Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py

   1 #!/usr/bin/env python
   2
   3 # Various small unit tests
   4
   5 import sys
   6 import unittest
   7 import xml.etree.ElementTree
   8
   9 # Allow direct execution
  10 import os
  11 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
  12
  13 #from youtube_dl.utils import htmlentity_transform
  14 from youtube_dl.utils import (
  15     timeconvert,
  16     sanitize_filename,
  17     unescapeHTML,
  18     orderedSet,
  19     DateRange,
  20     unified_strdate,
  21     find_xpath_attr,
  22     get_meta_content,
  23 )
  24
  25 if sys.version_info < (3, 0):
  26     _compat_str = lambda b: b.decode('unicode-escape')
  27 else:
  28     _compat_str = lambda s: s
  29
  30
  31 class TestUtil(unittest.TestCase):
  32     def test_timeconvert(self):
  33         self.assertTrue(timeconvert('') is None)
  34         self.assertTrue(timeconvert('bougrg') is None)
  35
  36     def test_sanitize_filename(self):
  37         self.assertEqual(sanitize_filename('abc'), 'abc')
  38         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  39
  40         self.assertEqual(sanitize_filename('123'), '123')
  41
  42         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  43         self.assertFalse('/' in sanitize_filename('abc/de///'))
  44
  45         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  46         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  47         self.assertEqual('yes no', sanitize_filename('yes? no'))
  48         self.assertEqual('this - that', sanitize_filename('this: that'))
  49
  50         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  51         aumlaut = _compat_str('\xe4')
  52         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  53         tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
  54         self.assertEqual(sanitize_filename(tests), tests)
  55
  56         forbidden = '"\0\\/'
  57         for fc in forbidden:
  58             for fbc in forbidden:
  59                 self.assertTrue(fbc not in sanitize_filename(fc))
  60
  61     def test_sanitize_filename_restricted(self):
  62         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  63         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  64
  65         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  66
  67         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  68         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  69
  70         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  71         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  72         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  73         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  74
  75         tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
  76         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  77         self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
  78
  79         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
  80         for fc in forbidden:
  81             for fbc in forbidden:
  82                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
  83
  84         # Handle a common case more neatly
  85         self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
  86         self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
  87         # .. but make sure the file name is never empty
  88         self.assertTrue(sanitize_filename('-', restricted=True) != '')
  89         self.assertTrue(sanitize_filename(':', restricted=True) != '')
  90
  91     def test_sanitize_ids(self):
  92         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
  93         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
  94         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
  95
  96     def test_ordered_set(self):
  97         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
  98         self.assertEqual(orderedSet([]), [])
  99         self.assertEqual(orderedSet([1]), [1])
 100         #keep the list ordered
 101         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 102
 103     def test_unescape_html(self):
 104         self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
 105
 106     def test_daterange(self):
 107         _20century = DateRange("19000101","20000101")
 108         self.assertFalse("17890714" in _20century)
 109         _ac = DateRange("00010101")
 110         self.assertTrue("19690721" in _ac)
 111         _firstmilenium = DateRange(end="10000101")
 112         self.assertTrue("07110427" in _firstmilenium)
 113
 114     def test_unified_dates(self):
 115         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 116         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 117         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 118         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 119
 120     def test_find_xpath_attr(self):
 121         testxml = u'''<root>
 122             <node/>
 123             <node x="a"/>
 124             <node x="a" y="c" />
 125             <node x="b" y="d" />
 126         </root>'''
 127         doc = xml.etree.ElementTree.fromstring(testxml)
 128
 129         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 130         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 131         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 132
 133     def test_meta_parser(self):
 134         testhtml = u'''
 135         <head>
 136             <meta name="description" content="foo &amp; bar">
 137             <meta content='Plato' name='author'/>
 138         </head>
 139         '''
 140         get_meta = lambda name: get_meta_content(name, testhtml)
 141         self.assertEqual(get_meta('description'), u'foo & bar')
 142         self.assertEqual(get_meta('author'), 'Plato')
 143
 144 if __name__ == '__main__':
 145     unittest.main()