4 from __future__
import unicode_literals
6 # Allow direct execution
10 sys
.path
.insert(0, os
.path
.dirname(os
.path
.dirname(os
.path
.abspath(__file__
))))
13 # Various small unit tests
16 import xml
.etree
.ElementTree
18 from youtube_dl
.utils
import (
77 from youtube_dl
.compat
import (
78 compat_etree_fromstring
,
82 class TestUtil(unittest
.TestCase
):
83 def test_timeconvert(self
):
84 self
.assertTrue(timeconvert('') is None)
85 self
.assertTrue(timeconvert('bougrg') is None)
87 def test_sanitize_filename(self
):
88 self
.assertEqual(sanitize_filename('abc'), 'abc')
89 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
91 self
.assertEqual(sanitize_filename('123'), '123')
93 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
94 self
.assertFalse('/' in sanitize_filename('abc/de///'))
96 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
97 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
98 self
.assertEqual('yes no', sanitize_filename('yes? no'))
99 self
.assertEqual('this - that', sanitize_filename('this: that'))
101 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
103 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
104 tests
= '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
105 self
.assertEqual(sanitize_filename(tests
), tests
)
108 sanitize_filename('New World record at 0:12:34'),
109 'New World record at 0_12_34')
111 self
.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
112 self
.assertEqual(sanitize_filename('--gasdgf', is_id
=True), '--gasdgf')
113 self
.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
114 self
.assertEqual(sanitize_filename('.gasdgf', is_id
=True), '.gasdgf')
118 for fbc
in forbidden
:
119 self
.assertTrue(fbc
not in sanitize_filename(fc
))
121 def test_sanitize_filename_restricted(self
):
122 self
.assertEqual(sanitize_filename('abc', restricted
=True), 'abc')
123 self
.assertEqual(sanitize_filename('abc_d-e', restricted
=True), 'abc_d-e')
125 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
127 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
128 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
130 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted
=True))
131 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted
=True))
132 self
.assertEqual('yes_no', sanitize_filename('yes? no', restricted
=True))
133 self
.assertEqual('this_-_that', sanitize_filename('this: that', restricted
=True))
135 tests
= 'a\xe4b\u4e2d\u56fd\u7684c'
136 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'a_b_c')
137 self
.assertTrue(sanitize_filename('\xf6', restricted
=True) != '') # No empty filename
139 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
141 for fbc
in forbidden
:
142 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
144 # Handle a common case more neatly
145 self
.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted
=True), 'Song')
146 self
.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted
=True), 'Speech')
147 # .. but make sure the file name is never empty
148 self
.assertTrue(sanitize_filename('-', restricted
=True) != '')
149 self
.assertTrue(sanitize_filename(':', restricted
=True) != '')
151 def test_sanitize_ids(self
):
152 self
.assertEqual(sanitize_filename('_n_cd26wFpw', is_id
=True), '_n_cd26wFpw')
153 self
.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id
=True), '_BD_eEpuzXw')
154 self
.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id
=True), 'N0Y__7-UOdI')
156 def test_sanitize_path(self
):
157 if sys
.platform
!= 'win32':
160 self
.assertEqual(sanitize_path('abc'), 'abc')
161 self
.assertEqual(sanitize_path('abc/def'), 'abc\\def')
162 self
.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
163 self
.assertEqual(sanitize_path('abc|def'), 'abc#def')
164 self
.assertEqual(sanitize_path('<>:"|?*'), '#######')
165 self
.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
166 self
.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
168 self
.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
169 self
.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
171 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
172 self
.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
173 self
.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
174 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
177 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
178 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
181 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
182 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
183 self
.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
184 self
.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
185 self
.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
