]> Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py
Rapsys Git / youtubedl / blob
? search:


173c495146c4fca68301465300b54a29c0d5bfd8
[youtubedl] / test / test_utils.py
1 #!/usr/bin/env python
2 # coding: utf-8
3
4 from __future__ import unicode_literals
5
6 # Allow direct execution
7 import os
8 import sys
9 import unittest
10 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
11
12
13 # Various small unit tests
14 import io
15 import json
16 import xml.etree.ElementTree
17
18 from youtube_dl.utils import (
19 age_restricted,
20 args_to_str,
21 encode_base_n,
22 clean_html,
23 date_from_str,
24 DateRange,
25 detect_exe_version,
26 determine_ext,
27 dict_get,
28 encode_compat_str,
29 encodeFilename,
30 escape_rfc3986,
31 escape_url,
32 extract_attributes,
33 ExtractorError,
34 find_xpath_attr,
35 fix_xml_ampersands,
36 get_element_by_class,
37 get_element_by_attribute,
38 get_elements_by_class,
39 get_elements_by_attribute,
40 InAdvancePagedList,
41 intlist_to_bytes,
42 is_html,
43 js_to_json,
44 limit_length,
45 mimetype2ext,
46 month_by_name,
47 ohdave_rsa_encrypt,
48 OnDemandPagedList,
49 orderedSet,
50 parse_age_limit,
51 parse_duration,
52 parse_filesize,
53 parse_count,
54 parse_iso8601,
55 pkcs1pad,
56 read_batch_urls,
57 sanitize_filename,
58 sanitize_path,
59 prepend_extension,
60 replace_extension,
61 remove_start,
62 remove_end,
63 remove_quotes,
64 shell_quote,
65 smuggle_url,
66 str_to_int,
67 strip_jsonp,
68 timeconvert,
69 unescapeHTML,
70 unified_strdate,
71 unified_timestamp,
72 unsmuggle_url,
73 uppercase_escape,
74 lowercase_escape,
75 url_basename,
76 base_url,
77 urljoin,
78 urlencode_postdata,
79 urshift,
80 update_url_query,
81 version_tuple,
82 xpath_with_ns,
83 xpath_element,
84 xpath_text,
85 xpath_attr,
86 render_table,
87 match_str,
88 parse_dfxp_time_expr,
89 dfxp2srt,
90 cli_option,
91 cli_valueless_option,
92 cli_bool_option,
93 parse_codecs,
94 )
95 from youtube_dl.compat import (
96 compat_chr,
97 compat_etree_fromstring,
98 compat_urlparse,
99 compat_parse_qs,
100 )
101
102
103 class TestUtil(unittest.TestCase):
104 def test_timeconvert(self):
105 self.assertTrue(timeconvert('') is None)
106 self.assertTrue(timeconvert('bougrg') is None)
107
108 def test_sanitize_filename(self):
109 self.assertEqual(sanitize_filename('abc'), 'abc')
110 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
111
112 self.assertEqual(sanitize_filename('123'), '123')
113
114 self.assertEqual('abc_de', sanitize_filename('abc/de'))
115 self.assertFalse('/' in sanitize_filename('abc/de///'))
116
117 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
118 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
119 self.assertEqual('yes no', sanitize_filename('yes? no'))
120 self.assertEqual('this - that', sanitize_filename('this: that'))
121
122 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
123 aumlaut = 'ä'
124 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
125 tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
126 self.assertEqual(sanitize_filename(tests), tests)
127
128 self.assertEqual(
129 sanitize_filename('New World record at 0:12:34'),
130 'New World record at 0_12_34')
131
132 self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
133 self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
134 self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
135 self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
136
137 forbidden = '"\0\\/'
138 for fc in forbidden:
139 for fbc in forbidden:
140 self.assertTrue(fbc not in sanitize_filename(fc))
141
142 def test_sanitize_filename_restricted(self):
143 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
144 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
145
146 self.assertEqual(sanitize_filename('123', restricted=True), '123')
147
148 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
149 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
150
151 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
152 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
153 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
154 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
155
156 tests = 'aäb\u4e2d\u56fd\u7684c'
157 self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
158 self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
159
160 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
161 for fc in forbidden:
162 for fbc in forbidden:
163 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
164
165 # Handle a common case more neatly
166 self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
167 self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
168 # .. but make sure the file name is never empty
169 self.assertTrue(sanitize_filename('-', restricted=True) != '')
170 self.assertTrue(sanitize_filename(':', restricted=True) != '')
171
172 self.assertEqual(sanitize_filename(
173 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
174 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
175
176 def test_sanitize_ids(self):
177 self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
178 self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
179 self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
180
181 def test_sanitize_path(self):
182 if sys.platform != 'win32':
183 return
184
185 self.assertEqual(sanitize_path('abc'), 'abc')
186 self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
187 self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
188 self.assertEqual(sanitize_path('abc|def'), 'abc#def')
189 self.assertEqual(sanitize_path('<>:"|?*'), '#######')
190 self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
191 self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
192
