_ 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     render_table,
  56 )
  57
  58
  59 class TestUtil(unittest.TestCase):
  60     def test_timeconvert(self):
  61         self.assertTrue(timeconvert('') is None)
  62         self.assertTrue(timeconvert('bougrg') is None)
  63
  64     def test_sanitize_filename(self):
  65         self.assertEqual(sanitize_filename('abc'), 'abc')
  66         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  67
  68         self.assertEqual(sanitize_filename('123'), '123')
  69
  70         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  71         self.assertFalse('/' in sanitize_filename('abc/de///'))
  72
  73         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  74         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  75         self.assertEqual('yes no', sanitize_filename('yes? no'))
  76         self.assertEqual('this - that', sanitize_filename('this: that'))
  77
  78         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  79         aumlaut = 'ä'
  80         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  81         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
  82         self.assertEqual(sanitize_filename(tests), tests)
  83
  84         self.assertEqual(
  85             sanitize_filename('New World record at 0:12:34'),
  86             'New World record at 0_12_34')
  87
  88         forbidden = '"\0\\/'
  89         for fc in forbidden:
  90             for fbc in forbidden:
  91                 self.assertTrue(fbc not in sanitize_filename(fc))
  92
  93     def test_sanitize_filename_restricted(self):
  94         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  95         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  96
  97         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  98
  99         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
 100         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
 101
 102         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
 103         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
 104         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
 105         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
 106
 107         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
 108         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
 109         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 110
 111         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 112         for fc in forbidden:
 113             for fbc in forbidden:
 114                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 115
 116         # Handle a common case more neatly
 117         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 118         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 119         # .. but make sure the file name is never empty
 120         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 121         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 122
 123     def test_sanitize_ids(self):
 124         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 125         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 126         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 127
 128     def test_ordered_set(self):
 129         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 130         self.assertEqual(orderedSet([]), [])
 131         self.assertEqual(orderedSet([1]), [1])
 132         # keep the list ordered
 133         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 134
 135     def test_unescape_html(self):
 136         self.assertEqual(unescapeHTML('%20;'), '%20;')
 137         self.assertEqual(
 138             unescapeHTML('&eacute;'), 'é')
 139
 140     def test_daterange(self):
 141         _20century = DateRange("19000101", "20000101")
 142         self.assertFalse("17890714" in _20century)
 143         _ac = DateRange("00010101")
 144         self.assertTrue("19690721" in _ac)
 145         _firstmilenium = DateRange(end="10000101")
 146         self.assertTrue("07110427" in _firstmilenium)
 147
 148     def test_unified_dates(self):
 149         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 150         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 151         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 152         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 153         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
 154         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 155         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 156         self.assertEqual(
 157             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
 158             '20141126')
 159         self.assertEqual(
 160             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
 161             '20150202')
 162
 163     def test_find_xpath_attr(self):
 164         testxml = '''<root>
 165             <node/>
 166             <node x="a"/>
 167             <node x="a" y="c" />
 168             <node x="b" y="d" />
 169         </root>'''
 170         doc = xml.etree.ElementTree.fromstring(testxml)
 171
 172         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 173         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 174         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 175
 176     def test_xpath_with_ns(self):
 177         testxml = '''<root xmlns:media="http://example.com/">
 178             <media:song>
 179                 <media:author>The Author</media:author>
 180                 <url>http://server.com/download.mp3</url>
 181             </media:song>
 182         </root>'''
 183         doc = xml.etree.ElementTree.fromstring(testxml)
 184         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 185         self.assertTrue(find('media:song') is not None)
 186         self.assertEqual(find('media:song/media:author').text, 'The Author')
 187         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 188
 189     def test_smuggle_url(self):
