CVE-2024-7592 Fix quadratic complexity in parsing quoted cookie

pythongh-123067: Fix quadratic complexity in parsing "-quoted cookie …

…values with backslashes (pythonGH-123075)

This fixes CVE-2024-7592.

Redo tests without a subtest

Backport how RegEx stuff is handled to Python2

Lib/Cookie.py

@@ -323,9 +323,13 @@ def _quote(str, LegalChars=_LegalChars,
         return '"' + _nulljoin( map(_Translator.get, str, str) ) + '"'
 # end _quote
 
+_unquote_sub = re.compile(r'\\(?:([0-3][0-7][0-7])|(.))').sub
 
-_OctalPatt = re.compile(r"\\[0-3][0-7][0-7]")
-_QuotePatt = re.compile(r"[\\].")
+def _unquote_replace(m):
+    if m.group(1):
+        return chr(int(m.group(1), 8))
+    else:
+        return m.group(2)
 
 def _unquote(str):
     # If there aren't any doublequotes,
@@ -345,28 +349,7 @@ def _unquote(str):
     #    \012 --> \n
     #    \"   --> "
     #
-    i = 0
-    n = len(str)
-    res = []
-    while 0 <= i < n:
-        Omatch = _OctalPatt.search(str, i)
-        Qmatch = _QuotePatt.search(str, i)
-        if not Omatch and not Qmatch:              # Neither matched
-            res.append(str[i:])
-            break
-        # else:
-        j = k = -1
-        if Omatch: j = Omatch.start(0)
-        if Qmatch: k = Qmatch.start(0)
-        if Qmatch and ( not Omatch or k < j ):     # QuotePatt matched
-            res.append(str[i:k])
-            res.append(str[k+1])
-            i = k+2
-        else:                                      # OctalPatt matched
-            res.append(str[i:j])
-            res.append( chr( int(str[j+1:j+4], 8) ) )
-            i = j+4
-    return _nulljoin(res)
+    return _unquote_sub(_unquote_replace, str)
 # end _unquote
 
 # The _getdate() routine is used to set the expiration time in

Lib/test/test_cookie.py

@@ -1,6 +1,7 @@
 # Simple test suite for Cookie.py
 
 from test.test_support import run_unittest, run_doctest, check_warnings
+from test import support
 import unittest
 import Cookie
 import pickle
@@ -156,6 +157,44 @@ def test_invalid_cookies(self):
             self.assertEqual(dict(C), {})
             self.assertEqual(C.output(), '')
 
+    def test_unquote(self):
+        cases = [
+            (r'a="b=\""', 'b="'),
+            (r'a="b=\\"', 'b=\\'),
+            (r'a="b=\="', 'b=='),
+            (r'a="b=\n"', 'b=n'),
+            (r'a="b=\042"', 'b="'),
+            (r'a="b=\134"', 'b=\\'),
+            (r'a="b=\377"', 'b=\xff'),
+            (r'a="b=\400"', 'b=400'),
+            (r'a="b=\42"', 'b=42'),
+            (r'a="b=\\042"', 'b=\\042'),
+            (r'a="b=\\134"', 'b=\\134'),
+            (r'a="b=\\\""', 'b=\\"'),
+            (r'a="b=\\\042"', 'b=\\"'),
+            (r'a="b=\134\""', 'b=\\"'),
+            (r'a="b=\134\042"', 'b=\\"'),
+        ]
+        for encoded, decoded in cases:
+            # with self.subTest(encoded):
+            C = Cookie.SimpleCookie()
+            C.load(encoded)
+            self.assertEqual(C['a'].value, decoded)
+
+    @support.requires_resource('cpu')
+    def test_unquote_large(self):
+        n = 10**6
+        for encoded in r'\\', r'\134':
+            # with self.subTest(encoded):
+            data = 'a="b=' + encoded*n + ';"'
+            C = Cookie.SimpleCookie()
+            C.load(data)
+            value = C['a'].value
+            self.assertEqual(value[:3], 'b=\\')
+            self.assertEqual(value[-2:], '\\;')
+            self.assertEqual(len(value), n + 3)
+
+
     def test_pickle(self):
         rawdata = 'Customer="WILE_E_COYOTE"; Path=/acme; Version=1'
         expected_output = 'Set-Cookie: %s' % rawdata

Misc/NEWS.d/next/Library/2024-08-16-19-13-21.gh-issue-123067.Nx9O4R.rst

@@ -0,0 +1 @@
+Fix quadratic complexity in parsing ``"``-quoted cookie values with backslashes by :mod:`http.cookies`.