Skip to content
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

Jump to bottom

feat: Support casting from/to Null #31

Merged
merged 3 commits into from
Feb 5, 2024
Merged

feat: Support casting from/to Null #31

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
dbc9929
Support casting to/from `DataType::Null` in `cast` kernel (#1572)
WinkerDu Jun 9, 2023
d55f664
feat: Support cast between `Decimal` and `Null`
MazterQyou Jun 9, 2023
31c0d8f
feat: Support `Null` ordering
MazterQyou Jun 9, 2023
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: 12 additions & 1 deletion arrow/src/array/array.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -555,7 +555,18 @@ pub fn new_null_array(data_type: &DataType, length: usize) -> ArrayRef {
})
}
DataType::Decimal(_, _) => {
unimplemented!("Creating null Decimal array not yet supported")
let null_buf: Buffer = MutableBuffer::new_null(length).into();
make_array(unsafe {
ArrayData::new_unchecked(
data_type.clone(),
length,
Some(length),
Some(null_buf.clone()),
0,
vec![null_buf],
vec![],
)
})
}
}
}
Expand Down
1 change: 1 addition & 0 deletions arrow/src/array/ord.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,6 +230,7 @@ pub fn build_compare(left: &dyn Array, right: &dyn Array) -> Result<DynComparato
let right: DecimalArray = DecimalArray::from(right.data().clone());
Box::new(move |i, j| left.value(i).cmp(&right.value(j)))
}
(Null, Null) => Box::new(|_, _| Ordering::Equal),
(lhs, _) => {
return Err(ArrowError::InvalidArgumentError(format!(
"The data type type {:?} has no natural order",
Expand Down
134 changes: 133 additions & 1 deletion arrow/src/compute/kernels/cast.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,8 +96,22 @@ pub fn can_cast_types(from_type: &DataType, to_type: &DataType) -> bool {
| Int64
| UInt64
| Float64
| Decimal(_, _)
| Date64
| Timestamp(_, _)
| Time64(_)
| Duration(_)
| Interval(_)
| FixedSizeBinary(_)
| Binary
| Utf8
| LargeBinary
| LargeUtf8
| List(_)
| LargeList(_)
| FixedSizeList(_, _)
| Struct(_)
| Map(_, _)
| Dictionary(_, _),
)
| (
Expand All @@ -114,8 +128,22 @@ pub fn can_cast_types(from_type: &DataType, to_type: &DataType) -> bool {
| Int64
| UInt64
| Float64
| Decimal(_, _)
| Date64
| Timestamp(_, _)
| Time64(_)
| Duration(_)
| Interval(_)
| FixedSizeBinary(_)
| Binary
| Utf8
| LargeBinary
| LargeUtf8
| List(_)
| LargeList(_)
| FixedSizeList(_, _)
| Struct(_)
| Map(_, _)
| Dictionary(_, _),
Null,
) => true,
Expand Down Expand Up @@ -483,6 +511,7 @@ pub fn cast_with_options(
Float64 => {
cast_decimal_to_float!(array, scale, Float64Builder, f64)
}
Null => Ok(new_null_array(to_type, array.len())),
_ => Err(ArrowError::CastError(format!(
"Casting from {:?} to {:?} not supported",
from_type, to_type
Expand Down Expand Up @@ -517,6 +546,7 @@ pub fn cast_with_options(
Utf8 => {
cast_string_to_decimal!(array, StringArray, precision, scale)
}
Null => Ok(new_null_array(to_type, array.len())),
_ => Err(ArrowError::CastError(format!(
"Casting from {:?} to {:?} not supported",
from_type, to_type
Expand All @@ -539,7 +569,20 @@ pub fn cast_with_options(
| UInt64
| Float64
| Date64
| Timestamp(_, _)
| Time64(_)
| Duration(_)
| Interval(_)
| FixedSizeBinary(_)
| Binary
| Utf8
| LargeBinary
| LargeUtf8
| List(_)
| LargeList(_)
| FixedSizeList(_, _)
| Struct(_)
| Map(_, _)
| Dictionary(_, _),
)
| (
Expand All @@ -557,7 +600,20 @@ pub fn cast_with_options(
| UInt64
| Float64
| Date64
| Timestamp(_, _)
| Time64(_)
| Duration(_)
| Interval(_)
| FixedSizeBinary(_)
| Binary
| Utf8
| LargeBinary
| LargeUtf8
| List(_)
| LargeList(_)
| FixedSizeList(_, _)
| Struct(_)
| Map(_, _)
| Dictionary(_, _),
Null,
) => Ok(new_null_array(to_type, array.len())),
Expand Down Expand Up @@ -4655,7 +4711,7 @@ mod tests {
}

#[test]
fn test_cast_null_array_from_and_to_others() {
fn test_cast_null_array_from_and_to_primitive_array() {
macro_rules! typed_test {
($ARR_TYPE:ident, $DATATYPE:ident, $TYPE:tt) => {{
{
Expand Down Expand Up @@ -4688,6 +4744,82 @@ mod tests {

typed_test!(Float32Array, Float32, Float32Type);
typed_test!(Float64Array, Float64, Float64Type);

typed_test!(Date32Array, Date32, Date32Type);
typed_test!(Date64Array, Date64, Date64Type);
}

fn cast_from_and_to_null(data_type: &DataType) {
// Cast from data_type to null
{
let array = new_null_array(data_type, 4);
assert_eq!(array.data_type(), data_type);
let cast_array = cast(&array, &DataType::Null).expect("cast failed");
assert_eq!(cast_array.data_type(), &DataType::Null);
for i in 0..4 {
assert!(cast_array.is_null(i));
}
}
// 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 {
assert!(cast_array.is_null(i));
}
}
}

#[test]
fn test_cast_null_from_and_to_variable_sized() {
cast_from_and_to_null(&DataType::Utf8);
cast_from_and_to_null(&DataType::LargeUtf8);
cast_from_and_to_null(&DataType::Binary);
cast_from_and_to_null(&DataType::LargeBinary);
}

#[test]
fn test_cast_null_from_and_to_nested_type() {
// Cast null from and to map
let data_type = DataType::Map(
Box::new(Field::new(
"entry",
DataType::Struct(vec![
Field::new("key", DataType::Utf8, false),
Field::new("value", DataType::Int32, true),
]),
false,
)),
false,
);
cast_from_and_to_null(&data_type);

// Cast null from and to list
let data_type =
DataType::List(Box::new(Field::new("item", DataType::Int32, true)));
cast_from_and_to_null(&data_type);
let data_type =
DataType::LargeList(Box::new(Field::new("item", DataType::Int32, true)));
cast_from_and_to_null(&data_type);
let data_type = DataType::FixedSizeList(
Box::new(Field::new("item", DataType::Int32, true)),
4,
);
cast_from_and_to_null(&data_type);

// Cast null from and to dictionary
let values = vec![None, None, None, None] as Vec<Option<&str>>;
let array: DictionaryArray<Int8Type> = values.into_iter().collect();
let array = Arc::new(array) as ArrayRef;
let data_type = array.data_type().to_owned();
cast_from_and_to_null(&data_type);

// Cast null from and to struct
let data_type =
DataType::Struct(vec![Field::new("data", DataType::Int64, false)]);
cast_from_and_to_null(&data_type);
}

/// Print the `DictionaryArray` `array` as a vector of strings
Expand Down
Loading