Merge remote-tracking branch 'jaimemf/format_spec_groups' (closes #6124)

[youtube-dl] / youtube_dl / compat.py

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index 54ccf1d28773dcc975ed43e8dd3704da77e4d4b4..ace5bd716aac0161b356625260f1138687568314 100644 (file)
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -42,6 +42,11 @@ try:
 except ImportError:  # Python 2
     import cookielib as compat_cookiejar
 
+try:
+    import http.cookies as compat_cookies
+except ImportError:  # Python 2
+    import Cookie as compat_cookies
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
@@ -77,8 +82,12 @@ except ImportError:
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
 except ImportError:  # Python 2
-    # HACK: The following are the correct unquote_to_bytes and unquote
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
     # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
 
@@ -123,7 +132,7 @@ except ImportError:  # Python 2
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        bits = compat_urllib_parse._asciire.split(string)
+        bits = _asciire.split(string)
         res = [bits[0]]
         append = res.append
         for i in range(1, len(bits), 2):
@@ -131,6 +140,15 @@ except ImportError:  # Python 2
             append(bits[i + 1])
         return ''.join(res)
 
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
+
 try:
     compat_str = unicode  # Python 2
 except NameError:
@@ -418,11 +436,17 @@ except TypeError:  # Python 2.6
             yield n
             n += step
 
+if sys.version_info >= (3, 0):
+    from tokenize import tokenize as compat_tokenize_tokenize
+else:
+    from tokenize import generate_tokens as compat_tokenize_tokenize
+
 __all__ = [
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
+    'compat_cookies',
     'compat_expanduser',
     'compat_get_terminal_size',
     'compat_getenv',
@@ -438,9 +462,11 @@ __all__ = [
     'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
+    'compat_tokenize_tokenize',
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
     'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',