aboutsummaryrefslogtreecommitdiff
path: root/test/test_utils.py
blob: bdd7f268af46d5eaaef35507f839989a8343316b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
#!/usr/bin/env python
# coding: utf-8

from __future__ import unicode_literals

# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))


# Various small unit tests
import io
import json
import xml.etree.ElementTree

from youtube_dl.utils import (
    age_restricted,
    args_to_str,
    clean_html,
    DateRange,
    detect_exe_version,
    encodeFilename,
    escape_rfc3986,
    escape_url,
    find_xpath_attr,
    fix_xml_ampersands,
    InAdvancePagedList,
    intlist_to_bytes,
    is_html,
    js_to_json,
    limit_length,
    OnDemandPagedList,
    orderedSet,
    parse_duration,
    parse_filesize,
    parse_iso8601,
    read_batch_urls,
    sanitize_filename,
    shell_quote,
    smuggle_url,
    str_to_int,
    strip_jsonp,
    struct_unpack,
    timeconvert,
    unescapeHTML,
    unified_strdate,
    unsmuggle_url,
    uppercase_escape,
    url_basename,
    urlencode_postdata,
    version_tuple,
    xpath_with_ns,
)


class TestUtil(unittest.TestCase):
    def test_timeconvert(self):
        self.assertTrue(timeconvert('') is None)
        self.assertTrue(timeconvert('bougrg') is None)

    def test_sanitize_filename(self):
        self.assertEqual(sanitize_filename('abc'), 'abc')
        self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')

        self.assertEqual(sanitize_filename('123'), '123')

        self.assertEqual('abc_de', sanitize_filename('abc/de'))
        self.assertFalse('/' in sanitize_filename('abc/de///'))

        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
        self.assertEqual('yes no', sanitize_filename('yes? no'))
        self.assertEqual('this - that', sanitize_filename('this: that'))

        self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
        aumlaut = 'ä'
        self.assertEqual(sanitize_filename(aumlaut), aumlaut)
        tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
        self.assertEqual(sanitize_filename(tests), tests)

        self.assertEqual(
            sanitize_filename('New World record at 0:12:34'),
            'New World record at 0_12_34')

        forbidden = '"\0\\/'
        for fc in forbidden:
            for fbc in forbidden:
                self.assertTrue(fbc not in sanitize_filename(fc))

    def test_sanitize_filename_restricted(self):
        self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
        self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')

        self.assertEqual(sanitize_filename('123', restricted=True), '123')

        self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
        self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))

        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
        self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
        self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))

        tests = 'a\xe4b\u4e2d\u56fd\u7684c'
        self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
        self.assertTrue(sanitize_filename('\xf6', restricted=True) != '')  # No empty filename

        forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
        for fc in forbidden:
            for fbc in forbidden:
                self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))

        # Handle a common case more neatly
        self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
        self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
        # .. but make sure the file name is never empty
        self.assertTrue(sanitize_filename('-', restricted=True) != '')
        self.assertTrue(sanitize_filename(':', restricted=True) != '')

    def test_sanitize_ids(self):
        self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
        self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
        self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')

    def test_ordered_set(self):
        self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
        self.assertEqual(orderedSet([]), [])
        self.assertEqual(orderedSet([1]), [1])
        # keep the list ordered
        self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])

    def test_unescape_html(self):
        self.assertEqual(unescapeHTML('%20;'), '%20;')
        self.assertEqual(
            unescapeHTML('&eacute;'), 'é')

    def test_daterange(self):
        _20century = DateRange("19000101", "20000101")
        self.assertFalse("17890714" in _20century)
        _ac = DateRange("00010101")
        self.assertTrue("19690721" in _ac)
        _firstmilenium = DateRange(end="10000101")
        self.assertTrue("07110427" in _firstmilenium)

    def test_unified_dates(self):
        self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
        self.assertEqual(unified_strdate('8/7/2009'), '20090708')
        self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
        self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
        self.assertEqual(unified_strdate('1968 12 10'), '19681210')
        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
        self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
        self.assertEqual(
            unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
            '20141126')

    def test_find_xpath_attr(self):
        testxml = '''<root>
            <node/>
            <node x="a"/>
            <node x="a" y="c" />
            <node x="b" y="d" />
        </root>'''
        doc = xml.etree.ElementTree.fromstring(testxml)

        self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
        self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
        self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])

