cloud-fan commented on a change in pull request #29045: URL: https://github.com/apache/spark/pull/29045#discussion_r454515540
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala ########## @@ -116,47 +116,53 @@ object OrcUtils extends Logging { } /** - * Returns the requested column ids from the given ORC file. Column id can be -1, which means the - * requested column doesn't exist in the ORC file. Returns None if the given ORC file is empty. + * @return Returns the requested column ids from the given ORC file and Boolean flag to use actual + * schema or result schema. Column id can be -1, which means the requested column doesn't + * exist in the ORC file. Returns None if the given ORC file is empty. */ def requestedColumnIds( isCaseSensitive: Boolean, dataSchema: StructType, requiredSchema: StructType, reader: Reader, - conf: Configuration): Option[Array[Int]] = { + conf: Configuration): (Option[Array[Int]], Boolean) = { + var sendActualSchema = false val orcFieldNames = reader.getSchema.getFieldNames.asScala if (orcFieldNames.isEmpty) { Review comment: If we can't do column pruning for the _col case, shall we simply return None? e.g. ``` if (orcFieldNames.isEmpty || orcFieldNames.forall(_.startsWith("_col"))) { None } ``` ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org