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     clean_html,
  22     DateRange,
  23     detect_exe_version,
  24     encodeFilename,
  25     escape_rfc3986,
  26     escape_url,
  27     ExtractorError,
  28     find_xpath_attr,
  29     fix_xml_ampersands,
  30     InAdvancePagedList,
  31     intlist_to_bytes,
  32     is_html,
  33     js_to_json,
  34     limit_length,
  35     OnDemandPagedList,
  36     orderedSet,
  37     parse_duration,
  38     parse_filesize,
  39     parse_iso8601,
  40     read_batch_urls,
  41     sanitize_filename,
  42     sanitize_path,
  43     prepend_extension,
  44     replace_extension,
  45     shell_quote,
  46     smuggle_url,
  47     str_to_int,
  48     strip_jsonp,
  49     struct_unpack,
  50     timeconvert,
  51     unescapeHTML,
  52     unified_strdate,
  53     unsmuggle_url,
  54     uppercase_escape,
  55     lowercase_escape,
  56     url_basename,
  57     urlencode_postdata,
  58     version_tuple,
  59     xpath_with_ns,
  60     xpath_element,
  61     xpath_text,
  62     xpath_attr,
  63     render_table,
  64     match_str,
  65     parse_dfxp_time_expr,
  66     dfxp2srt,
  67     cli_option,
  68     cli_valueless_option,
  69     cli_bool_option,
  70 )
  71 from youtube_dl.compat import (
  72     compat_etree_fromstring,
  73 )
  74
  75
  76 class TestUtil(unittest.TestCase):
  77     def test_timeconvert(self):
  78         self.assertTrue(timeconvert('') is None)
  79         self.assertTrue(timeconvert('bougrg') is None)
  80
  81     def test_sanitize_filename(self):
  82         self.assertEqual(sanitize_filename('abc'), 'abc')
  83         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  84
  85         self.assertEqual(sanitize_filename('123'), '123')
  86
  87         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  88         self.assertFalse('/' in sanitize_filename('abc/de///'))
  89
  90         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  91         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  92         self.assertEqual('yes no', sanitize_filename('yes? no'))
  93         self.assertEqual('this - that', sanitize_filename('this: that'))
  94
  95         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  96         aumlaut = 'ä'
  97         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  98         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
  99         self.assertEqual(sanitize_filename(tests), tests)
 100
 101         self.assertEqual(
 102             sanitize_filename('New World record at 0:12:34'),
 103             'New World record at 0_12_34')
 104
 105         self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
 106         self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
 107         self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
 108         self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
 109
 110         forbidden = '"\0\\/'
 111         for fc in forbidden:
 112             for fbc in forbidden:
 113                 self.assertTrue(fbc not in sanitize_filename(fc))
 114
 115     def test_sanitize_filename_restricted(self):
 116         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
 117         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
 118
 119         self.assertEqual(sanitize_filename('123', restricted=True), '123')
 120
 121         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
 122         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
 123
 124         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
 125         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
 126         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
 127         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 128
 129         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
 130         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
 131         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 132
 133         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 134         for fc in forbidden:
 135             for fbc in forbidden:
 136                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 137
 138         # Handle a common case more neatly
 139         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 140         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 141         # .. but make sure the file name is never empty
 142         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 143         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 144
 145     def test_sanitize_ids(self):
 146         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 147         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 148         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 149
 150     def test_sanitize_path(self):
 151         if sys.platform != 'win32':
 152             return
 153
 154         self.assertEqual(sanitize_path('abc'), 'abc')
 155         self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
 156         self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
 157         self.assertEqual(sanitize_path('abc|def'), 'abc#def')
 158         self.assertEqual(sanitize_path('<>:"|?*'), '#######')
 159         self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
 160         self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
 161
 162         self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
 163         self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
 164
 165         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
 166         self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
 167         self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
 168         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
 169
 170         self.assertEqual(
 171             sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
 172             'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
 173
 174         self.assertEqual(
 175             sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
 176             'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
 177         self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
 178         self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
 179         self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
 180
 181         self.assertEqual(sanitize_path('../abc'), '..\\abc')
 182         self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
 183         self.assertEqual(sanitize_path('./abc'), 'abc')
 184         self.assertEqual(sanitize_path('./../abc'), '..\\abc')
 185
 186     def test_prepend_extension(self):
 187         self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
 188         self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
 189         self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
 190         self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
 191         self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
 192         self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
 193
 194     def test_replace_extension(self):
 195         self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
 196         self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
 197         self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
 198         self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
 199         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
 200         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 201
 202     def test_ordered_set(self):
 203         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 204         self.assertEqual(orderedSet([]), [])
 205         self.assertEqual(orderedSet([1]), [1])
 206         # keep the list ordered
 207         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 208
 209     def test_unescape_html(self):
 210         self.assertEqual(unescapeHTML('%20;'), '%20;')
 211         self.assertEqual(unescapeHTML('&#x2F;'), '/')
 212         self.assertEqual(unescapeHTML('&#47;'), '/')
 213         self.assertEqual(unescapeHTML('&eacute;'), 'é')
 214         self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
 215
 216     def test_daterange(self):
 217         _20century = DateRange("19000101", "20000101")
 218         self.assertFalse("17890714" in _20century)
 219         _ac = DateRange("00010101")
 220         self.assertTrue("19690721" in _ac)
 221         _firstmilenium = DateRange(end="10000101")
 222         self.assertTrue("07110427" in _firstmilenium)
 223
 224     def test_unified_dates(self):
 225         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 226         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 227         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 228         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 229         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
 230         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 231         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 232         self.assertEqual(
 233             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
 234             '20141126')
 235         self.assertEqual(
 236             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
 237             '20150202')
 238         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 239         self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
 240
 241     def test_find_xpath_attr(self):
 242         testxml = '''<root>
 243             <node/>
 244             <node x="a"/>
 245             <node x="a" y="c" />
 246             <node x="b" y="d" />
 247             <node x="" />
 248         </root>'''
 249         doc = compat_etree_fromstring(testxml)
 250
 251         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
 252         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 253         self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
 254         self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
 255         self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
 256         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 257         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
 258         self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
 259         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 260         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
 261         self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
 262
 263     def test_xpath_with_ns(self):
 264         testxml = '''<root xmlns:media="http://example.com/">
 265             <media:song>
 266                 <media:author>The Author</media:author>
 267                 <url>http://server.com/download.mp3</url>
 268             </media:song>
 269         </root>'''
 270         doc = compat_etree_fromstring(testxml)
 271         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 272         self.assertTrue(find('media:song') is not None)
 273         self.assertEqual(find('media:song/media:author').text, 'The Author')
 274         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 275
 276     def test_xpath_element(self):
 277         doc = xml.etree.ElementTree.Element('root')
 278         div = xml.etree.ElementTree.SubElement(doc, 'div')
 279         p = xml.etree.ElementTree.SubElement(div, 'p')
 280         p.text = 'Foo'
 281         self.assertEqual(xpath_element(doc, 'div/p'), p)
 282         self.assertEqual(xpath_element(doc, ['div/p']), p)
 283         self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
 284         self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
 285         self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
 286         self.assertTrue(xpath_element(doc, 'div/bar') is None)
 287         self.assertTrue(xpath_element(doc, ['div/bar']) is None)
 288         self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
 289         self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
 290         self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
 291         self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
 292
 293     def test_xpath_text(self):
 294         testxml = '''<root>
 295             <div>
 296                 <p>Foo</p>
 297             </div>
 298         </root>'''
 299         doc = compat_etree_fromstring(testxml)
 300         self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
 301         self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
 302         self.assertTrue(xpath_text(doc, 'div/bar') is None)
 303         self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
 304
 305     def test_xpath_attr(self):
 306         testxml = '''<root>
 307             <div>
 308                 <p x="a">Foo</p>
 309             </div>
 310         </root>'''
 311         doc = compat_etree_fromstring(testxml)
 312         self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
 313         self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
 314         self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
 315         self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
 316         self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
 317         self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
 318         self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
 319
 320     def test_smuggle_url(self):
 321         data = {"ö": "ö", "abc": [3]}
 322         url = 'https://foo.bar/baz?x=y#a'
 323         smug_url = smuggle_url(url, data)
 324         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 325         self.assertEqual(url, unsmug_url)
 326         self.assertEqual(data, unsmug_data)
 327
 328         res_url, res_data = unsmuggle_url(url)
 329         self.assertEqual(res_url, url)
 330         self.assertEqual(res_data, None)
 331
 332     def test_shell_quote(self):
 333         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 334         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 335
 336     def test_str_to_int(self):
 337         self.assertEqual(str_to_int('123,456'), 123456)
 338         self.assertEqual(str_to_int('123.456'), 123456)
 339
 340     def test_url_basename(self):
 341         self.assertEqual(url_basename('http://foo.de/'), '')
 342         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 343         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 344         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 345         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 346         self.assertEqual(
 347             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 348             'trailer.mp4')
 349
 350     def test_parse_duration(self):
 351         self.assertEqual(parse_duration(None), None)
 352         self.assertEqual(parse_duration(False), None)
 353         self.assertEqual(parse_duration('invalid'), None)
 354         self.assertEqual(parse_duration('1'), 1)
 355         self.assertEqual(parse_duration('1337:12'), 80232)
 356         self.assertEqual(parse_duration('9:12:43'), 33163)
 357         self.assertEqual(parse_duration('12:00'), 720)
 358         self.assertEqual(parse_duration('00:01:01'), 61)
 359         self.assertEqual(parse_duration('x:y'), None)
 360         self.assertEqual(parse_duration('3h11m53s'), 11513)
 361         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 362         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 363         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 364         self.assertEqual(parse_duration('62m45s'), 3765)
 365         self.assertEqual(parse_duration('6m59s'), 419)
 366         self.assertEqual(parse_duration('49s'), 49)
 367         self.assertEqual(parse_duration('0h0m0s'), 0)
 368         self.assertEqual(parse_duration('0m0s'), 0)
 369         self.assertEqual(parse_duration('0s'), 0)
 370         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 371         self.assertEqual(parse_duration('T30M38S'), 1838)
 372         self.assertEqual(parse_duration('5 s'), 5)
 373         self.assertEqual(parse_duration('3 min'), 180)
 374         self.assertEqual(parse_duration('2.5 hours'), 9000)
 375         self.assertEqual(parse_duration('02:03:04'), 7384)
 376         self.assertEqual(parse_duration('01:02:03:04'), 93784)
 377         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
 378         self.assertEqual(parse_duration('87 Min.'), 5220)
 379
 380     def test_fix_xml_ampersands(self):
 381         self.assertEqual(
 382             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 383         self.assertEqual(
 384             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 385             '"&amp;x=y&amp;wrong;&amp;z=a')
 386         self.assertEqual(
 387             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 388             '&amp;&apos;&gt;&lt;&quot;')
 389         self.assertEqual(
 390             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 391         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 392
 393     def test_paged_list(self):
 394         def testPL(size, pagesize, sliceargs, expected):
 395             def get_page(pagenum):
 396                 firstid = pagenum * pagesize
 397                 upto = min(size, pagenum * pagesize + pagesize)
 398                 for i in range(firstid, upto):
 399                     yield i
 400
 401             pl = OnDemandPagedList(get_page, pagesize)
 402             got = pl.getslice(*sliceargs)
 403             self.assertEqual(got, expected)
 404
 405             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 406             got = iapl.getslice(*sliceargs)
 407             self.assertEqual(got, expected)
 408
 409         testPL(5, 2, (), [0, 1, 2, 3, 4])
 410         testPL(5, 2, (1,), [1, 2, 3, 4])
 411         testPL(5, 2, (2,), [2, 3, 4])
 412         testPL(5, 2, (4,), [4])
 413         testPL(5, 2, (0, 3), [0, 1, 2])
 414         testPL(5, 2, (1, 4), [1, 2, 3])
 415         testPL(5, 2, (2, 99), [2, 3, 4])
 416         testPL(5, 2, (20, 99), [])
 417
 418     def test_struct_unpack(self):
 419         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 420
 421     def test_read_batch_urls(self):
 422         f = io.StringIO('''\xef\xbb\xbf foo
 423             bar\r
 424             baz
 425             # More after this line\r
 426             ; or after this
 427             bam''')
 428         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 429
 430     def test_urlencode_postdata(self):
