jfr.im git - yt-dlp.git/blame_incremental

... / ...

Commit	Line	Data
	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	clean_html,
	22	DateRange,
	23	detect_exe_version,
	24	determine_ext,
	25	encodeFilename,
	26	escape_rfc3986,
	27	escape_url,
	28	ExtractorError,
	29	find_xpath_attr,
	30	fix_xml_ampersands,
	31	InAdvancePagedList,
	32	intlist_to_bytes,
	33	is_html,
	34	js_to_json,
	35	limit_length,
	36	OnDemandPagedList,
	37	orderedSet,
	38	parse_duration,
	39	parse_filesize,
	40	parse_iso8601,
	41	read_batch_urls,
	42	sanitize_filename,
	43	sanitize_path,
	44	prepend_extension,
	45	replace_extension,
	46	remove_quotes,
	47	shell_quote,
	48	smuggle_url,
	49	str_to_int,
	50	strip_jsonp,
	51	struct_unpack,
	52	timeconvert,
	53	unescapeHTML,
	54	unified_strdate,
	55	unsmuggle_url,
	56	uppercase_escape,
	57	lowercase_escape,
	58	url_basename,
	59	urlencode_postdata,
	60	version_tuple,
	61	xpath_with_ns,
	62	xpath_element,
	63	xpath_text,
	64	xpath_attr,
	65	render_table,
	66	match_str,
	67	parse_dfxp_time_expr,
	68	dfxp2srt,
	69	cli_option,
	70	cli_valueless_option,
	71	cli_bool_option,
	72	)
	73	from youtube_dl.compat import (
	74	compat_etree_fromstring,
	75	)
	76
	77
	78	class TestUtil(unittest.TestCase):
	79	def test_timeconvert(self):
	80	self.assertTrue(timeconvert('') is None)
	81	self.assertTrue(timeconvert('bougrg') is None)
	82
	83	def test_sanitize_filename(self):
	84	self.assertEqual(sanitize_filename('abc'), 'abc')
	85	self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
	86
	87	self.assertEqual(sanitize_filename('123'), '123')
	88
	89	self.assertEqual('abc_de', sanitize_filename('abc/de'))
	90	self.assertFalse('/' in sanitize_filename('abc/de///'))
	91
	92	self.assertEqual('abc_de', sanitize_filename('abc/<>\\*\|de'))
	93	self.assertEqual('xxx', sanitize_filename('xxx/<>\\*\|'))
	94	self.assertEqual('yes no', sanitize_filename('yes? no'))
	95	self.assertEqual('this - that', sanitize_filename('this: that'))
	96
	97	self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
	98	aumlaut = 'ä'
	99	self.assertEqual(sanitize_filename(aumlaut), aumlaut)
	100	tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
	101	self.assertEqual(sanitize_filename(tests), tests)
	102
	103	self.assertEqual(
	104	sanitize_filename('New World record at 0:12:34'),
	105	'New World record at 0_12_34')
	106
	107	self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
	108	self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
	109	self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
	110	self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
	111
	112	forbidden = '"\0\\/'
	113	for fc in forbidden:
	114	for fbc in forbidden:
	115	self.assertTrue(fbc not in sanitize_filename(fc))
	116
	117	def test_sanitize_filename_restricted(self):
	118	self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
	119	self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
	120
	121	self.assertEqual(sanitize_filename('123', restricted=True), '123')
	122
	123	self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
	124	self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
	125
	126	self.assertEqual('abc_de', sanitize_filename('abc/<>\\*\|de', restricted=True))
	127	self.assertEqual('xxx', sanitize_filename('xxx/<>\\*\|', restricted=True))
	128	self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
	129	self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
	130
	131	tests = 'a\xe4b\u4e2d\u56fd\u7684c'
	132	self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
	133	self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
	134
	135	forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
	136	for fc in forbidden:
	137	for fbc in forbidden:
	138	self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
	139
	140	# Handle a common case more neatly
	141	self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
	142	self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
	143	# .. but make sure the file name is never empty
	144	self.assertTrue(sanitize_filename('-', restricted=True) != '')
	145	self.assertTrue(sanitize_filename(':', restricted=True) != '')
	146
	147	def test_sanitize_ids(self):
	148	self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
	149	self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
	150	self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
	151
	152	def test_sanitize_path(self):
	153	if sys.platform != 'win32':
	154	return
	155
	156	self.assertEqual(sanitize_path('abc'), 'abc')
	157	self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
	158	self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
	159	self.assertEqual(sanitize_path('abc\|def'), 'abc#def')
	160	self.assertEqual(sanitize_path('<>:"\|?*'), '#######')
	161	self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
