Skip to content

Support casting Date to a time zone-specific timestamp #7141

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
alamb merged 3 commits into from
Feb 24, 2025
Merged

Support casting Date to a time zone-specific timestamp #7141

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c7af4b1
Date can cast to tz-aware timestamp
friendlymatthew Feb 16, 2025
1b47275
Cover other Date x TimeUnit cases
friendlymatthew Feb 16, 2025
7828b6d
Preserve local time when casting date to timestamp
friendlymatthew Feb 19, 2025
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
274 changes: 242 additions & 32 deletions arrow-cast/src/cast/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,8 +265,8 @@ pub fn can_cast_types(from_type: &DataType, to_type: &DataType) -> bool {
}
(Timestamp(_, _), _) if to_type.is_numeric() => true,
(_, Timestamp(_, _)) if from_type.is_numeric() => true,
(Date64, Timestamp(_, None)) => true,
(Date32, Timestamp(_, None)) => true,
(Date64, Timestamp(_, _)) => true,
(Date32, Timestamp(_, _)) => true,
(
Timestamp(_, _),
Timestamp(_, _)
Expand Down Expand Up @@ -1806,44 +1806,63 @@ pub fn cast_with_options(
})?,
))
}
(Date64, Timestamp(TimeUnit::Second, None)) => Ok(Arc::new(
array
(Date64, Timestamp(TimeUnit::Second, _)) => {
let array = array
.as_primitive::<Date64Type>()
.unary::<_, TimestampSecondType>(|x| x / MILLISECONDS),
)),
(Date64, Timestamp(TimeUnit::Millisecond, None)) => {
cast_reinterpret_arrays::<Date64Type, TimestampMillisecondType>(array)
.unary::<_, TimestampSecondType>(|x| x / MILLISECONDS);

cast_with_options(&array, to_type, cast_options)
}
(Date64, Timestamp(TimeUnit::Microsecond, None)) => Ok(Arc::new(
array
(Date64, Timestamp(TimeUnit::Millisecond, _)) => {
let array = array
.as_primitive::<Date64Type>()
.unary::<_, TimestampMicrosecondType>(|x| x * (MICROSECONDS / MILLISECONDS)),
)),
(Date64, Timestamp(TimeUnit::Nanosecond, None)) => Ok(Arc::new(
array
.reinterpret_cast::<TimestampMillisecondType>();

cast_with_options(&array, to_type, cast_options)
}

(Date64, Timestamp(TimeUnit::Microsecond, _)) => {
let array = array
.as_primitive::<Date64Type>()
.unary::<_, TimestampNanosecondType>(|x| x * (NANOSECONDS / MILLISECONDS)),
)),
(Date32, Timestamp(TimeUnit::Second, None)) => Ok(Arc::new(
array
.unary::<_, TimestampMicrosecondType>(|x| x * (MICROSECONDS / MILLISECONDS));

cast_with_options(&array, to_type, cast_options)
}
(Date64, Timestamp(TimeUnit::Nanosecond, _)) => {
let array = array
.as_primitive::<Date64Type>()
.unary::<_, TimestampNanosecondType>(|x| x * (NANOSECONDS / MILLISECONDS));

cast_with_options(&array, to_type, cast_options)
}
(Date32, Timestamp(TimeUnit::Second, _)) => {
let array = array
.as_primitive::<Date32Type>()
.unary::<_, TimestampSecondType>(|x| (x as i64) * SECONDS_IN_DAY),
)),
(Date32, Timestamp(TimeUnit::Millisecond, None)) => Ok(Arc::new(
array
.unary::<_, TimestampSecondType>(|x| (x as i64) * SECONDS_IN_DAY);

cast_with_options(&array, to_type, cast_options)
}
(Date32, Timestamp(TimeUnit::Millisecond, _)) => {
let array = array
.as_primitive::<Date32Type>()
.unary::<_, TimestampMillisecondType>(|x| (x as i64) * MILLISECONDS_IN_DAY),
)),
(Date32, Timestamp(TimeUnit::Microsecond, None)) => Ok(Arc::new(
array
.unary::<_, TimestampMillisecondType>(|x| (x as i64) * MILLISECONDS_IN_DAY);

