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 155dc0bc67 chore: add unchecked array builder methods (#10440)
155dc0bc67 is described below
commit 155dc0bc6799f4d3f4042181e317cb78812f0143
Author: RIchard Baah <[email protected]>
AuthorDate: Tue Jul 28 13:28:38 2026 -0400
chore: add unchecked array builder methods (#10440)
# 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 #10244.
# Rationale for this change
we can avoid un-needed validation at callsites by using
`new_unchecked()` instead of `new()`.
<!--
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?
added missing `new_unchecked` methods for PrimitiveArray, BooleanArray,
GenericListArray, FixedSizeListArray, FixedSizeBinaryArray and MapArray.
<!--
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?
n/a no call sites have been changes yet.
<!--
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.
-->
# Are there any user-facing changes?
users now have the option to construct these arrays without validation
but it must be done within an unsafe block.
<!--
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.
-->
---
arrow-array/src/array/boolean_array.rs | 11 ++++++++++
arrow-array/src/array/fixed_size_binary_array.rs | 24 ++++++++++++++++++++++
arrow-array/src/array/fixed_size_list_array.rs | 26 ++++++++++++++++++++++++
arrow-array/src/array/list_array.rs | 23 +++++++++++++++++++++
arrow-array/src/array/map_array.rs | 25 +++++++++++++++++++++++
arrow-array/src/array/primitive_array.rs | 18 ++++++++++++++++
6 files changed, 127 insertions(+)
diff --git a/arrow-array/src/array/boolean_array.rs
b/arrow-array/src/array/boolean_array.rs
index 9245f5b337..decf16bb6d 100644
--- a/arrow-array/src/array/boolean_array.rs
+++ b/arrow-array/src/array/boolean_array.rs
@@ -93,6 +93,17 @@ impl BooleanArray {
Self { values, nulls }
}
+ /// Create a new [`BooleanArray`] from the provided values and nulls
without validation.
+ ///
+ /// # Safety
+ /// - `values.len() == nulls.len()` if `nulls` is `Some`
+ pub unsafe fn new_unchecked(values: BooleanBuffer, nulls:
Option<NullBuffer>) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::new(values, nulls);
+ }
+ Self { values, nulls }
+ }
+
/// Create a new [`BooleanArray`] with length `len` consisting only of
nulls
pub fn new_null(len: usize) -> Self {
Self {
diff --git a/arrow-array/src/array/fixed_size_binary_array.rs
b/arrow-array/src/array/fixed_size_binary_array.rs
index 85e5d266c9..b53c001a89 100644
--- a/arrow-array/src/array/fixed_size_binary_array.rs
+++ b/arrow-array/src/array/fixed_size_binary_array.rs
@@ -118,6 +118,30 @@ impl FixedSizeBinaryArray {
Self::try_new(value_length, values, nulls).unwrap()
}
+ /// Create a new [`FixedSizeBinaryArray`] from the provided parts without
validation.
+ ///
+ /// # Safety
+ /// - `value_length >= 0`
+ /// - `values.len() == len * value_length as usize`
+ /// - `nulls.len() == len` if `nulls` is `Some`
+ pub unsafe fn new_unchecked(
+ value_length: i32,
+ values: Buffer,
+ nulls: Option<NullBuffer>,
+ len: usize,
+ ) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::try_new_with_len(value_length, values, nulls,
len).unwrap();
+ }
+ Self {
+ data_type: DataType::FixedSizeBinary(value_length),
+ value_data: values,
+ value_size: value_length as usize,
+ nulls,
+ len,
+ }
+ }
+
/// Create a new [`Scalar`] from `value`
pub fn new_scalar(value: impl AsRef<[u8]>) -> Scalar<Self> {
let v = value.as_ref();
diff --git a/arrow-array/src/array/fixed_size_list_array.rs
b/arrow-array/src/array/fixed_size_list_array.rs
index 01ccafd9cc..797fedbc71 100644
--- a/arrow-array/src/array/fixed_size_list_array.rs
+++ b/arrow-array/src/array/fixed_size_list_array.rs
@@ -142,6 +142,32 @@ impl FixedSizeListArray {
Self::try_new(field, size, values, nulls).unwrap()
}
+ /// Create a new [`FixedSizeListArray`] from the provided parts without
validation.
