1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/test/test_utils.py

187 lines
7.2 KiB
Python
Raw Normal View History

#!/usr/bin/env python
# coding: utf-8
# Allow direct execution
import os
2012-11-27 22:20:29 +00:00
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# Various small unit tests
import xml.etree.ElementTree
2012-11-27 22:20:29 +00:00
#from youtube_dl.utils import htmlentity_transform
from youtube_dl.utils import (
timeconvert,
sanitize_filename,
unescapeHTML,
orderedSet,
DateRange,
unified_strdate,
find_xpath_attr,
get_meta_content,
xpath_with_ns,
smuggle_url,
unsmuggle_url,
shell_quote,
encodeFilename,
str_to_int,
)
2012-11-28 11:59:27 +00:00
if sys.version_info < (3, 0):
2012-11-28 01:04:46 +00:00
_compat_str = lambda b: b.decode('unicode-escape')
2012-11-27 22:20:29 +00:00
else:
2012-11-28 01:04:46 +00:00
_compat_str = lambda s: s
2012-11-28 11:59:27 +00:00
class TestUtil(unittest.TestCase):
2012-11-28 01:04:46 +00:00
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')
aumlaut = _compat_str('\xe4')
self.assertEqual(sanitize_filename(aumlaut), aumlaut)
tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430')
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))
2012-11-28 11:59:27 +00:00
tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c')
2012-11-28 01:04:46 +00:00
self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
2012-11-28 11:59:27 +00:00
self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename
2012-11-28 01:04:46 +00:00
2012-11-28 11:59:27 +00:00
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
2012-11-28 01:04:46 +00:00
for fc in forbidden:
for fbc in forbidden:
self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
# Handle a common case more neatly
self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song')
self.assertEqual(sanitize_filename(_compat_str('\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):
2012-12-20 12:26:37 +00:00
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')
2012-11-28 01:04:46 +00:00
def test_ordered_set(self):
2012-11-28 11:59:27 +00:00
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
2012-11-28 01:04:46 +00:00
self.assertEqual(orderedSet([]), [])
self.assertEqual(orderedSet([1]), [1])
#keep the list ordered
2012-11-28 11:59:27 +00:00
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
2012-11-28 01:04:46 +00:00
def test_unescape_html(self):
self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
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')
2012-11-27 22:20:29 +00:00
2013-07-11 14:12:08 +00:00
def test_find_xpath_attr(self):
testxml = u'''<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_meta_parser(self):
testhtml = u'''
<head>
<meta name="description" content="foo &amp; bar">
<meta content='Plato' name='author'/>
</head>
'''
get_meta = lambda name: get_meta_content(name, testhtml)
self.assertEqual(get_meta('description'), u'foo & bar')
self.assertEqual(get_meta('author'), 'Plato')
def test_xpath_with_ns(self):
testxml = u'''<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, u'The Author')
self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3')
def test_smuggle_url(self):
data = {u"ö": u"ö", u"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(u'ñ€ß\'.mp4')]
self.assertEqual(shell_quote(args), u"""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)
2012-11-27 22:20:29 +00:00
if __name__ == '__main__':
2012-11-28 01:04:46 +00:00
unittest.main()