diff options
author | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2012-12-29 17:06:50 -0800 |
---|---|---|
committer | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2012-12-29 17:06:50 -0800 |
commit | 39dd953fd88e9aa7335603ab452d9c1bed4ba67a (patch) | |
tree | bfc1514717decc22a128ab10c4ebae9339f71034 /pyspark | |
parent | 59195c68ec37acf20d527189ed757397b273a207 (diff) | |
download | spark-39dd953fd88e9aa7335603ab452d9c1bed4ba67a.tar.gz spark-39dd953fd88e9aa7335603ab452d9c1bed4ba67a.tar.bz2 spark-39dd953fd88e9aa7335603ab452d9c1bed4ba67a.zip |
Add test for pyspark.RDD.saveAsTextFile().
Diffstat (limited to 'pyspark')
-rw-r--r-- | pyspark/pyspark/rdd.py | 9 |
1 files changed, 8 insertions, 1 deletions
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) |