view hgext/sparse.py @ 45962:a66568f20ddc

copies: use the rust code for `combine_changeset_copies` Changeset centric copy tracing now use the rust code. The rust code focussed on simplicity and will be optimised later. So the performance is not great yet. Now that all the pieces are in place we can start working on performance in the coming changesets. Below is a table that summarize how slower we got: Repo Cases Source-Rev Dest-Rev Py-time Rust-time Difference Factor ------------------------------------------------------------------------------------------------------------------------------------ mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 0.000049 s, 0.000046 s, -0.000003 s, × 0.9388 mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 0.000112 s, 0.000173 s, +0.000061 s, × 1.5446 mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 0.004216 s, 0.006303 s, +0.002087 s, × 1.4950 pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 0.000204 s, 0.000229 s, +0.000025 s, × 1.1225 pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 0.000058 s, 0.000056 s, -0.000002 s, × 0.9655 pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 0.000112 s, 0.000143 s, +0.000031 s, × 1.2768 pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 0.000339 s, 0.001166 s, +0.000827 s, × 3.4395 pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 0.010214 s, 0.022931 s, +0.012717 s, × 2.2451 pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 0.047497 s, 0.852446 s, +0.804949 s, × 17.9474 pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 0.075297 s, 2.221824 s, +2.146527 s, × 29.5075 pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 0.057322 s, 1.194162 s, +1.136840 s, × 20.8325 pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 0.796264 s, 62.468362 s, +61.672098 s, × 78.4518 pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 0.020491 s, 0.022116 s, +0.001625 s, × 1.0793 pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 0.121612 s, 2.972788 s, +2.851176 s, × 24.4449 netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 0.000143 s, 0.000180 s, +0.000037 s, × 1.2587 netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 0.000112 s, 0.000123 s, +0.000011 s, × 1.0982 netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 0.000232 s, 0.000315 s, +0.000083 s, × 1.3578 netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 0.000721 s, 0.001297 s, +0.000576 s, × 1.7989 netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 0.010115 s, 0.024884 s, +0.014769 s, × 2.4601 netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 0.015461 s, 0.032653 s, +0.017192 s, × 2.1120 netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 0.060756 s, 4.230118 s, +4.169362 s, × 69.6247 netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 0.605842 s, killed mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 0.000164 s, 0.000197 s, +0.000033 s, × 1.2012 mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 0.000331 s, 0.000622 s, +0.000291 s, × 1.8792 mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 0.000249 s, 0.000296 s, +0.000047 s, × 1.1888 mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 0.000711 s, 0.001626 s, +0.000915 s, × 2.2869 mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 0.003438 s, 0.006218 s, +0.002780 s, × 1.8086 mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.069869 s, 0.132760 s, +0.062891 s, × 1.9001 mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.005701 s, 0.029001 s, +0.023300 s, × 5.0870 mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.005757 s, 0.005886 s, +0.000129 s, × 1.0224 mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 0.061826 s, 3.619850 s, +3.558024 s, × 58.5490 mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.043354 s, 0.058678 s, +0.015324 s, × 1.3535 mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 0.198979 s, 11.926587 s, +11.727608 s, × 59.9389 mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 2.067096 s, killed mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 3.102616 s, killed mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 0.001212 s, 0.001204 s, -0.000008 s, × 0.9934 mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 0.001237 s, 0.001217 s, -0.000020 s, × 0.9838 mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 0.000557 s, 0.000605 s, +0.000048 s, × 1.0862 mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 0.001532 s, 0.001876 s, +0.000344 s, × 1.2245 mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 0.035166 s, 0.078190 s, +0.043024 s, × 2.2235 mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 0.070336 s, 0.135428 s, +0.065092 s, × 1.9254 mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 0.006080 s, 0.029123 s, +0.023043 s, × 4.7900 mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 0.006099 s, 0.006141 s, +0.000042 s, × 1.0069 mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 0.064317 s, 4.857827 s, +4.793510 s, × 75.5294 mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 0.303263 s, 10.674920 s, +10.371657 s, × 35.2002 mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 0.292804 s, 9.789462 s, +9.496658 s, × 33.4335 mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 0.107594 s, 1.087890 s, +0.980296 s, × 10.1111 mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 0.045202 s, 0.060556 s, +0.015354 s, × 1.3397 mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 1.926277 s, killed mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 0.794492 s, killed mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 84.521497 s, killed mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 0.965937 s, 19.647038 s, +18.681101 s, × 20.3399 mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 83.367146 s, killed mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 84.260895 s, killed mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 3.274537 s, killed mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 42.235843 s, killed mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 49.872829 s, killed Differential Revision: https://phab.mercurial-scm.org/D9299
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Thu, 01 Oct 2020 18:52:13 +0200
parents 5c8230ca37f2
children f927ad5a4e2c
line wrap: on
line source

