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     urlencode_postdata,
  37     xpath_with_ns,
  38 )
  39
  40 if sys.version_info < (3, 0):
  41     _compat_str = lambda b: b.decode('unicode-escape')
  42 else:
  43     _compat_str = lambda s: s
  44
  45
  46 class TestUtil(unittest.TestCase):
  47     def test_timeconvert(self):
  48         self.assertTrue(timeconvert('') is None)
  49         self.assertTrue(timeconvert('bougrg') is None)
  50
  51     def test_sanitize_filename(self):
  52         self.assertEqual(sanitize_filename('abc'), 'abc')
  53         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
  54
  55         self.assertEqual(sanitize_filename('123'), '123')
  56
  57         self.assertEqual('abc_de', sanitize_filename('abc/de'))
  58         self.assertFalse('/' in sanitize_filename('abc/de///'))
  59
  60         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
  61         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
  62         self.assertEqual('yes no', sanitize_filename('yes? no'))
  63         self.assertEqual('this - that', sanitize_filename('this: that'))
  64
  65         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
  66         aumlaut = _compat_str('\xe4')
  67         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
  68         tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
  69         self.assertEqual(sanitize_filename(tests), tests)
  70
  71         forbidden = '"\0\\/'
  72         for fc in forbidden:
  73             for fbc in forbidden:
  74                 self.assertTrue(fbc not in sanitize_filename(fc))
  75
  76     def test_sanitize_filename_restricted(self):
  77         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
  78         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
  79
  80         self.assertEqual(sanitize_filename('123', restricted=True), '123')
  81
  82         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
  83         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
  84
  85         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
  86         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
  87         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
  88         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
  89
  90         tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
  91         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
  92         self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '')  # No empty filename
  93
  94         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
  95         for fc in forbidden:
  96             for fbc in forbidden:
  97                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
  98
  99         # Handle a common case more neatly
 100         self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
 101         self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech')
 102         # .. but make sure the file name is never empty
 103         self.assertTrue(sanitize_filename('-', restricted=True) != '')
 104         self.assertTrue(sanitize_filename(':', restricted=True) != '')
 105
 106     def test_sanitize_ids(self):
 107         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
 108         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
 109         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
 110
 111     def test_ordered_set(self):
 112         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
 113         self.assertEqual(orderedSet([]), [])
 114         self.assertEqual(orderedSet([1]), [1])
 115         #keep the list ordered
 116         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
 117
 118     def test_unescape_html(self):
 119         self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
 120
 121     def test_daterange(self):
 122         _20century = DateRange("19000101","20000101")
 123         self.assertFalse("17890714" in _20century)
 124         _ac = DateRange("00010101")
 125         self.assertTrue("19690721" in _ac)
 126         _firstmilenium = DateRange(end="10000101")
 127         self.assertTrue("07110427" in _firstmilenium)
 128
 129     def test_unified_dates(self):
 130         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
 131         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
 132         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
 133         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
 134         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 135
 136     def test_find_xpath_attr(self):
 137         testxml = u'''<root>
 138             <node/>
 139             <node x="a"/>
 140             <node x="a" y="c" />
 141             <node x="b" y="d" />
 142         </root>'''
 143         doc = xml.etree.ElementTree.fromstring(testxml)
 144
 145         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
 146         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
 147         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 148
