X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/139d14b198add5b26a11ed5dca022feaa6581d98..ed1c1d2a80ce1ad325853e6c59a1fbaf2156adcc:/test/test_utils.py
diff --git a/test/test_utils.py b/test/test_utils.py
index e13e11b..efa73d0 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -18,50 +18,90 @@ import xml.etree.ElementTree
from youtube_dl.utils import (
age_restricted,
args_to_str,
+ encode_base_n,
clean_html,
+ date_from_str,
DateRange,
detect_exe_version,
+ determine_ext,
+ dict_get,
+ encode_compat_str,
encodeFilename,
escape_rfc3986,
escape_url,
+ extract_attributes,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
+ get_element_by_class,
+ get_element_by_attribute,
+ get_elements_by_class,
+ get_elements_by_attribute,
InAdvancePagedList,
intlist_to_bytes,
is_html,
js_to_json,
limit_length,
+ mimetype2ext,
+ month_by_name,
+ multipart_encode,
+ ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
+ parse_age_limit,
parse_duration,
parse_filesize,
+ parse_count,
parse_iso8601,
+ pkcs1pad,
read_batch_urls,
sanitize_filename,
sanitize_path,
+ expand_path,
prepend_extension,
replace_extension,
+ remove_start,
+ remove_end,
+ remove_quotes,
shell_quote,
smuggle_url,
str_to_int,
strip_jsonp,
- struct_unpack,
timeconvert,
unescapeHTML,
unified_strdate,
+ unified_timestamp,
unsmuggle_url,
uppercase_escape,
lowercase_escape,
url_basename,
+ base_url,
+ urljoin,
urlencode_postdata,
+ urshift,
+ update_url_query,
version_tuple,
xpath_with_ns,
+ xpath_element,
xpath_text,
+ xpath_attr,
render_table,
match_str,
parse_dfxp_time_expr,
dfxp2srt,
+ cli_option,
+ cli_valueless_option,
+ cli_bool_option,
+ parse_codecs,
+)
+from youtube_dl.compat import (
+ compat_chr,
+ compat_etree_fromstring,
+ compat_getenv,
+ compat_os_name,
+ compat_setenv,
+ compat_urlparse,
+ compat_parse_qs,
)
@@ -118,8 +158,8 @@ class TestUtil(unittest.TestCase):
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')
+ tests = 'aäb\u4e2d\u56fd\u7684c'
+ self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
@@ -134,6 +174,10 @@ class TestUtil(unittest.TestCase):
self.assertTrue(sanitize_filename('-', restricted=True) != '')
self.assertTrue(sanitize_filename(':', restricted=True) != '')
+ self.assertEqual(sanitize_filename(
+ 'ÃÃÃÃÃÃ
ÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÅÃÅÃÃÃÃÅ°ÃÃÃà áâãäåæçèéêëìÃîïðñòóôõöÅøÅùúûüűýþÿ', restricted=True),
+ 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
+
def test_sanitize_ids(self):
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
@@ -175,6 +219,18 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+ def test_expand_path(self):
+ def env(var):
+ return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
+
+ compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
+ self.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
+ self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
+ self.assertEqual(expand_path('~'), compat_getenv('HOME'))
+ self.assertEqual(
+ expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
+ '%s/expanded' % compat_getenv('HOME'))
+
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
@@ -191,6 +247,25 @@ class TestUtil(unittest.TestCase):
self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
+ def test_remove_start(self):
+ self.assertEqual(remove_start(None, 'A - '), None)
+ self.assertEqual(remove_start('A - B', 'A - '), 'B')
+ self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
+
+ def test_remove_end(self):
+ self.assertEqual(remove_end(None, ' - B'), None)
+ self.assertEqual(remove_end('A - B', ' - B'), 'A')
+ self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
+
+ def test_remove_quotes(self):
+ self.assertEqual(remove_quotes(None), None)
+ self.assertEqual(remove_quotes('"'), '"')
+ self.assertEqual(remove_quotes("'"), "'")
+ self.assertEqual(remove_quotes(';'), ';')
+ self.assertEqual(remove_quotes('";'), '";')
+ self.assertEqual(remove_quotes('""'), '')
+ self.assertEqual(remove_quotes('";"'), ';')
+
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([]), [])
@@ -202,8 +277,18 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(unescapeHTML('/'), '/')
self.assertEqual(unescapeHTML('/'), '/')
- self.assertEqual(
- unescapeHTML('é'), 'é')
+ self.assertEqual(unescapeHTML('é'), 'é')
+ self.assertEqual(unescapeHTML(''), '')
+ self.assertEqual(unescapeHTML('&a"'), '&a"')
+ # HTML5 entities
+ self.assertEqual(unescapeHTML('.''), '.\'')
+
+ def test_date_from_str(self):
+ self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
+ self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
