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