| From 3e3669c9c41a27e1466e2c28b3906e3dd0ce3e7e Mon Sep 17 00:00:00 2001 |
| From: Steve Dower <steve.dower@python.org> |
| Date: Thu, 7 Mar 2019 08:25:22 -0800 |
| Subject: [PATCH] bpo-36216: Add check for characters in netloc that normalize |
| to separators (GH-12201) |
| |
| CVE: CVE-2019-9636 |
| |
| Upstream-Status: Backport https://github.com/python/cpython/pull/12216/commits/3e3669c9c41a27e1466e2c28b3906e3dd0ce3e7e |
| |
| Signed-off-by: Martin Jansa <Martin.Jansa@gmail.com> |
| --- |
| Doc/library/urlparse.rst | 20 ++++++++++++++++ |
| Lib/test/test_urlparse.py | 24 +++++++++++++++++++ |
| Lib/urlparse.py | 17 +++++++++++++ |
| .../2019-03-06-09-38-40.bpo-36216.6q1m4a.rst | 3 +++ |
| 4 files changed, 64 insertions(+) |
| create mode 100644 Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst |
| |
| diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py |
| index 4e1ded73c266..73b0228ea8e3 100644 |
| --- a/Lib/test/test_urlparse.py |
| +++ b/Lib/test/test_urlparse.py |
| @@ -1,4 +1,6 @@ |
| from test import test_support |
| +import sys |
| +import unicodedata |
| import unittest |
| import urlparse |
| |
| @@ -624,6 +626,28 @@ def test_portseparator(self): |
| self.assertEqual(urlparse.urlparse("http://www.python.org:80"), |
| ('http','www.python.org:80','','','','')) |
| |
| + def test_urlsplit_normalization(self): |
| + # Certain characters should never occur in the netloc, |
| + # including under normalization. |
| + # Ensure that ALL of them are detected and cause an error |
| + illegal_chars = u'/:#?@' |
| + hex_chars = {'{:04X}'.format(ord(c)) for c in illegal_chars} |
| + denorm_chars = [ |
| + c for c in map(unichr, range(128, sys.maxunicode)) |
| + if (hex_chars & set(unicodedata.decomposition(c).split())) |
| + and c not in illegal_chars |
| + ] |
| + # Sanity check that we found at least one such character |
| + self.assertIn(u'\u2100', denorm_chars) |
| + self.assertIn(u'\uFF03', denorm_chars) |
| + |
| + for scheme in [u"http", u"https", u"ftp"]: |
| + for c in denorm_chars: |
| + url = u"{}://netloc{}false.netloc/path".format(scheme, c) |
| + print "Checking %r" % url |
| + with self.assertRaises(ValueError): |
| + urlparse.urlsplit(url) |
| + |
| def test_main(): |
| test_support.run_unittest(UrlParseTestCase) |
| |
| diff --git a/Lib/urlparse.py b/Lib/urlparse.py |
| index f7c2b032b097..54eda08651ab 100644 |
| --- a/Lib/urlparse.py |
| +++ b/Lib/urlparse.py |
| @@ -165,6 +165,21 @@ def _splitnetloc(url, start=0): |
| delim = min(delim, wdelim) # use earliest delim position |
| return url[start:delim], url[delim:] # return (domain, rest) |
| |
| +def _checknetloc(netloc): |
| + if not netloc or not isinstance(netloc, unicode): |
| + 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> |
| @@ -193,6 +208,7 @@ def urlsplit(url, scheme='', allow_fragments=True): |
| 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 v |
| @@ -216,6 +232,7 @@ def urlsplit(url, scheme='', allow_fragments=True): |
| 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 v |
| diff --git a/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst b/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst |
| new file mode 100644 |
| index 000000000000..1e1ad92c6feb |
| --- /dev/null |
| +++ b/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst |
| @@ -0,0 +1,3 @@ |
| +Changes urlsplit() to raise ValueError when the URL contains characters that |
| +decompose under IDNA encoding (NFKC-normalization) into characters that |
| +affect how the URL is parsed. |
| \ No newline at end of file |