From bc91b0b8eb859f7d7286c7adeaa8fa6abcf88b03 Mon Sep 17 00:00:00 2001 From: JinWang An Date: Wed, 21 Jun 2023 16:46:23 +0900 Subject: [PATCH] [CVE-2022-45061] gh-98433: Fix quadratic time idna decoding. (GH-99092) (GH-99232) From b0b590be9597fd5919228d251812dd54145f70a7 Mon Sep 17 00:00:00 2001 From: "Miss Islington (bot)" <31488909+miss-islington@users.noreply.github.com> Date: Mon, 7 Nov 2022 19:22:14 -0800 There was an unnecessary quadratic loop in idna decoding. This restores the behavior to linear. (cherry picked from commit a6f6c3a3d6f2b580f2d87885c9b8a9350ad7bf15) Co-authored-by: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> Co-authored-by: Gregory P. Smith Change-Id: I9a1277f3b3c6d07f04787402400a859a015fab21 Signed-off-by: JinWang An --- Lib/encodings/idna.py | 32 +++++++++++++++----------------- Lib/test/test_codecs.py | 6 ++++++ 2 files changed, 21 insertions(+), 17 deletions(-) diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py index ea90d67..2ce798c 100644 --- a/Lib/encodings/idna.py +++ b/Lib/encodings/idna.py @@ -39,23 +39,21 @@ def nameprep(label): # Check bidi RandAL = map(stringprep.in_table_d1, 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 filter(stringprep.in_table_d2, 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 0ec8bf5..1610f76 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -1318,6 +1318,12 @@ class IDNACodecTest(unittest.TestCase): self.assertEqual(u"pyth\xf6n.org".encode("idna"), "xn--pythn-mua.org") self.assertEqual(u"pyth\xf6n.org.".encode("idna"), "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): import StringIO r = codecs.getreader("idna")(StringIO.StringIO("abc")) -- 2.7.4