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 downcast macros (#2635) #2636

Merged
merged 3 commits into from
Sep 2, 2022
Merged

Add downcast macros (#2635) #2636

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
0fdbfff
Add downcast macros (#2635)
tustvold Sep 2, 2022
370d712
Add Float16 support and trailing commas
tustvold Sep 2, 2022
b6992d8
Review feedback
tustvold Sep 2, 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
299 changes: 299 additions & 0 deletions arrow/src/array/cast.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,213 @@
use crate::array::*;
use crate::datatypes::*;

/// Downcast an [`Array`] to a [`PrimitiveArray`] based on its [`DataType`], accepts
/// a number of subsequent patterns to match the data type
///
/// ```
/// # use arrow::downcast_primitive_array;
/// # use arrow::array::Array;
/// # use arrow::datatypes::DataType;
/// # use arrow::array::as_string_array;
///
/// fn print_primitive(array: &dyn Array) {
/// downcast_primitive_array!(
Copy link
Contributor

Choose a reason for hiding this comment

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

❤️ that certainly will make the macros in code such as https://github.com/apache/arrow-datafusion/blob/master/datafusion/physical-expr/src/expressions/binary.rs easier to deal with ❤️

/// array => {
/// for v in array {
/// println!("{:?}", v);
/// }
/// }
/// DataType::Utf8 => {
/// for v in as_string_array(array) {
/// println!("{:?}", v);
/// }
/// }
/// t => println!("Unsupported datatype {}", t)
/// )
/// }
/// ```
///
#[macro_export]
macro_rules! downcast_primitive_array {
($values:ident => $e:expr, $($p:pat => $fallback:expr $(,)*)*) => {
downcast_primitive_array!($values => {$e} $($p => $fallback)*)
};

($values:ident => $e:block $($p:pat => $fallback:expr $(,)*)*) => {
match $values.data_type() {
$crate::datatypes::DataType::Int8 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Int8Type,
>($values);
$e
}
$crate::datatypes::DataType::Int16 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Int16Type,
>($values);
$e
}
$crate::datatypes::DataType::Int32 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Int32Type,
>($values);
$e
}
$crate::datatypes::DataType::Int64 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Int64Type,
>($values);
$e
}
$crate::datatypes::DataType::UInt8 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::UInt8Type,
>($values);
$e
}
$crate::datatypes::DataType::UInt16 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::UInt16Type,
>($values);
$e
}
$crate::datatypes::DataType::UInt32 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::UInt32Type,
>($values);
$e
}
$crate::datatypes::DataType::UInt64 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::UInt64Type,
>($values);
$e
}
$crate::datatypes::DataType::Float16 => {
Copy link
Contributor Author

Choose a reason for hiding this comment

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

This was actually missing before

let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Float16Type,
>($values);
$e
}
$crate::datatypes::DataType::Float32 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Float32Type,
>($values);
$e
}
$crate::datatypes::DataType::Float64 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Float64Type,
>($values);
$e
}
$crate::datatypes::DataType::Date32 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Date32Type,
>($values);
$e
}
$crate::datatypes::DataType::Date64 => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Date64Type,
>($values);
$e
}
$crate::datatypes::DataType::Time32($crate::datatypes::TimeUnit::Second) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Time32SecondType,
>($values);
$e
}
$crate::datatypes::DataType::Time32($crate::datatypes::TimeUnit::Millisecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Time32MillisecondType,
>($values);
$e
}
$crate::datatypes::DataType::Time64($crate::datatypes::TimeUnit::Microsecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Time64MicrosecondType,
>($values);
$e
}
$crate::datatypes::DataType::Time64($crate::datatypes::TimeUnit::Nanosecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::Time64NanosecondType,
>($values);
$e
}
$crate::datatypes::DataType::Timestamp($crate::datatypes::TimeUnit::Second, _) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::TimestampSecondType,
>($values);
$e
}
$crate::datatypes::DataType::Timestamp($crate::datatypes::TimeUnit::Millisecond, _) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::TimestampMillisecondType,
>($values);
$e
}
$crate::datatypes::DataType::Timestamp($crate::datatypes::TimeUnit::Microsecond, _) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::TimestampMicrosecondType,
>($values);
$e
}
$crate::datatypes::DataType::Timestamp($crate::datatypes::TimeUnit::Nanosecond, _) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::TimestampNanosecondType,
>($values);
$e
}
$crate::datatypes::DataType::Interval($crate::datatypes::IntervalUnit::YearMonth) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::IntervalYearMonthType,
>($values);
$e
}
$crate::datatypes::DataType::Interval($crate::datatypes::IntervalUnit::DayTime) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::IntervalDayTimeType,
>($values);
$e
}
$crate::datatypes::DataType::Interval($crate::datatypes::IntervalUnit::MonthDayNano) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::IntervalMonthDayNanoType,
>($values);
$e
}
$crate::datatypes::DataType::Duration($crate::datatypes::TimeUnit::Second) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::DurationSecondType,
>($values);
$e
}
$crate::datatypes::DataType::Duration($crate::datatypes::TimeUnit::Millisecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::DurationMillisecondType,
>($values);
$e
}
$crate::datatypes::DataType::Duration($crate::datatypes::TimeUnit::Microsecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::DurationMicrosecondType,
>($values);
$e
}
$crate::datatypes::DataType::Duration($crate::datatypes::TimeUnit::Nanosecond) => {
let $values = $crate::array::as_primitive_array::<
$crate::datatypes::DurationNanosecondType,
>($values);
$e
}
$($p => $fallback,)*
}
};
}

