_ 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     clean_html,
  22     DateRange,
  23     detect_exe_version,
  24     encodeFilename,
  25     escape_rfc3986,
  26     escape_url,
  27     find_xpath_attr,
  28     fix_xml_ampersands,
  29     InAdvancePagedList,
  30     intlist_to_bytes,
  31     is_html,
  32     js_to_json,
  33     limit_length,
  34     OnDemandPagedList,
  35     orderedSet,
  36     parse_duration,
  37     parse_filesize,
  38     parse_iso8601,
  39     read_batch_urls,
  40     sanitize_filename,
  41     shell_quote,
  42     smuggle_url,
  43     str_to_int,
  44     strip_jsonp,
  45     struct_unpack,
  46     timeconvert,
  47     unescapeHTML,
  48     unified_strdate,
  49     unsmuggle_url,
  50     uppercase_escape,
  51     url_basename,
  52     urlencode_postdata,
  53     version_tuple,
  54     xpath_with_ns,
  55 )
  56
  57
  58 class TestUtil(unittest.TestCase):
  59     def test_timeconvert(self):
  60         self.assertTrue(timeconvert('') is None)
  61         self.assertTrue(timeconvert('bougrg') is None)
  62
  63     def test_sanitize_filename(self):
  64         self.assertEqual(sanitize_filename('abc'), 'abc')
  65         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  66
  67         self.assertEqual(sanitize_filename('123'), '123')
  68
  69         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  70         self.assertFalse('/' in sanitize_filename('abc/de///'))
  71
  72         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  73         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  74         self.assertEqual('yes no', sanitize_filename('yes? no'))
  75         self.assertEqual('this - that', sanitize_filename('this: that'))
  76
  77         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  78         aumlaut = 'ä'
  79         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  80         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
  81         self.assertEqual(sanitize_filename(tests), tests)
  82
  83         self.assertEqual(
  84             sanitize_filename('New World record at 0:12:34'),
  85             'New World record at 0_12_34')
  86
  87         forbidden = '"\0\\/'
  88         for fc in forbidden:
  89             for fbc in forbidden:
  90                 self.assertTrue(fbc not in sanitize_filename(fc))
  91
  92     def test_sanitize_filename_restricted(self):
  93         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  94         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  95
  96         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  97
  98         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  99         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
 100
 101         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
 102         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
 103         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
 104         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 105
 106         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
 107         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
 108         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 109
 110         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 111         for fc in forbidden:
 112             for fbc in forbidden:
 113                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 114
 115         # Handle a common case more neatly
 116         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 117         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 118         # .. but make sure the file name is never empty
 119         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 120         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 121
 122     def test_sanitize_ids(self):
 123         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 124         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 125         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 126
 127     def test_ordered_set(self):
 128         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 129         self.assertEqual(orderedSet([]), [])
 130         self.assertEqual(orderedSet([1]), [1])
 131         # keep the list ordered
 132         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 133
 134     def test_unescape_html(self):
 135         self.assertEqual(unescapeHTML('%20;'), '%20;')
 136         self.assertEqual(
 137             unescapeHTML('&eacute;'), 'é')
 138
 139     def test_daterange(self):
 140         _20century = DateRange("19000101", "20000101")
 141         self.assertFalse("17890714" in _20century)
 142         _ac = DateRange("00010101")
 143         self.assertTrue("19690721" in _ac)
 144         _firstmilenium = DateRange(end="10000101")
 145         self.assertTrue("07110427" in _firstmilenium)
 146
 147     def test_unified_dates(self):
 148         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 149         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 150         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 151         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 152         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
 153         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 154         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 155         self.assertEqual(
 156             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
 157             '20141126')
 158
 159     def test_find_xpath_attr(self):
 160         testxml = '''<root>
 161             <node/>
 162             <node x="a"/>
 163             <node x="a" y="c" />
 164             <node x="b" y="d" />
 165         </root>'''
 166         doc = xml.etree.ElementTree.fromstring(testxml)
 167
 168         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 169         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 170         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 171
 172     def test_xpath_with_ns(self):
