Created
October 12, 2013 13:57
-
-
Save windreamer/6950270 to your computer and use it in GitHub Desktop.
Portable hash in Cython
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from libc.stdint cimport int64_t | |
cdef tuple_hash(obj): | |
cdef int64_t mul = 1000003, l = len(obj), value = 0x345678, v | |
for i in obj: | |
l -= 1 | |
v = portable_hash(i) | |
if v == -1: | |
return -1 | |
value = (value ^ v) * mul | |
mul += <int64_t> (82520 + l * 2) | |
value += 97531 | |
if value == -1: | |
value = -2 | |
return value | |
cdef string_hash(obj): | |
cdef char* s = obj | |
cdef char c | |
cdef int64_t l = len(obj), value | |
if l == 0: | |
return 0 | |
value = s[0] << 7 | |
for c in s: | |
value = (1000003 * value) ^ c | |
value ^= l | |
if value == -1: | |
value = -2 | |
return value | |
def portable_hash(obj): | |
if obj is None: | |
return 1315925605 | |
elif isinstance(obj, basestring): | |
return string_hash(obj) | |
elif isinstance(obj, tuple): | |
return tuple_hash(obj) | |
elif isinstance(obj, (int, long, float)): | |
return hash(obj) | |
else: | |
raise TypeError('unhashable by portable_hash') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment