1 files changed, 60 insertions, 0 deletions
diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py
index 03b31ae962..1b52c144df 100644
--- a/python/pyspark/serializers.py
+++ b/python/pyspark/serializers.py
@@ -65,6 +65,9 @@ from itertools import chain, izip, product
 import marshal
 import struct
 import sys
+import types
+import collections
+
 from pyspark import cloudpickle
 
 
@@ -267,6 +270,63 @@ class NoOpSerializer(FramedSerializer):
         return obj
 
 
+# Hook namedtuple, make it picklable
+
+__cls = {}
+
+
+def _restore(name, fields, value):
+    """ Restore an object of namedtuple"""
+    k = (name, fields)
+    cls = __cls.get(k)
+    if cls is None:
+        cls = collections.namedtuple(name, fields)
+        __cls[k] = cls
+    return cls(*value)
+
+
+def _hack_namedtuple(cls):
+    """ Make class generated by namedtuple picklable """
+    name = cls.__name__
+    fields = cls._fields
+    def __reduce__(self):
+        return (_restore, (name, fields, tuple(self)))
+    cls.__reduce__ = __reduce__
+    return cls
+
+
+def _hijack_namedtuple():
+    """ Hack namedtuple() to make it picklable """
+    global _old_namedtuple # or it will put in closure
+
+    def _copy_func(f):
+        return types.FunctionType(f.func_code, f.func_globals, f.func_name,
+                f.func_defaults, f.func_closure)
+
+    _old_namedtuple = _copy_func(collections.namedtuple)
+
+    def namedtuple(name, fields, verbose=False, rename=False):
+        cls = _old_namedtuple(name, fields, verbose, rename)
+        return _hack_namedtuple(cls)
+
+    # replace namedtuple with new one
+    collections.namedtuple.func_globals["_old_namedtuple"] = _old_namedtuple
+    collections.namedtuple.func_globals["_hack_namedtuple"] = _hack_namedtuple
+    collections.namedtuple.func_code = namedtuple.func_code
+
+    # hack the cls already generated by namedtuple
+    # those created in other module can be pickled as normal,
+    # so only hack those in __main__ module
+    for n, o in sys.modules["__main__"].__dict__.iteritems():
+        if (type(o) is type and o.__base__ is tuple
+            and hasattr(o, "_fields")
+            and "__reduce__" not in o.__dict__):
+            _hack_namedtuple(o) # hack inplace
+
+
+_hijack_namedtuple()
+
+
 class PickleSerializer(FramedSerializer):
     """
     Serializes objects using Python's cPickle serializer: