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