Skip to content

Canonicalising pack #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
stephenpascoe wants to merge 2 commits into from
Closed

Canonicalising pack #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8d32bef
Option to create canonical packing by sorting dictionary keys.
Oct 23, 2011
ecdbd45
Test case for canonicalise option.
Oct 23, 2011
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 23 additions & 10 deletions msgpack/_msgpack.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,7 @@ cdef class Packer(object):
cdef object _berrors
cdef char *encoding
cdef char *unicode_errors
cdef bool _canonical

def __cinit__(self):
cdef int buf_size = 1024*1024
Expand All @@ -59,7 +60,8 @@ cdef class Packer(object):
self.pk.buf_size = buf_size
self.pk.length = 0

def __init__(self, default=None, encoding='utf-8', unicode_errors='strict'):
def __init__(self, default=None, encoding='utf-8', unicode_errors='strict',
canonical=False):
if default is not None:
if not PyCallable_Check(default):
raise TypeError("default must be a callable.")
Expand All @@ -79,6 +81,8 @@ cdef class Packer(object):
self._berrors = unicode_errors
self.unicode_errors = PyBytes_AsString(self._berrors)

self._canonical = canonical

def __dealloc__(self):
free(self.pk.buf);

Expand Down Expand Up @@ -131,11 +135,20 @@ cdef class Packer(object):
d = o
ret = msgpack_pack_map(&self.pk, len(d))
if ret == 0:
for k,v in d.items():
ret = self._pack(k, nest_limit-1)
if ret != 0: break
ret = self._pack(v, nest_limit-1)
if ret != 0: break
if self._canonical:
# Unfortunately can't use d.items() because a closure would
# be required
for k in sorted(d.keys()):
ret = self._pack(k, nest_limit-1)
if ret != 0: break
ret = self._pack(d[k], nest_limit-1)
if ret != 0: break
else:
for k,v in d.items():
ret = self._pack(k, nest_limit-1)
if ret != 0: break
ret = self._pack(v, nest_limit-1)
if ret != 0: break
elif PySequence_Check(o):
ret = msgpack_pack_array(&self.pk, len(o))
if ret == 0:
Expand All @@ -159,16 +172,16 @@ cdef class Packer(object):
return buf


def pack(object o, object stream, default=None, encoding='utf-8', unicode_errors='strict'):
def pack(object o, object stream, default=None, encoding='utf-8', unicode_errors='strict', canonical=False):
"""
pack an object `o` and write it to stream)."""
packer = Packer(default=default, encoding=encoding, unicode_errors=unicode_errors)
packer = Packer(default=default, encoding=encoding, unicode_errors=unicode_errors, canonical=canonical)
stream.write(packer.pack(o))

def packb(object o, default=None, encoding='utf-8', unicode_errors='strict'):
def packb(object o, default=None, encoding='utf-8', unicode_errors='strict', canonical=False):
"""
pack o and return packed bytes."""
packer = Packer(default=default, encoding=encoding, unicode_errors=unicode_errors)
packer = Packer(default=default, encoding=encoding, unicode_errors=unicode_errors, canonical=canonical)
return packer.pack(o)


Expand Down
27 changes: 27 additions & 0 deletions test/test_canonical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@

from nose.tools import *

from msgpack import packb


def test_canonical():
# This test serialises a dictionary 3 times.
# Without canonicalisation each serialisation would be different
# (on Python 2.6 anyway)
d = {'year': 1, 'month': 2, 'day': 3}
s1 = packb(d, canonical=True)

for i in range(30):
d[i] = i
for i in range(30):
del d[i]
s2 = packb(d, canonical=True)

d = dict(d)
s3 = packb(d, canonical=True)

eq_(s1, s2, s3)

if __name__ == '__main__':
from nose import main
main()