+ self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
+ self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
+ self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
def test_daterange(self):
_20century = DateRange("19000101", "20000101")
@@ -227,7 +312,44 @@ class TestUtil(unittest.TestCase):
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
+ self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
+ self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
+ self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
+ self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
+ self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
+ self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
+ self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
+
+ def test_unified_timestamps(self):
+ self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
+ self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
+ self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
+ self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
+ self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
+ self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
+ self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
+ self.assertEqual(
+ unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
+ 1417001400)
+ self.assertEqual(
+ unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
+ 1422902860)
+ self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
+ self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
+ self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
+ self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
+ self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
+ self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
+ self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
+ self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
+
+ def test_determine_ext(self):
+ self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
+ self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
+ self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
+ self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
+ self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
def test_find_xpath_attr(self):
testxml = '''
@@ -235,12 +357,21 @@ class TestUtil(unittest.TestCase):
+
'''
- doc = xml.etree.ElementTree.fromstring(testxml)
+ doc = compat_etree_fromstring(testxml)
+ self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
+ self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
+ self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
+ self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
+ self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
+ self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
+ self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
+ self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
def test_xpath_with_ns(self):
testxml = '''
@@ -249,23 +380,56 @@ class TestUtil(unittest.TestCase):
http://server.com/download.mp3
'''
- doc = xml.etree.ElementTree.fromstring(testxml)
+ doc = compat_etree_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_xpath_element(self):
+ doc = xml.etree.ElementTree.Element('root')
+ div = xml.etree.ElementTree.SubElement(doc, 'div')
+ p = xml.etree.ElementTree.SubElement(div, 'p')
+ p.text = 'Foo'
+ self.assertEqual(xpath_element(doc, 'div/p'), p)
+ self.assertEqual(xpath_element(doc, ['div/p']), p)
+ self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
+ self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
+ self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
+ self.assertTrue(xpath_element(doc, 'div/bar') is None)
+ self.assertTrue(xpath_element(doc, ['div/bar']) is None)
+ self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
+ self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
+ self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
+ self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
+
def test_xpath_text(self):
testxml = '''
'''
- doc = xml.etree.ElementTree.fromstring(testxml)
+ doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+ self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+ def test_xpath_attr(self):
+ testxml = '''
+
+ '''
+ doc = compat_etree_fromstring(testxml)
+ self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
+ self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
+ self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
+ self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
+ self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
