hgext/commitextras.py

rust: add `dirstate_tree` module

Mercurial needs to represent the filesystem hierarchy on which it operates, for
example in the dirstate. Its current on-disk representation is an unsorted, flat
structure that gets transformed in the current Rust code into a `HashMap`.
This loses the hierarchical information of the dirstate, leading to some
unfortunate performance and algorithmic compromises.

This module adds an implementation of a radix tree that is specialized for
representing the dirstate: its unit is the path component. I have made no
efforts to optimize either its memory footprint or its insertion speed: they're
pretty bad for now.

Following will be a few patches that modify the dirstate.status logic to use
that new hierarchical information, fixing issue 6335 in the same swing.

Differential Revision: https://phab.mercurial-scm.org/D9085

# 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)