    def test_xpath_with_ns(self):
        testxml = '''<root xmlns:media="http://example.com/">
            <media:song>
                <media:author>The Author</media:author>
                <url>http://server.com/download.mp3</url>
            </media:song>
        </root>'''
        doc = xml.etree.ElementTree.fromstring(testxml)
        find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
        self.assertTrue(find('media:song') is not None)
        self.assertEqual(find('media:song/media:author').text, 'The Author')
        self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')

    def test_smuggle_url(self):
        data = {"ö": "ö", "abc": [3]}
        url = 'https://foo.bar/baz?x=y#a'
        smug_url = smuggle_url(url, data)
        unsmug_url, unsmug_data = unsmuggle_url(smug_url)
        self.assertEqual(url, unsmug_url)
        self.assertEqual(data, unsmug_data)

        res_url, res_data = unsmuggle_url(url)
        self.assertEqual(res_url, url)
        self.assertEqual(res_data, None)

    def test_shell_quote(self):
        args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
        self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")

    def test_str_to_int(self):
        self.assertEqual(str_to_int('123,456'), 123456)
        self.assertEqual(str_to_int('123.456'), 123456)

    def test_url_basename(self):
        self.assertEqual(url_basename('http://foo.de/'), '')
        self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
        self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
        self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
        self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
        self.assertEqual(
            url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
            'trailer.mp4')

    def test_parse_duration(self):
        self.assertEqual(parse_duration(None), None)
        self.assertEqual(parse_duration(False), None)
        self.assertEqual(parse_duration('invalid'), None)
        self.assertEqual(parse_duration('1'), 1)
        self.assertEqual(parse_duration('1337:12'), 80232)
        self.assertEqual(parse_duration('9:12:43'), 33163)
        self.assertEqual(parse_duration('12:00'), 720)
        self.assertEqual(parse_duration('00:01:01'), 61)
        self.assertEqual(parse_duration('x:y'), None)
        self.assertEqual(parse_duration('3h11m53s'), 11513)
        self.assertEqual(parse_duration('3h 11m 53s'), 11513)
        self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
        self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
        self.assertEqual(parse_duration('62m45s'), 3765)
        self.assertEqual(parse_duration('6m59s'), 419)
        self.assertEqual(parse_duration('49s'), 49)
        self.assertEqual(parse_duration('0h0m0s'), 0)
        self.assertEqual(parse_duration('0m0s'), 0)
        self.assertEqual(parse_duration('0s'), 0)
        self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
        self.assertEqual(parse_duration('T30M38S'), 1838)
        self.assertEqual(parse_duration('5 s'), 5)
        self.assertEqual(parse_duration('3 min'), 180)
        self.assertEqual(parse_duration('2.5 hours'), 9000)

    def test_fix_xml_ampersands(self):
        self.assertEqual(
            fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
        self.assertEqual(
            fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
            '"&amp;x=y&amp;wrong;&amp;z=a')
        self.assertEqual(
            fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
            '&amp;&apos;&gt;&lt;&quot;')
        self.assertEqual(
            fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
        self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')

    def test_paged_list(self):
        def testPL(size, pagesize, sliceargs, expected):
            def get_page(pagenum):
                firstid = pagenum * pagesize
                upto = min(size, pagenum * pagesize + pagesize)
                for i in range(firstid, upto):
                    yield i

            pl = OnDemandPagedList(get_page, pagesize)
            got = pl.getslice(*sliceargs)
            self.assertEqual(got, expected)

            iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
            got = iapl.getslice(*sliceargs)
            self.assertEqual(got, expected)

        testPL(5, 2, (), [0, 1, 2, 3, 4])
        testPL(5, 2, (1,), [1, 2, 3, 4])
        testPL(5, 2, (2,), [2, 3, 4])
        testPL(5, 2, (4,), [4])
        testPL(5, 2, (0, 3), [0, 1, 2])
        testPL(5, 2, (1, 4), [1, 2, 3])
        testPL(5, 2, (2, 99), [2, 3, 4])
        testPL(5, 2, (20, 99), [])

    def test_struct_unpack(self):
        self.assertEqual(struct_unpack('!B', b'\x00'), (0,))

    def test_read_batch_urls(self):
        f = io.StringIO('''\xef\xbb\xbf foo
            bar\r
            baz
            # More after this line\r
            ; or after this
            bam''')
        self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])

