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 (
75 from youtube_dl
.compat
import (
76 compat_etree_fromstring
,
80 class TestUtil(unittest
.TestCase
):
81 def test_timeconvert(self
):
82 self
.assertTrue(timeconvert('') is None)
83 self
.assertTrue(timeconvert('bougrg') is None)
85 def test_sanitize_filename(self
):
86 self
.assertEqual(sanitize_filename('abc'), 'abc')
87 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
89 self
.assertEqual(sanitize_filename('123'), '123')
91 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
92 self
.assertFalse('/' in sanitize_filename('abc/de///'))
94 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
95 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
96 self
.assertEqual('yes no', sanitize_filename('yes? no'))
97 self
.assertEqual('this - that', sanitize_filename('this: that'))
99 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
101 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
102 tests
= '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
103 self
.assertEqual(sanitize_filename(tests
), tests
)
106 sanitize_filename('New World record at 0:12:34'),
107 'New World record at 0_12_34')
109 self
.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
110 self
.assertEqual(sanitize_filename('--gasdgf', is_id
=True), '--gasdgf')
111 self
.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
112 self
.assertEqual(sanitize_filename('.gasdgf', is_id
=True), '.gasdgf')
116 for fbc
in forbidden
:
117 self
.assertTrue(fbc
not in sanitize_filename(fc
))
119 def test_sanitize_filename_restricted(self
):
120 self
.assertEqual(sanitize_filename('abc', restricted
=True), 'abc')
121 self
.assertEqual(sanitize_filename('abc_d-e', restricted
=True), 'abc_d-e')
123 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
125 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
126 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
128 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted
=True))
129 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted
=True))
130 self
.assertEqual('yes_no', sanitize_filename('yes? no', restricted
=True))
131 self
.assertEqual('this_-_that', sanitize_filename('this: that', restricted
=True))
133 tests
= 'a\xe4b\u4e2d\u56fd\u7684c'
134 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'a_b_c')
135 self
.assertTrue(sanitize_filename('\xf6', restricted
=True) != '') # No empty filename
137 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
139 for fbc
in forbidden
:
140 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
142 # Handle a common case more neatly
143 self
.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted
=True), 'Song')
144 self
.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted
=True), 'Speech')
145 # .. but make sure the file name is never empty
146 self
.assertTrue(sanitize_filename('-', restricted
=True) != '')
147 self
.assertTrue(sanitize_filename(':', restricted
=True) != '')
149 def test_sanitize_ids(self
):
150 self
.assertEqual(sanitize_filename('_n_cd26wFpw', is_id
=True), '_n_cd26wFpw')
151 self
.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id
=True), '_BD_eEpuzXw')
152 self
.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id
=True), 'N0Y__7-UOdI')
154 def test_sanitize_path(self
):
155 if sys
.platform
!= 'win32':
158 self
.assertEqual(sanitize_path('abc'), 'abc')
159 self
.assertEqual(sanitize_path('abc/def'), 'abc\\def')
160 self
.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
161 self
.assertEqual(sanitize_path('abc|def'), 'abc#def')
162 self
.assertEqual(sanitize_path('<>:"|?*'), '#######')
163 self
.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
164 self
.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
166 self
.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
167 self
.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
169 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
170 self
.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
171 self
.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
172 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
175 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
176 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
179 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
180 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
181 self
.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
182 self
.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
183 self
.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
185 self
