Fix bug in pyspark.serializers.batch; add .gitignore.

pyspark/.gitignore

+*.pyc
+docs/

pyspark/pyspark/rdd.py

@@ -695,7 +695,9 @@ def _test():
     import doctest
     from pyspark.context import SparkContext
     globs = globals().copy()
-    globs['sc'] = SparkContext('local[4]', 'PythonTest')
+    # The small batch size here ensures that we see multiple batches,
+    # even in these small test examples:
+    globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2)
     doctest.testmod(globs=globs)
     globs['sc'].stop()
 

pyspark/pyspark/serializers.py

@@ -24,7 +24,7 @@ def batched(iterator, batchSize):
         if count == batchSize:
             yield Batch(items)
             items = []
-            count = []
+            count = 0
     if items:
         yield Batch(items)