]>
Commit | Line | Data |
---|---|---|
1 | #!/usr/bin/env python3 | |
2 | ||
3 | # Allow direct execution | |
4 | import os | |
5 | import sys | |
6 | import unittest | |
7 | ||
8 | sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) | |
9 | ||
10 | ||
11 | import contextlib | |
12 | import io | |
13 | import itertools | |
14 | import json | |
15 | import xml.etree.ElementTree | |
16 | ||
17 | from yt_dlp.compat import ( | |
18 | compat_etree_fromstring, | |
19 | compat_HTMLParseError, | |
20 | compat_os_name, | |
21 | ) | |
22 | from yt_dlp.utils import ( | |
23 | Config, | |
24 | DateRange, | |
25 | ExtractorError, | |
26 | InAdvancePagedList, | |
27 | LazyList, | |
28 | OnDemandPagedList, | |
29 | age_restricted, | |
30 | args_to_str, | |
31 | base_url, | |
32 | caesar, | |
33 | clean_html, | |
34 | clean_podcast_url, | |
35 | cli_bool_option, | |
36 | cli_option, | |
37 | cli_valueless_option, | |
38 | date_from_str, | |
39 | datetime_from_str, | |
40 | detect_exe_version, | |
41 | determine_ext, | |
42 | determine_file_encoding, | |
43 | dfxp2srt, | |
44 | dict_get, | |
45 | encode_base_n, | |
46 | encode_compat_str, | |
47 | encodeFilename, | |
48 | escape_rfc3986, | |
49 | escape_url, | |
50 | expand_path, | |
51 | extract_attributes, | |
52 | find_xpath_attr, | |
53 | fix_xml_ampersands, | |
54 | float_or_none, | |
55 | format_bytes, | |
56 | get_element_by_attribute, | |
57 | get_element_by_class, | |
58 | get_element_html_by_attribute, | |
59 | get_element_html_by_class, | |
60 | get_element_text_and_html_by_tag, | |
61 | get_elements_by_attribute, | |
62 | get_elements_by_class, | |
63 | get_elements_html_by_attribute, | |
64 | get_elements_html_by_class, | |
65 | get_elements_text_and_html_by_attribute, | |
66 | int_or_none, | |
67 | intlist_to_bytes, | |
68 | iri_to_uri, | |
69 | is_html, | |
70 | js_to_json, | |
71 | limit_length, | |
72 | locked_file, | |
73 | lowercase_escape, | |
74 | match_str, | |
75 | merge_dicts, | |
76 | mimetype2ext, | |
77 | month_by_name, | |
78 | multipart_encode, | |
79 | ohdave_rsa_encrypt, | |
80 | orderedSet, | |
81 | parse_age_limit, | |
82 | parse_bitrate, | |
83 | parse_codecs, | |
84 | parse_count, | |
85 | parse_dfxp_time_expr, | |
86 | parse_duration, | |
87 | parse_filesize, | |
88 | parse_iso8601, | |
89 | parse_qs, | |
90 | parse_resolution, | |
91 | pkcs1pad, | |
92 | prepend_extension, | |
93 | read_batch_urls, | |
94 | remove_end, | |
95 | remove_quotes, | |
96 | remove_start, | |
97 | render_table, | |
98 | replace_extension, | |
99 | rot47, | |
100 | sanitize_filename, | |
101 | sanitize_path, | |
102 | sanitize_url, | |
103 | sanitized_Request, | |
104 | shell_quote, | |
105 | smuggle_url, | |
106 | str_to_int, | |
107 | strip_jsonp, | |
108 | strip_or_none, | |
109 | subtitles_filename, | |
110 | timeconvert, | |
111 | unescapeHTML, | |
112 | unified_strdate, | |
113 | unified_timestamp, | |
114 | unsmuggle_url, | |
115 | update_url_query, | |
116 | uppercase_escape, | |
117 | url_basename, | |
118 | url_or_none, | |
119 | urlencode_postdata, | |
120 | urljoin, | |
121 | urshift, | |
122 | version_tuple, | |
123 | xpath_attr, | |
124 | xpath_element, | |
125 | xpath_text, | |
126 | xpath_with_ns, | |
127 | ) | |
128 | ||
129 | ||
130 | class TestUtil(unittest.TestCase): | |
131 | def test_timeconvert(self): | |
132 | self.assertTrue(timeconvert('') is None) | |
133 | self.assertTrue(timeconvert('bougrg') is None) | |
134 | ||
135 | def test_sanitize_filename(self): | |
136 | self.assertEqual(sanitize_filename(''), '') | |
137 | self.assertEqual(sanitize_filename('abc'), 'abc') | |
138 | self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') | |
139 | ||
140 | self.assertEqual(sanitize_filename('123'), '123') | |
141 | ||
142 | self.assertEqual('abc_de', sanitize_filename('abc/de')) | |
143 | self.assertFalse('/' in sanitize_filename('abc/de///')) | |
144 | ||
145 | self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) | |
146 | self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) | |
147 | self.assertEqual('yes no', sanitize_filename('yes? no')) | |
148 | self.assertEqual('this - that', sanitize_filename('this: that')) | |
149 | ||
150 | self.assertEqual(sanitize_filename('AT&T'), 'AT&T') | |
151 | aumlaut = 'ä' | |
152 | self.assertEqual(sanitize_filename(aumlaut), aumlaut) | |
153 | tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430' | |
154 | self.assertEqual(sanitize_filename(tests), tests) | |
155 | ||
156 | self.assertEqual( | |
157 | sanitize_filename('New World record at 0:12:34'), | |
158 | 'New World record at 0_12_34') | |
159 | ||
160 | self.assertEqual(sanitize_filename('--gasdgf'), '--gasdgf') | |
161 | self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf') | |
162 | self.assertEqual(sanitize_filename('--gasdgf', is_id=False), '_-gasdgf') | |
163 | self.assertEqual(sanitize_filename('.gasdgf'), '.gasdgf') | |
164 | self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf') | |
165 | self.assertEqual(sanitize_filename('.gasdgf', is_id=False), 'gasdgf') | |
166 | ||
167 | forbidden = '"\0\\/' | |
168 | for fc in forbidden: | |
169 | for fbc in forbidden: | |
170 | self.assertTrue(fbc not in sanitize_filename(fc)) | |
171 | ||
172 | def test_sanitize_filename_restricted(self): | |
173 | self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') | |
174 | self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') | |
175 | ||
176 | self.assertEqual(sanitize_filename('123', restricted=True), '123') | |
177 | ||
178 | self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) | |
179 | self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) | |
180 | ||
181 | self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) | |
182 | self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) | |
183 | self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) | |
184 | self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) | |
185 | ||
186 | tests = 'aäb\u4e2d\u56fd\u7684c' | |
187 | self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c') | |
188 | self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename | |
189 | ||
190 | forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#' | |
191 | for fc in forbidden: | |
192 | for fbc in forbidden: | |
193 | self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) | |
194 | ||
195 | # Handle a common case more neatly | |
196 | self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song') | |
197 | self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech') | |
198 | # .. but make sure the file name is never empty | |
199 | self.assertTrue(sanitize_filename('-', restricted=True) != '') | |
200 | self.assertTrue(sanitize_filename(':', restricted=True) != '') | |
201 | ||
202 | self.assertEqual(sanitize_filename( | |
203 | 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True), | |
204 | 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy') | |
205 | ||
206 | def test_sanitize_ids(self): | |
207 | self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') | |
208 | self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw') | |
209 | self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI') | |
210 | ||
211 | def test_sanitize_path(self): | |
212 | if sys.platform != 'win32': | |
213 | return | |
214 | ||
215 | self.assertEqual(sanitize_path('abc'), 'abc') | |
216 | self.assertEqual(sanitize_path('abc/def'), 'abc\\def') | |
217 | self.assertEqual(sanitize_path('abc\\def'), 'abc\\def') | |
218 | self.assertEqual(sanitize_path('abc|def'), 'abc#def') | |
219 | self.assertEqual(sanitize_path('<>:"|?*'), '#######') | |
220 | self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def') | |
221 | self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def') | |
222 | ||
223 | self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc') | |
224 | self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc') | |
225 | ||
226 | self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc') | |
227 | self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc') | |
228 | self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f') | |
229 | self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc') | |
230 | ||
231 | self.assertEqual( | |
232 | sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'), | |
233 | 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s') | |
234 | ||
235 | self.assertEqual( | |
236 | sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'), | |
237 | 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part') | |
238 | self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#') | |
239 | self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def') | |
240 | self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#') | |
241 | ||
242 | self.assertEqual(sanitize_path('../abc'), '..\\abc') | |
243 | self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc') | |
244 | self.assertEqual(sanitize_path('./abc'), 'abc') | |
245 | self.assertEqual(sanitize_path('./../abc'), '..\\abc') | |
246 | ||
247 | def test_sanitize_url(self): | |
248 | self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar') | |
249 | self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar') | |
250 | self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar') | |
251 | self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar') | |
252 | self.assertEqual(sanitize_url('foo bar'), 'foo bar') | |
253 | ||
254 | def test_extract_basic_auth(self): | |
255 | auth_header = lambda url: sanitized_Request(url).get_header('Authorization') | |
256 | self.assertFalse(auth_header('http://foo.bar')) | |
257 | self.assertFalse(auth_header('http://:foo.bar')) | |
258 | self.assertEqual(auth_header('http://@foo.bar'), 'Basic Og==') | |
259 | self.assertEqual(auth_header('http://:pass@foo.bar'), 'Basic OnBhc3M=') | |
260 | self.assertEqual(auth_header('http://user:@foo.bar'), 'Basic dXNlcjo=') | |
261 | self.assertEqual(auth_header('http://user:pass@foo.bar'), 'Basic dXNlcjpwYXNz') | |
262 | ||
263 | def test_expand_path(self): | |
264 | def env(var): | |
265 | return f'%{var}%' if sys.platform == 'win32' else f'${var}' | |
266 | ||
267 | os.environ['yt_dlp_EXPATH_PATH'] = 'expanded' | |
268 | self.assertEqual(expand_path(env('yt_dlp_EXPATH_PATH')), 'expanded') | |
269 | ||
270 | old_home = os.environ.get('HOME') | |
271 | test_str = R'C:\Documents and Settings\тест\Application Data' | |
272 | try: | |
273 | os.environ['HOME'] = test_str | |
274 | self.assertEqual(expand_path(env('HOME')), os.getenv('HOME')) | |
275 | self.assertEqual(expand_path('~'), os.getenv('HOME')) | |
276 | self.assertEqual( | |
277 | expand_path('~/%s' % env('yt_dlp_EXPATH_PATH')), | |
278 | '%s/expanded' % os.getenv('HOME')) | |
279 | finally: | |
280 | os.environ['HOME'] = old_home or '' | |
