From 66c4f3f38b867d8329b28c032bb907fd1a2f22d2 Mon Sep 17 00:00:00 2001 From: Abhilash Raj Date: Wed, 5 Jun 2019 12:56:33 -0400 Subject: bpo-21315: Fix parsing of encoded words with missing leading ws. (#13425) * bpo-21315: Fix parsing of encoded words with missing leading ws. Because of missing leading whitespace, encoded word would get parsed as unstructured token. This patch fixes that by looking for encoded words when splitting tokens with whitespace. Missing trailing whitespace around encoded word now register a defect instead. Original patch suggestion by David R. Murray on bpo-21315. --- Lib/test/test_email/test__header_value_parser.py | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'Lib/test/test_email/test__header_value_parser.py') diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 12da3cffb8..649923fa6c 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -118,7 +118,7 @@ class TestParser(TestParserMixin, TestEmailBase): '=?us-ascii?q?first?==?utf-8?q?second?=', 'first', 'first', - [], + [errors.InvalidHeaderDefect], '=?utf-8?q?second?=') def test_get_encoded_word_sets_extra_attributes(self): @@ -361,6 +361,25 @@ class TestParser(TestParserMixin, TestEmailBase): '=?utf-8?q?foo?==?utf-8?q?bar?=', 'foobar', 'foobar', + [errors.InvalidHeaderDefect, + errors.InvalidHeaderDefect], + '') + + def test_get_unstructured_ew_without_leading_whitespace(self): + self._test_get_x( + self._get_unst, + 'nowhitespace=?utf-8?q?somevalue?=', + 'nowhitespacesomevalue', + 'nowhitespacesomevalue', + [errors.InvalidHeaderDefect], + '') + + def test_get_unstructured_ew_without_trailing_whitespace(self): + self._test_get_x( + self._get_unst, + '=?utf-8?q?somevalue?=nowhitespace', + 'somevaluenowhitespace', + 'somevaluenowhitespace', [errors.InvalidHeaderDefect], '') @@ -546,7 +565,8 @@ class TestParser(TestParserMixin, TestEmailBase): '"=?utf-8?Q?not_really_valid?="', '"not really valid"', 'not really valid', - [errors.InvalidHeaderDefect], + [errors.InvalidHeaderDefect, + errors.InvalidHeaderDefect], '') # get_comment -- cgit v1.2.1