187 self
.assertEqual(sanitize_path('../abc'), '..\\abc')
188 self
.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
189 self
.assertEqual(sanitize_path('./abc'), 'abc')
190 self
.assertEqual(sanitize_path('./../abc'), '..\\abc')
192 def test_prepend_extension(self
):
193 self
.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
194 self
.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
195 self
.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
196 self
.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
197 self
.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
198 self
.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
200 def test_replace_extension(self
):
201 self
.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
202 self
.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
203 self
.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
204 self
.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
205 self
.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
206 self
.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
208 def test_remove_quotes(self
):
209 self
.assertEqual(remove_quotes(None), None)
210 self
.assertEqual(remove_quotes('"'), '"')
211 self
.assertEqual(remove_quotes("'"), "'")
212 self
.assertEqual(remove_quotes(';'), ';')
213 self
.assertEqual(remove_quotes('";'), '";')
214 self
.assertEqual(remove_quotes('""'), '')
215 self
.assertEqual(remove_quotes('";"'), ';')
217 def test_ordered_set(self
):
218 self
.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
219 self
.assertEqual(orderedSet([]), [])
220 self
.assertEqual(orderedSet([1]), [1])
221 # keep the list ordered
222 self
.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
224 def test_unescape_html(self
):
225 self
.assertEqual(unescapeHTML('%20;'), '%20;')
226 self
.assertEqual(unescapeHTML('/'), '/')
227 self
.assertEqual(unescapeHTML('/'), '/')
228 self
.assertEqual(unescapeHTML('é'), 'é')
229 self
.assertEqual(unescapeHTML('�'), '�')
231 def test_daterange(self
):
232 _20century
= DateRange("19000101", "20000101")
233 self
.assertFalse("17890714" in _20century
)
234 _ac
= DateRange("00010101")
235 self
.assertTrue("19690721" in _ac
)
236 _firstmilenium
= DateRange(end
="10000101")
237 self
.assertTrue("07110427" in _firstmilenium
)
239 def test_unified_dates(self
):
240 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
241 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
242 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
243 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
244 self
.assertEqual(unified_strdate('1968 12 10'), '19681210')
245 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
246 self
.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
248 unified_strdate('11/26/2014 11:30:00 AM PST', day_first
=False),
251 unified_strdate('2/2/2015 6:47:40 PM', day_first
=False),
253 self
.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
254 self
.assertEqual(unified_strdate('25-09-2014'), '20140925')
255 self
.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
257 def test_determine_ext(self
):
258 self
.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
259 self
.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
260 self
.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
261 self
.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
262 self
.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
264 def test_find_xpath_attr(self
):
272 doc
= compat_etree_fromstring(testxml
)
274 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n'), None)
275 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
276 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n'), None)
277 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n', 'v'), None)
278 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x'), doc
[1])
279 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
280 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'b'), doc
[3])
281 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y'), doc
[2])
282 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
283 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'd'), doc
[3])
284 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', ''), doc
[4])
286 def test_xpath_with_ns(self
):
287 testxml
= '''<root xmlns:media="http://example.com/">
289 <media:author>The Author</media:author>
290 <url>http://server.com/download.mp3</url>
293 doc
= compat_etree_fromstring(testxml
)
294 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}
))
295 self
.assertTrue(find('media:song') is not None)
296 self
.assertEqual(find('media:song/media:author').text
, 'The Author')
297 self
.assertEqual(find('media:song/url').text
