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

Add Decimal128 and Decimal256 to downcast_primitive #3056

Merged
merged 5 commits into from
Nov 9, 2022
Merged

Add Decimal128 and Decimal256 to downcast_primitive #3056

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b19f180
Add Decimal128 and Decimal256 to downcast_primitive
viirya Nov 9, 2022
6f9a520
Add doc test
viirya Nov 9, 2022
3e6d2bb
Fix test
viirya Nov 9, 2022
1af7263
For review
viirya Nov 9, 2022
690f73c
Merge remote-tracking branch 'upstream/master' into add_decimal_to_do…
viirya Nov 9, 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
8 changes: 8 additions & 0 deletions arrow-array/src/cast.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,6 +225,8 @@ macro_rules! downcast_temporal_array {
/// assert_eq!(primitive_size(&DataType::Int32), 4);
/// assert_eq!(primitive_size(&DataType::Int64), 8);
/// assert_eq!(primitive_size(&DataType::Float16), 2);
/// assert_eq!(primitive_size(&DataType::Decimal128(38, 10)), 16);
/// assert_eq!(primitive_size(&DataType::Decimal256(76, 20)), 32);
/// ```
///
/// [`DataType`]: arrow_schema::DataType
Expand All @@ -242,6 +244,12 @@ macro_rules! downcast_primitive {
$crate::repeat_pat!(arrow_schema::DataType::Float64, $($data_type),+) => {
$m!($crate::types::Float64Type $(, $args)*)
}
$crate::repeat_pat!(arrow_schema::DataType::Decimal128(_, _), $($data_type),+) => {
$m!($crate::types::Decimal128Type $(, $args)*)
}
$crate::repeat_pat!(arrow_schema::DataType::Decimal256(_, _), $($data_type),+) => {
$m!($crate::types::Decimal256Type $(, $args)*)
}
$crate::repeat_pat!(arrow_schema::DataType::Interval(arrow_schema::IntervalUnit::YearMonth), $($data_type),+) => {
$m!($crate::types::IntervalYearMonthType $(, $args)*)
}
Expand Down
13 changes: 12 additions & 1 deletion arrow/src/row/fixed.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,9 +326,20 @@ fn decode_fixed<T: FixedLengthEncoding + ToByteSlice>(
pub fn decode_primitive<T: ArrowPrimitiveType>(
rows: &mut [&[u8]],
options: SortOptions,
data_type: &DataType,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is technically unsafe as it could allow for transmute from decimal128 to decimal256, etc... I have a PR in the works to fix this

) -> PrimitiveArray<T>
where
T::Native: FixedLengthEncoding + ToByteSlice,
{
decode_fixed::<T::Native>(rows, T::DATA_TYPE, options).into()
let array_data: ArrayData = decode_fixed::<T::Native>(rows, T::DATA_TYPE, options);
match data_type {
DataType::Decimal128(_, _)
| DataType::Decimal256(_, _)
| DataType::Timestamp(_, _) => {
let data = array_data.into_builder().data_type(data_type.clone());

unsafe { data.build_unchecked().into() }
}
_ => array_data.into(),
}
}
36 changes: 4 additions & 32 deletions arrow/src/row/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,6 @@ use std::sync::Arc;

use arrow_array::cast::*;
use arrow_array::*;
use arrow_buffer::i256;

use crate::compute::SortOptions;
use crate::datatypes::*;
Expand Down Expand Up @@ -504,8 +503,6 @@ fn new_empty_rows(
array => lengths.iter_mut().for_each(|x| *x += fixed::encoded_len(array)),
DataType::Null => {},
DataType::Boolean => lengths.iter_mut().for_each(|x| *x += bool::ENCODED_LEN),
DataType::Decimal128(_, _) => lengths.iter_mut().for_each(|x| *x += i128::ENCODED_LEN),
DataType::Decimal256(_, _) => lengths.iter_mut().for_each(|x| *x += i256::ENCODED_LEN),
DataType::Binary => as_generic_binary_array::<i32>(array)
.iter()
.zip(lengths.iter_mut())
Expand Down Expand Up @@ -586,22 +583,6 @@ fn encode_column(
column => fixed::encode(out, column, opts),
DataType::Null => {}
DataType::Boolean => fixed::encode(out, as_boolean_array(column), opts),
DataType::Decimal128(_, _) => {
let column = column
.as_any()
.downcast_ref::<Decimal128Array>()
.unwrap();

fixed::encode(out, column, opts)
},
DataType::Decimal256(_, _) => {
let column = column
.as_any()
.downcast_ref::<Decimal256Array>()
.unwrap();

fixed::encode(out, column, opts)
},
DataType::Binary => {
variable::encode(out, as_generic_binary_array::<i32>(column).iter(), opts)
}
Expand Down Expand Up @@ -629,8 +610,8 @@ fn encode_column(
}

macro_rules! decode_primitive_helper {
($t:ty, $rows: ident, $options:ident) => {
Arc::new(decode_primitive::<$t>($rows, $options))
($t:ty, $rows: ident, $options:ident, $data_type: ident) => {
Arc::new(decode_primitive::<$t>($rows, $options, $data_type))
};
}

Expand All @@ -645,24 +626,15 @@ unsafe fn decode_column(
interner: Option<&OrderPreservingInterner>,
) -> Result<ArrayRef> {
let options = field.options;
let data_type = &field.data_type;
let array: ArrayRef = downcast_primitive! {
&field.data_type => (decode_primitive_helper, rows, options),
&field.data_type => (decode_primitive_helper, rows, options, data_type),
DataType::Null => Arc::new(NullArray::new(rows.len())),
DataType::Boolean => Arc::new(decode_bool(rows, options)),
DataType::Binary => Arc::new(decode_binary::<i32>(rows, options)),
DataType::LargeBinary => Arc::new(decode_binary::<i64>(rows, options)),
DataType::Utf8 => Arc::new(decode_string::<i32>(rows, options)),
DataType::LargeUtf8 => Arc::new(decode_string::<i64>(rows, options)),
DataType::Decimal128(p, s) => Arc::new(
decode_primitive::<Decimal128Type>(rows, options)
.with_precision_and_scale(*p, *s)
.unwrap(),
),
DataType::Decimal256(p, s) => Arc::new(
decode_primitive::<Decimal256Type>(rows, options)
.with_precision_and_scale(*p, *s)
.unwrap(),
),
DataType::Dictionary(k, v) => match k.as_ref() {
DataType::Int8 => Arc::new(decode_dictionary::<Int8Type>(
interner.unwrap(),
Expand Down