Issue #11467: Fix urlparse behavior when handling urls which contains scheme
specific part only digits. Patch by Santoso Wijaya.
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index a019a7b..e5528fa 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -187,11 +187,15 @@
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return v
- if url.endswith(':') or not url[i+1].isdigit():
- for c in url[:i]:
- if c not in scheme_chars:
- break
- else:
+ for c in url[:i]:
+ if c not in scheme_chars:
+ break
+ else:
+ try:
+ # make sure "url" is not actually a port number (in which case
+ # "scheme" is really part of the path
+ _testportnum = int(url[i+1:])
+ except ValueError:
scheme, url = url[:i].lower(), url[i+1:]
if url[:2] == '//':