aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/serializers.py
diff options
context:
space:
mode:
Diffstat (limited to 'python/pyspark/serializers.py')
-rw-r--r--python/pyspark/serializers.py4
1 files changed, 4 insertions, 0 deletions
diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py
index bd08c9a6d2..b8bda83517 100644
--- a/python/pyspark/serializers.py
+++ b/python/pyspark/serializers.py
@@ -181,6 +181,10 @@ class BatchedSerializer(Serializer):
def _batched(self, iterator):
if self.batchSize == self.UNLIMITED_BATCH_SIZE:
yield list(iterator)
+ elif hasattr(iterator, "__len__") and hasattr(iterator, "__getslice__"):
+ n = len(iterator)
+ for i in xrange(0, n, self.batchSize):
+ yield iterator[i: i + self.batchSize]
else:
items = []
count = 0