]> git.bitcoin.ninja Git - youtube-dl/blob - test/test_utils.py
Merge branch 'sportbox-fix' of https://github.com/maddoger/youtube-dl into maddoger...
[youtube-dl] / test / test_utils.py
1 #!/usr/bin/env python
2 # coding: utf-8
3
4 from __future__ import unicode_literals
5
6 # Allow direct execution
7 import os
8 import sys
9 import unittest
10 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
11
12
13 # Various small unit tests
14 import io
15 import json
16 import xml.etree.ElementTree
17
18 from youtube_dl.utils import (
19     age_restricted,
20     args_to_str,
21     clean_html,
22     DateRange,
23     detect_exe_version,
24     encodeFilename,
25     escape_rfc3986,
26     escape_url,
27     ExtractorError,
28     find_xpath_attr,
29     fix_xml_ampersands,
30     InAdvancePagedList,
31     intlist_to_bytes,
32     is_html,
33     js_to_json,
34     limit_length,
35     OnDemandPagedList,
36     orderedSet,
37     parse_duration,
38     parse_filesize,
39     parse_iso8601,
40     read_batch_urls,
41     sanitize_filename,
42     sanitize_path,
43     prepend_extension,
44     replace_extension,
45     shell_quote,
46     smuggle_url,
47     str_to_int,
48     strip_jsonp,
49     struct_unpack,
50     timeconvert,
51     unescapeHTML,
52     unified_strdate,
53     unsmuggle_url,
54     uppercase_escape,
55     lowercase_escape,
56     url_basename,
57     urlencode_postdata,
58     version_tuple,
59     xpath_with_ns,
60     xpath_text,
61     render_table,
62     match_str,
63     parse_dfxp_time_expr,
64     dfxp2srt,
65 )
66
67
68 class TestUtil(unittest.TestCase):
69     def test_timeconvert(self):
70         self.assertTrue(timeconvert('') is None)
71         self.assertTrue(timeconvert('bougrg') is None)
72
73     def test_sanitize_filename(self):
74         self.assertEqual(sanitize_filename('abc'), 'abc')
75         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
76
77         self.assertEqual(sanitize_filename('123'), '123')
78
79         self.assertEqual('abc_de', sanitize_filename('abc/de'))
80         self.assertFalse('/' in sanitize_filename('abc/de///'))
81
82         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
83         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
84         self.assertEqual('yes no', sanitize_filename('yes? no'))
85         self.assertEqual('this - that', sanitize_filename('this: that'))
86
87         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
88         aumlaut = 'ä'
89         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
90         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
91         self.assertEqual(sanitize_filename(tests), tests)
92
93         self.assertEqual(
94             sanitize_filename('New World record at 0:12:34'),
95             'New World record at 0_12_34')
96
97         self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
98         self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
99         self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
100         self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
101
102         forbidden = '"\0\\/'
103         for fc in forbidden:
104             for fbc in forbidden:
105                 self.assertTrue(fbc not in sanitize_filename(fc))
106
107     def test_sanitize_filename_restricted(self):
108         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
109         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
110
111         self.assertEqual(sanitize_filename('123', restricted=True), '123')
112
113         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
114         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
115
116         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
117         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
118         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
119         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
120
121         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
122         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
123         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
124
125         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
126         for fc in forbidden:
127             for fbc in forbidden:
128                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
129
130         # Handle a common case more neatly
131         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
132         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
133         # .. but make sure the file name is never empty
134         self.assertTrue(sanitize_filename('-', restricted=True) != '')
135         self.assertTrue(sanitize_filename(':', restricted=True) != '')
136
137     def test_sanitize_ids(self):
138         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
139         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
140         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
141
142     def test_sanitize_path(self):
143         if sys.platform != 'win32':
144             return
145
146         self.assertEqual(sanitize_path('abc'), 'abc')
147         self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
148         self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
149         self.assertEqual(sanitize_path('abc|def'), 'abc#def')
150         self.assertEqual(sanitize_path('<>:"|?*'), '#######')
151         self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
