]> jfr.im git - yt-dlp.git/blob - test/test_utils.py
Restrict more characters (Closes #566)
[yt-dlp.git] / test / test_utils.py
1 # Various small unit tests
2
3 import sys
4 import unittest
5
6 # Allow direct execution
7 import os
8 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
9
10 #from youtube_dl.utils import htmlentity_transform
11 from youtube_dl.utils import timeconvert
12 from youtube_dl.utils import sanitize_filename
13 from youtube_dl.utils import unescapeHTML
14 from youtube_dl.utils import orderedSet
15
16 if sys.version_info < (3, 0):
17 _compat_str = lambda b: b.decode('unicode-escape')
18 else:
19 _compat_str = lambda s: s
20
21
22 class TestUtil(unittest.TestCase):
23 def test_timeconvert(self):
24 self.assertTrue(timeconvert('') is None)
25 self.assertTrue(timeconvert('bougrg') is None)
26
27 def test_sanitize_filename(self):
28 self.assertEqual(sanitize_filename('abc'), 'abc')
29 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
30
31 self.assertEqual(sanitize_filename('123'), '123')
32
33 self.assertEqual('abc_de', sanitize_filename('abc/de'))
34 self.assertFalse('/' in sanitize_filename('abc/de///'))
35
36 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
37 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
38 self.assertEqual('yes no', sanitize_filename('yes? no'))
39 self.assertEqual('this - that', sanitize_filename('this: that'))
40
41 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
42 aumlaut = _compat_str('\xe4')
43 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
44 tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
45 self.assertEqual(sanitize_filename(tests), tests)
46
47 forbidden = '"\0\\/'
48 for fc in forbidden:
49 for fbc in forbidden:
50 self.assertTrue(fbc not in sanitize_filename(fc))
51
52 def test_sanitize_filename_restricted(self):
53 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
54 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
55
56 self.assertEqual(sanitize_filename('123', restricted=True), '123')
57
58 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
59 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
60
61 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
62 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
63 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
64 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
65
66 tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
67 self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
68 self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename
69
70 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
71 for fc in forbidden:
72 for fbc in forbidden:
73 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
74
75 # Handle a common case more neatly
76 self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
77 self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
78 # .. but make sure the file name is never empty
79 self.assertTrue(sanitize_filename('-', restricted=True) != '')
80 self.assertTrue(sanitize_filename(':', restricted=True) != '')
81
82 def test_ordered_set(self):
83 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
84 self.assertEqual(orderedSet([]), [])
85 self.assertEqual(orderedSet([1]), [1])
86 #keep the list ordered
87 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
88
89 def test_unescape_html(self):
90 self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
91
92 if __name__ == '__main__':
93 unittest.main()