281 | ||
282 | def test_prepend_extension(self): | |
283 | self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext') | |
284 | self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext') | |
285 | self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp') | |
286 | self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp') | |
287 | self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp') | |
288 | self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext') | |
289 | ||
290 | def test_replace_extension(self): | |
291 | self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp') | |
292 | self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp') | |
293 | self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp') | |
294 | self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp') | |
295 | self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') | |
296 | self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') | |
297 | ||
298 | def test_subtitles_filename(self): | |
299 | self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt') | |
300 | self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt') | |
301 | self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt') | |
302 | ||
303 | def test_remove_start(self): | |
304 | self.assertEqual(remove_start(None, 'A - '), None) | |
305 | self.assertEqual(remove_start('A - B', 'A - '), 'B') | |
306 | self.assertEqual(remove_start('B - A', 'A - '), 'B - A') | |
307 | ||
308 | def test_remove_end(self): | |
309 | self.assertEqual(remove_end(None, ' - B'), None) | |
310 | self.assertEqual(remove_end('A - B', ' - B'), 'A') | |
311 | self.assertEqual(remove_end('B - A', ' - B'), 'B - A') | |
312 | ||
313 | def test_remove_quotes(self): | |
314 | self.assertEqual(remove_quotes(None), None) | |
315 | self.assertEqual(remove_quotes('"'), '"') | |
316 | self.assertEqual(remove_quotes("'"), "'") | |
317 | self.assertEqual(remove_quotes(';'), ';') | |
318 | self.assertEqual(remove_quotes('";'), '";') | |
319 | self.assertEqual(remove_quotes('""'), '') | |
320 | self.assertEqual(remove_quotes('";"'), ';') | |
321 | ||
322 | def test_ordered_set(self): | |
323 | self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) | |
324 | self.assertEqual(orderedSet([]), []) | |
325 | self.assertEqual(orderedSet([1]), [1]) | |
326 | # keep the list ordered | |
327 | self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) | |
328 | ||
329 | def test_unescape_html(self): | |
330 | self.assertEqual(unescapeHTML('%20;'), '%20;') | |
331 | self.assertEqual(unescapeHTML('/'), '/') | |
332 | self.assertEqual(unescapeHTML('/'), '/') | |
333 | self.assertEqual(unescapeHTML('é'), 'é') | |
334 | self.assertEqual(unescapeHTML('�'), '�') | |
335 | self.assertEqual(unescapeHTML('&a"'), '&a"') | |
336 | # HTML5 entities | |
337 | self.assertEqual(unescapeHTML('.''), '.\'') | |
338 | ||
339 | def test_date_from_str(self): | |
340 | self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day')) | |
341 | self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week')) | |
342 | self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week')) | |
343 | self.assertEqual(date_from_str('20200229+365day'), date_from_str('20200229+1year')) | |
344 | self.assertEqual(date_from_str('20210131+28day'), date_from_str('20210131+1month')) | |
345 | ||
346 | def test_datetime_from_str(self): | |
347 | self.assertEqual(datetime_from_str('yesterday', precision='day'), datetime_from_str('now-1day', precision='auto')) | |
348 | self.assertEqual(datetime_from_str('now+7day', precision='day'), datetime_from_str('now+1week', precision='auto')) | |
349 | self.assertEqual(datetime_from_str('now+14day', precision='day'), datetime_from_str('now+2week', precision='auto')) | |
350 | self.assertEqual(datetime_from_str('20200229+365day', precision='day'), datetime_from_str('20200229+1year', precision='auto')) | |
351 | self.assertEqual(datetime_from_str('20210131+28day', precision='day'), datetime_from_str('20210131+1month', precision='auto')) | |
352 | self.assertEqual(datetime_from_str('20210131+59day', precision='day'), datetime_from_str('20210131+2month', precision='auto')) | |
353 | self.assertEqual(datetime_from_str('now+1day', precision='hour'), datetime_from_str('now+24hours', precision='auto')) | |
354 | self.assertEqual(datetime_from_str('now+23hours', precision='hour'), datetime_from_str('now+23hours', precision='auto')) | |
355 | ||
356 | def test_daterange(self): | |
357 | _20century = DateRange("19000101", "20000101") | |
358 | self.assertFalse("17890714" in _20century) | |
359 | _ac = DateRange("00010101") | |
360 | self.assertTrue("19690721" in _ac) | |
361 | _firstmilenium = DateRange(end="10000101") | |
362 | self.assertTrue("07110427" in _firstmilenium) | |
363 | ||
364 | def test_unified_dates(self): | |
365 | self.assertEqual(unified_strdate('December 21, 2010'), '20101221') | |
366 | self.assertEqual(unified_strdate('8/7/2009'), '20090708') | |
367 | self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') | |
368 | self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') | |
369 | self.assertEqual(unified_strdate('1968 12 10'), '19681210') | |
370 | self.assertEqual(unified_strdate('1968-12-10'), '19681210') | |
371 | self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128') | |
372 | self.assertEqual( | |
373 | unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False), | |
374 | '20141126') | |
375 | self.assertEqual( | |
376 | unified_strdate('2/2/2015 6:47:40 PM', day_first=False), | |
377 | '20150202') | |
378 | self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214') | |
379 | self.assertEqual(unified_strdate('25-09-2014'), '20140925') | |
380 | self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227') | |
381 | self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None) | |
382 | self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207') | |
383 | self.assertEqual(unified_strdate('July 15th, 2013'), '20130715') | |
384 | self.assertEqual(unified_strdate('September 1st, 2013'), '20130901') | |
385 | self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902') | |
386 | self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103') | |
387 | self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023') | |
388 | ||
389 | def test_unified_timestamps(self): | |
390 | self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) | |
391 | self.assertEqual(unified_timestamp('8/7/2009'), 1247011200) | |
392 | self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200) | |
393 | self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598) | |
394 | self.assertEqual(unified_timestamp('1968 12 10'), -33436800) | |
395 | self.assertEqual(unified_timestamp('1968-12-10'), -33436800) | |
396 | self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200) | |
397 | self.assertEqual( | |
398 | unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False), | |
399 | 1417001400) | |
400 | self.assertEqual( | |
401 | unified_timestamp('2/2/2015 6:47:40 PM', day_first=False), | |
402 | 1422902860) | |
403 | self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900) | |
404 | self.assertEqual(unified_timestamp('25-09-2014'), 1411603200) | |
405 | self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200) | |
406 | self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None) | |
407 | self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500) | |
408 | self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100) | |
409 | self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361) | |
410 | self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540) | |
411 | self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140) | |
412 | self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363) | |
413 | ||
414 | def test_determine_ext(self): | |
415 | self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4') | |
416 | self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None) | |
417 | self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None) | |
418 | self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None) | |
419 | self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8') | |
420 | self.assertEqual(determine_ext('foobar', None), None) | |
421 | ||
422 | def test_find_xpath_attr(self): | |
423 | testxml = '''<root> | |
424 | <node/> | |
425 | <node x="a"/> | |
426 | <node x="a" y="c" /> | |
427 | <node x="b" y="d" /> | |
428 | <node x="" /> | |
429 | </root>''' | |
430 | doc = compat_etree_fromstring(testxml) | |
431 | ||
432 | self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None) | |
433 | self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None) | |
434 | self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None) | |
435 | self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None) | |
436 | self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1]) | |
437 | self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1]) | |
438 | self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3]) | |
439 | self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2]) | |
440 | self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) | |
441 | self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3]) | |
442 | self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4]) | |
443 | ||
444 | def test_xpath_with_ns(self): | |
445 | testxml = '''<root xmlns:media="http://example.com/"> | |
446 | <media:song> | |
447 | <media:author>The Author</media:author> | |
448 | <url>http://server.com/download.mp3</url> | |
449 | </media:song> | |
450 | </root>''' | |
451 | doc = compat_etree_fromstring(testxml) | |
452 | find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'})) | |
453 | self.assertTrue(find('media:song') is not None) | |
454 | self.assertEqual(find('media:song/media:author').text, 'The Author') | |
455 | self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3') | |
456 | ||
457 | def test_xpath_element(self): | |
458 | doc = xml.etree.ElementTree.Element('root') | |
459 | div = xml.etree.ElementTree.SubElement(doc, 'div') | |
460 | p = xml.etree.ElementTree.SubElement(div, 'p') | |
461 | p.text = 'Foo' | |
462 | self.assertEqual(xpath_element(doc, 'div/p'), p) | |
463 | self.assertEqual(xpath_element(doc, ['div/p']), p) | |
464 | self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p) | |
465 | self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default') | |
466 | self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default') | |
467 | self.assertTrue(xpath_element(doc, 'div/bar') is None) | |
468 | self.assertTrue(xpath_element(doc, ['div/bar']) is None) | |
469 | self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None) | |
