[3.9] gh-98433: Fix quadratic time idna decoding. (GH-99092) (GH-99222) (#99230)

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>
Gbp-Pq: Name 0011-3.9-gh-98433-Fix-quadratic-time-idna-decoding.-GH-99.patch

diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py
index ea4058512fe366d40ec150a943d8d73b4861be22..bf98f513366b314d69d3af30d2f7b2a7ea7b07f7 100644 (file)
--- 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 8d112a171d7c4ef5f2138ff398d2b5270b3cccee..365280df798095dc5ae3932815631dd6cfe3ee59 100644 (file)
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -1532,6 +1532,12 @@ 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)