view hgext/strip.py @ 43301:90213d027154

sidedatacopies: only fetch information once for merge

Before this change, merge would result in reading the data from revlog twice.
With this change, we keep the information in memory until we encounter the other
parent.

When looking at pypy, I see about 1/3 of the changesets with copy information
being merge. Not doing duplicated fetch for them provide a significant speedup.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 0.767042 comb 0.760000 user 0.750000 sys 0.010000 (median of 11)
after:  ! wall 0.671162 comb 0.670000 user 0.650000 sys 0.020000 (median of 13)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 1.170169 comb 1.170000 user 1.130000 sys 0.040000 (median of 10)
after:  ! wall 1.030596 comb 1.040000 user 1.010000 sys 0.030000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.209846 comb 0.200000 user 0.200000 sys 0.000000 (median of 46)
after:  ! wall 0.170981 comb 0.170000 user 0.170000 sys 0.000000 (median of 56)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013248 comb 0.010000 user 0.010000 sys 0.000000 (median of 223)
after:  ! wall 0.013295 comb 0.020000 user 0.020000 sys 0.000000 (median of 222)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.001672 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after:  ! wall 0.001666 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8010)
after:  ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8007)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.168599 comb 0.160000 user 0.160000 sys 0.000000 (median of 58)
after:  ! wall 0.133316 comb 0.140000 user 0.140000 sys 0.000000 (median of 73)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.036052 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)
after:  ! wall 0.032558 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)

Differential Revision: https://phab.mercurial-scm.org/D7127

"""strip changesets and their descendants from history

This extension allows you to strip changesets and all their descendants from the
repository. See the command help for details.
"""
from __future__ import absolute_import

from mercurial.i18n import _
from mercurial.pycompat import getattr
from mercurial import (
    bookmarks as bookmarksmod,
    cmdutil,
    error,
    hg,
    lock as lockmod,
    merge,
    node as nodemod,
    pycompat,
    registrar,
    repair,
    scmutil,
    util,
)

nullid = nodemod.nullid
release = lockmod.release

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'


def checklocalchanges(repo, force=False):
    s = repo.status()
    if not force:
        cmdutil.checkunfinished(repo)
        cmdutil.bailifchanged(repo)
    else:
        cmdutil.checkunfinished(repo, skipmerge=True)
    return s


def _findupdatetarget(repo, nodes):
    unode, p2 = repo.changelog.parents(nodes[0])
    currentbranch = repo[None].branch()

    if (
        util.safehasattr(repo, b'mq')
        and p2 != nullid
        and p2 in [x.node for x in repo.mq.applied]
    ):
        unode = p2
    elif currentbranch != repo[unode].branch():
        pwdir = b'parents(wdir())'
        revset = b'max(((parents(%ln::%r) + %r) - %ln::%r) and branch(%s))'
        branchtarget = repo.revs(
            revset, nodes, pwdir, pwdir, nodes, pwdir, currentbranch
        )
        if branchtarget:
            cl = repo.changelog
            unode = cl.node(branchtarget.first())

    return unode


def strip(
    ui,
    repo,
    revs,
    update=True,
    backup=True,
    force=None,
    bookmarks=None,
    soft=False,
):
    with repo.wlock(), repo.lock():

        if update:
            checklocalchanges(repo, force=force)
            urev = _findupdatetarget(repo, revs)
            hg.clean(repo, urev)
            repo.dirstate.write(repo.currenttransaction())

        if soft:
            repair.softstrip(ui, repo, revs, backup)
        else:
            repair.strip(ui, repo, revs, backup)

        repomarks = repo._bookmarks
        if bookmarks:
            with repo.transaction(b'strip') as tr:
                if repo._activebookmark in bookmarks:
                    bookmarksmod.deactivate(repo)
                repomarks.applychanges(repo, tr, [(b, None) for b in bookmarks])
            for bookmark in sorted(bookmarks):
                ui.write(_(b"bookmark '%s' deleted\n") % bookmark)


@command(
    b"strip",
    [
        (
            b'r',
            b'rev',
            [],
            _(
                b'strip specified revision (optional, '
                b'can specify revisions without this '
                b'option)'
            ),
            _(b'REV'),
        ),
        (
            b'f',
            b'force',
            None,
            _(
                b'force removal of changesets, discard '
                b'uncommitted changes (no backup)'
            ),
        ),
        (b'', b'no-backup', None, _(b'do not save backup bundle')),
        (b'', b'nobackup', None, _(b'do not save backup bundle (DEPRECATED)'),),
        (b'n', b'', None, _(b'ignored  (DEPRECATED)')),
        (
            b'k',
            b'keep',
            None,
            _(b"do not modify working directory during strip"),
        ),
        (
            b'B',
            b'bookmark',
            [],
            _(b"remove revs only reachable from given bookmark"),
            _(b'BOOKMARK'),
        ),
        (
            b'',
            b'soft',
            None,
            _(b"simply drop changesets from visible history (EXPERIMENTAL)"),
        ),
    ],
    _(b'hg strip [-k] [-f] [-B bookmark] [-r] REV...'),
    helpcategory=command.CATEGORY_MAINTENANCE,
)
def stripcmd(ui, repo, *revs, **opts):
    """strip changesets and all their descendants from the repository

    The strip command removes the specified changesets and all their
    descendants. If the working directory has uncommitted changes, the
    operation is aborted unless the --force flag is supplied, in which
    case changes will be discarded.