470 | self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True) | |
471 | self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True) | |
472 | self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True) | |
473 | ||
474 | def test_xpath_text(self): | |
475 | testxml = '''<root> | |
476 | <div> | |
477 | <p>Foo</p> | |
478 | </div> | |
479 | </root>''' | |
480 | doc = compat_etree_fromstring(testxml) | |
481 | self.assertEqual(xpath_text(doc, 'div/p'), 'Foo') | |
482 | self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default') | |
483 | self.assertTrue(xpath_text(doc, 'div/bar') is None) | |
484 | self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True) | |
485 | ||
486 | def test_xpath_attr(self): | |
487 | testxml = '''<root> | |
488 | <div> | |
489 | <p x="a">Foo</p> | |
490 | </div> | |
491 | </root>''' | |
492 | doc = compat_etree_fromstring(testxml) | |
493 | self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a') | |
494 | self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None) | |
495 | self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None) | |
496 | self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default') | |
497 | self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default') | |
498 | self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True) | |
499 | self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True) | |
500 | ||
501 | def test_smuggle_url(self): | |
502 | data = {"ö": "ö", "abc": [3]} | |
503 | url = 'https://foo.bar/baz?x=y#a' | |
504 | smug_url = smuggle_url(url, data) | |
505 | unsmug_url, unsmug_data = unsmuggle_url(smug_url) | |
506 | self.assertEqual(url, unsmug_url) | |
507 | self.assertEqual(data, unsmug_data) | |
508 | ||
509 | res_url, res_data = unsmuggle_url(url) | |
510 | self.assertEqual(res_url, url) | |
511 | self.assertEqual(res_data, None) | |
512 | ||
513 | smug_url = smuggle_url(url, {'a': 'b'}) | |
514 | smug_smug_url = smuggle_url(smug_url, {'c': 'd'}) | |
515 | res_url, res_data = unsmuggle_url(smug_smug_url) | |
516 | self.assertEqual(res_url, url) | |
517 | self.assertEqual(res_data, {'a': 'b', 'c': 'd'}) | |
518 | ||
519 | def test_shell_quote(self): | |
520 | args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')] | |
521 | self.assertEqual( | |
522 | shell_quote(args), | |
523 | """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''') | |
524 | ||
525 | def test_float_or_none(self): | |
526 | self.assertEqual(float_or_none('42.42'), 42.42) | |
527 | self.assertEqual(float_or_none('42'), 42.0) | |
528 | self.assertEqual(float_or_none(''), None) | |
529 | self.assertEqual(float_or_none(None), None) | |
530 | self.assertEqual(float_or_none([]), None) | |
531 | self.assertEqual(float_or_none(set()), None) | |
532 | ||
533 | def test_int_or_none(self): | |
534 | self.assertEqual(int_or_none('42'), 42) | |
535 | self.assertEqual(int_or_none(''), None) | |
536 | self.assertEqual(int_or_none(None), None) | |
537 | self.assertEqual(int_or_none([]), None) | |
538 | self.assertEqual(int_or_none(set()), None) | |
539 | ||
540 | def test_str_to_int(self): | |
541 | self.assertEqual(str_to_int('123,456'), 123456) | |
542 | self.assertEqual(str_to_int('123.456'), 123456) | |
543 | self.assertEqual(str_to_int(523), 523) | |
544 | self.assertEqual(str_to_int('noninteger'), None) | |
545 | self.assertEqual(str_to_int([]), None) | |
546 | ||
547 | def test_url_basename(self): | |
548 | self.assertEqual(url_basename('http://foo.de/'), '') | |
549 | self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz') | |
550 | self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz') | |
551 | self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz') | |
552 | self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz') | |
553 | self.assertEqual( | |
554 | url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'), | |
555 | 'trailer.mp4') | |
556 | ||
557 | def test_base_url(self): | |
558 | self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/') | |
559 | self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/') | |
560 | self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/') | |
561 | self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/') | |
562 | self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/') | |
563 | ||
564 | def test_urljoin(self): | |
565 | self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
566 | self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
567 | self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
568 | self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
569 | self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt') | |
570 | self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
571 | self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
572 | self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
573 | self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
574 | self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt') | |
575 | self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
576 | self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt') | |
577 | self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
578 | self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt') | |
579 | self.assertEqual(urljoin('http://foo.de/', None), None) | |
580 | self.assertEqual(urljoin('http://foo.de/', ''), None) | |
581 | self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) | |
582 | self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') | |
583 | self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de') | |
584 | self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de') | |
585 | ||
586 | def test_url_or_none(self): | |
587 | self.assertEqual(url_or_none(None), None) | |
588 | self.assertEqual(url_or_none(''), None) | |
589 | self.assertEqual(url_or_none('foo'), None) | |
590 | self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') | |
591 | self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de') | |
592 | self.assertEqual(url_or_none('http$://foo.de'), None) | |
593 | self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') | |
594 | self.assertEqual(url_or_none('//foo.de'), '//foo.de') | |
595 | self.assertEqual(url_or_none('s3://foo.de'), None) | |
596 | self.assertEqual(url_or_none('rtmpte://foo.de'), 'rtmpte://foo.de') | |
597 | self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de') | |
598 | self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de') | |
599 | self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de') | |
600 | ||
601 | def test_parse_age_limit(self): | |
602 | self.assertEqual(parse_age_limit(None), None) | |
603 | self.assertEqual(parse_age_limit(False), None) | |
604 | self.assertEqual(parse_age_limit('invalid'), None) | |
605 | self.assertEqual(parse_age_limit(0), 0) | |
606 | self.assertEqual(parse_age_limit(18), 18) | |
607 | self.assertEqual(parse_age_limit(21), 21) | |
608 | self.assertEqual(parse_age_limit(22), None) | |
609 | self.assertEqual(parse_age_limit('18'), 18) | |
610 | self.assertEqual(parse_age_limit('18+'), 18) | |
611 | self.assertEqual(parse_age_limit('PG-13'), 13) | |
612 | self.assertEqual(parse_age_limit('TV-14'), 14) | |
613 | self.assertEqual(parse_age_limit('TV-MA'), 17) | |
614 | self.assertEqual(parse_age_limit('TV14'), 14) | |
615 | self.assertEqual(parse_age_limit('TV_G'), 0) | |
616 | ||
617 | def test_parse_duration(self): | |
618 | self.assertEqual(parse_duration(None), None) | |
619 | self.assertEqual(parse_duration(False), None) | |
620 | self.assertEqual(parse_duration('invalid'), None) | |
621 | self.assertEqual(parse_duration('1'), 1) | |
622 | self.assertEqual(parse_duration('1337:12'), 80232) | |
623 | self.assertEqual(parse_duration('9:12:43'), 33163) | |
624 | self.assertEqual(parse_duration('12:00'), 720) | |
625 | self.assertEqual(parse_duration('00:01:01'), 61) | |
626 | self.assertEqual(parse_duration('x:y'), None) | |
627 | self.assertEqual(parse_duration('3h11m53s'), 11513) | |
628 | self.assertEqual(parse_duration('3h 11m 53s'), 11513) | |
629 | self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513) | |
630 | self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513) | |
631 | self.assertEqual(parse_duration('3 hours, 11 minutes, 53 seconds'), 11513) | |
632 | self.assertEqual(parse_duration('3 hours, 11 mins, 53 secs'), 11513) | |
633 | self.assertEqual(parse_duration('62m45s'), 3765) | |
634 | self.assertEqual(parse_duration('6m59s'), 419) | |
635 | self.assertEqual(parse_duration('49s'), 49) | |
636 | self.assertEqual(parse_duration('0h0m0s'), 0) | |
637 | self.assertEqual(parse_duration('0m0s'), 0) | |
638 | self.assertEqual(parse_duration('0s'), 0) | |
639 | self.assertEqual(parse_duration('01:02:03.05'), 3723.05) | |
640 | self.assertEqual(parse_duration('T30M38S'), 1838) | |
641 | self.assertEqual(parse_duration('5 s'), 5) | |
642 | self.assertEqual(parse_duration('3 min'), 180) | |
643 | self.assertEqual(parse_duration('2.5 hours'), 9000) | |
644 | self.assertEqual(parse_duration('02:03:04'), 7384) | |
645 | self.assertEqual(parse_duration('01:02:03:04'), 93784) | |
646 | self.assertEqual(parse_duration('1 hour 3 minutes'), 3780) | |
647 | self.assertEqual(parse_duration('87 Min.'), 5220) | |
648 | self.assertEqual(parse_duration('PT1H0.040S'), 3600.04) | |
649 | self.assertEqual(parse_duration('PT00H03M30SZ'), 210) | |
650 | self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88) | |
651 | self.assertEqual(parse_duration('01:02:03:050'), 3723.05) | |
652 | self.assertEqual(parse_duration('103:050'), 103.05) | |
653 | ||
654 | def test_fix_xml_ampersands(self): | |
655 | self.assertEqual( | |
656 | fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a') | |
657 | self.assertEqual( | |
658 | fix_xml_ampersands('"&x=y&wrong;&z=a'), | |
659 | '"&x=y&wrong;&z=a') | |
660 | self.assertEqual( | |
661 | fix_xml_ampersands('&'><"'), | |
662 | '&'><"') | |
663 | self.assertEqual( | |
664 | fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼') | |
665 | self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#') | |
666 | ||
667 | def test_paged_list(self): | |
668 | def testPL(size, pagesize, sliceargs, expected): | |
669 | def get_page(pagenum): | |
670 | firstid = pagenum * pagesize | |
671 | upto = min(size, pagenum * pagesize + pagesize) | |
672 | yield from range(firstid, upto) | |
673 | ||
674 | pl = OnDemandPagedList(get_page, pagesize) | |
675 | got = pl.getslice(*sliceargs) | |
676 | self.assertEqual(got, expected) | |
677 | ||
678 | iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize) | |
679 | got = iapl.getslice(*sliceargs) | |
680 | self.assertEqual(got, expected) | |
681 | ||
682 | testPL(5, 2, (), [0, 1, 2, 3, 4]) | |
683 | testPL(5, 2, (1,), [1, 2, 3, 4]) | |
