beliefer commented on a change in pull request #34495:
URL: https://github.com/apache/spark/pull/34495#discussion_r744243576
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala
##########
@@ -370,6 +370,31 @@ private[parquet] class ParquetRowConverter(
}
}
+ // The converter doesn't support the TimestampLTZ Parquet type and
TimestampNTZ Catalyst type.
+ // This is to avoid mistakes in reading the timestamp values.
+ case TimestampNTZType
+ if parquetType.asPrimitiveType().getPrimitiveTypeName == INT64 &&
+
parquetType.getLogicalTypeAnnotation.isInstanceOf[TimestampLogicalTypeAnnotation]
&&
+ !parquetType.getLogicalTypeAnnotation
+ .asInstanceOf[TimestampLogicalTypeAnnotation].isAdjustedToUTC &&
+ parquetType.getLogicalTypeAnnotation
+ .asInstanceOf[TimestampLogicalTypeAnnotation].getUnit ==
TimeUnit.MICROS =>
+ new ParquetPrimitiveConverter(updater)
+
+ case TimestampNTZType
+ if parquetType.asPrimitiveType().getPrimitiveTypeName == INT64 &&
+
parquetType.getLogicalTypeAnnotation.isInstanceOf[TimestampLogicalTypeAnnotation]
&&
+ !parquetType.getLogicalTypeAnnotation
+ .asInstanceOf[TimestampLogicalTypeAnnotation].isAdjustedToUTC &&
+ parquetType.getLogicalTypeAnnotation
+ .asInstanceOf[TimestampLogicalTypeAnnotation].getUnit ==
TimeUnit.MILLIS =>
Review comment:
The condition seems the same as above，could you extract them？
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetWriteSupport.scala
##########
@@ -223,6 +223,12 @@ class ParquetWriteSupport extends
WriteSupport[InternalRow] with Logging {
recordConsumer.addLong(millis)
}
+ case TimestampNTZType =>
+ // For TimestampNTZType column, Spark always output as INT64 with
Timestamp annotation in
+ // MICROS time unit.
+ (row: SpecializedGetters, ordinal: Int) =>
+ recordConsumer.addLong(row.getLong(ordinal))
Review comment:
(row: SpecializedGetters, ordinal: Int) =>
recordConsumer.addLong(row.getLong(ordinal))
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
