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

   1 #!/usr/bin/env python
   2 # coding: utf-8
   3
   4 from __future__ import unicode_literals
   5
   6 # Allow direct execution
   7 import os
   8 import sys
   9 import unittest
  10 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
  11
  12
  13 # Various small unit tests
  14 import io
  15 import json
  16 import xml.etree.ElementTree
  17
  18 from youtube_dl.utils import (
  19     age_restricted,
  20     args_to_str,
  21     encode_base_n,
  22     clean_html,
  23     date_from_str,
  24     DateRange,
  25     detect_exe_version,
  26     determine_ext,
  27     dict_get,
  28     encode_compat_str,
  29     encodeFilename,
  30     escape_rfc3986,
  31     escape_url,
  32     extract_attributes,
  33     ExtractorError,
  34     find_xpath_attr,
  35     fix_xml_ampersands,
  36     get_element_by_class,
  37     InAdvancePagedList,
  38     intlist_to_bytes,
  39     is_html,
  40     js_to_json,
  41     limit_length,
  42     mimetype2ext,
  43     month_by_name,
  44     ohdave_rsa_encrypt,
  45     OnDemandPagedList,
  46     orderedSet,
  47     parse_age_limit,
  48     parse_duration,
  49     parse_filesize,
  50     parse_count,
  51     parse_iso8601,
  52     read_batch_urls,
  53     sanitize_filename,
  54     sanitize_path,
  55     prepend_extension,
  56     replace_extension,
  57     remove_start,
  58     remove_end,
  59     remove_quotes,
  60     shell_quote,
  61     smuggle_url,
  62     str_to_int,
  63     strip_jsonp,
  64     timeconvert,
  65     unescapeHTML,
  66     unified_strdate,
  67     unified_timestamp,
  68     unsmuggle_url,
  69     uppercase_escape,
  70     lowercase_escape,
  71     url_basename,
  72     base_url,
  73     urljoin,
  74     urlencode_postdata,
  75     urshift,
  76     update_url_query,
  77     version_tuple,
  78     xpath_with_ns,
  79     xpath_element,
  80     xpath_text,
  81     xpath_attr,
  82     render_table,
  83     match_str,
  84     parse_dfxp_time_expr,
  85     dfxp2srt,
  86     cli_option,
  87     cli_valueless_option,
  88     cli_bool_option,
  89     parse_codecs,
  90 )
  91 from youtube_dl.compat import (
  92     compat_chr,
  93     compat_etree_fromstring,
  94     compat_urlparse,
  95     compat_parse_qs,
  96 )
  97
  98
  99 class TestUtil(unittest.TestCase):
 100     def test_timeconvert(self):
 101         self.assertTrue(timeconvert('') is None)
 102         self.assertTrue(timeconvert('bougrg') is None)
 103
 104     def test_sanitize_filename(self):
 105         self.assertEqual(sanitize_filename('abc'), 'abc')
 106         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
 107
 108         self.assertEqual(sanitize_filename('123'), '123')
 109
 110         self.assertEqual('abc_de', sanitize_filename('abc/de'))
 111         self.assertFalse('/' in sanitize_filename('abc/de///'))
 112
 113         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
 114         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
 115         self.assertEqual('yes no', sanitize_filename('yes? no'))
 116         self.assertEqual('this - that', sanitize_filename('this: that'))
 117
 118         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
 119         aumlaut = 'ä'
 120         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
 121         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
 122         self.assertEqual(sanitize_filename(tests), tests)
 123
 124         self.assertEqual(
 125             sanitize_filename('New World record at 0:12:34'),
 126             'New World record at 0_12_34')
 127
 128         self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
 129         self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
 130         self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
 131         self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
 132
 133         forbidden = '"\0\\/'
 134         for fc in forbidden:
 135             for fbc in forbidden:
 136                 self.assertTrue(fbc not in sanitize_filename(fc))
 137
 138     def test_sanitize_filename_restricted(self):
 139         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
 140         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
 141
 142         self.assertEqual(sanitize_filename('123', restricted=True), '123')
 143
 144         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
 145         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
 146
 147         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
 148         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
 149         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
 150         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 151
 152         tests = 'aäb\u4e2d\u56fd\u7684c'
 153         self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
 154         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 155
 156         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 157         for fc in forbidden:
 158             for fbc in forbidden:
 159                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 160
 161         # Handle a common case more neatly
 162         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 163         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 164         # .. but make sure the file name is never empty
 165         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 166         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 167
 168         self.assertEqual(sanitize_filename(
 169             'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
 170             'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
 171
 172     def test_sanitize_ids(self):
 173         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 174         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 175         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 176
 177     def test_sanitize_path(self):
 178         if sys.platform != 'win32':
 179             return
 180
 181         self.assertEqual(sanitize_path('abc'), 'abc')
 182         self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
 183         self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
 184         self.assertEqual(sanitize_path('abc|def'), 'abc#def')
 185         self.assertEqual(sanitize_path('<>:"|?*'), '#######')
 186         self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
