aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
authorPrashant Sharma <prashant.s@imaginea.com>2013-12-11 10:21:53 +0530
committerPrashant Sharma <prashant.s@imaginea.com>2013-12-11 10:21:53 +0530
commit603af51bb5257744ce0db28e7f10db6a2ba899ec (patch)
tree31ad611d8d56147ec90108d2b3a92d38eae4d150 /python/pyspark/rdd.py
parent17db6a9041d5e83d7b6fe47f9c36758d0613fcd6 (diff)
parentd2efe13574090e93c600adeacc7f6356bc196e6c (diff)
downloadspark-603af51bb5257744ce0db28e7f10db6a2ba899ec.tar.gz
spark-603af51bb5257744ce0db28e7f10db6a2ba899ec.tar.bz2
spark-603af51bb5257744ce0db28e7f10db6a2ba899ec.zip
Merge branch 'master' into akka-bug-fix
Conflicts: core/pom.xml core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala pom.xml project/SparkBuild.scala streaming/pom.xml yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocationHandler.scala
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py5
1 files changed, 4 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index d2cb5f191a..61720dcf1a 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -605,7 +605,10 @@ class RDD(object):
'0\\n1\\n2\\n3\\n4\\n5\\n6\\n7\\n8\\n9\\n'
"""
def func(split, iterator):
- return (str(x).encode("utf-8") for x in iterator)
+ for x in iterator:
+ if not isinstance(x, basestring):
+ x = unicode(x)
+ yield x.encode("utf-8")
keyed = PipelinedRDD(self, func)
keyed._bypass_serializer = True
keyed._jrdd.map(self.ctx._jvm.BytesToString()).saveAsTextFile(path)