 149     def test_meta_parser(self):
 150         testhtml = u'''
 151         <head>
 152             <meta name="description" content="foo &amp; bar">
 153             <meta content='Plato' name='author'/>
 154         </head>
 155         '''
 156         get_meta = lambda name: get_meta_content(name, testhtml)
 157         self.assertEqual(get_meta('description'), u'foo & bar')
 158         self.assertEqual(get_meta('author'), 'Plato')
 159
 160     def test_xpath_with_ns(self):
 161         testxml = u'''<root xmlns:media="http://example.com/">
 162             <media:song>
 163                 <media:author>The Author</media:author>
 164                 <url>http://server.com/download.mp3</url>
 165             </media:song>
 166         </root>'''
 167         doc = xml.etree.ElementTree.fromstring(testxml)
 168         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
 169         self.assertTrue(find('media:song') is not None)
 170         self.assertEqual(find('media:song/media:author').text, u'The Author')
 171         self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
 172
 173     def test_smuggle_url(self):
 174         data = {u"ö": u"ö", u"abc": [3]}
 175         url = 'https://foo.bar/baz?x=y#a'
 176         smug_url = smuggle_url(url, data)
 177         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
 178         self.assertEqual(url, unsmug_url)
 179         self.assertEqual(data, unsmug_data)
 180
 181         res_url, res_data = unsmuggle_url(url)
 182         self.assertEqual(res_url, url)
 183         self.assertEqual(res_data, None)
 184
 185     def test_shell_quote(self):
 186         args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
 187         self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
 188
 189     def test_str_to_int(self):
 190         self.assertEqual(str_to_int('123,456'), 123456)
 191         self.assertEqual(str_to_int('123.456'), 123456)
 192
 193     def test_url_basename(self):
 194         self.assertEqual(url_basename(u'http://foo.de/'), u'')
 195         self.assertEqual(url_basename(u'http://foo.de/bar/baz'), 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#x=y'), u'baz')
 198         self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
 199         self.assertEqual(
 200             url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
 201             u'trailer.mp4')
 202
 203     def test_parse_duration(self):
 204         self.assertEqual(parse_duration(None), None)
 205         self.assertEqual(parse_duration('1'), 1)
 206         self.assertEqual(parse_duration('1337:12'), 80232)
 207         self.assertEqual(parse_duration('9:12:43'), 33163)
 208         self.assertEqual(parse_duration('12:00'), 720)
 209         self.assertEqual(parse_duration('00:01:01'), 61)
 210         self.assertEqual(parse_duration('x:y'), None)
 211         self.assertEqual(parse_duration('3h11m53s'), 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
 219     def test_fix_xml_ampersands(self):
 220         self.assertEqual(
 221             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
 222         self.assertEqual(
 223             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
 224             '"&amp;x=y&amp;wrong;&amp;z=a')
 225         self.assertEqual(
 226             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
 227             '&amp;&apos;&gt;&lt;&quot;')
 228         self.assertEqual(
 229             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
 230         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
 231
 232     def test_paged_list(self):
 233         def testPL(size, pagesize, sliceargs, expected):
 234             def get_page(pagenum):
 235                 firstid = pagenum * pagesize
 236                 upto = min(size, pagenum * pagesize + pagesize)
 237                 for i in range(firstid, upto):
 238                     yield i
 239
 240             pl = PagedList(get_page, pagesize)
 241             got = pl.getslice(*sliceargs)
 242             self.assertEqual(got, expected)
 243
 244         testPL(5, 2, (), [0, 1, 2, 3, 4])
 245         testPL(5, 2, (1,), [1, 2, 3, 4])
 246         testPL(5, 2, (2,), [2, 3, 4])
 247         testPL(5, 2, (4,), [4])
 248         testPL(5, 2, (0, 3), [0, 1, 2])
 249         testPL(5, 2, (1, 4), [1, 2, 3])
 250         testPL(5, 2, (2, 99), [2, 3, 4])
 251         testPL(5, 2, (20, 99), [])
 252
 253     def test_struct_unpack(self):
 254         self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
 255
 256     def test_read_batch_urls(self):
 257         f = io.StringIO(u'''\xef\xbb\xbf foo
 258             bar\r
 259             baz
 260             # More after this line\r
 261             ; or after this
 262             bam''')
 263         self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
 264
 265     def test_urlencode_postdata(self):
 266         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
 267         self.assertTrue(isinstance(data, bytes))
 268
 269 if __name__ == '__main__':
 270     unittest.main()