Python: Pickling a dict with some unpicklable items

Question

I have an object gui_project which has an attribute .namespace, which is a namespace dict. (i.e. a dict from strings to objects.)

(This is

Answer 1

I would use the pickler's documented support for persistent object references. Persistent object references are objects that are referenced by the pickle but not stored in the pickle.

http://docs.python.org/library/pickle.html#pickling-and-unpickling-external-objects

ZODB has used this API for years, so it's very stable. When unpickling, you can replace the object references with anything you like. In your case, you would want to replace the object references with markers indicating that the objects could not be pickled.

You could start with something like this (untested):

import cPickle

def persistent_id(obj):
    if isinstance(obj, wxObject):
        return "filtered:wxObject"
    else:
        return None

class FilteredObject:
    def __init__(self, about):
        self.about = about
    def __repr__(self):
        return 'FilteredObject(%s)' % repr(self.about)

def persistent_load(obj_id):
    if obj_id.startswith('filtered:'):
        return FilteredObject(obj_id[9:])
    else:
        raise cPickle.UnpicklingError('Invalid persistent id')

def dump_filtered(obj, file):
    p = cPickle.Pickler(file)
    p.persistent_id = persistent_id
    p.dump(obj)

def load_filtered(file)
    u = cPickle.Unpickler(file)
    u.persistent_load = persistent_load
    return u.load()

Then just call dump_filtered() and load_filtered() instead of pickle.dump() and pickle.load(). wxPython objects will be pickled as persistent IDs, to be replaced with FilteredObjects at unpickling time.

You could make the solution more generic by filtering out objects that are not of the built-in types and have no __getstate__ method.

Update (15 Nov 2010): Here is a way to achieve the same thing with wrapper classes. Using wrapper classes instead of subclasses, it's possible to stay within the documented API.

from cPickle import Pickler, Unpickler, UnpicklingError


class FilteredObject:
    def __init__(self, about):
        self.about = about
    def __repr__(self):
        return 'FilteredObject(%s)' % repr(self.about)


class MyPickler(object):

    def __init__(self, file, protocol=0):
        pickler = Pickler(file, protocol)
        pickler.persistent_id = self.persistent_id
        self.dump = pickler.dump
        self.clear_memo = pickler.clear_memo

    def persistent_id(self, obj):
        if not hasattr(obj, '__getstate__') and not isinstance(obj,
            (basestring, int, long, float, tuple, list, set, dict)):
            return "filtered:%s" % type(obj)
        else:
            return None


class MyUnpickler(object):

    def __init__(self, file):
        unpickler = Unpickler(file)
        unpickler.persistent_load = self.persistent_load
        self.load = unpickler.load
        self.noload = unpickler.noload

    def persistent_load(self, obj_id):
        if obj_id.startswith('filtered:'):
            return FilteredObject(obj_id[9:])
        else:
            raise UnpicklingError('Invalid persistent id')


if __name__ == '__main__':
    from cStringIO import StringIO

    class UnpickleableThing(object):
        pass

    f = StringIO()
    p = MyPickler(f)
    p.dump({'a': 1, 'b': UnpickleableThing()})

    f.seek(0)
    u = MyUnpickler(f)
    obj = u.load()
    print obj

    assert obj['a'] == 1
    assert isinstance(obj['b'], FilteredObject)
    assert obj['b'].about