193 self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
194 self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
195
196 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
197 self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
198 self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
199 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
200
201 self.assertEqual(
202 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
203 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
204
205 self.assertEqual(
206 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
207 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
208 self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
209 self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
210 self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
211
212 self.assertEqual(sanitize_path('../abc'), '..\\abc')
213 self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
214 self.assertEqual(sanitize_path('./abc'), 'abc')
215 self.assertEqual(sanitize_path('./../abc'), '..\\abc')
216
217 def test_prepend_extension(self):
218 self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
219 self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
220 self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
221 self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
222 self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
223 self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
224
225 def test_replace_extension(self):
226 self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
227 self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
228 self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
229 self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
230 self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
231 self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
232
233 def test_remove_start(self):
234 self.assertEqual(remove_start(None, 'A - '), None)
235 self.assertEqual(remove_start('A - B', 'A - '), 'B')
236 self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
237
238 def test_remove_end(self):
239 self.assertEqual(remove_end(None, ' - B'), None)
240 self.assertEqual(remove_end('A - B', ' - B'), 'A')
241 self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
242
243 def test_remove_quotes(self):
244 self.assertEqual(remove_quotes(None), None)
245 self.assertEqual(remove_quotes('"'), '"')
246 self.assertEqual(remove_quotes("'"), "'")
247 self.assertEqual(remove_quotes(';'), ';')
248 self.assertEqual(remove_quotes('";'), '";')
249 self.assertEqual(remove_quotes('""'), '')
250 self.assertEqual(remove_quotes('";"'), ';')
251
252 def test_ordered_set(self):
253 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
254 self.assertEqual(orderedSet([]), [])
255 self.assertEqual(orderedSet([1]), [1])
256 # keep the list ordered
257 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
258
259 def test_unescape_html(self):
260 self.assertEqual(unescapeHTML('%20;'), '%20;')
261 self.assertEqual(unescapeHTML('&#x2F;'), '/')
262 self.assertEqual(unescapeHTML('&#47;'), '/')
263 self.assertEqual(unescapeHTML('&eacute;'), 'é')
264 self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
265 # HTML5 entities
266 self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
267
268 def test_date_from_str(self):
269 self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
270 self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
271 self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
272 self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
273 self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
274
275 def test_daterange(self):
276 _20century = DateRange("19000101", "20000101")
277 self.assertFalse("17890714" in _20century)
278 _ac = DateRange("00010101")
279 self.assertTrue("19690721" in _ac)
280 _firstmilenium = DateRange(end="10000101")
281 self.assertTrue("07110427" in _firstmilenium)
282
283 def test_unified_dates(self):
284 self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
285 self.assertEqual(unified_strdate('8/7/2009'), '20090708')
286 self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
287 self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
288 self.assertEqual(unified_strdate('1968 12 10'), '19681210')
289 self.assertEqual(unified_strdate('1968-12-10'), '19681210')
290 self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
291 self.assertEqual(
292 unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
293 '20141126')
294 self.assertEqual(
295 unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
296 '20150202')
297 self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
298 self.assertEqual(unified_strdate('25-09-2014'), '20140925')
299 self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
300 self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
301 self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
302 self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
303 self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
304 self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
305
306 def test_unified_timestamps(self):
307 self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
308 self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
309 self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
310 self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
311 self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
312 self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
313 self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
314 self.assertEqual(
315 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
316 1417001400)
317 self.assertEqual(
