view hgext/commitextras.py @ 37947:3ea3c96ada54

encoding: introduce tagging type for non-lossy non-ASCII string

This fixes the weird behavior of toutf8b(), which would convert a local
string back to UTF-8 *only if* it was lossy in the system encoding.

Before b7b26e54e37a "encoding: avoid localstr when a string can be encoded
losslessly (issue2763)", all local strings were wrapped by the localstr
class. I think this would justify the round-trip behavior of toutf8b().

ASCII strings are special-cased, so the cost of wrapping with safelocalstr
is negligible.

  (with mercurial repo)
  $ export HGRCPATH=/dev/null HGPLAIN= HGENCODING=latin-1
  $ hg log --time --config experimental.evolution=all > /dev/null

  (original)
  time: real 11.340 secs (user 11.290+0.000 sys 0.060+0.000)
  time: real 11.390 secs (user 11.300+0.000 sys 0.080+0.000)
  time: real 11.430 secs (user 11.360+0.000 sys 0.070+0.000)

  (this patch)
  time: real 11.200 secs (user 11.100+0.000 sys 0.100+0.000)
  time: real 11.370 secs (user 11.300+0.000 sys 0.070+0.000)
  time: real 11.190 secs (user 11.130+0.000 sys 0.060+0.000)

# commitextras.py
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''adds a new flag extras to commit (ADVANCED)'''

from __future__ import absolute_import

import re

from mercurial.i18n import _
from mercurial import (
    commands,
    error,
    extensions,
    registrar,
)

cmdtable = {}
command = registrar.command(cmdtable)
testedwith = 'ships-with-hg-core'

usedinternally = {
    'amend_source',
    'branch',
    'close',
    'histedit_source',
    'topic',
    'rebase_source',
    'intermediate-source',
    '__touch-noise__',
    'source',
    'transplant_source',
}

def extsetup(ui):
    entry = extensions.wrapcommand(commands.table, 'commit', _commit)
    options = entry[1]
    options.append(('', 'extra', [],
        _('set a changeset\'s extra values'), _("KEY=VALUE")))

def _commit(orig, ui, repo, *pats, **opts):
    origcommit = repo.commit
    try:
        def _wrappedcommit(*innerpats, **inneropts):
            extras = opts.get(r'extra')
            if extras:
                for raw in extras:
                    if '=' not in raw:
                        msg = _("unable to parse '%s', should follow "
                                "KEY=VALUE format")
                        raise error.Abort(msg % raw)
                    k, v = raw.split('=', 1)
                    if not k:
                        msg = _("unable to parse '%s', keys can't be empty")
                        raise error.Abort(msg % raw)
                    if re.search('[^\w-]', k):
                        msg = _("keys can only contain ascii letters, digits,"
                                " '_' and '-'")
                        raise error.Abort(msg)
                    if k in usedinternally:
                        msg = _("key '%s' is used internally, can't be set "
                                "manually")
                        raise error.Abort(msg % k)
                    inneropts[r'extra'][k] = v
            return origcommit(*innerpats, **inneropts)

        # This __dict__ logic is needed because the normal
        # extension.wrapfunction doesn't seem to work.
        repo.__dict__[r'commit'] = _wrappedcommit
        return orig(ui, repo, *pats, **opts)
    finally:
        del repo.__dict__[r'commit']