]> Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py
0fa8731473317577f6ef7534d9ad5ead2064e32b
[youtubedl] / 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 clean_html,
20 DateRange,
21 encodeFilename,
22 find_xpath_attr,
23 fix_xml_ampersands,
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 intlist_to_bytes,
50 )
51
52
53 class TestUtil(unittest.TestCase):
54 def test_timeconvert(self):
55 self.assertTrue(timeconvert('') is None)
56 self.assertTrue(timeconvert('bougrg') is None)
57
58 def test_sanitize_filename(self):
59 self.assertEqual(sanitize_filename('abc'), 'abc')
60 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
61
62 self.assertEqual(sanitize_filename('123'), '123')
63
64 self.assertEqual('abc_de', sanitize_filename('abc/de'))
65 self.assertFalse('/' in sanitize_filename('abc/de///'))
66
67 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
68 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
69 self.assertEqual('yes no', sanitize_filename('yes? no'))
70 self.assertEqual('this - that', sanitize_filename('this: that'))
71
72 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
73 aumlaut = 'ä'
74 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
75 tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
76 self.assertEqual(sanitize_filename(tests), tests)
77
78 forbidden = '"\0\\/'
79 for fc in forbidden:
80 for fbc in forbidden:
81 self.assertTrue(fbc not in sanitize_filename(fc))
82
83 def test_sanitize_filename_restricted(self):
84 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
85 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
86
87 self.assertEqual(sanitize_filename('123', restricted=True), '123')
88
89 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
90 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
91
92 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
93 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
94 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
95 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
96
97 tests = 'a\xe4b\u4e2d\u56fd\u7684c'
98 self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
99 self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
100
101 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
102 for fc in forbidden:
103 for fbc in forbidden:
104 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
105
106 # Handle a common case more neatly
107 self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
108 self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
109 # .. but make sure the file name is never empty
110 self.assertTrue(sanitize_filename('-', restricted=True) != '')
111 self.assertTrue(sanitize_filename(':', restricted=True) != '')
112
113 def test_sanitize_ids(self):
114 self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
115 self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
116 self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
117
118 def test_ordered_set(self):
119 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
120 self.assertEqual(orderedSet([]), [])
121 self.assertEqual(orderedSet([1]), [1])
122 #keep the list ordered
123 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
124
125 def test_unescape_html(self):
126 self.assertEqual(unescapeHTML('%20;'), '%20;')
127 self.assertEqual(
128 unescapeHTML('&eacute;'), 'é')
129
130 def test_daterange(self):
131 _20century = DateRange("19000101","20000101")
132 self.assertFalse("17890714" in _20century)
133 _ac = DateRange("00010101")
134 self.assertTrue("19690721" in _ac)
135 _firstmilenium = DateRange(end="10000101")
136 self.assertTrue("07110427" in _firstmilenium)
137
138 def test_unified_dates(self):
139 self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
140 self.assertEqual(unified_strdate('8/7/2009'), '20090708')
141 self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
142 self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
143 self.assertEqual(unified_strdate('1968-12-10'), '19681210')
144 self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
145
146 def test_find_xpath_attr(self):
147 testxml = '''<root>
148 <node/>
149 <node x="a"/>
150 <node x="a" y="c" />
151 <node x="b" y="d" />
152 </root>'''
153 doc = xml.etree.ElementTree.fromstring(testxml)
154
155 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
156 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
157 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
158
159 def test_xpath_with_ns(self):
160 testxml = '''<root xmlns:media="http://example.com/">
161 <media:song>
162 <media:author>The Author</media:author>
163 <url>http://server.com/download.mp3</url>
164 </media:song>
165 </root>'''
166 doc = xml.etree.ElementTree.fromstring(testxml)
167 find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
168 self.assertTrue(find('media:song') is not None)
169 self.assertEqual(find('media:song/media:author').text, 'The Author')
170 self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
171
172 def test_smuggle_url(self):
173 data = {u"ö": u"ö", u"abc": [3]}
174 url = 'https://foo.bar/baz?x=y#a'
175 smug_url = smuggle_url(url, data)
176 unsmug_url, unsmug_data = unsmuggle_url(smug_url)
177 self.assertEqual(url, unsmug_url)
178 self.assertEqual(data, unsmug_data)
179
180 res_url, res_data = unsmuggle_url(url)
181 self.assertEqual(res_url, url)
182 self.assertEqual(res_data, None)
183
184 def test_shell_quote(self):
185 args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
186 self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
187
188 def test_str_to_int(self):
189 self.assertEqual(str_to_int('123,456'), 123456)
190 self.assertEqual(str_to_int('123.456'), 123456)
191
192 def test_url_basename(self):
193 self.assertEqual(url_basename('http://foo.de/'), '')
194 self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
195 self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
196 self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
197 self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
198 self.assertEqual(
