Revision: 8179
http://svn.sourceforge.net/mailman/?rev=8179&view=rev
Author: tkikuchi
Date: 2007-03-23 22:17:00 -0700 (Fri, 23 Mar 2007)
Log Message:
-----------
Brush up the fall-back-to-utf8 mechanizm in ToDigest.py. Neither cStringIO
nor StringIO have 'encoding'. What we need was unicode string StringIO and
python StringIO has it already. Also, use utf-8 for the table of contents
in MIME digest if the subject has a different charset.
Adding a test code for the multi-language digest.
Modified Paths:
--------------
trunk/mailman/Mailman/Handlers/ToDigest.py
trunk/mailman/Mailman/testing/test_handlers.py
Modified: trunk/mailman/Mailman/Handlers/ToDigest.py
===================================================================
--- trunk/mailman/Mailman/Handlers/ToDigest.py 2007-03-23 11:28:12 UTC (rev
8178)
+++ trunk/mailman/Mailman/Handlers/ToDigest.py 2007-03-24 05:17:00 UTC (rev
8179)
@@ -31,7 +31,7 @@
import time
import logging
-from StringIO import StringIO
+from StringIO import StringIO # cStringIO can't handle unicode.
from email.Charset import Charset
from email.Generator import Generator
from email.Header import decode_header, make_header, Header
@@ -163,8 +163,6 @@
mimemsg['Message-ID'] = Utils.unique_message_id(mlist)
# Set things up for the rfc1153 digest
plainmsg = StringIO()
- # cStringIO doesn't have encoding. Sigh.
- plainmsg.encoding = 'utf-8'
rfc1153msg = Message.Message()
rfc1153msg['From'] = mlist.GetRequestEmail()
rfc1153msg['Subject'] = digestsubj
@@ -211,7 +209,6 @@
#
# Meanwhile prepare things for the table of contents
toc = StringIO()
- toc.encoding = 'utf-8'
print >> toc, _("Today's Topics:\n")
# Now cruise through all the messages in the mailbox of digest messages,
# building the MIME payload and core of the RFC 1153 digest. We'll also
@@ -292,7 +289,10 @@
return
toctext = toc.getvalue()
# MIME
- tocpart = MIMEText(toctext.encode(lcset), _charset=lcset)
+ try:
+ tocpart = MIMEText(toctext.encode(lcset), _charset=lcset)
+ except UnicodeError:
+ tocpart = MIMEText(toctext.encode('utf-8'), _charset='utf-8')
tocpart['Content-Description']= _("Today's Topics ($msgcount messages)")
mimemsg.attach(tocpart)
# RFC 1153
@@ -333,16 +333,12 @@
# -- just stringfy it.
payload = msg.get_payload(decode=True) \
or msg.as_string().split('\n\n',1)[1]
- mcset = msg.get_content_charset('')
- if mcset and mcset <> lcset and mcset <> lcset_out:
- try:
- payload = unicode(payload, mcset, 'replace'
- ).encode(lcset, 'replace')
- except (UnicodeError, LookupError):
- # TK: Message has something unknown charset.
- # _out means charset in 'outer world'.
- payload = unicode(payload, lcset_out, 'replace'
- ).encode(lcset, 'replace')
+ mcset = msg.get_content_charset('us-ascii')
+ try:
+ payload = unicode(payload, mcset, 'replace')
+ except (LookupError, TypeError):
+ # unknown or empty charset
+ payload = unicode(payload, 'us-ascii', 'replace')
print >> plainmsg, payload
if not payload.endswith('\n'):
print >> plainmsg
@@ -403,7 +399,12 @@
listname=mlist.fqdn_listname,
isdigest=True)
# RFC 1153
- rfc1153msg.set_payload(plainmsg.getvalue().encode(lcset), lcset)
+ # If the entire digest message can't be encoded by list charset, fall
+ # back to 'utf-8'.
+ try:
+ rfc1153msg.set_payload(plainmsg.getvalue().encode(lcset), lcset)
+ except UnicodeError:
+ rfc1153msg.set_payload(plainmsg.getvalue().encode('utf-8'), 'utf-8')
virginq.enqueue(rfc1153msg,
recips=plainrecips,
listname=mlist.fqdn_listname,
Modified: trunk/mailman/Mailman/testing/test_handlers.py
===================================================================
--- trunk/mailman/Mailman/testing/test_handlers.py 2007-03-23 11:28:12 UTC
(rev 8178)
+++ trunk/mailman/Mailman/testing/test_handlers.py 2007-03-24 05:17:00 UTC
(rev 8179)
@@ -1606,6 +1606,41 @@
# BAW: this test is incomplete...
+ def test_send_i18n_digest(self):
+ eq = self.assertEqual
+ mlist = self._mlist
+ mlist.preferred_language = 'fr'
+ msg = email.message_from_string("""\
+From: [EMAIL PROTECTED]
+To: [EMAIL PROTECTED]
+Subject: =?iso-2022-jp?b?GyRCMGxIVhsoQg==?=
+MIME-Version: 1.0
+Content-Type: text/plain; charset=iso-2022-jp
+Content-Transfer-Encoding: 7bit
+
+\x1b$B0lHV\x1b(B
+""")
+ mlist.digest_size_threshhold = 0
+ ToDigest.process(mlist, msg, {})
+ files = self._sb.files()
+ eq(len(files), 2)
+ for filebase in files:
+ qmsg, qdata = self._sb.dequeue(filebase)
+ if qmsg.get_content_maintype() == 'multipart':
+ mimemsg = qmsg
+ mimedata = qdata
+ else:
+ rfc1153msg = qmsg
+ rfc1153data = qdata
+ eq(rfc1153msg.get_content_type(), 'text/plain')
+ eq(rfc1153msg.get_content_charset(), 'utf-8')
+ eq(rfc1153msg['content-transfer-encoding'], 'base64')
+ toc = mimemsg.get_payload()[1]
+ eq(toc.get_content_type(), 'text/plain')
+ eq(toc.get_content_charset(), 'utf-8')
+ eq(toc['content-transfer-encoding'], 'base64')
+
+
class TestToOutgoing(TestBase):
def setUp(self):
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
_______________________________________________
Mailman-checkins mailing list
[email protected]
Unsubscribe:
http://mail.python.org/mailman/options/mailman-checkins/archive%40jab.org
