[utils] Allow None in remove_{start,end}

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index e8b09e9db9fdc76aa9d8e2cca5a7dcc6fd2054f7..5301d07404b4d83c4df5c99dd9a69f577b87f091 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -50,6 +50,7 @@ from .compat import (
     compat_urllib_parse,
     compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
+    compat_urllib_parse_unquote_plus,
     compat_urllib_request,
     compat_urlparse,
     compat_xpath,
@@ -104,9 +105,9 @@ KNOWN_EXTENSIONS = (
     'f4f', 'f4m', 'm3u8', 'smil')
 
 # needed for sanitizing filenames in restricted mode
-ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ',
-                        itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOUUUUYP', ['ss'],
-                                        'aaaaaa', ['ae'], 'ceeeeiiiionoooooouuuuypy')))
+ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ',
+                        itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOO', ['OE'], 'UUUUYP', ['ss'],
+                                        'aaaaaa', ['ae'], 'ceeeeiiiionoooooo', ['oe'], 'uuuuypy')))
 
 
 def preferredencoding():
@@ -882,11 +883,17 @@ def make_socks_conn_class(base_class, socks_proxy):
     elif url_components.scheme.lower() == 'socks4a':
         socks_type = ProxyType.SOCKS4A
 
+    def unquote_if_non_empty(s):
+        if not s:
+            return s
+        return compat_urllib_parse_unquote_plus(s)
+
     proxy_args = (
         socks_type,
         url_components.hostname, url_components.port or 1080,
         True,  # Remote DNS
-        url_components.username, url_components.password
+        unquote_if_non_empty(url_components.username),
+        unquote_if_non_empty(url_components.password),
     )
 
     class SocksConnection(base_class):
@@ -1542,15 +1549,11 @@ def setproctitle(title):
 
 
 def remove_start(s, start):
-    if s.startswith(start):
-        return s[len(start):]
-    return s
+    return s[len(start):] if s is not None and s.startswith(start) else s
 
 
 def remove_end(s, end):
-    if s.endswith(end):
-        return s[:-len(end)]
-    return s
+    return s[:-len(end)] if s is not None and s.endswith(end) else s
 
 
 def remove_quotes(s):
@@ -1912,24 +1915,38 @@ def js_to_json(code):
         v = m.group(0)
         if v in ('true', 'false', 'null'):
             return v
-        if v.startswith('"'):
-            v = re.sub(r"\\'", "'", v[1:-1])
-        elif v.startswith("'"):
-            v = v[1:-1]
-            v = re.sub(r"\\\\|\\'|\"", lambda m: {
-                '\\\\': '\\\\',
-                "\\'": "'",
+        elif v.startswith('/*') or v == ',':
+            return ""
+
+        if v[0] in ("'", '"'):
+            v = re.sub(r'(?s)\\.|"', lambda m: {
                 '"': '\\"',
-            }[m.group(0)], v)
+                "\\'": "'",
+                '\\\n': '',
+                '\\x': '\\u00',
+            }.get(m.group(0), m.group(0)), v[1:-1])
+
+        INTEGER_TABLE = (
+            (r'^0[xX][0-9a-fA-F]+', 16),
+            (r'^0+[0-7]+', 8),
+        )
+
+        for regex, base in INTEGER_TABLE:
+            im = re.match(regex, v)
+            if im:
+                i = int(im.group(0), base)
+                return '"%d":' % i if v.endswith(':') else '%d' % i
+
         return '"%s"' % v
 
-    res = re.sub(r'''(?x)
-        "(?:[^"\\]*(?:\\\\|\\['"nu]))*[^"\\]*"|
-        '(?:[^'\\]*(?:\\\\|\\['"nu]))*[^'\\]*'|
-        [a-zA-Z_][.a-zA-Z_0-9]*
+    return re.sub(r'''(?sx)
+        "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
+        '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
+        /\*.*?\*/|,(?=\s*[\]}])|
+        [a-zA-Z_][.a-zA-Z_0-9]*|
+        (?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:\s*:)?|
+        [0-9]+(?=\s*:)
         ''', fix_kv, code)
-    res = re.sub(r',(\s*[\]}])', lambda m: m.group(1), res)
-    return res
 
 
 def qualities(quality_ids):
@@ -2015,11 +2032,7 @@ def mimetype2ext(mt):
 
 
 def urlhandle_detect_ext(url_handle):
-    try:
-        url_handle.headers
-        getheader = lambda h: url_handle.headers[h]
-    except AttributeError:  # Python < 3
-        getheader = url_handle.info().getheader
+    getheader = url_handle.headers.get
 
     cd = getheader('Content-Disposition')
     if cd: