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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
# xml.py - module for parsing and writing XML for PSKC files
# coding: utf-8
#
# Copyright (C) 2014-2016 Arthur de Jong
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library 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
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
# 02110-1301 USA
"""Module for parsing XML in PSKC files.
This module provides some utility functions for parsing XML files.
"""
from __future__ import absolute_import
# try to find a usable ElementTree module
try:
from lxml import etree
except ImportError: # pragma: no cover (different implementations)
import xml.etree.ElementTree as etree
# the relevant XML namespaces for PSKC
namespaces = dict(
# the XML namespace URI for version 1.0 of PSKC
pskc='urn:ietf:params:xml:ns:keyprov:pskc',
# the XML Signature namespace
ds='http://www.w3.org/2000/09/xmldsig#',
# the XML Encryption namespace
xenc='http://www.w3.org/2001/04/xmlenc#',
# the XML Encryption version 1.1 namespace
xenc11='http://www.w3.org/2009/xmlenc11#',
# the PKCS #5 namespace
pkcs5='http://www.rsasecurity.com/rsalabs/pkcs/schemas/pkcs-5v2-0#',
)
# register the namespaces so the correct short names will be used
for ns, namespace in namespaces.items():
etree.register_namespace(ns, namespace)
def parse(source):
"""Parse the provided file and return an element tree."""
return etree.parse(source)
def remove_namespaces(tree):
"""Remove namespaces from all elements in the tree."""
import re
for elem in tree.getiterator():
if isinstance(elem.tag, ''.__class__): # pragma: no branch
elem.tag = re.sub(r'^\{[^}]*\}', '', elem.tag)
def findall(tree, *matches):
"""Find the child elements."""
for match in matches:
for element in tree.findall(match, namespaces=namespaces):
yield element
def find(tree, *matches):
"""Find a child element that matches any of the patterns (or None)."""
try:
return next(findall(tree, *matches))
except StopIteration:
pass
def findtext(tree, *matches):
"""Get the text value of an element (or None)."""
element = find(tree, *matches)
if element is not None:
return element.text.strip()
def findint(tree, *matches):
"""Return an element value as an int (or None)."""
value = findtext(tree, *matches)
if value:
return int(value)
def findtime(tree, *matches):
"""Return an element value as a datetime (or None)."""
value = findtext(tree, *matches)
if value:
import dateutil.parser
return dateutil.parser.parse(value)
def findbin(tree, *matches):
"""Return the binary element value base64 decoded."""
value = findtext(tree, *matches)
if value:
import base64
return base64.b64decode(value)
def getint(tree, attribute):
"""Return an attribute value as an integer (or None)."""
value = tree.get(attribute)
if value:
return int(value)
def getbool(tree, attribute, default=None):
"""Return an attribute value as a boolean (or None)."""
value = tree.get(attribute)
if value:
value = value.lower()
if value in ('1', 'true'):
return True
elif value in ('0', 'false'):
return False
else:
raise ValueError('invalid boolean value: %r' % value)
return default
def _format(value):
import datetime
if isinstance(value, datetime.datetime):
value = value.isoformat()
if value.endswith('+00:00'):
value = value[:-6] + 'Z'
return value
elif value is True:
return 'true'
elif value is False:
return 'false'
return str(value)
def mk_elem(parent, tag=None, text=None, empty=False, **kwargs):
"""Add element as a child of parent."""
# special-case the top-level element
if tag is None:
tag = parent
parent = None
empty = True
# don't create empty elements
if not empty and text is None and \
all(x is None for x in kwargs.values()):
return
# replace namespace identifier with URL
if ':' in tag:
ns, name = tag.split(':', 1)
tag = '{%s}%s' % (namespaces[ns], name)
if parent is None:
element = etree.Element(tag)
else:
element = etree.SubElement(parent, tag)
# set text of element
if text is not None:
element.text = _format(text)
# set kwargs as attributes
for k, v in kwargs.items():
if v is not None:
element.set(k, _format(v))
return element
def tostring(element):
"""Return a serialised XML document for the element tree."""
from xml.dom import minidom
# if we are using lxml.etree move namespaces to toplevel element
if hasattr(element, 'nsmap'): # pragma: no cover (only on lxml)
# get all used namespaces
nsmap = {}
for e in element.iter():
nsmap.update(e.nsmap)
# replace toplevel element with all namespaces
e = etree.Element(element.tag, attrib=element.attrib, nsmap=nsmap)
for a in element:
e.append(a)
element = e
xml = etree.tostring(element, encoding='UTF-8')
return minidom.parseString(xml).toprettyxml(
indent=' ', encoding='UTF-8').strip()
|