_ Git - youtube-dl/blob - test/test_utils.py

   1 #!/usr/bin/env python
   2
   3 # Allow direct execution
   4 import os
   5 import sys
   6 import unittest
   7 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
   8
   9
  10 # Various small unit tests
  11 import xml.etree.ElementTree
  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     xpath_with_ns,
  24 )
  25
  26 if sys.version_info < (3, 0):
  27     _compat_str = lambda b: b.decode('unicode-escape')
  28 else:
  29     _compat_str = lambda s: s
  30
  31
  32 class TestUtil(unittest.TestCase):
  33     def test_timeconvert(self):
  34         self.assertTrue(timeconvert('') is None)
  35         self.assertTrue(timeconvert('bougrg') is None)
  36
  37     def test_sanitize_filename(self):
  38         self.assertEqual(sanitize_filename('abc'), 'abc')
  39         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  40
  41         self.assertEqual(sanitize_filename('123'), '123')
  42
  43         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  44         self.assertFalse('/' in sanitize_filename('abc/de///'))
  45
  46         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  47         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  48         self.assertEqual('yes no', sanitize_filename('yes? no'))
  49         self.assertEqual('this - that', sanitize_filename('this: that'))
  50
  51         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  52         aumlaut = _compat_str('\xe4')
  53         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  54         tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
  55         self.assertEqual(sanitize_filename(tests), tests)
  56
  57         forbidden = '"\0\\/'
  58         for fc in forbidden:
  59             for fbc in forbidden:
  60                 self.assertTrue(fbc not in sanitize_filename(fc))
  61
  62     def test_sanitize_filename_restricted(self):
  63         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  64         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  65
  66         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  67
  68         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  69         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  70
  71         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  72         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  73         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  74         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  75
  76         tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
  77         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  78         self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
  79
  80         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
  81         for fc in forbidden:
  82             for fbc in forbidden:
  83                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
  84
  85         # Handle a common case more neatly
  86         self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
  87         self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
  88         # .. but make sure the file name is never empty
  89         self.assertTrue(sanitize_filename('-', restricted=True) != '')
  90         self.assertTrue(sanitize_filename(':', restricted=True) != '')
  91
  92     def test_sanitize_ids(self):
  93         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
  94         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
  95         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
  96
  97     def test_ordered_set(self):
  98         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
  99         self.assertEqual(orderedSet([]), [])
 100         self.assertEqual(orderedSet([1]), [1])
 101         #keep the list ordered
 102         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 103
 104     def test_unescape_html(self):
 105         self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
 106
 107     def test_daterange(self):
 108         _20century = DateRange("19000101","20000101")
 109         self.assertFalse("17890714" in _20century)
 110         _ac = DateRange("00010101")
 111         self.assertTrue("19690721" in _ac)
 112         _firstmilenium = DateRange(end="10000101")
 113         self.assertTrue("07110427" in _firstmilenium)
 114
 115     def test_unified_dates(self):
 116         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 117         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 118         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 119         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 120
 121     def test_find_xpath_attr(self):
 122         testxml = u'''<root>
 123             <node/>
 124             <node x="a"/>
 125             <node x="a" y="c" />
 126             <node x="b" y="d" />
 127         </root>'''
 128         doc = xml.etree.ElementTree.fromstring(testxml)
 129
 130         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 131         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 132         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 133
 134     def test_meta_parser(self):
 135         testhtml = u'''
 136         <head>
 137             <meta name="description" content="foo &amp; bar">
 138             <meta content='Plato' name='author'/>
 139         </head>
 140         '''
 141         get_meta = lambda name: get_meta_content(name, testhtml)
 142         self.assertEqual(get_meta('description'), u'foo & bar')
 143         self.assertEqual(get_meta('author'), 'Plato')
 144
 145     def test_xpath_with_ns(self):
 146         testxml = u'''<root xmlns:media="http://example.com/">
 147             <media:song>
 148                 <media:author>The Author</media:author>
 149                 <url>http://server.com/download.mp3</url>
 150             </media:song>
 151         </root>'''
 152         doc = xml.etree.ElementTree.fromstring(testxml)
 153         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 154         self.assertTrue(find('media:song') is not None)
 155         self.assertEqual(find('media:song/media:author').text, u'The Author')
 156         self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
 157
 158 if __name__ == '__main__':
 159     unittest.main()