 187         self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
 188
 189         self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
 190         self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
 191
 192         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
 193         self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
 194         self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
 195         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
 196
 197         self.assertEqual(
 198             sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
 199             'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
 200
 201         self.assertEqual(
 202             sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
 203             'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
 204         self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
 205         self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
 206         self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
 207
 208         self.assertEqual(sanitize_path('../abc'), '..\\abc')
 209         self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
 210         self.assertEqual(sanitize_path('./abc'), 'abc')
 211         self.assertEqual(sanitize_path('./../abc'), '..\\abc')
 212
 213     def test_prepend_extension(self):
 214         self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
 215         self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
 216         self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
 217         self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
 218         self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
 219         self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
 220
 221     def test_replace_extension(self):
 222         self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
 223         self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
 224         self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
 225         self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
 226         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
 227         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 228
 229     def test_remove_start(self):
 230         self.assertEqual(remove_start(None, 'A - '), None)
 231         self.assertEqual(remove_start('A - B', 'A - '), 'B')
 232         self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
 233
 234     def test_remove_end(self):
 235         self.assertEqual(remove_end(None, ' - B'), None)
 236         self.assertEqual(remove_end('A - B', ' - B'), 'A')
 237         self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
 238
 239     def test_remove_quotes(self):
 240         self.assertEqual(remove_quotes(None), None)
 241         self.assertEqual(remove_quotes('"'), '"')
 242         self.assertEqual(remove_quotes("'"), "'")
 243         self.assertEqual(remove_quotes(';'), ';')
 244         self.assertEqual(remove_quotes('";'), '";')
 245         self.assertEqual(remove_quotes('""'), '')
 246         self.assertEqual(remove_quotes('";"'), ';')
 247
 248     def test_ordered_set(self):
 249         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 250         self.assertEqual(orderedSet([]), [])
 251         self.assertEqual(orderedSet([1]), [1])
 252         # keep the list ordered
 253         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 254
 255     def test_unescape_html(self):
 256         self.assertEqual(unescapeHTML('%20;'), '%20;')
 257         self.assertEqual(unescapeHTML('&#x2F;'), '/')
 258         self.assertEqual(unescapeHTML('&#47;'), '/')
 259         self.assertEqual(unescapeHTML('&eacute;'), 'é')
 260         self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
 261         # HTML5 entities
 262         self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
 263
 264     def test_date_from_str(self):
 265         self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
 266         self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
 267         self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
 268         self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
 269         self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
 270
 271     def test_daterange(self):
 272         _20century = DateRange("19000101", "20000101")
 273         self.assertFalse("17890714" in _20century)
 274         _ac = DateRange("00010101")
 275         self.assertTrue("19690721" in _ac)
 276         _firstmilenium = DateRange(end="10000101")
 277         self.assertTrue("07110427" in _firstmilenium)
 278
 279     def test_unified_dates(self):
 280         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 281         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 282         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 283         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 284         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
 285         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 286         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 287         self.assertEqual(
 288             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
 289             '20141126')
 290         self.assertEqual(
 291             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
 292             '20150202')
 293         self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
 294         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 295         self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
 296         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
 297         self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
 298
 299     def test_unified_timestamps(self):
 300         self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
 301         self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
 302         self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
 303         self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
 304         self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
 305         self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
 306         self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
 307         self.assertEqual(
 308             unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
 309             1417001400)
 310         self.assertEqual(
