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