, 'http://server.com/download.mp3')
299 def test_xpath_element(self
):
300 doc
= xml
.etree
.ElementTree
.Element('root')
301 div
= xml
.etree
.ElementTree
.SubElement(doc
, 'div')
302 p
= xml
.etree
.ElementTree
.SubElement(div
, 'p')
304 self
.assertEqual(xpath_element(doc
, 'div/p'), p
)
305 self
.assertEqual(xpath_element(doc
, ['div/p']), p
)
306 self
.assertEqual(xpath_element(doc
, ['div/bar', 'div/p']), p
)
307 self
.assertEqual(xpath_element(doc
, 'div/bar', default
='default'), 'default')
308 self
.assertEqual(xpath_element(doc
, ['div/bar'], default
='default'), 'default')
309 self
.assertTrue(xpath_element(doc
, 'div/bar') is None)
310 self
.assertTrue(xpath_element(doc
, ['div/bar']) is None)
311 self
.assertTrue(xpath_element(doc
, ['div/bar'], 'div/baz') is None)
312 self
.assertRaises(ExtractorError
, xpath_element
, doc
, 'div/bar', fatal
=True)
313 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar'], fatal
=True)
314 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar', 'div/baz'], fatal
=True)
316 def test_xpath_text(self
):
322 doc
= compat_etree_fromstring(testxml
)
323 self
.assertEqual(xpath_text(doc
, 'div/p'), 'Foo')
324 self
.assertEqual(xpath_text(doc
, 'div/bar', default
='default'), 'default')
325 self
.assertTrue(xpath_text(doc
, 'div/bar') is None)
326 self
.assertRaises(ExtractorError
, xpath_text
, doc
, 'div/bar', fatal
=True)
328 def test_xpath_attr(self
):
334 doc
= compat_etree_fromstring(testxml
)
335 self
.assertEqual(xpath_attr(doc
, 'div/p', 'x'), 'a')
336 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x'), None)
337 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y'), None)
338 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x', default
='default'), 'default')
339 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y', default
='default'), 'default')
340 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/bar', 'x', fatal
=True)
341 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/p', 'y', fatal
=True)
343 def test_smuggle_url(self
):
344 data
= {"ö": "ö", "abc": [3]}
345 url
= 'https://foo.bar/baz?x=y#a'
346 smug_url
= smuggle_url(url
, data
)
347 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
348 self
.assertEqual(url
, unsmug_url
)
349 self
.assertEqual(data
, unsmug_data
)
351 res_url
, res_data
= unsmuggle_url(url
)
352 self
.assertEqual(res_url
, url
)
353 self
.assertEqual(res_data
, None)
355 def test_shell_quote(self
):
356 args
= ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
357 self
.assertEqual(shell_quote(args
), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
359 def test_str_to_int(self
):
360 self
.assertEqual(str_to_int('123,456'), 123456)
361 self
.assertEqual(str_to_int('123.456'), 123456)
363 def test_url_basename(self
):
364 self
.assertEqual(url_basename('http://foo.de/'), '')
365 self
.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
366 self
.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
367 self
.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
368 self
.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
370 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
373 def test_parse_duration(self
):
374 self
.assertEqual(parse_duration(None), None)
375 self
.assertEqual(parse_duration(False), None)
376 self
.assertEqual(parse_duration('invalid'), None)
377 self
.assertEqual(parse_duration('1'), 1)
378 self
.assertEqual(parse_duration('1337:12'), 80232)
379 self
.assertEqual(parse_duration('9:12:43'), 33163)
380 self
.assertEqual(parse_duration('12:00'), 720)
381 self
.assertEqual(parse_duration('00:01:01'), 61)
382 self
.assertEqual(parse_duration('x:y'), None)
383 self
.assertEqual(parse_duration('3h11m53s'), 11513)
384 self
.assertEqual(parse_duration('3h 11m 53s'), 11513)
385 self
.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
386 self
.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
387 self
.assertEqual(parse_duration('62m45s'), 3765)
388 self
.assertEqual(parse_duration('6m59s'), 419)
389 self
.assertEqual(parse_duration('49s'), 49)
390 self
.assertEqual(parse_duration('0h0m0s'), 0)
391 self
.assertEqual(parse_duration('0m0s'), 0)
392 self
.assertEqual(parse_duration('0s'), 0)
393 self
.assertEqual(parse_duration('01:02:03.05'), 3723.05)
394 self
.assertEqual(parse_duration('T30M38S'), 1838)
395 self
.assertEqual(parse_duration('5 s'), 5)
396 self
.assertEqual(parse_duration('3 min'), 180)
397 self
.assertEqual(parse_duration('2.5 hours'), 9000)
398 self
.assertEqual(parse_duration('02:03:04'), 7384)
399 self
.assertEqual(parse_duration('01:02:03:04'), 93784)
400 self
.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
401 self
.assertEqual(parse_duration('87 Min.'), 5220)