    def test_urlencode_postdata(self):
        data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
        self.assertTrue(isinstance(data, bytes))

    def test_parse_iso8601(self):
        self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
        self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
        self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
        self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)

    def test_strip_jsonp(self):
        stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
        d = json.loads(stripped)
        self.assertEqual(d, [{"id": "532cb", "x": 3}])

        stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
        d = json.loads(stripped)
        self.assertEqual(d, {'STATUS': 'OK'})

    def test_uppercase_escape(self):
        self.assertEqual(uppercase_escape('aä'), 'aä')
        self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')

    def test_limit_length(self):
        self.assertEqual(limit_length(None, 12), None)
        self.assertEqual(limit_length('foo', 12), 'foo')
        self.assertTrue(
            limit_length('foo bar baz asd', 12).startswith('foo bar'))
        self.assertTrue('...' in limit_length('foo bar baz asd', 12))

    def test_escape_rfc3986(self):
        reserved = "!*'();:@&=+$,/?#[]"
        unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
        self.assertEqual(escape_rfc3986(reserved), reserved)
        self.assertEqual(escape_rfc3986(unreserved), unreserved)
        self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
        self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
        self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
        self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')

    def test_escape_url(self):
        self.assertEqual(
            escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
            'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
        )
        self.assertEqual(
            escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
            'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
        )
        self.assertEqual(
            escape_url('http://тест.рф/фрагмент'),
            'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
        )
        self.assertEqual(
            escape_url('http://тест.рф/абв?абв=абв#абв'),
            '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'
        )
        self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')

    def test_js_to_json_realworld(self):
        inp = '''{
            'clip':{'provider':'pseudo'}
        }'''
        self.assertEqual(js_to_json(inp), '''{
            "clip":{"provider":"pseudo"}
        }''')
        json.loads(js_to_json(inp))

        inp = '''{
            'playlist':[{'controls':{'all':null}}]
        }'''
        self.assertEqual(js_to_json(inp), '''{
            "playlist":[{"controls":{"all":null}}]
        }''')

    def test_js_to_json_edgecases(self):
        on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
        self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})

        on = js_to_json('{"abc": true}')
        self.assertEqual(json.loads(on), {'abc': True})

    def test_clean_html(self):
        self.assertEqual(clean_html('a:\nb'), 'a: b')
        self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')

    def test_intlist_to_bytes(self):
        self.assertEqual(
            intlist_to_bytes([0, 1, 127, 128, 255]),
            b'\x00\x01\x7f\x80\xff')

    def test_args_to_str(self):
        self.assertEqual(
            args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
            'foo ba/r -baz \'2 be\' \'\''
        )

    def test_parse_filesize(self):
        self.assertEqual(parse_filesize(None), None)
        self.assertEqual(parse_filesize(''), None)
        self.assertEqual(parse_filesize('91 B'), 91)
        self.assertEqual(parse_filesize('foobar'), None)
        self.assertEqual(parse_filesize('2 MiB'), 2097152)
        self.assertEqual(parse_filesize('5 GB'), 5000000000)
        self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
        self.assertEqual(parse_filesize('1,24 KB'), 1240)

    def test_version_tuple(self):
        self.assertEqual(version_tuple('1'), (1,))
        self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
        self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style

    def test_detect_exe_version(self):
        self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
configuration: --prefix=/usr --extra-'''), '1.2.1')
        self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
        self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
Trying to open render node...
Success at /dev/dri/renderD128.
ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')

    def test_age_restricted(self):
        self.assertFalse(age_restricted(None, 10))  # unrestricted content
        self.assertFalse(age_restricted(1, None))  # unrestricted policy
        self.assertFalse(age_restricted(8, 10))
        self.assertTrue(age_restricted(18, 14))
        self.assertFalse(age_restricted(18, 18))

    def test_is_html(self):
        self.assertFalse(is_html(b'\x49\x44\x43<html'))
        self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
        self.assertTrue(is_html(  # UTF-8 with BOM
            b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
        self.assertTrue(is_html(  # UTF-16-LE
            b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
        ))
        self.assertTrue(is_html(  # UTF-16-BE
            b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
        ))
        self.assertTrue(is_html(  # UTF-32-BE
            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'))
        self.assertTrue(is_html(  # UTF-32-LE
            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'))

if __name__ == '__main__':
    unittest.main()