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 100269a16a Fix string array equality when the values buffer is the
same and only the offsets to access it differ (#9325)
100269a16a is described below
commit 100269a16ac428f9c390d835bb61f1d886f41dd2
Author: Jörn Horstmann <[email protected]>
AuthorDate: Mon Feb 2 16:01:01 2026 +0100
Fix string array equality when the values buffer is the same and only the
offsets to access it differ (#9325)
# 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 #9323.
# Rationale for this change
This bug seems to have existed for at least the last 5 years (before
that, array equality had a lot more issues with offsets).
<!--
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?
Tested with unit tests.
# Are there any user-facing changes?
no
---
arrow-array/src/array/string_array.rs | 8 +++++
arrow-data/src/equal/list.rs | 2 +-
arrow-data/src/equal/variable_size.rs | 57 ++++++++++++++++++++++++++++-------
3 files changed, 55 insertions(+), 12 deletions(-)
diff --git a/arrow-array/src/array/string_array.rs
b/arrow-array/src/array/string_array.rs
index 80f3153ece..9cd4a9dc15 100644
--- a/arrow-array/src/array/string_array.rs
+++ b/arrow-array/src/array/string_array.rs
@@ -551,4 +551,12 @@ mod tests {
let err_return = array.into_builder().unwrap_err();
assert_eq!(&err_return, &shared_array);
}
+
+ #[test]
+ fn test_non_null_string_array_equal() {
+ let a = StringArray::from(vec![Some("ab"), Some("c")]);
+ let b = StringArray::from(vec![Some("a"), Some("bc")]);
+
+ assert_ne!(a, b);
+ }
}
diff --git a/arrow-data/src/equal/list.rs b/arrow-data/src/equal/list.rs
index ba5e5a8c93..13214ab6f0 100644
--- a/arrow-data/src/equal/list.rs
+++ b/arrow-data/src/equal/list.rs
@@ -21,7 +21,7 @@ use num_integer::Integer;
use super::equal_range;
-fn lengths_equal<T: ArrowNativeType + Integer>(lhs: &[T], rhs: &[T]) -> bool {
+pub(super) fn lengths_equal<T: ArrowNativeType + Integer>(lhs: &[T], rhs:
&[T]) -> bool {
// invariant from `base_equal`
debug_assert_eq!(lhs.len(), rhs.len());
diff --git a/arrow-data/src/equal/variable_size.rs
b/arrow-data/src/equal/variable_size.rs
index c83a39ebd8..10aeafd7e9 100644
--- a/arrow-data/src/equal/variable_size.rs
+++ b/arrow-data/src/equal/variable_size.rs
@@ -15,12 +15,12 @@
// specific language governing permissions and limitations
// under the License.
+use super::utils::equal_len;
use crate::data::{ArrayData, contains_nulls};
+use crate::equal::list::lengths_equal;
use arrow_buffer::ArrowNativeType;
use num_integer::Integer;
-use super::utils::equal_len;
-
fn offset_value_equal<T: ArrowNativeType + Integer>(
lhs_values: &[u8],
rhs_values: &[u8],
@@ -63,15 +63,18 @@ pub(super) fn variable_sized_equal<T: ArrowNativeType +
Integer>(
// Only checking one null mask here because by the time the control flow
reaches
// this point, the equality of the two masks would have already been
verified.
if !contains_nulls(lhs.nulls(), lhs_start, len) {
- offset_value_equal(
- lhs_values,
- rhs_values,
- lhs_offsets,
- rhs_offsets,
- lhs_start,
- rhs_start,
- len,
- )
+ let lhs_offsets_slice = &lhs_offsets[lhs_start..lhs_start + len + 1];
+ let rhs_offsets_slice = &rhs_offsets[rhs_start..rhs_start + len + 1];
+ lengths_equal(lhs_offsets_slice, rhs_offsets_slice)
+ && offset_value_equal(
+ lhs_values,
+ rhs_values,
+ lhs_offsets,
+ rhs_offsets,
+ lhs_start,
+ rhs_start,
+ len,
+ )
} else {
(0..len).all(|i| {
let lhs_pos = lhs_start + i;
@@ -95,3 +98,35 @@ pub(super) fn variable_sized_equal<T: ArrowNativeType +
Integer>(
})
}
}
+
+#[cfg(test)]
+mod tests {
+ use crate::ArrayData;
+ use crate::equal::variable_size::variable_sized_equal;
+ use arrow_buffer::Buffer;
+ use arrow_schema::DataType;
+
+ #[test]
+ fn test_variable_sized_equal_diff_offsets() {
+ let a = ArrayData::builder(DataType::Utf8)
+ .buffers(vec![
+ Buffer::from_vec(vec![0_i32, 3, 6]),
+ Buffer::from_slice_ref(b"foobar"),
+ ])
+ .null_bit_buffer(Some(Buffer::from_slice_ref([0b01_u8])))
+ .len(2)
+ .build()
+ .unwrap();
+ let b = ArrayData::builder(DataType::Utf8)
+ .buffers(vec![
+ Buffer::from_vec(vec![0_i32, 2, 6]),
+ Buffer::from_slice_ref(b"foobar"),
+ ])
+ .null_bit_buffer(Some(Buffer::from_slice_ref([0b01_u8])))
+ .len(2)
+ .build()
+ .unwrap();
+
+ assert!(!variable_sized_equal::<i32>(&a, &b, 0, 0, 2));
+ }
+}
