You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2020/07/06 18:09:14 UTC
[GitHub] [spark] viirya commented on a change in pull request #28993: [SPARK-32168][SQL] Fix hidden partitioning correctness bug in SQL overwrite
viirya commented on a change in pull request #28993:
URL: https://github.com/apache/spark/pull/28993#discussion_r450395441
##########
File path: sql/catalyst/src/test/scala/org/apache/spark/sql/connector/InMemoryTable.scala
##########
@@ -78,10 +92,44 @@ class InMemoryTable(
throw new IllegalArgumentException(s"Unsupported type, ${dataType.simpleString}")
}
} else {
- value
+ (value, schema(index).dataType)
}
}
- partCols.map(fieldNames => extractor(fieldNames, schema, row))
+
+ partitioning.map {
+ case IdentityTransform(ref) =>
+ extractor(ref.fieldNames, schema, row)._1
+ case YearsTransform(ref) =>
+ extractor(ref.fieldNames, schema, row) match {
+ case (days: Int, DateType) =>
+ ChronoUnit.YEARS.between(EPOCH_LOCAL_DATE, DateTimeUtils.daysToLocalDate(days))
+ case (micros: Long, TimestampType) =>
+ val localDate = DateTimeUtils.microsToInstant(micros).atZone(UTC).toLocalDate
+ ChronoUnit.YEARS.between(EPOCH_LOCAL_DATE, localDate)
+ }
+ case MonthsTransform(ref) =>
+ extractor(ref.fieldNames, schema, row) match {
+ case (days: Int, DateType) =>
+ ChronoUnit.MONTHS.between(EPOCH_LOCAL_DATE, DateTimeUtils.daysToLocalDate(days))
+ case (micros: Long, TimestampType) =>
+ val localDate = DateTimeUtils.microsToInstant(micros).atZone(UTC).toLocalDate
+ ChronoUnit.MONTHS.between(EPOCH_LOCAL_DATE, localDate)
+ }
+ case DaysTransform(ref) =>
+ extractor(ref.fieldNames, schema, row) match {
+ case (days, DateType) =>
+ days
+ case (micros: Long, TimestampType) =>
+ ChronoUnit.DAYS.between(Instant.EPOCH, DateTimeUtils.microsToInstant(micros))
+ }
+ case HoursTransform(ref) =>
+ extractor(ref.fieldNames, schema, row) match {
+ case (micros: Long, TimestampType) =>
+ ChronoUnit.HOURS.between(Instant.EPOCH, DateTimeUtils.microsToInstant(micros))
+ }
+ case BucketTransform(numBuckets, ref) =>
+ (extractor(ref.fieldNames, schema, row).hashCode() & Integer.MAX_VALUE) % numBuckets
Review comment:
nit: `extractor(ref.fieldNames, schema, row)._1.hashCode()`?
----------------------------------------------------------------
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:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org