.assertEqual(sanitize_path('../abc'), '..\\abc')
186 self
.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
187 self
.assertEqual(sanitize_path('./abc'), 'abc')
188 self
.assertEqual(sanitize_path('./../abc'), '..\\abc')
190 def test_prepend_extension(self
):
191 self
.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
192 self
.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
193 self
.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
194 self
.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
195 self
.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
196 self
.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
198 def test_replace_extension(self
):
199 self
.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
200 self
.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
201 self
.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
202 self
.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
203 self
.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
204 self
.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
206 def test_remove_quotes(self
):
207 self
.assertEqual(remove_quotes(None), None)
208 self
.assertEqual(remove_quotes('"'), '"')
209 self
.assertEqual(remove_quotes("'"), "'")
210 self
.assertEqual(remove_quotes(';'), ';')
211 self
.assertEqual(remove_quotes('";'), '";')
212 self
.assertEqual(remove_quotes('""'), '')
213 self
.assertEqual(remove_quotes('";"'), ';')
215 def test_ordered_set(self
):
216 self
.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
217 self
.assertEqual(orderedSet([]), [])
218 self
.assertEqual(orderedSet([1]), [1])
219 # keep the list ordered
220 self
.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
222 def test_unescape_html(self
):
223 self
.assertEqual(unescapeHTML('%20;'), '%20;')
224 self
.assertEqual(unescapeHTML('/'), '/')
225 self
.assertEqual(unescapeHTML('/'), '/')
226 self
.assertEqual(unescapeHTML('é'), 'é')
227 self
.assertEqual(unescapeHTML('�'), '�')
229 def test_daterange(self
):
230 _20century
= DateRange("19000101", "20000101")
231 self
.assertFalse("17890714" in _20century
)
232 _ac
= DateRange("00010101")
233 self
.assertTrue("19690721" in _ac
)
234 _firstmilenium
= DateRange(end
="10000101")
235 self
.assertTrue("07110427" in _firstmilenium
)
237 def test_unified_dates(self
):
238 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
239 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
240 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
241 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
242 self
.assertEqual(unified_strdate('1968 12 10'), '19681210')
243 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
244 self
.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
246 unified_strdate('11/26/2014 11:30:00 AM PST', day_first
=False),
249 unified_strdate('2/2/2015 6:47:40 PM', day_first
=False),
251 self
.assertEqual(unified_strdate('25-09-2014'), '20140925')
252 self
.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
254 def test_determine_ext(self
):
255 self
.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
256 self
.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
257 self
.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
258 self
.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
259 self
.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
261 def test_find_xpath_attr(self
):
269 doc
= compat_etree_fromstring(testxml
)
271 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n'), None)
272 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
273 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n'), None)
274 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n', 'v'), None)
275 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x'), doc
[1])
276 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
277 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'b'), doc
[3])
278 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y'), doc
[2])
279 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
280 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'd'), doc
[3])
281 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', ''), doc
[4])
283 def test_xpath_with_ns(self
):
284 testxml
= '''<root xmlns:media="http://example.com/">
286 <media:author>The Author</media:author>
287 <url>http://server.com/download.mp3</url>
290 doc
= compat_etree_fromstring(testxml
)
291 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}
))
292 self
.assertTrue(find('media:song') is not None)
293 self
.assertEqual(find('media:song/media:author').text
, 'The Author')
