import zlib def levenshtein(a,b): "Calculates the Levenshtein distance between a and b." n, m = len(a), len(b) if n > m: # Make sure n <= m, to use O(min(n,m)) space a,b = b,a n,m = m,n current = range(n+1) for i in range(1,m+1): previous, current = current, [i]+[0]*n for j in range(1,n+1): add, delete = previous[j]+1, current[j-1]+1 change = previous[j-1] if a[j-1] != b[i-1]: change = change + 1 current[j] = min(add, delete, change) return current[n] def compress(x): c = zlib.compress(x, 9) # strip headers FLG = c[1] if ord(FLG) & (1 << 5): # DICTID c = c[6:] else: c = c[2:] return c[:-4] def dist(a, b): return min(levenshtein(a, b), levenshtein(compress(a), compress(b))) print dist("a"*8, "a"*8) print dist("apple", "appel") print dist("apple", "bannana") print dist("a"*100, "b"*100) print dist("the quick brown fox jumped over the fence", "the quic brown fox jumped over the fence") print dist("Robert", "Roberto")