 190         data = {"ö": "ö", "abc": [3]}
 191         url = 'https://foo.bar/baz?x=y#a'
 192         smug_url = smuggle_url(url, data)
 193         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 194         self.assertEqual(url, unsmug_url)
 195         self.assertEqual(data, unsmug_data)
 196
 197         res_url, res_data = unsmuggle_url(url)
 198         self.assertEqual(res_url, url)
 199         self.assertEqual(res_data, None)
 200
 201     def test_shell_quote(self):
 202         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 203         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 204
 205     def test_str_to_int(self):
 206         self.assertEqual(str_to_int('123,456'), 123456)
 207         self.assertEqual(str_to_int('123.456'), 123456)
 208
 209     def test_url_basename(self):
 210         self.assertEqual(url_basename('http://foo.de/'), '')
 211         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 212         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 213         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 214         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 215         self.assertEqual(
 216             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 217             'trailer.mp4')
 218
 219     def test_parse_duration(self):
 220         self.assertEqual(parse_duration(None), None)
 221         self.assertEqual(parse_duration(False), None)
 222         self.assertEqual(parse_duration('invalid'), None)
 223         self.assertEqual(parse_duration('1'), 1)
 224         self.assertEqual(parse_duration('1337:12'), 80232)
 225         self.assertEqual(parse_duration('9:12:43'), 33163)
 226         self.assertEqual(parse_duration('12:00'), 720)
 227         self.assertEqual(parse_duration('00:01:01'), 61)
 228         self.assertEqual(parse_duration('x:y'), None)
 229         self.assertEqual(parse_duration('3h11m53s'), 11513)
 230         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 231         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 232         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 233         self.assertEqual(parse_duration('62m45s'), 3765)
 234         self.assertEqual(parse_duration('6m59s'), 419)
 235         self.assertEqual(parse_duration('49s'), 49)
 236         self.assertEqual(parse_duration('0h0m0s'), 0)
 237         self.assertEqual(parse_duration('0m0s'), 0)
 238         self.assertEqual(parse_duration('0s'), 0)
 239         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 240         self.assertEqual(parse_duration('T30M38S'), 1838)
 241         self.assertEqual(parse_duration('5 s'), 5)
 242         self.assertEqual(parse_duration('3 min'), 180)
 243         self.assertEqual(parse_duration('2.5 hours'), 9000)
 244         self.assertEqual(parse_duration('02:03:04'), 7384)
 245         self.assertEqual(parse_duration('01:02:03:04'), 93784)
 246
 247     def test_fix_xml_ampersands(self):
 248         self.assertEqual(
 249             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 250         self.assertEqual(
 251             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 252             '"&amp;x=y&amp;wrong;&amp;z=a')
 253         self.assertEqual(
 254             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 255             '&amp;&apos;&gt;&lt;&quot;')
 256         self.assertEqual(
 257             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 258         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 259
 260     def test_paged_list(self):
 261         def testPL(size, pagesize, sliceargs, expected):
 262             def get_page(pagenum):
 263                 firstid = pagenum * pagesize
 264                 upto = min(size, pagenum * pagesize + pagesize)
 265                 for i in range(firstid, upto):
 266                     yield i
 267
 268             pl = OnDemandPagedList(get_page, pagesize)
 269             got = pl.getslice(*sliceargs)
 270             self.assertEqual(got, expected)
 271
 272             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 273             got = iapl.getslice(*sliceargs)
 274             self.assertEqual(got, expected)
 275
 276         testPL(5, 2, (), [0, 1, 2, 3, 4])
 277         testPL(5, 2, (1,), [1, 2, 3, 4])
 278         testPL(5, 2, (2,), [2, 3, 4])
 279         testPL(5, 2, (4,), [4])
 280         testPL(5, 2, (0, 3), [0, 1, 2])
 281         testPL(5, 2, (1, 4), [1, 2, 3])
 282         testPL(5, 2, (2, 99), [2, 3, 4])
 283         testPL(5, 2, (20, 99), [])
 284
 285     def test_struct_unpack(self):
 286         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 287
 288     def test_read_batch_urls(self):
 289         f = io.StringIO('''\xef\xbb\xbf foo
 290             bar\r
 291             baz
 292             # More after this line\r
 293             ; or after this
 294             bam''')
 295         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 296
 297     def test_urlencode_postdata(self):
 298         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 299         self.assertTrue(isinstance(data, bytes))
 300
 301     def test_parse_iso8601(self):
 302         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 303         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 304         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 305         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 306
 307     def test_strip_jsonp(self):
 308         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 309         d = json.loads(stripped)
 310         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 311
 312         stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
 313         d = json.loads(stripped)
 314         self.assertEqual(d, {'STATUS': 'OK'})
 315
 316     def test_uppercase_escape(self):
 317         self.assertEqual(uppercase_escape('aä'), 'aä')
 318         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 319
 320     def test_limit_length(self):
 321         self.assertEqual(limit_length(None, 12), None)