/// Force downcast of an [`Array`], such as an [`ArrayRef`], to
/// [`PrimitiveArray<T>`], panic'ing on failure.
///
Expand Down Expand Up @@ -53,6 +260,98 @@ where
.expect("Unable to downcast to primitive array")
}

/// Downcast an [`Array`] to a [`DictionaryArray`] based on its [`DataType`], accepts
/// a number of subsequent patterns to match the data type
///
/// ```
/// # use arrow::downcast_dictionary_array;
/// # use arrow::array::{Array, StringArray};
/// # use arrow::datatypes::DataType;
/// # use arrow::array::as_string_array;
///
/// fn print_strings(array: &dyn Array) {
/// downcast_dictionary_array!(
/// array => match array.values().data_type() {
/// DataType::Utf8 => {
/// for v in array.downcast_dict::<StringArray>().unwrap() {
/// println!("{:?}", v);
/// }
/// }
/// t => println!("Unsupported dictionary value type {}", t),
/// },
/// DataType::Utf8 => {
/// for v in as_string_array(array) {
/// println!("{:?}", v);
/// }
/// }
/// t => println!("Unsupported datatype {}", t)
Copy link
Contributor

Choose a reason for hiding this comment

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

I think it would be good to extend this example to show the String array as well -- not only to document how to support other types, but also because the StringArray is so common

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done, and threw in a bit of TypedDictionaryArray spice as well 😆

Copy link
Contributor

Choose a reason for hiding this comment

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

🥘 👍

/// )
/// }
/// ```
#[macro_export]
macro_rules! downcast_dictionary_array {
($values:ident => $e:expr, $($p:pat => $fallback:expr $(,)*)*) => {
downcast_dictionary_array!($values => {$e} $($p => $fallback)*)
};

($values:ident => $e:block $($p:pat => $fallback:expr $(,)*)*) => {
match $values.data_type() {
$crate::datatypes::DataType::Dictionary(k, _) => match k.as_ref() {
$crate::datatypes::DataType::Int8 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::Int8Type,
>($values);
$e
},
$crate::datatypes::DataType::Int16 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::Int16Type,
>($values);
$e
},
$crate::datatypes::DataType::Int32 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::Int32Type,
>($values);
$e
},
$crate::datatypes::DataType::Int64 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::Int64Type,
>($values);
$e
},
$crate::datatypes::DataType::UInt8 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::UInt8Type,
>($values);
$e
},
$crate::datatypes::DataType::UInt16 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::UInt16Type,
>($values);
$e
},
$crate::datatypes::DataType::UInt32 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::UInt32Type,
>($values);
$e
},
$crate::datatypes::DataType::UInt64 => {
let $values = $crate::array::as_dictionary_array::<
$crate::datatypes::UInt64Type,
>($values);
$e
},
k => unreachable!("unsupported dictionary key type: {}", k)
}
$($p => $fallback,)*
}
}
}

/// Force downcast of an [`Array`], such as an [`ArrayRef`] to
/// [`DictionaryArray<T>`], panic'ing on failure.
///
Expand Down
Loading