152         self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
153
154         self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
155         self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
156
157         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
158         self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
159         self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
160         self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
161
162         self.assertEqual(
163             sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
164             'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
165
166         self.assertEqual(
167             sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
168             'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
169         self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
170         self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
171         self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
172
173         self.assertEqual(sanitize_path('../abc'), '..\\abc')
174         self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
175         self.assertEqual(sanitize_path('./abc'), 'abc')
176         self.assertEqual(sanitize_path('./../abc'), '..\\abc')
177
178     def test_prepend_extension(self):
179         self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
180         self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
181         self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
182         self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
183         self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
184         self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
185
186     def test_replace_extension(self):
187         self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
188         self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
189         self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
190         self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
191         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
192         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
193
194     def test_ordered_set(self):
195         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
196         self.assertEqual(orderedSet([]), [])
197         self.assertEqual(orderedSet([1]), [1])
198         # keep the list ordered
199         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
200
201     def test_unescape_html(self):
202         self.assertEqual(unescapeHTML('%20;'), '%20;')
203         self.assertEqual(unescapeHTML('&#x2F;'), '/')
204         self.assertEqual(unescapeHTML('&#47;'), '/')
205         self.assertEqual(
206             unescapeHTML('&eacute;'), 'é')
207
208     def test_daterange(self):
209         _20century = DateRange("19000101", "20000101")
210         self.assertFalse("17890714" in _20century)
211         _ac = DateRange("00010101")
212         self.assertTrue("19690721" in _ac)
213         _firstmilenium = DateRange(end="10000101")
214         self.assertTrue("07110427" in _firstmilenium)
215
216     def test_unified_dates(self):
217         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
218         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
219         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
220         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
221         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
222         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
223         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
224         self.assertEqual(
225             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
226             '20141126')
227         self.assertEqual(
228             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
229             '20150202')
230         self.assertEqual(unified_strdate('25-09-2014'), '20140925')
231
232     def test_find_xpath_attr(self):
233         testxml = '''<root>
234             <node/>
235             <node x="a"/>
236             <node x="a" y="c" />
237             <node x="b" y="d" />
238         </root>'''
239         doc = xml.etree.ElementTree.fromstring(testxml)
240
241         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
242         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
243         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
244
245     def test_xpath_with_ns(self):
246         testxml = '''<root xmlns:media="http://example.com/">
247             <media:song>
248                 <media:author>The Author</media:author>
249                 <url>http://server.com/download.mp3</url>
250             </media:song>
251         </root>'''
252         doc = xml.etree.ElementTree.fromstring(testxml)
253         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
254         self.assertTrue(find('media:song') is not None)
255         self.assertEqual(find('media:song/media:author').text, 'The Author')
256         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
257
258     def test_xpath_text(self):
259         testxml = '''<root>
260             <div>
261                 <p>Foo</p>
262             </div>
263         </root>'''
264         doc = xml.etree.ElementTree.fromstring(testxml)
265         self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
266         self.assertTrue(xpath_text(doc, 'div/bar') is None)