# sparse.py - allow sparse checkouts of the working directory
#
# Copyright 2014 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.

"""allow sparse checkouts of the working directory (EXPERIMENTAL)

(This extension is not yet protected by backwards compatibility
guarantees. Any aspect may break in future releases until this
notice is removed.)

This extension allows the working directory to only consist of a
subset of files for the revision. This allows specific files or
directories to be explicitly included or excluded. Many repository
operations have performance proportional to the number of files in
the working directory. So only realizing a subset of files in the
working directory can improve performance.

Sparse Config Files
-------------------

The set of files that are part of a sparse checkout are defined by
a sparse config file. The file defines 3 things: includes (files to
include in the sparse checkout), excludes (files to exclude from the
sparse checkout), and profiles (links to other config files).

The file format is newline delimited. Empty lines and lines beginning
with ``#`` are ignored.

Lines beginning with ``%include `` denote another sparse config file
to include. e.g. ``%include tests.sparse``. The filename is relative
to the repository root.

The special lines ``[include]`` and ``[exclude]`` denote the section
for includes and excludes that follow, respectively. It is illegal to
have ``[include]`` after ``[exclude]``.

Non-special lines resemble file patterns to be added to either includes
or excludes. The syntax of these lines is documented by :hg:`help patterns`.
Patterns are interpreted as ``glob:`` by default and match against the
root of the repository.

Exclusion patterns take precedence over inclusion patterns. So even
if a file is explicitly included, an ``[exclude]`` entry can remove it.

For example, say you have a repository with 3 directories, ``frontend/``,
``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond
to different projects and it is uncommon for someone working on one
to need the files for the other. But ``tools/`` contains files shared
between both projects. Your sparse config files may resemble::

  # frontend.sparse
  frontend/**
  tools/**

  # backend.sparse
  backend/**
  tools/**

Say the backend grows in size. Or there's a directory with thousands
of files you wish to exclude. You can modify the profile to exclude
certain files::

  [include]
  backend/**
  tools/**

  [exclude]
  tools/tests/**
"""

from __future__ import absolute_import

from mercurial.i18n import _
from mercurial.pycompat import setattr
from mercurial import (
    commands,
    dirstate,
    error,
    extensions,
    logcmdutil,
    match as matchmod,
    merge as mergemod,
    pycompat,
    registrar,
    sparse,
    util,
)

# 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'

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


def extsetup(ui):
    sparse.enabled = True

    _setupclone(ui)
    _setuplog(ui)
    _setupadd(ui)
    _setupdirstate(ui)


def replacefilecache(cls, propname, replacement):
    """Replace a filecache property with a new class. This allows changing the
    cache invalidation condition."""
    origcls = cls
    assert callable(replacement)
    while cls is not object:
        if propname in cls.__dict__:
            orig = cls.__dict__[propname]
            setattr(cls, propname, replacement(orig))
            break
        cls = cls.__bases__[0]

    if cls is object:
        raise AttributeError(
            _(b"type '%s' has no property '%s'") % (origcls, propname)
        )


def _setuplog(ui):
    entry = commands.table[b'log|history']
    entry[1].append(
        (
            b'',
            b'sparse',
            None,
            b"limit to changesets affecting the sparse checkout",
        )
    )

