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     orderedSet,
  24     OnDemandPagedList,
  25     InAdvancePagedList,
  26     parse_duration,
  27     read_batch_urls,
  28     sanitize_filename,
  29     shell_quote,
  30     smuggle_url,
  31     str_to_int,
  32     struct_unpack,
  33     timeconvert,
  34     unescapeHTML,
  35     unified_strdate,
  36     unsmuggle_url,
  37     url_basename,
  38     urlencode_postdata,
  39     xpath_with_ns,
  40     parse_iso8601,
  41     strip_jsonp,
  42     uppercase_escape,
  43     limit_length,
  44     escape_rfc3986,
  45     escape_url,
  46     js_to_json,
  47     get_filesystem_encoding,
  48 )
  49
  50
  51 class TestUtil(unittest.TestCase):
  52     def test_timeconvert(self):
  53         self.assertTrue(timeconvert('') is None)
  54         self.assertTrue(timeconvert('bougrg') is None)
  55
  56     def test_sanitize_filename(self):
  57         self.assertEqual(sanitize_filename('abc'), 'abc')
  58         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  59
  60         self.assertEqual(sanitize_filename('123'), '123')
  61
  62         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  63         self.assertFalse('/' in sanitize_filename('abc/de///'))
  64
  65         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  66         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  67         self.assertEqual('yes no', sanitize_filename('yes? no'))
  68         self.assertEqual('this - that', sanitize_filename('this: that'))
  69
  70         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  71         aumlaut = 'ä'
  72         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  73         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
  74         self.assertEqual(sanitize_filename(tests), tests)
  75
  76         forbidden = '"\0\\/'
  77         for fc in forbidden:
  78             for fbc in forbidden:
  79                 self.assertTrue(fbc not in sanitize_filename(fc))
  80
  81     def test_sanitize_filename_restricted(self):
  82         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  83         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  84
  85         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  86
  87         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  88         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  89
  90         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  91         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  92         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  93         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  94
  95         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
  96         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  97         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
  98
  99         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
 100         for fc in forbidden:
 101             for fbc in forbidden:
 102                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
 103
 104         # Handle a common case more neatly
 105         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
 106         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
 107         # .. but make sure the file name is never empty
 108         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 109         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 110
 111     def test_sanitize_ids(self):
 112         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 113         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 114         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 115
 116     def test_ordered_set(self):
 117         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 118         self.assertEqual(orderedSet([]), [])
 119         self.assertEqual(orderedSet([1]), [1])
 120         #keep the list ordered
 121         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 122
 123     def test_unescape_html(self):
 124         self.assertEqual(unescapeHTML('%20;'), '%20;')
 125         self.assertEqual(
 126             unescapeHTML('&eacute;'), 'é')
 127
 128     def test_daterange(self):
 129         _20century = DateRange("19000101","20000101")
 130         self.assertFalse("17890714" in _20century)
 131         _ac = DateRange("00010101")
 132         self.assertTrue("19690721" in _ac)
 133         _firstmilenium = DateRange(end="10000101")
 134         self.assertTrue("07110427" in _firstmilenium)
 135
 136     def test_unified_dates(self):
 137         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 138         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 139         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 140         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 141         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 142         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
 143
 144     def test_find_xpath_attr(self):
 145         testxml = '''<root>
 146             <node/>
 147             <node x="a"/>
 148             <node x="a" y="c" />
 149             <node x="b" y="d" />
 150         </root>'''
 151         doc = xml.etree.ElementTree.fromstring(testxml)
 152
 153         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 154         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 155         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 156
 157     def test_xpath_with_ns(self):
 158         testxml = '''<root xmlns:media="http://example.com/">
 159             <media:song>
 160                 <media:author>The Author</media:author>
 161                 <url>http://server.com/download.mp3</url>
 162             </media:song>
 163         </root>'''
 164         doc = xml.etree.ElementTree.fromstring(testxml)
 165         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 166         self.assertTrue(find('media:song') is not None)
 167         self.assertEqual(find('media:song/media:author').text, 'The Author')
 168         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 169
 170     def test_smuggle_url(self):
 171         data = {u"ö": u"ö", u"abc": [3]}
 172         url = 'https://foo.bar/baz?x=y#a'
 173         smug_url = smuggle_url(url, data)
 174         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 175         self.assertEqual(url, unsmug_url)
 176         self.assertEqual(data, unsmug_data)
 177
 178         res_url, res_data = unsmuggle_url(url)
 179         self.assertEqual(res_url, url)
 180         self.assertEqual(res_data, None)
 181
 182     def test_shell_quote(self):
 183         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
 184         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 185
 186     def test_str_to_int(self):
 187         self.assertEqual(str_to_int('123,456'), 123456)
 188         self.assertEqual(str_to_int('123.456'), 123456)
 189
 190     def test_url_basename(self):
 191         self.assertEqual(url_basename('http://foo.de/'), '')
