From 9bb8e18ca46fe66fa6802602f8a7228a24dd785f Mon Sep 17 00:00:00 2001                                              
From: "Miss Islington (bot)"
 <31488909+miss-islington@users.noreply.github.com>
Date: Mon, 7 Nov 2022 19:23:16 -0800
Subject: [PATCH] [3.11] gh-98433: Fix quadratic time idna decoding. (GH-99092)
  (GH-99222)
   
There was an unnecessary quadratic loop in idna decoding. This restores
the behavior to linear.
    
(cherry picked from commit d315722564927c7202dd6e111dc79eaf14240b0d)
     
(cherry picked from commit a6f6c3a3d6f2b580f2d87885c9b8a9350ad7bf15)
      
Co-authored-by: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>
Co-authored-by: Gregory P. Smith <greg@krypto.org>
---
 Lib/encodings/idna.py                         | 32 +++++++++----------
 Lib/test/test_codecs.py                       |  6 ++++
 ...2-11-04-09-29-36.gh-issue-98433.l76c5G.rst |  6 ++++
 3 files changed, 27 insertions(+), 17 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Security/2022-11-04-09-29-36.gh-issue-98433.l76c5G.rst

diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py
index ea40585..bf98f51 100644
--- a/Lib/encodings/idna.py
+++ b/Lib/encodings/idna.py
@@ -39,23 +39,21 @@ def nameprep(label):
 
     # Check bidi
     RandAL = [stringprep.in_table_d1(x) for x in label]
-    for c in RandAL:
-        if c:
-            # There is a RandAL char in the string. Must perform further
-            # tests:
-            # 1) The characters in section 5.8 MUST be prohibited.
-            # This is table C.8, which was already checked
-            # 2) If a string contains any RandALCat character, the string
-            # MUST NOT contain any LCat character.
-            if any(stringprep.in_table_d2(x) for x in label):
-                raise UnicodeError("Violation of BIDI requirement 2")
-
-            # 3) If a string contains any RandALCat character, a
-            # RandALCat character MUST be the first character of the
-            # string, and a RandALCat character MUST be the last
-            # character of the string.
-            if not RandAL[0] or not RandAL[-1]:
-                raise UnicodeError("Violation of BIDI requirement 3")
+    if any(RandAL):
+        # There is a RandAL char in the string. Must perform further
+        # tests:
+        # 1) The characters in section 5.8 MUST be prohibited.
+        # This is table C.8, which was already checked
+        # 2) If a string contains any RandALCat character, the string
+        # MUST NOT contain any LCat character.
+        if any(stringprep.in_table_d2(x) for x in label):
+            raise UnicodeError("Violation of BIDI requirement 2")
+        # 3) If a string contains any RandALCat character, a
+        # RandALCat character MUST be the first character of the
+        # string, and a RandALCat character MUST be the last
+        # character of the string.
+        if not RandAL[0] or not RandAL[-1]:
+            raise UnicodeError("Violation of BIDI requirement 3")
 
     return label
 
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index f7310fb..439fab7 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -1534,6 +1534,12 @@ class IDNACodecTest(unittest.TestCase):
         self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org")
         self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.")
 
+    def test_builtin_decode_length_limit(self):
+        with self.assertRaisesRegex(UnicodeError, "too long"):
+            (b"xn--016c"+b"a"*1100).decode("idna")
+        with self.assertRaisesRegex(UnicodeError, "too long"):
+            (b"xn--016c"+b"a"*70).decode("idna")
+
     def test_stream(self):
         r = codecs.getreader("idna")(io.BytesIO(b"abc"))
         r.read(3)
diff --git a/Misc/NEWS.d/next/Security/2022-11-04-09-29-36.gh-issue-98433.l76c5G.rst b/Misc/NEWS.d/next/Security/2022-11-04-09-29-36.gh-issue-98433.l76c5G.rst
new file mode 100644
index 0000000..5185fac
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2022-11-04-09-29-36.gh-issue-98433.l76c5G.rst
@@ -0,0 +1,6 @@
+The IDNA codec decoder used on DNS hostnames by :mod:`socket` or :mod:`asyncio`
+related name resolution functions no longer involves a quadratic algorithm.
+This prevents a potential CPU denial of service if an out-of-spec excessive
+length hostname involving bidirectional characters were decoded. Some protocols
+such as :mod:`urllib` http ``3xx`` redirects potentially allow for an attacker
+to supply such a name.
-- 
2.27.0