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