318 unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
319 1422902860)
320 self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
321 self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
322 self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
323 self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
324 self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
325 self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
326
327 def test_determine_ext(self):
328 self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
329 self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
330 self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
331 self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
332 self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
333
334 def test_find_xpath_attr(self):
335 testxml = '''<root>
336 <node/>
337 <node x="a"/>
338 <node x="a" y="c" />
339 <node x="b" y="d" />
340 <node x="" />
341 </root>'''
342 doc = compat_etree_fromstring(testxml)
343
344 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
345 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
346 self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
347 self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
348 self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
349 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
350 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
351 self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
352 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
353 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
354 self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
355
356 def test_xpath_with_ns(self):
357 testxml = '''<root xmlns:media="http://example.com/">
358 <media:song>
359 <media:author>The Author</media:author>
360 <url>http://server.com/download.mp3</url>
361 </media:song>
362 </root>'''
363 doc = compat_etree_fromstring(testxml)
364 find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
365 self.assertTrue(find('media:song') is not None)
366 self.assertEqual(find('media:song/media:author').text, 'The Author')
367 self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
368
369 def test_xpath_element(self):
370 doc = xml.etree.ElementTree.Element('root')
371 div = xml.etree.ElementTree.SubElement(doc, 'div')
372 p = xml.etree.ElementTree.SubElement(div, 'p')
373 p.text = 'Foo'
374 self.assertEqual(xpath_element(doc, 'div/p'), p)
375 self.assertEqual(xpath_element(doc, ['div/p']), p)
376 self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
377 self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
378 self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
379 self.assertTrue(xpath_element(doc, 'div/bar') is None)
380 self.assertTrue(xpath_element(doc, ['div/bar']) is None)
381 self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
382 self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
383 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
384 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
385
386 def test_xpath_text(self):
387 testxml = '''<root>
388 <div>
389 <p>Foo</p>
390 </div>
391 </root>'''
392 doc = compat_etree_fromstring(testxml)
393 self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
394 self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
395 self.assertTrue(xpath_text(doc, 'div/bar') is None)
396 self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
397
398 def test_xpath_attr(self):
399 testxml = '''<root>
400 <div>
401 <p x="a">Foo</p>
402 </div>
403 </root>'''
404 doc = compat_etree_fromstring(testxml)
405 self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
406 self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
407 self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
408 self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
409 self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
410 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
411 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
412
413 def test_smuggle_url(self):
414 data = {"ö": "ö", "abc": [3]}
415 url = 'https://foo.bar/baz?x=y#a'
416 smug_url = smuggle_url(url, data)
417 unsmug_url, unsmug_data = unsmuggle_url(smug_url)
418 self.assertEqual(url, unsmug_url)
419 self.assertEqual(data, unsmug_data)
420
421 res_url, res_data = unsmuggle_url(url)
422 self.assertEqual(res_url, url)
423 self.assertEqual(res_data, None)
424
425 smug_url = smuggle_url(url, {'a': 'b'})
426 smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
427 res_url, res_data = unsmuggle_url(smug_smug_url)
428 self.assertEqual(res_url, url)
429 self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
430
431 def test_shell_quote(self):
432 args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
433 self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
434
435 def test_str_to_int(self):
436 self.assertEqual(str_to_int('123,456'), 123456)
437 self.assertEqual(str_to_int('123.456'), 123456)
438
439 def test_url_basename(self):
440 self.assertEqual(url_basename('http://foo.de/'), '')
441 self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
442 self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
443 self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
444 self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
445 self.assertEqual(
446 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
447 'trailer.mp4')
448
449 def test_base_url(self):
450 self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
451 self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
452 self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
453 self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
454 self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