cast_with_options(&array, to_type, cast_options)
}
(Date32, Timestamp(TimeUnit::Microsecond, _)) => {
let array = array
.as_primitive::<Date32Type>()
.unary::<_, TimestampMicrosecondType>(|x| (x as i64) * MICROSECONDS_IN_DAY),
)),
(Date32, Timestamp(TimeUnit::Nanosecond, None)) => Ok(Arc::new(
array
.unary::<_, TimestampMicrosecondType>(|x| (x as i64) * MICROSECONDS_IN_DAY);

cast_with_options(&array, to_type, cast_options)
}
(Date32, Timestamp(TimeUnit::Nanosecond, _)) => {
let array = array
.as_primitive::<Date32Type>()
.unary::<_, TimestampNanosecondType>(|x| (x as i64) * NANOSECONDS_IN_DAY),
)),
.unary::<_, TimestampNanosecondType>(|x| (x as i64) * NANOSECONDS_IN_DAY);

cast_with_options(&array, to_type, cast_options)
}

(_, Duration(unit)) if from_type.is_numeric() => {
let array = cast_with_options(array, &Int64, cast_options)?;
Expand Down Expand Up @@ -5217,6 +5236,197 @@ mod tests {
}};
}

#[test]
fn test_cast_date32_to_timestamp_and_timestamp_with_timezone() {
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let a = Date32Array::from(vec![Some(18628), None, None]); // 2021-1-1, 2022-1-1
let array = Arc::new(a) as ArrayRef;

let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Second, Some(tz.into())),
)
.unwrap();
let c = b.as_primitive::<TimestampSecondType>();
let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00+05:45", result.value(0));

let b = cast(&array, &DataType::Timestamp(TimeUnit::Second, None)).unwrap();
let c = b.as_primitive::<TimestampSecondType>();
let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00", result.value(0));
}
Comment on lines +5239 to +5260
Copy link
Contributor Author

@friendlymatthew friendlymatthew Feb 19, 2025

Choose a reason for hiding this comment

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

Proof that casting a Date to a Timestamp with/without time zones result in the same string.

Not the biggest fan of this test case, would appreciate some comments if we would want to a test case that compares the cast results (with/without time zone).


#[test]
fn test_cast_date32_to_timestamp_with_timezone() {
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let a = Date32Array::from(vec![Some(18628), Some(18993), None]); // 2021-1-1, 2022-1-1
Copy link
Member

@xudong963 xudong963 Feb 17, 2025

Choose a reason for hiding this comment

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

So the default tz of date is UTC, right?

Copy link
Contributor Author

@friendlymatthew friendlymatthew Feb 17, 2025

Choose a reason for hiding this comment

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

So the default tz of date is UTC, right?

Yes, but shouldn't we ensure Dates cast to timestamps with a particular timezone?

I'm also a bit confused by this comment. Are you implying that a is improperly constructed? (i.e. the third element shouldn't be None?) Here's a similar test case that tests for time zone aware timestamps:

arrow-rs/arrow-cast/src/cast/mod.rs

Lines 5277 to 5291 in 38d6e69

let array_with_tz =
TimestampMillisecondArray::from(vec![Some(864000003005), Some(1545696002001), None])
.with_timezone(tz.to_string());
let expected = vec![
Some("1997-05-19 05:45:03.005000"),
Some("2018-12-25 05:45:02.001000"),
None,
];
assert_cast_timestamp_to_string!(
array_with_tz,
DataType::Utf8View,
StringViewArray,
cast_options,
expected
);

Maybe I'm misunderstanding something. Would appreciate some clarification. Thank you!

Copy link
Member

@xudong963 xudong963 Feb 18, 2025

Choose a reason for hiding this comment

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

The test is okay for me. Thanks!

I'm just curious about which particular timezone we should use. Should we depend on a time zone configuration or use the UTC directly?

Copy link
Contributor Author

@friendlymatthew friendlymatthew Feb 18, 2025

Choose a reason for hiding this comment

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

I'm just curious about which particular timezone we should use. Should we depend on a time zone configuration or use the UTC directly?

