[CVE-2022-0391] bpo-43882 - urllib.parse should sanitize urls containing ASCII newlin...

Co-authored-by: Gregory P. Smith <greg@krypto.org>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
(cherry picked from commit 76cd81d)
Co-authored-by: Senthil Kumaran <senthil@uthcode.com>
Co-authored-by: Senthil Kumaran <skumaran@gatech.edu>
(cherry picked from commit 515a7bc)

Co-authored-by: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>
Change-Id: Ia736aa48623abda5b1f8d10c9512dcbb139db492
Signed-off-by: JinWang An <jinwang.an@samsung.com>

diff --git a/Doc/library/urllib.rst b/Doc/library/urllib.rst
index 084d567..aa1a388 100644 (file)
--- a/Doc/library/urllib.rst
+++ b/Doc/library/urllib.rst
@@ -284,6 +284,13 @@ Utility functions
    :func:`parse_qs` and :func:`parse_qsl` which are used to parse query strings
    into Python data structures.
 
+.. seealso::
+
+   `WHATWG`_ -  URL Living standard
+         Working Group for the URL Standard that defines URLs, domains, IP addresses, the
+               application/x-www-form-urlencoded format, and their API.
+
+.. _WHATWG: https://url.spec.whatwg.org/
 
 .. function:: pathname2url(path)
 

diff --git a/Doc/library/urlparse.rst b/Doc/library/urlparse.rst
index c77fb89..1588d8a 100644 (file)
--- a/Doc/library/urlparse.rst
+++ b/Doc/library/urlparse.rst
@@ -247,6 +247,9 @@ The :mod:`urlparse` module defines the following functions:
    decomposed before parsing, or is not a Unicode string, no error will be
    raised.
 
+   Following the `WHATWG spec`_ that updates RFC 3986, ASCII newline
+   ``\n``, ``\r`` and tab ``\t`` characters are stripped from the URL.
+
    .. versionadded:: 2.2
 
    .. versionchanged:: 2.5
@@ -256,6 +259,8 @@ The :mod:`urlparse` module defines the following functions:
       Characters that affect netloc parsing under NFKC normalization will
       now raise :exc:`ValueError`.
 
+.. _WHATWG spec: https://url.spec.whatwg.org/#concept-basic-url-parser
+
 
 .. function:: urlunsplit(parts)
 

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 86c4a05..1bee8ad 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -504,6 +504,55 @@ class UrlParseTestCase(unittest.TestCase):
         p = urlparse.urlsplit(url)
         self.assertEqual(p.port, None)
 
+    def test_urlsplit_remove_unsafe_bytes(self):
+        # Remove ASCII tabs and newlines from input, for http common case scenario.
+        url = "h\nttp://www.python\n.org\t/java\nscript:\talert('msg\r\n')/?query\n=\tsomething#frag\nment"
+        p = urllib.parse.urlsplit(url)
+        self.assertEqual(p.scheme, "http")
+        self.assertEqual(p.netloc, "www.python.org")
+        self.assertEqual(p.path, "/javascript:alert('msg')/")
+        self.assertEqual(p.query, "query=something")
+        self.assertEqual(p.fragment, "fragment")
+        self.assertEqual(p.username, None)
+        self.assertEqual(p.password, None)
+        self.assertEqual(p.hostname, "www.python.org")
+        self.assertEqual(p.port, None)
+        self.assertEqual(p.geturl(), "http://www.python.org/javascript:alert('msg')/?query=something#fragment")
+
+        # Remove ASCII tabs and newlines from input as bytes, for http common case scenario.
+        url = b"h\nttp://www.python\n.org\t/java\nscript:\talert('msg\r\n')/?query\n=\tsomething#frag\nment"
+        p = urllib.parse.urlsplit(url)
+        self.assertEqual(p.scheme, b"http")
+        self.assertEqual(p.netloc, b"www.python.org")
+        self.assertEqual(p.path, b"/javascript:alert('msg')/")
+        self.assertEqual(p.query, b"query=something")
+        self.assertEqual(p.fragment, b"fragment")
+        self.assertEqual(p.username, None)
+        self.assertEqual(p.password, None)
+        self.assertEqual(p.hostname, b"www.python.org")
+        self.assertEqual(p.port, None)
+        self.assertEqual(p.geturl(), b"http://www.python.org/javascript:alert('msg')/?query=something#fragment")
+
+        # any scheme
+        url = "x-new-scheme\t://www.python\n.org\t/java\nscript:\talert('msg\r\n')/?query\n=\tsomething#frag\nment"
+        p = urllib.parse.urlsplit(url)
+        self.assertEqual(p.geturl(), "x-new-scheme://www.python.org/javascript:alert('msg')/?query=something#fragment")
+
+        # Remove ASCII tabs and newlines from input as bytes, any scheme.
+        url = b"x-new-scheme\t://www.python\n.org\t/java\nscript:\talert('msg\r\n')/?query\n=\tsomething#frag\nment"
+        p = urllib.parse.urlsplit(url)
+        self.assertEqual(p.geturl(), b"x-new-scheme://www.python.org/javascript:alert('msg')/?query=something#fragment")
+
+        # Unsafe bytes is not returned from urlparse cache.
+        # scheme is stored after parsing, sending an scheme with unsafe bytes *will not* return an unsafe scheme
+        url = "https://www.python\n.org\t/java\nscript:\talert('msg\r\n')/?query\n=\tsomething#frag\nment"
+        scheme = "htt\nps"
+        for _ in range(2):
+            p = urllib.parse.urlsplit(url, scheme=scheme)
+            self.assertEqual(p.scheme, "https")
+            self.assertEqual(p.geturl(), "https://www.python.org/javascript:alert('msg')/?query=something#fragment")
+
+
     def test_issue14072(self):
         p1 = urlparse.urlsplit('tel:+31-641044153')
         self.assertEqual(p1.scheme, 'tel')

diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 798b467..d015f2c 100644 (file)
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -62,6 +62,9 @@ scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
                 '0123456789'
                 '+-.')
 
+# Unsafe bytes to be removed per WHATWG spec
+_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']
+
 MAX_CACHE_SIZE = 20
 _parse_cache = {}
 
@@ -184,12 +187,19 @@ def _checknetloc(netloc):
                              "under NFKC normalization"
                              % netloc)
 
+def _remove_unsafe_bytes_from_url(url):
+    for b in _UNSAFE_URL_BYTES_TO_REMOVE:
+        url = url.replace(b, "")
+    return url
+
 def urlsplit(url, scheme='', allow_fragments=True):
     """Parse a URL into 5 components:
     <scheme>://<netloc>/<path>?<query>#<fragment>
     Return a 5-tuple: (scheme, netloc, path, query, fragment).
     Note that we don't break the components up in smaller bits
     (e.g. netloc is a single string) and we don't expand % escapes."""
+    url = _remove_unsafe_bytes_from_url(url)
+    scheme = _remove_unsafe_bytes_from_url(scheme)
     allow_fragments = bool(allow_fragments)
     key = url, scheme, allow_fragments, type(url), type(scheme)
     cached = _parse_cache.get(key, None)