455
456 def test_urljoin(self):
457 self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
458 self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
459 self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
460 self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
461 self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
462 self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
463 self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
464 self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
465 self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
466 self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
467 self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
468 self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
469 self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
470 self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
471 self.assertEqual(urljoin('http://foo.de/', None), None)
472 self.assertEqual(urljoin('http://foo.de/', ''), None)
473 self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
474 self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
475
476 def test_parse_age_limit(self):
477 self.assertEqual(parse_age_limit(None), None)
478 self.assertEqual(parse_age_limit(False), None)
479 self.assertEqual(parse_age_limit('invalid'), None)
480 self.assertEqual(parse_age_limit(0), 0)
481 self.assertEqual(parse_age_limit(18), 18)
482 self.assertEqual(parse_age_limit(21), 21)
483 self.assertEqual(parse_age_limit(22), None)
484 self.assertEqual(parse_age_limit('18'), 18)
485 self.assertEqual(parse_age_limit('18+'), 18)
486 self.assertEqual(parse_age_limit('PG-13'), 13)
487 self.assertEqual(parse_age_limit('TV-14'), 14)
488 self.assertEqual(parse_age_limit('TV-MA'), 17)
489
490 def test_parse_duration(self):
491 self.assertEqual(parse_duration(None), None)
492 self.assertEqual(parse_duration(False), None)
493 self.assertEqual(parse_duration('invalid'), None)
494 self.assertEqual(parse_duration('1'), 1)
495 self.assertEqual(parse_duration('1337:12'), 80232)
496 self.assertEqual(parse_duration('9:12:43'), 33163)
497 self.assertEqual(parse_duration('12:00'), 720)
498 self.assertEqual(parse_duration('00:01:01'), 61)
499 self.assertEqual(parse_duration('x:y'), None)
500 self.assertEqual(parse_duration('3h11m53s'), 11513)
501 self.assertEqual(parse_duration('3h 11m 53s'), 11513)
502 self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
503 self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
504 self.assertEqual(parse_duration('62m45s'), 3765)
505 self.assertEqual(parse_duration('6m59s'), 419)
506 self.assertEqual(parse_duration('49s'), 49)
507 self.assertEqual(parse_duration('0h0m0s'), 0)
508 self.assertEqual(parse_duration('0m0s'), 0)
509 self.assertEqual(parse_duration('0s'), 0)
510 self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
511 self.assertEqual(parse_duration('T30M38S'), 1838)
512 self.assertEqual(parse_duration('5 s'), 5)
513 self.assertEqual(parse_duration('3 min'), 180)
514 self.assertEqual(parse_duration('2.5 hours'), 9000)
515 self.assertEqual(parse_duration('02:03:04'), 7384)
516 self.assertEqual(parse_duration('01:02:03:04'), 93784)
517 self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
518 self.assertEqual(parse_duration('87 Min.'), 5220)
519 self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
520 self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
521
522 def test_fix_xml_ampersands(self):
523 self.assertEqual(
524 fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
525 self.assertEqual(
526 fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
527 '"&amp;x=y&amp;wrong;&amp;z=a')
528 self.assertEqual(
529 fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
530 '&amp;&apos;&gt;&lt;&quot;')
531 self.assertEqual(
532 fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
533 self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
534
535 def test_paged_list(self):
536 def testPL(size, pagesize, sliceargs, expected):
537 def get_page(pagenum):
538 firstid = pagenum * pagesize
539 upto = min(size, pagenum * pagesize + pagesize)
540 for i in range(firstid, upto):
541 yield i
542
543 pl = OnDemandPagedList(get_page, pagesize)
544 got = pl.getslice(*sliceargs)
545 self.assertEqual(got, expected)
546
547 iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
548 got = iapl.getslice(*sliceargs)
549 self.assertEqual(got, expected)
550
551 testPL(5, 2, (), [0, 1, 2, 3, 4])
552 testPL(5, 2, (1,), [1, 2, 3, 4])
553 testPL(5, 2, (2,), [2, 3, 4])
554 testPL(5, 2, (4,), [4])
555 testPL(5, 2, (0, 3), [0, 1, 2])
556 testPL(5, 2, (1, 4), [1, 2, 3])
557 testPL(5, 2, (2, 99), [2, 3, 4])
558 testPL(5, 2, (20, 99), [])
559
560 def test_read_batch_urls(self):
561 f = io.StringIO('''\xef\xbb\xbf foo
562 bar\r
563 baz
564 # More after this line\r
565 ; or after this
566 bam''')
567 self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
568
569 def test_urlencode_postdata(self):
570 data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
571 self.assertTrue(isinstance(data, bytes))
572
573 def test_update_url_query(self):
574 def query_dict(url):
575 return compat_parse_qs(compat_urlparse.urlparse(url).query)
576 self.assertEqual(query_dict(update_url_query(
577 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
578 query_dict('http://example.com/path?quality=HD&format=mp4'))
579 self.assertEqual(query_dict(update_url_query(
580 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
581 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
582 self.assertEqual(query_dict(update_url_query(
583 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
584 query_dict('http://example.com/path?fields=id,formats,subtitles'))