 311             unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
 312             1422902860)
 313         self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
 314         self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
 315         self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
 316         self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
 317         self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
 318         self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
 319
 320     def test_determine_ext(self):
 321         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
 322         self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
 323         self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
 324         self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
 325         self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
 326
 327     def test_find_xpath_attr(self):
 328         testxml = '''<root>
 329             <node/>
 330             <node x="a"/>
 331             <node x="a" y="c" />
 332             <node x="b" y="d" />
 333             <node x="" />
 334         </root>'''
 335         doc = compat_etree_fromstring(testxml)
 336
 337         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
 338         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 339         self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
 340         self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
 341         self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
 342         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 343         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
 344         self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
 345         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 346         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
 347         self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
 348
 349     def test_xpath_with_ns(self):
 350         testxml = '''<root xmlns:media="http://example.com/">
 351             <media:song>
 352                 <media:author>The Author</media:author>
 353                 <url>http://server.com/download.mp3</url>
 354             </media:song>
 355         </root>'''
 356         doc = compat_etree_fromstring(testxml)
 357         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 358         self.assertTrue(find('media:song') is not None)
 359         self.assertEqual(find('media:song/media:author').text, 'The Author')
 360         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 361
 362     def test_xpath_element(self):
 363         doc = xml.etree.ElementTree.Element('root')
 364         div = xml.etree.ElementTree.SubElement(doc, 'div')
 365         p = xml.etree.ElementTree.SubElement(div, 'p')
 366         p.text = 'Foo'
 367         self.assertEqual(xpath_element(doc, 'div/p'), p)
 368         self.assertEqual(xpath_element(doc, ['div/p']), p)
 369         self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
 370         self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
 371         self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
 372         self.assertTrue(xpath_element(doc, 'div/bar') is None)
 373         self.assertTrue(xpath_element(doc, ['div/bar']) is None)
 374         self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
 375         self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
 376         self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
 377         self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
 378
 379     def test_xpath_text(self):
 380         testxml = '''<root>
 381             <div>
 382                 <p>Foo</p>
 383             </div>
 384         </root>'''
 385         doc = compat_etree_fromstring(testxml)
 386         self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
 387         self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
 388         self.assertTrue(xpath_text(doc, 'div/bar') is None)
 389         self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
 390
 391     def test_xpath_attr(self):
 392         testxml = '''<root>
 393             <div>
 394                 <p x="a">Foo</p>
 395             </div>
 396         </root>'''
 397         doc = compat_etree_fromstring(testxml)
 398         self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
 399         self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
 400         self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
 401         self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
 402         self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
 403         self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
 404         self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
 405
 406     def test_smuggle_url(self):
 407         data = {"ö": "ö", "abc": [3]}
 408         url = 'https://foo.bar/baz?x=y#a'
 409         smug_url = smuggle_url(url, data)
 410         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 411         self.assertEqual(url, unsmug_url)
 412         self.assertEqual(data, unsmug_data)
 413
 414         res_url, res_data = unsmuggle_url(url)
 415         self.assertEqual(res_url, url)
 416         self.assertEqual(res_data, None)
 417
 418         smug_url = smuggle_url(url, {'a': 'b'})
 419         smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
 420         res_url, res_data = unsmuggle_url(smug_smug_url)
 421         self.assertEqual(res_url, url)
 422         self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
 423
 424     def test_shell_quote(self):
 425         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 426         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 427
 428     def test_str_to_int(self):
 429         self.assertEqual(str_to_int('123,456'), 123456)
 430         self.assertEqual(str_to_int('123.456'), 123456)
 431
 432     def test_url_basename(self):
 433         self.assertEqual(url_basename('http://foo.de/'), '')
 434         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 435         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 436         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 437         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 438         self.assertEqual(
 439             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 440             'trailer.mp4')
 441
