]> git.bitcoin.ninja Git - youtube-dl/blob - test/test_utils.py
[test_compat] Ignore unicode_literals
[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     DateRange,
20     encodeFilename,
21     find_xpath_attr,
22     fix_xml_ampersands,
23     get_meta_content,
24     orderedSet,
25     OnDemandPagedList,
26     InAdvancePagedList,
27     parse_duration,
28     read_batch_urls,
29     sanitize_filename,
30     shell_quote,
31     smuggle_url,
32     str_to_int,
33     struct_unpack,
34     timeconvert,
35     unescapeHTML,
36     unified_strdate,
37     unsmuggle_url,
38     url_basename,
39     urlencode_postdata,
40     xpath_with_ns,
41     parse_iso8601,
42     strip_jsonp,
43     uppercase_escape,
44     limit_length,
45     escape_rfc3986,
46     escape_url,
47     js_to_json,
48     get_filesystem_encoding,
49 )
50
51
52 class TestUtil(unittest.TestCase):
53     def test_timeconvert(self):
54         self.assertTrue(timeconvert('') is None)
55         self.assertTrue(timeconvert('bougrg') is None)
56
57     def test_sanitize_filename(self):
58         self.assertEqual(sanitize_filename('abc'), 'abc')
59         self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
60
61         self.assertEqual(sanitize_filename('123'), '123')
62
63         self.assertEqual('abc_de', sanitize_filename('abc/de'))
64         self.assertFalse('/' in sanitize_filename('abc/de///'))
65
66         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
67         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
68         self.assertEqual('yes no', sanitize_filename('yes? no'))
69         self.assertEqual('this - that', sanitize_filename('this: that'))
70
71         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
72         aumlaut = 'ä'
73         self.assertEqual(sanitize_filename(aumlaut), aumlaut)
74         tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
75         self.assertEqual(sanitize_filename(tests), tests)
76
77         forbidden = '"\0\\/'
78         for fc in forbidden:
79             for fbc in forbidden:
80                 self.assertTrue(fbc not in sanitize_filename(fc))
81
82     def test_sanitize_filename_restricted(self):
83         self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
84         self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
85
86         self.assertEqual(sanitize_filename('123', restricted=True), '123')
87
88         self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
89         self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
90
91         self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
92         self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
93         self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
94         self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
95
96         tests = 'a\xe4b\u4e2d\u56fd\u7684c'
97         self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
98         self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename
99
100         forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
101         for fc in forbidden:
102             for fbc in forbidden:
103                 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
104
105         # Handle a common case more neatly
106         self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
107         self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
108         # .. but make sure the file name is never empty
109         self.assertTrue(sanitize_filename('-', restricted=True) != '')
110         self.assertTrue(sanitize_filename(':', restricted=True) != '')
111
112     def test_sanitize_ids(self):
113         self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
114         self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
115         self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
116
117     def test_ordered_set(self):
118         self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
119         self.assertEqual(orderedSet([]), [])
120         self.assertEqual(orderedSet([1]), [1])
121         #keep the list ordered
122         self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
123
124     def test_unescape_html(self):
125         self.assertEqual(unescapeHTML('%20;'), '%20;')
126         self.assertEqual(
127             unescapeHTML('&eacute;'), 'é')
128         
129     def test_daterange(self):
130         _20century = DateRange("19000101","20000101")
131         self.assertFalse("17890714" in _20century)
132         _ac = DateRange("00010101")
133         self.assertTrue("19690721" in _ac)
134         _firstmilenium = DateRange(end="10000101")
135         self.assertTrue("07110427" in _firstmilenium)
136
137     def test_unified_dates(self):
138         self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
139         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
140         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
141         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
142         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
143         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
144
145     def test_find_xpath_attr(self):
146         testxml = '''<root>
147             <node/>
148             <node x="a"/>
149             <node x="a" y="c" />
150             <node x="b" y="d" />
151         </root>'''
152         doc = xml.etree.ElementTree.fromstring(testxml)
153
154         self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
155         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
156         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
157
158     def test_meta_parser(self):
159         testhtml = '''
160         <head>
161             <meta name="description" content="foo &amp; bar">
162             <meta content='Plato' name='author'/>
163         </head>
164         '''
165         get_meta = lambda name: get_meta_content(name, testhtml)
166         self.assertEqual(get_meta('description'), 'foo & bar')
167         self.assertEqual(get_meta('author'), 'Plato')
168
169     def test_xpath_with_ns(self):
170         testxml = '''<root xmlns:media="http://example.com/">
171             <media:song>
172                 <media:author>The Author</media:author>
173                 <url>http://server.com/download.mp3</url>
174             </media:song>
175         </root>'''
176         doc = xml.etree.ElementTree.fromstring(testxml)
177         find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
178         self.assertTrue(find('media:song') is not None)
179         self.assertEqual(find('media:song/media:author').text, 'The Author')
180         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
181
182     def test_smuggle_url(self):
183         data = {u"ö": u"ö", u"abc": [3]}
184         url = 'https://foo.bar/baz?x=y#a'
185         smug_url = smuggle_url(url, data)
186         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
187         self.assertEqual(url, unsmug_url)
188         self.assertEqual(data, unsmug_data)
189
190         res_url, res_data = unsmuggle_url(url)
191         self.assertEqual(res_url, url)
192         self.assertEqual(res_data, None)
193
194     def test_shell_quote(self):
195         args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