294 self
.assertEqual(find('media:song/url').text
, 'http://server.com/download.mp3')
296 def test_xpath_element(self
):
297 doc
= xml
.etree
.ElementTree
.Element('root')
298 div
= xml
.etree
.ElementTree
.SubElement(doc
, 'div')
299 p
= xml
.etree
.ElementTree
.SubElement(div
, 'p')
301 self
.assertEqual(xpath_element(doc
, 'div/p'), p
)
302 self
.assertEqual(xpath_element(doc
, ['div/p']), p
)
303 self
.assertEqual(xpath_element(doc
, ['div/bar', 'div/p']), p
)
304 self
.assertEqual(xpath_element(doc
, 'div/bar', default
='default'), 'default')
305 self
.assertEqual(xpath_element(doc
, ['div/bar'], default
='default'), 'default')
306 self
.assertTrue(xpath_element(doc
, 'div/bar') is None)
307 self
.assertTrue(xpath_element(doc
, ['div/bar']) is None)
308 self
.assertTrue(xpath_element(doc
, ['div/bar'], 'div/baz') is None)
309 self
.assertRaises(ExtractorError
, xpath_element
, doc
, 'div/bar', fatal
=True)
310 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar'], fatal
=True)
311 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar', 'div/baz'], fatal
=True)
313 def test_xpath_text(self
):
319 doc
= compat_etree_fromstring(testxml
)
320 self
.assertEqual(xpath_text(doc
, 'div/p'), 'Foo')
321 self
.assertEqual(xpath_text(doc
, 'div/bar', default
='default'), 'default')
322 self
.assertTrue(xpath_text(doc
, 'div/bar') is None)
323 self
.assertRaises(ExtractorError
, xpath_text
, doc
, 'div/bar', fatal
=True)
325 def test_xpath_attr(self
):
331 doc
= compat_etree_fromstring(testxml
)
332 self
.assertEqual(xpath_attr(doc
, 'div/p', 'x'), 'a')
333 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x'), None)
334 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y'), None)
335 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x', default
='default'), 'default')
336 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y', default
='default'), 'default')
337 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/bar', 'x', fatal
=True)
338 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/p', 'y', fatal
=True)
340 def test_smuggle_url(self
):
341 data
= {"ö": "ö", "abc": [3]}
342 url
= 'https://foo.bar/baz?x=y#a'
343 smug_url
= smuggle_url(url
, data
)
344 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
345 self
.assertEqual(url
, unsmug_url
)
346 self
.assertEqual(data
, unsmug_data
)
348 res_url
, res_data
= unsmuggle_url(url
)
349 self
.assertEqual(res_url
, url
)
350 self
.assertEqual(res_data
, None)
352 def test_shell_quote(self
):
353 args
= ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
354 self
.assertEqual(shell_quote(args
), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
356 def test_str_to_int(self
):
357 self
.assertEqual(str_to_int('123,456'), 123456)
358 self
.assertEqual(str_to_int('123.456'), 123456)
360 def test_url_basename(self
):
361 self
.assertEqual(url_basename('http://foo.de/'), '')
362 self
.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
363 self
.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
364 self
.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
365 self
.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
367 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
370 def test_parse_duration(self
):
371 self
.assertEqual(parse_duration(None), None)
372 self
.assertEqual(parse_duration(False), None)
373 self
.assertEqual(parse_duration('invalid'), None)
374 self
.assertEqual(parse_duration('1'), 1)
375 self
.assertEqual(parse_duration('1337:12'), 80232)
376 self
.assertEqual(parse_duration('9:12:43'), 33163)
377 self
.assertEqual(parse_duration('12:00'), 720)
378 self
.assertEqual(parse_duration('00:01:01'), 61)
379 self
.assertEqual(parse_duration('x:y'), None)
380 self
.assertEqual(parse_duration('3h11m53s'), 11513)
381 self
.assertEqual(parse_duration('3h 11m 53s'), 11513)
382 self
.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
383 self
.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
384 self
.assertEqual(parse_duration('62m45s'), 3765)
385 self
.assertEqual(parse_duration('6m59s'), 419)
386 self
.assertEqual(parse_duration('49s'), 49)
387 self
.assertEqual(parse_duration('0h0m0s'), 0)
388 self
.assertEqual(parse_duration('0m0s'), 0)
389 self
.assertEqual(parse_duration('0s'), 0)
390 self
.assertEqual(parse_duration('01:02:03.05'), 3723.05)
391 self
.assertEqual(parse_duration('T30M38S'), 1838)
392 self
.assertEqual(parse_duration('5 s'), 5)
393 self
.assertEqual(parse_duration('3 min'), 180)
394 self
.assertEqual(parse_duration('2.5 hours'), 9000)
395 self
.assertEqual(parse_duration('02:03:04'), 7384)