 442     def test_base_url(self):
 443         self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
 444         self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
 445         self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
 446         self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
 447         self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
 448
 449     def test_urljoin(self):
 450         self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 451         self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
 452         self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 453         self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 454         self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 455         self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 456         self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
 457         self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 458         self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
 459         self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 460         self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
 461         self.assertEqual(urljoin('http://foo.de/', None), None)
 462         self.assertEqual(urljoin('http://foo.de/', ''), None)
 463         self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
 464
 465     def test_parse_age_limit(self):
 466         self.assertEqual(parse_age_limit(None), None)
 467         self.assertEqual(parse_age_limit(False), None)
 468         self.assertEqual(parse_age_limit('invalid'), None)
 469         self.assertEqual(parse_age_limit(0), 0)
 470         self.assertEqual(parse_age_limit(18), 18)
 471         self.assertEqual(parse_age_limit(21), 21)
 472         self.assertEqual(parse_age_limit(22), None)
 473         self.assertEqual(parse_age_limit('18'), 18)
 474         self.assertEqual(parse_age_limit('18+'), 18)
 475         self.assertEqual(parse_age_limit('PG-13'), 13)
 476         self.assertEqual(parse_age_limit('TV-14'), 14)
 477         self.assertEqual(parse_age_limit('TV-MA'), 17)
 478
 479     def test_parse_duration(self):
 480         self.assertEqual(parse_duration(None), None)
 481         self.assertEqual(parse_duration(False), None)
 482         self.assertEqual(parse_duration('invalid'), None)
 483         self.assertEqual(parse_duration('1'), 1)
 484         self.assertEqual(parse_duration('1337:12'), 80232)
 485         self.assertEqual(parse_duration('9:12:43'), 33163)
 486         self.assertEqual(parse_duration('12:00'), 720)
 487         self.assertEqual(parse_duration('00:01:01'), 61)
 488         self.assertEqual(parse_duration('x:y'), None)
 489         self.assertEqual(parse_duration('3h11m53s'), 11513)
 490         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 491         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 492         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 493         self.assertEqual(parse_duration('62m45s'), 3765)
 494         self.assertEqual(parse_duration('6m59s'), 419)
 495         self.assertEqual(parse_duration('49s'), 49)
 496         self.assertEqual(parse_duration('0h0m0s'), 0)
 497         self.assertEqual(parse_duration('0m0s'), 0)
 498         self.assertEqual(parse_duration('0s'), 0)
 499         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 500         self.assertEqual(parse_duration('T30M38S'), 1838)
 501         self.assertEqual(parse_duration('5 s'), 5)
 502         self.assertEqual(parse_duration('3 min'), 180)
 503         self.assertEqual(parse_duration('2.5 hours'), 9000)
 504         self.assertEqual(parse_duration('02:03:04'), 7384)
 505         self.assertEqual(parse_duration('01:02:03:04'), 93784)
 506         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
 507         self.assertEqual(parse_duration('87 Min.'), 5220)
 508         self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
 509
 510     def test_fix_xml_ampersands(self):
 511         self.assertEqual(
 512             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 513         self.assertEqual(
 514             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 515             '"&amp;x=y&amp;wrong;&amp;z=a')
 516         self.assertEqual(
 517             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 518             '&amp;&apos;&gt;&lt;&quot;')
 519         self.assertEqual(
 520             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 521         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 522
 523     def test_paged_list(self):
 524         def testPL(size, pagesize, sliceargs, expected):
 525             def get_page(pagenum):
 526                 firstid = pagenum * pagesize
 527                 upto = min(size, pagenum * pagesize + pagesize)
 528                 for i in range(firstid, upto):
 529                     yield i
 530
 531             pl = OnDemandPagedList(get_page, pagesize)
 532             got = pl.getslice(*sliceargs)
 533             self.assertEqual(got, expected)
 534
 535             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 536             got = iapl.getslice(*sliceargs)
 537             self.assertEqual(got, expected)
 538
 539         testPL(5, 2, (), [0, 1, 2, 3, 4])
 540         testPL(5, 2, (1,), [1, 2, 3, 4])
 541         testPL(5, 2, (2,), [2, 3, 4])
 542         testPL(5, 2, (4,), [4])
 543         testPL(5, 2, (0, 3), [0, 1, 2])
 544         testPL(5, 2, (1, 4), [1, 2, 3])
 545         testPL(5, 2, (2, 99), [2, 3, 4])
 546         testPL(5, 2, (20, 99), [])
 547
 548     def test_read_batch_urls(self):
 549         f = io.StringIO('''\xef\xbb\xbf foo
 550             bar\r
 551             baz
 552             # More after this line\r
 553             ; or after this
 554             bam''')
 555         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 556
 557     def test_urlencode_postdata(self):
 558         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 559         self.assertTrue(isinstance(data, bytes))
 560
 561     def test_update_url_query(self):
 562         def query_dict(url):
 563             return compat_parse_qs(compat_urlparse.urlparse(url).query)
 564         self.assertEqual(query_dict(update_url_query(
 565             'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
 566             query_dict('http://example.com/path?quality=HD&format=mp4'))
 567         self.assertEqual(query_dict(update_url_query(
