Skip to content

implement eq_dyn, neq_dyn, lt_dyn, lt_eq_dyn, gt_dyn, gt_eq_dyn for timestamp types #1095

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 2 commits into from
Dec 29, 2021
Merged

implement eq_dyn, neq_dyn, lt_dyn, lt_eq_dyn, gt_dyn, gt_eq_dyn for timestamp types #1095

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
568f0ac
implement eq_dyn, neq_dyn, lt_dyn, lt_eq_dyn, gt_dyn, gt_eq_dyn for t…
viirya Dec 25, 2021
ea4bd36
Simplify test code
viirya Dec 25, 2021
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
117 changes: 110 additions & 7 deletions arrow/src/compute/kernels/comparison.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,10 @@ use crate::buffer::{bitwise_bin_op_helper, buffer_unary_not, Buffer, MutableBuff
use crate::compute::binary_boolean_kernel;
use crate::compute::util::combine_option_bitmap;
use crate::datatypes::{
ArrowNumericType, DataType, Float32Type, Float64Type, Int16Type, Int32Type,
Int64Type, Int8Type, UInt16Type, UInt32Type, UInt64Type, UInt8Type,
ArrowNumericType, DataType, Date32Type, Date64Type, Float32Type, Float64Type,
Int16Type, Int32Type, Int64Type, Int8Type, TimeUnit, TimestampMicrosecondType,
TimestampMillisecondType, TimestampNanosecondType, TimestampSecondType, UInt16Type,
UInt32Type, UInt64Type, UInt8Type,
};
use crate::error::{ArrowError, Result};
use crate::util::bit_util;
Expand Down Expand Up @@ -1136,6 +1138,60 @@ macro_rules! typed_compares {
(DataType::LargeUtf8, DataType::LargeUtf8) => {
typed_cmp!($LEFT, $RIGHT, LargeStringArray, $OP_STR, i64)
}
(
DataType::Timestamp(TimeUnit::Nanosecond, _),
DataType::Timestamp(TimeUnit::Nanosecond, _),
) => {
typed_cmp!(
$LEFT,
$RIGHT,
TimestampNanosecondArray,
$OP_PRIM,
TimestampNanosecondType
)
}
(
DataType::Timestamp(TimeUnit::Microsecond, _),
DataType::Timestamp(TimeUnit::Microsecond, _),
) => {
typed_cmp!(
$LEFT,
$RIGHT,
TimestampMicrosecondArray,
$OP_PRIM,
TimestampMicrosecondType
)
}
(
DataType::Timestamp(TimeUnit::Millisecond, _),
DataType::Timestamp(TimeUnit::Millisecond, _),
) => {
typed_cmp!(
$LEFT,
$RIGHT,
TimestampMillisecondArray,
$OP_PRIM,
TimestampMillisecondType
)
}
(
DataType::Timestamp(TimeUnit::Second, _),
DataType::Timestamp(TimeUnit::Second, _),
) => {
typed_cmp!(
$LEFT,
$RIGHT,
TimestampSecondArray,
$OP_PRIM,
TimestampSecondType
)
}
(DataType::Date32, DataType::Date32) => {
typed_cmp!($LEFT, $RIGHT, Date32Array, $OP_PRIM, Date32Type)
}
(DataType::Date64, DataType::Date64) => {
typed_cmp!($LEFT, $RIGHT, Date64Array, $OP_PRIM, Date64Type)
}
(t1, t2) if t1 == t2 => Err(ArrowError::NotYetImplemented(format!(
"Comparing arrays of type {} is not yet implemented",
t1
Expand Down Expand Up @@ -1478,13 +1534,14 @@ mod tests {
use crate::{array::Int32Array, array::Int64Array, datatypes::Field};

