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     DateRange,
  20     encodeFilename,
  21     find_xpath_attr,
  22     fix_xml_ampersands,
  23     get_meta_content,
  24     orderedSet,
  25     OnDemandPagedList,
  26     InAdvancePagedList,
  27     parse_duration,
  28     read_batch_urls,
  29     sanitize_filename,
  30     shell_quote,
  31     smuggle_url,
  32     str_to_int,
  33     struct_unpack,
  34     timeconvert,
  35     unescapeHTML,
  36     unified_strdate,
  37     unsmuggle_url,
  38     url_basename,
  39     urlencode_postdata,
  40     xpath_with_ns,
  41     parse_iso8601,
  42     strip_jsonp,
  43     uppercase_escape,
  44     limit_length,
  45     escape_rfc3986,
  46     escape_url,
  47     js_to_json,
  48     get_filesystem_encoding,
  49     compat_getenv,
  50     compat_expanduser,
  51 )
  52
  53
  54 class TestUtil(unittest.TestCase):
  55     def test_timeconvert(self):
  56         self.assertTrue(timeconvert('') is None)
  57         self.assertTrue(timeconvert('bougrg') is None)
  58
  59     def test_sanitize_filename(self):
  60         self.assertEqual(sanitize_filename('abc'), 'abc')
  61         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  62
  63         self.assertEqual(sanitize_filename('123'), '123')
  64
  65         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  66         self.assertFalse('/' in sanitize_filename('abc/de///'))
  67
  68         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  69         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  70         self.assertEqual('yes no', sanitize_filename('yes? no'))
  71         self.assertEqual('this - that', sanitize_filename('this: that'))
  72
  73         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  74         aumlaut = 'ä'
  75         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  76         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
  77         self.assertEqual(sanitize_filename(tests), tests)
  78
  79         forbidden = '"\0\\/'
  80         for fc in forbidden:
  81             for fbc in forbidden:
  82                 self.assertTrue(fbc not in sanitize_filename(fc))
  83
  84     def test_sanitize_filename_restricted(self):
  85         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  86         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  87
  88         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  89
  90         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  91         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  92
  93         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  94         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  95         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  96         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  97
  98         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
  99         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
 100         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
 101
 102         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 103         for fc in forbidden:
 104             for fbc in forbidden:
 105                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 106
 107         # Handle a common case more neatly
 108         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 109         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 110         # .. but make sure the file name is never empty
 111         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 112         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 113
 114     def test_sanitize_ids(self):
 115         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 116         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 117         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 118
 119     def test_ordered_set(self):
 120         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 121         self.assertEqual(orderedSet([]), [])
 122         self.assertEqual(orderedSet([1]), [1])
 123         #keep the list ordered
 124         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 125
 126     def test_unescape_html(self):
 127         self.assertEqual(unescapeHTML('%20;'), '%20;')
 128         self.assertEqual(
 129             unescapeHTML('&eacute;'), 'é')
 130
 131     def test_daterange(self):
 132         _20century = DateRange("19000101","20000101")
 133         self.assertFalse("17890714" in _20century)
 134         _ac = DateRange("00010101")
 135         self.assertTrue("19690721" in _ac)
 136         _firstmilenium = DateRange(end="10000101")
 137         self.assertTrue("07110427" in _firstmilenium)
 138
 139     def test_unified_dates(self):
 140         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 141         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 142         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 143         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 144         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 145         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 146
 147     def test_find_xpath_attr(self):
 148         testxml = '''<root>
 149             <node/>
 150             <node x="a"/>
 151             <node x="a" y="c" />
 152             <node x="b" y="d" />
 153         </root>'''
 154         doc = xml.etree.ElementTree.fromstring(testxml)
 155
 156         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 157         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 158         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 159
 160     def test_meta_parser(self):
 161         testhtml = '''
 162         <head>
 163             <meta name="description" content="foo &amp; bar">
 164             <meta content='Plato' name='author'/>
 165         </head>
 166         '''
 167         get_meta = lambda name: get_meta_content(name, testhtml)
 168         self.assertEqual(get_meta('description'), 'foo & bar')
 169         self.assertEqual(get_meta('author'), 'Plato')
 170
 171     def test_xpath_with_ns(self):
 172         testxml = '''<root xmlns:media="http://example.com/">
 173             <media:song>
 174                 <media:author>The Author</media:author>
 175                 <url>http://server.com/download.mp3</url>
 176             </media:song>
 177         </root>'''
 178         doc = xml.etree.ElementTree.fromstring(testxml)
 179         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 180         self.assertTrue(find('media:song') is not None)
 181         self.assertEqual(find('media:song/media:author').text, 'The Author')
 182         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 183
 184     def test_smuggle_url(self):
 185         data = {u"ö": u"ö", u"abc": [3]}
 186         url = 'https://foo.bar/baz?x=y#a'
 187         smug_url = smuggle_url(url, data)
 188         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 189         self.assertEqual(url, unsmug_url)
 190         self.assertEqual(data, unsmug_data)
 191
 192         res_url, res_data = unsmuggle_url(url)
 193         self.assertEqual(res_url, url)
 194         self.assertEqual(res_data, None)
 195
 196     def test_shell_quote(self):
 197         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 198         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 199
 200     def test_str_to_int(self):
 201         self.assertEqual(str_to_int('123,456'), 123456)
 202         self.assertEqual(str_to_int('123.456'), 123456)
 203
 204     def test_url_basename(self):