 568             'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
 569             query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
 570         self.assertEqual(query_dict(update_url_query(
 571             'http://example.com/path', {'fields': 'id,formats,subtitles'})),
 572             query_dict('http://example.com/path?fields=id,formats,subtitles'))
 573         self.assertEqual(query_dict(update_url_query(
 574             'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
 575             query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
 576         self.assertEqual(query_dict(update_url_query(
 577             'http://example.com/path?manifest=f4m', {'manifest': []})),
 578             query_dict('http://example.com/path'))
 579         self.assertEqual(query_dict(update_url_query(
 580             'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
 581             query_dict('http://example.com/path?system=LINUX'))
 582         self.assertEqual(query_dict(update_url_query(
 583             'http://example.com/path', {'fields': b'id,formats,subtitles'})),
 584             query_dict('http://example.com/path?fields=id,formats,subtitles'))
 585         self.assertEqual(query_dict(update_url_query(
 586             'http://example.com/path', {'width': 1080, 'height': 720})),
 587             query_dict('http://example.com/path?width=1080&height=720'))
 588         self.assertEqual(query_dict(update_url_query(
 589             'http://example.com/path', {'bitrate': 5020.43})),
 590             query_dict('http://example.com/path?bitrate=5020.43'))
 591         self.assertEqual(query_dict(update_url_query(
 592             'http://example.com/path', {'test': '第二行тест'})),
 593             query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
 594
 595     def test_dict_get(self):
 596         FALSE_VALUES = {
 597             'none': None,
 598             'false': False,
 599             'zero': 0,
 600             'empty_string': '',
 601             'empty_list': [],
 602         }
 603         d = FALSE_VALUES.copy()
 604         d['a'] = 42
 605         self.assertEqual(dict_get(d, 'a'), 42)
 606         self.assertEqual(dict_get(d, 'b'), None)
 607         self.assertEqual(dict_get(d, 'b', 42), 42)
 608         self.assertEqual(dict_get(d, ('a', )), 42)
 609         self.assertEqual(dict_get(d, ('b', 'a', )), 42)
 610         self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
 611         self.assertEqual(dict_get(d, ('b', 'c', )), None)
 612         self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
 613         for key, false_value in FALSE_VALUES.items():
 614             self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
 615             self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
 616
 617     def test_encode_compat_str(self):
 618         self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
 619         self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
 620
 621     def test_parse_iso8601(self):
 622         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 623         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 624         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 625         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 626         self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
 627         self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
 628
 629     def test_strip_jsonp(self):
 630         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 631         d = json.loads(stripped)
 632         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 633
 634         stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
 635         d = json.loads(stripped)
 636         self.assertEqual(d, {'STATUS': 'OK'})
 637
 638         stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
 639         d = json.loads(stripped)
 640         self.assertEqual(d, {'status': 'success'})
 641
 642     def test_uppercase_escape(self):
 643         self.assertEqual(uppercase_escape('aä'), 'aä')
 644         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 645
 646     def test_lowercase_escape(self):
 647         self.assertEqual(lowercase_escape('aä'), 'aä')
 648         self.assertEqual(lowercase_escape('\\u0026'), '&')
 649
 650     def test_limit_length(self):
 651         self.assertEqual(limit_length(None, 12), None)
 652         self.assertEqual(limit_length('foo', 12), 'foo')
 653         self.assertTrue(
 654             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 655         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 656
 657     def test_mimetype2ext(self):
 658         self.assertEqual(mimetype2ext(None), None)
 659         self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
 660         self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
 661         self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
 662         self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
 663         self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
 664
 665     def test_month_by_name(self):
 666         self.assertEqual(month_by_name(None), None)
 667         self.assertEqual(month_by_name('December', 'en'), 12)
 668         self.assertEqual(month_by_name('décembre', 'fr'), 12)
 669         self.assertEqual(month_by_name('December'), 12)
 670         self.assertEqual(month_by_name('décembre'), None)
 671         self.assertEqual(month_by_name('Unknown', 'unknown'), None)
 672
 673     def test_parse_codecs(self):
 674         self.assertEqual(parse_codecs(''), {})
 675         self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
 676             'vcodec': 'avc1.77.30',
 677             'acodec': 'mp4a.40.2',
 678         })
 679         self.assertEqual(parse_codecs('mp4a.40.2'), {
 680             'vcodec': 'none',
 681             'acodec': 'mp4a.40.2',
 682         })
 683         self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
 684             'vcodec': 'avc1.42001e',
 685             'acodec': 'mp4a.40.5',
 686         })
 687         self.assertEqual(parse_codecs('avc3.640028'), {
 688             'vcodec': 'avc3.640028',
 689             'acodec': 'none',
 690         })
 691         self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
 692             'vcodec': 'h264',
 693             'acodec': 'aac',
 694         })
 695
 696     def test_escape_rfc3986(self):
 697         reserved = "!*'();:@&=+$,/?#[]"
