How to limit the size of a dictionary?

Question

Python 2.7 and 3.1 have OrderedDict and there are pure-Python implementations for earlier Pythons.

from collections import OrderedDict

class LimitedSizeDict(OrderedDict):
    def __init__(self, *args, **kwds):
        self.size_limit = kwds.pop("size_limit", None)
        OrderedDict.__init__(self, *args, **kwds)
        self._check_size_limit()

    def __setitem__(self, key, value):
        OrderedDict.__setitem__(self, key, value)
        self._check_size_limit()

    def _check_size_limit(self):
        if self.size_limit is not None:
            while len(self) > self.size_limit:
                self.popitem(last=False)

You would also have to override other methods that can insert items, such as update. The primary use of OrderedDict is so you can control what gets popped easily, otherwise a normal dict would work.

cachetools will provide you nice implementation of Mapping Hashes that does this (and it works on python 2 and 3).

Excerpt of the documentation:

For the purpose of this module, a cache is a mutable mapping of a fixed maximum size. When the cache is full, i.e. by adding another item the cache would exceed its maximum size, the cache must choose which item(s) to discard based on a suitable cache algorithm.

Here's a simple, no-LRU Python 2.6+ solution (in older Pythons you could do something similar with UserDict.DictMixin, but in 2.6 and better that's not recommended, and the ABCs from collections are preferable anyway...):

import collections

class MyDict(collections.MutableMapping):
    def __init__(self, maxlen, *a, **k):
        self.maxlen = maxlen
        self.d = dict(*a, **k)
        while len(self) > maxlen:
            self.popitem()
    def __iter__(self):
        return iter(self.d)
    def __len__(self):
        return len(self.d)
    def __getitem__(self, k):
        return self.d[k]
    def __delitem__(self, k):
        del self.d[k]
    def __setitem__(self, k, v):
        if k not in self and len(self) == self.maxlen:
            self.popitem()
        self.d[k] = v

d = MyDict(5)
for i in range(10):
    d[i] = i
    print(sorted(d))

As other answers mentioned, you probably don't want to subclass dict -- the explicit delegation to self.d is unfortunately boilerplatey but it does guarantee that every other method is properly supplied by collections.MutableMapping.

Here is a simple and efficient LRU cache written with dirt simple Python code that runs on any python version 1.5.2 or later:

class LRU_Cache:

    def __init__(self, original_function, maxsize=1000):
        self.original_function = original_function
        self.maxsize = maxsize
        self.mapping = {}

        PREV, NEXT, KEY, VALUE = 0, 1, 2, 3         # link fields
        self.head = [None, None, None, None]        # oldest
        self.tail = [self.head, None, None, None]   # newest
        self.head[NEXT] = self.tail

    def __call__(self, *key):
        PREV, NEXT = 0, 1
        mapping, head, tail = self.mapping, self.head, self.tail

        link = mapping.get(key, head)
        if link is head:
            value = self.original_function(*key)
            if len(mapping) >= self.maxsize:
                old_prev, old_next, old_key, old_value = head[NEXT]
                head[NEXT] = old_next
                old_next[PREV] = head
                del mapping[old_key]
            last = tail[PREV]
            link = [last, tail, key, value]
            mapping[key] = last[NEXT] = tail[PREV] = link
        else:
            link_prev, link_next, key, value = link
            link_prev[NEXT] = link_next
            link_next[PREV] = link_prev
            last = tail[PREV]
            last[NEXT] = tail[PREV] = link
            link[PREV] = last
            link[NEXT] = tail
        return value

if __name__ == '__main__':
    p = LRU_Cache(pow, maxsize=3)
    for i in [1,2,3,4,5,3,1,5,1,1]:
        print(i, p(i, 2))

You can create a custom dictionary class by subclassing dict. In your case, you would have to override __setitem__ to have check your own length and delete something if the limit is recahed. The following example would print the current lenght after every insertion:

class mydict(dict):
    def __setitem__(self, k, v):
        dict.__setitem__(self, k, v)
        print len(self)

d = mydict()
d['foo'] = 'bar'
d['bar'] = 'baz'