From 39dd953fd88e9aa7335603ab452d9c1bed4ba67a Mon Sep 17 00:00:00 2001
From: Josh Rosen <joshrosen@eecs.berkeley.edu>
Date: Sat, 29 Dec 2012 17:06:50 -0800
Subject: [PATCH] Add test for pyspark.RDD.saveAsTextFile().
---
pyspark/pyspark/rdd.py | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/pyspark/pyspark/rdd.py b/pyspark/pyspark/rdd.py
index 21dda31c4e..cbffb6cc1f 100644
--- a/pyspark/pyspark/rdd.py
+++ b/pyspark/pyspark/rdd.py
@@ -351,10 +351,17 @@ class RDD(object):
"""
return self.take(1)[0]
- # TODO: add test and fix for use with Batch
def saveAsTextFile(self, path):
"""
Save this RDD as a text file, using string representations of elements.
+
+ >>> tempFile = NamedTemporaryFile(delete=True)
+ >>> tempFile.close()
+ >>> sc.parallelize(range(10)).saveAsTextFile(tempFile.name)
+ >>> from fileinput import input
+ >>> from glob import glob
+ >>> ''.join(input(glob(tempFile.name + "/part-0000*")))
+ '0\\n1\\n2\\n3\\n4\\n5\\n6\\n7\\n8\\n9\\n'
"""
def func(iterator):
return (str(x).encode("utf-8") for x in iterator)
--
GitLab