test/test_utils.py

   1 #!/usr/bin/env python
   2 # coding: utf-8
   3
   4 # Allow direct execution
   5 import os
   6 import sys
   7 import unittest
   8 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
   9
  10
  11 # Various small unit tests
  12 import io
  13 import xml.etree.ElementTree
  14
  15 #from youtube_dl.utils import htmlentity_transform
  16 from youtube_dl.utils import (
  17     DateRange,
  18     encodeFilename,
  19     find_xpath_attr,
  20     fix_xml_ampersands,
  21     get_meta_content,
  22     orderedSet,
  23     PagedList,
  24     parse_duration,
  25     read_batch_urls,
  26     sanitize_filename,
  27     shell_quote,
  28     smuggle_url,
  29     str_to_int,
  30     struct_unpack,
  31     timeconvert,
  32     unescapeHTML,
  33     unified_strdate,
  34     unsmuggle_url,
  35     url_basename,
  36     xpath_with_ns,
  37 )
  38
  39 if sys.version_info < (3, 0):
  40     _compat_str = lambda b: b.decode('unicode-escape')
  41 else:
  42     _compat_str = lambda s: s
  43
  44
  45 class TestUtil(unittest.TestCase):
  46     def test_timeconvert(self):
  47         self.assertTrue(timeconvert('') is None)
  48         self.assertTrue(timeconvert('bougrg') is None)
  49
  50     def test_sanitize_filename(self):
  51         self.assertEqual(sanitize_filename('abc'), 'abc')
  52         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  53
  54         self.assertEqual(sanitize_filename('123'), '123')
  55
  56         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  57         self.assertFalse('/' in sanitize_filename('abc/de///'))
  58
  59         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  60         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  61         self.assertEqual('yes no', sanitize_filename('yes? no'))
  62         self.assertEqual('this - that', sanitize_filename('this: that'))
  63
  64         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  65         aumlaut = _compat_str('\xe4')
  66         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  67         tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
  68         self.assertEqual(sanitize_filename(tests), tests)
  69
  70         forbidden = '"\0\\/'
  71         for fc in forbidden:
  72             for fbc in forbidden:
  73                 self.assertTrue(fbc not in sanitize_filename(fc))
  74
  75     def test_sanitize_filename_restricted(self):
  76         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  77         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  78
  79         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  80
  81         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  82         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  83
  84         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  85         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  86         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  87         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  88
  89         tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
  90         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  91         self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
  92
  93         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
  94         for fc in forbidden:
  95             for fbc in forbidden:
  96                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
  97
  98         # Handle a common case more neatly
  99         self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
 100         self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
 101         # .. but make sure the file name is never empty
 102         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 103         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 104
 105     def test_sanitize_ids(self):
 106         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 107         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 108         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 109
 110     def test_ordered_set(self):
 111         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 112         self.assertEqual(orderedSet([]), [])
 113         self.assertEqual(orderedSet([1]), [1])
 114         #keep the list ordered
 115         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 116
 117     def test_unescape_html(self):
 118         self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
 119
 120     def test_daterange(self):
 121         _20century = DateRange("19000101","20000101")
 122         self.assertFalse("17890714" in _20century)
 123         _ac = DateRange("00010101")
 124         self.assertTrue("19690721" in _ac)
 125         _firstmilenium = DateRange(end="10000101")
 126         self.assertTrue("07110427" in _firstmilenium)
 127
 128     def test_unified_dates(self):
 129         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 130         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 131         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 132         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 133         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 134
 135     def test_find_xpath_attr(self):
 136         testxml = u'''<root>
 137             <node/>
 138             <node x="a"/>
 139             <node x="a" y="c" />
 140             <node x="b" y="d" />
 141         </root>'''
 142         doc = xml.etree.ElementTree.fromstring(testxml)