267         self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
268
269     def test_smuggle_url(self):
270         data = {"ö": "ö", "abc": [3]}
271         url = 'https://foo.bar/baz?x=y#a'
272         smug_url = smuggle_url(url, data)
273         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
274         self.assertEqual(url, unsmug_url)
275         self.assertEqual(data, unsmug_data)
276
277         res_url, res_data = unsmuggle_url(url)
278         self.assertEqual(res_url, url)
279         self.assertEqual(res_data, None)
280
281     def test_shell_quote(self):
282         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
283         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
284
285     def test_str_to_int(self):
286         self.assertEqual(str_to_int('123,456'), 123456)
287         self.assertEqual(str_to_int('123.456'), 123456)
288
289     def test_url_basename(self):
290         self.assertEqual(url_basename('http://foo.de/'), '')
291         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
292         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
293         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
294         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
295         self.assertEqual(
296             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
297             'trailer.mp4')
298
299     def test_parse_duration(self):
300         self.assertEqual(parse_duration(None), None)
301         self.assertEqual(parse_duration(False), None)
302         self.assertEqual(parse_duration('invalid'), None)
303         self.assertEqual(parse_duration('1'), 1)
304         self.assertEqual(parse_duration('1337:12'), 80232)
305         self.assertEqual(parse_duration('9:12:43'), 33163)
306         self.assertEqual(parse_duration('12:00'), 720)
307         self.assertEqual(parse_duration('00:01:01'), 61)
308         self.assertEqual(parse_duration('x:y'), None)
309         self.assertEqual(parse_duration('3h11m53s'), 11513)
310         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
311         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
312         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
313         self.assertEqual(parse_duration('62m45s'), 3765)
314         self.assertEqual(parse_duration('6m59s'), 419)
315         self.assertEqual(parse_duration('49s'), 49)
316         self.assertEqual(parse_duration('0h0m0s'), 0)
317         self.assertEqual(parse_duration('0m0s'), 0)
318         self.assertEqual(parse_duration('0s'), 0)
319         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
320         self.assertEqual(parse_duration('T30M38S'), 1838)
321         self.assertEqual(parse_duration('5 s'), 5)
322         self.assertEqual(parse_duration('3 min'), 180)
323         self.assertEqual(parse_duration('2.5 hours'), 9000)
324         self.assertEqual(parse_duration('02:03:04'), 7384)
325         self.assertEqual(parse_duration('01:02:03:04'), 93784)
326         self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
327
328     def test_fix_xml_ampersands(self):
329         self.assertEqual(
330             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
331         self.assertEqual(
332             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
333             '"&amp;x=y&amp;wrong;&amp;z=a')
334         self.assertEqual(
335             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
336             '&amp;&apos;&gt;&lt;&quot;')
337         self.assertEqual(
338             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
339         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
340
341     def test_paged_list(self):
342         def testPL(size, pagesize, sliceargs, expected):
343             def get_page(pagenum):
344                 firstid = pagenum * pagesize
345                 upto = min(size, pagenum * pagesize + pagesize)
346                 for i in range(firstid, upto):
347                     yield i
348
349             pl = OnDemandPagedList(get_page, pagesize)
350             got = pl.getslice(*sliceargs)
351             self.assertEqual(got, expected)
352
353             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
354             got = iapl.getslice(*sliceargs)
355             self.assertEqual(got, expected)
356
357         testPL(5, 2, (), [0, 1, 2, 3, 4])
358         testPL(5, 2, (1,), [1, 2, 3, 4])
359         testPL(5, 2, (2,), [2, 3, 4])
360         testPL(5, 2, (4,), [4])
361         testPL(5, 2, (0, 3), [0, 1, 2])
362         testPL(5, 2, (1, 4), [1, 2, 3])
363         testPL(5, 2, (2, 99), [2, 3, 4])
364         testPL(5, 2, (20, 99), [])
365
366     def test_struct_unpack(self):
367         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
368
369     def test_read_batch_urls(self):
370         f = io.StringIO('''\xef\xbb\xbf foo
371             bar\r
372             baz
373             # More after this line\r
374             ; or after this
375             bam''')
376         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
377
378     def test_urlencode_postdata(self):
379         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
380         self.assertTrue(isinstance(data, bytes))
381
382     def test_parse_iso8601(self):
383         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
384         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
385         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