403 def test_fix_xml_ampersands(self
):
405 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
407 fix_xml_ampersands('"&x=y&wrong;&z=a'),
408 '"&x=y&wrong;&z=a')
410 fix_xml_ampersands('&'><"'),
411 '&'><"')
413 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
414 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
416 def test_paged_list(self
):
417 def testPL(size
, pagesize
, sliceargs
, expected
):
418 def get_page(pagenum
):
419 firstid
= pagenum
* pagesize
420 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
421 for i
in range(firstid
, upto
):
424 pl
= OnDemandPagedList(get_page
, pagesize
)
425 got
= pl
.getslice(*sliceargs
)
426 self
.assertEqual(got
, expected
)
428 iapl
= InAdvancePagedList(get_page
, size
// pagesize
+ 1, pagesize
)
429 got
= iapl
.getslice(*sliceargs
)
430 self
.assertEqual(got
, expected
)
432 testPL(5, 2, (), [0, 1, 2, 3, 4])
433 testPL(5, 2, (1,), [1, 2, 3, 4])
434 testPL(5, 2, (2,), [2, 3, 4])
435 testPL(5, 2, (4,), [4])
436 testPL(5, 2, (0, 3), [0, 1, 2])
437 testPL(5, 2, (1, 4), [1, 2, 3])
438 testPL(5, 2, (2, 99), [2, 3, 4])
439 testPL(5, 2, (20, 99), [])
441 def test_struct_unpack(self
):
442 self
.assertEqual(struct_unpack('!B', b
'\x00'), (0,))
444 def test_read_batch_urls(self
):
445 f
= io
.StringIO('''\xef\xbb\xbf foo
448 # More after this line\r
451 self
.assertEqual(read_batch_urls(f
), ['foo', 'bar', 'baz', 'bam'])
453 def test_urlencode_postdata(self
):
454 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}
)
455 self
.assertTrue(isinstance(data
, bytes))
457 def test_dict_get(self
):
465 d
= FALSE_VALUES
.copy()
467 self
.assertEqual(dict_get(d
, 'a'), 42)
468 self
.assertEqual(dict_get(d
, 'b'), None)
469 self
.assertEqual(dict_get(d
, 'b', 42), 42)
470 self
.assertEqual(dict_get(d
, ('a', )), 42)
471 self
.assertEqual(dict_get(d
, ('b', 'a', )), 42)
472 self
.assertEqual(dict_get(d
, ('b', 'c', 'a', 'd', )), 42)
473 self
.assertEqual(dict_get(d
, ('b', 'c', )), None)
474 self
.assertEqual(dict_get(d
, ('b', 'c', ), 42), 42)
475 for key
, false_value
in FALSE_VALUES
.items():
476 self
.assertEqual(dict_get(d
, ('b', 'c', key
, )), None)
477 self
.assertEqual(dict_get(d
, ('b', 'c', key
, ), skip_false_values
=False), false_value
)
479 def test_encode_compat_str(self
):
480 self
.assertEqual(encode_compat_str(b
'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
481 self
.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
483 def test_parse_iso8601(self
):
484 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
485 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
486 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
487 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
488 self
.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
489 self
.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
491 def test_strip_jsonp(self
):
492 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
493 d
= json
.loads(stripped
)
494 self
.assertEqual(d
, [{"id": "532cb", "x": 3}
])
496 stripped
= strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
497 d
= json
.loads(stripped
)
498 self
.assertEqual(d
, {'STATUS': 'OK'}
)
500 stripped
= strip_jsonp('ps.embedHandler({"status": "success"});')
501 d
= json
.loads(stripped
)
502 self
.assertEqual(d
, {'status': 'success'}
)
504 def test_uppercase_escape(self
):
505 self
.assertEqual(uppercase_escape('aä'), 'aä')
506 self
.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
508 def test_lowercase_escape(self
):
509 self
.assertEqual(lowercase_escape('aä'), 'aä')
510 self
.assertEqual(lowercase_escape('\\u0026'), '&')
512 def test_limit_length(self
):
513 self
.assertEqual(limit_length(None, 12), None)
514 self
.assertEqual(limit_length('foo', 12), 'foo')
516 limit_length('foo bar baz asd', 12).startswith('foo bar'))
517 self
.assertTrue('...' in limit_length('foo bar baz asd', 12))
519 def test_escape_rfc3986(self
):
520 reserved
= "!*'();:@&=+$,/?#[]"
521 unreserved
= 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
522 self
.assertEqual(escape_rfc3986(reserved
), reserved
)
523 self
.assertEqual(escape_rfc3986(unreserved
), unreserved
)
524 self
.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
525 self
.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
526 self
.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
527 self
.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
529 def test_escape_url(self
):
531 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
532 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
535 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
536 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
539 escape_url('http://тест.рф/фрагмент'),
540 'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
