mail: add methods to handle non-ascii chars

- headencode, addressencode: encode headers
- mimeencode: encode message parts not containing patches
- new email config "charsets"

Users may configure email.charsets as a list of charsets they
consider appropriate for the recipients of their outgoing mails.

Conversion is tried in this order:
1. us-ascii
   (ascii, us-ascii are removed from email.charsets if present)
2. email.charsets (if present) in order given
3. util._fallbackencoding, util._encoding, utf-8
   if not already in email.charsets

mercurial/mail.py

@@ -1,86 +1,159 b''
 # mail.py - mail sending bits for mercurial
 #
 # Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from i18n import _
 import os, smtplib, socket
+import email.Header, email.MIMEText, email.Utils
 import util
 
 def _smtp(ui):
     '''build an smtp connection and return a function to send mail'''
     local_hostname = ui.config('smtp', 'local_hostname')
     s = smtplib.SMTP(local_hostname=local_hostname)
     mailhost = ui.config('smtp', 'host')
     if not mailhost:
         raise util.Abort(_('no [smtp]host in hgrc - cannot send mail'))
     mailport = int(ui.config('smtp', 'port', 25))
     ui.note(_('sending mail: smtp host %s, port %s\n') %
             (mailhost, mailport))
     s.connect(host=mailhost, port=mailport)
     if ui.configbool('smtp', 'tls'):
         if not hasattr(socket, 'ssl'):
             raise util.Abort(_("can't use TLS: Python SSL support "
                                "not installed"))
         ui.note(_('(using tls)\n'))
         s.ehlo()
         s.starttls()
         s.ehlo()
     username = ui.config('smtp', 'username')
     password = ui.config('smtp', 'password')
     if username and not password:
         password = ui.getpass()
     if username and password:
         ui.note(_('(authenticating to mail server as %s)\n') %
                   (username))
         s.login(username, password)
 
     def send(sender, recipients, msg):
         try:
             return s.sendmail(sender, recipients, msg)
         except smtplib.SMTPRecipientsRefused, inst:
             recipients = [r[1] for r in inst.recipients.values()]
             raise util.Abort('\n' + '\n'.join(recipients))
         except smtplib.SMTPException, inst:
             raise util.Abort(inst)
 
     return send
 
 def _sendmail(ui, sender, recipients, msg):
     '''send mail using sendmail.'''
     program = ui.config('email', 'method')
     cmdline = '%s -f %s %s' % (program, util.email(sender),
                                ' '.join(map(util.email, recipients)))
     ui.note(_('sending mail: %s\n') % cmdline)
     fp = util.popen(cmdline, 'w')
     fp.write(msg)
     ret = fp.close()
     if ret:
         raise util.Abort('%s %s' % (
             os.path.basename(program.split(None, 1)[0]),
             util.explain_exit(ret)[0]))
 
 def connect(ui):
     '''make a mail connection. return a function to send mail.
     call as sendmail(sender, list-of-recipients, msg).'''
     if ui.config('email', 'method', 'smtp') == 'smtp':
         return _smtp(ui)
     return lambda s, r, m: _sendmail(ui, s, r, m)
 
 def sendmail(ui, sender, recipients, msg):
     send = connect(ui)
     return send(sender, recipients, msg)
 
 def validateconfig(ui):
     '''determine if we have enough config data to try sending email.'''
     method = ui.config('email', 'method', 'smtp')
     if method == 'smtp':
         if not ui.config('smtp', 'host'):
             raise util.Abort(_('smtp specified as email transport, '
                                'but no smtp host configured'))
     else:
         if not util.find_exe(method):
             raise util.Abort(_('%r specified as email transport, '
                                'but not in PATH') % method)
+
+def _charsets(ui):
+    '''Obtains charsets to send mail parts not containing patches.'''
+    charsets = [cs.lower() for cs in ui.configlist('email', 'charsets')]
+    fallbacks = [util._fallbackencoding.lower(),
+                 util._encoding.lower(), 'utf-8']
+    for cs in fallbacks: # util.unique does not keep order
+        if cs not in charsets:
+            charsets.append(cs)
+    return [cs for cs in charsets if not cs.endswith('ascii')]
+
+def _encode(ui, s, charsets):
+    '''Returns (converted) string, charset tuple.
+    Finds out best charset by cycling through sendcharsets in descending
+    order. Tries both _encoding and _fallbackencoding for input. Only as
+    last resort send as is in fake ascii.
+    Caveat: Do not use for mail parts containing patches!'''
+    try:
+        s.decode('ascii')
+    except UnicodeDecodeError:
+        sendcharsets = charsets or _charsets(ui)
+        for ics in (util._encoding, util._fallbackencoding):
+            try:
+                u = s.decode(ics)
+            except UnicodeDecodeError:
+                continue
+            for ocs in sendcharsets:
+                try:
+                    return u.encode(ocs), ocs
+                except UnicodeEncodeError:
+                    pass
+                except LookupError:
+                    ui.warn(_('ignoring invalid sendcharset: %s\n') % cs)
+    # if ascii, or all conversion attempts fail, send (broken) ascii
+    return s, 'us-ascii'
+
+def headencode(ui, s, charsets=None, display=False):
+    '''Returns RFC-2047 compliant header from given string.'''
+    if not display:
+        # split into words?
+        s, cs = _encode(ui, s, charsets)
+        return str(email.Header.Header(s, cs))
+    return s
+
+def addressencode(ui, address, charsets=None, display=False):
+    '''Turns address into RFC-2047 compliant header.'''
+    if display or not address:
+        return address or ''
+    name, addr = email.Utils.parseaddr(address)
+    name = headencode(ui, name, charsets)
+    try:
+        acc, dom = addr.split('@')
+        acc = acc.encode('ascii')
+        dom = dom.encode('idna')
+        addr = '%s@%s' % (acc, dom)
+    except UnicodeDecodeError:
+        raise util.Abort(_('invalid email address: %s') % addr)
+    except ValueError:
+        try:
+            # too strict?
+            addr = addr.encode('ascii')
+        except UnicodeDecodeError:
+            raise util.Abort(_('invalid local address: %s') % addr)
+    return email.Utils.formataddr((name, addr))
+
+def mimeencode(ui, s, charsets=None, display=False):
+    '''creates mime text object, encodes it if needed, and sets
+    charset and transfer-encoding accordingly.'''
+    cs = 'us-ascii'
+    if not display:
+        s, cs = _encode(ui, s, charsets)
+    return email.MIMEText.MIMEText(s, 'plain', cs)