From 65dcc8a8dc41d3453fd6b987073a5f1b30c5c0fd Mon Sep 17 00:00:00 2001 From: Andrei Troie Date: Sat, 5 Oct 2019 17:19:15 +0100 Subject: [PATCH] bpo-38332: Catch KeyError from unknown cte in encoded-word. (GH-16503) KeyError should cause a failure in parsing the encoded word and should be caught and raised as a _InvalidEWError instead. --- Lib/email/_header_value_parser.py | 2 +- Lib/test/test_email/test__encoded_words.py | 2 ++ Lib/test/test_email/test__header_value_parser.py | 12 ++++++++++++ .../Library/2019-10-05-02-07-52.bpo-38332.hwrPN7.rst | 3 +++ 4 files changed, 18 insertions(+), 1 deletion(-) create mode 100644 Misc/NEWS.d/next/Library/2019-10-05-02-07-52.bpo-38332.hwrPN7.rst diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index 16c19907d68..1668b4a14e9 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -1057,7 +1057,7 @@ def get_encoded_word(value): value = ''.join(remainder) try: text, charset, lang, defects = _ew.decode('=?' + tok + '?=') - except ValueError: + except (ValueError, KeyError): raise _InvalidEwError( "encoded word format invalid: '{}'".format(ew.cte)) ew.charset = charset diff --git a/Lib/test/test_email/test__encoded_words.py b/Lib/test/test_email/test__encoded_words.py index 5a59aebba89..0b8b1de3359 100644 --- a/Lib/test/test_email/test__encoded_words.py +++ b/Lib/test/test_email/test__encoded_words.py @@ -58,6 +58,8 @@ class TestDecode(TestEmailBase): _ew.decode('=?') with self.assertRaises(ValueError): _ew.decode('') + with self.assertRaises(KeyError): + _ew.decode('=?utf-8?X?somevalue?=') def _test(self, source, result, charset='us-ascii', lang='', defects=[]): res, char, l, d = _ew.decode(source) diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 058d902459b..46d90b38e91 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -89,6 +89,10 @@ class TestParser(TestParserMixin, TestEmailBase): with self.assertRaises(errors.HeaderParseError): parser.get_encoded_word('=?abc?=') + def test_get_encoded_word_invalid_cte(self): + with self.assertRaises(errors.HeaderParseError): + parser.get_encoded_word('=?utf-8?X?somevalue?=') + def test_get_encoded_word_valid_ew(self): self._test_get_x(parser.get_encoded_word, '=?us-ascii?q?this_is_a_test?= bird', @@ -399,6 +403,14 @@ class TestParser(TestParserMixin, TestEmailBase): [], '') + def test_get_unstructured_invalid_ew_cte(self): + self._test_get_x(self._get_unst, + '=?utf-8?X?=somevalue?=', + '=?utf-8?X?=somevalue?=', + '=?utf-8?X?=somevalue?=', + [], + '') + # get_qp_ctext def test_get_qp_ctext_only(self): diff --git a/Misc/NEWS.d/next/Library/2019-10-05-02-07-52.bpo-38332.hwrPN7.rst b/Misc/NEWS.d/next/Library/2019-10-05-02-07-52.bpo-38332.hwrPN7.rst new file mode 100644 index 00000000000..600c702cf3b --- /dev/null +++ b/Misc/NEWS.d/next/Library/2019-10-05-02-07-52.bpo-38332.hwrPN7.rst @@ -0,0 +1,3 @@ +Prevent :exc:`KeyError` thrown by :func:`_encoded_words.decode` when given +an encoded-word with invalid content-type encoding from propagating all the +way to :func:`email.message.get`.