 698         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 699         self.assertEqual(escape_rfc3986(reserved), reserved)
 700         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 701         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 702         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 703         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 704         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 705
 706     def test_escape_url(self):
 707         self.assertEqual(
 708             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 709             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 710         )
 711         self.assertEqual(
 712             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 713             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 714         )
 715         self.assertEqual(
 716             escape_url('http://тест.рф/фрагмент'),
 717             'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 718         )
 719         self.assertEqual(
 720             escape_url('http://тест.рф/абв?абв=абв#абв'),
 721             'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
 722         )
 723         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 724
 725     def test_js_to_json_realworld(self):
 726         inp = '''{
 727             'clip':{'provider':'pseudo'}
 728         }'''
 729         self.assertEqual(js_to_json(inp), '''{
 730             "clip":{"provider":"pseudo"}
 731         }''')
 732         json.loads(js_to_json(inp))
 733
 734         inp = '''{
 735             'playlist':[{'controls':{'all':null}}]
 736         }'''
 737         self.assertEqual(js_to_json(inp), '''{
 738             "playlist":[{"controls":{"all":null}}]
 739         }''')
 740
 741         inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
 742         self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
 743
 744         inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
 745         json_code = js_to_json(inp)
 746         self.assertEqual(json.loads(json_code), json.loads(inp))
 747
 748         inp = '''{
 749             0:{src:'skipped', type: 'application/dash+xml'},
 750             1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
 751         }'''
 752         self.assertEqual(js_to_json(inp), '''{
 753             "0":{"src":"skipped", "type": "application/dash+xml"},
 754             "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
 755         }''')
 756
 757         inp = '''{"foo":101}'''
 758         self.assertEqual(js_to_json(inp), '''{"foo":101}''')
 759
 760         inp = '''{"duration": "00:01:07"}'''
 761         self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
 762
 763     def test_js_to_json_edgecases(self):
 764         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 765         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 766
 767         on = js_to_json('{"abc": true}')
 768         self.assertEqual(json.loads(on), {'abc': True})
 769
 770         # Ignore JavaScript code as well
 771         on = js_to_json('''{
 772             "x": 1,
 773             y: "a",
 774             z: some.code
 775         }''')
 776         d = json.loads(on)
 777         self.assertEqual(d['x'], 1)
 778         self.assertEqual(d['y'], 'a')
 779
 780         on = js_to_json('["abc", "def",]')
 781         self.assertEqual(json.loads(on), ['abc', 'def'])
 782
 783         on = js_to_json('{"abc": "def",}')
 784         self.assertEqual(json.loads(on), {'abc': 'def'})
 785
 786         on = js_to_json('{ 0: /* " \n */ ",]" , }')
 787         self.assertEqual(json.loads(on), {'0': ',]'})
 788
 789         on = js_to_json(r'["<p>x<\/p>"]')
 790         self.assertEqual(json.loads(on), ['<p>x</p>'])
 791
 792         on = js_to_json(r'["\xaa"]')
 793         self.assertEqual(json.loads(on), ['\u00aa'])
 794
 795         on = js_to_json("['a\\\nb']")
 796         self.assertEqual(json.loads(on), ['ab'])
 797
 798         on = js_to_json('{0xff:0xff}')
 799         self.assertEqual(json.loads(on), {'255': 255})
 800
 801         on = js_to_json('{077:077}')
 802         self.assertEqual(json.loads(on), {'63': 63})
 803
 804         on = js_to_json('{42:42}')
 805         self.assertEqual(json.loads(on), {'42': 42})
 806
 807     def test_extract_attributes(self):
 808         self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
 809         self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
 810         self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
 811         self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
 812         self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
 813         self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
 814         self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
 815         self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'})  # XML
 816         self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
 817         self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'})  # HTML 3.2
 818         self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'})  # HTML 4.0
 819         self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
 820         self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
 821         self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
 822         self.assertEqual(extract_attributes('<e x >'), {'x': None})
 823         self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
 824         self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
 825         self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
 826         self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
 827         self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
 828         self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
 829         self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
 830         self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'})  # Names lowercased
 831         self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
 832         self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
 833         self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
 834         self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
 835         self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
 836         # "Narrow" Python builds don't support unicode code points outside BMP.
