1 files changed, 154 insertions, 0 deletions

diff --git a/meta/recipes-devtools/python/python3/CVE-2019-9636.patch b/meta/recipes-devtools/python/python3/CVE-2019-9636.patch
new file mode 100644
index 0000000000..ce8eb666cf
--- /dev/null
+++ b/meta/recipes-devtools/python/python3/CVE-2019-9636.patch
@@ -0,0 +1,154 @@
+From b0305339567b64e07df87620e97e4cb99332aef6 Mon Sep 17 00:00:00 2001
+From: Steve Dower <steve.dower@microsoft.com>
+Date: Sun, 10 Mar 2019 21:59:24 -0700
+Subject: [PATCH] bpo-36216: Add check for characters in netloc that normalize
+ to separators (GH-12201) (#12223)
+
+CVE: CVE-2019-9636
+Upstream-Status: Backport
+[https://github.com/python/cpython/commit/c0d95113b070799679bcb9dc49d4960d82e8bb08]
+
+Signed-off-by: Dan Tran <dantran@microsoft.com>
+---
+ Doc/library/urllib.parse.rst                  | 18 +++++++++++++++
+ Lib/test/test_urlparse.py                     | 23 +++++++++++++++++++
+ Lib/urllib/parse.py                           | 17 ++++++++++++++
+ .../2019-03-06-09-38-40.bpo-36216.6q1m4a.rst  |  3 +++
+ 4 files changed, 61 insertions(+)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst
+
+diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst
+index 6f722a8897..a4c6b6726e 100644
+--- a/Doc/library/urllib.parse.rst
++++ b/Doc/library/urllib.parse.rst
+@@ -120,6 +120,11 @@ or on combining URL components into a URL string.
+    Unmatched square brackets in the :attr:`netloc` attribute will raise a
+    :exc:`ValueError`.
+ 
++   Characters in the :attr:`netloc` attribute that decompose under NFKC
++   normalization (as used by the IDNA encoding) into any of ``/``, ``?``,
++   ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is
++   decomposed before parsing, no error will be raised.
++
+    .. versionchanged:: 3.2
+       Added IPv6 URL parsing capabilities.
+ 
+@@ -128,6 +133,10 @@ or on combining URL components into a URL string.
+       false), in accordance with :rfc:`3986`.  Previously, a whitelist of
+       schemes that support fragments existed.
+ 
++   .. versionchanged:: 3.5.7
++      Characters that affect netloc parsing under NFKC normalization will
++      now raise :exc:`ValueError`.
++
+ 
+ .. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace')
+ 
+@@ -236,6 +245,15 @@ or on combining URL components into a URL string.
+    Unmatched square brackets in the :attr:`netloc` attribute will raise a
+    :exc:`ValueError`.
+ 
++   Characters in the :attr:`netloc` attribute that decompose under NFKC
++   normalization (as used by the IDNA encoding) into any of ``/``, ``?``,
++   ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is
++   decomposed before parsing, no error will be raised.
++
++   .. versionchanged:: 3.5.7
++      Characters that affect netloc parsing under NFKC normalization will
++      now raise :exc:`ValueError`.
++
+ 
+ .. function:: urlunsplit(parts)
+ 
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index e2cf1b7e0f..d0420b0e74 100644
+--- a/Lib/test/test_urlparse.py
++++ b/Lib/test/test_urlparse.py
+@@ -1,3 +1,5 @@
++import sys
++import unicodedata
+ import unittest
+ import urllib.parse
+ 
+@@ -970,6 +972,27 @@ class UrlParseTestCase(unittest.TestCase):
+                 expected.append(name)
+         self.assertCountEqual(urllib.parse.__all__, expected)
+ 
++    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 = '/:#?@'
++        hex_chars = {'{:04X}'.format(ord(c)) for c in illegal_chars}
++        denorm_chars = [
++            c for c in map(chr, 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('\u2100', denorm_chars)
++        self.assertIn('\uFF03', denorm_chars)
++
++        for scheme in ["http", "https", "ftp"]:
++            for c in denorm_chars:
++                url = "{}://netloc{}false.netloc/path".format(scheme, c)
++                with self.subTest(url=url, char='{:04X}'.format(ord(c))):
++                    with self.assertRaises(ValueError):
++                        urllib.parse.urlsplit(url)
+ 
+ class Utility_Tests(unittest.TestCase):
+     """Testcase to test the various utility functions in the urllib."""
+diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
+index 62e8ddf04b..7ba2b445f5 100644
+--- a/Lib/urllib/parse.py
++++ b/Lib/urllib/parse.py
+@@ -327,6 +327,21 @@ 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 any(ord(c) > 127 for c in netloc):
++        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>
+@@ -356,6 +371,7 @@ 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 _coerce_result(v)
+@@ -379,6 +395,7 @@ 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 _coerce_result(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 0000000000..5546394157
+--- /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.
+-- 
+2.22.0.vfs.1.1.57.gbaf16c8
+