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