684 | testPL(5, 2, (2,), [2, 3, 4]) | |
685 | testPL(5, 2, (4,), [4]) | |
686 | testPL(5, 2, (0, 3), [0, 1, 2]) | |
687 | testPL(5, 2, (1, 4), [1, 2, 3]) | |
688 | testPL(5, 2, (2, 99), [2, 3, 4]) | |
689 | testPL(5, 2, (20, 99), []) | |
690 | ||
691 | def test_read_batch_urls(self): | |
692 | f = io.StringIO('''\xef\xbb\xbf foo | |
693 | bar\r | |
694 | baz | |
695 | # More after this line\r | |
696 | ; or after this | |
697 | bam''') | |
698 | self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam']) | |
699 | ||
700 | def test_urlencode_postdata(self): | |
701 | data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) | |
702 | self.assertTrue(isinstance(data, bytes)) | |
703 | ||
704 | def test_update_url_query(self): | |
705 | self.assertEqual(parse_qs(update_url_query( | |
706 | 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})), | |
707 | parse_qs('http://example.com/path?quality=HD&format=mp4')) | |
708 | self.assertEqual(parse_qs(update_url_query( | |
709 | 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})), | |
710 | parse_qs('http://example.com/path?system=LINUX&system=WINDOWS')) | |
711 | self.assertEqual(parse_qs(update_url_query( | |
712 | 'http://example.com/path', {'fields': 'id,formats,subtitles'})), | |
713 | parse_qs('http://example.com/path?fields=id,formats,subtitles')) | |
714 | self.assertEqual(parse_qs(update_url_query( | |
715 | 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})), | |
716 | parse_qs('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails')) | |
717 | self.assertEqual(parse_qs(update_url_query( | |
718 | 'http://example.com/path?manifest=f4m', {'manifest': []})), | |
719 | parse_qs('http://example.com/path')) | |
720 | self.assertEqual(parse_qs(update_url_query( | |
721 | 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})), | |
722 | parse_qs('http://example.com/path?system=LINUX')) | |
723 | self.assertEqual(parse_qs(update_url_query( | |
724 | 'http://example.com/path', {'fields': b'id,formats,subtitles'})), | |
725 | parse_qs('http://example.com/path?fields=id,formats,subtitles')) | |
726 | self.assertEqual(parse_qs(update_url_query( | |
727 | 'http://example.com/path', {'width': 1080, 'height': 720})), | |
728 | parse_qs('http://example.com/path?width=1080&height=720')) | |
729 | self.assertEqual(parse_qs(update_url_query( | |
730 | 'http://example.com/path', {'bitrate': 5020.43})), | |
731 | parse_qs('http://example.com/path?bitrate=5020.43')) | |
732 | self.assertEqual(parse_qs(update_url_query( | |
733 | 'http://example.com/path', {'test': '第二行тест'})), | |
734 | parse_qs('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82')) | |
735 | ||
736 | def test_multipart_encode(self): | |
737 | self.assertEqual( | |
738 | multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0], | |
739 | b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n') | |
740 | self.assertEqual( | |
741 | multipart_encode({'欄位'.encode(): '值'.encode()}, boundary='AAAAAA')[0], | |
742 | b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n') | |
743 | self.assertRaises( | |
744 | ValueError, multipart_encode, {b'field': b'value'}, boundary='value') | |
745 | ||
746 | def test_dict_get(self): | |
747 | FALSE_VALUES = { | |
748 | 'none': None, | |
749 | 'false': False, | |
750 | 'zero': 0, | |
751 | 'empty_string': '', | |
752 | 'empty_list': [], | |
753 | } | |
754 | d = FALSE_VALUES.copy() | |
755 | d['a'] = 42 | |
756 | self.assertEqual(dict_get(d, 'a'), 42) | |
757 | self.assertEqual(dict_get(d, 'b'), None) | |
758 | self.assertEqual(dict_get(d, 'b', 42), 42) | |
759 | self.assertEqual(dict_get(d, ('a', )), 42) | |
760 | self.assertEqual(dict_get(d, ('b', 'a', )), 42) | |
761 | self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42) | |
762 | self.assertEqual(dict_get(d, ('b', 'c', )), None) | |
763 | self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42) | |
764 | for key, false_value in FALSE_VALUES.items(): | |
765 | self.assertEqual(dict_get(d, ('b', 'c', key, )), None) | |
766 | self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value) | |
767 | ||
768 | def test_merge_dicts(self): | |
769 | self.assertEqual(merge_dicts({'a': 1}, {'b': 2}), {'a': 1, 'b': 2}) | |
770 | self.assertEqual(merge_dicts({'a': 1}, {'a': 2}), {'a': 1}) | |
771 | self.assertEqual(merge_dicts({'a': 1}, {'a': None}), {'a': 1}) | |
772 | self.assertEqual(merge_dicts({'a': 1}, {'a': ''}), {'a': 1}) | |
773 | self.assertEqual(merge_dicts({'a': 1}, {}), {'a': 1}) | |
774 | self.assertEqual(merge_dicts({'a': None}, {'a': 1}), {'a': 1}) | |
775 | self.assertEqual(merge_dicts({'a': ''}, {'a': 1}), {'a': ''}) | |
776 | self.assertEqual(merge_dicts({'a': ''}, {'a': 'abc'}), {'a': 'abc'}) | |
777 | self.assertEqual(merge_dicts({'a': None}, {'a': ''}, {'a': 'abc'}), {'a': 'abc'}) | |
778 | ||
779 | def test_encode_compat_str(self): | |
780 | self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест') | |
781 | self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест') | |
782 | ||
783 | def test_parse_iso8601(self): | |
784 | self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266) | |
785 | self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) | |
786 | self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266) | |
787 | self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266) | |
788 | self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251) | |
789 | self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None) | |
790 | ||
791 | def test_strip_jsonp(self): | |
792 | stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);') | |
793 | d = json.loads(stripped) | |
794 | self.assertEqual(d, [{"id": "532cb", "x": 3}]) | |
795 | ||
796 | stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc') | |
797 | d = json.loads(stripped) | |
798 | self.assertEqual(d, {'STATUS': 'OK'}) | |
799 | ||
800 | stripped = strip_jsonp('ps.embedHandler({"status": "success"});') | |
801 | d = json.loads(stripped) | |
802 | self.assertEqual(d, {'status': 'success'}) | |
803 | ||
804 | stripped = strip_jsonp('window.cb && window.cb({"status": "success"});') | |
805 | d = json.loads(stripped) | |
806 | self.assertEqual(d, {'status': 'success'}) | |
807 | ||
808 | stripped = strip_jsonp('window.cb && cb({"status": "success"});') | |
809 | d = json.loads(stripped) | |
810 | self.assertEqual(d, {'status': 'success'}) | |
811 | ||
812 | stripped = strip_jsonp('({"status": "success"});') | |
813 | d = json.loads(stripped) | |
814 | self.assertEqual(d, {'status': 'success'}) | |
815 | ||
816 | def test_strip_or_none(self): | |
817 | self.assertEqual(strip_or_none(' abc'), 'abc') | |
818 | self.assertEqual(strip_or_none('abc '), 'abc') | |
819 | self.assertEqual(strip_or_none(' abc '), 'abc') | |
820 | self.assertEqual(strip_or_none('\tabc\t'), 'abc') | |
821 | self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc') | |
822 | self.assertEqual(strip_or_none('abc'), 'abc') | |
823 | self.assertEqual(strip_or_none(''), '') | |
824 | self.assertEqual(strip_or_none(None), None) | |
825 | self.assertEqual(strip_or_none(42), None) | |
826 | self.assertEqual(strip_or_none([]), None) | |
827 | ||
828 | def test_uppercase_escape(self): | |
829 | self.assertEqual(uppercase_escape('aä'), 'aä') | |
830 | self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') | |
831 | ||
832 | def test_lowercase_escape(self): | |
833 | self.assertEqual(lowercase_escape('aä'), 'aä') | |
834 | self.assertEqual(lowercase_escape('\\u0026'), '&') | |
835 | ||
836 | def test_limit_length(self): | |
837 | self.assertEqual(limit_length(None, 12), None) | |
838 | self.assertEqual(limit_length('foo', 12), 'foo') | |
839 | self.assertTrue( | |
840 | limit_length('foo bar baz asd', 12).startswith('foo bar')) | |
841 | self.assertTrue('...' in limit_length('foo bar baz asd', 12)) | |
842 | ||
843 | def test_mimetype2ext(self): | |
844 | self.assertEqual(mimetype2ext(None), None) | |
845 | self.assertEqual(mimetype2ext('video/x-flv'), 'flv') | |
846 | self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8') | |
847 | self.assertEqual(mimetype2ext('text/vtt'), 'vtt') | |
848 | self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt') | |
849 | self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html') | |
850 | self.assertEqual(mimetype2ext('audio/x-wav'), 'wav') | |
851 | self.assertEqual(mimetype2ext('audio/x-wav;codec=pcm'), 'wav') | |
852 | ||
853 | def test_month_by_name(self): | |
854 | self.assertEqual(month_by_name(None), None) | |
855 | self.assertEqual(month_by_name('December', 'en'), 12) | |
856 | self.assertEqual(month_by_name('décembre', 'fr'), 12) | |
857 | self.assertEqual(month_by_name('December'), 12) | |
858 | self.assertEqual(month_by_name('décembre'), None) | |
859 | self.assertEqual(month_by_name('Unknown', 'unknown'), None) | |
860 | ||
861 | def test_parse_codecs(self): | |
862 | self.assertEqual(parse_codecs(''), {}) | |
863 | self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), { | |
864 | 'vcodec': 'avc1.77.30', | |
865 | 'acodec': 'mp4a.40.2', | |
866 | 'dynamic_range': None, | |
867 | }) | |
868 | self.assertEqual(parse_codecs('mp4a.40.2'), { | |
869 | 'vcodec': 'none', | |
870 | 'acodec': 'mp4a.40.2', | |
871 | 'dynamic_range': None, | |
872 | }) | |
873 | self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), { | |
874 | 'vcodec': 'avc1.42001e', | |
875 | 'acodec': 'mp4a.40.5', | |
876 | 'dynamic_range': None, | |
877 | }) | |
878 | self.assertEqual(parse_codecs('avc3.640028'), { | |
879 | 'vcodec': 'avc3.640028', | |
880 | 'acodec': 'none', | |
881 | 'dynamic_range': None, | |
882 | }) | |
883 | self.assertEqual(parse_codecs(', h264,,newcodec,aac'), { | |
884 | 'vcodec': 'h264', | |
885 | 'acodec': 'aac', | |
886 | 'dynamic_range': None, | |
887 | }) | |
888 | self.assertEqual(parse_codecs('av01.0.05M.08'), { | |
889 | 'vcodec': 'av01.0.05M.08', | |
890 | 'acodec': 'none', | |
891 | 'dynamic_range': None, | |
892 | }) | |
893 | self.assertEqual(parse_codecs('vp9.2'), { | |
894 | 'vcodec': 'vp9.2', | |
895 | 'acodec': 'none', | |
896 | 'dynamic_range': 'HDR10', | |
897 | }) | |
898 | self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), { | |
899 | 'vcodec': 'av01.0.12M.10.0.110.09.16.09.0', | |
900 | 'acodec': 'none', | |
901 | 'dynamic_range': 'HDR10', | |
902 | }) | |
903 | self.assertEqual(parse_codecs('dvhe'), { | |
904 | 'vcodec': 'dvhe', | |
905 | 'acodec': 'none', | |
906 | 'dynamic_range': 'DV', | |
907 | }) | |
908 | self.assertEqual(parse_codecs('theora, vorbis'), { | |
909 | 'vcodec': 'theora', | |
910 | 'acodec': 'vorbis', | |
911 | 'dynamic_range': None, | |
912 | }) | |
913 | self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), { | |
914 | 'vcodec': 'unknownvcodec', | |
915 | 'acodec': 'unknownacodec', | |
916 | }) | |