 837         try:
 838             compat_chr(0x10000)
 839             supports_outside_bmp = True
 840         except ValueError:
 841             supports_outside_bmp = False
 842         if supports_outside_bmp:
 843             self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
 844
 845     def test_clean_html(self):
 846         self.assertEqual(clean_html('a:\nb'), 'a: b')
 847         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
 848
 849     def test_intlist_to_bytes(self):
 850         self.assertEqual(
 851             intlist_to_bytes([0, 1, 127, 128, 255]),
 852             b'\x00\x01\x7f\x80\xff')
 853
 854     def test_args_to_str(self):
 855         self.assertEqual(
 856             args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
 857             'foo ba/r -baz \'2 be\' \'\''
 858         )
 859
 860     def test_parse_filesize(self):
 861         self.assertEqual(parse_filesize(None), None)
 862         self.assertEqual(parse_filesize(''), None)
 863         self.assertEqual(parse_filesize('91 B'), 91)
 864         self.assertEqual(parse_filesize('foobar'), None)
 865         self.assertEqual(parse_filesize('2 MiB'), 2097152)
 866         self.assertEqual(parse_filesize('5 GB'), 5000000000)
 867         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
 868         self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
 869         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 870         self.assertEqual(parse_filesize('1,24 kb'), 1240)
 871         self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
 872
 873     def test_parse_count(self):
 874         self.assertEqual(parse_count(None), None)
 875         self.assertEqual(parse_count(''), None)
 876         self.assertEqual(parse_count('0'), 0)
 877         self.assertEqual(parse_count('1000'), 1000)
 878         self.assertEqual(parse_count('1.000'), 1000)
 879         self.assertEqual(parse_count('1.1k'), 1100)
 880         self.assertEqual(parse_count('1.1kk'), 1100000)
 881         self.assertEqual(parse_count('1.1kk '), 1100000)
 882         self.assertEqual(parse_count('1.1kk views'), 1100000)
 883
 884     def test_version_tuple(self):
 885         self.assertEqual(version_tuple('1'), (1,))
 886         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
 887         self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
 888
 889     def test_detect_exe_version(self):
 890         self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
 891 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
 892 configuration: --prefix=/usr --extra-'''), '1.2.1')
 893         self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
 894 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
 895         self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
 896 Trying to open render node...
 897 Success at /dev/dri/renderD128.
 898 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 899
 900     def test_age_restricted(self):
 901         self.assertFalse(age_restricted(None, 10))  # unrestricted content
 902         self.assertFalse(age_restricted(1, None))  # unrestricted policy
 903         self.assertFalse(age_restricted(8, 10))
 904         self.assertTrue(age_restricted(18, 14))
 905         self.assertFalse(age_restricted(18, 18))
 906
 907     def test_is_html(self):
 908         self.assertFalse(is_html(b'\x49\x44\x43<html'))
 909         self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
 910         self.assertTrue(is_html(  # UTF-8 with BOM
 911             b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
 912         self.assertTrue(is_html(  # UTF-16-LE
 913             b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
 914         ))
 915         self.assertTrue(is_html(  # UTF-16-BE
 916             b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
 917         ))
 918         self.assertTrue(is_html(  # UTF-32-BE
 919             b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
 920         self.assertTrue(is_html(  # UTF-32-LE
 921             b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
 922
 923     def test_render_table(self):
 924         self.assertEqual(
 925             render_table(
 926                 ['a', 'bcd'],
 927                 [[123, 4], [9999, 51]]),
 928             'a    bcd\n'
 929             '123  4\n'
 930             '9999 51')
 931
 932     def test_match_str(self):
 933         self.assertRaises(ValueError, match_str, 'xy>foobar', {})
 934         self.assertFalse(match_str('xy', {'x': 1200}))
 935         self.assertTrue(match_str('!xy', {'x': 1200}))
 936         self.assertTrue(match_str('x', {'x': 1200}))
 937         self.assertFalse(match_str('!x', {'x': 1200}))
 938         self.assertTrue(match_str('x', {'x': 0}))
 939         self.assertFalse(match_str('x>0', {'x': 0}))
 940         self.assertFalse(match_str('x>0', {}))
 941         self.assertTrue(match_str('x>?0', {}))
 942         self.assertTrue(match_str('x>1K', {'x': 1200}))
 943         self.assertFalse(match_str('x>2K', {'x': 1200}))
 944         self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
 945         self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
 946         self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
 947         self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
 948         self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
 949         self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
 950         self.assertFalse(match_str(
 951             'like_count > 100 & dislike_count <? 50 & description',
 952             {'like_count': 90, 'description': 'foo'}))
 953         self.assertTrue(match_str(
 954             'like_count > 100 & dislike_count <? 50 & description',
 955             {'like_count': 190, 'description': 'foo'}))
 956         self.assertFalse(match_str(
 957             'like_count > 100 & dislike_count <? 50 & description',
