diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py index 1b52c144df0876b413fb8acdf71352572b45c592..a10f85b55ad301e8874c82c3249f4ab1ce3cf94f 100644 --- a/python/pyspark/serializers.py +++ b/python/pyspark/serializers.py @@ -297,8 +297,11 @@ def _hack_namedtuple(cls): def _hijack_namedtuple(): """ Hack namedtuple() to make it picklable """ - global _old_namedtuple # or it will put in closure + # hijack only one time + if hasattr(collections.namedtuple, "__hijack"): + return + 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) @@ -313,6 +316,7 @@ def _hijack_namedtuple(): collections.namedtuple.func_globals["_old_namedtuple"] = _old_namedtuple collections.namedtuple.func_globals["_hack_namedtuple"] = _hack_namedtuple collections.namedtuple.func_code = namedtuple.func_code + collections.namedtuple.__hijack = 1 # hack the cls already generated by namedtuple # those created in other module can be pickled as normal,