    def _initialrevs(orig, repo, wopts):
        revs = orig(repo, wopts)
        if wopts.opts.get(b'sparse'):
            sparsematch = sparse.matcher(repo)

            def ctxmatch(rev):
                ctx = repo[rev]
                return any(f for f in ctx.files() if sparsematch(f))

            revs = revs.filter(ctxmatch)
        return revs

    extensions.wrapfunction(logcmdutil, b'_initialrevs', _initialrevs)


def _clonesparsecmd(orig, ui, repo, *args, **opts):
    include_pat = opts.get('include')
    exclude_pat = opts.get('exclude')
    enableprofile_pat = opts.get('enable_profile')
    narrow_pat = opts.get('narrow')
    include = exclude = enableprofile = False
    if include_pat:
        pat = include_pat
        include = True
    if exclude_pat:
        pat = exclude_pat
        exclude = True
    if enableprofile_pat:
        pat = enableprofile_pat
        enableprofile = True
    if sum([include, exclude, enableprofile]) > 1:
        raise error.Abort(_(b"too many flags specified."))
    # if --narrow is passed, it means they are includes and excludes for narrow
    # clone
    if not narrow_pat and (include or exclude or enableprofile):

        def clonesparse(orig, ctx, *args, **kwargs):
            sparse.updateconfig(
                ctx.repo().unfiltered(),
                pat,
                {},
                include=include,
                exclude=exclude,
                enableprofile=enableprofile,
                usereporootpaths=True,
            )
            return orig(ctx, *args, **kwargs)

        extensions.wrapfunction(mergemod, b'update', clonesparse)
    return orig(ui, repo, *args, **opts)


def _setupclone(ui):
    entry = commands.table[b'clone']
    entry[1].append((b'', b'enable-profile', [], b'enable a sparse profile'))
    entry[1].append((b'', b'include', [], b'include sparse pattern'))
    entry[1].append((b'', b'exclude', [], b'exclude sparse pattern'))
    extensions.wrapcommand(commands.table, b'clone', _clonesparsecmd)


def _setupadd(ui):
    entry = commands.table[b'add']
    entry[1].append(
        (
            b's',
            b'sparse',
            None,
            b'also include directories of added files in sparse config',
        )
    )

    def _add(orig, ui, repo, *pats, **opts):
        if opts.get('sparse'):
            dirs = set()
            for pat in pats:
                dirname, basename = util.split(pat)
                dirs.add(dirname)
            sparse.updateconfig(repo, list(dirs), opts, include=True)
        return orig(ui, repo, *pats, **opts)

    extensions.wrapcommand(commands.table, b'add', _add)


def _setupdirstate(ui):
    """Modify the dirstate to prevent stat'ing excluded files,
    and to prevent modifications to files outside the checkout.
    """

    def walk(orig, self, match, subrepos, unknown, ignored, full=True):
        # hack to not exclude explicitly-specified paths so that they can
        # be warned later on e.g. dirstate.add()
        em = matchmod.exact(match.files())
        sm = matchmod.unionmatcher([self._sparsematcher, em])
        match = matchmod.intersectmatchers(match, sm)
        return orig(self, match, subrepos, unknown, ignored, full)

    extensions.wrapfunction(dirstate.dirstate, b'walk', walk)

    # dirstate.rebuild should not add non-matching files
    def _rebuild(orig, self, parent, allfiles, changedfiles=None):
        matcher = self._sparsematcher
        if not matcher.always():
            allfiles = [f for f in allfiles if matcher(f)]
            if changedfiles:
                changedfiles = [f for f in changedfiles if matcher(f)]

            if changedfiles is not None:
                # In _rebuild, these files will be deleted from the dirstate
                # when they are not found to be in allfiles
                dirstatefilestoremove = {f for f in self if not matcher(f)}
                changedfiles = dirstatefilestoremove.union(changedfiles)

        return orig(self, parent, allfiles, changedfiles)

    extensions.wrapfunction(dirstate.dirstate, b'rebuild', _rebuild)

