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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
|
'''
Take care of archives formats
'''
import tarfile
import zipfile
import shutil
import os
import logging
import tempfile
import parser
import mat
class GenericArchiveStripper(parser.GenericParser):
'''
Represent a generic archive
'''
def __init__(self, filename, parser, mime, backup, add2archive):
super(GenericArchiveStripper, self).__init__(filename, parser, mime,
backup, add2archive)
self.compression = ''
self.add2archive = add2archive
self.tempdir = tempfile.mkdtemp()
def __del__(self):
'''
Remove the temp dir
'''
shutil.rmtree(self.tempdir)
def remove_all(self):
'''
Call _remove_all() with in argument : "normal"
'''
self._remove_all('normal')
def remove_all_ugly(self):
'''
call remove_all() with in argument : "ugly"
'''
self._remove_all('ugly')
def _remove_all(self, method):
'''
Remove all meta, normal way if method is "normal",
else, use the ugly way (with possible data loss)
'''
raise NotImplementedError
class ZipStripper(GenericArchiveStripper):
'''
Represent a zip file
'''
def is_file_clean(self, fileinfo):
'''
Check if a ZipInfo object is clean of metadatas added
by zip itself, independently of the corresponding file metadatas
'''
if fileinfo.comment is not '':
return False
elif fileinfo.date_time is not 0:
return False
elif fileinfo.create_system is not 0:
return False
elif fileinfo.create_version is not 0:
return False
else:
return True
def is_clean(self):
'''
Check if the given file is clean from harmful metadata
'''
zipin = zipfile.ZipFile(self.filename, 'r')
if zipin.comment != '':
logging.debug('%s has a comment' % self.filename)
return False
for item in zipin.infolist():
#I have not found a way to remove the crap added by zipfile :/
#if not self.is_file_clean(item):
# logging.debug('%s from %s has compromizing zipinfo' %
# (item.filename, self.filename))
# return False
zipin.extract(item, self.tempdir)
name = os.path.join(self.tempdir, item.filename)
if os.path.isfile(name):
try:
cfile = mat.create_class_file(name, False,
self.add2archive)
if not cfile.is_clean():
return False
except:
#best solution I have found
logging.info('%s\'s fileformat is not supported, or is a \
harmless format' % item.filename)
_, ext = os.path.splitext(name)
bname = os.path.basename(item.filename)
if ext not in parser.NOMETA:
if bname != 'mimetype':
return False
mat.secure_remove(name)
zipin.close()
return True
def get_meta(self):
'''
Return all the metadata of a ZipFile (don't return metadatas
of contained files : should it ?)
'''
zipin = zipfile.ZipFile(self.filename, 'r')
metadata = {}
for field in zipin.infolist():
zipmeta = {}
zipmeta['comment'] = field.comment
zipmeta['modified'] = field.date_time
zipmeta['system'] = field.create_system
zipmeta['zip_version'] = field.create_version
metadata[field.filename] = zipmeta
metadata["%s comment" % self.filename] = zipin.comment
zipin.close()
return metadata
def _remove_all(self, method):
'''
So far, the zipfile module does not allow to write a ZipInfo
object into a zipfile (and it's a shame !) : so data added
by zipfile itself could not be removed. It's a big concern.
Is shiping a patched version of zipfile.py a good idea ?
'''
zipin = zipfile.ZipFile(self.filename, 'r')
zipout = zipfile.ZipFile(self.output, 'w',
allowZip64=True)
for item in zipin.infolist():
zipin.extract(item, self.tempdir)
name = os.path.join(self.tempdir, item.filename)
if os.path.isfile(name):
try:
cfile = mat.create_class_file(name, False,
self.add2archive)
if method is 'normal':
cfile.remove_all()
else:
cfile.remove_all_ugly()
logging.debug('Processing %s from %s' % (item.filename,
self.filename))
zipout.write(name, item.filename)
except:
logging.info('%s\' fileformat is not supported' %
item.filename)
if self.add2archive:
zipout.write(name, item.filename)
mat.secure_remove(name)
zipout.comment = ''
zipin.close()
zipout.close()
logging.info('%s treated' % self.filename)
self.do_backup()
class TarStripper(GenericArchiveStripper):
'''
Represent a tarfile archive
'''
def _remove(self, current_file):
'''
remove the meta added by tar itself to the file
'''
current_file.mtime = 0
current_file.uid = 0
current_file.gid = 0
current_file.uname = ''
current_file.gname = ''
return current_file
def _remove_all(self, method):
tarin = tarfile.open(self.filename, 'r' + self.compression)
tarout = tarfile.open(self.output, 'w' + self.compression)
for item in tarin.getmembers():
tarin.extract(item, self.tempdir)
name = os.path.join(self.tempdir, item.name)
if item.type is '0': # is item a regular file ?
#no backup file
try:
cfile = mat.create_class_file(name, False,
self.add2archive)
if method is 'normal':
cfile.remove_all()
else:
cfile.remove_all_ugly()
tarout.add(name, item.name, filter=self._remove)
except:
logging.info('%s\' format is not supported' %
item.name)
if self.add2archive:
tarout.add(name, item.name, filter=self._remove)
mat.secure_remove(name)
tarin.close()
tarout.close()
self.do_backup()
def is_file_clean(self, current_file):
'''
Check metadatas added by tar
'''
if current_file.mtime is not 0:
return False
elif current_file.uid is not 0:
return False
elif current_file.gid is not 0:
return False
elif current_file.uname is not '':
return False
elif current_file.gname is not '':
return False
else:
return True
def is_clean(self):
'''
Check if the file is clean from harmful metadatas
'''
tarin = tarfile.open(self.filename, 'r' + self.compression)
for item in tarin.getmembers():
if not self.is_file_clean(item):
return False
tarin.extract(item, self.tempdir)
name = os.path.join(self.tempdir, item.name)
if item.type is '0': # is item a regular file ?
#no backup file
try:
class_file = mat.create_class_file(name,
False, self.add2archive)
if not class_file.is_clean():
return False
except:
#best solution I have found
logging.error('%s is not supported' % item.filename)
_, ext = os.path.splitext(name)
if ext not in parser.NOMETA:
return False
mat.secure_remove(name)
tarin.close()
return True
def get_meta(self):
'''
Return a dict with all the meta of the file
'''
tarin = tarfile.open(self.filename, 'r' + self.compression)
metadata = {}
for current_file in tarin.getmembers():
if current_file.type is '0':
if not self.is_file_clean(current_file): # if there is meta
current_meta = {}
current_meta['mtime'] = current_file.mtime
current_meta['uid'] = current_file.uid
current_meta['gid'] = current_file.gid
current_meta['uname'] = current_file.uname
current_meta['gname'] = current_file.gname
metadata[current_file.name] = current_meta
tarin.close()
return metadata
class GzipStripper(TarStripper):
'''
Represent a tar.gz archive
'''
def __init__(self, filename, parser, mime, backup, add2archive):
super(GzipStripper, self).__init__(filename, parser, mime, backup,
add2archive)
self.compression = ':gz'
class Bzip2Stripper(TarStripper):
'''
Represents a tar.bz2 archive
'''
def __init__(self, filename, parser, mime, backup, add2archive):
super(Bzip2Stripper, self).__init__(filename, parser, mime, backup,
add2archive)
self.compression = ':bz2'
|
