From 078f3fbda860e2f5de34153c55dfc3fecb4256e9 Mon Sep 17 00:00:00 2001
From: Chia-Yung Su <chiayung@appier.com>
Date: Thu, 14 Aug 2014 10:43:08 -0700
Subject: [PATCH] [SPARK-3011][SQL] _temporary directory should be filtered out
by sqlContext.parquetFile
Author: Chia-Yung Su <chiayung@appier.com>
Closes #1924 from joesu/bugfix-spark3011 and squashes the following commits:
c7e44f2 [Chia-Yung Su] match syntax
f8fc32a [Chia-Yung Su] filter out tmp dir
---
.../main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
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 2867dc0a8b..37091bcf73 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
@@ -375,7 +375,8 @@ 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(0) == '.' || name == FileOutputCommitter.SUCCEEDED_FILE_NAME ||
+ name == FileOutputCommitter.TEMP_DIR_NAME
}
// NOTE (lian): Parquet "_metadata" file can be very slow if the file consists of lots of row
--
GitLab