199 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
200 'trailer.mp4')
201
202 def test_parse_duration(self):
203 self.assertEqual(parse_duration(None), None)
204 self.assertEqual(parse_duration('1'), 1)
205 self.assertEqual(parse_duration('1337:12'), 80232)
206 self.assertEqual(parse_duration('9:12:43'), 33163)
207 self.assertEqual(parse_duration('12:00'), 720)
208 self.assertEqual(parse_duration('00:01:01'), 61)
209 self.assertEqual(parse_duration('x:y'), None)
210 self.assertEqual(parse_duration('3h11m53s'), 11513)
211 self.assertEqual(parse_duration('3h 11m 53s'), 11513)
212 self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
213 self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
214 self.assertEqual(parse_duration('62m45s'), 3765)
215 self.assertEqual(parse_duration('6m59s'), 419)
216 self.assertEqual(parse_duration('49s'), 49)
217 self.assertEqual(parse_duration('0h0m0s'), 0)
218 self.assertEqual(parse_duration('0m0s'), 0)
219 self.assertEqual(parse_duration('0s'), 0)
220 self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
221 self.assertEqual(parse_duration('T30M38S'), 1838)
222
223 def test_fix_xml_ampersands(self):
224 self.assertEqual(
225 fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
226 self.assertEqual(
227 fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
228 '"&amp;x=y&amp;wrong;&amp;z=a')
229 self.assertEqual(
230 fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
231 '&amp;&apos;&gt;&lt;&quot;')
232 self.assertEqual(
233 fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
234 self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
235
236 def test_paged_list(self):
237 def testPL(size, pagesize, sliceargs, expected):
238 def get_page(pagenum):
239 firstid = pagenum * pagesize
240 upto = min(size, pagenum * pagesize + pagesize)
241 for i in range(firstid, upto):
242 yield i
243
244 pl = OnDemandPagedList(get_page, pagesize)
245 got = pl.getslice(*sliceargs)
246 self.assertEqual(got, expected)
247
248 iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
249 got = iapl.getslice(*sliceargs)
250 self.assertEqual(got, expected)
251
252 testPL(5, 2, (), [0, 1, 2, 3, 4])
253 testPL(5, 2, (1,), [1, 2, 3, 4])
254 testPL(5, 2, (2,), [2, 3, 4])
255 testPL(5, 2, (4,), [4])
256 testPL(5, 2, (0, 3), [0, 1, 2])
257 testPL(5, 2, (1, 4), [1, 2, 3])
258 testPL(5, 2, (2, 99), [2, 3, 4])
259 testPL(5, 2, (20, 99), [])
260
261 def test_struct_unpack(self):
262 self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
263
264 def test_read_batch_urls(self):
265 f = io.StringIO('''\xef\xbb\xbf foo
266 bar\r
267 baz
268 # More after this line\r
269 ; or after this
270 bam''')
271 self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
272
273 def test_urlencode_postdata(self):
274 data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
275 self.assertTrue(isinstance(data, bytes))
276
277 def test_parse_iso8601(self):
278 self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
279 self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
280 self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
281 self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
282
283 def test_strip_jsonp(self):
284 stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
285 d = json.loads(stripped)
286 self.assertEqual(d, [{"id": "532cb", "x": 3}])
287
288 stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
289 d = json.loads(stripped)
290 self.assertEqual(d, {'STATUS': 'OK'})
291
292 def test_uppercase_escape(self):
293 self.assertEqual(uppercase_escape('aä'), 'aä')
294 self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
295
296 def test_limit_length(self):
297 self.assertEqual(limit_length(None, 12), None)
298 self.assertEqual(limit_length('foo', 12), 'foo')
299 self.assertTrue(
300 limit_length('foo bar baz asd', 12).startswith('foo bar'))
301 self.assertTrue('...' in limit_length('foo bar baz asd', 12))
302
303 def test_escape_rfc3986(self):
304 reserved = "!*'();:@&=+$,/?#[]"
305 unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
306 self.assertEqual(escape_rfc3986(reserved), reserved)
307 self.assertEqual(escape_rfc3986(unreserved), unreserved)
308 self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
309 self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
310 self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
311 self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
312
313 def test_escape_url(self):
314 self.assertEqual(
315 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
316 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
317 )
318 self.assertEqual(
319 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
320 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
321 )
322 self.assertEqual(
323 escape_url('http://тест.рф/фрагмент'),
324 'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
325 )
326 self.assertEqual(
327 escape_url('http://тест.рф/абв?абв=абв#абв'),
328 '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'
329 )
330 self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
331
332 def test_js_to_json_realworld(self):
333 inp = '''{
334 'clip':{'provider':'pseudo'}
335 }'''
336 self.assertEqual(js_to_json(inp), '''{
337 "clip":{"provider":"pseudo"}
338 }''')
339 json.loads(js_to_json(inp))
340
341 inp = '''{
342 'playlist':[{'controls':{'all':null}}]
343 }'''
344 self.assertEqual(js_to_json(inp), '''{
345 "playlist":[{"controls":{"all":null}}]
346 }''')
347
348 def test_js_to_json_edgecases(self):
349 on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
350 self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
351
352 on = js_to_json('{"abc": true}')
353 self.assertEqual(json.loads(on), {'abc': True})
354
355 def test_clean_html(self):
356 self.assertEqual(clean_html('a:\nb'), 'a: b')
357 self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
358
359 def test_intlist_to_bytes(self):
360 self.assertEqual(
361 intlist_to_bytes([0, 1, 127, 128, 255]),
362 b'\x00\x01\x7f\x80\xff')
363
364 if __name__ == '__main__':
365 unittest.main()