[3.8] bpo-27657: Fix urlparse() with numeric paths (GH-661) (#16839)

* 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. (cherry picked from commit 5a88d50) Co-authored-by: Tim Graham <timograham@gmail.com>

Author: orsenthil

Lib/test/test_urlparse.py

@@ -709,15 +709,17 @@ def test_withoutscheme(self):
 
  def test_portseparator(self):
  # Issue 754016 makes changes for port separator ':' from scheme separator
- self.assertEqual(urllib.parse.urlparse("path:80"),
- ('','','path:80','','',''))
+ self.assertEqual(urllib.parse.urlparse("http:80"), ('http','','80','','',''))
+ self.assertEqual(urllib.parse.urlparse("https:80"), ('https','','80','','',''))
+ self.assertEqual(urllib.parse.urlparse("path:80"), ('path','','80','','',''))
  self.assertEqual(urllib.parse.urlparse("http:"),('http','','','','',''))
  self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','',''))
  self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
  ('http','www.python.org:80','','','',''))
  # As usual, need to check bytes input as well
- self.assertEqual(urllib.parse.urlparse(b"path:80"),
- (b'',b'',b'path:80',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"http:80"), (b'http',b'',b'80',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"https:80"), (b'https',b'',b'80',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"path:80"), (b'path',b'',b'80',b'',b'',b''))
  self.assertEqual(urllib.parse.urlparse(b"http:"),(b'http',b'',b'',b'',b'',b''))
  self.assertEqual(urllib.parse.urlparse(b"https:"),(b'https',b'',b'',b'',b'',b''))
  self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"),

Lib/urllib/parse.py

@@ -431,31 +431,11 @@ def urlsplit(url, scheme='', allow_fragments=True):
  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)

Misc/NEWS.d/next/Library/2017-12-26-14-32-23.bpo-27657.6BhyVK.rst

@@ -0,0 +1,2 @@
+Fix urllib.parse.urlparse() with numeric paths. A string like "path:80" is
+no longer parsed as a path but as a scheme ("path") and a path ("80").