917 | self.assertEqual(parse_codecs('unknown'), {}) | |
918 | ||
919 | def test_escape_rfc3986(self): | |
920 | reserved = "!*'();:@&=+$,/?#[]" | |
921 | unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~' | |
922 | self.assertEqual(escape_rfc3986(reserved), reserved) | |
923 | self.assertEqual(escape_rfc3986(unreserved), unreserved) | |
924 | self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82') | |
925 | self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82') | |
926 | self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar') | |
927 | self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar') | |
928 | ||
929 | def test_escape_url(self): | |
930 | self.assertEqual( | |
931 | escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'), | |
932 | 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4' | |
933 | ) | |
934 | self.assertEqual( | |
935 | escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'), | |
936 | 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290' | |
937 | ) | |
938 | self.assertEqual( | |
939 | escape_url('http://тест.рф/фрагмент'), | |
940 | 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82' | |
941 | ) | |
942 | self.assertEqual( | |
943 | escape_url('http://тест.рф/абв?абв=абв#абв'), | |
944 | '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' | |
945 | ) | |
946 | self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0') | |
947 | ||
948 | def test_js_to_json_realworld(self): | |
949 | inp = '''{ | |
950 | 'clip':{'provider':'pseudo'} | |
951 | }''' | |
952 | self.assertEqual(js_to_json(inp), '''{ | |
953 | "clip":{"provider":"pseudo"} | |
954 | }''') | |
955 | json.loads(js_to_json(inp)) | |
956 | ||
957 | inp = '''{ | |
958 | 'playlist':[{'controls':{'all':null}}] | |
959 | }''' | |
960 | self.assertEqual(js_to_json(inp), '''{ | |
961 | "playlist":[{"controls":{"all":null}}] | |
962 | }''') | |
963 | ||
964 | inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"''' | |
965 | self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''') | |
966 | ||
967 | inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"' | |
968 | json_code = js_to_json(inp) | |
969 | self.assertEqual(json.loads(json_code), json.loads(inp)) | |
970 | ||
971 | inp = '''{ | |
972 | 0:{src:'skipped', type: 'application/dash+xml'}, | |
973 | 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'}, | |
974 | }''' | |
975 | self.assertEqual(js_to_json(inp), '''{ | |
976 | "0":{"src":"skipped", "type": "application/dash+xml"}, | |
977 | "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"} | |
978 | }''') | |
979 | ||
980 | inp = '''{"foo":101}''' | |
981 | self.assertEqual(js_to_json(inp), '''{"foo":101}''') | |
982 | ||
983 | inp = '''{"duration": "00:01:07"}''' | |
984 | self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''') | |
985 | ||
986 | inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''' | |
987 | self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''') | |
988 | ||
989 | def test_js_to_json_edgecases(self): | |
990 | on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") | |
991 | self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) | |
992 | ||
993 | on = js_to_json('{"abc": true}') | |
994 | self.assertEqual(json.loads(on), {'abc': True}) | |
995 | ||
996 | # Ignore JavaScript code as well | |
997 | on = js_to_json('''{ | |
998 | "x": 1, | |
999 | y: "a", | |
1000 | z: some.code | |
1001 | }''') | |
1002 | d = json.loads(on) | |
1003 | self.assertEqual(d['x'], 1) | |
1004 | self.assertEqual(d['y'], 'a') | |
1005 | ||
1006 | # Just drop ! prefix for now though this results in a wrong value | |
1007 | on = js_to_json('''{ | |
1008 | a: !0, | |
1009 | b: !1, | |
1010 | c: !!0, | |
1011 | d: !!42.42, | |
1012 | e: !!![], | |
1013 | f: !"abc", | |
1014 | g: !"", | |
1015 | !42: 42 | |
1016 | }''') | |
1017 | self.assertEqual(json.loads(on), { | |
1018 | 'a': 0, | |
1019 | 'b': 1, | |
1020 | 'c': 0, | |
1021 | 'd': 42.42, | |
1022 | 'e': [], | |
1023 | 'f': "abc", | |
1024 | 'g': "", | |
1025 | '42': 42 | |
1026 | }) | |
1027 | ||
1028 | on = js_to_json('["abc", "def",]') | |
1029 | self.assertEqual(json.loads(on), ['abc', 'def']) | |
1030 | ||
1031 | on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]') | |
1032 | self.assertEqual(json.loads(on), ['abc', 'def']) | |
1033 | ||
1034 | on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]') | |
1035 | self.assertEqual(json.loads(on), ['abc', 'def']) | |
1036 | ||
1037 | on = js_to_json('{"abc": "def",}') | |
1038 | self.assertEqual(json.loads(on), {'abc': 'def'}) | |
1039 | ||
1040 | on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}') | |
1041 | self.assertEqual(json.loads(on), {'abc': 'def'}) | |
1042 | ||
1043 | on = js_to_json('{ 0: /* " \n */ ",]" , }') | |
1044 | self.assertEqual(json.loads(on), {'0': ',]'}) | |
1045 | ||
1046 | on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }') | |
1047 | self.assertEqual(json.loads(on), {'0': ',]'}) | |
1048 | ||
1049 | on = js_to_json('{ 0: // comment\n1 }') | |
1050 | self.assertEqual(json.loads(on), {'0': 1}) | |
1051 | ||
1052 | on = js_to_json(r'["<p>x<\/p>"]') | |
1053 | self.assertEqual(json.loads(on), ['<p>x</p>']) | |
1054 | ||
1055 | on = js_to_json(r'["\xaa"]') | |
1056 | self.assertEqual(json.loads(on), ['\u00aa']) | |
1057 | ||
1058 | on = js_to_json("['a\\\nb']") | |
1059 | self.assertEqual(json.loads(on), ['ab']) | |
1060 | ||
1061 | on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/") | |
1062 | self.assertEqual(json.loads(on), ['ab']) | |
1063 | ||
1064 | on = js_to_json('{0xff:0xff}') | |
1065 | self.assertEqual(json.loads(on), {'255': 255}) | |
1066 | ||
1067 | on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}') | |
1068 | self.assertEqual(json.loads(on), {'255': 255}) | |
1069 | ||
1070 | on = js_to_json('{077:077}') | |
1071 | self.assertEqual(json.loads(on), {'63': 63}) | |
1072 | ||
1073 | on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}') | |
1074 | self.assertEqual(json.loads(on), {'63': 63}) | |
1075 | ||
1076 | on = js_to_json('{42:42}') | |
1077 | self.assertEqual(json.loads(on), {'42': 42}) | |
1078 | ||
1079 | on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}') | |
1080 | self.assertEqual(json.loads(on), {'42': 42}) | |
1081 | ||
1082 | on = js_to_json('{42:4.2e1}') | |
1083 | self.assertEqual(json.loads(on), {'42': 42.0}) | |
1084 | ||
1085 | on = js_to_json('{ "0x40": "0x40" }') | |
1086 | self.assertEqual(json.loads(on), {'0x40': '0x40'}) | |
1087 | ||
1088 | on = js_to_json('{ "040": "040" }') | |
1089 | self.assertEqual(json.loads(on), {'040': '040'}) | |
1090 | ||
1091 | on = js_to_json('[1,//{},\n2]') | |
1092 | self.assertEqual(json.loads(on), [1, 2]) | |
1093 | ||
1094 | def test_js_to_json_malformed(self): | |
1095 | self.assertEqual(js_to_json('42a1'), '42"a1"') | |
1096 | self.assertEqual(js_to_json('42a-1'), '42"a"-1') | |
1097 | ||
1098 | def test_extract_attributes(self): | |
1099 | self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}) | |
1100 | self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'}) | |
1101 | self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'}) | |
1102 | self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"}) | |
1103 | self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'}) | |
1104 | self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}) | |
1105 | self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}) | |
1106 | self.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}) # XML | |
1107 | self.assertEqual(extract_attributes('<e x=""">'), {'x': '"'}) | |
1108 | self.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}) # HTML 3.2 | |
1109 | self.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}) # HTML 4.0 | |
1110 | self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'}) | |
1111 | self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"}) | |
1112 | self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'}) | |
1113 | self.assertEqual(extract_attributes('<e x >'), {'x': None}) | |
1114 | self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None}) | |
1115 | self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'}) | |
1116 | self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'}) | |
1117 | self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'}) | |
1118 | self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'}) | |
1119 | self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'}) | |
1120 | self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'}) | |
1121 | self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased | |
1122 | self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'}) | |
1123 | self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'}) | |
1124 | self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'}) | |
1125 | self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'}) | |
1126 | self.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'}) | |
1127 | # "Narrow" Python builds don't support unicode code points outside BMP. | |
1128 | try: | |
1129 | chr(0x10000) | |
1130 | supports_outside_bmp = True | |
1131 | except ValueError: | |
1132 | supports_outside_bmp = False | |
1133 | if supports_outside_bmp: | |
1134 | self.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'}) | |
1135 | # Malformed HTML should not break attributes extraction on older Python | |
1136 | self.assertEqual(extract_attributes('<mal"formed/>'), {}) | |
1137 | ||
1138 | def test_clean_html(self): | |
1139 | self.assertEqual(clean_html('a:\nb'), 'a: b') | |
1140 | self.assertEqual(clean_html('a:\n "b"'), 'a: "b"') | |
1141 | self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb') | |
1142 | ||
1143 | def test_intlist_to_bytes(self): | |
1144 | self.assertEqual( | |
1145 | intlist_to_bytes([0, 1, 127, 128, 255]), | |
1146 | b'\x00\x01\x7f\x80\xff') | |
1147 | ||
1148 | def test_args_to_str(self): | |
1149 | self.assertEqual( | |
1150 | args_to_str(['foo', 'ba/r', '-baz', '2 be', '']), | |
1151 | 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""' | |
1152 | ) | |
1153 | ||
1154 | def test_parse_filesize(self): | |
1155 | self.assertEqual(parse_filesize(None), None) | |
1156 | self.assertEqual(parse_filesize(''), None) | |
1157 | self.assertEqual(parse_filesize('91 B'), 91) | |
1158 | self.assertEqual(parse_filesize('foobar'), None) | |
1159 | self.assertEqual(parse_filesize('2 MiB'), 2097152) | |
1160 | self.assertEqual(parse_filesize('5 GB'), 5000000000) | |
1161 | self.assertEqual(parse_filesize('1.2Tb'), 1200000000000) | |
1162 | self.assertEqual(parse_filesize('1.2tb'), 1200000000000) | |
1163 | self.assertEqual(parse_filesize('1,24 KB'), 1240) | |
1164 | self.assertEqual(parse_filesize('1,24 kb'), 1240) | |
