Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/11509#discussion_r55117222 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InsertIntoHadoopFsRelation.scala --- @@ -101,45 +111,28 @@ private[sql] case class InsertIntoHadoopFsRelation( job.setOutputValueClass(classOf[InternalRow]) FileOutputFormat.setOutputPath(job, qualifiedOutputPath) - // A partitioned relation schema's can be different from the input logicalPlan, since - // partition columns are all moved after data column. We Project to adjust the ordering. - // TODO: this belongs in the analyzer. - val project = Project( - relation.schema.map(field => UnresolvedAttribute.quoted(field.name)), query) - val queryExecution = DataFrame(sqlContext, project).queryExecution + val partitionSet = AttributeSet(partitionColumns) + val dataColumns = query.output.filterNot(partitionSet.contains) + val queryExecution = DataFrame(sqlContext, query).queryExecution --- End diff -- Use QueryExecution directly instead of DataFrame here?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org