+ self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
+ self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
+
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
@@ -278,9 +442,17 @@ class TestUtil(unittest.TestCase):
self.assertEqual(res_url, url)
self.assertEqual(res_data, None)
+ smug_url = smuggle_url(url, {'a': 'b'})
+ smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
+ res_url, res_data = unsmuggle_url(smug_smug_url)
+ self.assertEqual(res_url, url)
+ self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
+
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename('ñâ¬Ã\'.mp4')]
- self.assertEqual(shell_quote(args), """ffmpeg -i 'ñâ¬Ã'"'"'.mp4'""")
+ self.assertEqual(
+ shell_quote(args),
+ """ffmpeg -i 'ñâ¬Ã'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñâ¬Ã'.mp4"''')
def test_str_to_int(self):
self.assertEqual(str_to_int('123,456'), 123456)
@@ -296,6 +468,47 @@ class TestUtil(unittest.TestCase):
url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
'trailer.mp4')
+ def test_base_url(self):
+ self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
+ self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
+ self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
+ self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
+ self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
+
+ def test_urljoin(self):
+ self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', None), None)
+ self.assertEqual(urljoin('http://foo.de/', ''), None)
+ self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
+ self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
+
+ def test_parse_age_limit(self):
+ self.assertEqual(parse_age_limit(None), None)
+ self.assertEqual(parse_age_limit(False), None)
+ self.assertEqual(parse_age_limit('invalid'), None)
+ self.assertEqual(parse_age_limit(0), 0)
+ self.assertEqual(parse_age_limit(18), 18)
+ self.assertEqual(parse_age_limit(21), 21)
+ self.assertEqual(parse_age_limit(22), None)
+ self.assertEqual(parse_age_limit('18'), 18)
+ self.assertEqual(parse_age_limit('18+'), 18)
+ self.assertEqual(parse_age_limit('PG-13'), 13)
+ self.assertEqual(parse_age_limit('TV-14'), 14)
+ self.assertEqual(parse_age_limit('TV-MA'), 17)
+
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
@@ -324,6 +537,9 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
+ self.assertEqual(parse_duration('87 Min.'), 5220)
+ self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
+ self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
def test_fix_xml_ampersands(self):
self.assertEqual(
@@ -363,9 +579,6 @@ class TestUtil(unittest.TestCase):
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
@@ -379,11 +592,83 @@ class TestUtil(unittest.TestCase):
data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
self.assertTrue(isinstance(data, bytes))
+ def test_update_url_query(self):
+ def query_dict(url):
+ return compat_parse_qs(compat_urlparse.urlparse(url).query)
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
+ query_dict('http://example.com/path?quality=HD&format=mp4'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
+ query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path?manifest=f4m', {'manifest': []})),
+ query_dict('http://example.com/path'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
+ query_dict('http://example.com/path?system=LINUX'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'width': 1080, 'height': 720})),
+ query_dict('http://example.com/path?width=1080&height=720'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'bitrate': 5020.43})),
+ query_dict('http://example.com/path?bitrate=5020.43'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'test': '第äºè¡ÑеÑÑ'})),
+ query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
+
+ def test_multipart_encode(self):
+ self.assertEqual(
+ multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
+ self.assertEqual(
+ multipart_encode({'æ¬ä½'.encode('utf-8'): 'å¼'.encode('utf-8')}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
+ self.assertRaises(
+ ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
+
+ def test_dict_get(self):
+ FALSE_VALUES = {
+ 'none': None,
+ 'false': False,
+ 'zero': 0,
+ 'empty_string': '',
+ 'empty_list': [],
+ }
+ d = FALSE_VALUES.copy()
+ d['a'] = 42
+ self.assertEqual(dict_get(d, 'a'), 42)
+ self.assertEqual(dict_get(d, 'b'), None)
+ self.assertEqual(dict_get(d, 'b', 42), 42)
+ self.assertEqual(dict_get(d, ('a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', )), None)
+ self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
