tustvold commented on code in PR #5603:
URL: https://github.com/apache/arrow-datafusion/pull/5603#discussion_r1137254192
##########
datafusion/common/src/scalar.rs:
##########
@@ -563,46 +843,154 @@ macro_rules! get_sign {
};
}
+#[derive(Clone, Copy)]
+enum IntervalMode {
+ Milli,
+ Nano,
+}
+
+/// This function computes subtracts `rhs_ts` from `lhs_ts`, taking timezones
+/// into account when given. Units of the resulting interval is specified by
+/// the argument `mode`.
+/// The default behavior of Datafusion is the following:
+/// - When subtracting timestamps at seconds/milliseconds precision, the output
+/// interval will have the type [`IntervalDayTimeType`].
+/// - When subtracting timestamps at microseconds/nanoseconds precision, the
+/// output interval will have the type [`IntervalMonthDayNanoType`].
+fn ts_sub_to_interval(
+ lhs_ts: i64,
+ rhs_ts: i64,
+ lhs_tz: &Option<String>,
+ rhs_tz: &Option<String>,
+ mode: IntervalMode,
+) -> Result<ScalarValue, DataFusionError> {
+ let lhs_dt = with_timezone_to_naive_datetime(lhs_ts, lhs_tz, mode)?;
+ let rhs_dt = with_timezone_to_naive_datetime(rhs_ts, rhs_tz, mode)?;
+ let delta_secs = lhs_dt.signed_duration_since(rhs_dt);
+
+ match mode {
+ IntervalMode::Milli => {
+ let as_millisecs = delta_secs.num_milliseconds();
+ Ok(ScalarValue::IntervalDayTime(Some(
+ IntervalDayTimeType::make_value(
+ (as_millisecs / MILLISECS_IN_ONE_DAY) as i32,
+ (as_millisecs % MILLISECS_IN_ONE_DAY) as i32,
+ ),
+ )))
+ }
+ IntervalMode::Nano => {
+ let as_nanosecs = delta_secs.num_nanoseconds().ok_or_else(|| {
+ DataFusionError::Execution(String::from(
+ "Can not compute timestamp differences with nanosecond
precision",
+ ))
+ })?;
+ Ok(ScalarValue::IntervalMonthDayNano(Some(
+ IntervalMonthDayNanoType::make_value(
+ 0,
+ (as_nanosecs / NANOSECS_IN_ONE_DAY) as i32,
+ as_nanosecs % NANOSECS_IN_ONE_DAY,
+ ),
+ )))
+ }
+ }
+}
+
+/// This function creates the [`NaiveDateTime`] object corresponding to the
+/// given timestamp using the units (tick size) implied by argument `mode`.
+#[inline]
+fn with_timezone_to_naive_datetime(
Review Comment:
> corresponding UTC offsets of these timestamps
The timezones may not be of the form `"+02:00"` they might also be
`"America/Los_Angeles"` in which case the offset to UTC depends on the date in
question. See
https://github.com/apache/arrow-rs/pull/3801/files#diff-5f92a7816bbae9b685c2f85ab84a268b85246bfaa14272c5afd339810ad471f3R22
My suggestion is to use the chrono `DateTime` abstraction to handle applying
the offset correctly, along with `Tz` to handle parsing the timezone string
correctly.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
