This is an automated email from the ASF dual-hosted git repository.
xudong963 pushed a commit to branch branch-51
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/branch-51 by this push:
new 6dcde50500 [branch-51]: Add timezone to date_trunc fast path (#18596)
(#18629)
6dcde50500 is described below
commit 6dcde50500cc59d0bd68fcad3fa2263264f1ab39
Author: Haresh Khanna <[email protected]>
AuthorDate: Wed Nov 12 11:00:02 2025 +0530
[branch-51]: Add timezone to date_trunc fast path (#18596) (#18629)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123. -->
- Closes #18597
## Rationale for this change
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes. -->
A check is recently added to `invoke_with_args` that checks for the
output type of the result with the expected output type from the UDF -
https://github.com/apache/datafusion/pull/17515. Because the fast path
misses adding the timezone, the assertion added in this PR fails.
## What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
Include timezone information in the fast path.
## Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
Yes, added a unit test and SLT test
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
No
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Closes #.
## Rationale for this change
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
## What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
## Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---
datafusion/functions/src/datetime/date_trunc.rs | 177 +++++++++++++++++++++-
datafusion/sqllogictest/test_files/timestamps.slt | 55 ++++---
2 files changed, 210 insertions(+), 22 deletions(-)
diff --git a/datafusion/functions/src/datetime/date_trunc.rs
b/datafusion/functions/src/datetime/date_trunc.rs
index 913e6217af..c8376cf844 100644
--- a/datafusion/functions/src/datetime/date_trunc.rs
+++ b/datafusion/functions/src/datetime/date_trunc.rs
@@ -276,6 +276,7 @@ impl ScalarUDFImpl for DateTruncFunc {
T::UNIT,
array,
granularity,
+ tz_opt.clone(),
)?;
return Ok(ColumnarValue::Array(result));
}
@@ -522,6 +523,7 @@ fn general_date_trunc_array_fine_granularity<T:
ArrowTimestampType>(
tu: TimeUnit,
array: &PrimitiveArray<T>,
granularity: DateTruncGranularity,
+ tz_opt: Option<Arc<str>>,
) -> Result<ArrayRef> {
let unit = match (tu, granularity) {
(Second, DateTruncGranularity::Minute) => NonZeroI64::new(60),
@@ -556,7 +558,8 @@ fn general_date_trunc_array_fine_granularity<T:
ArrowTimestampType>(
.iter()
.map(|v| *v - i64::rem_euclid(*v, unit)),
array.nulls().cloned(),
- );
+ )
+ .with_timezone_opt(tz_opt);
Ok(Arc::new(array))
} else {
// truncate to the same or smaller unit
@@ -1094,4 +1097,176 @@ mod tests {
}
});
}
+
+ #[test]
+ fn test_date_trunc_fine_granularity_timezones() {
+ let cases = [
+ // Test "second" granularity
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:42:30.500000Z",
+ "2020-09-08T13:42:31.999999Z",
+ ],
+ Some("+00".into()),
+ "second",
+ vec![
+ "2020-09-08T13:42:29.000000Z",
+ "2020-09-08T13:42:30.000000Z",
+ "2020-09-08T13:42:31.000000Z",
+ ],
+ ),
+ (
+ vec![
+ "2020-09-08T13:42:29.190855+05",
+ "2020-09-08T13:42:30.500000+05",
+ "2020-09-08T13:42:31.999999+05",
+ ],
+ Some("+05".into()),
+ "second",
+ vec![
+ "2020-09-08T13:42:29.000000+05",
+ "2020-09-08T13:42:30.000000+05",
+ "2020-09-08T13:42:31.000000+05",
+ ],
+ ),
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:42:30.500000Z",
+ "2020-09-08T13:42:31.999999Z",
+ ],
+ Some("Europe/Berlin".into()),
+ "second",
+ vec![
+ "2020-09-08T13:42:29.000000Z",
+ "2020-09-08T13:42:30.000000Z",
+ "2020-09-08T13:42:31.000000Z",
+ ],
+ ),
+ // Test "minute" granularity
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:43:30.500000Z",
+ "2020-09-08T13:44:31.999999Z",
+ ],
+ Some("+00".into()),
+ "minute",
+ vec![
+ "2020-09-08T13:42:00.000000Z",
+ "2020-09-08T13:43:00.000000Z",
+ "2020-09-08T13:44:00.000000Z",
+ ],
+ ),
+ (
+ vec![
+ "2020-09-08T13:42:29.190855+08",
+ "2020-09-08T13:43:30.500000+08",
+ "2020-09-08T13:44:31.999999+08",
+ ],
+ Some("+08".into()),
+ "minute",
+ vec![
+ "2020-09-08T13:42:00.000000+08",
+ "2020-09-08T13:43:00.000000+08",
+ "2020-09-08T13:44:00.000000+08",
+ ],
