aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py6
1 files changed, 3 insertions, 3 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index a59778c721..3a1c56af5b 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -537,8 +537,8 @@ class RDD(object):
"""
Return an RDD created by piping elements to a forked external process.
- >>> sc.parallelize([1, 2, 3]).pipe('cat').collect()
- ['1', '2', '3']
+ >>> sc.parallelize(['1', '2', '', '3']).pipe('cat').collect()
+ ['1', '2', '', '3']
"""
def func(iterator):
pipe = Popen(shlex.split(command), env=env, stdin=PIPE, stdout=PIPE)
@@ -547,7 +547,7 @@ class RDD(object):
out.write(str(obj).rstrip('\n') + '\n')
out.close()
Thread(target=pipe_objs, args=[pipe.stdin]).start()
- return (x.rstrip('\n') for x in pipe.stdout)
+ return (x.rstrip('\n') for x in iter(pipe.stdout.readline, ''))
return self.mapPartitions(func)
def foreach(self, f):