From a7f8a4f5ee757450ce8d4028021441435081cf53 Mon Sep 17 00:00:00 2001 From: Michael Armbrust <michael@databricks.com> Date: Thu, 14 Aug 2014 13:00:21 -0700 Subject: [PATCH] Revert [SPARK-3011][SQL] _temporary directory should be filtered out by sqlContext.parquetFile Reverts #1924 due to build failures with hadoop 0.23. Author: Michael Armbrust <michael@databricks.com> Closes #1949 from marmbrus/revert1924 and squashes the following commits: 6bff940 [Michael Armbrust] Revert "[SPARK-3011][SQL] _temporary directory should be filtered out by sqlContext.parquetFile" --- .../main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala index b0579f76da..c79a9ac2da 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala @@ -378,8 +378,7 @@ private[parquet] object ParquetTypesConverter extends Logging { val children = fs.listStatus(path).filterNot { status => val name = status.getPath.getName - name(0) == '.' || name == FileOutputCommitter.SUCCEEDED_FILE_NAME || - name == FileOutputCommitter.TEMP_DIR_NAME + name(0) == '.' || name == FileOutputCommitter.SUCCEEDED_FILE_NAME } // NOTE (lian): Parquet "_metadata" file can be very slow if the file consists of lots of row -- GitLab