[yt-dlp.git] / test / test_utils.py

#!/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,
    render_table,
)


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)
        self.assertEqual(parse_duration('02:03:04'), 7384)
        self.assertEqual(parse_duration('01:02:03:04'), 93784)

    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})

        # Ignore JavaScript code as well
        on = js_to_json('''{
            "x": 1,
            y: "a",
            z: some.code
        }''')
        d = json.loads(on)
        self.assertEqual(d['x'], 1)
        self.assertEqual(d['y'], 'a')

    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'))

    def test_render_table(self):
        self.assertEqual(
            render_table(
                ['a', 'bcd'],
                [[123, 4], [9999, 51]]),
            'a    bcd\n'
            '123  4\n'
            '9999 51')


if __name__ == '__main__':
    unittest.main()
Commit	Line	Data
e387eb5a	1	#!/usr/bin/env python
9d4660ca	2	# coding: utf-8
e387eb5a	3
4e408e47 PH	4	from __future__ import unicode_literals
4e408e47 PH	5
44a5f171 PH	6	# Allow direct execution
44a5f171 PH	7	import os
dae7c920	8	import sys
44fb3454	9	import unittest
44a5f171	10	sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
44fb3454	11
44a5f171 PH	12
44a5f171 PH	13	# Various small unit tests
62e609ab	14	import io
fac55558	15	import json
44a5f171	16	import xml.etree.ElementTree
dae7c920	17
a921f407	18	from youtube_dl.utils import (
05900629	19	age_restricted,
cae97f65	20	args_to_str,
e4bdb37e	21	clean_html,
a921f407	22	DateRange,
cae97f65	23	detect_exe_version,
29eb5174	24	encodeFilename,
cae97f65 PH	25	escape_rfc3986,
cae97f65 PH	26	escape_url,
a921f407	27	find_xpath_attr,
5aafe895	28	fix_xml_ampersands,
9c44d242	29	InAdvancePagedList,
cae97f65	30	intlist_to_bytes,
61ca9a80	31	is_html,
cae97f65 PH	32	js_to_json,
	33	limit_length,
	34	OnDemandPagedList,
	35	orderedSet,
608d11f5	36	parse_duration,
cae97f65 PH	37	parse_filesize,
cae97f65 PH	38	parse_iso8601,
62e609ab	39	read_batch_urls,
29eb5174	40	sanitize_filename,
a6a173c2	41	shell_quote,
29eb5174	42	smuggle_url,
f53c966a	43	str_to_int,
cae97f65	44	strip_jsonp,
b53466e1	45	struct_unpack,
29eb5174 PH	46	timeconvert,
	47	unescapeHTML,
	48	unified_strdate,
	49	unsmuggle_url,
cae97f65	50	uppercase_escape,
29eb5174	51	url_basename,
b74fa8cd	52	urlencode_postdata,
5f9b8394	53	version_tuple,
cae97f65	54	xpath_with_ns,
cfb56d1a	55	render_table,
a921f407	56	)
44fb3454	57
627dcfff	58
44fb3454	59	class TestUtil(unittest.TestCase):
59ae15a5 PH	60	def test_timeconvert(self):
	61	self.assertTrue(timeconvert('') is None)
	62	self.assertTrue(timeconvert('bougrg') is None)
	63
	64	def test_sanitize_filename(self):
	65	self.assertEqual(sanitize_filename('abc'), 'abc')
	66	self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
	67
	68	self.assertEqual(sanitize_filename('123'), '123')
	69
	70	self.assertEqual('abc_de', sanitize_filename('abc/de'))
	71	self.assertFalse('/' in sanitize_filename('abc/de///'))
	72
	73	self.assertEqual('abc_de', sanitize_filename('abc/<>\\*\|de'))
	74	self.assertEqual('xxx', sanitize_filename('xxx/<>\\*\|'))
	75	self.assertEqual('yes no', sanitize_filename('yes? no'))
	76	self.assertEqual('this - that', sanitize_filename('this: that'))
	77
	78	self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
4e408e47	79	aumlaut = 'ä'
59ae15a5	80	self.assertEqual(sanitize_filename(aumlaut), aumlaut)
4e408e47	81	tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
59ae15a5 PH	82	self.assertEqual(sanitize_filename(tests), tests)
59ae15a5 PH	83
2aeb06d6 PH	84	self.assertEqual(
	85	sanitize_filename('New World record at 0:12:34'),
	86	'New World record at 0_12_34')
	87
59ae15a5 PH	88	forbidden = '"\0\\/'
	89	for fc in forbidden:
	90	for fbc in forbidden:
	91	self.assertTrue(fbc not in sanitize_filename(fc))
	92