585 self.assertEqual(query_dict(update_url_query(
586 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
587 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
588 self.assertEqual(query_dict(update_url_query(
589 'http://example.com/path?manifest=f4m', {'manifest': []})),
590 query_dict('http://example.com/path'))
591 self.assertEqual(query_dict(update_url_query(
592 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
593 query_dict('http://example.com/path?system=LINUX'))
594 self.assertEqual(query_dict(update_url_query(
595 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
596 query_dict('http://example.com/path?fields=id,formats,subtitles'))
597 self.assertEqual(query_dict(update_url_query(
598 'http://example.com/path', {'width': 1080, 'height': 720})),
599 query_dict('http://example.com/path?width=1080&height=720'))
600 self.assertEqual(query_dict(update_url_query(
601 'http://example.com/path', {'bitrate': 5020.43})),
602 query_dict('http://example.com/path?bitrate=5020.43'))
603 self.assertEqual(query_dict(update_url_query(
604 'http://example.com/path', {'test': '第二行тест'})),
605 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
606
607 def test_dict_get(self):
608 FALSE_VALUES = {
609 'none': None,
610 'false': False,
611 'zero': 0,
612 'empty_string': '',
613 'empty_list': [],
614 }
615 d = FALSE_VALUES.copy()
616 d['a'] = 42
617 self.assertEqual(dict_get(d, 'a'), 42)
618 self.assertEqual(dict_get(d, 'b'), None)
619 self.assertEqual(dict_get(d, 'b', 42), 42)
620 self.assertEqual(dict_get(d, ('a', )), 42)
621 self.assertEqual(dict_get(d, ('b', 'a', )), 42)
622 self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
623 self.assertEqual(dict_get(d, ('b', 'c', )), None)
624 self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
625 for key, false_value in FALSE_VALUES.items():
626 self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
627 self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
628
629 def test_encode_compat_str(self):
630 self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
631 self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
632
633 def test_parse_iso8601(self):
634 self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
635 self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
636 self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
637 self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
638 self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
639 self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
640
641 def test_strip_jsonp(self):
642 stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
643 d = json.loads(stripped)
644 self.assertEqual(d, [{"id": "532cb", "x": 3}])
645
646 stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
647 d = json.loads(stripped)
648 self.assertEqual(d, {'STATUS': 'OK'})
649
650 stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
651 d = json.loads(stripped)
652 self.assertEqual(d, {'status': 'success'})
653
654 def test_uppercase_escape(self):
655 self.assertEqual(uppercase_escape('aä'), 'aä')
656 self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
657
658 def test_lowercase_escape(self):
659 self.assertEqual(lowercase_escape('aä'), 'aä')
660 self.assertEqual(lowercase_escape('\\u0026'), '&')
661
662 def test_limit_length(self):
663 self.assertEqual(limit_length(None, 12), None)
664 self.assertEqual(limit_length('foo', 12), 'foo')
665 self.assertTrue(
666 limit_length('foo bar baz asd', 12).startswith('foo bar'))
667 self.assertTrue('...' in limit_length('foo bar baz asd', 12))
668
669 def test_mimetype2ext(self):
670 self.assertEqual(mimetype2ext(None), None)
671 self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
672 self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
673 self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
674 self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
675 self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
676
677 def test_month_by_name(self):
678 self.assertEqual(month_by_name(None), None)
679 self.assertEqual(month_by_name('December', 'en'), 12)
680 self.assertEqual(month_by_name('décembre', 'fr'), 12)
681 self.assertEqual(month_by_name('December'), 12)
682 self.assertEqual(month_by_name('décembre'), None)
683 self.assertEqual(month_by_name('Unknown', 'unknown'), None)
684
685 def test_parse_codecs(self):
686 self.assertEqual(parse_codecs(''), {})
687 self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
688 'vcodec': 'avc1.77.30',
689 'acodec': 'mp4a.40.2',
690 })
691 self.assertEqual(parse_codecs('mp4a.40.2'), {
692 'vcodec': 'none',
693 'acodec': 'mp4a.40.2',
694 })
695 self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
696 'vcodec': 'avc1.42001e',
697 'acodec': 'mp4a.40.5',
698 })
699 self.assertEqual(parse_codecs('avc3.640028'), {
700 'vcodec': 'avc3.640028',
701 'acodec': 'none',
702 })
703 self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
704 'vcodec': 'h264',
705 'acodec': 'aac',
706 })
707
708 def test_escape_rfc3986(self):
709 reserved = "!*'();:@&=+$,/?#[]"
710 unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
711 self.assertEqual(escape_rfc3986(reserved), reserved)
712 self.assertEqual(escape_rfc3986(unreserved), unreserved)
713 self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
714 self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
715 self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
716 self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
717
718 def test_escape_url(self):
719 self.assertEqual(
720 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
721 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
722 )
723 self.assertEqual(
724 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
