hgext/commitextras.py

pycompat: use os.fsencode() to re-encode sys.argv

Historically, the previous code made sense, as Py_EncodeLocale() and
fs.fsencode() could possibly use different encodings. However, this is not the
case anymore for Python 3.2, which uses the locale encoding as the filesystem
encoding (this is not true for later Python versions, but see below). See
https://vstinner.github.io/painful-history-python-filesystem-encoding.html for
a source and more background information.

Using os.fsencode() is safer, as the documentation for sys.argv says that it can
be used to get the original bytes. When doing further changes, the Python
developers will take care that this continues to work.

One concrete case where os.fsencode() is more correct is when enabling Python's
UTF-8 mode. Py_DecodeLocale() will use UTF-8 in this case. Our previous code
would have encoded it using the locale encoding (which might be different),
whereas os.fsencode() will encode it with UTF-8.

Since we don’t claim to support the UTF-8 mode, this is not really a bug and the
patch can go to the default branch. It might be a good idea to not commit this
to the stable branch, as it could in theory introduce regressions.

# 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,
    util,
)

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

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


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


def _commit(orig, ui, repo, *pats, **opts):
    if util.safehasattr(repo, 'unfiltered'):
        repo = repo.unfiltered()

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

    repo.__class__ = repoextra
    return orig(ui, repo, *pats, **opts)