view mercurial/mail.py @ 14365:a8e3931e3fb5

revlog: linearize created changegroups in generaldelta revlogs

This greatly improves the speed of the bundling process, and often reduces the
bundle size considerably. (Although if the repository is already ordered, this
has little effect on both time and bundle size.)

For non-generaldelta clients, the reduced bundle size translates to a reduced
repository size, similar to shrinking the revlogs (which uses the exact same
algorithm). For generaldelta clients the difference is minor.

When the new bundle format comes, reordering will not be necessary since we
can then store the deltaparent relationsships directly. The eventual default
behavior for clients and servers is presented in the table below, where "new"
implies support for GD as well as the new bundle format:

                    old client                    new client
old server          old bundle, no reorder        old bundle, no reorder
new server, non-GD  old bundle, no reorder[1]     old bundle, no reorder[2]
new server, GD      old bundle, reorder[3]        new bundle, no reorder[4]

[1] reordering is expensive on the server in this case, skip it
[2] client can choose to do its own redelta here
[3] reordering is needed because otherwise the pull does a lot of extra
    work on the server
[4] reordering isn't needed because client can get deltabase in bundle
    format

Currently, the default is to reorder on GD-servers, and not otherwise. A new
setting, bundle.reorder, has been added to override the default reordering
behavior. It can be set to either 'auto' (the default), or any true or false
value as a standard boolean setting, to either force the reordering on or off
regardless of generaldelta.


Some timing data from a relatively branch test repository follows. All
bundling is done with --all --type none options.

Non-generaldelta, non-shrunk repo:
-----------------------------------
Size: 276M

Without reorder (default):
Bundle time: 14.4 seconds
Bundle size: 939M

With reorder:
Bundle time: 1 minute, 29.3 seconds
Bundle size: 381M

Generaldelta, non-shrunk repo:
-----------------------------------
Size: 87M

Without reorder:
Bundle time: 2 minutes, 1.4 seconds
Bundle size: 939M

With reorder (default):
Bundle time: 25.5 seconds
Bundle size: 381M

# 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 version 2 or any later version.

from i18n import _
import util, encoding
import os, smtplib, socket, quopri
import email.Header, email.MIMEText, email.Utils

_oldheaderinit = email.Header.Header.__init__
def _unifiedheaderinit(self, *args, **kw):
    """
    Python2.7 introduces a backwards incompatible change
    (Python issue1974, r70772) in email.Generator.Generator code:
    pre-2.7 code passed "continuation_ws='\t'" to the Header
    constructor, and 2.7 removed this parameter.

    Default argument is continuation_ws=' ', which means that the
    behaviour is different in <2.7 and 2.7

    We consider the 2.7 behaviour to be preferable, but need
    to have an unified behaviour for versions 2.4 to 2.7
    """
    # override continuation_ws
    kw['continuation_ws'] = ' '
    _oldheaderinit(self, *args, **kw)

email.Header.Header.__dict__['__init__'] = _unifiedheaderinit

def _smtp(ui):
    '''build an smtp connection and return a function to send mail'''
    local_hostname = ui.config('smtp', 'local_hostname')
    tls = ui.config('smtp', 'tls', 'none')
    # backward compatible: when tls = true, we use starttls.
    starttls = tls == 'starttls' or util.parsebool(tls)
    smtps = tls == 'smtps'
    if (starttls or smtps) and not hasattr(socket, 'ssl'):
        raise util.Abort(_("can't use TLS: Python SSL support not installed"))
    if smtps:
        ui.note(_('(using smtps)\n'))
        s = smtplib.SMTP_SSL(local_hostname=local_hostname)
    else:
        s = smtplib.SMTP(local_hostname=local_hostname)
    mailhost = ui.config('smtp', 'host')
    if not mailhost:
        raise util.Abort(_('smtp.host not configured - cannot send mail'))
    mailport = util.getport(ui.config('smtp', 'port', 25))
    ui.note(_('sending mail: smtp host %s, port %s\n') %
            (mailhost, mailport))
    s.connect(host=mailhost, port=mailport)
    if starttls:
        ui.note(_('(using starttls)\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))
        try:
            s.login(username, password)
        except smtplib.SMTPException, inst:
            raise util.Abort(inst)

    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.explainexit(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.findexe(method):
            raise util.Abort(_('%r specified as email transport, '
                               'but not in PATH') % method)

def mimetextpatch(s, subtype='plain', display=False):
    '''If patch in utf-8 transfer-encode it.'''

    enc = None
    for line in s.splitlines():
        if len(line) > 950:
            s = quopri.encodestring(s)
            enc = "quoted-printable"
            break

    cs = 'us-ascii'
    if not display:
        try:
            s.decode('us-ascii')
        except UnicodeDecodeError:
            try:
                s.decode('utf-8')
                cs = 'utf-8'
            except UnicodeDecodeError:
                # We'll go with us-ascii as a fallback.
                pass

    msg = email.MIMEText.MIMEText(s, subtype, cs)
    if enc:
        del msg['Content-Transfer-Encoding']
        msg['Content-Transfer-Encoding'] = enc
    return msg

def _charsets(ui):
    '''Obtains charsets to send mail parts not containing patches.'''
    charsets = [cs.lower() for cs in ui.configlist('email', 'charsets')]
    fallbacks = [encoding.fallbackencoding.lower(),
                 encoding.encoding.lower(), 'utf-8']
    for cs in fallbacks: # find unique charsets while keeping 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 (encoding.encoding, encoding.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') % ocs)
    # 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, name, addr, charsets=None):
    name = headencode(ui, name, charsets)
    try:
        acc, dom = addr.split('@')
        acc = acc.encode('ascii')
        dom = dom.decode(encoding.encoding).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 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)
    return _addressencode(ui, name, addr, charsets)

def addrlistencode(ui, addrs, charsets=None, display=False):
    '''Turns a list of addresses into a list of RFC-2047 compliant headers.
    A single element of input list may contain multiple addresses, but output
    always has one address per item'''
    if display:
        return [a.strip() for a in addrs if a.strip()]

    result = []
    for name, addr in email.Utils.getaddresses(addrs):
        if name or addr:
            result.append(_addressencode(ui, name, addr, charsets))
    return result

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)