Skip to content

chore: Use an enum to express the different kinds of nullability in an array #18048

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 15, 2025
Merged

chore: Use an enum to express the different kinds of nullability in an array #18048

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4efb2b4
chore: Use an enum to express the different kinds of nullability in a…
martin-g Oct 14, 2025
faec195
Use the Nulls enum also in .../multi_group_by/primitive.rs
martin-g Oct 15, 2025
3df1fde
Use the Nulls enum in .../multi_group_by/bytes[_view].rs as well
martin-g Oct 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions datafusion/physical-plan/src/aggregates/group_values/multi_group_by/boolean.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

use std::sync::Arc;

use crate::aggregates::group_values::multi_group_by::Nulls;
use crate::aggregates::group_values::multi_group_by::{nulls_equal_to, GroupColumn};
use crate::aggregates::group_values::null_builder::MaybeNullBufferBuilder;
use arrow::array::{Array as _, ArrayRef, AsArray, BooleanArray, BooleanBufferBuilder};
Expand Down Expand Up @@ -115,15 +116,15 @@ impl<const NULLABLE: bool> GroupColumn for BooleanGroupValueBuilder<NULLABLE> {
let null_count = array.null_count();
let num_rows = array.len();
let all_null_or_non_null = if null_count == 0 {
Some(true)
Nulls::None
} else if null_count == num_rows {
Some(false)
Nulls::All
} else {
None
Nulls::Some
};

match (NULLABLE, all_null_or_non_null) {
(true, None) => {
(true, Nulls::Some) => {
for &row in rows {
if array.is_null(row) {
self.nulls.append(true);
Expand All @@ -135,14 +136,14 @@ impl<const NULLABLE: bool> GroupColumn for BooleanGroupValueBuilder<NULLABLE> {
}
}

(true, Some(true)) => {
(true, Nulls::None) => {
self.nulls.append_n(rows.len(), false);
for &row in rows {
self.buffer.append(arr.value(row));
}
}

(true, Some(false)) => {
(true, Nulls::All) => {
self.nulls.append_n(rows.len(), true);
self.buffer.append_n(rows.len(), bool::default());
}
Expand Down
16 changes: 9 additions & 7 deletions datafusion/physical-plan/src/aggregates/group_values/multi_group_by/bytes.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,9 @@
// specific language governing permissions and limitations
// under the License.

use crate::aggregates::group_values::multi_group_by::{nulls_equal_to, GroupColumn};
use crate::aggregates::group_values::multi_group_by::{
nulls_equal_to, GroupColumn, Nulls,
};
use crate::aggregates::group_values::null_builder::MaybeNullBufferBuilder;
use arrow::array::{
types::GenericStringType, Array, ArrayRef, AsArray, BufferBuilder,
Expand Down Expand Up @@ -138,28 +140,28 @@ where
let null_count = array.null_count();
let num_rows = array.len();
let all_null_or_non_null = if null_count == 0 {
Some(true)
Nulls::None
} else if null_count == num_rows {
Some(false)
Nulls::All
} else {
None
Nulls::Some
};

match all_null_or_non_null {
None => {
Nulls::Some => {
for &row in rows {
self.append_val_inner::<B>(array, row)?
}
}

Some(true) => {
Nulls::None => {
self.nulls.append_n(rows.len(), false);
for &row in rows {
self.do_append_val_inner(arr, row)?;
}
}

Some(false) => {
Nulls::All => {
self.nulls.append_n(rows.len(), true);

let new_len = self.offsets.len() + rows.len();
Expand Down
16 changes: 9 additions & 7 deletions datafusion/physical-plan/src/aggregates/group_values/multi_group_by/bytes_view.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,9 @@
// specific language governing permissions and limitations
// under the License.

use crate::aggregates::group_values::multi_group_by::{nulls_equal_to, GroupColumn};
use crate::aggregates::group_values::multi_group_by::{
nulls_equal_to, GroupColumn, Nulls,
};
use crate::aggregates::group_values::null_builder::MaybeNullBufferBuilder;
use arrow::array::{make_view, Array, ArrayRef, AsArray, ByteView, GenericByteViewArray};
use arrow::buffer::{Buffer, ScalarBuffer};
Expand Down Expand Up @@ -145,28 +147,28 @@ impl<B: ByteViewType> ByteViewGroupValueBuilder<B> {
let null_count = array.null_count();
let num_rows = array.len();
let all_null_or_non_null = if null_count == 0 {
Some(true)
Nulls::None
} else if null_count == num_rows {
Some(false)
Nulls::All
} else {
None
Nulls::Some
};

match all_null_or_non_null {
None => {
Nulls::Some => {
for &row in rows {
self.append_val_inner(array, row);
}
}

Some(true) => {
Nulls::None => {
self.nulls.append_n(rows.len(), false);
for &row in rows {
self.do_append_val_inner(arr, row);
}
}

Some(false) => {
Nulls::All => {
self.nulls.append_n(rows.len(), true);
let new_len = self.views.len() + rows.len();
self.views.resize(new_len, 0);
Expand Down
10 changes: 10 additions & 0 deletions datafusion/physical-plan/src/aggregates/group_values/multi_group_by/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1250,6 +1250,16 @@ fn supported_type(data_type: &DataType) -> bool {
)
}

///Shows how many `null`s there are in an array
enum Nulls {
/// All array items are `null`s
All,
/// There are both `null`s and non-`null`s in the array items
Some,
/// There are no `null`s in the array items
None,
}

#[cfg(test)]
mod tests {
use std::{collections::HashMap, sync::Arc};
Expand Down
16 changes: 9 additions & 7 deletions datafusion/physical-plan/src/aggregates/group_values/multi_group_by/primitive.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,9 @@
// specific language governing permissions and limitations
// under the License.

use crate::aggregates::group_values::multi_group_by::{nulls_equal_to, GroupColumn};
use crate::aggregates::group_values::multi_group_by::{
nulls_equal_to, GroupColumn, Nulls,
};
use crate::aggregates::group_values::null_builder::MaybeNullBufferBuilder;
use arrow::array::ArrowNativeTypeOp;
use arrow::array::{cast::AsArray, Array, ArrayRef, ArrowPrimitiveType, PrimitiveArray};
Expand Down Expand Up @@ -132,15 +134,15 @@ impl<T: ArrowPrimitiveType, const NULLABLE: bool> GroupColumn
let null_count = array.null_count();
let num_rows = array.len();
let all_null_or_non_null = if null_count == 0 {
Some(true)
Nulls::None
} else if null_count == num_rows {
Some(false)
Nulls::All
} else {
None
Nulls::Some
};

match (NULLABLE, all_null_or_non_null) {
(true, None) => {
(true, Nulls::Some) => {
for &row in rows {
if array.is_null(row) {
self.nulls.append(true);
Expand All @@ -152,14 +154,14 @@ impl<T: ArrowPrimitiveType, const NULLABLE: bool> GroupColumn
}
}

(true, Some(true)) => {
(true, Nulls::None) => {
self.nulls.append_n(rows.len(), false);
for &row in rows {
self.group_values.push(arr.value(row));
}
}

(true, Some(false)) => {
(true, Nulls::All) => {
self.nulls.append_n(rows.len(), true);
self.group_values
.extend(iter::repeat_n(T::default_value(), rows.len()));
Expand Down