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.py4
1 files changed, 3 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 240381e5ba..c708b69cc1 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -1191,7 +1191,9 @@ class RDD(object):
for x in iterator:
if not isinstance(x, basestring):
x = unicode(x)
- yield x.encode("utf-8")
+ if isinstance(x, unicode):
+ x = x.encode("utf-8")
+ yield x
keyed = self.mapPartitionsWithIndex(func)
keyed._bypass_serializer = True
keyed._jrdd.map(self.ctx._jvm.BytesToString()).saveAsTextFile(path)