396 self
.assertEqual(parse_duration('01:02:03:04'), 93784)
397 self
.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
398 self
.assertEqual(parse_duration('87 Min.'), 5220)
400 def test_fix_xml_ampersands(self
):
402 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
404 fix_xml_ampersands('"&x=y&wrong;&z=a'),
405 '"&x=y&wrong;&z=a')
407 fix_xml_ampersands('&'><"'),
408 '&'><"')
410 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
411 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
413 def test_paged_list(self
):
414 def testPL(size
, pagesize
, sliceargs
, expected
):
415 def get_page(pagenum
):
416 firstid
= pagenum
* pagesize
417 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
418 for i
in range(firstid
, upto
):
421 pl
= OnDemandPagedList(get_page
, pagesize
)
422 got
= pl
.getslice(*sliceargs
)
423 self
.assertEqual(got
, expected
)
425 iapl
= InAdvancePagedList(get_page
, size
// pagesize
+ 1, pagesize
)
426 got
= iapl
.getslice(*sliceargs
)
427 self
.assertEqual(got
, expected
)
429 testPL(5, 2, (), [0, 1, 2, 3, 4])
430 testPL(5, 2, (1,), [1, 2, 3, 4])
431 testPL(5, 2, (2,), [2, 3, 4])
432 testPL(5, 2, (4,), [4])
433 testPL(5, 2, (0, 3), [0, 1, 2])
434 testPL(5, 2, (1, 4), [1, 2, 3])
435 testPL(5, 2, (2, 99), [2, 3, 4])
436 testPL(5, 2, (20, 99), [])
438 def test_struct_unpack(self
):
439 self
.assertEqual(struct_unpack('!B', b
'\x00'), (0,))
441 def test_read_batch_urls(self
):
442 f
= io
.StringIO('''\xef\xbb\xbf foo
445 # More after this line\r
448 self
.assertEqual(read_batch_urls(f
), ['foo', 'bar', 'baz', 'bam'])
450 def test_urlencode_postdata(self
):
451 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}
)
452 self
.assertTrue(isinstance(data
, bytes))
454 def test_dict_get(self
):
462 d
= FALSE_VALUES
.copy()
464 self
.assertEqual(dict_get(d
, 'a'), 42)
465 self
.assertEqual(dict_get(d
, 'b'), None)
466 self
.assertEqual(dict_get(d
, 'b', 42), 42)
467 self
.assertEqual(dict_get(d
, ('a', )), 42)
468 self
.assertEqual(dict_get(d
, ('b', 'a', )), 42)
469 self
.assertEqual(dict_get(d
, ('b', 'c', 'a', 'd', )), 42)
470 self
.assertEqual(dict_get(d
, ('b', 'c', )), None)
471 self
.assertEqual(dict_get(d
, ('b', 'c', ), 42), 42)
472 for key
, false_value
in FALSE_VALUES
.items():
473 self
.assertEqual(dict_get(d
, ('b', 'c', key
, )), None)
474 self
.assertEqual(dict_get(d
, ('b', 'c', key
, ), skip_false_values
=False), false_value
)
476 def test_encode_compat_str(self
):
477 self
.assertEqual(encode_compat_str(b
'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
478 self
.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
480 def test_parse_iso8601(self
):
481 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
482 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
483 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
484 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
485 self
.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
486 self
.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
488 def test_strip_jsonp(self
):
489 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
490 d
= json
.loads(stripped
)
491 self
.assertEqual(d
, [{"id": "532cb", "x": 3}
])
493 stripped
= strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
494 d
= json
.loads(stripped
)
495 self
.assertEqual(d
, {'STATUS': 'OK'}
)
497 stripped
= strip_jsonp('ps.embedHandler({"status": "success"});')
498 d
= json
.loads(stripped
)
499 self
.assertEqual(d
, {'status': 'success'}
)
501 def test_uppercase_escape(self
):
502 self
.assertEqual(uppercase_escape('aä'), 'aä')
503 self
.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
505 def test_lowercase_escape(self
):
506 self
.assertEqual(lowercase_escape('aä'), 'aä')
507 self
.assertEqual(lowercase_escape('\\u0026'), '&')
509 def test_limit_length(self
):
510 self
.assertEqual(limit_length(None, 12), None)
511 self
.assertEqual(limit_length('foo', 12), 'foo')
513 limit_length('foo bar baz asd', 12).startswith('foo bar'))
514 self
.assertTrue('...' in limit_length('foo bar baz asd', 12))
516 def test_escape_rfc3986(self
):
517 reserved
= "!*'();:@&=+$,/?#[]"
518 unreserved
= 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
519 self
.assertEqual(escape_rfc3986(reserved
), reserved
)
520 self
.assertEqual(escape_rfc3986(unreserved
), unreserved
)
521 self
.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
522 self
.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
523 self
.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
524 self
.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