196         self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
197
198     def test_str_to_int(self):
199         self.assertEqual(str_to_int('123,456'), 123456)
200         self.assertEqual(str_to_int('123.456'), 123456)
201
202     def test_url_basename(self):
203         self.assertEqual(url_basename('http://foo.de/'), '')
204         self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
205         self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
206         self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
207         self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
208         self.assertEqual(
209             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
210             'trailer.mp4')
211
212     def test_parse_duration(self):
213         self.assertEqual(parse_duration(None), None)
214         self.assertEqual(parse_duration('1'), 1)
215         self.assertEqual(parse_duration('1337:12'), 80232)
216         self.assertEqual(parse_duration('9:12:43'), 33163)
217         self.assertEqual(parse_duration('12:00'), 720)
218         self.assertEqual(parse_duration('00:01:01'), 61)
219         self.assertEqual(parse_duration('x:y'), None)
220         self.assertEqual(parse_duration('3h11m53s'), 11513)
221         self.assertEqual(parse_duration('3h 11m 53s'), 11513)
222         self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
223         self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
224         self.assertEqual(parse_duration('62m45s'), 3765)
225         self.assertEqual(parse_duration('6m59s'), 419)
226         self.assertEqual(parse_duration('49s'), 49)
227         self.assertEqual(parse_duration('0h0m0s'), 0)
228         self.assertEqual(parse_duration('0m0s'), 0)
229         self.assertEqual(parse_duration('0s'), 0)
230         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
231
232     def test_fix_xml_ampersands(self):
233         self.assertEqual(
234             fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
235         self.assertEqual(
236             fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
237             '"&amp;x=y&amp;wrong;&amp;z=a')
238         self.assertEqual(
239             fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
240             '&amp;&apos;&gt;&lt;&quot;')
241         self.assertEqual(
242             fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
243         self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
244
245     def test_paged_list(self):
246         def testPL(size, pagesize, sliceargs, expected):
247             def get_page(pagenum):
248                 firstid = pagenum * pagesize
249                 upto = min(size, pagenum * pagesize + pagesize)
250                 for i in range(firstid, upto):
251                     yield i
252
253             pl = OnDemandPagedList(get_page, pagesize)
254             got = pl.getslice(*sliceargs)
255             self.assertEqual(got, expected)
256
257             iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
258             got = iapl.getslice(*sliceargs)
259             self.assertEqual(got, expected)
260
261         testPL(5, 2, (), [0, 1, 2, 3, 4])
262         testPL(5, 2, (1,), [1, 2, 3, 4])
263         testPL(5, 2, (2,), [2, 3, 4])
264         testPL(5, 2, (4,), [4])
265         testPL(5, 2, (0, 3), [0, 1, 2])
266         testPL(5, 2, (1, 4), [1, 2, 3])
267         testPL(5, 2, (2, 99), [2, 3, 4])
268         testPL(5, 2, (20, 99), [])
269
270     def test_struct_unpack(self):
271         self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
272
273     def test_read_batch_urls(self):
274         f = io.StringIO('''\xef\xbb\xbf foo
275             bar\r
276             baz
277             # More after this line\r
278             ; or after this
279             bam''')
280         self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
281
282     def test_urlencode_postdata(self):
283         data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
284         self.assertTrue(isinstance(data, bytes))
285
286     def test_parse_iso8601(self):
287         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
288         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
289         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
290         self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
291
292     def test_strip_jsonp(self):
293         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
294         d = json.loads(stripped)
295         self.assertEqual(d, [{"id": "532cb", "x": 3}])
296
297     def test_uppercase_escape(self):
298         self.assertEqual(uppercase_escape('aä'), 'aä')
299         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
300
301     def test_limit_length(self):
302         self.assertEqual(limit_length(None, 12), None)
303         self.assertEqual(limit_length('foo', 12), 'foo')
304         self.assertTrue(
305             limit_length('foo bar baz asd', 12).startswith('foo bar'))
306         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
307
308     def test_escape_rfc3986(self):
309         reserved = "!*'();:@&=+$,/?#[]"
310         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
311         self.assertEqual(escape_rfc3986(reserved), reserved)
312         self.assertEqual(escape_rfc3986(unreserved), unreserved)
313         self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
314         self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
315         self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
316         self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
317
318     def test_escape_url(self):
319         self.assertEqual(
320             escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
321             'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
322         )
323         self.assertEqual(
324             escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
325             'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
326         )
327         self.assertEqual(
328             escape_url('http://тест.рф/фрагмент'),
329             'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
330         )
331         self.assertEqual(
332             escape_url('http://тест.рф/абв?абв=абв#абв'),
333             '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'
334         )
335         self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
336
337     def test_js_to_json_realworld(self):
338         inp = '''{
339             'clip':{'provider':'pseudo'}
340         }'''
341         self.assertEqual(js_to_json(inp), '''{
342             "clip":{"provider":"pseudo"}
343         }''')
344         json.loads(js_to_json(inp))
345
346         inp = '''{
347             'playlist':[{'controls':{'all':null}}]
348         }'''
349         self.assertEqual(js_to_json(inp), '''{
350             "playlist":[{"controls":{"all":null}}]
351         }''')
352
353     def test_js_to_json_edgecases(self):
354         on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
355         self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
356
357         on = js_to_json('{"abc": true}')
358         self.assertEqual(json.loads(on), {'abc': True})
359
360 if __name__ == '__main__':
361     unittest.main()