Github user mgaido91 commented on a diff in the pull request: https://github.com/apache/spark/pull/21950#discussion_r210841402 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PruneFileSourcePartitions.scala --- @@ -76,4 +78,16 @@ private[sql] object PruneFileSourcePartitions extends Rule[LogicalPlan] { op } } + + private def calcPartSize(catalogTable: Option[CatalogTable], sizeInBytes: Long): Long = { + val conf: SQLConf = SQLConf.get + val factor = conf.sizeDeserializationFactor + if (catalogTable.isDefined && factor != 1.0 && + // TODO: The serde check should be in a utility function, since it is also checked elsewhere + catalogTable.get.storage.serde.exists(s => s.contains("Parquet") || s.contains("Orc"))) { --- End diff -- I am not sure about this. We are saying that only Parquet/ORC files can be compressed?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org