 173         testxml = '''<root xmlns:media="http://example.com/">
 174             <media:song>
 175                 <media:author>The Author</media:author>
 176                 <url>http://server.com/download.mp3</url>
 177             </media:song>
 178         </root>'''
 179         doc = xml.etree.ElementTree.fromstring(testxml)
 180         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 181         self.assertTrue(find('media:song') is not None)
 182         self.assertEqual(find('media:song/media:author').text, 'The Author')
 183         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 184
 185     def test_smuggle_url(self):
 186         data = {"ö": "ö", "abc": [3]}
 187         url = 'https://foo.bar/baz?x=y#a'
 188         smug_url = smuggle_url(url, data)
 189         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 190         self.assertEqual(url, unsmug_url)
 191         self.assertEqual(data, unsmug_data)
 192
 193         res_url, res_data = unsmuggle_url(url)
 194         self.assertEqual(res_url, url)
 195         self.assertEqual(res_data, None)
 196
 197     def test_shell_quote(self):
 198         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 199         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 200
 201     def test_str_to_int(self):
 202         self.assertEqual(str_to_int('123,456'), 123456)
 203         self.assertEqual(str_to_int('123.456'), 123456)
 204
 205     def test_url_basename(self):
 206         self.assertEqual(url_basename('http://foo.de/'), '')
 207         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 208         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 209         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 210         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 211         self.assertEqual(
 212             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 213             'trailer.mp4')
 214
 215     def test_parse_duration(self):
 216         self.assertEqual(parse_duration(None), None)
 217         self.assertEqual(parse_duration(False), None)
 218         self.assertEqual(parse_duration('invalid'), None)
 219         self.assertEqual(parse_duration('1'), 1)
 220         self.assertEqual(parse_duration('1337:12'), 80232)
 221         self.assertEqual(parse_duration('9:12:43'), 33163)
 222         self.assertEqual(parse_duration('12:00'), 720)
 223         self.assertEqual(parse_duration('00:01:01'), 61)
 224         self.assertEqual(parse_duration('x:y'), None)
 225         self.assertEqual(parse_duration('3h11m53s'), 11513)
 226         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 227         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 228         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 229         self.assertEqual(parse_duration('62m45s'), 3765)
 230         self.assertEqual(parse_duration('6m59s'), 419)
 231         self.assertEqual(parse_duration('49s'), 49)
 232         self.assertEqual(parse_duration('0h0m0s'), 0)
 233         self.assertEqual(parse_duration('0m0s'), 0)
 234         self.assertEqual(parse_duration('0s'), 0)
 235         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 236         self.assertEqual(parse_duration('T30M38S'), 1838)
 237         self.assertEqual(parse_duration('5 s'), 5)
 238         self.assertEqual(parse_duration('3 min'), 180)
 239         self.assertEqual(parse_duration('2.5 hours'), 9000)
 240
 241     def test_fix_xml_ampersands(self):
 242         self.assertEqual(
 243             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 244         self.assertEqual(
 245             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 246             '"&amp;x=y&amp;wrong;&amp;z=a')
 247         self.assertEqual(
 248             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 249             '&amp;&apos;&gt;&lt;&quot;')
 250         self.assertEqual(
 251             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 252         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 253
 254     def test_paged_list(self):
 255         def testPL(size, pagesize, sliceargs, expected):
 256             def get_page(pagenum):
 257                 firstid = pagenum * pagesize
 258                 upto = min(size, pagenum * pagesize + pagesize)
 259                 for i in range(firstid, upto):
 260                     yield i
 261
 262             pl = OnDemandPagedList(get_page, pagesize)
 263             got = pl.getslice(*sliceargs)
 264             self.assertEqual(got, expected)
 265
 266             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 267             got = iapl.getslice(*sliceargs)
 268             self.assertEqual(got, expected)
 269
 270         testPL(5, 2, (), [0, 1, 2, 3, 4])
 271         testPL(5, 2, (1,), [1, 2, 3, 4])
 272         testPL(5, 2, (2,), [2, 3, 4])
 273         testPL(5, 2, (4,), [4])
 274         testPL(5, 2, (0, 3), [0, 1, 2])
 275         testPL(5, 2, (1, 4), [1, 2, 3])
 276         testPL(5, 2, (2, 99), [2, 3, 4])
 277         testPL(5, 2, (20, 99), [])
 278
 279     def test_struct_unpack(self):
 280         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 281
 282     def test_read_batch_urls(self):
 283         f = io.StringIO('''\xef\xbb\xbf foo
 284             bar\r
 285             baz
 286             # More after this line\r
 287             ; or after this
 288             bam''')
 289         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 290
 291     def test_urlencode_postdata(self):
 292         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 293         self.assertTrue(isinstance(data, bytes))
 294
 295     def test_parse_iso8601(self):
 296         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 297         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 298         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 299         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 300
 301     def test_strip_jsonp(self):
 302         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 303         d = json.loads(stripped)