	162	self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
	163
	164	self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
	165	self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
	166
	167	self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
	168	self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
	169	self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
	170	self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
	171
	172	self.assertEqual(
	173	sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
	174	'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
	175
	176	self.assertEqual(
	177	sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
	178	'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
	179	self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
	180	self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
	181	self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
	182
	183	self.assertEqual(sanitize_path('../abc'), '..\\abc')
	184	self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
	185	self.assertEqual(sanitize_path('./abc'), 'abc')
	186	self.assertEqual(sanitize_path('./../abc'), '..\\abc')
	187
	188	def test_prepend_extension(self):
	189	self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
	190	self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
	191	self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
	192	self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
	193	self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
	194	self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
	195
	196	def test_replace_extension(self):
	197	self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
	198	self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
	199	self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
	200	self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
	201	self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
	202	self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
	203
	204	def test_remove_quotes(self):
	205	self.assertEqual(remove_quotes(None), None)
	206	self.assertEqual(remove_quotes('"'), '"')
	207	self.assertEqual(remove_quotes("'"), "'")
	208	self.assertEqual(remove_quotes(';'), ';')
	209	self.assertEqual(remove_quotes('";'), '";')
	210	self.assertEqual(remove_quotes('""'), '')
	211	self.assertEqual(remove_quotes('";"'), ';')
	212
	213	def test_ordered_set(self):
	214	self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
	215	self.assertEqual(orderedSet([]), [])
	216	self.assertEqual(orderedSet([1]), [1])
	217	# keep the list ordered
	218	self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
	219
	220	def test_unescape_html(self):
	221	self.assertEqual(unescapeHTML('%20;'), '%20;')
	222	self.assertEqual(unescapeHTML('/'), '/')
	223	self.assertEqual(unescapeHTML('/'), '/')
	224	self.assertEqual(unescapeHTML('é'), 'é')
	225	self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
	226
	227	def test_daterange(self):
	228	_20century = DateRange("19000101", "20000101")
	229	self.assertFalse("17890714" in _20century)
	230	_ac = DateRange("00010101")
	231	self.assertTrue("19690721" in _ac)
	232	_firstmilenium = DateRange(end="10000101")
	233	self.assertTrue("07110427" in _firstmilenium)
	234
	235	def test_unified_dates(self):
	236	self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
	237	self.assertEqual(unified_strdate('8/7/2009'), '20090708')
	238	self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
	239	self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
	240	self.assertEqual(unified_strdate('1968 12 10'), '19681210')
	241	self.assertEqual(unified_strdate('1968-12-10'), '19681210')
	242	self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
	243	self.assertEqual(
	244	unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
	245	'20141126')
	246	self.assertEqual(
	247	unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
	248	'20150202')
	249	self.assertEqual(unified_strdate('25-09-2014'), '20140925')
	250	self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
	251
	252	def test_determine_ext(self):
	253	self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
	254	self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
	255	self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
	256	self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
	257	self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
	258
	259	def test_find_xpath_attr(self):
	260	testxml = '''<root>
	261	<node/>
	262	<node x="a"/>
	263	<node x="a" y="c" />
	264	<node x="b" y="d" />
	265	<node x="" />
	266	</root>'''
	267	doc = compat_etree_fromstring(testxml)
	268
	269	self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
	270	self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
	271	self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