 322         self.assertEqual(limit_length('foo', 12), 'foo')
 323         self.assertTrue(
 324             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 325         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 326
 327     def test_escape_rfc3986(self):
 328         reserved = "!*'();:@&=+$,/?#[]"
 329         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 330         self.assertEqual(escape_rfc3986(reserved), reserved)
 331         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 332         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 333         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 334         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 335         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 336
 337     def test_escape_url(self):
 338         self.assertEqual(
 339             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 340             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 341         )
 342         self.assertEqual(
 343             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 344             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 345         )
 346         self.assertEqual(
 347             escape_url('http://тест.рф/фрагмент'),
 348             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 349         )
 350         self.assertEqual(
 351             escape_url('http://тест.рф/абв?абв=абв#абв'),
 352             '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'
 353         )
 354         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 355
 356     def test_js_to_json_realworld(self):
 357         inp = '''{
 358             'clip':{'provider':'pseudo'}
 359         }'''
 360         self.assertEqual(js_to_json(inp), '''{
 361             "clip":{"provider":"pseudo"}
 362         }''')
 363         json.loads(js_to_json(inp))
 364
 365         inp = '''{
 366             'playlist':[{'controls':{'all':null}}]
 367         }'''
 368         self.assertEqual(js_to_json(inp), '''{
 369             "playlist":[{"controls":{"all":null}}]
 370         }''')
 371
 372     def test_js_to_json_edgecases(self):
 373         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 374         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 375
 376         on = js_to_json('{"abc": true}')
 377         self.assertEqual(json.loads(on), {'abc': True})
 378
 379         # Ignore JavaScript code as well
 380         on = js_to_json('''{
 381             "x": 1,
 382             y: "a",
 383             z: some.code
 384         }''')
 385         d = json.loads(on)
 386         self.assertEqual(d['x'], 1)
 387         self.assertEqual(d['y'], 'a')
 388
 389     def test_clean_html(self):
 390         self.assertEqual(clean_html('a:\nb'), 'a: b')
 391         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
 392
 393     def test_intlist_to_bytes(self):
 394         self.assertEqual(
 395             intlist_to_bytes([0, 1, 127, 128, 255]),
 396             b'\x00\x01\x7f\x80\xff')
 397
 398     def test_args_to_str(self):
 399         self.assertEqual(
 400             args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
 401             'foo ba/r -baz \'2 be\' \'\''
 402         )
 403
 404     def test_parse_filesize(self):
 405         self.assertEqual(parse_filesize(None), None)
 406         self.assertEqual(parse_filesize(''), None)
 407         self.assertEqual(parse_filesize('91 B'), 91)
 408         self.assertEqual(parse_filesize('foobar'), None)
 409         self.assertEqual(parse_filesize('2 MiB'), 2097152)
 410         self.assertEqual(parse_filesize('5 GB'), 5000000000)
 411         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
 412         self.assertEqual(parse_filesize('1,24 KB'), 1240)
 413
 414     def test_version_tuple(self):
 415         self.assertEqual(version_tuple('1'), (1,))
 416         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
 417         self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
 418
 419     def test_detect_exe_version(self):
 420         self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
 421 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
 422 configuration: --prefix=/usr --extra-'''), '1.2.1')
 423         self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
 424 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
 425         self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
 426 Trying to open render node...
 427 Success at /dev/dri/renderD128.
 428 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
 429
 430     def test_age_restricted(self):
 431         self.assertFalse(age_restricted(None, 10))  # unrestricted content
 432         self.assertFalse(age_restricted(1, None))  # unrestricted policy
 433         self.assertFalse(age_restricted(8, 10))
 434         self.assertTrue(age_restricted(18, 14))
 435         self.assertFalse(age_restricted(18, 18))
 436
 437     def test_is_html(self):
 438         self.assertFalse(is_html(b'\x49\x44\x43<html'))
 439         self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
 440         self.assertTrue(is_html(  # UTF-8 with BOM
 441             b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
 442         self.assertTrue(is_html(  # UTF-16-LE
 443             b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
 444         ))
 445         self.assertTrue(is_html(  # UTF-16-BE
 446             b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
 447         ))
 448         self.assertTrue(is_html(  # UTF-32-BE
 449             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'))
 450         self.assertTrue(is_html(  # UTF-32-LE
 451             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'))
 452
 453     def test_render_table(self):
 454         self.assertEqual(
 455             render_table(
 456                 ['a', 'bcd'],
 457                 [[123, 4], [9999, 51]]),
 458             'a    bcd\n'
 459             '123  4\n'
 460             '9999 51')
 461
 462
 463 if __name__ == '__main__':
 464     unittest.main()