543 escape_url('http://тест.рф/абв?абв=абв#абв'),
544 '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'
546 self
.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
548 def test_js_to_json_realworld(self
):
550 'clip':{'provider':'pseudo'}
552 self
.assertEqual(js_to_json(inp
), '''{
553 "clip":{"provider":"pseudo"}
555 json
.loads(js_to_json(inp
))
558 'playlist':[{'controls':{'all':null}}]
560 self
.assertEqual(js_to_json(inp
), '''{
561 "playlist":[{"controls":{"all":null}}]
564 inp
= '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
565 self
.assertEqual(js_to_json(inp
), '''"The CW's 'Crazy Ex-Girlfriend'"''')
567 inp
= '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
568 json_code
= js_to_json(inp
)
569 self
.assertEqual(json
.loads(json_code
), json
.loads(inp
))
571 def test_js_to_json_edgecases(self
):
572 on
= js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
573 self
.assertEqual(json
.loads(on
), {"abc_def": "1'\\2\\'3\"4"}
)
575 on
= js_to_json('{"abc": true}')
576 self
.assertEqual(json
.loads(on
), {'abc': True}
)
578 # Ignore JavaScript code as well
585 self
.assertEqual(d
['x'], 1)
586 self
.assertEqual(d
['y'], 'a')
588 on
= js_to_json('["abc", "def",]')
589 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
591 on
= js_to_json('{"abc": "def",}')
592 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
594 def test_clean_html(self
):
595 self
.assertEqual(clean_html('a:\nb'), 'a: b')
596 self
.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
598 def test_intlist_to_bytes(self
):
600 intlist_to_bytes([0, 1, 127, 128, 255]),
601 b
'\x00\x01\x7f\x80\xff')
603 def test_args_to_str(self
):
605 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
606 'foo ba/r -baz \'2 be\' \'\''
609 def test_parse_filesize(self
):
610 self
.assertEqual(parse_filesize(None), None)
611 self
.assertEqual(parse_filesize(''), None)
612 self
.assertEqual(parse_filesize('91 B'), 91)
613 self
.assertEqual(parse_filesize('foobar'), None)
614 self
.assertEqual(parse_filesize('2 MiB'), 2097152)
615 self
.assertEqual(parse_filesize('5 GB'), 5000000000)
616 self
.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
617 self
.assertEqual(parse_filesize('1,24 KB'), 1240)
619 def test_version_tuple(self
):
620 self
.assertEqual(version_tuple('1'), (1,))
621 self
.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
622 self
.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
624 def test_detect_exe_version(self
):
625 self
.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
626 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
627 configuration: --prefix=/usr --extra-'''), '1.2.1')
628 self
.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
629 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
630 self
.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
631 Trying to open render node...
632 Success at /dev/dri/renderD128.
633 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
635 def test_age_restricted(self
):
636 self
.assertFalse(age_restricted(None, 10)) # unrestricted content
637 self
.assertFalse(age_restricted(1, None)) # unrestricted policy
638 self
.assertFalse(age_restricted(8, 10))
639 self
.assertTrue(age_restricted(18, 14))
640 self
.assertFalse(age_restricted(18, 18))
642 def test_is_html(self
):
643 self
.assertFalse(is_html(b
'\x49\x44\x43<html'))
644 self
.assertTrue(is_html(b
'<!DOCTYPE foo>\xaaa'))
645 self
.assertTrue(is_html( # UTF-8 with BOM
646 b
'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
647 self
.assertTrue(is_html( # UTF-16-LE
648 b
'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
650 self
.assertTrue(is_html( # UTF-16-BE
651 b
'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
653 self
.assertTrue(is_html( # UTF-32-BE
654 b
'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
655 self
.assertTrue(is_html( # UTF-32-LE
656 b
'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
658 def test_render_table(self
):
662 [[123, 4], [9999, 51]]),
667 def test_match_str(self
):
668 self
.assertRaises(ValueError, match_str
, 'xy>foobar', {})
669 self
.assertFalse(match_str('xy', {'x': 1200}
))
670 self
.assertTrue(match_str('!xy', {'x': 1200}
))
671 self
.assertTrue(match_str('x', {'x': 1200}
))
672 self
.assertFalse(match_str('!x', {'x': 1200}
))
673 self
.assertTrue(match_str('x', {'x': 0}
))
674 self
.assertFalse(match_str('x>0', {'x': 0}
))
675 self
.assertFalse(match_str('x>0', {}))
676 self
.assertTrue(match_str('x>?0', {}))
677 self
.assertTrue(match_str('x>1K', {'x': 1200}
))
678 self
.assertFalse(match_str('x>2K', {'x': 1200}
))
679 self
.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}
))
680 self
.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}
