MaxGekk commented on a change in pull request #27915: [WIP][SPARK-31159][SQL]
Rebase date/timestamp from/to Julian calendar in parquet
URL: https://github.com/apache/spark/pull/27915#discussion_r392953812
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala
##########
@@ -974,4 +974,102 @@ object DateTimeUtils {
}
}.mkString("'")
}
+
+ /**
+ * Converts the given microseconds to a local date-time in UTC time zone in
Proleptic Gregorian
+ * calendar, interprets the result as a local date-time in Julian calendar
in UTC time zone.
+ * And takes microseconds since the epoch from the Julian timestamp.
+ *
+ * @param micros The number of microseconds since the epoch
'1970-01-01T00:00:00Z'.
+ * @return The rebased microseconds since the epoch in Julian calendar.
+ */
+ def rebaseGregorianToJulianMicros(micros: Long): Long = {
+ val ldt =
microsToInstant(micros).atZone(ZoneId.systemDefault).toLocalDateTime
+ val cal = new Calendar.Builder()
+ // `gregory` is a hybrid calendar that supports both
+ // the Julian and Gregorian calendar systems
+ .setCalendarType("gregory")
+ .setDate(ldt.getYear, ldt.getMonthValue - 1, ldt.getDayOfMonth)
+ .setTimeOfDay(ldt.getHour, ldt.getMinute, ldt.getSecond)
+ .build()
+ millisToMicros(cal.getTimeInMillis) + ldt.get(ChronoField.MICRO_OF_SECOND)
+ }
+
+ /**
+ * Converts the given microseconds to a local date-time in UTC time zone in
Julian calendar,
+ * interprets the result as a local date-time in Proleptic Gregorian
calendar in UTC time zone.
+ * And takes microseconds since the epoch from the Gregorian timestamp.
+ *
+ * @param micros The number of microseconds since the epoch
'1970-01-01T00:00:00Z'.
+ * @return The rebased microseconds since the epoch in Proleptic Gregorian
calendar.
+ */
+ def rebaseJulianToGregorianMicros(micros: Long): Long = {
+ val cal = new Calendar.Builder()
+ // `gregory` is a hybrid calendar that supports both
+ // the Julian and Gregorian calendar systems
+ .setCalendarType("gregory")
+ .setInstant(microsToMillis(micros))
+ .build()
+ val localDateTime = LocalDateTime.of(
+ cal.get(Calendar.YEAR),
+ cal.get(Calendar.MONTH) + 1,
+ cal.get(Calendar.DAY_OF_MONTH),
+ cal.get(Calendar.HOUR_OF_DAY),
+ cal.get(Calendar.MINUTE),
+ cal.get(Calendar.SECOND),
+ (Math.floorMod(micros, MICROS_PER_SECOND) * NANOS_PER_MICROS).toInt)
+ instantToMicros(localDateTime.atZone(ZoneId.systemDefault).toInstant)
+ }
+
+ /**
+ * Converts the given number of days since the epoch day 1970-01-01 to
+ * a local date in Julian calendar, interprets the result as a local
+ * date in Proleptic Gregorian calendar, and take the number of days
+ * since the epoch from the Gregorian date.
+ *
+ * @param days The number of days since the epoch in Julian calendar.
+ * @return The rebased number of days in Gregorian calendar.
+ */
+ def rebaseJulianToGregorianDays(days: Int): Int = {
+ val utcCal = new Calendar.Builder()
+ // `gregory` is a hybrid calendar that supports both
+ // the Julian and Gregorian calendar systems
+ .setCalendarType("gregory")
+ .setTimeZone(TimeZoneUTC)
Review comment:
We can use particular time zone here because the conversion of "logical"
days is independent from time zone, actually. `UTC` is selected to avoid the
problem of rounding micros to/from days because zone offset in UTC is 0.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