	272	self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
	273	self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
	274	self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
	275	self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
	276	self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
	277	self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
	278	self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
	279	self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
	280
	281	def test_xpath_with_ns(self):
	282	testxml = '''<root xmlns:media="http://example.com/">
	283	<media:song>
	284	<media:author>The Author</media:author>
	285	<url>http://server.com/download.mp3</url>
	286	</media:song>
	287	</root>'''
	288	doc = compat_etree_fromstring(testxml)
	289	find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
	290	self.assertTrue(find('media:song') is not None)
	291	self.assertEqual(find('media:song/media:author').text, 'The Author')
	292	self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
	293
	294	def test_xpath_element(self):
	295	doc = xml.etree.ElementTree.Element('root')
	296	div = xml.etree.ElementTree.SubElement(doc, 'div')
	297	p = xml.etree.ElementTree.SubElement(div, 'p')
	298	p.text = 'Foo'
	299	self.assertEqual(xpath_element(doc, 'div/p'), p)
	300	self.assertEqual(xpath_element(doc, ['div/p']), p)
	301	self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
	302	self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
	303	self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
	304	self.assertTrue(xpath_element(doc, 'div/bar') is None)
	305	self.assertTrue(xpath_element(doc, ['div/bar']) is None)
	306	self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
	307	self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
	308	self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
	309	self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
	310
	311	def test_xpath_text(self):
	312	testxml = '''<root>
	313	<div>
	314	<p>Foo</p>
	315	</div>
	316	</root>'''
	317	doc = compat_etree_fromstring(testxml)
	318	self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
	319	self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
	320	self.assertTrue(xpath_text(doc, 'div/bar') is None)
	321	self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
	322
	323	def test_xpath_attr(self):
	324	testxml = '''<root>
	325	<div>
	326	<p x="a">Foo</p>
	327	</div>
	328	</root>'''
	329	doc = compat_etree_fromstring(testxml)
	330	self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
	331	self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
	332	self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
	333	self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
	334	self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
	335	self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
	336	self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
	337
	338	def test_smuggle_url(self):
	339	data = {"ö": "ö", "abc": [3]}
	340	url = 'https://foo.bar/baz?x=y#a'
	341	smug_url = smuggle_url(url, data)
	342	unsmug_url, unsmug_data = unsmuggle_url(smug_url)
	343	self.assertEqual(url, unsmug_url)
	344	self.assertEqual(data, unsmug_data)
	345
	346	res_url, res_data = unsmuggle_url(url)
	347	self.assertEqual(res_url, url)
	348	self.assertEqual(res_data, None)
	349
	350	def test_shell_quote(self):
	351	args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
	352	self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
	353
	354	def test_str_to_int(self):
	355	self.assertEqual(str_to_int('123,456'), 123456)
	356	self.assertEqual(str_to_int('123.456'), 123456)
	357
	358	def test_url_basename(self):
	359	self.assertEqual(url_basename('http://foo.de/'), '')
	360	self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
	361	self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
	362	self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
	363	self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
	364	self.assertEqual(
	365	url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
	366	'trailer.mp4')
	367
	368	def test_parse_duration(self):
	369	self.assertEqual(parse_duration(None), None)
	370	self.assertEqual(parse_duration(False), None)
	371	self.assertEqual(parse_duration('invalid'), None)
	372	self.assertEqual(parse_duration('1'), 1)
	373	self.assertEqual(parse_duration('1337:12'), 80232)
	374	self.assertEqual(parse_duration('9:12:43'), 33163)
	375	self.assertEqual(parse_duration('12:00'), 720)
	376	self.assertEqual(parse_duration('00:01:01'), 61)
	377	self.assertEqual(parse_duration('x:y'), None)
	378	self.assertEqual(parse_duration('3h11m53s'), 11513)
	379	self.assertEqual(parse_duration('3h 11m 53s'), 11513)
	380	self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
