1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
# -*- coding:utf-8 -*-
## c14n.py
##
## Copyright (C) 2007-2008 Brendan Taylor <whateley AT gmail.com>
##
## This file is part of Gajim.
##
## Gajim is free software; you can redistribute it and/or modify
## it under the terms of the GNU General Public License as published
## by the Free Software Foundation; version 3 only.
##
## Gajim is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License
## along with Gajim. If not, see <http://www.gnu.org/licenses/>.
##
"""
XML canonicalisation methods (for XEP-0116)
"""
def c14n(node, is_buggy):
s = "<" + node.name
if node.namespace:
if not node.parent or node.parent.namespace != node.namespace:
s += ' xmlns="%s"' % node.namespace
sorted_attrs = sorted(node.attrs.keys())
for key in sorted_attrs:
if not is_buggy and key == 'xmlns':
continue
val = str(node.attrs[key])
# like XMLescape() but with whitespace and without >
s += ' %s="%s"' % (key, normalise_attr(val))
s += ">"
cnt = 0
if node.kids:
for a in node.kids:
if (len(node.data)-1) >= cnt:
s = s + normalise_text(node.data[cnt])
s = s + c14n(a, is_buggy)
cnt += 1
if (len(node.data)-1) >= cnt: s = s + normalise_text(node.data[cnt])
if not node.kids and s.endswith('>'):
s=s[:-1]+' />'
else:
s = s + "</" + node.name + ">"
return s
def normalise_attr(val):
return val.replace('&', '&').replace('<', '<').replace('"', '"').replace('\t', '	').replace('\n', '
').replace('\r', '
')
def normalise_text(val):
return val.replace('&', '&').replace('<', '<').replace('>', '>').replace('\r', '
')
|