 431         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 432         self.assertTrue(isinstance(data, bytes))
 433
 434     def test_parse_iso8601(self):
 435         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 436         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 437         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 438         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 439         self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
 440         self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
 441
 442     def test_strip_jsonp(self):
 443         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 444         d = json.loads(stripped)
 445         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 446
 447         stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
 448         d = json.loads(stripped)
 449         self.assertEqual(d, {'STATUS': 'OK'})
 450
 451     def test_uppercase_escape(self):
 452         self.assertEqual(uppercase_escape('aä'), 'aä')
 453         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 454
 455     def test_lowercase_escape(self):
 456         self.assertEqual(lowercase_escape('aä'), 'aä')
 457         self.assertEqual(lowercase_escape('\\u0026'), '&')
 458
 459     def test_limit_length(self):
 460         self.assertEqual(limit_length(None, 12), None)
 461         self.assertEqual(limit_length('foo', 12), 'foo')
 462         self.assertTrue(
 463             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 464         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 465
 466     def test_escape_rfc3986(self):
 467         reserved = "!*'();:@&=+$,/?#[]"
 468         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 469         self.assertEqual(escape_rfc3986(reserved), reserved)
 470         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 471         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 472         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 473         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 474         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 475
 476     def test_escape_url(self):
 477         self.assertEqual(
 478             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 479             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 480         )
 481         self.assertEqual(
 482             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 483             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 484         )
 485         self.assertEqual(
 486             escape_url('http://тест.рф/фрагмент'),
 487             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 488         )
 489         self.assertEqual(
 490             escape_url('http://тест.рф/абв?абв=абв#абв'),
 491             'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
 492         )
 493         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 494
 495     def test_js_to_json_realworld(self):
 496         inp = '''{
 497             'clip':{'provider':'pseudo'}
 498         }'''
 499         self.assertEqual(js_to_json(inp), '''{
 500             "clip":{"provider":"pseudo"}
 501         }''')
 502         json.loads(js_to_json(inp))
 503
 504         inp = '''{
 505             'playlist':[{'controls':{'all':null}}]
 506         }'''
 507         self.assertEqual(js_to_json(inp), '''{
 508             "playlist":[{"controls":{"all":null}}]
 509         }''')
 510
 511         inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
 512         self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
 513
 514         inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
 515         json_code = js_to_json(inp)
 516         self.assertEqual(json.loads(json_code), json.loads(inp))
 517
 518     def test_js_to_json_edgecases(self):
 519         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 520         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 521
 522         on = js_to_json('{"abc": true}')
 523         self.assertEqual(json.loads(on), {'abc': True})
 524
 525         # Ignore JavaScript code as well
 526         on = js_to_json('''{
 527             "x": 1,
 528             y: "a",
 529             z: some.code
 530         }''')
 531         d = json.loads(on)
 532         self.assertEqual(d['x'], 1)
 533         self.assertEqual(d['y'], 'a')
 534
 535         on = js_to_json('["abc", "def",]')
 536         self.assertEqual(json.loads(on), ['abc', 'def'])
 537
 538         on = js_to_json('{"abc": "def",}')
 539         self.assertEqual(json.loads(on), {'abc': 'def'})
 540
 541     def test_clean_html(self):
 542         self.assertEqual(clean_html('a:\nb'), 'a: b')
 543         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
 544
 545     def test_intlist_to_bytes(self):
 546         self.assertEqual(
 547             intlist_to_bytes([0, 1, 127, 128, 255]),
 548             b'\x00\x01\x7f\x80\xff')
 549
 550     def test_args_to_str(self):
 551         self.assertEqual(
 552             args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
 553             'foo ba/r -baz \'2 be\' \'\''
 554         )
 555
 556     def test_parse_filesize(self):
 557         self.assertEqual(parse_filesize(None), None)
 558         self.assertEqual(parse_filesize(''), None)
 559         self.assertEqual(parse_filesize('91 B'), 91)
 560         self.assertEqual(parse_filesize('foobar'), None)
 561         self.assertEqual(parse_filesize('2 MiB'), 2097152)
 562         self.assertEqual(parse_filesize('5 GB'), 5000000000)
 563         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
 564         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 565
 566     def test_version_tuple(self):
 567         self.assertEqual(version_tuple('1'), (1,))
 568         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
 569         self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
 570
 571     def test_detect_exe_version(self):
 572         self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
 573 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
 574 configuration: --prefix=/usr --extra-'''), '1.2.1')