    If a parent of the working directory is stripped, then the working
    directory will automatically be updated to the most recent
    available ancestor of the stripped parent after the operation
    completes.

    Any stripped changesets are stored in ``.hg/strip-backup`` as a
    bundle (see :hg:`help bundle` and :hg:`help unbundle`). They can
    be restored by running :hg:`unbundle .hg/strip-backup/BUNDLE`,
    where BUNDLE is the bundle file created by the strip. Note that
    the local revision numbers will in general be different after the
    restore.

    Use the --no-backup option to discard the backup bundle once the
    operation completes.

    Strip is not a history-rewriting operation and can be used on
    changesets in the public phase. But if the stripped changesets have
    been pushed to a remote repository you will likely pull them again.

    Return 0 on success.
    """
    opts = pycompat.byteskwargs(opts)
    backup = True
    if opts.get(b'no_backup') or opts.get(b'nobackup'):
        backup = False

    cl = repo.changelog
    revs = list(revs) + opts.get(b'rev')
    revs = set(scmutil.revrange(repo, revs))

    with repo.wlock():
        bookmarks = set(opts.get(b'bookmark'))
        if bookmarks:
            repomarks = repo._bookmarks
            if not bookmarks.issubset(repomarks):
                raise error.Abort(
                    _(b"bookmark '%s' not found")
                    % b','.join(sorted(bookmarks - set(repomarks.keys())))
                )

            # If the requested bookmark is not the only one pointing to a
            # a revision we have to only delete the bookmark and not strip
            # anything. revsets cannot detect that case.
            nodetobookmarks = {}
            for mark, node in pycompat.iteritems(repomarks):
                nodetobookmarks.setdefault(node, []).append(mark)
            for marks in nodetobookmarks.values():
                if bookmarks.issuperset(marks):
                    rsrevs = scmutil.bookmarkrevs(repo, marks[0])
                    revs.update(set(rsrevs))
            if not revs:
                with repo.lock(), repo.transaction(b'bookmark') as tr:
                    bmchanges = [(b, None) for b in bookmarks]
                    repomarks.applychanges(repo, tr, bmchanges)
                for bookmark in sorted(bookmarks):
                    ui.write(_(b"bookmark '%s' deleted\n") % bookmark)

        if not revs:
            raise error.Abort(_(b'empty revision set'))

        descendants = set(cl.descendants(revs))
        strippedrevs = revs.union(descendants)
        roots = revs.difference(descendants)

        # if one of the wdir parent is stripped we'll need
        # to update away to an earlier revision
        update = any(
            p != nullid and cl.rev(p) in strippedrevs
            for p in repo.dirstate.parents()
        )

        rootnodes = set(cl.node(r) for r in roots)

        q = getattr(repo, 'mq', None)
        if q is not None and q.applied:
            # refresh queue state if we're about to strip
            # applied patches
            if cl.rev(repo.lookup(b'qtip')) in strippedrevs:
                q.applieddirty = True
                start = 0
                end = len(q.applied)
                for i, statusentry in enumerate(q.applied):
                    if statusentry.node in rootnodes:
                        # if one of the stripped roots is an applied
                        # patch, only part of the queue is stripped
                        start = i
                        break
                del q.applied[start:end]
                q.savedirty()

        revs = sorted(rootnodes)
        if update and opts.get(b'keep'):
            urev = _findupdatetarget(repo, revs)
            uctx = repo[urev]

            # only reset the dirstate for files that would actually change
            # between the working context and uctx
            descendantrevs = repo.revs(b"%d::.", uctx.rev())
            changedfiles = []
            for rev in descendantrevs:
                # blindly reset the files, regardless of what actually changed
                changedfiles.extend(repo[rev].files())

            # reset files that only changed in the dirstate too
            dirstate = repo.dirstate
            dirchanges = [f for f in dirstate if dirstate[f] != b'n']
            changedfiles.extend(dirchanges)

            repo.dirstate.rebuild(urev, uctx.manifest(), changedfiles)
            repo.dirstate.write(repo.currenttransaction())

            # clear resolve state
            merge.mergestate.clean(repo, repo[b'.'].node())

            update = False

        strip(
            ui,
            repo,
            revs,
            backup=backup,
            update=update,
            force=opts.get(b'force'),
            bookmarks=bookmarks,
            soft=opts[b'soft'],
        )

    return 0