	93	def test_sanitize_filename_restricted(self):
	94	self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
	95	self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
	96
	97	self.assertEqual(sanitize_filename('123', restricted=True), '123')
	98
	99	self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
	100	self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
	101
	102	self.assertEqual('abc_de', sanitize_filename('abc/<>\\*\|de', restricted=True))
	103	self.assertEqual('xxx', sanitize_filename('xxx/<>\\*\|', restricted=True))
	104	self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
	105	self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
	106
4e408e47	107	tests = 'a\xe4b\u4e2d\u56fd\u7684c'
59ae15a5	108	self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c')
4e408e47	109	self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
59ae15a5	110
627dcfff	111	forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
59ae15a5 PH	112	for fc in forbidden:
	113	for fbc in forbidden:
	114	self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
	115
	116	# Handle a common case more neatly
4e408e47 PH	117	self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
4e408e47 PH	118	self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
59ae15a5 PH	119	# .. but make sure the file name is never empty
	120	self.assertTrue(sanitize_filename('-', restricted=True) != '')
	121	self.assertTrue(sanitize_filename(':', restricted=True) != '')
	122
796173d0	123	def test_sanitize_ids(self):
314d506b PH	124	self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
	125	self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
	126	self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
796173d0	127
59ae15a5	128	def test_ordered_set(self):
627dcfff	129	self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
59ae15a5 PH	130	self.assertEqual(orderedSet([]), [])
59ae15a5 PH	131	self.assertEqual(orderedSet([1]), [1])
5f6a1245	132	# keep the list ordered
627dcfff	133	self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
59ae15a5 PH	134
59ae15a5 PH	135	def test_unescape_html(self):
4e408e47 PH	136	self.assertEqual(unescapeHTML('%20;'), '%20;')
	137	self.assertEqual(
	138	unescapeHTML('é'), 'é')
5f6a1245	139
bd558525	140	def test_daterange(self):
5f6a1245	141	_20century = DateRange("19000101", "20000101")
bd558525 JMF	142	self.assertFalse("17890714" in _20century)
	143	_ac = DateRange("00010101")
	144	self.assertTrue("19690721" in _ac)
	145	_firstmilenium = DateRange(end="10000101")
	146	self.assertTrue("07110427" in _firstmilenium)
37254abc	147
bf50b038 JMF	148	def test_unified_dates(self):
	149	self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
	150	self.assertEqual(unified_strdate('8/7/2009'), '20090708')
	151	self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
	152	self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
a69801e2	153	self.assertEqual(unified_strdate('1968 12 10'), '19681210')
026fcc04	154	self.assertEqual(unified_strdate('1968-12-10'), '19681210')
99b67fec	155	self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
42bdd9d0 PH	156	self.assertEqual(
	157	unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
	158	'20141126')
dae7c920	159
59ae56fa	160	def test_find_xpath_attr(self):
4e408e47	161	testxml = '''<root>
59ae56fa PH	162	<node/>
	163	<node x="a"/>
	164	<node x="a" y="c" />
	165	<node x="b" y="d" />
	166	</root>'''
	167	doc = xml.etree.ElementTree.fromstring(testxml)
	168
	169	self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
	170	self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
	171	self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
	172
d7e66d39	173	def test_xpath_with_ns(self):
4e408e47	174	testxml = '''<root xmlns:media="http://example.com/">
d7e66d39 JMF	175	<media:song>
	176	<media:author>The Author</media:author>
