bpo-27657: Fix urlparse() with numeric paths (#661)
* bpo-27657: Fix urlparse() with numeric paths
Revert parsing decision from bpo-754016 in favor of the documented
consensus in bpo-16932 of how to treat strings without a // to
designate the netloc.
* bpo-22891: Remove urlsplit() optimization for 'http' prefixed inputs.
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 3a38dc1..31fd7e1 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -431,31 +431,11 @@
netloc = query = fragment = ''
i = url.find(':')
if i > 0:
- if url[:i] == 'http': # optimize the common case
- url = url[i+1:]
- if url[:2] == '//':
- netloc, url = _splitnetloc(url, 2)
- if (('[' in netloc and ']' not in netloc) or
- (']' in netloc and '[' not in netloc)):
- raise ValueError("Invalid IPv6 URL")
- if allow_fragments and '#' in url:
- url, fragment = url.split('#', 1)
- if '?' in url:
- url, query = url.split('?', 1)
- _checknetloc(netloc)
- v = SplitResult('http', netloc, url, query, fragment)
- _parse_cache[key] = v
- return _coerce_result(v)
for c in url[:i]:
if c not in scheme_chars:
break
else:
- # make sure "url" is not actually a port number (in which case
- # "scheme" is really part of the path)
- rest = url[i+1:]
- if not rest or any(c not in '0123456789' for c in rest):
- # not a port number
- scheme, url = url[:i].lower(), rest
+ scheme, url = url[:i].lower(), url[i+1:]
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)