386         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
387
388     def test_strip_jsonp(self):
389         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
390         d = json.loads(stripped)
391         self.assertEqual(d, [{"id": "532cb", "x": 3}])
392
393         stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
394         d = json.loads(stripped)
395         self.assertEqual(d, {'STATUS': 'OK'})
396
397     def test_uppercase_escape(self):
398         self.assertEqual(uppercase_escape('aä'), 'aä')
399         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
400
401     def test_lowercase_escape(self):
402         self.assertEqual(lowercase_escape('aä'), 'aä')
403         self.assertEqual(lowercase_escape('\\u0026'), '&')
404
405     def test_limit_length(self):
406         self.assertEqual(limit_length(None, 12), None)
407         self.assertEqual(limit_length('foo', 12), 'foo')
408         self.assertTrue(
409             limit_length('foo bar baz asd', 12).startswith('foo bar'))
410         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
411
412     def test_escape_rfc3986(self):
413         reserved = "!*'();:@&=+$,/?#[]"
414         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
415         self.assertEqual(escape_rfc3986(reserved), reserved)
416         self.assertEqual(escape_rfc3986(unreserved), unreserved)
417         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
418         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
419         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
420         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
421
422     def test_escape_url(self):
423         self.assertEqual(
424             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
425             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
426         )
427         self.assertEqual(
428             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
429             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
430         )
431         self.assertEqual(
432             escape_url('http://тест.рф/фрагмент'),
433             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
434         )
435         self.assertEqual(
436             escape_url('http://тест.рф/абв?абв=абв#абв'),
437             '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'
438         )
439         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
440
441     def test_js_to_json_realworld(self):
442         inp = '''{
443             'clip':{'provider':'pseudo'}
444         }'''
445         self.assertEqual(js_to_json(inp), '''{
446             "clip":{"provider":"pseudo"}
447         }''')
448         json.loads(js_to_json(inp))
449
450         inp = '''{
451             'playlist':[{'controls':{'all':null}}]
452         }'''
453         self.assertEqual(js_to_json(inp), '''{
454             "playlist":[{"controls":{"all":null}}]
455         }''')
456
457         inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
458         json_code = js_to_json(inp)
459         self.assertEqual(json.loads(json_code), json.loads(inp))
460
461     def test_js_to_json_edgecases(self):
462         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
463         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
464
465         on = js_to_json('{"abc": true}')
466         self.assertEqual(json.loads(on), {'abc': True})
467
468         # Ignore JavaScript code as well
469         on = js_to_json('''{
470             "x": 1,
471             y: "a",
472             z: some.code
473         }''')
474         d = json.loads(on)
475         self.assertEqual(d['x'], 1)
476         self.assertEqual(d['y'], 'a')
477
478         on = js_to_json('["abc", "def",]')
479         self.assertEqual(json.loads(on), ['abc', 'def'])
480
481         on = js_to_json('{"abc": "def",}')
482         self.assertEqual(json.loads(on), {'abc': 'def'})
483
484     def test_clean_html(self):
485         self.assertEqual(clean_html('a:\nb'), 'a: b')
486         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
487
488     def test_intlist_to_bytes(self):
489         self.assertEqual(
490             intlist_to_bytes([0, 1, 127, 128, 255]),
491             b'\x00\x01\x7f\x80\xff')
492
493     def test_args_to_str(self):
494         self.assertEqual(
495             args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
496             'foo ba/r -baz \'2 be\' \'\''
497         )
498
499     def test_parse_filesize(self):
500         self.assertEqual(parse_filesize(None), None)
501         self.assertEqual(parse_filesize(''), None)
502         self.assertEqual(parse_filesize('91 B'), 91)
503         self.assertEqual(parse_filesize('foobar'), None)
504         self.assertEqual(parse_filesize('2 MiB'), 2097152)
505         self.assertEqual(parse_filesize('5 GB'), 5000000000)
506         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
507         self.assertEqual(parse_filesize('1,24 KB'), 1240)
508
509     def test_version_tuple(self):
510         self.assertEqual(version_tuple('1'), (1,))
511         self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
512         self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
513
514     def test_detect_exe_version(self):
515         self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
516 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
517 configuration: --prefix=/usr --extra-'''), '1.2.1')
