hgext/split.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Tue, 09 Apr 2024 22:36:35 +0200
changeset 51594 e3a5ec2d236a
parent 50884 b5066b2b40f2
permissions -rw-r--r--
outgoing: rework the handling of the `missingroots` case to be faster The previous implementation was slow, to the point it was taking a significant amount of `hg bundle --type none-streamv2` call. We rework the code to compute the same value much faster, making the operation disappear from the `hg bundle --type none-streamv2` profile. Someone would remark that producing a streamclone does not requires an `outgoing` object. However that is a matter for another day. There is other user of `missingroots` (non stream `hg bundle` call for example), and they will also benefit from this rework. We implement an old TODO in the process, directly computing the missing and common attribute as we have most element at hand already. ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 7.750458 after: 6.665565 (-14.00%, -1.08) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 0.700229 after: 0.496050 (-29.16%, -0.20) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 346.508952 after: 316.749699 (-8.59%, -29.76) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 3.401700 after: 2.915810 (-14.28%, -0.49) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 1.870798 after: 1.461583 (-21.87%, -0.41) note: this whole `missingroots` of outgoing has a limited number of callers and could likely be replace by something simpler (like taking an explicit "missing_revs" set for example). However this is a wider change and we focus on a small impact, quick rework that does not change the API for now.

# split.py - split a changeset into smaller ones
#
# Copyright 2015 Laurent Charignon <lcharignon@fb.com>
# Copyright 2017 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.
"""command to split a changeset into smaller ones (EXPERIMENTAL)"""


from mercurial.i18n import _

from mercurial.node import (
    nullrev,
    short,
)

from mercurial import (
    bookmarks,
    cmdutil,
    commands,
    error,
    hg,
    logcmdutil,
    registrar,
    revsetlang,
    rewriteutil,
    scmutil,
    util,
)

# allow people to use split without explicitly enabling rebase extension
from . import rebase

cmdtable = {}
command = registrar.command(cmdtable)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'


@command(
    b'split',
    [
        (b'r', b'rev', b'', _(b"revision to split"), _(b'REV')),
        (b'', b'rebase', True, _(b'rebase descendants after split')),
    ]
    + cmdutil.commitopts2,
    _(b'hg split [--no-rebase] [[-r] REV]'),
    helpcategory=command.CATEGORY_CHANGE_MANAGEMENT,
    helpbasic=True,
)
def split(ui, repo, *revs, **opts):
    """split a changeset into smaller ones

    Repeatedly prompt changes and commit message for new changesets until there
    is nothing left in the original changeset.

    If --rev was not given, split the working directory parent.

    By default, rebase connected non-obsoleted descendants onto the new
    changeset. Use --no-rebase to avoid the rebase.
    """
    revlist = []
    if opts.get('rev'):
        revlist.append(opts.get('rev'))
    revlist.extend(revs)
    with repo.wlock(), repo.lock():
        tr = repo.transaction(b'split')
        # If the rebase somehow runs into conflicts, make sure
        # we close the transaction so the user can continue it.
        with util.acceptintervention(tr):
            revs = logcmdutil.revrange(repo, revlist or [b'.'])
            if len(revs) > 1:
                raise error.InputError(_(b'cannot split multiple revisions'))

            rev = revs.first()
            # Handle nullrev specially here (instead of leaving for precheck()
            # below) so we get a nicer message and error code.
            if rev is None or rev == nullrev:
                ui.status(_(b'nothing to split\n'))
                return 1
            ctx = repo[rev]
            if ctx.node() is None:
                raise error.InputError(_(b'cannot split working directory'))

            if opts.get('rebase'):
                # Skip obsoleted descendants and their descendants so the rebase
                # won't cause conflicts for sure.
                descendants = list(repo.revs(b'(%d::) - (%d)', rev, rev))
                torebase = list(
                    repo.revs(
                        b'%ld - (%ld & obsolete())::', descendants, descendants
                    )
                )
            else:
                torebase = []
            rewriteutil.precheck(repo, [rev] + torebase, b'split')

            if len(ctx.parents()) > 1:
                raise error.InputError(_(b'cannot split a merge changeset'))

            cmdutil.bailifchanged(repo)

            # Deactivate bookmark temporarily so it won't get moved
            # unintentionally
            bname = repo._activebookmark
            if bname and repo._bookmarks[bname] != ctx.node():
                bookmarks.deactivate(repo)

            wnode = repo[b'.'].node()
            top = None
            try:
                top = dosplit(ui, repo, tr, ctx, **opts)
            finally:
                # top is None: split failed, need update --clean recovery.
                # wnode == ctx.node(): wnode split, no need to update.
                if top is None or wnode != ctx.node():
                    hg.clean(repo, wnode, show_stats=False)
                if bname:
                    bookmarks.activate(repo, bname)
            if torebase and top:
                dorebase(ui, repo, torebase, top)


def dosplit(ui, repo, tr, ctx, **opts):
    committed = []  # [ctx]

    # Set working parent to ctx.p1(), and keep working copy as ctx's content
    if ctx.node() != repo.dirstate.p1():
        hg.clean(repo, ctx.node(), show_stats=False)
    with repo.dirstate.changing_parents(repo):
        scmutil.movedirstate(repo, ctx.p1())

    # Any modified, added, removed, deleted result means split is incomplete
    def incomplete(repo):
        st = repo.status()
        return any((st.modified, st.added, st.removed, st.deleted))

    # Main split loop
    while incomplete(repo):
        if committed:
            header = _(
                b'HG: Splitting %s. So far it has been split into:\n'
            ) % short(ctx.node())
            # We don't want color codes in the commit message template, so
            # disable the label() template function while we render it.
            with ui.configoverride(
                {(b'templatealias', b'label(l,x)'): b"x"}, b'split'
            ):
                for c in committed:
                    summary = cmdutil.format_changeset_summary(ui, c, b'split')
                    header += _(b'HG: - %s\n') % summary
            header += _(
                b'HG: Write commit message for the next split changeset.\n'
            )
        else:
            header = _(
                b'HG: Splitting %s. Write commit message for the '
                b'first split changeset.\n'
            ) % short(ctx.node())
        opts.update(
            {
                'edit': True,
                'interactive': True,
                'message': header + ctx.description(),
            }
        )
        origctx = repo[b'.']
        commands.commit(ui, repo, **opts)
        newctx = repo[b'.']
        # Ensure user didn't do a "no-op" split (such as deselecting
        # everything).
        if origctx.node() != newctx.node():
            committed.append(newctx)

    if not committed:
        raise error.InputError(_(b'cannot split an empty revision'))

    if len(committed) != 1 or committed[0].node() != ctx.node():
        # Ensure we don't strip a node if we produce the same commit as already
        # exists
        scmutil.cleanupnodes(
            repo,
            {ctx.node(): [c.node() for c in committed]},
            operation=b'split',
            fixphase=True,
        )

    return committed[-1]


def dorebase(ui, repo, src, destctx):
    rebase.rebase(
        ui,
        repo,
        rev=[revsetlang.formatspec(b'%ld', src)],
        dest=revsetlang.formatspec(b'%d', destctx.rev()),
    )