diff options
author | R. David Murray <rdmurray@bitdance.com> | 2010-12-24 22:36:49 (GMT) |
---|---|---|
committer | R. David Murray <rdmurray@bitdance.com> | 2010-12-24 22:36:49 (GMT) |
commit | dfd7eb0ba2f3296f28028970e395e38f3ae9eedc (patch) | |
tree | 02ded19904da4eeea1f27afcaf6b042734348188 | |
parent | ddf53709eedd94450cc95c3ea0758c621790193d (diff) | |
download | cpython-dfd7eb0ba2f3296f28028970e395e38f3ae9eedc.zip cpython-dfd7eb0ba2f3296f28028970e395e38f3ae9eedc.tar.gz cpython-dfd7eb0ba2f3296f28028970e395e38f3ae9eedc.tar.bz2 |
#1693546: don't add quotes around RFC 2231 encoded values.
The RFC is bit hard to understand on this point, but the examples
clearly show that parameter values that are encoded according
to its charset/language rules don't have surrounding quotes, and
the ABNF does not allow for quotes. So when we produce such
encoded values, we no longer add quotes.
-rw-r--r-- | Lib/email/message.py | 4 | ||||
-rw-r--r-- | Lib/email/test/test_email.py | 50 | ||||
-rw-r--r-- | Misc/NEWS | 3 |
3 files changed, 52 insertions, 5 deletions
diff --git a/Lib/email/message.py b/Lib/email/message.py index 8d68c09..d2483ca 100644 --- a/Lib/email/message.py +++ b/Lib/email/message.py @@ -66,17 +66,19 @@ def _formatparam(param, value=None, quote=True): if value is not None and len(value) > 0: # A tuple is used for RFC 2231 encoded parameter values where items # are (charset, language, value). charset is a string, not a Charset - # instance. + # instance. RFC 2231 encoded values are never quoted, per RFC. if isinstance(value, tuple): # Encode as per RFC 2231 param += '*' value = utils.encode_rfc2231(value[2], value[0], value[1]) + return '%s=%s' % (param, value) else: try: value.encode('ascii') except UnicodeEncodeError: param += '*' value = utils.encode_rfc2231(value, 'utf-8', '') + return '%s=%s' % (param, value) # BAW: Please check this. I think that if quote is set it should # force quoting even if not necessary. if quote or tspecials.search(value): diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py index 53c4042..73ac347 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -534,7 +534,7 @@ class TestMessageAPI(TestEmailBase): msg.add_header('Content-Disposition', 'attachment', filename="Fußballer.ppt") self.assertEqual( - 'attachment; filename*="utf-8\'\'Fu%C3%9Fballer.ppt"', + 'attachment; filename*=utf-8\'\'Fu%C3%9Fballer.ppt', msg['Content-Disposition']) def test_nonascii_add_header_via_triple(self): @@ -542,7 +542,23 @@ class TestMessageAPI(TestEmailBase): msg.add_header('Content-Disposition', 'attachment', filename=('iso-8859-1', '', 'Fußballer.ppt')) self.assertEqual( - 'attachment; filename*="iso-8859-1\'\'Fu%DFballer.ppt"', + 'attachment; filename*=iso-8859-1\'\'Fu%DFballer.ppt', + msg['Content-Disposition']) + + def test_ascii_add_header_with_tspecial(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename="windows [filename].ppt") + self.assertEqual( + 'attachment; filename="windows [filename].ppt"', + msg['Content-Disposition']) + + def test_nonascii_add_header_with_tspecial(self): + msg = Message() + msg.add_header('Content-Disposition', 'attachment', + filename="Fußballer [filename].ppt") + self.assertEqual( + "attachment; filename*=utf-8''Fu%C3%9Fballer%20%5Bfilename%5D.ppt", msg['Content-Disposition']) @@ -3643,7 +3659,7 @@ To: bbb@zzz.org Subject: This is a test message Date: Fri, 4 May 2001 14:05:44 -0400 Content-Type: text/plain; charset=us-ascii; - title*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21" + title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21 Hi, @@ -3673,7 +3689,7 @@ To: bbb@zzz.org Subject: This is a test message Date: Fri, 4 May 2001 14:05:44 -0400 Content-Type: text/plain; charset="us-ascii"; - title*="us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21" + title*=us-ascii'en'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20isn%27t%20it%21 Hi, @@ -3688,6 +3704,32 @@ Do you like this message? msg = self._msgobj('msg_32.txt') eq(msg.get_content_charset(), 'us-ascii') + def test_rfc2231_parse_rfc_quoting(self): + m = textwrap.dedent('''\ + Content-Disposition: inline; + \tfilename*0*=''This%20is%20even%20more%20; + \tfilename*1*=%2A%2A%2Afun%2A%2A%2A%20; + \tfilename*2="is it not.pdf" + + ''') + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + self.assertEqual(m, msg.as_string()) + + def test_rfc2231_parse_extra_quoting(self): + m = textwrap.dedent('''\ + Content-Disposition: inline; + \tfilename*0*="''This%20is%20even%20more%20"; + \tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20"; + \tfilename*2="is it not.pdf" + + ''') + msg = email.message_from_string(m) + self.assertEqual(msg.get_filename(), + 'This is even more ***fun*** is it not.pdf') + self.assertEqual(m, msg.as_string()) + def test_rfc2231_no_language_or_charset(self): m = '''\ Content-Transfer-Encoding: 8bit @@ -11,6 +11,9 @@ Core and Builtins Library ------- +- Issue #1693546: fix email.message RFC 2231 parameter encoding to be in better + compliance (no "s around encoded values). + - Improved the diff message in the unittest module's assertCountEqual(). - Issue #1155362: email.utils.parsedate_tz now handles a missing space before |