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
|
#!/usr/bin/python3
import unittest
import shutil
import os
import zipfile
import tempfile
from src import pdf, images, audio, office, parser_factory
class TestParserFactory(unittest.TestCase):
def test_subsubcalss(self):
""" Test that our module auto-detection is handling sub-sub-classes """
parser, mimetype = parser_factory.get_parser('./tests/data/dirty.mp3')
self.assertEqual(mimetype, 'audio/mpeg')
self.assertEqual(parser.__class__, audio.MP3Parser)
class TestGetMeta(unittest.TestCase):
def test_pdf(self):
p = pdf.PDFParser('./tests/data/dirty.pdf')
meta = p.get_meta()
self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
self.assertEqual(meta['creator'], "'Certified by IEEE PDFeXpress at 03/19/2016 2:56:07 AM'")
self.assertEqual(meta['DocumentID'], "uuid:4a1a79c8-404e-4d38-9580-5bc081036e61")
self.assertEqual(meta['PTEX.Fullbanner'], "This is pdfTeX, Version " \
"3.1415926-2.5-1.40.14 (TeX Live 2013/Debian) kpathsea " \
"version 6.1.1")
def test_png(self):
p = images.PNGParser('./tests/data/dirty.png')
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
self.assertEqual(meta['ModifyDate'], "2018:03:20 21:59:25")
def test_jpg(self):
p = images.JPGParser('./tests/data/dirty.jpg')
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'Created with GIMP')
def test_tiff(self):
p = images.JPGParser('./tests/data/dirty.tiff')
meta = p.get_meta()
self.assertEqual(meta['Make'], 'OLYMPUS IMAGING CORP.')
self.assertEqual(meta['Model'], 'C7070WZ')
self.assertEqual(meta['ModifyDate'], '2005:12:26 17:09:35')
def test_mp3(self):
p = audio.MP3Parser('./tests/data/dirty.mp3')
meta = p.get_meta()
self.assertEqual(meta['TXXX:I am a'], 'various comment')
def test_ogg(self):
p = audio.OGGParser('./tests/data/dirty.ogg')
meta = p.get_meta()
self.assertEqual(meta['title'], 'I am so')
def test_flac(self):
p = audio.FLACParser('./tests/data/dirty.flac')
meta = p.get_meta()
self.assertEqual(meta['title'], 'I am so')
def test_docx(self):
p = office.MSOfficeParser('./tests/data/dirty.docx')
meta = p.get_meta()
self.assertEqual(meta['cp:lastModifiedBy'], 'Julien Voisin')
self.assertEqual(meta['dc:creator'], 'julien voisin')
self.assertEqual(meta['Application'], 'LibreOffice/5.4.5.1$Linux_X86_64 LibreOffice_project/40m0$Build-1')
def test_libreoffice(self):
p = office.LibreOfficeParser('./tests/data/dirty.odt')
meta = p.get_meta()
self.assertEqual(meta['meta:initial-creator'], 'jvoisin ')
self.assertEqual(meta['meta:creation-date'], '2011-07-26T03:27:48')
self.assertEqual(meta['meta:generator'], 'LibreOffice/3.3$Unix LibreOffice_project/330m19$Build-202')
class TestDeepCleaning(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
print('[+] %s is clean inside %s' %(complete_path, p.filename))
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)
ret = p.remove_all()
self.assertTrue(ret)
p = office.MSOfficeParser('./tests/data/clean.docx.cleaned')
self.assertEqual(p.get_meta(), {})
self.__check_zip_meta(p)
self.__check_deep_meta(p)
os.remove('./tests/data/clean.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.odt.cleaned')
self.assertEqual(p.get_meta(), {})
self.__check_zip_meta(p)
self.__check_deep_meta(p)
os.remove('./tests/data/clean.odt')
class TestCleaning(unittest.TestCase):
def test_pdf(self):
shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
p = pdf.PDFParser('./tests/data/clean.pdf')
meta = p.get_meta()
self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
ret = p.remove_all()
self.assertTrue(ret)
p = pdf.PDFParser('./tests/data/clean.pdf.cleaned')
expected_meta = {'creation-date': -1, 'format': 'PDF-1.5', 'mod-date': -1}
self.assertEqual(p.get_meta(), expected_meta)
os.remove('./tests/data/clean.pdf')
def test_png(self):
shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
p = images.PNGParser('./tests/data/clean.png')
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'This is a comment, be careful!')
ret = p.remove_all()
self.assertTrue(ret)
p = images.PNGParser('./tests/data/clean.png.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.png')
def test_jpg(self):
shutil.copy('./tests/data/dirty.jpg', './tests/data/clean.jpg')
p = images.JPGParser('./tests/data/clean.jpg')
meta = p.get_meta()
self.assertEqual(meta['Comment'], 'Created with GIMP')
ret = p.remove_all()
self.assertTrue(ret)
p = images.JPGParser('./tests/data/clean.jpg.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.jpg')
def test_mp3(self):
shutil.copy('./tests/data/dirty.mp3', './tests/data/clean.mp3')
p = audio.MP3Parser('./tests/data/clean.mp3')
meta = p.get_meta()
self.assertEqual(meta['TXXX:I am a'], 'various comment')
ret = p.remove_all()
self.assertTrue(ret)
p = audio.MP3Parser('./tests/data/clean.mp3.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.mp3')
def test_ogg(self):
shutil.copy('./tests/data/dirty.ogg', './tests/data/clean.ogg')
p = audio.OGGParser('./tests/data/clean.ogg')
meta = p.get_meta()
self.assertEqual(meta['title'], 'I am so')
ret = p.remove_all()
self.assertTrue(ret)
p = audio.OGGParser('./tests/data/clean.ogg.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.ogg')
def test_flac(self):
shutil.copy('./tests/data/dirty.flac', './tests/data/clean.flac')
p = audio.FLACParser('./tests/data/clean.flac')
meta = p.get_meta()
self.assertEqual(meta['title'], 'I am so')
ret = p.remove_all()
self.assertTrue(ret)
p = audio.FLACParser('./tests/data/clean.flac.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.flac')
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)
ret = p.remove_all()
self.assertTrue(ret)
p = office.MSOfficeParser('./tests/data/clean.docx.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.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.odt.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.odt')
def test_tiff(self):
shutil.copy('./tests/data/dirty.tiff', './tests/data/clean.tiff')
p = images.TiffParser('./tests/data/clean.tiff')
meta = p.get_meta()
self.assertEqual(meta['Model'], 'C7070WZ')
ret = p.remove_all()
self.assertTrue(ret)
p = images.TiffParser('./tests/data/clean.tiff.cleaned')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.tiff')
|