	381	self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
	382	self.assertEqual(parse_duration('62m45s'), 3765)
	383	self.assertEqual(parse_duration('6m59s'), 419)
	384	self.assertEqual(parse_duration('49s'), 49)
	385	self.assertEqual(parse_duration('0h0m0s'), 0)
	386	self.assertEqual(parse_duration('0m0s'), 0)
	387	self.assertEqual(parse_duration('0s'), 0)
	388	self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
	389	self.assertEqual(parse_duration('T30M38S'), 1838)
	390	self.assertEqual(parse_duration('5 s'), 5)
	391	self.assertEqual(parse_duration('3 min'), 180)
	392	self.assertEqual(parse_duration('2.5 hours'), 9000)
	393	self.assertEqual(parse_duration('02:03:04'), 7384)
	394	self.assertEqual(parse_duration('01:02:03:04'), 93784)
	395	self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
	396	self.assertEqual(parse_duration('87 Min.'), 5220)
	397
	398	def test_fix_xml_ampersands(self):
	399	self.assertEqual(
	400	fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
	401	self.assertEqual(
	402	fix_xml_ampersands('"&x=y&wrong;&z=a'),
	403	'"&x=y&wrong;&z=a')
	404	self.assertEqual(
	405	fix_xml_ampersands('&'><"'),
	406	'&'><"')
	407	self.assertEqual(
	408	fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
	409	self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
	410
	411	def test_paged_list(self):
	412	def testPL(size, pagesize, sliceargs, expected):
	413	def get_page(pagenum):
	414	firstid = pagenum * pagesize
	415	upto = min(size, pagenum * pagesize + pagesize)
	416	for i in range(firstid, upto):
	417	yield i
	418
	419	pl = OnDemandPagedList(get_page, pagesize)
	420	got = pl.getslice(*sliceargs)
	421	self.assertEqual(got, expected)
	422
	423	iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
	424	got = iapl.getslice(*sliceargs)
	425	self.assertEqual(got, expected)
	426
	427	testPL(5, 2, (), [0, 1, 2, 3, 4])
	428	testPL(5, 2, (1,), [1, 2, 3, 4])
	429	testPL(5, 2, (2,), [2, 3, 4])
	430	testPL(5, 2, (4,), [4])
	431	testPL(5, 2, (0, 3), [0, 1, 2])
	432	testPL(5, 2, (1, 4), [1, 2, 3])
	433	testPL(5, 2, (2, 99), [2, 3, 4])
	434	testPL(5, 2, (20, 99), [])
	435
	436	def test_struct_unpack(self):
	437	self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
	438
	439	def test_read_batch_urls(self):
	440	f = io.StringIO('''\xef\xbb\xbf foo
	441	bar\r
	442	baz
	443	# More after this line\r
	444	; or after this
	445	bam''')
	446	self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
	447
	448	def test_urlencode_postdata(self):
	449	data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
	450	self.assertTrue(isinstance(data, bytes))
	451
	452	def test_parse_iso8601(self):
	453	self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
	454	self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
	455	self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
	456	self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
	457	self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
	458	self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
	459
	460	def test_strip_jsonp(self):
	461	stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
	462	d = json.loads(stripped)
	463	self.assertEqual(d, [{"id": "532cb", "x": 3}])
	464
	465	stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
	466	d = json.loads(stripped)
	467	self.assertEqual(d, {'STATUS': 'OK'})
	468
	469	def test_uppercase_escape(self):
	470	self.assertEqual(uppercase_escape('aä'), 'aä')
	471	self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
	472
	473	def test_lowercase_escape(self):
	474	self.assertEqual(lowercase_escape('aä'), 'aä')
	475	self.assertEqual(lowercase_escape('\\u0026'), '&')
	476
	477	def test_limit_length(self):
	478	self.assertEqual(limit_length(None, 12), None)
	479	self.assertEqual(limit_length('foo', 12), 'foo')
	480	self.assertTrue(
	481	limit_length('foo bar baz asd', 12).startswith('foo bar'))
	482	self.assertTrue('...' in limit_length('foo bar baz asd', 12))
	483
	484	def test_escape_rfc3986(self):
	485	reserved = "!*'();:@&=+$,/?#[]"
	486	unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
	487	self.assertEqual(escape_rfc3986(reserved), reserved)
	488	self.assertEqual(escape_rfc3986(unreserved), unreserved)
	489	self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
	490	self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
	491	self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
	492	self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
	493
	494	def test_escape_url(self):
	495	self.assertEqual(
	496	escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
	497	'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
	498	)
	499	self.assertEqual(
	500	escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
	501	'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
	502	)
	503	self.assertEqual(