725 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
726 )
727 self.assertEqual(
728 escape_url('http://тест.рф/фрагмент'),
729 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
730 )
731 self.assertEqual(
732 escape_url('http://тест.рф/абв?абв=абв#абв'),
733 'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
734 )
735 self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
736
737 def test_js_to_json_realworld(self):
738 inp = '''{
739 'clip':{'provider':'pseudo'}
740 }'''
741 self.assertEqual(js_to_json(inp), '''{
742 "clip":{"provider":"pseudo"}
743 }''')
744 json.loads(js_to_json(inp))
745
746 inp = '''{
747 'playlist':[{'controls':{'all':null}}]
748 }'''
749 self.assertEqual(js_to_json(inp), '''{
750 "playlist":[{"controls":{"all":null}}]
751 }''')
752
753 inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
754 self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
755
756 inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
757 json_code = js_to_json(inp)
758 self.assertEqual(json.loads(json_code), json.loads(inp))
759
760 inp = '''{
761 0:{src:'skipped', type: 'application/dash+xml'},
762 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
763 }'''
764 self.assertEqual(js_to_json(inp), '''{
765 "0":{"src":"skipped", "type": "application/dash+xml"},
766 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
767 }''')
768
769 inp = '''{"foo":101}'''
770 self.assertEqual(js_to_json(inp), '''{"foo":101}''')
771
772 inp = '''{"duration": "00:01:07"}'''
773 self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
774
775 def test_js_to_json_edgecases(self):
776 on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
777 self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
778
779 on = js_to_json('{"abc": true}')
780 self.assertEqual(json.loads(on), {'abc': True})
781
782 # Ignore JavaScript code as well
783 on = js_to_json('''{
784 "x": 1,
785 y: "a",
786 z: some.code
787 }''')
788 d = json.loads(on)
789 self.assertEqual(d['x'], 1)
790 self.assertEqual(d['y'], 'a')
791
792 on = js_to_json('["abc", "def",]')
793 self.assertEqual(json.loads(on), ['abc', 'def'])
794
795 on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
796 self.assertEqual(json.loads(on), ['abc', 'def'])
797
798 on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
799 self.assertEqual(json.loads(on), ['abc', 'def'])
800
801 on = js_to_json('{"abc": "def",}')
802 self.assertEqual(json.loads(on), {'abc': 'def'})
803
804 on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
805 self.assertEqual(json.loads(on), {'abc': 'def'})
806
807 on = js_to_json('{ 0: /* " \n */ ",]" , }')
808 self.assertEqual(json.loads(on), {'0': ',]'})
809
810 on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
811 self.assertEqual(json.loads(on), {'0': ',]'})
812
813 on = js_to_json('{ 0: // comment\n1 }')
814 self.assertEqual(json.loads(on), {'0': 1})
815
816 on = js_to_json(r'["<p>x<\/p>"]')
817 self.assertEqual(json.loads(on), ['<p>x</p>'])
818
819 on = js_to_json(r'["\xaa"]')
820 self.assertEqual(json.loads(on), ['\u00aa'])
821
822 on = js_to_json("['a\\\nb']")
823 self.assertEqual(json.loads(on), ['ab'])
824
825 on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
826 self.assertEqual(json.loads(on), ['ab'])
827
828 on = js_to_json('{0xff:0xff}')
829 self.assertEqual(json.loads(on), {'255': 255})
830
831 on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
832 self.assertEqual(json.loads(on), {'255': 255})
833
834 on = js_to_json('{077:077}')
835 self.assertEqual(json.loads(on), {'63': 63})
836
837 on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
838 self.assertEqual(json.loads(on), {'63': 63})
839
840 on = js_to_json('{42:42}')
841 self.assertEqual(json.loads(on), {'42': 42})
842
843 on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
844 self.assertEqual(json.loads(on), {'42': 42})
845
846 def test_extract_attributes(self):
847 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
848 self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
849 self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
850 self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
851 self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
852 self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
853 self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
854 self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'}) # XML
855 self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
856 self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'}) # HTML 3.2
857 self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'}) # HTML 4.0
858 self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
859 self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
860 self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
861 self.assertEqual(extract_attributes('<e x >'), {'x': None})
862 self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
863 self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
864 self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
865 self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
866 self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
867 self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
868 self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
869 self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
870 self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
871 self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
872 self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
873 self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
874 self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
875 # "Narrow" Python builds don't support unicode code points outside BMP.
