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

   1 #!/usr/bin/env python
   2 # coding: utf-8
   3
   4 # Allow direct execution
   5 import os
   6 import sys
   7 import unittest
   8 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
   9
  10
  11 # Various small unit tests
  12 import xml.etree.ElementTree
  13
  14 #from youtube_dl.utils import htmlentity_transform
  15 from youtube_dl.utils import (
  16     timeconvert,
  17     sanitize_filename,
  18     unescapeHTML,
  19     orderedSet,
  20     DateRange,
  21     unified_strdate,
  22     find_xpath_attr,
  23     get_meta_content,
  24     xpath_with_ns,
  25     smuggle_url,
  26     unsmuggle_url,
  27     shell_quote,
  28     encodeFilename,
  29 )
  30
  31 if sys.version_info < (3, 0):
  32     _compat_str = lambda b: b.decode('unicode-escape')
  33 else:
  34     _compat_str = lambda s: s
  35
  36
  37 class TestUtil(unittest.TestCase):
  38     def test_timeconvert(self):
  39         self.assertTrue(timeconvert('') is None)
  40         self.assertTrue(timeconvert('bougrg') is None)
  41
  42     def test_sanitize_filename(self):
  43         self.assertEqual(sanitize_filename('abc'), 'abc')
  44         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  45
  46         self.assertEqual(sanitize_filename('123'), '123')
  47
  48         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  49         self.assertFalse('/' in sanitize_filename('abc/de///'))
  50
  51         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  52         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  53         self.assertEqual('yes no', sanitize_filename('yes? no'))
  54         self.assertEqual('this - that', sanitize_filename('this: that'))
  55
  56         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  57         aumlaut = _compat_str('\xe4')
  58         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  59         tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
  60         self.assertEqual(sanitize_filename(tests), tests)
  61
  62         forbidden = '"\0\\/'
  63         for fc in forbidden:
  64             for fbc in forbidden:
  65                 self.assertTrue(fbc not in sanitize_filename(fc))
  66
  67     def test_sanitize_filename_restricted(self):
  68         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  69         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  70
  71         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  72
  73         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  74         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  75
  76         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  77         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  78         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  79         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  80
  81         tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
  82         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  83         self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
  84
  85         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
  86         for fc in forbidden:
  87             for fbc in forbidden:
  88                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
  89
  90         # Handle a common case more neatly
  91         self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
  92         self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
  93         # .. but make sure the file name is never empty
  94         self.assertTrue(sanitize_filename('-', restricted=True) != '')
  95         self.assertTrue(sanitize_filename(':', restricted=True) != '')
  96
  97     def test_sanitize_ids(self):
  98         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
  99         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 100         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 101
 102     def test_ordered_set(self):
 103         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 104         self.assertEqual(orderedSet([]), [])
 105         self.assertEqual(orderedSet([1]), [1])
 106         #keep the list ordered
 107         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 108
 109     def test_unescape_html(self):
 110         self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
 111
 112     def test_daterange(self):
 113         _20century = DateRange("19000101","20000101")
 114         self.assertFalse("17890714" in _20century)
 115         _ac = DateRange("00010101")
 116         self.assertTrue("19690721" in _ac)
 117         _firstmilenium = DateRange(end="10000101")
 118         self.assertTrue("07110427" in _firstmilenium)
 119
 120     def test_unified_dates(self):
 121         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 122         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 123         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 124         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 125
 126     def test_find_xpath_attr(self):
 127         testxml = u'''<root>
 128             <node/>
 129             <node x="a"/>
 130             <node x="a" y="c" />
 131             <node x="b" y="d" />
 132         </root>'''
 133         doc = xml.etree.ElementTree.fromstring(testxml)
 134
 135         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 136         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 137         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 138
 139     def test_meta_parser(self):
 140         testhtml = u'''
 141         <head>
 142             <meta name="description" content="foo &amp; bar">
 143             <meta content='Plato' name='author'/>
 144         </head>
 145         '''
 146         get_meta = lambda name: get_meta_content(name, testhtml)
 147         self.assertEqual(get_meta('description'), u'foo & bar')
 148         self.assertEqual(get_meta('author'), 'Plato')
 149
 150     def test_xpath_with_ns(self):
 151         testxml = u'''<root xmlns:media="http://example.com/">
 152             <media:song>
 153                 <media:author>The Author</media:author>
 154                 <url>http://server.com/download.mp3</url>
 155             </media:song>
 156         </root>'''
 157         doc = xml.etree.ElementTree.fromstring(testxml)
 158         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 159         self.assertTrue(find('media:song') is not None)
 160         self.assertEqual(find('media:song/media:author').text, u'The Author')
 161         self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
 162
 163     def test_smuggle_url(self):
 164         data = {u"ö": u"ö", u"abc": [3]}
 165         url = 'https://foo.bar/baz?x=y#a'
 166         smug_url = smuggle_url(url, data)
 167         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 168         self.assertEqual(url, unsmug_url)
 169         self.assertEqual(data, unsmug_data)
 170
 171         res_url, res_data = unsmuggle_url(url)
 172         self.assertEqual(res_url, url)
 173         self.assertEqual(res_data, None)
 174
 175     def test_shell_quote(self):
 176         args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
 177         self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 178
 179
 180 if __name__ == '__main__':
 181     unittest.main()