diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 172ed85fab9267b7cfffbec8c0474701c9faf23f..a9fec17a9da69fb4ce1f7153d4ee31e60a6cb2f8 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -399,7 +399,7 @@ class RDD(object): >>> sc.parallelize(range(10)).saveAsTextFile(tempFile.name) >>> from fileinput import input >>> from glob import glob - >>> ''.join(input(glob(tempFile.name + "/part-0000*"))) + >>> ''.join(sorted(input(glob(tempFile.name + "/part-0000*")))) '0\\n1\\n2\\n3\\n4\\n5\\n6\\n7\\n8\\n9\\n' """ def func(split, iterator):