	177	<url>http://server.com/download.mp3</url>
	178	</media:song>
	179	</root>'''
	180	doc = xml.etree.ElementTree.fromstring(testxml)
	181	find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
	182	self.assertTrue(find('media:song') is not None)
4e408e47 PH	183	self.assertEqual(find('media:song/media:author').text, 'The Author')
4e408e47 PH	184	self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
d7e66d39	185
9d4660ca	186	def test_smuggle_url(self):
e075a44a	187	data = {"ö": "ö", "abc": [3]}
9d4660ca PH	188	url = 'https://foo.bar/baz?x=y#a'
	189	smug_url = smuggle_url(url, data)
	190	unsmug_url, unsmug_data = unsmuggle_url(smug_url)
	191	self.assertEqual(url, unsmug_url)
	192	self.assertEqual(data, unsmug_data)
	193
	194	res_url, res_data = unsmuggle_url(url)
	195	self.assertEqual(res_url, url)
	196	self.assertEqual(res_data, None)
	197
a6a173c2	198	def test_shell_quote(self):
4e408e47 PH	199	args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
4e408e47 PH	200	self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
a6a173c2	201
f53c966a JMF	202	def test_str_to_int(self):
	203	self.assertEqual(str_to_int('123,456'), 123456)
	204	self.assertEqual(str_to_int('123.456'), 123456)
	205
29eb5174	206	def test_url_basename(self):
4e408e47 PH	207	self.assertEqual(url_basename('http://foo.de/'), '')
	208	self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
	209	self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
	210	self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
	211	self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
d6c7a367	212	self.assertEqual(
4e408e47 PH	213	url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
4e408e47 PH	214	'trailer.mp4')
9d4660ca	215
608d11f5 PH	216	def test_parse_duration(self):
608d11f5 PH	217	self.assertEqual(parse_duration(None), None)
a5fb718c S	218	self.assertEqual(parse_duration(False), None)
a5fb718c S	219	self.assertEqual(parse_duration('invalid'), None)
608d11f5 PH	220	self.assertEqual(parse_duration('1'), 1)
	221	self.assertEqual(parse_duration('1337:12'), 80232)
	222	self.assertEqual(parse_duration('9:12:43'), 33163)
2db806b4 S	223	self.assertEqual(parse_duration('12:00'), 720)
2db806b4 S	224	self.assertEqual(parse_duration('00:01:01'), 61)
608d11f5	225	self.assertEqual(parse_duration('x:y'), None)
2db806b4	226	self.assertEqual(parse_duration('3h11m53s'), 11513)
ca7b3246 S	227	self.assertEqual(parse_duration('3h 11m 53s'), 11513)
	228	self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
	229	self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
2db806b4 S	230	self.assertEqual(parse_duration('62m45s'), 3765)
	231	self.assertEqual(parse_duration('6m59s'), 419)
	232	self.assertEqual(parse_duration('49s'), 49)
	233	self.assertEqual(parse_duration('0h0m0s'), 0)
	234	self.assertEqual(parse_duration('0m0s'), 0)
	235	self.assertEqual(parse_duration('0s'), 0)
7adcbe75	236	self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
6a68bb57	237	self.assertEqual(parse_duration('T30M38S'), 1838)
e8df5cee PH	238	self.assertEqual(parse_duration('5 s'), 5)
	239	self.assertEqual(parse_duration('3 min'), 180)
	240	self.assertEqual(parse_duration('2.5 hours'), 9000)
8f4b58d7 PH	241	self.assertEqual(parse_duration('02:03:04'), 7384)
8f4b58d7 PH	242	self.assertEqual(parse_duration('01:02:03:04'), 93784)
608d11f5	243
5aafe895 PH	244	def test_fix_xml_ampersands(self):
	245	self.assertEqual(
	246	fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
	247	self.assertEqual(
	248	fix_xml_ampersands('"&x=y&wrong;&z=a'),
	249	'"&x=y&wrong;&z=a')
	250	self.assertEqual(
	251	fix_xml_ampersands('&'><"'),
	252	'&'><"')
	253	self.assertEqual(
	254	fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
	255	self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
	256
b7ab0590 PH	257	def test_paged_list(self):
	258	def testPL(size, pagesize, sliceargs, expected):