876 try:
877 compat_chr(0x10000)
878 supports_outside_bmp = True
879 except ValueError:
880 supports_outside_bmp = False
881 if supports_outside_bmp:
882 self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
883
884 def test_clean_html(self):
885 self.assertEqual(clean_html('a:\nb'), 'a: b')
886 self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
887
888 def test_intlist_to_bytes(self):
889 self.assertEqual(
890 intlist_to_bytes([0, 1, 127, 128, 255]),
891 b'\x00\x01\x7f\x80\xff')
892
893 def test_args_to_str(self):
894 self.assertEqual(
895 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
896 'foo ba/r -baz \'2 be\' \'\''
897 )
898
899 def test_parse_filesize(self):
900 self.assertEqual(parse_filesize(None), None)
901 self.assertEqual(parse_filesize(''), None)
902 self.assertEqual(parse_filesize('91 B'), 91)
903 self.assertEqual(parse_filesize('foobar'), None)
904 self.assertEqual(parse_filesize('2 MiB'), 2097152)
905 self.assertEqual(parse_filesize('5 GB'), 5000000000)
906 self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
907 self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
908 self.assertEqual(parse_filesize('1,24 KB'), 1240)
909 self.assertEqual(parse_filesize('1,24 kb'), 1240)
910 self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
911
912 def test_parse_count(self):
913 self.assertEqual(parse_count(None), None)
914 self.assertEqual(parse_count(''), None)
915 self.assertEqual(parse_count('0'), 0)
916 self.assertEqual(parse_count('1000'), 1000)
917 self.assertEqual(parse_count('1.000'), 1000)
918 self.assertEqual(parse_count('1.1k'), 1100)
919 self.assertEqual(parse_count('1.1kk'), 1100000)
920 self.assertEqual(parse_count('1.1kk '), 1100000)
921 self.assertEqual(parse_count('1.1kk views'), 1100000)
922
923 def test_version_tuple(self):
924 self.assertEqual(version_tuple('1'), (1,))
925 self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
926 self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
927
928 def test_detect_exe_version(self):
929 self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
930 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
931 configuration: --prefix=/usr --extra-'''), '1.2.1')
932 self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
933 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
934 self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
935 Trying to open render node...
936 Success at /dev/dri/renderD128.
937 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
938
939 def test_age_restricted(self):
940 self.assertFalse(age_restricted(None, 10)) # unrestricted content
941 self.assertFalse(age_restricted(1, None)) # unrestricted policy
942 self.assertFalse(age_restricted(8, 10))
943 self.assertTrue(age_restricted(18, 14))
944 self.assertFalse(age_restricted(18, 18))
945
946 def test_is_html(self):
947 self.assertFalse(is_html(b'\x49\x44\x43<html'))
948 self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
949 self.assertTrue(is_html( # UTF-8 with BOM
950 b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
951 self.assertTrue(is_html( # UTF-16-LE
952 b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
953 ))
954 self.assertTrue(is_html( # UTF-16-BE
955 b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
956 ))
957 self.assertTrue(is_html( # UTF-32-BE
958 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'))
959 self.assertTrue(is_html( # UTF-32-LE
960 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'))
961
962 def test_render_table(self):
963 self.assertEqual(
964 render_table(
965 ['a', 'bcd'],
966 [[123, 4], [9999, 51]]),
967 'a bcd\n'
968 '123 4\n'
969 '9999 51')
970
971 def test_match_str(self):
972 self.assertRaises(ValueError, match_str, 'xy>foobar', {})
973 self.assertFalse(match_str('xy', {'x': 1200}))
974 self.assertTrue(match_str('!xy', {'x': 1200}))
975 self.assertTrue(match_str('x', {'x': 1200}))
976 self.assertFalse(match_str('!x', {'x': 1200}))
977 self.assertTrue(match_str('x', {'x': 0}))
978 self.assertFalse(match_str('x>0', {'x': 0}))
979 self.assertFalse(match_str('x>0', {}))
980 self.assertTrue(match_str('x>?0', {}))
981 self.assertTrue(match_str('x>1K', {'x': 1200}))
982 self.assertFalse(match_str('x>2K', {'x': 1200}))
983 self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
984 self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
985 self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
986 self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
987 self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
988 self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
989 self.assertFalse(match_str(
990 'like_count > 100 & dislike_count <? 50 & description',
991 {'like_count': 90, 'description': 'foo'}))
992 self.assertTrue(match_str(
993 'like_count > 100 & dislike_count <? 50 & description',
994 {'like_count': 190, 'description': 'foo'}))
995 self.assertFalse(match_str(
996 'like_count > 100 & dislike_count <? 50 & description',
997 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
998 self.assertFalse(match_str(
999 'like_count > 100 & dislike_count <? 50 & description',
1000 {'like_count': 190, 'dislike_count': 10}))
1001
1002 def test_parse_dfxp_time_expr(self):
1003 self.assertEqual(parse_dfxp_time_expr(None), None)
1004 self.assertEqual(parse_dfxp_time_expr(''), None)
1005 self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
1006 self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1007 self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1008 self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1009 self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1010
