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
|
import os
import re
import zipfile
from typing import Dict, Set, Pattern
import xml.etree.ElementTree as ET # type: ignore
from .archive import ArchiveBasedAbstractParser
# Make pyflakes happy
assert Set
assert Pattern
def _parse_xml(full_path: str):
""" This function parse XML, with namespace support. """
namespace_map = dict()
for _, (key, value) in ET.iterparse(full_path, ("start-ns", )):
namespace_map[key] = value
ET.register_namespace(key, value)
return ET.parse(full_path), namespace_map
class MSOfficeParser(ArchiveBasedAbstractParser):
mimetypes = {
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
'application/vnd.openxmlformats-officedocument.presentationml.presentation'
}
files_to_keep = {
'[Content_Types].xml',
'_rels/.rels',
'word/_rels/document.xml.rels',
'word/document.xml',
'word/fontTable.xml',
'word/settings.xml',
'word/styles.xml',
}
files_to_omit = set(map(re.compile, { # type: ignore
'^docProps/',
}))
@staticmethod
def __remove_revisions(full_path: str) -> bool:
""" In this function, we're changing the XML document in several
different times, since we don't want to change the tree we're currently
iterating on.
"""
try:
tree, namespace = _parse_xml(full_path)
except ET.ParseError:
return False
# Revisions are either deletions (`w:del`) or
# insertions (`w:ins`)
del_presence = tree.find('.//w:del', namespace)
ins_presence = tree.find('.//w:ins', namespace)
if del_presence is None and ins_presence is None:
return True # No revisions are present
parent_map = {c:p for p in tree.iter() for c in p}
elements = list()
for element in tree.iterfind('.//w:del', namespace):
elements.append(element)
for element in elements:
parent_map[element].remove(element)
elements = list()
for element in tree.iterfind('.//w:ins', namespace):
for position, item in enumerate(tree.iter()): #pragma: no cover
if item == element:
for children in element.iterfind('./*'):
elements.append((element, position, children))
break
for (element, position, children) in elements:
parent_map[element].insert(position, children)
parent_map[element].remove(element)
tree.write(full_path, xml_declaration=True)
return True
def _specific_cleanup(self, full_path: str) -> bool:
if full_path.endswith('/word/document.xml'):
# this file contains the revisions
return self.__remove_revisions(full_path)
return True
def get_meta(self) -> Dict[str, str]:
"""
Yes, I know that parsing xml with regexp ain't pretty,
be my guest and fix it if you want.
"""
metadata = {}
zipin = zipfile.ZipFile(self.filename)
for item in zipin.infolist():
if item.filename.startswith('docProps/') and item.filename.endswith('.xml'):
try:
content = zipin.read(item).decode('utf-8')
results = re.findall(r"<(.+)>(.+)</\1>", content, re.I|re.M)
for (key, value) in results:
metadata[key] = value
except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file
metadata[item.filename] = 'harmful content'
for key, value in self._get_zipinfo_meta(item).items():
metadata[key] = value
zipin.close()
return metadata
class LibreOfficeParser(ArchiveBasedAbstractParser):
mimetypes = {
'application/vnd.oasis.opendocument.text',
'application/vnd.oasis.opendocument.spreadsheet',
'application/vnd.oasis.opendocument.presentation',
'application/vnd.oasis.opendocument.graphics',
'application/vnd.oasis.opendocument.chart',
'application/vnd.oasis.opendocument.formula',
'application/vnd.oasis.opendocument.image',
}
files_to_keep = {
'META-INF/manifest.xml',
'content.xml',
'manifest.rdf',
'mimetype',
'settings.xml',
'styles.xml',
}
files_to_omit = set(map(re.compile, { # type: ignore
r'^meta\.xml$',
'^Configurations2/',
'^Thumbnails/',
}))
@staticmethod
def __remove_revisions(full_path: str) -> bool:
try:
tree, namespace = _parse_xml(full_path)
except ET.ParseError:
return False
if 'office' not in namespace.keys(): # no revisions in the current file
return True
for text in tree.getroot().iterfind('.//office:text', namespace):
for changes in text.iterfind('.//text:tracked-changes', namespace):
text.remove(changes)
tree.write(full_path, xml_declaration=True)
return True
def _specific_cleanup(self, full_path: str) -> bool:
if os.path.basename(full_path) == 'content.xml':
return self.__remove_revisions(full_path)
return True
def get_meta(self) -> Dict[str, str]:
"""
Yes, I know that parsing xml with regexp ain't pretty,
be my guest and fix it if you want.
"""
metadata = {}
zipin = zipfile.ZipFile(self.filename)
for item in zipin.infolist():
if item.filename == 'meta.xml':
try:
content = zipin.read(item).decode('utf-8')
results = re.findall(r"<((?:meta|dc|cp).+?)>(.+)</\1>", content, re.I|re.M)
for (key, value) in results:
metadata[key] = value
except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file
metadata[item.filename] = 'harmful content'
for key, value in self._get_zipinfo_meta(item).items():
metadata[key] = value
zipin.close()
return metadata
|