/// Evaluate `KERNEL` with two vectors as inputs and assert against the expected output.
/// `A_VEC` and `B_VEC` can be of type `Vec<i64>` or `Vec<Option<i64>>`.
/// `A_VEC` and `B_VEC` can be of type `Vec<T>` or `Vec<Option<T>>` where `T` is the native
/// type of the data type of the Arrow array element.
/// `EXPECTED` can be either `Vec<bool>` or `Vec<Option<bool>>`.
/// The main reason for this macro is that inputs and outputs align nicely after `cargo fmt`.
macro_rules! cmp_i64 {
($KERNEL:ident, $DYN_KERNEL:ident, $A_VEC:expr, $B_VEC:expr, $EXPECTED:expr) => {
let a = Int64Array::from($A_VEC);
let b = Int64Array::from($B_VEC);
macro_rules! cmp_vec {
($KERNEL:ident, $DYN_KERNEL:ident, $ARRAY:ident, $A_VEC:expr, $B_VEC:expr, $EXPECTED:expr) => {
let a = $ARRAY::from($A_VEC);
let b = $ARRAY::from($B_VEC);
let c = $KERNEL(&a, &b).unwrap();
assert_eq!(BooleanArray::from($EXPECTED), c);

Expand All @@ -1496,6 +1553,16 @@ mod tests {
};
}

/// Evaluate `KERNEL` with two vectors as inputs and assert against the expected output.
/// `A_VEC` and `B_VEC` can be of type `Vec<i64>` or `Vec<Option<i64>>`.
/// `EXPECTED` can be either `Vec<bool>` or `Vec<Option<bool>>`.
/// The main reason for this macro is that inputs and outputs align nicely after `cargo fmt`.
macro_rules! cmp_i64 {
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 a nice refactor

($KERNEL:ident, $DYN_KERNEL:ident, $A_VEC:expr, $B_VEC:expr, $EXPECTED:expr) => {
cmp_vec!($KERNEL, $DYN_KERNEL, Int64Array, $A_VEC, $B_VEC, $EXPECTED);
};
}

/// Evaluate `KERNEL` with one vectors and one scalar as inputs and assert against the expected output.
/// `A_VEC` can be of type `Vec<i64>` or `Vec<Option<i64>>`.
/// `EXPECTED` can be either `Vec<bool>` or `Vec<Option<bool>>`.
Expand All @@ -1517,6 +1584,15 @@ mod tests {
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![false, false, true, false, false, false, false, true, false, false]
);

cmp_vec!(
eq,
eq_dyn,
TimestampSecondArray,
vec![8, 8, 8, 8, 8, 8, 8, 8, 8, 8],
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![false, false, true, false, false, false, false, true, false, false]
);
}

#[test]
Expand Down Expand Up @@ -1564,6 +1640,15 @@ mod tests {
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![true, true, false, true, true, true, true, false, true, true]
);

cmp_vec!(
neq,
neq_dyn,
TimestampMillisecondArray,
vec![8, 8, 8, 8, 8, 8, 8, 8, 8, 8],
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![true, true, false, true, true, true, true, false, true, true]
);
}

#[test]
Expand Down Expand Up @@ -1770,6 +1855,15 @@ mod tests {
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![false, false, false, true, true, false, false, false, true, true]
);

cmp_vec!(
lt,
lt_dyn,
TimestampMillisecondArray,
vec![8, 8, 8, 8, 8, 8, 8, 8, 8, 8],
vec![6, 7, 8, 9, 10, 6, 7, 8, 9, 10],
vec![false, false, false, true, true, false, false, false, true, true]
);
}

#[test]
Expand All @@ -1791,6 +1885,15 @@ mod tests {
vec![None, Some(1), None, Some(1), None, Some(3), None, Some(3),],
vec![None, None, None, Some(false), None, None, None, Some(true)]
);

cmp_vec!(
lt,
lt_dyn,
TimestampMillisecondArray,
vec![None, None, Some(1), Some(1), None, None, Some(2), Some(2),],
vec![None, Some(1), None, Some(1), None, Some(3), None, Some(3),],
vec![None, None, None, Some(false), None, None, None, Some(true)]
);
}

#[test]
Expand Down