 958             {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
 959         self.assertFalse(match_str(
 960             'like_count > 100 & dislike_count <? 50 & description',
 961             {'like_count': 190, 'dislike_count': 10}))
 962
 963     def test_parse_dfxp_time_expr(self):
 964         self.assertEqual(parse_dfxp_time_expr(None), None)
 965         self.assertEqual(parse_dfxp_time_expr(''), None)
 966         self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
 967         self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
 968         self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
 969         self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
 970         self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
 971
 972     def test_dfxp2srt(self):
 973         dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
 974             <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
 975             <body>
 976                 <div xml:lang="en">
 977                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
 978                     <p begin="1" end="2">第二行<br/>♪♪</p>
 979                     <p begin="2" dur="1"><span>Third<br/>Line</span></p>
 980                     <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
 981                     <p begin="-1" end="-1">Ignore, two</p>
 982                     <p begin="3" dur="-1">Ignored, three</p>
 983                 </div>
 984             </body>
 985             </tt>'''
 986         srt_data = '''1
 987 00:00:00,000 --> 00:00:01,000
 988 The following line contains Chinese characters and special symbols
 989
 990 2
 991 00:00:01,000 --> 00:00:02,000
 992 第二行
 993 ♪♪
 994
 995 3
 996 00:00:02,000 --> 00:00:03,000
 997 Third
 998 Line
 999
1000 '''
1001         self.assertEqual(dfxp2srt(dfxp_data), srt_data)
1002
1003         dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
1004             <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1005             <body>
1006                 <div xml:lang="en">
1007                     <p begin="0" end="1">The first line</p>
1008                 </div>
1009             </body>
1010             </tt>'''
1011         srt_data = '''1
1012 00:00:00,000 --> 00:00:01,000
1013 The first line
1014
1015 '''
1016         self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
1017
1018     def test_cli_option(self):
1019         self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1020         self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
1021         self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1022         self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
1023
1024     def test_cli_valueless_option(self):
1025         self.assertEqual(cli_valueless_option(
1026             {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1027         self.assertEqual(cli_valueless_option(
1028             {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
1029         self.assertEqual(cli_valueless_option(
1030             {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1031         self.assertEqual(cli_valueless_option(
1032             {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
1033         self.assertEqual(cli_valueless_option(
1034             {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
1035         self.assertEqual(cli_valueless_option(
1036             {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1037
1038     def test_cli_bool_option(self):
1039         self.assertEqual(
1040             cli_bool_option(
1041                 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
1042             ['--no-check-certificate', 'true'])
1043         self.assertEqual(
1044             cli_bool_option(
1045                 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
1046             ['--no-check-certificate=true'])
1047         self.assertEqual(
1048             cli_bool_option(
1049                 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1050             ['--check-certificate', 'false'])
1051         self.assertEqual(
1052             cli_bool_option(
1053                 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1054             ['--check-certificate=false'])
1055         self.assertEqual(
1056             cli_bool_option(
1057                 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1058             ['--check-certificate', 'true'])
1059         self.assertEqual(
1060             cli_bool_option(
1061                 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1062             ['--check-certificate=true'])
1063
1064     def test_ohdave_rsa_encrypt(self):
1065         N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1066         e = 65537
1067
1068         self.assertEqual(
1069             ohdave_rsa_encrypt(b'aa111222', e, N),
1070             '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1071
1072     def test_encode_base_n(self):
1073         self.assertEqual(encode_base_n(0, 30), '0')
1074         self.assertEqual(encode_base_n(80, 30), '2k')
1075
1076         custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1077         self.assertEqual(encode_base_n(0, 30, custom_table), '9')
1078         self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
1079
1080         self.assertRaises(ValueError, encode_base_n, 0, 70)
1081         self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
1082
1083     def test_urshift(self):
1084         self.assertEqual(urshift(3, 1), 1)
1085         self.assertEqual(urshift(-3, 1), 2147483646)
1086
1087     def test_get_element_by_class(self):
1088         html = '''
1089             <span class="foo bar">nice</span>
1090         '''
1091
1092         self.assertEqual(get_element_by_class('foo', html), 'nice')
1093         self.assertEqual(get_element_by_class('no-such-class', html), None)
1094
1095
1096 if __name__ == '__main__':
1097     unittest.main()