	504	escape_url('http://тест.рф/фрагмент'),
	505	'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
	506	)
	507	self.assertEqual(
	508	escape_url('http://тест.рф/абв?абв=абв#абв'),
	509	'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
	510	)
	511	self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
	512
	513	def test_js_to_json_realworld(self):
	514	inp = '''{
	515	'clip':{'provider':'pseudo'}
	516	}'''
	517	self.assertEqual(js_to_json(inp), '''{
	518	"clip":{"provider":"pseudo"}
	519	}''')
	520	json.loads(js_to_json(inp))
	521
	522	inp = '''{
	523	'playlist':[{'controls':{'all':null}}]
	524	}'''
	525	self.assertEqual(js_to_json(inp), '''{
	526	"playlist":[{"controls":{"all":null}}]
	527	}''')
	528
	529	inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
	530	self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
	531
	532	inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
	533	json_code = js_to_json(inp)
	534	self.assertEqual(json.loads(json_code), json.loads(inp))
	535
	536	def test_js_to_json_edgecases(self):
	537	on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
	538	self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
	539
	540	on = js_to_json('{"abc": true}')
	541	self.assertEqual(json.loads(on), {'abc': True})
	542
	543	# Ignore JavaScript code as well
	544	on = js_to_json('''{
	545	"x": 1,
	546	y: "a",
	547	z: some.code
	548	}''')
	549	d = json.loads(on)
	550	self.assertEqual(d['x'], 1)
	551	self.assertEqual(d['y'], 'a')
	552
	553	on = js_to_json('["abc", "def",]')
	554	self.assertEqual(json.loads(on), ['abc', 'def'])
	555
	556	on = js_to_json('{"abc": "def",}')
	557	self.assertEqual(json.loads(on), {'abc': 'def'})
	558
	559	def test_clean_html(self):
	560	self.assertEqual(clean_html('a:\nb'), 'a: b')
	561	self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
	562
	563	def test_intlist_to_bytes(self):
	564	self.assertEqual(
	565	intlist_to_bytes([0, 1, 127, 128, 255]),
	566	b'\x00\x01\x7f\x80\xff')
	567
	568	def test_args_to_str(self):
	569	self.assertEqual(
	570	args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
	571	'foo ba/r -baz \'2 be\' \'\''
	572	)
	573
	574	def test_parse_filesize(self):
	575	self.assertEqual(parse_filesize(None), None)
	576	self.assertEqual(parse_filesize(''), None)
	577	self.assertEqual(parse_filesize('91 B'), 91)
	578	self.assertEqual(parse_filesize('foobar'), None)
	579	self.assertEqual(parse_filesize('2 MiB'), 2097152)
	580	self.assertEqual(parse_filesize('5 GB'), 5000000000)
	581	self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
	582	self.assertEqual(parse_filesize('1,24 KB'), 1240)
	583
	584	def test_version_tuple(self):
	585	self.assertEqual(version_tuple('1'), (1,))
	586	self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
	587	self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
	588
	589	def test_detect_exe_version(self):
	590	self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
	591	built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
	592	configuration: --prefix=/usr --extra-'''), '1.2.1')
	593	self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
	594	built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
	595	self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
	596	Trying to open render node...
	597	Success at /dev/dri/renderD128.
	598	ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
	599
	600	def test_age_restricted(self):
	601	self.assertFalse(age_restricted(None, 10)) # unrestricted content
	602	self.assertFalse(age_restricted(1, None)) # unrestricted policy
	603	self.assertFalse(age_restricted(8, 10))
	604	self.assertTrue(age_restricted(18, 14))
	605	self.assertFalse(age_restricted(18, 18))
	606
	607	def test_is_html(self):
	608	self.assertFalse(is_html(b'\x49\x44\x43<html'))
	609	self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
	610	self.assertTrue(is_html( # UTF-8 with BOM
	611	b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
	612	self.assertTrue(is_html( # UTF-16-LE
	613	b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
	614	))
	615	self.assertTrue(is_html( # UTF-16-BE
	616	b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
	617	))
	618	self.assertTrue(is_html( # UTF-32-BE
	619	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'))
	620	self.assertTrue(is_html( # UTF-32-LE
	621	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'))
	622
	623	def test_render_table(self):
	624	self.assertEqual(
	625	render_table(
	626	['a', 'bcd'],
	627	[[123, 4], [9999, 51]]),
	628	'a bcd\n'
	629	'123 4\n'
	630	'9999 51')
	631
	632	def test_match_str(self):
	633	self.assertRaises(ValueError, match_str, 'xy>foobar', {})
	634	self.assertFalse(match_str('xy', {'x': 1200}))
	635	self.assertTrue(match_str('!xy', {'x': 1200}))
	636	self.assertTrue(match_str('x', {'x': 1200}))