1165 | self.assertEqual(parse_filesize('8.5 megabytes'), 8500000) | |
1166 | ||
1167 | def test_parse_count(self): | |
1168 | self.assertEqual(parse_count(None), None) | |
1169 | self.assertEqual(parse_count(''), None) | |
1170 | self.assertEqual(parse_count('0'), 0) | |
1171 | self.assertEqual(parse_count('1000'), 1000) | |
1172 | self.assertEqual(parse_count('1.000'), 1000) | |
1173 | self.assertEqual(parse_count('1.1k'), 1100) | |
1174 | self.assertEqual(parse_count('1.1 k'), 1100) | |
1175 | self.assertEqual(parse_count('1,1 k'), 1100) | |
1176 | self.assertEqual(parse_count('1.1kk'), 1100000) | |
1177 | self.assertEqual(parse_count('1.1kk '), 1100000) | |
1178 | self.assertEqual(parse_count('1,1kk'), 1100000) | |
1179 | self.assertEqual(parse_count('100 views'), 100) | |
1180 | self.assertEqual(parse_count('1,100 views'), 1100) | |
1181 | self.assertEqual(parse_count('1.1kk views'), 1100000) | |
1182 | self.assertEqual(parse_count('10M views'), 10000000) | |
1183 | self.assertEqual(parse_count('has 10M views'), 10000000) | |
1184 | ||
1185 | def test_parse_resolution(self): | |
1186 | self.assertEqual(parse_resolution(None), {}) | |
1187 | self.assertEqual(parse_resolution(''), {}) | |
1188 | self.assertEqual(parse_resolution(' 1920x1080'), {'width': 1920, 'height': 1080}) | |
1189 | self.assertEqual(parse_resolution('1920×1080 '), {'width': 1920, 'height': 1080}) | |
1190 | self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080}) | |
1191 | self.assertEqual(parse_resolution('720p'), {'height': 720}) | |
1192 | self.assertEqual(parse_resolution('4k'), {'height': 2160}) | |
1193 | self.assertEqual(parse_resolution('8K'), {'height': 4320}) | |
1194 | self.assertEqual(parse_resolution('pre_1920x1080_post'), {'width': 1920, 'height': 1080}) | |
1195 | self.assertEqual(parse_resolution('ep1x2'), {}) | |
1196 | self.assertEqual(parse_resolution('1920, 1080'), {'width': 1920, 'height': 1080}) | |
1197 | ||
1198 | def test_parse_bitrate(self): | |
1199 | self.assertEqual(parse_bitrate(None), None) | |
1200 | self.assertEqual(parse_bitrate(''), None) | |
1201 | self.assertEqual(parse_bitrate('300kbps'), 300) | |
1202 | self.assertEqual(parse_bitrate('1500kbps'), 1500) | |
1203 | self.assertEqual(parse_bitrate('300 kbps'), 300) | |
1204 | ||
1205 | def test_version_tuple(self): | |
1206 | self.assertEqual(version_tuple('1'), (1,)) | |
1207 | self.assertEqual(version_tuple('10.23.344'), (10, 23, 344)) | |
1208 | self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style | |
1209 | ||
1210 | def test_detect_exe_version(self): | |
1211 | self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1 | |
1212 | built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4) | |
1213 | configuration: --prefix=/usr --extra-'''), '1.2.1') | |
1214 | self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685 | |
1215 | built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685') | |
1216 | self.assertEqual(detect_exe_version('''X server found. dri2 connection failed! | |
1217 | Trying to open render node... | |
1218 | Success at /dev/dri/renderD128. | |
1219 | ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') | |
1220 | ||
1221 | def test_age_restricted(self): | |
1222 | self.assertFalse(age_restricted(None, 10)) # unrestricted content | |
1223 | self.assertFalse(age_restricted(1, None)) # unrestricted policy | |
1224 | self.assertFalse(age_restricted(8, 10)) | |
1225 | self.assertTrue(age_restricted(18, 14)) | |
1226 | self.assertFalse(age_restricted(18, 18)) | |
1227 | ||
1228 | def test_is_html(self): | |
1229 | self.assertFalse(is_html(b'\x49\x44\x43<html')) | |
1230 | self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa')) | |
1231 | self.assertTrue(is_html( # UTF-8 with BOM | |
1232 | b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa')) | |
1233 | self.assertTrue(is_html( # UTF-16-LE | |
1234 | b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00' | |
1235 | )) | |
1236 | self.assertTrue(is_html( # UTF-16-BE | |
1237 | b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4' | |
1238 | )) | |
1239 | self.assertTrue(is_html( # UTF-32-BE | |
1240 | 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')) | |
1241 | self.assertTrue(is_html( # UTF-32-LE | |
1242 | 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')) | |
1243 | ||
1244 | def test_render_table(self): | |
1245 | self.assertEqual( | |
1246 | render_table( | |
1247 | ['a', 'empty', 'bcd'], | |
1248 | [[123, '', 4], [9999, '', 51]]), | |
1249 | 'a empty bcd\n' | |
1250 | '123 4\n' | |
1251 | '9999 51') | |
1252 | ||
1253 | self.assertEqual( | |
1254 | render_table( | |
1255 | ['a', 'empty', 'bcd'], | |
1256 | [[123, '', 4], [9999, '', 51]], | |
1257 | hide_empty=True), | |
1258 | 'a bcd\n' | |
1259 | '123 4\n' | |
1260 | '9999 51') | |
1261 | ||
1262 | self.assertEqual( | |
1263 | render_table( | |
1264 | ['\ta', 'bcd'], | |
1265 | [['1\t23', 4], ['\t9999', 51]]), | |
1266 | ' a bcd\n' | |
1267 | '1 23 4\n' | |
1268 | '9999 51') | |
1269 | ||
1270 | self.assertEqual( | |
1271 | render_table( | |
1272 | ['a', 'bcd'], | |
1273 | [[123, 4], [9999, 51]], | |
1274 | delim='-'), | |
1275 | 'a bcd\n' | |
1276 | '--------\n' | |
1277 | '123 4\n' | |
1278 | '9999 51') | |
1279 | ||
1280 | self.assertEqual( | |
1281 | render_table( | |
1282 | ['a', 'bcd'], | |
1283 | [[123, 4], [9999, 51]], | |
1284 | delim='-', extra_gap=2), | |
1285 | 'a bcd\n' | |
1286 | '----------\n' | |
1287 | '123 4\n' | |
1288 | '9999 51') | |
1289 | ||
1290 | def test_match_str(self): | |
1291 | # Unary | |
1292 | self.assertFalse(match_str('xy', {'x': 1200})) | |
1293 | self.assertTrue(match_str('!xy', {'x': 1200})) | |
1294 | self.assertTrue(match_str('x', {'x': 1200})) | |
1295 | self.assertFalse(match_str('!x', {'x': 1200})) | |
1296 | self.assertTrue(match_str('x', {'x': 0})) | |
1297 | self.assertTrue(match_str('is_live', {'is_live': True})) | |
1298 | self.assertFalse(match_str('is_live', {'is_live': False})) | |
1299 | self.assertFalse(match_str('is_live', {'is_live': None})) | |
1300 | self.assertFalse(match_str('is_live', {})) | |
1301 | self.assertFalse(match_str('!is_live', {'is_live': True})) | |
1302 | self.assertTrue(match_str('!is_live', {'is_live': False})) | |
1303 | self.assertTrue(match_str('!is_live', {'is_live': None})) | |
1304 | self.assertTrue(match_str('!is_live', {})) | |
1305 | self.assertTrue(match_str('title', {'title': 'abc'})) | |
1306 | self.assertTrue(match_str('title', {'title': ''})) | |
1307 | self.assertFalse(match_str('!title', {'title': 'abc'})) | |
1308 | self.assertFalse(match_str('!title', {'title': ''})) | |
1309 | ||
1310 | # Numeric | |
1311 | self.assertFalse(match_str('x>0', {'x': 0})) | |
1312 | self.assertFalse(match_str('x>0', {})) | |
1313 | self.assertTrue(match_str('x>?0', {})) | |
1314 | self.assertTrue(match_str('x>1K', {'x': 1200})) | |
1315 | self.assertFalse(match_str('x>2K', {'x': 1200})) | |
1316 | self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200})) | |
1317 | self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200})) | |
1318 | self.assertTrue(match_str('x > 1:0:0', {'x': 3700})) | |
1319 | ||
1320 | # String | |
1321 | self.assertFalse(match_str('y=a212', {'y': 'foobar42'})) | |
1322 | self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'})) | |
1323 | self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'})) | |
1324 | self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'})) | |
1325 | self.assertTrue(match_str('y^=foo', {'y': 'foobar42'})) | |
1326 | self.assertFalse(match_str('y!^=foo', {'y': 'foobar42'})) | |
1327 | self.assertFalse(match_str('y^=bar', {'y': 'foobar42'})) | |
1328 | self.assertTrue(match_str('y!^=bar', {'y': 'foobar42'})) | |
1329 | self.assertRaises(ValueError, match_str, 'x^=42', {'x': 42}) | |
1330 | self.assertTrue(match_str('y*=bar', {'y': 'foobar42'})) | |
1331 | self.assertFalse(match_str('y!*=bar', {'y': 'foobar42'})) | |
1332 | self.assertFalse(match_str('y*=baz', {'y': 'foobar42'})) | |
1333 | self.assertTrue(match_str('y!*=baz', {'y': 'foobar42'})) | |
1334 | self.assertTrue(match_str('y$=42', {'y': 'foobar42'})) | |
1335 | self.assertFalse(match_str('y$=43', {'y': 'foobar42'})) | |
1336 | ||
1337 | # And | |
1338 | self.assertFalse(match_str( | |
1339 | 'like_count > 100 & dislike_count <? 50 & description', | |
1340 | {'like_count': 90, 'description': 'foo'})) | |
1341 | self.assertTrue(match_str( | |
1342 | 'like_count > 100 & dislike_count <? 50 & description', | |
1343 | {'like_count': 190, 'description': 'foo'})) | |
1344 | self.assertFalse(match_str( | |
1345 | 'like_count > 100 & dislike_count <? 50 & description', | |
1346 | {'like_count': 190, 'dislike_count': 60, 'description': 'foo'})) | |
1347 | self.assertFalse(match_str( | |
1348 | 'like_count > 100 & dislike_count <? 50 & description', | |
1349 | {'like_count': 190, 'dislike_count': 10})) | |
1350 | ||
1351 | # Regex | |
1352 | self.assertTrue(match_str(r'x~=\bbar', {'x': 'foo bar'})) | |
1353 | self.assertFalse(match_str(r'x~=\bbar.+', {'x': 'foo bar'})) | |
1354 | self.assertFalse(match_str(r'x~=^FOO', {'x': 'foo bar'})) | |
1355 | self.assertTrue(match_str(r'x~=(?i)^FOO', {'x': 'foo bar'})) | |
1356 | ||
1357 | # Quotes | |
1358 | self.assertTrue(match_str(r'x^="foo"', {'x': 'foo "bar"'})) | |
1359 | self.assertFalse(match_str(r'x^="foo "', {'x': 'foo "bar"'})) | |
1360 | self.assertFalse(match_str(r'x$="bar"', {'x': 'foo "bar"'})) | |
1361 | self.assertTrue(match_str(r'x$=" \"bar\""', {'x': 'foo "bar"'})) | |
1362 | ||
1363 | # Escaping & | |
1364 | self.assertFalse(match_str(r'x=foo & bar', {'x': 'foo & bar'})) | |
1365 | self.assertTrue(match_str(r'x=foo \& bar', {'x': 'foo & bar'})) | |
1366 | self.assertTrue(match_str(r'x=foo \& bar & x^=foo', {'x': 'foo & bar'})) | |
1367 | self.assertTrue(match_str(r'x="foo \& bar" & x^=foo', {'x': 'foo & bar'})) | |
1368 | ||
1369 | # Example from docs | |
1370 | self.assertTrue(match_str( | |
1371 | r"!is_live & like_count>?100 & description~='(?i)\bcats \& dogs\b'", | |
1372 | {'description': 'Raining Cats & Dogs'})) | |
1373 | ||
1374 | # Incomplete | |
1375 | self.assertFalse(match_str('id!=foo', {'id': 'foo'}, True)) | |
1376 | self.assertTrue(match_str('x', {'id': 'foo'}, True)) | |
1377 | self.assertTrue(match_str('!x', {'id': 'foo'}, True)) | |
1378 | self.assertFalse(match_str('x', {'id': 'foo'}, False)) | |
1379 | ||
1380 | def test_parse_dfxp_time_expr(self): | |
1381 | self.assertEqual(parse_dfxp_time_expr(None), None) | |
1382 | self.assertEqual(parse_dfxp_time_expr(''), None) | |
1383 | self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1) | |
1384 | self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1) | |
1385 | self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0) | |
