bpo-36216: Add check for characters in netloc that normalize to separators (GH-12201)
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index dc21711..8b6c9b1 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -396,6 +396,21 @@
delim = min(delim, wdelim) # use earliest delim position
return url[start:delim], url[delim:] # return (domain, rest)
+def _checknetloc(netloc):
+ if not netloc or netloc.isascii():
+ return
+ # looking for characters like \u2100 that expand to 'a/c'
+ # IDNA uses NFKC equivalence, so normalize for this check
+ import unicodedata
+ netloc2 = unicodedata.normalize('NFKC', netloc)
+ if netloc == netloc2:
+ return
+ _, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay
+ for c in '/?#@:':
+ if c in netloc2:
+ raise ValueError("netloc '" + netloc2 + "' contains invalid " +
+ "characters under NFKC normalization")
+
def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
@@ -424,6 +439,7 @@
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)
@@ -447,6 +463,7 @@
url, fragment = url.split('#', 1)
if '?' in url:
url, query = url.split('?', 1)
+ _checknetloc(netloc)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)