]>
Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py
51eb0b6b936c7ea5d21cfef9bdc0b70f2ee7663a
4 # Allow direct execution
8 sys
.path
.insert(0, os
.path
.dirname(os
.path
.dirname(os
.path
.abspath(__file__
))))
11 # Various small unit tests
14 import xml
.etree
.ElementTree
16 #from youtube_dl.utils import htmlentity_transform
17 from youtube_dl
.utils
import (
44 if sys
.version_info
< (3, 0):
45 _compat_str
= lambda b
: b
.decode('unicode-escape')
47 _compat_str
= lambda s
: s
50 class TestUtil(unittest
.TestCase
):
51 def test_timeconvert(self
):
52 self
.assertTrue(timeconvert('') is None)
53 self
.assertTrue(timeconvert('bougrg') is None)
55 def test_sanitize_filename(self
):
56 self
.assertEqual(sanitize_filename('abc'), 'abc')
57 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
59 self
.assertEqual(sanitize_filename('123'), '123')
61 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
62 self
.assertFalse('/' in sanitize_filename('abc/de///'))
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'))
69 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
70 aumlaut
= _compat_str('\xe4')
71 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
72 tests
= _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
73 self
.assertEqual(sanitize_filename(tests
), tests
)
78 self
.assertTrue(fbc
not in sanitize_filename(fc
))
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')
84 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
86 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
87 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
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))
94 tests
= _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
95 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'a_b_c')
96 self
.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted
=True) != '') # No empty filename
98 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
100 for fbc
in forbidden
:
101 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
103 # Handle a common case more neatly
104 self
.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted
=True), 'Song')
105 self
.assertEqual(sanitize_filename(_compat_str('\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) != '')
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')
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])
122 def test_unescape_html(self
):
123 self
.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
125 def test_daterange(self
):
126 _20century
= DateRange("19000101","20000101")
127 self
.assertFalse("17890714" in _20century
)
128 _ac
= DateRange("00010101")
129 self
.assertTrue("19690721" in _ac
)
130 _firstmilenium
= DateRange(end
="10000101")
131 self
.assertTrue("07110427" in _firstmilenium
)
133 def test_unified_dates(self
):
134 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
135 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
136 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
137 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
138 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
140 def test_find_xpath_attr(self
):
147 doc
= xml
.etree
.ElementTree
.fromstring(testxml
)
149 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
150 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
151 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
153 def test_meta_parser(self
):
156 <meta name="description" content="foo & bar">
157 <meta content='Plato' name='author'/>
160 get_meta
= lambda name
: get_meta_content(name
, testhtml
)
161 self
.assertEqual(get_meta('description'), u
'foo & bar')
162 self
.assertEqual(get_meta('author'), 'Plato')
164 def test_xpath_with_ns(self
):
165 testxml
= u
'''<root xmlns:media="http://example.com/">
167 <media:author>The Author</media:author>
168 <url>http://server.com/download.mp3</url>
171 doc
= xml
.etree
.ElementTree
.fromstring(testxml
)
172 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}))
173 self
.assertTrue(find('media:song') is not None)
174 self
.assertEqual(find('media:song/media:author').text