1386 | self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1) | |
1387 | self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1) | |
1388 | ||
1389 | def test_dfxp2srt(self): | |
1390 | dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?> | |
1391 | <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter"> | |
1392 | <body> | |
1393 | <div xml:lang="en"> | |
1394 | <p begin="0" end="1">The following line contains Chinese characters and special symbols</p> | |
1395 | <p begin="1" end="2">第二行<br/>♪♪</p> | |
1396 | <p begin="2" dur="1"><span>Third<br/>Line</span></p> | |
1397 | <p begin="3" end="-1">Lines with invalid timestamps are ignored</p> | |
1398 | <p begin="-1" end="-1">Ignore, two</p> | |
1399 | <p begin="3" dur="-1">Ignored, three</p> | |
1400 | </div> | |
1401 | </body> | |
1402 | </tt>'''.encode() | |
1403 | srt_data = '''1 | |
1404 | 00:00:00,000 --> 00:00:01,000 | |
1405 | The following line contains Chinese characters and special symbols | |
1406 | ||
1407 | 2 | |
1408 | 00:00:01,000 --> 00:00:02,000 | |
1409 | 第二行 | |
1410 | ♪♪ | |
1411 | ||
1412 | 3 | |
1413 | 00:00:02,000 --> 00:00:03,000 | |
1414 | Third | |
1415 | Line | |
1416 | ||
1417 | ''' | |
1418 | self.assertEqual(dfxp2srt(dfxp_data), srt_data) | |
1419 | ||
1420 | dfxp_data_no_default_namespace = b'''<?xml version="1.0" encoding="UTF-8"?> | |
1421 | <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter"> | |
1422 | <body> | |
1423 | <div xml:lang="en"> | |
1424 | <p begin="0" end="1">The first line</p> | |
1425 | </div> | |
1426 | </body> | |
1427 | </tt>''' | |
1428 | srt_data = '''1 | |
1429 | 00:00:00,000 --> 00:00:01,000 | |
1430 | The first line | |
1431 | ||
1432 | ''' | |
1433 | self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data) | |
1434 | ||
1435 | dfxp_data_with_style = b'''<?xml version="1.0" encoding="utf-8"?> | |
1436 | <tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata"> | |
1437 | <head> | |
1438 | <styling> | |
1439 | <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" /> | |
1440 | <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" /> | |
1441 | <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" /> | |
1442 | <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" /> | |
1443 | </styling> | |
1444 | </head> | |
1445 | <body tts:textAlign="center" style="s0"> | |
1446 | <div> | |
1447 | <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p> | |
1448 | <p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p> | |
1449 | <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p> | |
1450 | <p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p> | |
1451 | </div> | |
1452 | </body> | |
1453 | </tt>''' | |
1454 | srt_data = '''1 | |
1455 | 00:00:02,080 --> 00:00:05,840 | |
1456 | <font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font> | |
1457 | ||
1458 | 2 | |
1459 | 00:00:02,080 --> 00:00:05,840 | |
1460 | <b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1 | |
1461 | </font>part 2</font></b> | |
1462 | ||
1463 | 3 | |
1464 | 00:00:05,840 --> 00:00:09,560 | |
1465 | <u><font color="lime">line 3 | |
1466 | part 3</font></u> | |
1467 | ||
1468 | 4 | |
1469 | 00:00:09,560 --> 00:00:12,360 | |
1470 | <i><u><font color="yellow"><font color="lime">inner | |
1471 | </font>style</font></u></i> | |
1472 | ||
1473 | ''' | |
1474 | self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data) | |
1475 | ||
1476 | dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?> | |
1477 | <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter"> | |
1478 | <body> | |
1479 | <div xml:lang="en"> | |
1480 | <p begin="0" end="1">Line 1</p> | |
1481 | <p begin="1" end="2">第二行</p> | |
1482 | </div> | |
1483 | </body> | |
1484 | </tt>'''.encode('utf-16') | |
1485 | srt_data = '''1 | |
1486 | 00:00:00,000 --> 00:00:01,000 | |
1487 | Line 1 | |
1488 | ||
1489 | 2 | |
1490 | 00:00:01,000 --> 00:00:02,000 | |
1491 | 第二行 | |
1492 | ||
1493 | ''' | |
1494 | self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data) | |
1495 | ||
1496 | def test_cli_option(self): | |
1497 | self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128']) | |
1498 | self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), []) | |
1499 | self.assertEqual(cli_option({}, '--proxy', 'proxy'), []) | |
1500 | self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10']) | |
1501 | ||
1502 | def test_cli_valueless_option(self): | |
1503 | self.assertEqual(cli_valueless_option( | |
1504 | {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader']) | |
1505 | self.assertEqual(cli_valueless_option( | |
1506 | {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), []) | |
1507 | self.assertEqual(cli_valueless_option( | |
1508 | {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate']) | |
1509 | self.assertEqual(cli_valueless_option( | |
1510 | {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), []) | |
1511 | self.assertEqual(cli_valueless_option( | |
1512 | {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), []) | |
1513 | self.assertEqual(cli_valueless_option( | |
1514 | {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate']) | |
1515 | ||
1516 | def test_cli_bool_option(self): | |
1517 | self.assertEqual( | |
1518 | cli_bool_option( | |
1519 | {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), | |
1520 | ['--no-check-certificate', 'true']) | |
1521 | self.assertEqual( | |
1522 | cli_bool_option( | |
1523 | {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='), | |
1524 | ['--no-check-certificate=true']) | |
1525 | self.assertEqual( | |
1526 | cli_bool_option( | |
1527 | {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'), | |
1528 | ['--check-certificate', 'false']) | |
1529 | self.assertEqual( | |
1530 | cli_bool_option( | |
1531 | {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), | |
1532 | ['--check-certificate=false']) | |
1533 | self.assertEqual( | |
1534 | cli_bool_option( | |
1535 | {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'), | |
1536 | ['--check-certificate', 'true']) | |
1537 | self.assertEqual( | |
1538 | cli_bool_option( | |
1539 | {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), | |
1540 | ['--check-certificate=true']) | |
1541 | self.assertEqual( | |
1542 | cli_bool_option( | |
1543 | {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), | |
1544 | []) | |
1545 | ||
1546 | def test_ohdave_rsa_encrypt(self): | |
1547 | N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd | |
1548 | e = 65537 | |
1549 | ||
1550 | self.assertEqual( | |
1551 | ohdave_rsa_encrypt(b'aa111222', e, N), | |
1552 | '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881') | |
1553 | ||
1554 | def test_pkcs1pad(self): | |
1555 | data = [1, 2, 3] | |
1556 | padded_data = pkcs1pad(data, 32) | |
1557 | self.assertEqual(padded_data[:2], [0, 2]) | |
1558 | self.assertEqual(padded_data[28:], [0, 1, 2, 3]) | |
1559 | ||
1560 | self.assertRaises(ValueError, pkcs1pad, data, 8) | |
1561 | ||
1562 | def test_encode_base_n(self): | |
1563 | self.assertEqual(encode_base_n(0, 30), '0') | |
1564 | self.assertEqual(encode_base_n(80, 30), '2k') | |
1565 | ||
1566 | custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA' | |
1567 | self.assertEqual(encode_base_n(0, 30, custom_table), '9') | |
1568 | self.assertEqual(encode_base_n(80, 30, custom_table), '7P') | |
1569 | ||
1570 | self.assertRaises(ValueError, encode_base_n, 0, 70) | |
1571 | self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) | |
1572 | ||
1573 | def test_caesar(self): | |
1574 | self.assertEqual(caesar('ace', 'abcdef', 2), 'cea') | |
1575 | self.assertEqual(caesar('cea', 'abcdef', -2), 'ace') | |
1576 | self.assertEqual(caesar('ace', 'abcdef', -2), 'eac') | |
1577 | self.assertEqual(caesar('eac', 'abcdef', 2), 'ace') | |
1578 | self.assertEqual(caesar('ace', 'abcdef', 0), 'ace') | |
1579 | self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz') | |
1580 | self.assertEqual(caesar('abc', 'acegik', 2), 'ebg') | |
1581 | self.assertEqual(caesar('ebg', 'acegik', -2), 'abc') | |
1582 | ||
1583 | def test_rot47(self): | |
1584 | self.assertEqual(rot47('yt-dlp'), r'JE\5=A') | |
1585 | self.assertEqual(rot47('YT-DLP'), r'*%\s{!') | |
1586 | ||
1587 | def test_urshift(self): | |
1588 | self.assertEqual(urshift(3, 1), 1) | |
1589 | self.assertEqual(urshift(-3, 1), 2147483646) | |
1590 | ||
1591 | GET_ELEMENT_BY_CLASS_TEST_STRING = ''' | |
1592 | <span class="foo bar">nice</span> | |
1593 | ''' | |
1594 | ||
1595 | def test_get_element_by_class(self): | |
1596 | html = self.GET_ELEMENT_BY_CLASS_TEST_STRING | |
1597 | ||
1598 | self.assertEqual(get_element_by_class('foo', html), 'nice') | |
1599 | self.assertEqual(get_element_by_class('no-such-class', html), None) | |
1600 | ||
1601 | def test_get_element_html_by_class(self): | |
1602 | html = self.GET_ELEMENT_BY_CLASS_TEST_STRING | |
1603 | ||
1604 | self.assertEqual(get_element_html_by_class('foo', html), html.strip()) | |
1605 | self.assertEqual(get_element_by_class('no-such-class', html), None) | |
1606 | ||
1607 | GET_ELEMENT_BY_ATTRIBUTE_TEST_STRING = ''' | |
1608 | <div itemprop="author" itemscope>foo</div> | |
1609 | ''' | |
1610 | ||
1611 | def test_get_element_by_attribute(self): | |
1612 | html = self.GET_ELEMENT_BY_CLASS_TEST_STRING | |
1613 | ||
1614 | self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice') | |
1615 | self.assertEqual(get_element_by_attribute('class', 'foo', html), None) | |
1616 | self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None) | |
1617 | ||
1618 | html = self.GET_ELEMENT_BY_ATTRIBUTE_TEST_STRING | |
1619 | ||
1620 | self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo') | |
1621 | ||
1622 | def test_get_element_html_by_attribute(self): | |
1623 | html = self.GET_ELEMENT_BY_CLASS_TEST_STRING | |
1624 | ||
1625 | self.assertEqual(get_element_html_by_attribute('class', 'foo bar', html), html.strip()) | |
1626 | self.assertEqual(get_element_html_by_attribute('class', 'foo', html), None) | |
1627 | self.assertEqual(get_element_html_by_attribute('class', 'no-such-foo', html), None) | |
1628 | ||
1629 | html = self.GET_ELEMENT_BY_ATTRIBUTE_TEST_STRING | |
1630 | ||
1631 | self.assertEqual(get_element_html_by_attribute('itemprop', 'author', html), html.strip()) | |
1632 | ||
1633 | GET_ELEMENTS_BY_CLASS_TEST_STRING = ''' | |
1634 | <span class="foo bar">nice</span><span class="foo bar">also nice</span> | |
1635 | ''' | |
1636 | GET_ELEMENTS_BY_CLASS_RES = ['<span class="foo bar">nice</span>', '<span class="foo bar">also nice</span>'] | |
1637 | ||
1638 | def test_get_elements_by_class(self): | |
1639 | html = self.GET_ELEMENTS_BY_CLASS_TEST_STRING | |
1640 | ||
1641 | self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice']) | |
1642 | self.assertEqual(get_elements_by_class('no-such-class', html), []) | |
1643 | ||
