[SPARK-10542] [PYSPARK] fix serialize namedtuple

Author: Davies Liu <davies@databricks.com>

Closes #8707 from davies/fix_namedtuple.

python/pyspark/cloudpickle.py

@@ -350,6 +350,11 @@ def save_global(self, obj, name=None, pack=struct.pack):
             if new_override:
                 d['__new__'] = obj.__new__
 
+            # workaround for namedtuple (hijacked by PySpark)
+            if getattr(obj, '_is_namedtuple_', False):
+                self.save_reduce(_load_namedtuple, (obj.__name__, obj._fields))
+                return
+
             self.save(_load_class)
             self.save_reduce(typ, (obj.__name__, obj.__bases__, {"__doc__": obj.__doc__}), obj=obj)
             d.pop('__doc__', None)
@@ -382,7 +387,7 @@ def save_instancemethod(self, obj):
             self.save_reduce(types.MethodType, (obj.__func__, obj.__self__), obj=obj)
         else:
             self.save_reduce(types.MethodType, (obj.__func__, obj.__self__, obj.__self__.__class__),
-                         obj=obj)
+                             obj=obj)
     dispatch[types.MethodType] = save_instancemethod
 
     def save_inst(self, obj):
@@ -744,6 +749,14 @@ def _load_class(cls, d):
     return cls
 
 
+def _load_namedtuple(name, fields):
+    """
+    Loads a class generated by namedtuple
+    """
+    from collections import namedtuple
+    return namedtuple(name, fields)
+
+
 """Constructors for 3rd party libraries
 Note: These can never be renamed due to client compatibility issues"""
 

python/pyspark/serializers.py

@@ -359,6 +359,7 @@ def _hack_namedtuple(cls):
     def __reduce__(self):
         return (_restore, (name, fields, tuple(self)))
     cls.__reduce__ = __reduce__
+    cls._is_namedtuple_ = True
     return cls
 
 

python/pyspark/tests.py

@@ -218,6 +218,11 @@ def test_namedtuple(self):
         p2 = loads(dumps(p1, 2))
         self.assertEqual(p1, p2)
 
+        from pyspark.cloudpickle import dumps
+        P2 = loads(dumps(P))
+        p3 = P2(1, 3)
+        self.assertEqual(p1, p3)
+
     def test_itemgetter(self):
         from operator import itemgetter
         ser = CloudPickleSerializer()