, u
'The Author')
175 self
.assertEqual(find('media:song/url').text
, u
'http://server.com/download.mp3')
177 def test_smuggle_url(self
):
178 data
= {u
"ö": u
"ö", u
"abc": [3]}
179 url
= 'https://foo.bar/baz?x=y#a'
180 smug_url
= smuggle_url(url
, data
)
181 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
182 self
.assertEqual(url
, unsmug_url
)
183 self
.assertEqual(data
, unsmug_data
)
185 res_url
, res_data
= unsmuggle_url(url
)
186 self
.assertEqual(res_url
, url
)
187 self
.assertEqual(res_data
, None)
189 def test_shell_quote(self
):
190 args
= ['ffmpeg', '-i', encodeFilename(u
'ñ€ß\'.mp4')]
191 self
.assertEqual(shell_quote(args
), u
"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
193 def test_str_to_int(self
):
194 self
.assertEqual(str_to_int('123,456'), 123456)
195 self
.assertEqual(str_to_int('123.456'), 123456)
197 def test_url_basename(self
):
198 self
.assertEqual(url_basename(u
'http://foo.de/'), u
'')
199 self
.assertEqual(url_basename(u
'http://foo.de/bar/baz'), u
'baz')
200 self
.assertEqual(url_basename(u
'http://foo.de/bar/baz?x=y'), u
'baz')
201 self
.assertEqual(url_basename(u
'http://foo.de/bar/baz#x=y'), u
'baz')
202 self
.assertEqual(url_basename(u
'http://foo.de/bar/baz/'), u
'baz')
204 url_basename(u
'http://media.w3.org/2010/05/sintel/trailer.mp4'),
207 def test_parse_duration(self
):
208 self
.assertEqual(parse_duration(None), None)
209 self
.assertEqual(parse_duration('1'), 1)
210 self
.assertEqual(parse_duration('1337:12'), 80232)
211 self
.assertEqual(parse_duration('9:12:43'), 33163)
212 self
.assertEqual(parse_duration('12:00'), 720)
213 self
.assertEqual(parse_duration('00:01:01'), 61)
214 self
.assertEqual(parse_duration('x:y'), None)
215 self
.assertEqual(parse_duration('3h11m53s'), 11513)
216 self
.assertEqual(parse_duration('62m45s'), 3765)
217 self
.assertEqual(parse_duration('6m59s'), 419)
218 self
.assertEqual(parse_duration('49s'), 49)
219 self
.assertEqual(parse_duration('0h0m0s'), 0)
220 self
.assertEqual(parse_duration('0m0s'), 0)
221 self
.assertEqual(parse_duration('0s'), 0)
223 def test_fix_xml_ampersands(self
):
225 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
227 fix_xml_ampersands('"&x=y&wrong;&z=a'),
228 '"&x=y&wrong;&z=a')
230 fix_xml_ampersands('&'><"'),
231 '&'><"')
233 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
234 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
236 def test_paged_list(self
):
237 def testPL(size
, pagesize
, sliceargs
, expected
):
238 def get_page(pagenum
):
239 firstid
= pagenum
* pagesize
240 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
241 for i
in range(firstid
, upto
):
244 pl
= PagedList(get_page
, pagesize
)
245 got
= pl
.getslice(*sliceargs
)
246 self
.assertEqual(got
, expected
)
248 testPL(5, 2, (), [0, 1, 2, 3, 4])
249 testPL(5, 2, (1,), [1, 2, 3, 4])
250 testPL(5, 2, (2,), [2, 3, 4])
251 testPL(5, 2, (4,), [4])
252 testPL(5, 2, (0, 3), [0, 1, 2])
253 testPL(5, 2, (1, 4), [1, 2, 3])
254 testPL(5, 2, (2, 99), [2, 3, 4])
255 testPL(5, 2, (20, 99), [])
257 def test_struct_unpack(self
):
258 self
.assertEqual(struct_unpack(u
'!B', b
'\x00'), (0,))
260 def test_read_batch_urls(self
):
261 f
= io
.StringIO(u
'''\xef\xbb\xbf foo
264 # More after this line\r
267 self
.assertEqual(read_batch_urls(f
), [u
'foo', u
'bar', u
'baz', u
'bam'])
269 def test_urlencode_postdata(self
):
270 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
271 self
.assertTrue(isinstance(data
, bytes))
273 def test_parse_iso8601(self
):
274 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
275 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
276 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
278 def test_strip_jsonp(self
):
279 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
280 d
= json
.loads(stripped
)
281 self
.assertEqual(d
, [{"id": "532cb", "x": 3}])
283 def test_uppercase_escpae(self
):
284 self
.assertEqual(uppercase_escape(u
'aä'), u
'aä')
285 self
.assertEqual(uppercase_escape(u
'\\U0001d550'), u
'𝕐')
287 if __name__
== '__main__':