[Python-ideas] Identity dicts and sets

Wed Jan 2 21:03:48 CET 2013

On Wed, 2 Jan 2013 11:43:47 -0800
Eli Bendersky <eliben at gmail.com> wrote:
> On Wed, Jan 2, 2013 at 6:01 AM, Serhiy Storchaka <storchaka at gmail.com>wrote:
>> > I propose to add new standard collection types: IdentityDict and
> > IdentitySet. They are almost same as ordinal dict and set, but uses
> > identity check instead of equality check (and id() or hash(id()) as a
> > hash). They will be useful for pickling, for implementing __sizeof__() for
> > compound types, and for other graph algorithms.
> >
> > Of course, they can be implemented using ordinal dicts:
> >
> > IdentityDict: key -> value as a dict: id(key) -> (key, value)
> > IdentitySet as a dict: id(value) -> value
> >
> > However implementing them directly in the core has advantages, it consumes
> > less memory and time, and more comfortable for use from C. IdentityDict and
> > IdentitySet implementations will share almost all code with implementations
> > of ordinal dict and set, only lookup function and metainformation will be
> > different. However dict and set already use a lookup function overloading.
> >
> >
> I agree that the data structures may be useful, but is there no way to some
> allow the customization of existing data structures instead, without losing
> performance? It's a shame to have another kind of dict just for this
> purpose.

The implementation kindof already exists in _pickle.c, IIRC (it's used
for the memo dict).
Regards
Antoine.