 575         self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
 576 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
 577         self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
 578 Trying to open render node...
 579 Success at /dev/dri/renderD128.
 580 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 581
 582     def test_age_restricted(self):
 583         self.assertFalse(age_restricted(None, 10))  # unrestricted content
 584         self.assertFalse(age_restricted(1, None))  # unrestricted policy
 585         self.assertFalse(age_restricted(8, 10))
 586         self.assertTrue(age_restricted(18, 14))
 587         self.assertFalse(age_restricted(18, 18))
 588
 589     def test_is_html(self):
 590         self.assertFalse(is_html(b'\x49\x44\x43<html'))
 591         self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
 592         self.assertTrue(is_html(  # UTF-8 with BOM
 593             b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
 594         self.assertTrue(is_html(  # UTF-16-LE
 595             b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
 596         ))
 597         self.assertTrue(is_html(  # UTF-16-BE
 598             b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
 599         ))
 600         self.assertTrue(is_html(  # UTF-32-BE
 601             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'))
 602         self.assertTrue(is_html(  # UTF-32-LE
 603             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'))
 604
 605     def test_render_table(self):
 606         self.assertEqual(
 607             render_table(
 608                 ['a', 'bcd'],
 609                 [[123, 4], [9999, 51]]),
 610             'a    bcd\n'
 611             '123  4\n'
 612             '9999 51')
 613
 614     def test_match_str(self):
 615         self.assertRaises(ValueError, match_str, 'xy>foobar', {})
 616         self.assertFalse(match_str('xy', {'x': 1200}))
 617         self.assertTrue(match_str('!xy', {'x': 1200}))
 618         self.assertTrue(match_str('x', {'x': 1200}))
 619         self.assertFalse(match_str('!x', {'x': 1200}))
 620         self.assertTrue(match_str('x', {'x': 0}))
 621         self.assertFalse(match_str('x>0', {'x': 0}))
 622         self.assertFalse(match_str('x>0', {}))
 623         self.assertTrue(match_str('x>?0', {}))
 624         self.assertTrue(match_str('x>1K', {'x': 1200}))
 625         self.assertFalse(match_str('x>2K', {'x': 1200}))
 626         self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
 627         self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
 628         self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
 629         self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
 630         self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
 631         self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
 632         self.assertFalse(match_str(
 633             'like_count > 100 & dislike_count <? 50 & description',
 634             {'like_count': 90, 'description': 'foo'}))
 635         self.assertTrue(match_str(
 636             'like_count > 100 & dislike_count <? 50 & description',
 637             {'like_count': 190, 'description': 'foo'}))
 638         self.assertFalse(match_str(
 639             'like_count > 100 & dislike_count <? 50 & description',
 640             {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
 641         self.assertFalse(match_str(
 642             'like_count > 100 & dislike_count <? 50 & description',
 643             {'like_count': 190, 'dislike_count': 10}))
 644
 645     def test_parse_dfxp_time_expr(self):
 646         self.assertEqual(parse_dfxp_time_expr(None), 0.0)
 647         self.assertEqual(parse_dfxp_time_expr(''), 0.0)
 648         self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
 649         self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
 650         self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
 651         self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
 652
 653     def test_dfxp2srt(self):
 654         dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
 655             <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
 656             <body>
 657                 <div xml:lang="en">
 658                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
 659                     <p begin="1" end="2">第二行<br/>♪♪</p>
 660                     <p begin="2" dur="1"><span>Third<br/>Line</span></p>
 661                 </div>
 662             </body>
 663             </tt>'''
 664         srt_data = '''1
 665 00:00:00,000 --> 00:00:01,000
 666 The following line contains Chinese characters and special symbols
 667
 668 2
 669 00:00:01,000 --> 00:00:02,000
 670 第二行
 671 ♪♪
 672
 673 3
 674 00:00:02,000 --> 00:00:03,000
 675 Third
 676 Line
 677
 678 '''
 679         self.assertEqual(dfxp2srt(dfxp_data), srt_data)
 680
 681         dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
 682             <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
 683             <body>
 684                 <div xml:lang="en">
 685                     <p begin="0" end="1">The first line</p>
 686                 </div>
 687             </body>
 688             </tt>'''
 689         srt_data = '''1
 690 00:00:00,000 --> 00:00:01,000
 691 The first line
 692
 693 '''
 694         self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
 695
 696     def test_cli_option(self):
 697         self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
 698         self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
 699         self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
 700
 701     def test_cli_valueless_option(self):
 702         self.assertEqual(cli_valueless_option(
 703             {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
 704         self.assertEqual(cli_valueless_option(
 705             {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
 706         self.assertEqual(cli_valueless_option(
 707             {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
 708         self.assertEqual(cli_valueless_option(
 709             {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
 710         self.assertEqual(cli_valueless_option(
 711             {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
 712         self.assertEqual(cli_valueless_option(
 713             {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
 714
 715     def test_cli_bool_option(self):
 716         self.assertEqual(
 717             cli_bool_option(
 718                 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
 719             ['--no-check-certificate', 'true'])
 720         self.assertEqual(
 721             cli_bool_option(
 722                 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
 723             ['--no-check-certificate=true'])
 724         self.assertEqual(
 725             cli_bool_option(
 726                 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
 727             ['--check-certificate', 'false'])
 728         self.assertEqual(
 729             cli_bool_option(
 730                 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
 731             ['--check-certificate=false'])
 732         self.assertEqual(
 733             cli_bool_option(
 734                 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
 735             ['--check-certificate', 'true'])
 736         self.assertEqual(
 737             cli_bool_option(
 738                 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
 739             ['--check-certificate=true'])
 740
 741
 742 if __name__ == '__main__':
 743     unittest.main()