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

Support comparison between dictionary array and binary array #2645

Merged
merged 2 commits into from
Sep 6, 2022
Merged

Support comparison between dictionary array and binary array #2645

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
82595c2
Support comparison between dictionary array and binary array
viirya Sep 4, 2022
eb2bdae
Use downcast_dictionary_array
viirya Sep 6, 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
179 changes: 179 additions & 0 deletions arrow/src/compute/kernels/comparison.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2175,6 +2175,50 @@ macro_rules! typed_dict_string_array_cmp {
}};
}

#[cfg(feature = "dyn_cmp_dict")]
macro_rules! typed_dict_binary_array_cmp {
Copy link
Contributor

Choose a reason for hiding this comment

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

I wonder if we could use downcast_dictionary_array here?

Copy link
Member Author

Choose a reason for hiding this comment

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

Yea, nice catch. We could use it here and save some code.

($LEFT: expr, $RIGHT: expr, $LEFT_KEY_TYPE: expr, $RIGHT_TYPE: tt, $OP: expr) => {{
match $LEFT_KEY_TYPE {
DataType::Int8 => {
let left = as_dictionary_array::<Int8Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::Int16 => {
let left = as_dictionary_array::<Int16Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::Int32 => {
let left = as_dictionary_array::<Int32Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::Int64 => {
let left = as_dictionary_array::<Int64Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::UInt8 => {
let left = as_dictionary_array::<UInt8Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::UInt16 => {
let left = as_dictionary_array::<UInt16Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::UInt32 => {
let left = as_dictionary_array::<UInt32Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
DataType::UInt64 => {
let left = as_dictionary_array::<UInt64Type>($LEFT);
cmp_dict_binary_array::<_, $RIGHT_TYPE, _>(left, $RIGHT, $OP)
}
t => Err(ArrowError::NotYetImplemented(format!(
"Cannot compare dictionary array of key type {}",
t
))),
}
}};
}

#[cfg(feature = "dyn_cmp_dict")]
macro_rules! typed_dict_boolean_array_cmp {
Copy link
Member Author

Choose a reason for hiding this comment

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

Also removed this macro and use downcast_dictionary_array instead.

($LEFT: expr, $RIGHT: expr, $LEFT_KEY_TYPE: expr, $OP: expr) => {{
Expand Down Expand Up @@ -2264,6 +2308,12 @@ macro_rules! typed_cmp_dict_non_dict {
(DataType::LargeUtf8, DataType::LargeUtf8) => {
typed_dict_string_array_cmp!($LEFT, $RIGHT, left_key_type.as_ref(), i64, $OP)
}
(DataType::Binary, DataType::Binary) => {
typed_dict_binary_array_cmp!($LEFT, $RIGHT, left_key_type.as_ref(), i32, $OP)
}
(DataType::LargeBinary, DataType::LargeBinary) => {
typed_dict_binary_array_cmp!($LEFT, $RIGHT, left_key_type.as_ref(), i64, $OP)
}
(t1, t2) if t1 == t2 => Err(ArrowError::NotYetImplemented(format!(
"Comparing dictionary array of type {} with array of type {} is not yet implemented",
t1, t2
Expand Down Expand Up @@ -2675,6 +2725,29 @@ where
)
}

/// Perform given operation on `DictionaryArray` and `GenericBinaryArray`. The value
/// type of `DictionaryArray` is same as `GenericBinaryArray`'s type.
#[cfg(feature = "dyn_cmp_dict")]
fn cmp_dict_binary_array<K, OffsetSize: OffsetSizeTrait, F>(
left: &DictionaryArray<K>,
right: &dyn Array,
op: F,
) -> Result<BooleanArray>
where
K: ArrowNumericType,
F: Fn(&[u8], &[u8]) -> bool,
{
compare_op(
left.downcast_dict::<GenericBinaryArray<OffsetSize>>()
.unwrap(),
right
.as_any()
.downcast_ref::<GenericBinaryArray<OffsetSize>>()
.unwrap(),
op,
)
}

/// Perform given operation on two `DictionaryArray`s which value type is
/// primitive type. Returns an error if the two arrays have different value
/// type
Expand Down Expand Up @@ -6152,6 +6225,112 @@ mod tests {
);
}

#[test]
#[cfg(feature = "dyn_cmp_dict")]
fn test_eq_dyn_neq_dyn_dictionary_to_binary_array() {
let values: BinaryArray = ["hello", "", "parquet"]
.into_iter()
.map(|b| Some(b.as_bytes()))
.collect();

let keys = UInt64Array::from(vec![Some(0_u64), None, Some(2), Some(2)]);
let dict_array = DictionaryArray::<UInt64Type>::try_new(&keys, &values).unwrap();

let array: BinaryArray = ["hello", "", "parquet", "test"]
.into_iter()
.map(|b| Some(b.as_bytes()))
.collect();

let result = eq_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(false)])
);

let result = eq_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(false)])
);

let result = neq_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(true)])
);

let result = neq_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(true)])
);
}

#[test]
#[cfg(feature = "dyn_cmp_dict")]
fn test_lt_dyn_lt_eq_dyn_gt_dyn_gt_eq_dyn_dictionary_to_binary_array() {
let values: BinaryArray = ["hello", "", "parquet"]
.into_iter()
.map(|b| Some(b.as_bytes()))
.collect();

let keys = UInt64Array::from(vec![Some(0_u64), None, Some(2), Some(2)]);
let dict_array = DictionaryArray::<UInt64Type>::try_new(&keys, &values).unwrap();

let array: BinaryArray = ["hello", "", "parquet", "test"]
.into_iter()
.map(|b| Some(b.as_bytes()))
.collect();

let result = lt_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(true)])
);

let result = lt_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(false)])
);

let result = lt_eq_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(true)])
);

let result = lt_eq_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(false)])
);

let result = gt_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(false)])
);

let result = gt_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(false), None, Some(false), Some(true)])
);

let result = gt_eq_dyn(&dict_array, &array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(false)])
);

let result = gt_eq_dyn(&array, &dict_array);
assert_eq!(
result.unwrap(),
BooleanArray::from(vec![Some(true), None, Some(true), Some(true)])
);
}

#[test]
fn test_dict_nlike_kernels() {
let data =
Expand Down