+ ),
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:43:30.500000Z",
+ "2020-09-08T13:44:31.999999Z",
+ ],
+ Some("America/Sao_Paulo".into()),
+ "minute",
+ vec![
+ "2020-09-08T13:42:00.000000Z",
+ "2020-09-08T13:43:00.000000Z",
+ "2020-09-08T13:44:00.000000Z",
+ ],
+ ),
+ // Test with None (no timezone)
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:43:30.500000Z",
+ "2020-09-08T13:44:31.999999Z",
+ ],
+ None,
+ "minute",
+ vec![
+ "2020-09-08T13:42:00.000000Z",
+ "2020-09-08T13:43:00.000000Z",
+ "2020-09-08T13:44:00.000000Z",
+ ],
+ ),
+ // Test millisecond granularity
+ (
+ vec![
+ "2020-09-08T13:42:29.190855Z",
+ "2020-09-08T13:42:29.191999Z",
+ "2020-09-08T13:42:29.192500Z",
+ ],
+ Some("Asia/Kolkata".into()),
+ "millisecond",
+ vec![
+ "2020-09-08T19:12:29.190000+05:30",
+ "2020-09-08T19:12:29.191000+05:30",
+ "2020-09-08T19:12:29.192000+05:30",
+ ],
+ ),
+ ];
+
+ cases
+ .iter()
+ .for_each(|(original, tz_opt, granularity, expected)| {
+ let input = original
+ .iter()
+ .map(|s| Some(string_to_timestamp_nanos(s).unwrap()))
+ .collect::<TimestampNanosecondArray>()
+ .with_timezone_opt(tz_opt.clone());
+ let right = expected
+ .iter()
+ .map(|s| Some(string_to_timestamp_nanos(s).unwrap()))
+ .collect::<TimestampNanosecondArray>()
+ .with_timezone_opt(tz_opt.clone());
+ let batch_len = input.len();
+ let arg_fields = vec![
+ Field::new("a", DataType::Utf8, false).into(),
+ Field::new("b", input.data_type().clone(), false).into(),
+ ];
+ let args = datafusion_expr::ScalarFunctionArgs {
+ args: vec![
+ ColumnarValue::Scalar(ScalarValue::from(*granularity)),
+ ColumnarValue::Array(Arc::new(input)),
+ ],
+ arg_fields,
+ number_rows: batch_len,
+ return_field: Field::new(
+ "f",
+ DataType::Timestamp(TimeUnit::Nanosecond,
tz_opt.clone()),
+ true,
+ )
+ .into(),
+ config_options: Arc::new(ConfigOptions::default()),
+ };
+ let result =
DateTruncFunc::new().invoke_with_args(args).unwrap();
+ if let ColumnarValue::Array(result) = result {
+ assert_eq!(
+ result.data_type(),
+ &DataType::Timestamp(TimeUnit::Nanosecond,
tz_opt.clone()),
+ "Failed for granularity: {granularity}, timezone:
{tz_opt:?}"
+ );
+ let left =
as_primitive_array::<TimestampNanosecondType>(&result);
+ assert_eq!(
+ left, &right,
+ "Failed for granularity: {granularity}, timezone:
{tz_opt:?}"
+ );
+ } else {
+ panic!("unexpected column type");
+ }
+ });
+ }
}
diff --git a/datafusion/sqllogictest/test_files/timestamps.slt
b/datafusion/sqllogictest/test_files/timestamps.slt
index cdacad0fda..5c365b056d 100644
--- a/datafusion/sqllogictest/test_files/timestamps.slt
+++ b/datafusion/sqllogictest/test_files/timestamps.slt
@@ -45,6 +45,9 @@ create table ts_data_millis as select arrow_cast(ts /
1000000, 'Timestamp(Millis
statement ok
create table ts_data_secs as select arrow_cast(ts / 1000000000,
'Timestamp(Second, None)') as ts, value from ts_data;
+statement ok
+create table ts_data_micros_kolkata as select arrow_cast(ts / 1000,
'Timestamp(Microsecond, Some("Asia/Kolkata"))') as ts, value from ts_data;
+
##########
## Current date Tests
@@ -1873,27 +1876,6 @@ true false true true
-##########
-## Common timestamp data
-##########
-
-statement ok
-drop table ts_data
-
-statement ok
-drop table ts_data_nanos
-
-statement ok
-drop table ts_data_micros
-
-statement ok
-drop table ts_data_millis
-
-statement ok
-drop table ts_data_secs
-
-
-
##########
## Timezone impact on scalar functions
#
@@ -3703,3 +3685,34 @@ SELECT
FROM (SELECT CAST('2005-09-10 13:31:00 +02:00' AS timestamp with time zone) AS
a)
----
Timestamp(ns, "+00") 2005-09-10T11:31:00Z 2005-09-10T11:31:00Z
2005-09-10T11:31:00Z 2005-09-10T11:31:00Z
+
+query P
+SELECT
+ date_trunc('millisecond', ts)
+FROM ts_data_micros_kolkata
+----
+2020-09-08T19:12:29.190+05:30
+2020-09-08T18:12:29.190+05:30
+2020-09-08T17:12:29.190+05:30
+
+##########
+## Common timestamp data
+##########
+
+statement ok
+drop table ts_data
+
+statement ok
+drop table ts_data_nanos
+
+statement ok
+drop table ts_data_micros
+
+statement ok
+drop table ts_data_millis
+
+statement ok
+drop table ts_data_secs
+
+statement ok
+drop table ts_data_micros_kolkata
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