	259	def get_page(pagenum):
	260	firstid = pagenum * pagesize
	261	upto = min(size, pagenum * pagesize + pagesize)
	262	for i in range(firstid, upto):
	263	yield i
	264
9c44d242	265	pl = OnDemandPagedList(get_page, pagesize)
b7ab0590 PH	266	got = pl.getslice(*sliceargs)
	267	self.assertEqual(got, expected)
	268
9c44d242 PH	269	iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
	270	got = iapl.getslice(*sliceargs)
	271	self.assertEqual(got, expected)
	272
b7ab0590 PH	273	testPL(5, 2, (), [0, 1, 2, 3, 4])
	274	testPL(5, 2, (1,), [1, 2, 3, 4])
	275	testPL(5, 2, (2,), [2, 3, 4])
	276	testPL(5, 2, (4,), [4])
	277	testPL(5, 2, (0, 3), [0, 1, 2])
	278	testPL(5, 2, (1, 4), [1, 2, 3])
	279	testPL(5, 2, (2, 99), [2, 3, 4])
	280	testPL(5, 2, (20, 99), [])
	281
b53466e1	282	def test_struct_unpack(self):
4e408e47	283	self.assertEqual(struct_unpack('!B', b'\x00'), (0,))
b53466e1	284
62e609ab	285	def test_read_batch_urls(self):
4e408e47	286	f = io.StringIO('''\xef\xbb\xbf foo
62e609ab PH	287	bar\r
	288	baz
	289	# More after this line\r
	290	; or after this
	291	bam''')
4e408e47	292	self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
62e609ab	293
b74fa8cd JMF	294	def test_urlencode_postdata(self):
	295	data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
	296	self.assertTrue(isinstance(data, bytes))
	297
912b38b4 PH	298	def test_parse_iso8601(self):
	299	self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
	300	self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
	301	self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
6ad4013d	302	self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
912b38b4	303
fac55558 PH	304	def test_strip_jsonp(self):
	305	stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
	306	d = json.loads(stripped)
	307	self.assertEqual(d, [{"id": "532cb", "x": 3}])
	308
609a61e3 PH	309	stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
	310	d = json.loads(stripped)
	311	self.assertEqual(d, {'STATUS': 'OK'})
	312
173a7026	313	def test_uppercase_escape(self):
4e408e47 PH	314	self.assertEqual(uppercase_escape('aä'), 'aä')
4e408e47 PH	315	self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
fac55558	316
a020a0dc PH	317	def test_limit_length(self):
	318	self.assertEqual(limit_length(None, 12), None)
	319	self.assertEqual(limit_length('foo', 12), 'foo')
	320	self.assertTrue(
	321	limit_length('foo bar baz asd', 12).startswith('foo bar'))
	322	self.assertTrue('...' in limit_length('foo bar baz asd', 12))
	323
d05cfe06 S	324	def test_escape_rfc3986(self):
	325	reserved = "!*'();:@&=+$,/?#[]"
	326	unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
	327	self.assertEqual(escape_rfc3986(reserved), reserved)
	328	self.assertEqual(escape_rfc3986(unreserved), unreserved)
	329	self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
	330	self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
	331	self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
	332	self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
	333
	334	def test_escape_url(self):
	335	self.assertEqual(
	336	escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
	337	'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
	338	)
	339	self.assertEqual(
	340	escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
	341	'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
	342	)
	343	self.assertEqual(
	344	escape_url('http://тест.рф/фрагмент'),
	345	'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
	346	)
	347	self.assertEqual(
	348	escape_url('http://тест.рф/абв?абв=абв#абв'),
	349	'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'
	350	)
	351	self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
	352
e7b6d122	353	def test_js_to_json_realworld(self):
410f3e73	354	inp = '''{
e7b6d122	355	'clip':{'provider':'pseudo'}
410f3e73 PH	356	}'''
410f3e73 PH	357	self.assertEqual(js_to_json(inp), '''{
