Computing an md5 hash of a data structure

Question

I want to compute an md5 hash not of a string, but of an entire data structure. I understand the mechanics of a way to do this (dispatch on the type of the value, canonical

Answer 1

I ended up writing it myself as I thought I would have to:

class Hasher(object):
    """Hashes Python data into md5."""
    def __init__(self):
        self.md5 = md5()

    def update(self, v):
        """Add `v` to the hash, recursively if needed."""
        self.md5.update(str(type(v)))
        if isinstance(v, basestring):
            self.md5.update(v)
        elif isinstance(v, (int, long, float)):
            self.update(str(v))
        elif isinstance(v, (tuple, list)):
            for e in v:
                self.update(e)
        elif isinstance(v, dict):
            keys = v.keys()
            for k in sorted(keys):
                self.update(k)
                self.update(v[k])
        else:
            for k in dir(v):
                if k.startswith('__'):
                    continue
                a = getattr(v, k)
                if inspect.isroutine(a):
                    continue
                self.update(k)
                self.update(a)

    def digest(self):
        """Retrieve the digest of the hash."""
        return self.md5.digest()