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
|
#!/usr/bin/env python3
import unittest
import shutil
import os
import zipfile
import tempfile
from libmat2 import office, parser_factory
class TestZipMetadata(unittest.TestCase):
def __check_deep_meta(self, p):
tempdir = tempfile.mkdtemp()
zipin = zipfile.ZipFile(p.filename)
zipin.extractall(tempdir)
for subdir, dirs, files in os.walk(tempdir):
for f in files:
complete_path = os.path.join(subdir, f)
inside_p, _ = parser_factory.get_parser(complete_path)
if inside_p is None:
continue
self.assertEqual(inside_p.get_meta(), {})
shutil.rmtree(tempdir)
def __check_zip_meta(self, p):
zipin = zipfile.ZipFile(p.filename)
for item in zipin.infolist():
self.assertEqual(item.comment, b'')
self.assertEqual(item.date_time, (1980, 1, 1, 0, 0, 0))
self.assertEqual(item.create_system, 3) # 3 is UNIX
def test_office(self):
shutil.copy('./tests/data/dirty.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
self.assertEqual(meta['word/media/image1.png']['Comment'], 'This is a comment, be careful!')
ret = p.remove_all()
self.assertTrue(ret)
p = office.MSOfficeParser('./tests/data/clean.cleaned.docx')
self.assertEqual(p.get_meta(), {})
self.__check_zip_meta(p)
self.__check_deep_meta(p)
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
def test_libreoffice(self):
shutil.copy('./tests/data/dirty.odt', './tests/data/clean.odt')
p = office.LibreOfficeParser('./tests/data/clean.odt')
meta = p.get_meta()
self.assertIsNotNone(meta)
ret = p.remove_all()
self.assertTrue(ret)
p = office.LibreOfficeParser('./tests/data/clean.cleaned.odt')
self.assertEqual(p.get_meta(), {})
self.__check_zip_meta(p)
self.__check_deep_meta(p)
os.remove('./tests/data/clean.odt')
os.remove('./tests/data/clean.cleaned.odt')
class TestZipOrder(unittest.TestCase):
def test_libreoffice(self):
shutil.copy('./tests/data/dirty.odt', './tests/data/clean.odt')
p = office.LibreOfficeParser('./tests/data/clean.odt')
meta = p.get_meta()
self.assertIsNotNone(meta)
is_unordered = False
with zipfile.ZipFile('./tests/data/clean.odt') as zin:
previous_name = ''
for item in zin.infolist():
if previous_name == '':
if item.filename == 'mimetype':
continue
previous_name = item.filename
continue
elif item.filename < previous_name:
is_unordered = True
break
self.assertTrue(is_unordered)
ret = p.remove_all()
self.assertTrue(ret)
with zipfile.ZipFile('./tests/data/clean.cleaned.odt') as zin:
previous_name = ''
for item in zin.infolist():
if previous_name == '':
if item.filename == 'mimetype':
continue
previous_name = item.filename
continue
self.assertGreaterEqual(item.filename, previous_name)
os.remove('./tests/data/clean.odt')
os.remove('./tests/data/clean.cleaned.odt')
class TestRsidRemoval(unittest.TestCase):
def test_office(self):
shutil.copy('./tests/data/office_revision_session_ids.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
how_many_rsid = False
with zipfile.ZipFile('./tests/data/clean.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:rsid')
how_many_rsid += num
self.assertEqual(how_many_rsid, 11)
ret = p.remove_all()
self.assertTrue(ret)
with zipfile.ZipFile('./tests/data/clean.cleaned.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:rsid')
self.assertEqual(num, 0)
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
class TestNsidRemoval(unittest.TestCase):
def test_office(self):
shutil.copy('./tests/data/dirty_with_nsid.docx', './tests/data/clean.docx')
p = office.MSOfficeParser('./tests/data/clean.docx')
meta = p.get_meta()
self.assertIsNotNone(meta)
how_many_rsid = False
with zipfile.ZipFile('./tests/data/clean.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:rsid')
how_many_rsid += num
self.assertEqual(how_many_rsid, 1190)
ret = p.remove_all()
self.assertTrue(ret)
with zipfile.ZipFile('./tests/data/clean.cleaned.docx') as zin:
for item in zin.infolist():
if not item.filename.endswith('.xml'):
continue
num = zin.read(item).decode('utf-8').lower().count('w:nsid')
self.assertEqual(num, 0)
os.remove('./tests/data/clean.docx')
os.remove('./tests/data/clean.cleaned.docx')
|