+ ///
+ /// # Safety
+ /// - `size >= 0`
+ /// - `values.len() == len * size as usize`
+ /// - `nulls.len() == len` if `nulls` is `Some`
+ /// - `field.data_type() == values.data_type()`
+ pub unsafe fn new_unchecked(
+ field: FieldRef,
+ size: i32,
+ values: ArrayRef,
+ nulls: Option<NullBuffer>,
+ len: usize,
+ ) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::try_new_with_length(field, size, values, nulls,
len).unwrap();
+ }
+ Self {
+ data_type: DataType::FixedSizeList(field, size),
+ values,
+ value_length: size,
+ nulls,
+ len,
+ }
+ }
+
/// Create a new [`FixedSizeListArray`] from the provided parts, returning
an error on failure.
///
/// Note that if `size == 0` and `nulls` is `None` (a degenerate,
non-nullable
diff --git a/arrow-array/src/array/list_array.rs
b/arrow-array/src/array/list_array.rs
index f74ff7d3f3..4ae2b5668c 100644
--- a/arrow-array/src/array/list_array.rs
+++ b/arrow-array/src/array/list_array.rs
@@ -272,6 +272,29 @@ impl<OffsetSize: OffsetSizeTrait>
GenericListArray<OffsetSize> {
Self::try_new(field, offsets, values, nulls).unwrap()
}
+ /// Create a new [`GenericListArray`] from the provided parts without
validation.
+ ///
+ /// # Safety
+ /// - `offsets.len() - 1 == nulls.len()` if `nulls` is `Some`
+ /// - `offsets.last() <= values.len()`
+ /// - `field.data_type() == values.data_type()`
+ pub unsafe fn new_unchecked(
+ field: FieldRef,
+ offsets: OffsetBuffer<OffsetSize>,
+ values: ArrayRef,
+ nulls: Option<NullBuffer>,
+ ) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::new(field, offsets, values, nulls);
+ }
+ Self {
+ data_type: Self::DATA_TYPE_CONSTRUCTOR(field),
+ nulls,
+ values,
+ value_offsets: offsets,
+ }
+ }
+
/// Create a new [`GenericListArray`] of length `len` where all values are
null
pub fn new_null(field: FieldRef, len: usize) -> Self {
let values = new_empty_array(field.data_type());
diff --git a/arrow-array/src/array/map_array.rs
b/arrow-array/src/array/map_array.rs
index e51c90fca6..f244ddf2b8 100644
--- a/arrow-array/src/array/map_array.rs
+++ b/arrow-array/src/array/map_array.rs
@@ -146,6 +146,31 @@ impl MapArray {
Self::try_new(field, offsets, entries, nulls, ordered).unwrap()
}
+ /// Create a new [`MapArray`] from the provided parts without validation.
+ ///
+ /// # Safety
+ /// - `offsets.len() - 1 == nulls.len()` if `nulls` is `Some`
+ /// - `offsets.last() <= entries.len()`
+ /// - `entries` has exactly 2 columns and its keys column is non-nullable
+ /// - `field.data_type() == entries.data_type()`
+ pub unsafe fn new_unchecked(
+ field: FieldRef,
+ offsets: OffsetBuffer<i32>,
+ entries: StructArray,
+ nulls: Option<NullBuffer>,
+ ordered: bool,
+ ) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::new(field, offsets, entries, nulls, ordered);
+ }
+ Self {
+ data_type: DataType::Map(field, ordered),
+ nulls,
+ entries,
+ value_offsets: offsets,
+ }
+ }
+
/// Deconstruct this array into its constituent parts
pub fn into_parts(
self,
diff --git a/arrow-array/src/array/primitive_array.rs
b/arrow-array/src/array/primitive_array.rs
index 667f816c6b..8946af2b74 100644
--- a/arrow-array/src/array/primitive_array.rs
+++ b/arrow-array/src/array/primitive_array.rs
@@ -636,6 +636,24 @@ impl<T: ArrowPrimitiveType> PrimitiveArray<T> {
Self::try_new(values, nulls).unwrap()
}
+ /// Create a new [`PrimitiveArray`] from the provided values and nulls
without validation.
+ ///
+ /// # Safety
+ /// - `values.len() == nulls.len()` if `nulls` is `Some`
+ pub unsafe fn new_unchecked(
+ values: ScalarBuffer<T::Native>,
+ nulls: Option<NullBuffer>,
+ ) -> Self {
+ if cfg!(feature = "force_validate") {
+ return Self::new(values, nulls);
+ }
+ Self {
+ data_type: T::DATA_TYPE,
+ values,
+ nulls,
+ }
+ }
+
/// Create a new [`PrimitiveArray`] of the given length where all values
are null
pub fn new_null(length: usize) -> Self {
Self {