1644 | def test_get_elements_html_by_class(self): | |
1645 | html = self.GET_ELEMENTS_BY_CLASS_TEST_STRING | |
1646 | ||
1647 | self.assertEqual(get_elements_html_by_class('foo', html), self.GET_ELEMENTS_BY_CLASS_RES) | |
1648 | self.assertEqual(get_elements_html_by_class('no-such-class', html), []) | |
1649 | ||
1650 | def test_get_elements_by_attribute(self): | |
1651 | html = self.GET_ELEMENTS_BY_CLASS_TEST_STRING | |
1652 | ||
1653 | self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice']) | |
1654 | self.assertEqual(get_elements_by_attribute('class', 'foo', html), []) | |
1655 | self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), []) | |
1656 | ||
1657 | def test_get_elements_html_by_attribute(self): | |
1658 | html = self.GET_ELEMENTS_BY_CLASS_TEST_STRING | |
1659 | ||
1660 | self.assertEqual(get_elements_html_by_attribute('class', 'foo bar', html), self.GET_ELEMENTS_BY_CLASS_RES) | |
1661 | self.assertEqual(get_elements_html_by_attribute('class', 'foo', html), []) | |
1662 | self.assertEqual(get_elements_html_by_attribute('class', 'no-such-foo', html), []) | |
1663 | ||
1664 | def test_get_elements_text_and_html_by_attribute(self): | |
1665 | html = self.GET_ELEMENTS_BY_CLASS_TEST_STRING | |
1666 | ||
1667 | self.assertEqual( | |
1668 | list(get_elements_text_and_html_by_attribute('class', 'foo bar', html)), | |
1669 | list(zip(['nice', 'also nice'], self.GET_ELEMENTS_BY_CLASS_RES))) | |
1670 | self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'foo', html)), []) | |
1671 | self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'no-such-foo', html)), []) | |
1672 | ||
1673 | GET_ELEMENT_BY_TAG_TEST_STRING = ''' | |
1674 | random text lorem ipsum</p> | |
1675 | <div> | |
1676 | this should be returned | |
1677 | <span>this should also be returned</span> | |
1678 | <div> | |
1679 | this should also be returned | |
1680 | </div> | |
1681 | closing tag above should not trick, so this should also be returned | |
1682 | </div> | |
1683 | but this text should not be returned | |
1684 | ''' | |
1685 | GET_ELEMENT_BY_TAG_RES_OUTERDIV_HTML = GET_ELEMENT_BY_TAG_TEST_STRING.strip()[32:276] | |
1686 | GET_ELEMENT_BY_TAG_RES_OUTERDIV_TEXT = GET_ELEMENT_BY_TAG_RES_OUTERDIV_HTML[5:-6] | |
1687 | GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML = GET_ELEMENT_BY_TAG_TEST_STRING.strip()[78:119] | |
1688 | GET_ELEMENT_BY_TAG_RES_INNERSPAN_TEXT = GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML[6:-7] | |
1689 | ||
1690 | def test_get_element_text_and_html_by_tag(self): | |
1691 | html = self.GET_ELEMENT_BY_TAG_TEST_STRING | |
1692 | ||
1693 | self.assertEqual( | |
1694 | get_element_text_and_html_by_tag('div', html), | |
1695 | (self.GET_ELEMENT_BY_TAG_RES_OUTERDIV_TEXT, self.GET_ELEMENT_BY_TAG_RES_OUTERDIV_HTML)) | |
1696 | self.assertEqual( | |
1697 | get_element_text_and_html_by_tag('span', html), | |
1698 | (self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_TEXT, self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML)) | |
1699 | self.assertRaises(compat_HTMLParseError, get_element_text_and_html_by_tag, 'article', html) | |
1700 | ||
1701 | def test_iri_to_uri(self): | |
1702 | self.assertEqual( | |
1703 | iri_to_uri('https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b'), | |
1704 | 'https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b') # Same | |
1705 | self.assertEqual( | |
1706 | iri_to_uri('https://www.google.com/search?q=Käsesoßenrührlöffel'), # German for cheese sauce stirring spoon | |
1707 | 'https://www.google.com/search?q=K%C3%A4seso%C3%9Fenr%C3%BChrl%C3%B6ffel') | |
1708 | self.assertEqual( | |
1709 | iri_to_uri('https://www.google.com/search?q=lt<+gt>+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#'), | |
1710 | 'https://www.google.com/search?q=lt%3C+gt%3E+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#') | |
1711 | self.assertEqual( | |
1712 | iri_to_uri('http://правозащита38.рф/category/news/'), | |
1713 | 'http://xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/') | |
1714 | self.assertEqual( | |
1715 | iri_to_uri('http://www.правозащита38.рф/category/news/'), | |
1716 | 'http://www.xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/') | |
1717 | self.assertEqual( | |
1718 | iri_to_uri('https://i❤.ws/emojidomain/👍👏🤝💪'), | |
1719 | 'https://xn--i-7iq.ws/emojidomain/%F0%9F%91%8D%F0%9F%91%8F%F0%9F%A4%9D%F0%9F%92%AA') | |
1720 | self.assertEqual( | |
1721 | iri_to_uri('http://日本語.jp/'), | |
1722 | 'http://xn--wgv71a119e.jp/') | |
1723 | self.assertEqual( | |
1724 | iri_to_uri('http://导航.中国/'), | |
1725 | 'http://xn--fet810g.xn--fiqs8s/') | |
1726 | ||
1727 | def test_clean_podcast_url(self): | |
1728 | self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3') | |
1729 | self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3') | |
1730 | ||
1731 | def test_LazyList(self): | |
1732 | it = list(range(10)) | |
1733 | ||
1734 | self.assertEqual(list(LazyList(it)), it) | |
1735 | self.assertEqual(LazyList(it).exhaust(), it) | |
1736 | self.assertEqual(LazyList(it)[5], it[5]) | |
1737 | ||
1738 | self.assertEqual(LazyList(it)[5:], it[5:]) | |
1739 | self.assertEqual(LazyList(it)[:5], it[:5]) | |
1740 | self.assertEqual(LazyList(it)[::2], it[::2]) | |
1741 | self.assertEqual(LazyList(it)[1::2], it[1::2]) | |
1742 | self.assertEqual(LazyList(it)[5::-1], it[5::-1]) | |
1743 | self.assertEqual(LazyList(it)[6:2:-2], it[6:2:-2]) | |
1744 | self.assertEqual(LazyList(it)[::-1], it[::-1]) | |
1745 | ||
1746 | self.assertTrue(LazyList(it)) | |
1747 | self.assertFalse(LazyList(range(0))) | |
1748 | self.assertEqual(len(LazyList(it)), len(it)) | |
1749 | self.assertEqual(repr(LazyList(it)), repr(it)) | |
1750 | self.assertEqual(str(LazyList(it)), str(it)) | |
1751 | ||
1752 | self.assertEqual(list(LazyList(it, reverse=True)), it[::-1]) | |
1753 | self.assertEqual(list(reversed(LazyList(it))[::-1]), it) | |
1754 | self.assertEqual(list(reversed(LazyList(it))[1:3:7]), it[::-1][1:3:7]) | |
1755 | ||
1756 | def test_LazyList_laziness(self): | |
1757 | ||
1758 | def test(ll, idx, val, cache): | |
1759 | self.assertEqual(ll[idx], val) | |
1760 | self.assertEqual(ll._cache, list(cache)) | |
1761 | ||
1762 | ll = LazyList(range(10)) | |
1763 | test(ll, 0, 0, range(1)) | |
1764 | test(ll, 5, 5, range(6)) | |
1765 | test(ll, -3, 7, range(10)) | |
1766 | ||
1767 | ll = LazyList(range(10), reverse=True) | |
1768 | test(ll, -1, 0, range(1)) | |
1769 | test(ll, 3, 6, range(10)) | |
1770 | ||
1771 | ll = LazyList(itertools.count()) | |
1772 | test(ll, 10, 10, range(11)) | |
1773 | ll = reversed(ll) | |
1774 | test(ll, -15, 14, range(15)) | |
1775 | ||
1776 | def test_format_bytes(self): | |
1777 | self.assertEqual(format_bytes(0), '0.00B') | |
1778 | self.assertEqual(format_bytes(1000), '1000.00B') | |
1779 | self.assertEqual(format_bytes(1024), '1.00KiB') | |
1780 | self.assertEqual(format_bytes(1024**2), '1.00MiB') | |
1781 | self.assertEqual(format_bytes(1024**3), '1.00GiB') | |
1782 | self.assertEqual(format_bytes(1024**4), '1.00TiB') | |
1783 | self.assertEqual(format_bytes(1024**5), '1.00PiB') | |
1784 | self.assertEqual(format_bytes(1024**6), '1.00EiB') | |
1785 | self.assertEqual(format_bytes(1024**7), '1.00ZiB') | |
1786 | self.assertEqual(format_bytes(1024**8), '1.00YiB') | |
1787 | self.assertEqual(format_bytes(1024**9), '1024.00YiB') | |
1788 | ||
1789 | def test_hide_login_info(self): | |
1790 | self.assertEqual(Config.hide_login_info(['-u', 'foo', '-p', 'bar']), | |
1791 | ['-u', 'PRIVATE', '-p', 'PRIVATE']) | |
1792 | self.assertEqual(Config.hide_login_info(['-u']), ['-u']) | |
1793 | self.assertEqual(Config.hide_login_info(['-u', 'foo', '-u', 'bar']), | |
1794 | ['-u', 'PRIVATE', '-u', 'PRIVATE']) | |
1795 | self.assertEqual(Config.hide_login_info(['--username=foo']), | |
1796 | ['--username=PRIVATE']) | |
1797 | ||
1798 | def test_locked_file(self): | |
1799 | TEXT = 'test_locked_file\n' | |
1800 | FILE = 'test_locked_file.ytdl' | |
1801 | MODES = 'war' # Order is important | |
1802 | ||
1803 | try: | |
1804 | for lock_mode in MODES: | |
1805 | with locked_file(FILE, lock_mode, False) as f: | |
1806 | if lock_mode == 'r': | |
1807 | self.assertEqual(f.read(), TEXT * 2, 'Wrong file content') | |
1808 | else: | |
1809 | f.write(TEXT) | |
1810 | for test_mode in MODES: | |
1811 | testing_write = test_mode != 'r' | |
1812 | try: | |
1813 | with locked_file(FILE, test_mode, False): | |
1814 | pass | |
1815 | except (BlockingIOError, PermissionError): | |
1816 | if not testing_write: # FIXME | |
1817 | print(f'Known issue: Exclusive lock ({lock_mode}) blocks read access ({test_mode})') | |
1818 | continue | |
1819 | self.assertTrue(testing_write, f'{test_mode} is blocked by {lock_mode}') | |
1820 | else: | |
1821 | self.assertFalse(testing_write, f'{test_mode} is not blocked by {lock_mode}') | |
1822 | finally: | |
1823 | with contextlib.suppress(OSError): | |
1824 | os.remove(FILE) | |
1825 | ||
1826 | def test_determine_file_encoding(self): | |
1827 | self.assertEqual(determine_file_encoding(b''), (None, 0)) | |
1828 | self.assertEqual(determine_file_encoding(b'--verbose -x --audio-format mkv\n'), (None, 0)) | |
1829 | ||
1830 | self.assertEqual(determine_file_encoding(b'\xef\xbb\xbf'), ('utf-8', 3)) | |
1831 | self.assertEqual(determine_file_encoding(b'\x00\x00\xfe\xff'), ('utf-32-be', 4)) | |
1832 | self.assertEqual(determine_file_encoding(b'\xff\xfe'), ('utf-16-le', 2)) | |
1833 | ||
1834 | self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-'), ('cp932', 0)) | |
1835 | self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\n'), ('cp932', 0)) | |
1836 | self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\r\n'), ('cp932', 0)) | |
1837 | ||
1838 | self.assertEqual(determine_file_encoding(b'# coding: utf-8\n--verbose'), ('utf-8', 0)) | |
1839 | self.assertEqual(determine_file_encoding(b'# coding: someencodinghere-12345\n--verbose'), ('someencodinghere-12345', 0)) | |
1840 | ||
1841 | self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932'), ('cp932', 0)) | |
1842 | self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\n'), ('cp932', 0)) | |
1843 | self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\r\n'), ('cp932', 0)) | |
1844 | self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932,euc-jp\r\n'), ('cp932', 0)) | |
1845 | ||
1846 | self.assertEqual(determine_file_encoding( | |
1847 | b'\0\0\0#\0\0\0 \0\0\0c\0\0\0o\0\0\0d\0\0\0i\0\0\0n\0\0\0g\0\0\0:\0\0\0 \0\0\0u\0\0\0t\0\0\0f\0\0\0-\0\0\x003\0\0\x002\0\0\0-\0\0\0b\0\0\0e'), | |
1848 | ('utf-32-be', 0)) | |
1849 | self.assertEqual(determine_file_encoding( | |
1850 | b'#\0 \0c\0o\0d\0i\0n\0g\0:\0 \0u\0t\0f\0-\x001\x006\0-\0l\0e\0'), | |
1851 | ('utf-16-le', 0)) | |
1852 | ||
1853 | ||
1854 | if __name__ == '__main__': | |
1855 | unittest.main() |