This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/main by this push:
new 73077404cd fix: write error for dbg output of out of range timestamps
(#10130)
73077404cd is described below
commit 73077404cdeaa52bad71602a1a7234a5b04418ab
Author: Jeffrey Vo <[email protected]>
AuthorDate: Thu Jul 2 20:28:24 2026 +0900
fix: write error for dbg output of out of range timestamps (#10130)
# 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.
-->
- Closes #7287
# 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.
-->
Confusing to print `null` when the value is not formattable via chrono,
so instead clearly write an error.
# 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.
-->
Instead of writing `null` in debug output of timestamp arrays for values
that exceed chronos range, write an error message for that row similar
to date/time types
# 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)?
If this PR claims a performance improvement, please include evidence
such as benchmark results.
-->
Yes.
# 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 call them out.
-->
Not really.
---
arrow-array/src/array/primitive_array.rs | 79 ++++++++++++++++++++++++++------
1 file changed, 66 insertions(+), 13 deletions(-)
diff --git a/arrow-array/src/array/primitive_array.rs
b/arrow-array/src/array/primitive_array.rs
index b51f5f5186..667f816c6b 100644
--- a/arrow-array/src/array/primitive_array.rs
+++ b/arrow-array/src/array/primitive_array.rs
@@ -1360,21 +1360,30 @@ impl<T: ArrowPrimitiveType> std::fmt::Debug for
PrimitiveArray<T> {
// if the time zone is valid, construct a
DateTime<Tz> and format it as rfc3339
Ok(tz) => match as_datetime_with_timezone::<T>(v,
tz) {
Some(datetime) => write!(f, "{}",
datetime.to_rfc3339()),
- None => write!(f, "null"),
+ None => write!(
+ f,
+ "Cast error: Failed to convert {v} to
timestamp for {data_type}"
+ ),
},
// if the time zone is invalid, shows
NaiveDateTime with an error message
Err(_) => match as_datetime::<T>(v) {
Some(datetime) => {
write!(f, "{datetime:?} (Unknown Time Zone
'{tz_string}')")
}
- None => write!(f, "null"),
+ None => write!(
+ f,
+ "Cast error: Failed to convert {v} to
timestamp for {data_type}"
+ ),
},
}
}
// for Timestamp without TimeZone
None => match as_datetime::<T>(v) {
Some(datetime) => write!(f, "{datetime:?}"),
- None => write!(f, "null"),
+ None => write!(
+ f,
+ "Cast error: Failed to convert {v} to timestamp
for {data_type}"
+ ),
},
}
}
@@ -2127,6 +2136,60 @@ mod tests {
);
}
+ #[test]
+ fn test_timestamp_fmt_debug_out_of_range() {
+ // Include a true null into dataset to ensure we don't write that as
an error
+ let data = Int64Array::new(
+ vec![i64::MAX, i64::MIN, i64::MAX].into(),
+ Some(vec![true, true, false].into()),
+ );
+
+ let arr = data.reinterpret_cast::<TimestampSecondType>();
+ assert_eq!(
+ "PrimitiveArray<Timestamp(s)>
+[
+ Cast error: Failed to convert 9223372036854775807 to timestamp for
Timestamp(s),
+ Cast error: Failed to convert -9223372036854775808 to timestamp for
Timestamp(s),
+ null,
+]",
+ format!("{arr:?}")
+ );
+
+ let arr = data.reinterpret_cast::<TimestampMillisecondType>();
+ assert_eq!(
+ "PrimitiveArray<Timestamp(ms)>
+[
+ Cast error: Failed to convert 9223372036854775807 to timestamp for
Timestamp(ms),
+ Cast error: Failed to convert -9223372036854775808 to timestamp for
Timestamp(ms),
+ null,
+]",
+ format!("{arr:?}")
+ );
+
+ let arr = data.reinterpret_cast::<TimestampMicrosecondType>();
+ assert_eq!(
+ "PrimitiveArray<Timestamp(µs)>
+[
+ Cast error: Failed to convert 9223372036854775807 to timestamp for
Timestamp(µs),
+ Cast error: Failed to convert -9223372036854775808 to timestamp for
Timestamp(µs),
+ null,
+]",
+ format!("{arr:?}")
+ );
+
+ // Nanoseconds always in range
+ let arr = data.reinterpret_cast::<TimestampNanosecondType>();
+ assert_eq!(
+ "PrimitiveArray<Timestamp(ns)>
+[
+ 2262-04-11T23:47:16.854775807,
+ 1677-09-21T00:12:43.145224192,
+ null,
+]",
+ format!("{arr:?}")
+ );
+ }
+
#[test]
fn test_timestamp_utc_fmt_debug() {
let arr: PrimitiveArray<TimestampMillisecondType> =
@@ -2232,16 +2295,6 @@ mod tests {
)
}
- #[test]
- fn test_timestamp_micros_out_of_range() {
- // replicate the issue from
https://github.com/apache/arrow-datafusion/issues/3832
- let arr: PrimitiveArray<TimestampMicrosecondType> =
vec![9065525203050843594].into();
- assert_eq!(
- "PrimitiveArray<Timestamp(µs)>\n[\n null,\n]",
- format!("{arr:?}")
- )
- }
-
#[test]
fn test_primitive_array_builder() {
// Test building a primitive array with ArrayData builder and offset