518         self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
519 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
520         self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
521 Trying to open render node...
522 Success at /dev/dri/renderD128.
523 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
524
525     def test_age_restricted(self):
526         self.assertFalse(age_restricted(None, 10))  # unrestricted content
527         self.assertFalse(age_restricted(1, None))  # unrestricted policy
528         self.assertFalse(age_restricted(8, 10))
529         self.assertTrue(age_restricted(18, 14))
530         self.assertFalse(age_restricted(18, 18))
531
532     def test_is_html(self):
533         self.assertFalse(is_html(b'\x49\x44\x43<html'))
534         self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
535         self.assertTrue(is_html(  # UTF-8 with BOM
536             b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
537         self.assertTrue(is_html(  # UTF-16-LE
538             b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
539         ))
540         self.assertTrue(is_html(  # UTF-16-BE
541             b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
542         ))
543         self.assertTrue(is_html(  # UTF-32-BE
544             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'))
545         self.assertTrue(is_html(  # UTF-32-LE
546             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'))
547
548     def test_render_table(self):
549         self.assertEqual(
550             render_table(
551                 ['a', 'bcd'],
552                 [[123, 4], [9999, 51]]),
553             'a    bcd\n'
554             '123  4\n'
555             '9999 51')
556
557     def test_match_str(self):
558         self.assertRaises(ValueError, match_str, 'xy>foobar', {})
559         self.assertFalse(match_str('xy', {'x': 1200}))
560         self.assertTrue(match_str('!xy', {'x': 1200}))
561         self.assertTrue(match_str('x', {'x': 1200}))
562         self.assertFalse(match_str('!x', {'x': 1200}))
563         self.assertTrue(match_str('x', {'x': 0}))
564         self.assertFalse(match_str('x>0', {'x': 0}))
565         self.assertFalse(match_str('x>0', {}))
566         self.assertTrue(match_str('x>?0', {}))
567         self.assertTrue(match_str('x>1K', {'x': 1200}))
568         self.assertFalse(match_str('x>2K', {'x': 1200}))
569         self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
570         self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
571         self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
572         self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
573         self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
574         self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
575         self.assertFalse(match_str(
576             'like_count > 100 & dislike_count <? 50 & description',
577             {'like_count': 90, 'description': 'foo'}))
578         self.assertTrue(match_str(
579             'like_count > 100 & dislike_count <? 50 & description',
580             {'like_count': 190, 'description': 'foo'}))
581         self.assertFalse(match_str(
582             'like_count > 100 & dislike_count <? 50 & description',
583             {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
584         self.assertFalse(match_str(
585             'like_count > 100 & dislike_count <? 50 & description',
586             {'like_count': 190, 'dislike_count': 10}))
587
588     def test_parse_dfxp_time_expr(self):
589         self.assertEqual(parse_dfxp_time_expr(None), 0.0)
590         self.assertEqual(parse_dfxp_time_expr(''), 0.0)
591         self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
592         self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
593         self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
594         self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
595
596     def test_dfxp2srt(self):
597         dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
598             <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
599             <body>
600                 <div xml:lang="en">
601                     <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
602                     <p begin="1" end="2">第二行<br/>♪♪</p>
603                     <p begin="2" dur="1"><span>Third<br/>Line</span></p>
604                 </div>
605             </body>
606             </tt>'''
607         srt_data = '''1
608 00:00:00,000 --> 00:00:01,000
609 The following line contains Chinese characters and special symbols
610
611 2
612 00:00:01,000 --> 00:00:02,000
613 第二行
614 ♪♪
615
616 3
617 00:00:02,000 --> 00:00:03,000
618 Third
619 Line
620
621 '''
622         self.assertEqual(dfxp2srt(dfxp_data), srt_data)
623
624
625 if __name__ == '__main__':
626     unittest.main()