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 ee6c3fba69 fix: support cast from `Null` to list view/run
encoded/union types (#9134)
ee6c3fba69 is described below
commit ee6c3fba69f60f4522bf6dd46127d4091de96f0f
Author: Jeffrey Vo <[email protected]>
AuthorDate: Mon Jan 12 11:33:56 2026 +0900
fix: support cast from `Null` to list view/run encoded/union types (#9134)
# 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 #9133
# 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.
-->
Allow casting null arrays to all types we support. We missed (large)
list view, run end encoded and union.
# 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.
-->
Refactor from null arm to accept all target types to enable casting to
large list view, list view, run end encoded and union types.
# 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)?
-->
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-cast/src/cast/mod.rs | 115 +++++++++++++++------------------------------
arrow-data/src/data.rs | 24 +++++++++-
2 files changed, 60 insertions(+), 79 deletions(-)
diff --git a/arrow-cast/src/cast/mod.rs b/arrow-cast/src/cast/mod.rs
index 67fd02837d..39a94efc56 100644
--- a/arrow-cast/src/cast/mod.rs
+++ b/arrow-cast/src/cast/mod.rs
@@ -104,41 +104,7 @@ pub fn can_cast_types(from_type: &DataType, to_type:
&DataType) -> bool {
}
match (from_type, to_type) {
- (
- Null,
- Boolean
- | Int8
- | UInt8
- | Int16
- | UInt16
- | Float16
- | Int32
- | UInt32
- | Float32
- | Date32
- | Time32(_)
- | Int64
- | UInt64
- | Float64
- | Date64
- | Timestamp(_, _)
- | Time64(_)
- | Duration(_)
- | Interval(_)
- | FixedSizeBinary(_)
- | Binary
- | Utf8
- | LargeBinary
- | LargeUtf8
- | BinaryView
- | Utf8View
- | List(_)
- | LargeList(_)
- | FixedSizeList(_, _)
- | Struct(_)
- | Map(_, _)
- | Dictionary(_, _),
- ) => true,
+ (Null, _) => true,
// Dictionary/List conditions should be put in front of others
(Dictionary(_, from_value_type), Dictionary(_, to_value_type)) => {
can_cast_types(from_value_type, to_value_type)
@@ -212,7 +178,7 @@ pub fn can_cast_types(from_type: &DataType, to_type:
&DataType) -> bool {
) => true,
// signed numeric to decimal
(
- Null | Int8 | Int16 | Int32 | Int64 | Float32 | Float64,
+ Int8 | Int16 | Int32 | Int64 | Float32 | Float64,
Decimal32(_, _) | Decimal64(_, _) | Decimal128(_, _) |
Decimal256(_, _),
) => true,
// decimal to unsigned numeric
@@ -805,41 +771,7 @@ pub fn cast_with_options(
return Ok(make_array(array.to_data()));
}
match (from_type, to_type) {
- (
- Null,
- Boolean
- | Int8
- | UInt8
- | Int16
- | UInt16
- | Float16
- | Int32
- | UInt32
- | Float32
- | Date32
- | Time32(_)
- | Int64
- | UInt64
- | Float64
- | Date64
- | Timestamp(_, _)
- | Time64(_)
- | Duration(_)
- | Interval(_)
- | FixedSizeBinary(_)
- | Binary
- | Utf8
- | LargeBinary
- | LargeUtf8
- | BinaryView
- | Utf8View
- | List(_)
- | LargeList(_)
- | FixedSizeList(_, _)
- | Struct(_)
- | Map(_, _)
- | Dictionary(_, _),
- ) => Ok(new_null_array(to_type, array.len())),
+ (Null, _) => Ok(new_null_array(to_type, array.len())),
(RunEndEncoded(index_type, _), _) => match index_type.data_type() {
Int16 => run_end_encoded_cast::<Int16Type>(array, to_type,
cast_options),
Int32 => run_end_encoded_cast::<Int32Type>(array, to_type,
cast_options),
@@ -8199,19 +8131,29 @@ mod tests {
typed_test!(Date64Array, Date64, Date64Type);
}
- fn cast_from_null_to_other(data_type: &DataType) {
+ fn cast_from_null_to_other_base(data_type: &DataType, is_complex: bool) {
// Cast from null to data_type
- {
- let array = new_null_array(&DataType::Null, 4);
- assert_eq!(array.data_type(), &DataType::Null);
- let cast_array = cast(&array, data_type).expect("cast failed");
- assert_eq!(cast_array.data_type(), data_type);
- for i in 0..4 {
+ let array = new_null_array(&DataType::Null, 4);
+ assert_eq!(array.data_type(), &DataType::Null);
+ let cast_array = cast(&array, data_type).expect("cast failed");
+ assert_eq!(cast_array.data_type(), data_type);
+ for i in 0..4 {
+ if is_complex {
+ assert!(cast_array.logical_nulls().unwrap().is_null(i));
+ } else {
assert!(cast_array.is_null(i));
}
}
}
+ fn cast_from_null_to_other(data_type: &DataType) {
+ cast_from_null_to_other_base(data_type, false);
+ }
+
+ fn cast_from_null_to_other_complex(data_type: &DataType) {
+ cast_from_null_to_other_base(data_type, true);
+ }
+
#[test]
fn test_cast_null_from_and_to_variable_sized() {
cast_from_null_to_other(&DataType::Utf8);
@@ -8255,6 +8197,23 @@ mod tests {
// Cast null from and to struct
let data_type = DataType::Struct(vec![Field::new("data",
DataType::Int64, false)].into());
cast_from_null_to_other(&data_type);
+
+ let target_type = DataType::ListView(Arc::new(Field::new("item",
DataType::Int32, true)));
+ cast_from_null_to_other(&target_type);
+
+ let target_type =
+ DataType::LargeListView(Arc::new(Field::new("item",
DataType::Int32, true)));
+ cast_from_null_to_other(&target_type);
+
+ let fields = UnionFields::from_fields(vec![Field::new("a",
DataType::Int64, false)]);
+ let target_type = DataType::Union(fields, UnionMode::Sparse);
+ cast_from_null_to_other_complex(&target_type);
+
+ let target_type = DataType::RunEndEncoded(
+ Arc::new(Field::new("item", DataType::Int32, true)),
+ Arc::new(Field::new("item", DataType::Int32, true)),
+ );
+ cast_from_null_to_other_complex(&target_type);
}
/// Print the `DictionaryArray` `array` as a vector of strings
diff --git a/arrow-data/src/data.rs b/arrow-data/src/data.rs
index df3b2c578f..f83d604441 100644
--- a/arrow-data/src/data.rs
+++ b/arrow-data/src/data.rs
@@ -698,7 +698,29 @@ impl ArrayData {
false,
)
}
- d => unreachable!("{d}"),
+ // Handled by Some(width) branch above
+ DataType::Int8
+ | DataType::Int16
+ | DataType::Int32
+ | DataType::Int64
+ | DataType::UInt8
+ | DataType::UInt16
+ | DataType::UInt32
+ | DataType::UInt64
+ | DataType::Float16
+ | DataType::Float32
+ | DataType::Float64
+ | DataType::Timestamp(_, _)
+ | DataType::Date32
+ | DataType::Date64
+ | DataType::Time32(_)
+ | DataType::Time64(_)
+ | DataType::Duration(_)
+ | DataType::Interval(_)
+ | DataType::Decimal32(_, _)
+ | DataType::Decimal64(_, _)
+ | DataType::Decimal128(_, _)
+ | DataType::Decimal256(_, _) => unreachable!("{data_type}"),
},
};