526 def test_escape_url(self
):
528 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
529 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
532 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
533 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
536 escape_url('http://тест.рф/фрагмент'),
537 'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
540 escape_url('http://тест.рф/абв?абв=абв#абв'),
541 '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'
543 self
.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
545 def test_js_to_json_realworld(self
):
547 'clip':{'provider':'pseudo'}
549 self
.assertEqual(js_to_json(inp
), '''{
550 "clip":{"provider":"pseudo"}
552 json
.loads(js_to_json(inp
))
555 'playlist':[{'controls':{'all':null}}]
557 self
.assertEqual(js_to_json(inp
), '''{
558 "playlist":[{"controls":{"all":null}}]
561 inp
= '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
562 self
.assertEqual(js_to_json(inp
), '''"The CW's 'Crazy Ex-Girlfriend'"''')
564 inp
= '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
565 json_code
= js_to_json(inp
)
566 self
.assertEqual(json
.loads(json_code
), json
.loads(inp
))
568 def test_js_to_json_edgecases(self
):
569 on
= js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
570 self
.assertEqual(json
.loads(on
), {"abc_def": "1'\\2\\'3\"4"}
)
572 on
= js_to_json('{"abc": true}')
573 self
.assertEqual(json
.loads(on
), {'abc': True}
)
575 # Ignore JavaScript code as well
582 self
.assertEqual(d
['x'], 1)
583 self
.assertEqual(d
['y'], 'a')
585 on
= js_to_json('["abc", "def",]')
586 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
588 on
= js_to_json('{"abc": "def",}')
589 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
591 def test_clean_html(self
):
592 self
.assertEqual(clean_html('a:\nb'), 'a: b')
593 self
.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
595 def test_intlist_to_bytes(self
):
597 intlist_to_bytes([0, 1, 127, 128, 255]),
598 b
'\x00\x01\x7f\x80\xff')
600 def test_args_to_str(self
):
602 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
603 'foo ba/r -baz \'2 be\' \'\''
606 def test_parse_filesize(self
):
607 self
.assertEqual(parse_filesize(None), None)
608 self
.assertEqual(parse_filesize(''), None)
609 self
.assertEqual(parse_filesize('91 B'), 91)
610 self
.assertEqual(parse_filesize('foobar'), None)
611 self
.assertEqual(parse_filesize('2 MiB'), 2097152)
612 self
.assertEqual(parse_filesize('5 GB'), 5000000000)
613 self
.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
614 self
.assertEqual(parse_filesize('1,24 KB'), 1240)
616 def test_version_tuple(self
):
617 self
.assertEqual(version_tuple('1'), (1,))
618 self
.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
619 self
.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
621 def test_detect_exe_version(self
):
622 self
.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
623 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
624 configuration: --prefix=/usr --extra-'''), '1.2.1')
625 self
.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
626 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
627 self
.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
628 Trying to open render node...
629 Success at /dev/dri/renderD128.
630 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
632 def test_age_restricted(self
):
633 self
.assertFalse(age_restricted(None, 10)) # unrestricted content
634 self
.assertFalse(age_restricted(1, None)) # unrestricted policy
635 self
.assertFalse(age_restricted(8, 10))
636 self
.assertTrue(age_restricted(18, 14))
637 self
.assertFalse(age_restricted(18, 18))
639 def test_is_html(self
):
640 self
.assertFalse(is_html(b
'\x49\x44\x43<html'))
641 self
.assertTrue(is_html(b
'<!DOCTYPE foo>\xaaa'))
642 self
.assertTrue(is_html( # UTF-8 with BOM
643 b
'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
644 self
.assertTrue(is_html( # UTF-16-LE
645 b
'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
647 self
.assertTrue(is_html( # UTF-16-BE
648 b
'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
650 self
.assertTrue(is_html( # UTF-32-BE
651 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'))
652 self
.assertTrue(is_html( # UTF-32-LE
653 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'))
655 def test_render_table(self
):
659 [[123, 4], [9999, 51]]),
664 def test_match_str(self
):
665 self
.assertRaises(ValueError, match_str
, 'xy>foobar', {})
666 self
.assertFalse(match_str('xy', {'x': 1200}
))
667 self
.assertTrue(match_str('!xy', {'x': 1200}
))