 143
 144         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 145         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 146         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 147
 148     def test_meta_parser(self):
 149         testhtml = u'''
 150         <head>
 151             <meta name="description" content="foo &amp; bar">
 152             <meta content='Plato' name='author'/>
 153         </head>
 154         '''
 155         get_meta = lambda name: get_meta_content(name, testhtml)
 156         self.assertEqual(get_meta('description'), u'foo & bar')
 157         self.assertEqual(get_meta('author'), 'Plato')
 158
 159     def test_xpath_with_ns(self):
 160         testxml = u'''<root xmlns:media="http://example.com/">
 161             <media:song>
 162                 <media:author>The Author</media:author>
 163                 <url>http://server.com/download.mp3</url>
 164             </media:song>
 165         </root>'''
 166         doc = xml.etree.ElementTree.fromstring(testxml)
 167         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 168         self.assertTrue(find('media:song') is not None)
 169         self.assertEqual(find('media:song/media:author').text, u'The Author')
 170         self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
 171
 172     def test_smuggle_url(self):
 173         data = {u"ö": u"ö", u"abc": [3]}
 174         url = 'https://foo.bar/baz?x=y#a'
 175         smug_url = smuggle_url(url, data)
 176         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 177         self.assertEqual(url, unsmug_url)
 178         self.assertEqual(data, unsmug_data)
 179
 180         res_url, res_data = unsmuggle_url(url)
 181         self.assertEqual(res_url, url)
 182         self.assertEqual(res_data, None)
 183
 184     def test_shell_quote(self):
 185         args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
 186         self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 187
 188     def test_str_to_int(self):
 189         self.assertEqual(str_to_int('123,456'), 123456)
 190         self.assertEqual(str_to_int('123.456'), 123456)
 191
 192     def test_url_basename(self):
 193         self.assertEqual(url_basename(u'http://foo.de/'), u'')
 194         self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
 195         self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
 196         self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
 197         self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
 198         self.assertEqual(
 199             url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
 200             u'trailer.mp4')
 201
 202     def test_parse_duration(self):
 203         self.assertEqual(parse_duration(None), None)
 204         self.assertEqual(parse_duration('1'), 1)
 205         self.assertEqual(parse_duration('1337:12'), 80232)
 206         self.assertEqual(parse_duration('9:12:43'), 33163)
 207         self.assertEqual(parse_duration('12:00'), 720)
 208         self.assertEqual(parse_duration('00:01:01'), 61)
 209         self.assertEqual(parse_duration('x:y'), None)
 210         self.assertEqual(parse_duration('3h11m53s'), 11513)
 211         self.assertEqual(parse_duration('62m45s'), 3765)
 212         self.assertEqual(parse_duration('6m59s'), 419)
 213         self.assertEqual(parse_duration('49s'), 49)
 214         self.assertEqual(parse_duration('0h0m0s'), 0)
 215         self.assertEqual(parse_duration('0m0s'), 0)
 216         self.assertEqual(parse_duration('0s'), 0)
 217
 218     def test_fix_xml_ampersands(self):
 219         self.assertEqual(
 220             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 221         self.assertEqual(
 222             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 223             '"&amp;x=y&amp;wrong;&amp;z=a')
 224         self.assertEqual(
 225             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 226             '&amp;&apos;&gt;&lt;&quot;')
 227         self.assertEqual(
 228             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 229         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 230
 231     def test_paged_list(self):
 232         def testPL(size, pagesize, sliceargs, expected):
 233             def get_page(pagenum):
 234                 firstid = pagenum * pagesize
 235                 upto = min(size, pagenum * pagesize + pagesize)
 236                 for i in range(firstid, upto):
 237                     yield i
 238
 239             pl = PagedList(get_page, pagesize)
 240             got = pl.getslice(*sliceargs)
 241             self.assertEqual(got, expected)
 242
 243         testPL(5, 2, (), [0, 1, 2, 3, 4])
 244         testPL(5, 2, (1,), [1, 2, 3, 4])
 245         testPL(5, 2, (2,), [2, 3, 4])
 246         testPL(5, 2, (4,), [4])
 247         testPL(5, 2, (0, 3), [0, 1, 2])
 248         testPL(5, 2, (1, 4), [1, 2, 3])
 249         testPL(5, 2, (2, 99), [2, 3, 4])
 250         testPL(5, 2, (20, 99), [])
 251
 252     def test_struct_unpack(self):
 253         self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
 254
 255     def test_read_batch_urls(self):
 256         f = io.StringIO(u'''\xef\xbb\xbf foo
 257             bar\r
 258             baz
 259             # More after this line\r
 260             ; or after this
 261             bam''')
 262         self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
 263
 264 if __name__ == '__main__':
 265     unittest.main()