1011 def test_dfxp2srt(self):
1012 dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
1013 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1014 <body>
1015 <div xml:lang="en">
1016 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1017 <p begin="1" end="2">第二行<br/>♪♪</p>
1018 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1019 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1020 <p begin="-1" end="-1">Ignore, two</p>
1021 <p begin="3" dur="-1">Ignored, three</p>
1022 </div>
1023 </body>
1024 </tt>'''
1025 srt_data = '''1
1026 00:00:00,000 --> 00:00:01,000
1027 The following line contains Chinese characters and special symbols
1028
1029 2
1030 00:00:01,000 --> 00:00:02,000
1031 第二行
1032 ♪♪
1033
1034 3
1035 00:00:02,000 --> 00:00:03,000
1036 Third
1037 Line
1038
1039 '''
1040 self.assertEqual(dfxp2srt(dfxp_data), srt_data)
1041
1042 dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
1043 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1044 <body>
1045 <div xml:lang="en">
1046 <p begin="0" end="1">The first line</p>
1047 </div>
1048 </body>
1049 </tt>'''
1050 srt_data = '''1
1051 00:00:00,000 --> 00:00:01,000
1052 The first line
1053
1054 '''
1055 self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
1056
1057 def test_cli_option(self):
1058 self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1059 self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
1060 self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1061 self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
1062
1063 def test_cli_valueless_option(self):
1064 self.assertEqual(cli_valueless_option(
1065 {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1066 self.assertEqual(cli_valueless_option(
1067 {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
1068 self.assertEqual(cli_valueless_option(
1069 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1070 self.assertEqual(cli_valueless_option(
1071 {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
1072 self.assertEqual(cli_valueless_option(
1073 {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
1074 self.assertEqual(cli_valueless_option(
1075 {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1076
1077 def test_cli_bool_option(self):
1078 self.assertEqual(
1079 cli_bool_option(
1080 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
1081 ['--no-check-certificate', 'true'])
1082 self.assertEqual(
1083 cli_bool_option(
1084 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
1085 ['--no-check-certificate=true'])
1086 self.assertEqual(
1087 cli_bool_option(
1088 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1089 ['--check-certificate', 'false'])
1090 self.assertEqual(
1091 cli_bool_option(
1092 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1093 ['--check-certificate=false'])
1094 self.assertEqual(
1095 cli_bool_option(
1096 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1097 ['--check-certificate', 'true'])
1098 self.assertEqual(
1099 cli_bool_option(
1100 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1101 ['--check-certificate=true'])
1102
1103 def test_ohdave_rsa_encrypt(self):
1104 N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1105 e = 65537
1106
1107 self.assertEqual(
1108 ohdave_rsa_encrypt(b'aa111222', e, N),
1109 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1110
1111 def test_pkcs1pad(self):
1112 data = [1, 2, 3]
1113 padded_data = pkcs1pad(data, 32)
1114 self.assertEqual(padded_data[:2], [0, 2])
1115 self.assertEqual(padded_data[28:], [0, 1, 2, 3])
1116
1117 self.assertRaises(ValueError, pkcs1pad, data, 8)
1118
1119 def test_encode_base_n(self):
1120 self.assertEqual(encode_base_n(0, 30), '0')
1121 self.assertEqual(encode_base_n(80, 30), '2k')
1122
1123 custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1124 self.assertEqual(encode_base_n(0, 30, custom_table), '9')
1125 self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
1126
1127 self.assertRaises(ValueError, encode_base_n, 0, 70)
1128 self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
1129
1130 def test_urshift(self):
1131 self.assertEqual(urshift(3, 1), 1)
1132 self.assertEqual(urshift(-3, 1), 2147483646)
1133
1134 def test_get_element_by_class(self):
1135 html = '''
1136 <span class="foo bar">nice</span>
1137 '''
1138
1139 self.assertEqual(get_element_by_class('foo', html), 'nice')
1140 self.assertEqual(get_element_by_class('no-such-class', html), None)
1141
1142 def test_get_element_by_attribute(self):
1143 html = '''
1144 <span class="foo bar">nice</span>
1145 '''
1146
1147 self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
1148 self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
1149 self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
1150
1151 def test_get_elements_by_class(self):
1152 html = '''
1153 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1154 '''
1155
1156 self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
1157 self.assertEqual(get_elements_by_class('no-such-class', html), [])
1158
1159 def test_get_elements_by_attribute(self):
1160 html = '''
1161 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1162 '''
1163
1164 self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
1165 self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
1166 self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
1167
1168
1169 if __name__ == '__main__':
1170 unittest.main()
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...