 192         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
 193         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
 194         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
 195         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
 196         self.assertEqual(
 197             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
 198             'trailer.mp4')
 199
 200     def test_parse_duration(self):
 201         self.assertEqual(parse_duration(None), None)
 202         self.assertEqual(parse_duration('1'), 1)
 203         self.assertEqual(parse_duration('1337:12'), 80232)
 204         self.assertEqual(parse_duration('9:12:43'), 33163)
 205         self.assertEqual(parse_duration('12:00'), 720)
 206         self.assertEqual(parse_duration('00:01:01'), 61)
 207         self.assertEqual(parse_duration('x:y'), None)
 208         self.assertEqual(parse_duration('3h11m53s'), 11513)
 209         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
 210         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
 211         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
 212         self.assertEqual(parse_duration('62m45s'), 3765)
 213         self.assertEqual(parse_duration('6m59s'), 419)
 214         self.assertEqual(parse_duration('49s'), 49)
 215         self.assertEqual(parse_duration('0h0m0s'), 0)
 216         self.assertEqual(parse_duration('0m0s'), 0)
 217         self.assertEqual(parse_duration('0s'), 0)
 218         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
 219
 220     def test_fix_xml_ampersands(self):
 221         self.assertEqual(
 222             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 223         self.assertEqual(
 224             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 225             '"&amp;x=y&amp;wrong;&amp;z=a')
 226         self.assertEqual(
 227             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 228             '&amp;&apos;&gt;&lt;&quot;')
 229         self.assertEqual(
 230             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 231         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 232
 233     def test_paged_list(self):
 234         def testPL(size, pagesize, sliceargs, expected):
 235             def get_page(pagenum):
 236                 firstid = pagenum * pagesize
 237                 upto = min(size, pagenum * pagesize + pagesize)
 238                 for i in range(firstid, upto):
 239                     yield i
 240
 241             pl = OnDemandPagedList(get_page, pagesize)
 242             got = pl.getslice(*sliceargs)
 243             self.assertEqual(got, expected)
 244
 245             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
 246             got = iapl.getslice(*sliceargs)
 247             self.assertEqual(got, expected)
 248
 249         testPL(5, 2, (), [0, 1, 2, 3, 4])
 250         testPL(5, 2, (1,), [1, 2, 3, 4])
 251         testPL(5, 2, (2,), [2, 3, 4])
 252         testPL(5, 2, (4,), [4])
 253         testPL(5, 2, (0, 3), [0, 1, 2])
 254         testPL(5, 2, (1, 4), [1, 2, 3])
 255         testPL(5, 2, (2, 99), [2, 3, 4])
 256         testPL(5, 2, (20, 99), [])
 257
 258     def test_struct_unpack(self):
 259         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
 260
 261     def test_read_batch_urls(self):
 262         f = io.StringIO('''\xef\xbb\xbf foo
 263             bar\r
 264             baz
 265             # More after this line\r
 266             ; or after this
 267             bam''')
 268         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
 269
 270     def test_urlencode_postdata(self):
 271         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 272         self.assertTrue(isinstance(data, bytes))
 273
 274     def test_parse_iso8601(self):
 275         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
 276         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
 277         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
 278         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 279
 280     def test_strip_jsonp(self):
 281         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
 282         d = json.loads(stripped)
 283         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 284
 285     def test_uppercase_escape(self):
 286         self.assertEqual(uppercase_escape('aä'), 'aä')
 287         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 288
 289     def test_limit_length(self):
 290         self.assertEqual(limit_length(None, 12), None)
 291         self.assertEqual(limit_length('foo', 12), 'foo')
 292         self.assertTrue(
 293             limit_length('foo bar baz asd', 12).startswith('foo bar'))
 294         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 295
 296     def test_escape_rfc3986(self):
 297         reserved = "!*'();:@&=+$,/?#[]"
 298         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
 299         self.assertEqual(escape_rfc3986(reserved), reserved)
 300         self.assertEqual(escape_rfc3986(unreserved), unreserved)
 301         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
 302         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
 303         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
 304         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
 305
 306     def test_escape_url(self):
 307         self.assertEqual(
 308             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
 309             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
 310         )
 311         self.assertEqual(
 312             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
 313             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
 314         )
 315         self.assertEqual(
 316             escape_url('http://тест.рф/фрагмент'),
 317             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
 318         )
 319         self.assertEqual(
 320             escape_url('http://тест.рф/абв?абв=абв#абв'),
 321             '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'
 322         )
 323         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
 324
 325     def test_js_to_json_realworld(self):
 326         inp = '''{
 327             'clip':{'provider':'pseudo'}
 328         }'''
 329         self.assertEqual(js_to_json(inp), '''{
 330             "clip":{"provider":"pseudo"}
 331         }''')
 332         json.loads(js_to_json(inp))
 333
 334         inp = '''{
 335             'playlist':[{'controls':{'all':null}}]
 336         }'''
 337         self.assertEqual(js_to_json(inp), '''{
 338             "playlist":[{"controls":{"all":null}}]
 339         }''')
 340
 341     def test_js_to_json_edgecases(self):
 342         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
 343         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
 344
 345         on = js_to_json('{"abc": true}')
 346         self.assertEqual(json.loads(on), {'abc': True})
 347
 348 if __name__ == '__main__':
 349     unittest.main()