# HG changeset patch
# User Mads Kiilerich <mads@kiilerich.com>
# Date 2021-05-18 00:58:06
# Node ID f0fbb0fe4462e2980c1de2263f77e3acc4b8e237
# Parent  070b8c39736fb41a6fb38ffa11a2c5bcbdeb757e

git: update check for invalid URL characters to work with Python versions that include an attempt at fixing the very same problem

With changes like
https://github.com/python/cpython/commit/76cd81d60310d65d01f9d7b48a8985d8ab89c8b4
making it to Python 3.10 and being backported to previous Python versions, the
approach in a8a51a3bdb61 no longer works when combined with
urllib.parse.urlparse in d2f59de17bef: path will never contain the invalid
characters.

To catch this case anyway, add a new check to verify that the parsed URL can
roundtrip back to the original representation with urllib.parse.urlunparse .

The actual exception might vary, but one of them should always fire.

There is a risk that the new check will reject some URLs that somehow isn't
normalized. No such cases have been found yet.

diff --git a/kallithea/lib/vcs/backends/git/repository.py b/kallithea/lib/vcs/backends/git/repository.py
--- a/kallithea/lib/vcs/backends/git/repository.py
+++ b/kallithea/lib/vcs/backends/git/repository.py
@@ -192,7 +192,11 @@ class GitRepository(BaseRepository):
         >>> GitRepository._check_url('git://example.com/\t')
         Traceback (most recent call last):
         ...
+        urllib.error.URLError: <urlopen error Invalid ...>
+
+        The failure above will be one of, depending on the level of WhatWG support:
         urllib.error.URLError: <urlopen error Invalid whitespace character in path: '\t'>
+        urllib.error.URLError: <urlopen error Invalid url: 'git://example.com/	' normalizes to 'git://example.com/'>
         """
         try:
             parsed_url = urllib.parse.urlparse(url)
@@ -204,6 +208,10 @@ class GitRepository(BaseRepository):
         if os.path.isabs(url) and os.path.isdir(url):
             return
 
+        unparsed_url = urllib.parse.urlunparse(parsed_url)
+        if unparsed_url != url:
+            raise urllib.error.URLError("Invalid url: '%s' normalizes to '%s'" % (url, unparsed_url))
+
         if parsed_url.scheme == 'git':
             # Mitigate problems elsewhere with incorrect handling of encoded paths.
             # Don't trust urllib.parse.unquote but be prepared for more flexible implementations elsewhere.