+ for key, false_value in FALSE_VALUES.items():
+ self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
+ self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
+
+ def test_encode_compat_str(self):
+ self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'ÑеÑÑ')
+ self.assertEqual(encode_compat_str('ÑеÑÑ', 'utf-8'), 'ÑеÑÑ')
+
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)
+ self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
+ self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@@ -394,6 +679,18 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'STATUS': 'OK'})
+ stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
+ stripped = strip_jsonp('window.cb && window.cb({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
+ stripped = strip_jsonp('window.cb && cb({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), 'ð')
@@ -409,6 +706,45 @@ class TestUtil(unittest.TestCase):
limit_length('foo bar baz asd', 12).startswith('foo bar'))
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
+ def test_mimetype2ext(self):
+ self.assertEqual(mimetype2ext(None), None)
+ self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
+ self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
+ self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
+ self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
+ self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
+
+ def test_month_by_name(self):
+ self.assertEqual(month_by_name(None), None)
+ self.assertEqual(month_by_name('December', 'en'), 12)
+ self.assertEqual(month_by_name('décembre', 'fr'), 12)
+ self.assertEqual(month_by_name('December'), 12)
+ self.assertEqual(month_by_name('décembre'), None)
+ self.assertEqual(month_by_name('Unknown', 'unknown'), None)
+
+ def test_parse_codecs(self):
+ self.assertEqual(parse_codecs(''), {})
+ self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
+ 'vcodec': 'avc1.77.30',
+ 'acodec': 'mp4a.40.2',
+ })
+ self.assertEqual(parse_codecs('mp4a.40.2'), {
+ 'vcodec': 'none',
+ 'acodec': 'mp4a.40.2',
+ })
+ self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
+ 'vcodec': 'avc1.42001e',
+ 'acodec': 'mp4a.40.5',
+ })
+ self.assertEqual(parse_codecs('avc3.640028'), {
+ 'vcodec': 'avc3.640028',
+ 'acodec': 'none',
+ })
+ self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
+ 'vcodec': 'h264',
+ 'acodec': 'aac',
+ })
+
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"
unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
@@ -430,11 +766,11 @@ class TestUtil(unittest.TestCase):
)
self.assertEqual(
escape_url('http://ÑеÑÑ.ÑÑ/ÑÑагменÑ'),
- 'http://ÑеÑÑ.ÑÑ/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+ 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
)
self.assertEqual(
escape_url('http://ÑеÑÑ.ÑÑ/абв?абв=абв#абв'),
- 'http://ÑеÑÑ.ÑÑ/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+ 'http://xn--e1aybc.xn--p1ai/%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')
@@ -454,10 +790,28 @@ class TestUtil(unittest.TestCase):
"playlist":[{"controls":{"all":null}}]
}''')
+ inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
+ self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
+
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))
+ inp = '''{
+ 0:{src:'skipped', type: 'application/dash+xml'},
+ 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
+ }'''
+ self.assertEqual(js_to_json(inp), '''{
+ "0":{"src":"skipped", "type": "application/dash+xml"},
+ "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
+ }''')
+
+ inp = '''{"foo":101}'''
+ self.assertEqual(js_to_json(inp), '''{"foo":101}''')
+
+ inp = '''{"duration": "00:01:07"}'''
+ self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
+
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"})
@@ -478,12 +832,101 @@ class TestUtil(unittest.TestCase):
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
+ on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
+ self.assertEqual(json.loads(on), ['abc', 'def'])
+
+ on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
+ self.assertEqual(json.loads(on), ['abc', 'def'])
+
on = js_to_json('{"abc": "def",}')
self.assertEqual(json.loads(on), {'abc': 'def'})
+ on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'abc': 'def'})
+
+ on = js_to_json('{ 0: /* " \n */ ",]" , }')
+ self.assertEqual(json.loads(on), {'0': ',]'})
+
+ on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
+ self.assertEqual(json.loads(on), {'0': ',]'})
+
+ on = js_to_json('{ 0: // comment\n1 }')
+ self.assertEqual(json.loads(on), {'0': 1})
+
+ on = js_to_json(r'["
