Github user mallman commented on a diff in the pull request: https://github.com/apache/spark/pull/22357#discussion_r216714387 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaPruning.scala --- @@ -110,7 +110,17 @@ private[sql] object ParquetSchemaPruning extends Rule[LogicalPlan] { val projectionRootFields = projects.flatMap(getRootFields) val filterRootFields = filters.flatMap(getRootFields) - (projectionRootFields ++ filterRootFields).distinct + // Kind of expressions don't need to access any fields of a root fields, e.g., `IsNotNull`. + // For them, if there are any nested fields accessed in the query, we don't need to add root + // field access of above expressions. + // For example, for a query `SELECT name.first FROM contacts WHERE name IS NOT NULL`, + // we don't need to read nested fields of `name` struct other than `first` field. --- End diff -- Yeah, I'm okay with leaving it as-is.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org