Skip to content

Alternative implementation of nullif kernel by slicing nested buffers #1499

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

Closed
jhorstmann wants to merge 6 commits into from
Closed

Alternative implementation of nullif kernel by slicing nested buffers #1499

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8e3055b
Alternative implementation of nullif kernel by slicing nested buffers
jhorstmann Mar 29, 2022
239a9a2
Remove requirement that offsets start at zero so that the offset buff…
jhorstmann Mar 31, 2022
cbbfa77
Also skip copying string offsets
jhorstmann Mar 31, 2022
bf41041
Implement nullif and slicing for FixedSizeList
jhorstmann Mar 31, 2022
d67842e
Implement nullif and slicing StructArray
jhorstmann Mar 31, 2022
c22862d
Remove unused var in test
jhorstmann Mar 31, 2022
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
64 changes: 35 additions & 29 deletions arrow/src/array/array_list.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,13 +241,6 @@ impl<OffsetSize: OffsetSizeTrait> GenericListArray<OffsetSize> {
let value_offsets = data.buffers()[0].as_ptr();

let value_offsets = unsafe { RawPtrBox::<OffsetSize>::new(value_offsets) };
unsafe {
if !(*value_offsets.as_ptr().offset(0)).is_zero() {
return Err(ArrowError::InvalidArgumentError(String::from(
"offsets do not start at zero",
)));
}
}
Ok(Self {
data,
values,
Expand Down Expand Up @@ -1027,6 +1020,41 @@ mod tests {
assert_eq!(8, sliced_list_array.value_offset(3));
}

#[test]
fn test_list_array_offsets_need_not_start_at_zero() {
let value_data = ArrayData::builder(DataType::Int32)
.len(8)
.add_buffer(Buffer::from_slice_ref(&[0, 1, 2, 3, 4, 5, 6, 7]))
.build()
.unwrap();

let value_offsets = Buffer::from_slice_ref(&[2, 2, 5, 7]);

let list_data_type =
DataType::List(Box::new(Field::new("item", DataType::Int32, false)));
let list_data = ArrayData::builder(list_data_type)
.len(3)
.add_buffer(value_offsets)
.add_child_data(value_data)
.build()
.unwrap();

let list_array = make_array(list_data);
let list_array = list_array.as_any().downcast_ref::<ListArray>().unwrap();

assert_eq!(list_array.len(), 3);

assert!(list_array.value(0).is_empty());
assert_eq!(
list_array.value(1).as_ref(),
&PrimitiveArray::<Int32Type>::from(vec![2, 3, 4])
);
assert_eq!(
list_array.value(2).as_ref(),
&PrimitiveArray::<Int32Type>::from(vec![5, 6])
);
}

#[test]
#[should_panic(expected = "assertion failed: (offset + length) <= self.len()")]
fn test_fixed_size_list_array_index_out_of_bound() {
Expand Down Expand Up @@ -1100,28 +1128,6 @@ mod tests {
drop(ListArray::from(list_data));
}

#[test]
#[should_panic(expected = "offsets do not start at zero")]
fn test_list_array_invalid_value_offset_start() {
let value_data = ArrayData::builder(DataType::Int32)
.len(8)
.add_buffer(Buffer::from_slice_ref(&[0, 1, 2, 3, 4, 5, 6, 7]))
.build()
.unwrap();

let value_offsets = Buffer::from_slice_ref(&[2, 2, 5, 7]);

let list_data_type =
DataType::List(Box::new(Field::new("item", DataType::Int32, false)));
let list_data = ArrayData::builder(list_data_type)
.len(3)
.add_buffer(value_offsets)
.add_child_data(value_data)
.build()
.unwrap();
drop(ListArray::from(list_data));
}

#[test]
#[should_panic(expected = "memory is not aligned")]
fn test_primitive_array_alignment() {
Expand Down
7 changes: 0 additions & 7 deletions arrow/src/array/array_map.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,13 +139,6 @@ impl MapArray {
let value_offsets = data.buffers()[0].as_ptr();

let value_offsets = unsafe { RawPtrBox::<i32>::new(value_offsets) };
unsafe {
if (*value_offsets.as_ptr().offset(0)) != 0 {
return Err(ArrowError::InvalidArgumentError(String::from(
"offsets do not start at zero",
)));
}
}
Ok(Self {
data,
values,
Expand Down
Loading