summaryrefslogtreecommitdiffstats
path: root/Lib/email
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/email')
-rw-r--r--Lib/email/_parseaddr.py5
-rw-r--r--Lib/email/header.py3
-rw-r--r--Lib/email/message.py6
-rw-r--r--Lib/email/test/test_email.py27
-rw-r--r--Lib/email/test/test_email_renamed.py20
5 files changed, 54 insertions, 7 deletions
diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py
index 8047df2..81913a3 100644
--- a/Lib/email/_parseaddr.py
+++ b/Lib/email/_parseaddr.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2002-2006 Python Software Foundation
+# Copyright (C) 2002-2007 Python Software Foundation
# Contact: email-sig@python.org
"""Email address parsing code.
@@ -172,6 +172,7 @@ class AddrlistClass:
self.pos = 0
self.LWS = ' \t'
self.CR = '\r\n'
+ self.FWS = self.LWS + self.CR
self.atomends = self.specials + self.LWS + self.CR
# Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it
# is obsolete syntax. RFC 2822 requires that we recognize obsolete
@@ -418,7 +419,7 @@ class AddrlistClass:
plist = []
while self.pos < len(self.field):
- if self.field[self.pos] in self.LWS:
+ if self.field[self.pos] in self.FWS:
self.pos += 1
elif self.field[self.pos] == '"':
plist.append(self.getquote())
diff --git a/Lib/email/header.py b/Lib/email/header.py
index 3de44f9..ab0d3fc 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -39,7 +39,8 @@ ecre = re.compile(r'''
\? # literal ?
(?P<encoded>.*?) # non-greedy up to the next ?= is the encoded string
\?= # literal ?=
- ''', re.VERBOSE | re.IGNORECASE)
+ (?=[ \t]|$) # whitespace or the end of the string
+ ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE)
# Field name regexp, including trailing colon, but not separating whitespace,
# according to RFC 2822. Character range is from tilde to exclamation mark.
diff --git a/Lib/email/message.py b/Lib/email/message.py
index 9d25cb0..6fc3af1 100644
--- a/Lib/email/message.py
+++ b/Lib/email/message.py
@@ -238,7 +238,7 @@ class Message:
self.del_param('charset')
self._charset = None
return
- if isinstance(charset, str):
+ if isinstance(charset, basestring):
charset = email.charset.Charset(charset)
if not isinstance(charset, email.charset.Charset):
raise TypeError(charset)
@@ -756,7 +756,9 @@ class Message:
charset = charset[2]
# charset character must be in us-ascii range
try:
- charset = unicode(charset, 'us-ascii').encode('us-ascii')
+ if isinstance(charset, str):
+ charset = unicode(charset, 'us-ascii')
+ charset = charset.encode('us-ascii')
except UnicodeError:
return failobj
# RFC 2046, $4.1.2 says charsets are not case sensitive
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index c3269d7..a2e09fa 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001-2007 Python Software Foundation
# Contact: email-sig@python.org
# email package unit tests
@@ -501,6 +501,13 @@ class TestMessageAPI(TestEmailBase):
msg.set_payload(x)
self.assertEqual(msg.get_payload(decode=True), x)
+ def test_get_content_charset(self):
+ msg = Message()
+ msg.set_charset('us-ascii')
+ self.assertEqual('us-ascii', msg.get_content_charset())
+ msg.set_charset(u'us-ascii')
+ self.assertEqual('us-ascii', msg.get_content_charset())
+
# Test the email.Encoders module
@@ -1519,6 +1526,18 @@ class TestRFC2047(unittest.TestCase):
hu = make_header(dh).__unicode__()
eq(hu, u'The quick brown fox jumped over the lazy dog')
+ def test_rfc2047_without_whitespace(self):
+ s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
+ dh = decode_header(s)
+ self.assertEqual(dh, [(s, None)])
+
+ def test_rfc2047_with_whitespace(self):
+ s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
+ dh = decode_header(s)
+ self.assertEqual(dh, [('Sm', None), ('\xf6', 'iso-8859-1'),
+ ('rg', None), ('\xe5', 'iso-8859-1'),
+ ('sbord', None)])
+
# Test the MIMEMessage class
@@ -2164,6 +2183,12 @@ class TestMiscellaneous(TestEmailBase):
# formataddr() quotes the name if there's a dot in it
self.assertEqual(Utils.formataddr((a, b)), y)
+ def test_multiline_from_comment(self):
+ x = """\
+Foo
+\tBar <foo@example.com>"""
+ self.assertEqual(Utils.parseaddr(x), ('Foo Bar', 'foo@example.com'))
+
def test_quote_dump(self):
self.assertEqual(
Utils.formataddr(('A Silly; Person', 'person@dom.ain')),
diff --git a/Lib/email/test/test_email_renamed.py b/Lib/email/test/test_email_renamed.py
index 21061b0..7f72270 100644
--- a/Lib/email/test/test_email_renamed.py
+++ b/Lib/email/test/test_email_renamed.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2001-2006 Python Software Foundation
+# Copyright (C) 2001-2007 Python Software Foundation
# Contact: email-sig@python.org
# email package unit tests
@@ -1524,6 +1524,18 @@ class TestRFC2047(unittest.TestCase):
hu = make_header(dh).__unicode__()
eq(hu, u'The quick brown fox jumped over the lazy dog')
+ def test_rfc2047_missing_whitespace(self):
+ s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
+ dh = decode_header(s)
+ self.assertEqual(dh, [(s, None)])
+
+ def test_rfc2047_with_whitespace(self):
+ s = 'Sm =?ISO-8859-1?B?9g==?= rg =?ISO-8859-1?B?5Q==?= sbord'
+ dh = decode_header(s)
+ self.assertEqual(dh, [('Sm', None), ('\xf6', 'iso-8859-1'),
+ ('rg', None), ('\xe5', 'iso-8859-1'),
+ ('sbord', None)])
+
# Test the MIMEMessage class
@@ -2170,6 +2182,12 @@ class TestMiscellaneous(TestEmailBase):
# formataddr() quotes the name if there's a dot in it
self.assertEqual(utils.formataddr((a, b)), y)
+ def test_multiline_from_comment(self):
+ x = """\
+Foo
+\tBar <foo@example.com>"""
+ self.assertEqual(utils.parseaddr(x), ('Foo Bar', 'foo@example.com'))
+
def test_quote_dump(self):
self.assertEqual(
utils.formataddr(('A Silly; Person', 'person@dom.ain')),
generated by cgit v0.12 at 2024-11-24 13:53:53 (GMT)