[SPARK-9828] [PYSPARK] Mutable values should not be default arguments

Author: MechCoder <manojkumarsivaraj334@gmail.com>

Closes #8110 from MechCoder/spark-9828.

1 files changed, 4 insertions, 1 deletions

diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index fa8e0a0574..9ef60a7e2c 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -700,7 +700,7 @@ class RDD(object):
         return self.map(lambda x: (f(x), x)).groupByKey(numPartitions)
 
     @ignore_unicode_prefix
-    def pipe(self, command, env={}, checkCode=False):
+    def pipe(self, command, env=None, checkCode=False):
         """
         Return an RDD created by piping elements to a forked external process.
 
@@ -709,6 +709,9 @@ class RDD(object):
 
         :param checkCode: whether or not to check the return value of the shell command.
         """
+        if env is None:
+            env = dict()
+
         def func(iterator):
             pipe = Popen(
                 shlex.split(command), env=env, stdin=PIPE, stdout=PIPE)