yt-dlp/test/test_utils.py

415 lines
17 KiB
Python
Raw Normal View History

#!/usr/bin/env python
# coding: utf-8
2014-08-27 13:11:45 -04:00
from __future__ import unicode_literals
# Allow direct execution
import os
2012-11-27 17:20:29 -05:00
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
2012-11-27 17:20:29 -05:00
from youtube_dl.utils import (
age_restricted,
args_to_str,
2014-11-13 09:02:31 -05:00
clean_html,
DateRange,
detect_exe_version,
encodeFilename,
escape_rfc3986,
escape_url,
find_xpath_attr,
2014-01-20 16:11:34 -05:00
fix_xml_ampersands,
InAdvancePagedList,
intlist_to_bytes,
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,
2014-02-15 10:24:43 -05:00
struct_unpack,
timeconvert,
unescapeHTML,
unified_strdate,
unsmuggle_url,
uppercase_escape,
url_basename,
urlencode_postdata,
version_tuple,
xpath_with_ns,
)
2012-11-28 06:59:27 -05:00
class TestUtil(unittest.TestCase):
2012-11-27 20:04:46 -05:00
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')
2014-08-27 13:11:45 -04:00
aumlaut = 'ä'
2012-11-27 20:04:46 -05:00
self.assertEqual(sanitize_filename(aumlaut), aumlaut)
2014-08-27 13:11:45 -04:00
tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
2012-11-27 20:04:46 -05:00
self.assertEqual(sanitize_filename(tests), tests)
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))
2014-08-27 13:11:45 -04:00
tests = 'a\xe4b\u4e2d\u56fd\u7684c'
2012-11-27 20:04:46 -05:00
self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
2014-08-27 13:11:45 -04:00
self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
2012-11-27 20:04:46 -05:00
2012-11-28 06:59:27 -05:00
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
2012-11-27 20:04:46 -05:00
for fc in forbidden:
for fbc in forbidden:
self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
# Handle a common case more neatly
2014-08-27 13:11:45 -04:00
self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
2012-11-27 20:04:46 -05:00
# .. 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):
2012-12-20 07:26:37 -05:00
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')
2012-11-27 20:04:46 -05:00
def test_ordered_set(self):
2012-11-28 06:59:27 -05:00
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
2012-11-27 20:04:46 -05:00
self.assertEqual(orderedSet([]), [])
self.assertEqual(orderedSet([1]), [1])
2014-11-23 14:41:03 -05:00
# keep the list ordered
2012-11-28 06:59:27 -05:00
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
2012-11-27 20:04:46 -05:00
def test_unescape_html(self):
2014-08-27 13:11:45 -04:00
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(
unescapeHTML('&eacute;'), 'é')
2014-11-23 14:41:03 -05:00
def test_daterange(self):
2014-11-23 14:41:03 -05:00
_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')
2014-02-09 12:09:57 -05:00
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
2014-09-29 06:45:18 -04:00
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')
2012-11-27 17:20:29 -05:00
2013-07-11 10:12:08 -04:00
def test_find_xpath_attr(self):
2014-08-27 13:11:45 -04:00
testxml = '''<root>
2013-07-11 10:12:08 -04:00
<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):
2014-08-27 13:11:45 -04:00
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)
2014-08-27 13:11:45 -04:00
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):
2014-11-26 07:07:32 -05:00
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):
2014-08-27 13:11:45 -04:00
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):
2014-08-27 13:11:45 -04:00
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')
2013-12-17 06:32:58 -05:00
self.assertEqual(
2014-08-27 13:11:45 -04:00
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('1'), 1)
self.assertEqual(parse_duration('1337:12'), 80232)
self.assertEqual(parse_duration('9:12:43'), 33163)
2014-02-16 15:46:26 -05:00
self.assertEqual(parse_duration('12:00'), 720)
self.assertEqual(parse_duration('00:01:01'), 61)
self.assertEqual(parse_duration('x:y'), None)
2014-02-16 15:46:26 -05:00
self.assertEqual(parse_duration('3h11m53s'), 11513)
2014-08-30 19:41:30 -04:00
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)
2014-02-16 15:46:26 -05:00
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)
2014-08-25 06:59:53 -04:00
self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
2014-11-16 08:55:22 -05:00
self.assertEqual(parse_duration('T30M38S'), 1838)
2014-12-04 11:35:40 -05:00
self.assertEqual(parse_duration('5 s'), 5)
self.assertEqual(parse_duration('3 min'), 180)
self.assertEqual(parse_duration('2.5 hours'), 9000)
2014-01-20 16:11:34 -05:00
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), [])
2014-02-15 10:24:43 -05:00
def test_struct_unpack(self):
2014-08-27 13:11:45 -04:00
self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
2014-02-15 10:24:43 -05:00
def test_read_batch_urls(self):
2014-08-27 13:11:45 -04:00
f = io.StringIO('''\xef\xbb\xbf foo
bar\r
baz
# More after this line\r
; or after this
bam''')
2014-08-27 13:11:45 -04:00
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))
2014-03-23 20:40:09 -04:00
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)
2014-03-23 20:40:09 -04:00
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}])
2014-11-13 10:28:05 -05:00
stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
d = json.loads(stripped)
self.assertEqual(d, {'STATUS': 'OK'})
def test_uppercase_escape(self):
2014-08-27 13:11:45 -04:00
self.assertEqual(uppercase_escape(''), '')
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')
2014-09-30 05:12:59 -04:00
def test_js_to_json_realworld(self):
2014-09-30 01:56:24 -04:00
inp = '''{
2014-09-30 05:12:59 -04:00
'clip':{'provider':'pseudo'}
2014-09-30 01:56:24 -04:00
}'''
self.assertEqual(js_to_json(inp), '''{
2014-09-30 05:12:59 -04:00
"clip":{"provider":"pseudo"}
2014-09-30 01:56:24 -04:00
}''')
json.loads(js_to_json(inp))
2014-09-30 05:12:59 -04:00
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})
2014-11-13 09:02:31 -05:00
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\' \'\''
)
2014-11-25 03:54:54 -05:00
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)
2014-11-25 03:54:54 -05:00
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))
2012-11-27 17:20:29 -05:00
if __name__ == '__main__':
2012-11-27 20:04:46 -05:00
unittest.main()