From 3d278f7a8fde294c361504fb46145df41928f7f1 Mon Sep 17 00:00:00 2001 From: Cheng Lian Date: Mon, 18 May 2015 10:22:56 +0800 Subject: [PATCH] Fixes a bug when reading a single Parquet data file --- .../scala/org/apache/spark/sql/sources/interfaces.scala | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala b/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala index da9fc8bca77a5..894579abf1991 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala @@ -478,8 +478,11 @@ abstract class HadoopFsRelation private[sql](maybePartitionSpec: Option[Partitio requiredColumns: Array[String], filters: Array[Filter], inputPaths: Array[String]): RDD[Row] = { - val inputStatuses = inputPaths.flatMap { path => - fileStatusCache.leafFiles.values.filter(_.getPath.getParent == new Path(path)) + val inputStatuses = inputPaths.flatMap { input => + fileStatusCache.leafFiles.values.filter { status => + val path = new Path(input) + status.getPath.getParent == path || status.getPath == path + } } buildScan(requiredColumns, filters, inputStatuses) }