]);
+ let array2 = RunArray::<Int32Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let cmp = make_comparator(&slice1, &array2,
SortOptions::default()).unwrap();
+
+ // slice1[0]=1, array2[0]=1
+ assert_eq!(cmp(0, 0), Ordering::Equal);
+ // slice1[1]=2, array2[1]=1
+ assert_eq!(cmp(1, 1), Ordering::Greater);
+ // slice1[3]=2, array2[3]=2
+ assert_eq!(cmp(3, 3), Ordering::Equal);
+ }
+
+ #[test]
+ fn test_run_end_encoded_sliced_with_nulls() {
+ // Create a RunEndEncoded array with nulls:
+ // original: [1, 1, null, null, 2, 2, null, 3]
+ // run_ends: [2, 4, 6, 7, 8], values: [1, null, 2, null, 3]
+ let run_ends = Int32Array::from(vec![2, 4, 6, 7, 8]);
+ let values = Int32Array::from(vec![Some(1), None, Some(2), None,
Some(3)]);
+ let array = RunArray::<Int32Type>::try_new(&run_ends,
&values).unwrap();
+
+ // slice1 = array[1..6] => [1, null, null, 2, 2]
+ let slice1 = array.slice(1, 5);
+ // slice2 = array[3..8] => [null, 2, 2, null, 3]
+ let slice2 = array.slice(3, 5);
+
+ let opts = SortOptions::default(); // nulls_first=true,
descending=false
+ let cmp = make_comparator(&slice1, &slice2, opts).unwrap();
+
+ // slice1[0]=1, slice2[0]=null
+ assert_eq!(cmp(0, 0), Ordering::Greater);
+ // slice1[1]=null, slice2[0]=null
+ assert_eq!(cmp(1, 0), Ordering::Equal);
+ // slice1[1]=null, slice2[1]=2
+ assert_eq!(cmp(1, 1), Ordering::Less);
+ // slice1[3]=2, slice2[1]=2
+ assert_eq!(cmp(3, 1), Ordering::Equal);
+ // slice1[4]=2, slice2[4]=3
+ assert_eq!(cmp(4, 4), Ordering::Less);
+ // slice1[3]=2, slice2[3]=null
+ assert_eq!(cmp(3, 3), Ordering::Greater);
+ }
+
+ #[test]
+ fn test_run_end_encoded_different_types() {
+ // Test with different run end types - should fail
+ let run_ends1 = Int32Array::from(vec![2, 4, 6]);
+ let values1 = Int32Array::from(vec![1, 2, 3]);
+ let array1 = RunArray::<Int32Type>::try_new(&run_ends1,
&values1).unwrap();
+
+ let run_ends2 = Int64Array::from(vec![2_i64, 4, 6]);
+ let values2 = Int64Array::from(vec![1_i64, 2, 3]);
+ let array2 = RunArray::<Int64Type>::try_new(&run_ends2,
&values2).unwrap();
+
+ let result = make_comparator(&array1, &array2, SortOptions::default());
+ assert!(result.is_err());
+ let err = match result {
+ Err(e) => e.to_string(),
+ Ok(_) => panic!("Expected error"),
+ };
+ assert!(err.contains("Cannot compare RunEndEncoded arrays"));
+ }
}