))
681 self
.assertFalse(match_str('y=a212', {'y': 'foobar42'}
))
682 self
.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}
))
683 self
.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}
))
684 self
.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}
))
685 self
.assertFalse(match_str(
686 'like_count > 100 & dislike_count <? 50 & description',
687 {'like_count': 90, 'description': 'foo'}
))
688 self
.assertTrue(match_str(
689 'like_count > 100 & dislike_count <? 50 & description',
690 {'like_count': 190, 'description': 'foo'}
))
691 self
.assertFalse(match_str(
692 'like_count > 100 & dislike_count <? 50 & description',
693 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}
))
694 self
.assertFalse(match_str(
695 'like_count > 100 & dislike_count <? 50 & description',
696 {'like_count': 190, 'dislike_count': 10}
))
698 def test_parse_dfxp_time_expr(self
):
699 self
.assertEqual(parse_dfxp_time_expr(None), None)
700 self
.assertEqual(parse_dfxp_time_expr(''), None)
701 self
.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
702 self
.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
703 self
.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
704 self
.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
705 self
.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
707 def test_dfxp2srt(self
):
708 dfxp_data
= '''<?xml version="1.0" encoding="UTF-8"?>
709 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
712 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
713 <p begin="1" end="2">第二行<br/>♪♪</p>
714 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
715 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
716 <p begin="-1" end="-1">Ignore, two</p>
717 <p begin="3" dur="-1">Ignored, three</p>
722 00:00:00,000 --> 00:00:01,000
723 The following line contains Chinese characters and special symbols
726 00:00:01,000 --> 00:00:02,000
731 00:00:02,000 --> 00:00:03,000
736 self
.assertEqual(dfxp2srt(dfxp_data
), srt_data
)
738 dfxp_data_no_default_namespace
= '''<?xml version="1.0" encoding="UTF-8"?>
739 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
742 <p begin="0" end="1">The first line</p>
747 00:00:00,000 --> 00:00:01,000
751 self
.assertEqual(dfxp2srt(dfxp_data_no_default_namespace
), srt_data
)
753 def test_cli_option(self
):
754 self
.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}
, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
755 self
.assertEqual(cli_option({'proxy': None}
, '--proxy', 'proxy'), [])
756 self
.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
758 def test_cli_valueless_option(self
):
759 self
.assertEqual(cli_valueless_option(
760 {'downloader': 'external'}
, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
761 self
.assertEqual(cli_valueless_option(
762 {'downloader': 'internal'}
, '--external-downloader', 'downloader', 'external'), [])
763 self
.assertEqual(cli_valueless_option(
764 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
765 self
.assertEqual(cli_valueless_option(
766 {'nocheckcertificate': False}
, '--no-check-certificate', 'nocheckcertificate'), [])
767 self
.assertEqual(cli_valueless_option(
768 {'checkcertificate': True}
, '--no-check-certificate', 'checkcertificate', False), [])
769 self
.assertEqual(cli_valueless_option(
770 {'checkcertificate': False}
, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
772 def test_cli_bool_option(self
):
775 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'),
776 ['--no-check-certificate', 'true'])
779 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate', separator
='='),
780 ['--no-check-certificate=true'])
783 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
784 ['--check-certificate', 'false'])
787 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
788 ['--check-certificate=false'])
791 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
792 ['--check-certificate', 'true'])
795 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
796 ['--check-certificate=true'])
798 def test_ohdave_rsa_encrypt(self
):
799 N
= 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
803 ohdave_rsa_encrypt(b
'aa111222', e
, N
),
804 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
806 def test_encode_base_n(self
):
807 self
.assertEqual(encode_base_n(0, 30), '0')
808 self
.assertEqual(encode_base_n(80, 30), '2k')
810 custom_table
= '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
811 self
.assertEqual(encode_base_n(0, 30, custom_table
), '9')
812 self
.assertEqual(encode_base_n(80, 30, custom_table
), '7P')
814 self
.assertRaises(ValueError, encode_base_n
, 0, 70)
815 self
.assertRaises(ValueError, encode_base_n
, 0, 60, custom_table
)
817 if __name__
== '__main__':