668 self
.assertTrue(match_str('x', {'x': 1200}
))
669 self
.assertFalse(match_str('!x', {'x': 1200}
))
670 self
.assertTrue(match_str('x', {'x': 0}
))
671 self
.assertFalse(match_str('x>0', {'x': 0}
))
672 self
.assertFalse(match_str('x>0', {}))
673 self
.assertTrue(match_str('x>?0', {}))
674 self
.assertTrue(match_str('x>1K', {'x': 1200}
))
675 self
.assertFalse(match_str('x>2K', {'x': 1200}
))
676 self
.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}
))
677 self
.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}
))
678 self
.assertFalse(match_str('y=a212', {'y': 'foobar42'}
))
679 self
.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}
))
680 self
.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}
))
681 self
.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}
))
682 self
.assertFalse(match_str(
683 'like_count > 100 & dislike_count <? 50 & description',
684 {'like_count': 90, 'description': 'foo'}
))
685 self
.assertTrue(match_str(
686 'like_count > 100 & dislike_count <? 50 & description',
687 {'like_count': 190, 'description': 'foo'}
))
688 self
.assertFalse(match_str(
689 'like_count > 100 & dislike_count <? 50 & description',
690 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}
))
691 self
.assertFalse(match_str(
692 'like_count > 100 & dislike_count <? 50 & description',
693 {'like_count': 190, 'dislike_count': 10}
))
695 def test_parse_dfxp_time_expr(self
):
696 self
.assertEqual(parse_dfxp_time_expr(None), None)
697 self
.assertEqual(parse_dfxp_time_expr(''), None)
698 self
.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
699 self
.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
700 self
.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
701 self
.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
702 self
.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
704 def test_dfxp2srt(self
):
705 dfxp_data
= '''<?xml version="1.0" encoding="UTF-8"?>
706 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
709 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
710 <p begin="1" end="2">第二行<br/>♪♪</p>
711 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
712 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
713 <p begin="-1" end="-1">Ignore, two</p>
714 <p begin="3" dur="-1">Ignored, three</p>
719 00:00:00,000 --> 00:00:01,000
720 The following line contains Chinese characters and special symbols
723 00:00:01,000 --> 00:00:02,000
728 00:00:02,000 --> 00:00:03,000
733 self
.assertEqual(dfxp2srt(dfxp_data
), srt_data
)
735 dfxp_data_no_default_namespace
= '''<?xml version="1.0" encoding="UTF-8"?>
736 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
739 <p begin="0" end="1">The first line</p>
744 00:00:00,000 --> 00:00:01,000
748 self
.assertEqual(dfxp2srt(dfxp_data_no_default_namespace
), srt_data
)
750 def test_cli_option(self
):
751 self
.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}
, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
752 self
.assertEqual(cli_option({'proxy': None}
, '--proxy', 'proxy'), [])
753 self
.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
755 def test_cli_valueless_option(self
):
756 self
.assertEqual(cli_valueless_option(
757 {'downloader': 'external'}
, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
758 self
.assertEqual(cli_valueless_option(
759 {'downloader': 'internal'}
, '--external-downloader', 'downloader', 'external'), [])
760 self
.assertEqual(cli_valueless_option(
761 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
762 self
.assertEqual(cli_valueless_option(
763 {'nocheckcertificate': False}
, '--no-check-certificate', 'nocheckcertificate'), [])
764 self
.assertEqual(cli_valueless_option(
765 {'checkcertificate': True}
, '--no-check-certificate', 'checkcertificate', False), [])
766 self
.assertEqual(cli_valueless_option(
767 {'checkcertificate': False}
, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
769 def test_cli_bool_option(self
):
772 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'),
773 ['--no-check-certificate', 'true'])
776 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate', separator
='='),
777 ['--no-check-certificate=true'])
780 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
781 ['--check-certificate', 'false'])
784 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
785 ['--check-certificate=false'])
788 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
789 ['--check-certificate', 'true'])
792 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
793 ['--check-certificate=true'])
796 if __name__
== '__main__':