x<\/p>"]')
+ self.assertEqual(json.loads(on), ['
x
'])
+
+ on = js_to_json(r'["\xaa"]')
+ self.assertEqual(json.loads(on), ['\u00aa'])
+
+ on = js_to_json("['a\\\nb']")
+ self.assertEqual(json.loads(on), ['ab'])
+
+ on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
+ self.assertEqual(json.loads(on), ['ab'])
+
+ on = js_to_json('{0xff:0xff}')
+ self.assertEqual(json.loads(on), {'255': 255})
+
+ on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'255': 255})
+
+ on = js_to_json('{077:077}')
+ self.assertEqual(json.loads(on), {'63': 63})
+
+ on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'63': 63})
+
+ on = js_to_json('{42:42}')
+ self.assertEqual(json.loads(on), {'42': 42})
+
+ on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'42': 42})
+
+ def test_extract_attributes(self):
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(""), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': "a 'b' c"})
+ self.assertEqual(extract_attributes(''), {'x': 'a "b" c'})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': '&'}) # XML
+ self.assertEqual(extract_attributes(''), {'x': '"'})
+ self.assertEqual(extract_attributes(''), {'x': '£'}) # HTML 3.2
+ self.assertEqual(extract_attributes(''), {'x': 'λ'}) # HTML 4.0
+ self.assertEqual(extract_attributes(''), {'x': '&foo'})
+ self.assertEqual(extract_attributes(''), {'x': "'"})
+ self.assertEqual(extract_attributes(''), {'x': '"'})
+ self.assertEqual(extract_attributes(''), {'x': None})
+ self.assertEqual(extract_attributes(''), {'x': 'y', 'a': None})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'y': '2', 'x': '3'})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': 'y'})
+ self.assertEqual(extract_attributes(""), {'x': 'y'})
+ self.assertEqual(extract_attributes(''), {'x': '\ny\n'})
+ self.assertEqual(extract_attributes(''), {'caps': 'x'}) # Names lowercased
+ self.assertEqual(extract_attributes(''), {'x': '2'})
+ self.assertEqual(extract_attributes(''), {'x': '2'})
+ self.assertEqual(extract_attributes(''), {'_:funny-name1': '1'})
+ self.assertEqual(extract_attributes(''), {'x': 'Fáilte ä¸ç \U0001f600'})
+ self.assertEqual(extract_attributes(''), {'x': 'décompose\u0301'})
+ # "Narrow" Python builds don't support unicode code points outside BMP.
+ try:
+ compat_chr(0x10000)
+ supports_outside_bmp = True
+ except ValueError:
+ supports_outside_bmp = False
+ if supports_outside_bmp:
+ self.assertEqual(extract_attributes(''), {'x': 'Smile \U0001f600!'})
+ # Malformed HTML should not break attributes extraction on older Python
+ self.assertEqual(extract_attributes(''), {})
+
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
+ self.assertEqual(clean_html('a
\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
self.assertEqual(
@@ -493,7 +936,7 @@ class TestUtil(unittest.TestCase):
def test_args_to_str(self):
self.assertEqual(
args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
- 'foo ba/r -baz \'2 be\' \'\''
+ 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""'
)
def test_parse_filesize(self):
@@ -504,7 +947,21 @@ class TestUtil(unittest.TestCase):
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('1.2tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
+ self.assertEqual(parse_filesize('1,24 kb'), 1240)
+ self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
+
+ def test_parse_count(self):
+ self.assertEqual(parse_count(None), None)
+ self.assertEqual(parse_count(''), None)
+ self.assertEqual(parse_count('0'), 0)
+ self.assertEqual(parse_count('1000'), 1000)
+ self.assertEqual(parse_count('1.000'), 1000)
+ self.assertEqual(parse_count('1.1k'), 1100)
+ self.assertEqual(parse_count('1.1kk'), 1100000)
+ self.assertEqual(parse_count('1.1kk '), 1100000)
+ self.assertEqual(parse_count('1.1kk views'), 1100000)
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
@@ -586,12 +1043,13 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
{'like_count': 190, 'dislike_count': 10}))
def test_parse_dfxp_time_expr(self):
- self.assertEqual(parse_dfxp_time_expr(None), 0.0)
- self.assertEqual(parse_dfxp_time_expr(''), 0.0)
+ self.assertEqual(parse_dfxp_time_expr(None), None)
+ self.assertEqual(parse_dfxp_time_expr(''), None)
self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+ self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
def test_dfxp2srt(self):
dfxp_data = '''
@@ -601,9 +1059,12 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
The following line contains Chinese characters and special symbols
第äºè¡
âªâª
Third
Line
+ Lines with invalid timestamps are ignored
+ Ignore, two
+ Ignored, three