Other test cases use random time zones like the +0545 mentioned above. I'd argue that for the sake of testing, we'd want to use a non-default time zone.

let array = Arc::new(a) as ArrayRef;
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Second, Some(tz.into())),
)
.unwrap();
let c = b.as_primitive::<TimestampSecondType>();
assert_eq!(1609438500, c.value(0));
assert_eq!(1640974500, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00+05:45", result.value(0));
assert_eq!("2022-01-01T00:00:00+05:45", result.value(1));
}

#[test]
fn test_cast_date32_to_timestamp_with_timezone_ms() {
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let a = Date32Array::from(vec![Some(18628), Some(18993), None]); // 2021-1-1, 2022-1-1
let array = Arc::new(a) as ArrayRef;
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Millisecond, Some(tz.into())),
)
.unwrap();
let c = b.as_primitive::<TimestampMillisecondType>();
assert_eq!(1609438500000, c.value(0));
assert_eq!(1640974500000, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00+05:45", result.value(0));
assert_eq!("2022-01-01T00:00:00+05:45", result.value(1));
}

#[test]
fn test_cast_date32_to_timestamp_with_timezone_us() {
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let a = Date32Array::from(vec![Some(18628), Some(18993), None]); // 2021-1-1, 2022-1-1
let array = Arc::new(a) as ArrayRef;
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Microsecond, Some(tz.into())),
)
.unwrap();
let c = b.as_primitive::<TimestampMicrosecondType>();
assert_eq!(1609438500000000, c.value(0));
assert_eq!(1640974500000000, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00+05:45", result.value(0));
assert_eq!("2022-01-01T00:00:00+05:45", result.value(1));
}

#[test]
fn test_cast_date32_to_timestamp_with_timezone_ns() {
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let a = Date32Array::from(vec![Some(18628), Some(18993), None]); // 2021-1-1, 2022-1-1
let array = Arc::new(a) as ArrayRef;
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Nanosecond, Some(tz.into())),
)
.unwrap();
let c = b.as_primitive::<TimestampNanosecondType>();
assert_eq!(1609438500000000000, c.value(0));
assert_eq!(1640974500000000000, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("2021-01-01T00:00:00+05:45", result.value(0));
assert_eq!("2022-01-01T00:00:00+05:45", result.value(1));
}

#[test]
fn test_cast_date64_to_timestamp_with_timezone() {
let array = Date64Array::from(vec![Some(864000000005), Some(1545696000001), None]);
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Second, Some(tz.into())),
)
.unwrap();

let c = b.as_primitive::<TimestampSecondType>();
assert_eq!(863979300, c.value(0));
assert_eq!(1545675300, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("1997-05-19T00:00:00+05:45", result.value(0));
assert_eq!("2018-12-25T00:00:00+05:45", result.value(1));
}

#[test]
fn test_cast_date64_to_timestamp_with_timezone_ms() {
let array = Date64Array::from(vec![Some(864000000005), Some(1545696000001), None]);
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Millisecond, Some(tz.into())),
)
.unwrap();

let c = b.as_primitive::<TimestampMillisecondType>();
assert_eq!(863979300005, c.value(0));
assert_eq!(1545675300001, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("1997-05-19T00:00:00.005+05:45", result.value(0));
assert_eq!("2018-12-25T00:00:00.001+05:45", result.value(1));
}

#[test]
fn test_cast_date64_to_timestamp_with_timezone_us() {
let array = Date64Array::from(vec![Some(864000000005), Some(1545696000001), None]);
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Microsecond, Some(tz.into())),
)
.unwrap();

let c = b.as_primitive::<TimestampMicrosecondType>();
assert_eq!(863979300005000, c.value(0));
assert_eq!(1545675300001000, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("1997-05-19T00:00:00.005+05:45", result.value(0));
assert_eq!("2018-12-25T00:00:00.001+05:45", result.value(1));
}

#[test]
fn test_cast_date64_to_timestamp_with_timezone_ns() {
let array = Date64Array::from(vec![Some(864000000005), Some(1545696000001), None]);
let tz = "+0545"; // UTC + 0545 is Asia/Kathmandu
let b = cast(
&array,
&DataType::Timestamp(TimeUnit::Nanosecond, Some(tz.into())),
)
.unwrap();

let c = b.as_primitive::<TimestampNanosecondType>();
assert_eq!(863979300005000000, c.value(0));
assert_eq!(1545675300001000000, c.value(1));
assert!(c.is_null(2));

let string_array = cast(&c, &DataType::Utf8).unwrap();
let result = string_array.as_string::<i32>();
assert_eq!("1997-05-19T00:00:00.005+05:45", result.value(0));
assert_eq!("2018-12-25T00:00:00.001+05:45", result.value(1));
}

#[test]
fn test_cast_timestamp_to_strings() {
// "2018-12-25T00:00:02.001", "1997-05-19T00:00:03.005", None
Expand Down
Loading