[Python-checkins] cpython (merge 3.2 -> 3.2): Merge from remote

Thu Mar 17 02:54:34 CET 2011

http://hg.python.org/cpython/rev/21fe6d393242
changeset: 68636:21fe6d393242
branch: 3.2
parent: 68633:5c2d15c6007e
parent: 68631:74a8c46fb272
user: Nick Coghlan <ncoghlan at gmail.com>
date: Wed Mar 16 22:09:10 2011 -0400
summary:
 Merge from remote
files:
 Misc/NEWS

diff --git a/Lib/email/message.py b/Lib/email/message.py
--- a/Lib/email/message.py
+++ b/Lib/email/message.py
@@ -48,9 +48,9 @@
 def _splitparam(param):
 # Split header parameters. BAW: this may be too simple. It isn't
 # strictly RFC 2045 (section 5.1) compliant, but it catches most headers
- # found in the wild. We may eventually need a full fledged parser
- # eventually.
- a, sep, b = param.partition(';')
+ # found in the wild. We may eventually need a full fledged parser.
+ # RDM: we might have a Header here; for now just stringify it.
+ a, sep, b = str(param).partition(';')
 if not sep:
 return a.strip(), None
 return a.strip(), b.strip()
@@ -90,6 +90,8 @@
 return param
 
 def _parseparam(s):
+ # RDM This might be a Header, so for now stringify it.
+ s = ';' + str(s)
 plist = []
 while s[:1] == ';':
 s = s[1:]
@@ -240,7 +242,8 @@
 if i is not None and not isinstance(self._payload, list):
 raise TypeError('Expected list, got %s' % type(self._payload))
 payload = self._payload
- cte = self.get('content-transfer-encoding', '').lower()
+ # cte might be a Header, so for now stringify it.
+ cte = str(self.get('content-transfer-encoding', '')).lower()
 # payload may be bytes here.
 if isinstance(payload, str):
 if _has_surrogates(payload):
@@ -561,7 +564,7 @@
 if value is missing:
 return failobj
 params = []
- for p in _parseparam(';' + value):
+ for p in _parseparam(value):
 try:
 name, val = p.split('=', 1)
 name = name.strip()
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -2995,6 +2995,58 @@
 ['foo at bar.com',
 'g\uFFFD\uFFFDst'])
 
+ def test_get_content_type_with_8bit(self):
+ msg = email.message_from_bytes(textwrap.dedent("""\
+ Content-Type: text/pl\xA7in; charset=utf-8
+ """).encode('latin-1'))
+ self.assertEqual(msg.get_content_type(), "text/pl\uFFFDin")
+ self.assertEqual(msg.get_content_maintype(), "text")
+ self.assertEqual(msg.get_content_subtype(), "pl\uFFFDin")
+
+ def test_get_params_with_8bit(self):
+ msg = email.message_from_bytes(
+ 'X-Header: foo=\xa7ne; b\xa7r=two; baz=three\n'.encode('latin-1'))
+ self.assertEqual(msg.get_params(header='x-header'),
+ [('foo', '\uFFFDne'), ('b\uFFFDr', 'two'), ('baz', 'three')])
+ self.assertEqual(msg.get_param('Foo', header='x-header'), '\uFFFdne')
+ # XXX: someday you might be able to get 'b\xa7r', for now you can't.
+ self.assertEqual(msg.get_param('b\xa7r', header='x-header'), None)
+
+ def test_get_rfc2231_params_with_8bit(self):
+ msg = email.message_from_bytes(textwrap.dedent("""\
+ Content-Type: text/plain; charset=us-ascii;
+ title*=us-ascii'en'This%20is%20not%20f\xa7n"""
+ ).encode('latin-1'))
+ self.assertEqual(msg.get_param('title'),
+ ('us-ascii', 'en', 'This is not f\uFFFDn'))
+
+ def test_set_rfc2231_params_with_8bit(self):
+ msg = email.message_from_bytes(textwrap.dedent("""\
+ Content-Type: text/plain; charset=us-ascii;
+ title*=us-ascii'en'This%20is%20not%20f\xa7n"""
+ ).encode('latin-1'))
+ msg.set_param('title', 'test')
+ self.assertEqual(msg.get_param('title'), 'test')
+
+ def test_del_rfc2231_params_with_8bit(self):
+ msg = email.message_from_bytes(textwrap.dedent("""\
+ Content-Type: text/plain; charset=us-ascii;
+ title*=us-ascii'en'This%20is%20not%20f\xa7n"""
+ ).encode('latin-1'))
+ msg.del_param('title')
+ self.assertEqual(msg.get_param('title'), None)
+ self.assertEqual(msg.get_content_maintype(), 'text')
+
+ def test_get_payload_with_8bit_cte_header(self):
+ msg = email.message_from_bytes(textwrap.dedent("""\
+ Content-Transfer-Encoding: b\xa7se64
+ Content-Type: text/plain; charset=latin-1
+
+ payload
+ """).encode('latin-1'))
+ self.assertEqual(msg.get_payload(), 'payload\n')
+ self.assertEqual(msg.get_payload(decode=True), b'payload\n')
+
 non_latin_bin_msg = textwrap.dedent("""\
 From: foo at bar.com
 To: báz
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -42,6 +42,9 @@
 
 - Issue #11577: fix ResourceWarning triggered by improved binhex test coverage
 
+- Issue #11243: fix the parameter querying methods of Message to work if
+ the headers contain un-encoded non-ASCII data.
+
 - Issue #11401: fix handling of headers with no value; this fixes a regression
 relative to Python2 and the result is now the same as it was in Python2.
 
-- 
Repository URL: http://hg.python.org/cpython
