aboutsummaryrefslogtreecommitdiff
path: root/test/test_utils.py
blob: b8fc13aefca50d375d7ae4140f3fd9b26639ac61 (plain)
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
# Various small unit tests

import sys
import unittest

# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

#from youtube_dl.utils import htmlentity_transform
from youtube_dl.utils import timeconvert
from youtube_dl.utils import sanitize_filename
from youtube_dl.utils import unescapeHTML
from youtube_dl.utils import orderedSet

if sys.version < (3,0):
	_compat_str = lambda b: b.decode('unicode-escape')
else:
	_compat_str = lambda s: s

class TestUtil(unittest.TestCase):
	def test_timeconvert(self):
		self.assertTrue(timeconvert('') is None)
		self.assertTrue(timeconvert('bougrg') is None)

	def test_sanitize_filename(self):
		self.assertEqual(sanitize_filename('abc'), 'abc')
		self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')

		self.assertEqual(sanitize_filename('123'), '123')

		self.assertEqual('abc_de', sanitize_filename('abc/de'))
		self.assertFalse('/' in sanitize_filename('abc/de///'))

		self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
		self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
		self.assertEqual('yes no', sanitize_filename('yes? no'))
		self.assertEqual('this - that', sanitize_filename('this: that'))

		self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
		aumlaut = _compat_str('\xe4')
		self.assertEqual(sanitize_filename(aumlaut), aumlaut)
		tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
		self.assertEqual(sanitize_filename(tests), tests)

		forbidden = '"\0\\/'
		for fc in forbidden:
			for fbc in forbidden:
				self.assertTrue(fbc not in sanitize_filename(fc))

	def test_sanitize_filename_restricted(self):
		self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
		self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')

		self.assertEqual(sanitize_filename('123', restricted=True), '123')

		self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
		self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))

		self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
		self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
		self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
		self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))

		tests =_compat_str('a\xe4b\u4e2d\u56fd\u7684c')
		self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
		self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename

		forbidden = '"\0\\/&!: \'\t\n'
		for fc in forbidden:
			for fbc in forbidden:
				self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))

		# Handle a common case more neatly
		self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
		self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
		# .. but make sure the file name is never empty
		self.assertTrue(sanitize_filename('-', restricted=True) != '')
		self.assertTrue(sanitize_filename(':', restricted=True) != '')

	def test_ordered_set(self):
		self.assertEqual(orderedSet([1,1,2,3,4,4,5,6,7,3,5]), [1,2,3,4,5,6,7])
		self.assertEqual(orderedSet([]), [])
		self.assertEqual(orderedSet([1]), [1])
		#keep the list ordered
		self.assertEqual(orderedSet([135,1,1,1]), [135,1])

	def test_unescape_html(self):
		self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))

if __name__ == '__main__':
	unittest.main()