Github user xuanyuanking commented on a diff in the pull request: https://github.com/apache/spark/pull/14957#discussion_r84592806 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala --- @@ -97,7 +99,15 @@ object FileSourceStrategy extends Strategy with Logging { dataColumns .filter(requiredAttributes.contains) .filterNot(partitionColumns.contains) - val outputSchema = readDataColumns.toStructType + val outputSchema = if (fsRelation.sqlContext.conf.isParquetNestColumnPruning + && fsRelation.fileFormat.isInstanceOf[ParquetFileFormat]) { + val totalSchema = readDataColumns.toStructType + val prunedSchema = StructType( + generateStructFieldsContainsNesting(projects, totalSchema)) + // Merge schema in same StructType and merge with filterAttributes + prunedSchema.fields.map(f => StructType(Array(f))).reduceLeft(_ merge _) + .merge(filterAttributes.toSeq.toStructType) + } else readDataColumns.toStructType --- End diff -- fix done
--- 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