read_batch_urls,
sanitize_filename,
sanitize_path,
- sanitize_url_path_consecutive_slashes,
+ prepend_extension,
+ replace_extension,
shell_quote,
smuggle_url,
str_to_int,
unified_strdate,
unsmuggle_url,
uppercase_escape,
+ lowercase_escape,
url_basename,
urlencode_postdata,
- url_infer_protocol,
version_tuple,
xpath_with_ns,
xpath_text,
render_table,
match_str,
+ parse_dfxp_time_expr,
+ dfxp2srt,
)
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
- def test_sanitize_url_path_consecutive_slashes(self):
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
- 'http://hostname/foo/bar/filename.html')
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
- 'http://hostname/foo/bar/filename.html')
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname//'),
- 'http://hostname/')
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
- 'http://hostname/foo/bar/filename.html')
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname/'),
- 'http://hostname/')
- self.assertEqual(
- sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
- 'http://hostname/abc/')
+ 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')
+ self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+ self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
+ self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
+ self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+
+ def test_replace_extension(self):
+ self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
+ self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
+ self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
+ self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
+ self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
+ self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
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])
url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
'trailer.mp4')
- def test_url_infer_protocol(self):
- self.assertEqual(url_infer_protocol('http://foo.com/', '//bar.com/'), 'http://bar.com/')
- self.assertEqual(url_infer_protocol('http://foo.com/', 'https://bar.com/'), 'https://bar.com/')
-
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
+ def test_lowercase_escape(self):
+ self.assertEqual(lowercase_escape('aä'), 'aä')
+ self.assertEqual(lowercase_escape('\\u0026'), '&')
+
def test_limit_length(self):
self.assertEqual(limit_length(None, 12), None)
self.assertEqual(limit_length('foo', 12), 'foo')
'like_count > 100 & dislike_count <? 50 & description',
{'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('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)
+
+ def test_dfxp2srt(self):
+ dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
+ <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
+ <p begin="1" end="2">第二行<br/>♪♪</p>
+ <p begin="2" dur="1"><span>Third<br/>Line</span></p>
+ </div>
+ </body>
+ </tt>'''
+ srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The following line contains Chinese characters and special symbols
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+♪♪
+
+3
+00:00:02,000 --> 00:00:03,000
+Third
+Line
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data), srt_data)
+
if __name__ == '__main__':
unittest.main()