Github user nongli commented on a diff in the pull request: https://github.com/apache/spark/pull/9774#discussion_r45257861 --- Diff: core/src/main/scala/org/apache/spark/rdd/SqlNewHadoopRDD.scala --- @@ -150,9 +155,30 @@ private[spark] class SqlNewHadoopRDD[V: ClassTag]( configurable.setConf(conf) case _ => } - private[this] var reader = format.createRecordReader( - split.serializableHadoopSplit.value, hadoopAttemptContext) - reader.initialize(split.serializableHadoopSplit.value, hadoopAttemptContext) + private[this] var reader: RecordReader[Void, V] = null + + /** + * If the format is ParquetInputFormat, try to create the optimized RecordReader. If this + * fails (for example, unsupported schema), try with the normal reader. + * TODO: plumb this through a different way? + */ + if (enableUnsafeRowParquetReader && + format.getClass.getName == "org.apache.parquet.hadoop.ParquetInputFormat") { + reader = Utils.classForName( + "org.apache.spark.sql.execution.datasources.parquet.UnsafeRowParquetRecordReader") --- End diff -- This thing is in the wrong package. I'll clean this up when I move this class.
--- 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