 205         self.assertEqual(url_basename('http://foo.de/'), '')
 206         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 207         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 208         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 209         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 210         self.assertEqual(
 211             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 212             'trailer.mp4')
 213
 214     def test_parse_duration(self):
 215         self.assertEqual(parse_duration(None), None)
 216         self.assertEqual(parse_duration('1'), 1)
 217         self.assertEqual(parse_duration('1337:12'), 80232)
 218         self.assertEqual(parse_duration('9:12:43'), 33163)
 219         self.assertEqual(parse_duration('12:00'), 720)
 220         self.assertEqual(parse_duration('00:01:01'), 61)
 221         self.assertEqual(parse_duration('x:y'), None)
 222         self.assertEqual(parse_duration('3h11m53s'), 11513)
 223         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 224         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 225         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 226         self.assertEqual(parse_duration('62m45s'), 3765)
 227         self.assertEqual(parse_duration('6m59s'), 419)
 228         self.assertEqual(parse_duration('49s'), 49)
 229         self.assertEqual(parse_duration('0h0m0s'), 0)
 230         self.assertEqual(parse_duration('0m0s'), 0)
 231         self.assertEqual(parse_duration('0s'), 0)
 232         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 233
 234     def test_fix_xml_ampersands(self):
 235         self.assertEqual(
 236             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 237         self.assertEqual(
 238             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 239             '"&amp;x=y&amp;wrong;&amp;z=a')
 240         self.assertEqual(
 241             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 242             '&amp;&apos;&gt;&lt;&quot;')
 243         self.assertEqual(
 244             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 245         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 246
 247     def test_paged_list(self):
 248         def testPL(size, pagesize, sliceargs, expected):
 249             def get_page(pagenum):
 250                 firstid = pagenum * pagesize
 251                 upto = min(size, pagenum * pagesize + pagesize)
 252                 for i in range(firstid, upto):
 253                     yield i
 254
 255             pl = OnDemandPagedList(get_page, pagesize)
 256             got = pl.getslice(*sliceargs)
 257             self.assertEqual(got, expected)
 258
 259             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 260             got = iapl.getslice(*sliceargs)
 261             self.assertEqual(got, expected)
 262
 263         testPL(5, 2, (), [0, 1, 2, 3, 4])
 264         testPL(5, 2, (1,), [1, 2, 3, 4])
 265         testPL(5, 2, (2,), [2, 3, 4])
 266         testPL(5, 2, (4,), [4])
 267         testPL(5, 2, (0, 3), [0, 1, 2])
 268         testPL(5, 2, (1, 4), [1, 2, 3])
 269         testPL(5, 2, (2, 99), [2, 3, 4])
 270         testPL(5, 2, (20, 99), [])
 271
 272     def test_struct_unpack(self):
 273         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 274
 275     def test_read_batch_urls(self):
 276         f = io.StringIO('''\xef\xbb\xbf foo
 277             bar\r
 278             baz
 279             # More after this line\r
 280             ; or after this
 281             bam''')
 282         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 283
 284     def test_urlencode_postdata(self):
 285         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 286         self.assertTrue(isinstance(data, bytes))
 287
 288     def test_parse_iso8601(self):
 289         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 290         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 291         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 292
 293     def test_strip_jsonp(self):
 294         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 295         d = json.loads(stripped)
 296         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 297
 298     def test_uppercase_escape(self):
 299         self.assertEqual(uppercase_escape('aä'), 'aä')
 300         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 301
 302     def test_limit_length(self):
 303         self.assertEqual(limit_length(None, 12), None)
 304         self.assertEqual(limit_length('foo', 12), 'foo')
 305         self.assertTrue(
 306             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 307         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 308
 309     def test_escape_rfc3986(self):
 310         reserved = "!*'();:@&=+$,/?#[]"
 311         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 312         self.assertEqual(escape_rfc3986(reserved), reserved)
 313         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 314         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 315         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 316         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 317         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 318
 319     def test_escape_url(self):
 320         self.assertEqual(
 321             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 322             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 323         )
 324         self.assertEqual(
 325             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 326             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 327         )
 328         self.assertEqual(
 329             escape_url('http://тест.рф/фрагмент'),
 330             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 331         )
 332         self.assertEqual(
 333             escape_url('http://тест.рф/абв?абв=абв#абв'),
 334             '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'
 335         )
 336         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 337
 338     def test_js_to_json_realworld(self):
 339         inp = '''{
 340             'clip':{'provider':'pseudo'}
 341         }'''
 342         self.assertEqual(js_to_json(inp), '''{
 343             "clip":{"provider":"pseudo"}
 344         }''')
 345         json.loads(js_to_json(inp))
 346
 347         inp = '''{
 348             'playlist':[{'controls':{'all':null}}]
 349         }'''
 350         self.assertEqual(js_to_json(inp), '''{
 351             "playlist":[{"controls":{"all":null}}]
 352         }''')
 353
 354     def test_js_to_json_edgecases(self):
 355         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 356         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 357
 358         on = js_to_json('{"abc": true}')
 359         self.assertEqual(json.loads(on), {'abc': True})
 360
 361     def test_compat_getenv(self):
 362         test_str = 'тест'
 363         os.environ['YOUTUBE-DL-TEST'] = (test_str if sys.version_info >= (3, 0)
 364             else test_str.encode(get_filesystem_encoding()))
 365         self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
 366
 367     def test_compat_expanduser(self):
 368         test_str = 'C:\Documents and Settings\тест\Application Data'
 369         os.environ['HOME'] = (test_str if sys.version_info >= (3, 0)
 370             else test_str.encode(get_filesystem_encoding()))
 371         self.assertEqual(compat_expanduser('~'), test_str)
 372
 373 if __name__ == '__main__':
 374     unittest.main()