homepage

Eli Bendersky wrote on Tue, Jan 01, 2013 at 15:54:00 +0000:
> Why did you change the class name, by the way, I don't think it's
> a valid change at least for 3.3 in terms of backwards compatibility.
> 
With unmodified tip of 3.4:
 >>> import pickle, xml.etree.ElementTree as ET
 >>> pickle.dumps(ET.Element('foo'))
 Traceback (most recent call last):
 File "<stdin>", line 1, in <module>
 _pickle.PicklingError: Can't pickle <class 'Element'>: attribute lookup builtins.Element failed
I added the "_elementtree" to the tp_name in order to bypass the above
error. Module-qualified names were in use elsewhere (including by
_elementtree._element_iterator) so it seemed reasonable. I'll defer to
you about compatibility implications of this change.
> Regarding that compatibility, and even easier idea would be for the
> C pickle to return the same __dict__ implicitly gathered from the
> Python version, and then only one version of the unpickle is required.
That makes sense. But going forward it might be even better to define
an explicit __reduce__/__getstate__ for the Python version too, so if
the instance dict grows new members, they won't get serialised
unintentionally. (This consideration is also why C code in the latest
patch makes some effort to notice unknown args in the dict.)