e7b6d122	358	"clip":{"provider":"pseudo"}
410f3e73 PH	359	}''')
	360	json.loads(js_to_json(inp))
	361
e7b6d122 PH	362	inp = '''{
	363	'playlist':[{'controls':{'all':null}}]
	364	}'''
	365	self.assertEqual(js_to_json(inp), '''{
	366	"playlist":[{"controls":{"all":null}}]
	367	}''')
	368
	369	def test_js_to_json_edgecases(self):
	370	on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
	371	self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
	372
	373	on = js_to_json('{"abc": true}')
	374	self.assertEqual(json.loads(on), {'abc': True})
	375
8f4b58d7 PH	376	# Ignore JavaScript code as well
	377	on = js_to_json('''{
	378	"x": 1,
	379	y: "a",
	380	z: some.code
	381	}''')
	382	d = json.loads(on)
	383	self.assertEqual(d['x'], 1)
	384	self.assertEqual(d['y'], 'a')
	385
e4bdb37e PH	386	def test_clean_html(self):
	387	self.assertEqual(clean_html('a:\nb'), 'a: b')
	388	self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
	389
4c0924bb PH	390	def test_intlist_to_bytes(self):
	391	self.assertEqual(
	392	intlist_to_bytes([0, 1, 127, 128, 255]),
	393	b'\x00\x01\x7f\x80\xff')
	394
7d4111ed PH	395	def test_args_to_str(self):
	396	self.assertEqual(
	397	args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
	398	'foo ba/r -baz \'2 be\' \'\''
	399	)
	400
be64b5b0 PH	401	def test_parse_filesize(self):
	402	self.assertEqual(parse_filesize(None), None)
	403	self.assertEqual(parse_filesize(''), None)
	404	self.assertEqual(parse_filesize('91 B'), 91)
	405	self.assertEqual(parse_filesize('foobar'), None)
	406	self.assertEqual(parse_filesize('2 MiB'), 2097152)
	407	self.assertEqual(parse_filesize('5 GB'), 5000000000)
	408	self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
4349c07d	409	self.assertEqual(parse_filesize('1,24 KB'), 1240)
be64b5b0	410
5f9b8394 PH	411	def test_version_tuple(self):
	412	self.assertEqual(version_tuple('1'), (1,))
	413	self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
47d7c642	414	self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
5f9b8394	415
cae97f65 PH	416	def test_detect_exe_version(self):
	417	self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
	418	built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
	419	configuration: --prefix=/usr --extra-'''), '1.2.1')
	420	self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
	421	built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
	422	self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
	423	Trying to open render node...
	424	Success at /dev/dri/renderD128.
	425	ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
	426
05900629 PH	427	def test_age_restricted(self):
	428	self.assertFalse(age_restricted(None, 10)) # unrestricted content
	429	self.assertFalse(age_restricted(1, None)) # unrestricted policy
	430	self.assertFalse(age_restricted(8, 10))
	431	self.assertTrue(age_restricted(18, 14))
	432	self.assertFalse(age_restricted(18, 18))
	433
61ca9a80 PH	434	def test_is_html(self):
	435	self.assertFalse(is_html(b'\x49\x44\x43<html'))
	436	self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
	437	self.assertTrue(is_html( # UTF-8 with BOM
	438	b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
	439	self.assertTrue(is_html( # UTF-16-LE
	440	b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
	441	))
	442	self.assertTrue(is_html( # UTF-16-BE
	443	b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
	444	))
	445	self.assertTrue(is_html( # UTF-32-BE
	446	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'))
	447	self.assertTrue(is_html( # UTF-32-LE
	448	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'))
	449
cfb56d1a PH	450	def test_render_table(self):
	451	self.assertEqual(
	452	render_table(
	453	['a', 'bcd'],
	454	[[123, 4], [9999, 51]]),
	455	'a bcd\n'
	456	'123 4\n'
	457	'9999 51')
	458
	459
dae7c920	460	if __name__ == '__main__':
59ae15a5	461	unittest.main()