 304         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 305
 306         stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
 307         d = json.loads(stripped)
 308         self.assertEqual(d, {'STATUS': 'OK'})
 309
 310     def test_uppercase_escape(self):
 311         self.assertEqual(uppercase_escape('aä'), 'aä')
 312         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 313
 314     def test_limit_length(self):
 315         self.assertEqual(limit_length(None, 12), None)
 316         self.assertEqual(limit_length('foo', 12), 'foo')
 317         self.assertTrue(
 318             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 319         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 320
 321     def test_escape_rfc3986(self):
 322         reserved = "!*'();:@&=+$,/?#[]"
 323         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 324         self.assertEqual(escape_rfc3986(reserved), reserved)
 325         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 326         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 327         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 328         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 329         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 330
 331     def test_escape_url(self):
 332         self.assertEqual(
 333             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 334             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 335         )
 336         self.assertEqual(
 337             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 338             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 339         )
 340         self.assertEqual(
 341             escape_url('http://тест.рф/фрагмент'),
 342             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 343         )
 344         self.assertEqual(
 345             escape_url('http://тест.рф/абв?абв=абв#абв'),
 346             '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'
 347         )
 348         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 349
 350     def test_js_to_json_realworld(self):
 351         inp = '''{
 352             'clip':{'provider':'pseudo'}
 353         }'''
 354         self.assertEqual(js_to_json(inp), '''{
 355             "clip":{"provider":"pseudo"}
 356         }''')
 357         json.loads(js_to_json(inp))
 358
 359         inp = '''{
 360             'playlist':[{'controls':{'all':null}}]
 361         }'''
 362         self.assertEqual(js_to_json(inp), '''{
 363             "playlist":[{"controls":{"all":null}}]
 364         }''')
 365
 366     def test_js_to_json_edgecases(self):
 367         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 368         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 369
 370         on = js_to_json('{"abc": true}')
 371         self.assertEqual(json.loads(on), {'abc': True})
 372
 373     def test_clean_html(self):
 374         self.assertEqual(clean_html('a:\nb'), 'a: b')
 375         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
 376
 377     def test_intlist_to_bytes(self):
 378         self.assertEqual(
 379             intlist_to_bytes([0, 1, 127, 128, 255]),
 380             b'\x00\x01\x7f\x80\xff')
 381
 382     def test_args_to_str(self):
 383         self.assertEqual(
 384             args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
 385             'foo ba/r -baz \'2 be\' \'\''
 386         )
 387
 388     def test_parse_filesize(self):
 389         self.assertEqual(parse_filesize(None), None)
 390         self.assertEqual(parse_filesize(''), None)
 391         self.assertEqual(parse_filesize('91 B'), 91)
 392         self.assertEqual(parse_filesize('foobar'), None)
 393         self.assertEqual(parse_filesize('2 MiB'), 2097152)
 394         self.assertEqual(parse_filesize('5 GB'), 5000000000)
 395         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
 396         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 397
 398     def test_version_tuple(self):
 399         self.assertEqual(version_tuple('1'), (1,))
 400         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
 401         self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
 402
 403     def test_detect_exe_version(self):
 404         self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
 405 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
 406 configuration: --prefix=/usr --extra-'''), '1.2.1')
 407         self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
 408 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
 409         self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
 410 Trying to open render node...
 411 Success at /dev/dri/renderD128.
 412 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 413
 414     def test_age_restricted(self):
 415         self.assertFalse(age_restricted(None, 10))  # unrestricted content
 416         self.assertFalse(age_restricted(1, None))  # unrestricted policy
 417         self.assertFalse(age_restricted(8, 10))
 418         self.assertTrue(age_restricted(18, 14))
 419         self.assertFalse(age_restricted(18, 18))
 420
 421     def test_is_html(self):
 422         self.assertFalse(is_html(b'\x49\x44\x43<html'))
 423         self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
 424         self.assertTrue(is_html(  # UTF-8 with BOM
 425             b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
 426         self.assertTrue(is_html(  # UTF-16-LE
 427             b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
 428         ))
 429         self.assertTrue(is_html(  # UTF-16-BE
 430             b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
 431         ))
 432         self.assertTrue(is_html(  # UTF-32-BE
 433             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'))
 434         self.assertTrue(is_html(  # UTF-32-LE
 435             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'))
 436
 437 if __name__ == '__main__':
 438     unittest.main()