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
|
#
# ElementTree
# $Id: ElementInclude.py 3375 2008-02-13 08:05:08Z fredrik $
#
# limited xinclude support for element trees
#
# history:
# 2003-08-15 fl created
# 2003-11-14 fl fixed default loader
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2008 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
# Licensed to PSF under a Contributor Agreement.
# See https://www.python.org/psf/license for licensing details.
##
# Limited XInclude support for the ElementTree package.
##
import copy
from . import ElementTree
from urllib.parse import urljoin
XINCLUDE = "{http://www.w3.org/2001/XInclude}"
XINCLUDE_INCLUDE = XINCLUDE + "include"
XINCLUDE_FALLBACK = XINCLUDE + "fallback"
# For security reasons, the inclusion depth is limited to this read-only value by default.
DEFAULT_MAX_INCLUSION_DEPTH = 6
##
# Fatal include error.
class FatalIncludeError(SyntaxError):
pass
class LimitedRecursiveIncludeError(FatalIncludeError):
pass
##
# Default loader. This loader reads an included resource from disk.
#
# @param href Resource reference.
# @param parse Parse mode. Either "xml" or "text".
# @param encoding Optional text encoding (UTF-8 by default for "text").
# @return The expanded resource. If the parse mode is "xml", this
# is an ElementTree instance. If the parse mode is "text", this
# is a Unicode string. If the loader fails, it can return None
# or raise an OSError exception.
# @throws OSError If the loader fails to load the resource.
def default_loader(href, parse, encoding=None):
if parse == "xml":
with open(href, 'rb') as file:
data = ElementTree.parse(file).getroot()
else:
if not encoding:
encoding = 'UTF-8'
with open(href, 'r', encoding=encoding) as file:
data = file.read()
return data
##
# Expand XInclude directives.
#
# @param elem Root element.
# @param loader Optional resource loader. If omitted, it defaults
# to {@link default_loader}. If given, it should be a callable
# that implements the same interface as <b>default_loader</b>.
# @param base_url The base URL of the original file, to resolve
# relative include file references.
# @param max_depth The maximum number of recursive inclusions.
# Limited to reduce the risk of malicious content explosion.
# Pass a negative value to disable the limitation.
# @throws LimitedRecursiveIncludeError If the {@link max_depth} was exceeded.
# @throws FatalIncludeError If the function fails to include a given
# resource, or if the tree contains malformed XInclude elements.
# @throws IOError If the function fails to load a given resource.
# @returns the node or its replacement if it was an XInclude node
def include(elem, loader=None, base_url=None,
max_depth=DEFAULT_MAX_INCLUSION_DEPTH):
if max_depth is None:
max_depth = -1
elif max_depth < 0:
raise ValueError("expected non-negative depth or None for 'max_depth', got %r" % max_depth)
if hasattr(elem, 'getroot'):
elem = elem.getroot()
if loader is None:
loader = default_loader
_include(elem, loader, base_url, max_depth, set())
def _include(elem, loader, base_url, max_depth, _parent_hrefs):
# look for xinclude elements
i = 0
while i < len(elem):
e = elem[i]
if e.tag == XINCLUDE_INCLUDE:
# process xinclude directive
href = e.get("href")
if base_url:
href = urljoin(base_url, href)
parse = e.get("parse", "xml")
if parse == "xml":
if href in _parent_hrefs:
raise FatalIncludeError("recursive include of %s" % href)
if max_depth == 0:
raise LimitedRecursiveIncludeError(
"maximum xinclude depth reached when including file %s" % href)
_parent_hrefs.add(href)
node = loader(href, parse)
if node is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
node = copy.copy(node) # FIXME: this makes little sense with recursive includes
_include(node, loader, href, max_depth - 1, _parent_hrefs)
_parent_hrefs.remove(href)
if e.tail:
node.tail = (node.tail or "") + e.tail
elem[i] = node
elif parse == "text":
text = loader(href, parse, e.get("encoding"))
if text is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
if e.tail:
text += e.tail
if i:
node = elem[i-1]
node.tail = (node.tail or "") + text
else:
elem.text = (elem.text or "") + text
del elem[i]
continue
else:
raise FatalIncludeError(
"unknown parse type in xi:include tag (%r)" % parse
)
elif e.tag == XINCLUDE_FALLBACK:
raise FatalIncludeError(
"xi:fallback tag must be child of xi:include (%r)" % e.tag
)
else:
_include(e, loader, base_url, max_depth, _parent_hrefs)
i += 1
|
