MaxGekk commented on a change in pull request #26102: [SPARK-29448][SQL] Support the `INTERVAL` type by Parquet datasource URL: https://github.com/apache/spark/pull/26102#discussion_r335142560
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala ########## @@ -325,6 +325,26 @@ private[parquet] class ParquetRowConverter( override def set(value: Any): Unit = updater.set(value.asInstanceOf[InternalRow].copy()) }) + case CalendarIntervalType + if parquetType.asPrimitiveType().getPrimitiveTypeName == FIXED_LEN_BYTE_ARRAY => + new ParquetPrimitiveConverter(updater) { + override def addBinary(value: Binary): Unit = { + assert( + value.length() == 12, + "Intervals are expected to be stored in 12-byte fixed len byte array, " + + s"but got a ${value.length()}-byte array.") + + val buf = value.toByteBuffer.order(ByteOrder.LITTLE_ENDIAN) + val milliseconds = buf.getInt + var microseconds = milliseconds * DateTimeUtils.MICROS_PER_MILLIS + val days = buf.getInt + val daysInUs = Math.multiplyExact(days, DateTimeUtils.MICROS_PER_DAY) Review comment: This can be fixed only if we change structure of `CalendarInterval` but such modifications are almost orthogonal to this PR. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org