	637	self.assertFalse(match_str('!x', {'x': 1200}))
	638	self.assertTrue(match_str('x', {'x': 0}))
	639	self.assertFalse(match_str('x>0', {'x': 0}))
	640	self.assertFalse(match_str('x>0', {}))
	641	self.assertTrue(match_str('x>?0', {}))
	642	self.assertTrue(match_str('x>1K', {'x': 1200}))
	643	self.assertFalse(match_str('x>2K', {'x': 1200}))
	644	self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
	645	self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
	646	self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
	647	self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
	648	self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
	649	self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
	650	self.assertFalse(match_str(
	651	'like_count > 100 & dislike_count <? 50 & description',
	652	{'like_count': 90, 'description': 'foo'}))
	653	self.assertTrue(match_str(
	654	'like_count > 100 & dislike_count <? 50 & description',
	655	{'like_count': 190, 'description': 'foo'}))
	656	self.assertFalse(match_str(
	657	'like_count > 100 & dislike_count <? 50 & description',
	658	{'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
	659	self.assertFalse(match_str(
	660	'like_count > 100 & dislike_count <? 50 & description',
	661	{'like_count': 190, 'dislike_count': 10}))
	662
	663	def test_parse_dfxp_time_expr(self):
	664	self.assertEqual(parse_dfxp_time_expr(None), None)
	665	self.assertEqual(parse_dfxp_time_expr(''), None)
	666	self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
	667	self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
	668	self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
	669	self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
	670
	671	def test_dfxp2srt(self):
	672	dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
	673	<tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
	674	<body>
	675	<div xml:lang="en">
	676	<p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
	677	<p begin="1" end="2">第二行<br/>♪♪</p>
	678	<p begin="2" dur="1"><span>Third<br/>Line</span></p>
	679	<p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
	680	<p begin="-1" end="-1">Ignore, two</p>
	681	<p begin="3" dur="-1">Ignored, three</p>
	682	</div>
	683	</body>
	684	</tt>'''
	685	srt_data = '''1
	686	00:00:00,000 --> 00:00:01,000
	687	The following line contains Chinese characters and special symbols
	688
	689	2
	690	00:00:01,000 --> 00:00:02,000
	691	第二行
	692	♪♪
	693
	694	3
	695	00:00:02,000 --> 00:00:03,000
	696	Third
	697	Line
	698
	699	'''
	700	self.assertEqual(dfxp2srt(dfxp_data), srt_data)
	701
	702	dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
	703	<tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
	704	<body>
	705	<div xml:lang="en">
	706	<p begin="0" end="1">The first line</p>
	707	</div>
	708	</body>
	709	</tt>'''
	710	srt_data = '''1
	711	00:00:00,000 --> 00:00:01,000
	712	The first line
	713
	714	'''
	715	self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
	716
	717	def test_cli_option(self):
	718	self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
	719	self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
	720	self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
	721
	722	def test_cli_valueless_option(self):
	723	self.assertEqual(cli_valueless_option(
	724	{'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
	725	self.assertEqual(cli_valueless_option(
	726	{'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
	727	self.assertEqual(cli_valueless_option(
	728	{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
	729	self.assertEqual(cli_valueless_option(
	730	{'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
	731	self.assertEqual(cli_valueless_option(
	732	{'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
	733	self.assertEqual(cli_valueless_option(
	734	{'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
	735
	736	def test_cli_bool_option(self):
	737	self.assertEqual(
	738	cli_bool_option(
	739	{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
	740	['--no-check-certificate', 'true'])
	741	self.assertEqual(
	742	cli_bool_option(
	743	{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
	744	['--no-check-certificate=true'])
	745	self.assertEqual(
	746	cli_bool_option(
	747	{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
	748	['--check-certificate', 'false'])
	749	self.assertEqual(
	750	cli_bool_option(
	751	{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
	752	['--check-certificate=false'])
	753	self.assertEqual(
	754	cli_bool_option(
	755	{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
	756	['--check-certificate', 'true'])
	757	self.assertEqual(
	758	cli_bool_option(
	759	{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
	760	['--check-certificate=true'])
	761
	762
	763	if __name__ == '__main__':
	764	unittest.main()