    # Prevent adding files that are outside the sparse checkout
    editfuncs = [
        b'normal',
        b'add',
        b'normallookup',
        b'copy',
        b'remove',
        b'merge',
    ]
    hint = _(
        b'include file with `hg debugsparse --include <pattern>` or use '
        + b'`hg add -s <file>` to include file directory while adding'
    )
    for func in editfuncs:

        def _wrapper(orig, self, *args, **kwargs):
            sparsematch = self._sparsematcher
            if not sparsematch.always():
                for f in args:
                    if f is not None and not sparsematch(f) and f not in self:
                        raise error.Abort(
                            _(
                                b"cannot add '%s' - it is outside "
                                b"the sparse checkout"
                            )
                            % f,
                            hint=hint,
                        )
            return orig(self, *args, **kwargs)

        extensions.wrapfunction(dirstate.dirstate, func, _wrapper)


@command(
    b'debugsparse',
    [
        (b'I', b'include', False, _(b'include files in the sparse checkout')),
        (b'X', b'exclude', False, _(b'exclude files in the sparse checkout')),
        (b'd', b'delete', False, _(b'delete an include/exclude rule')),
        (
            b'f',
            b'force',
            False,
            _(b'allow changing rules even with pending changes'),
        ),
        (b'', b'enable-profile', False, _(b'enables the specified profile')),
        (b'', b'disable-profile', False, _(b'disables the specified profile')),
        (b'', b'import-rules', False, _(b'imports rules from a file')),
        (b'', b'clear-rules', False, _(b'clears local include/exclude rules')),
        (
            b'',
            b'refresh',
            False,
            _(b'updates the working after sparseness changes'),
        ),
        (b'', b'reset', False, _(b'makes the repo full again')),
    ]
    + commands.templateopts,
    _(b'[--OPTION] PATTERN...'),
    helpbasic=True,
)
def debugsparse(ui, repo, *pats, **opts):
    """make the current checkout sparse, or edit the existing checkout

    The sparse command is used to make the current checkout sparse.
    This means files that don't meet the sparse condition will not be
    written to disk, or show up in any working copy operations. It does
    not affect files in history in any way.

    Passing no arguments prints the currently applied sparse rules.

    --include and --exclude are used to add and remove files from the sparse
    checkout. The effects of adding an include or exclude rule are applied
    immediately. If applying the new rule would cause a file with pending
    changes to be added or removed, the command will fail. Pass --force to
    force a rule change even with pending changes (the changes on disk will
    be preserved).

    --delete removes an existing include/exclude rule. The effects are
    immediate.

    --refresh refreshes the files on disk based on the sparse rules. This is
    only necessary if .hg/sparse was changed by hand.

    --enable-profile and --disable-profile accept a path to a .hgsparse file.
    This allows defining sparse checkouts and tracking them inside the
    repository. This is useful for defining commonly used sparse checkouts for
    many people to use. As the profile definition changes over time, the sparse
    checkout will automatically be updated appropriately, depending on which
    changeset is checked out. Changes to .hgsparse are not applied until they
    have been committed.

    --import-rules accepts a path to a file containing rules in the .hgsparse
    format, allowing you to add --include, --exclude and --enable-profile rules
    in bulk. Like the --include, --exclude and --enable-profile switches, the
    changes are applied immediately.

    --clear-rules removes all local include and exclude rules, while leaving
    any enabled profiles in place.

    Returns 0 if editing the sparse checkout succeeds.
    """
    opts = pycompat.byteskwargs(opts)
    include = opts.get(b'include')
    exclude = opts.get(b'exclude')
    force = opts.get(b'force')
    enableprofile = opts.get(b'enable_profile')
    disableprofile = opts.get(b'disable_profile')
    importrules = opts.get(b'import_rules')
    clearrules = opts.get(b'clear_rules')
    delete = opts.get(b'delete')
    refresh = opts.get(b'refresh')
    reset = opts.get(b'reset')
    count = sum(
        [
            include,
            exclude,
            enableprofile,
            disableprofile,
            delete,
            importrules,
            refresh,
            clearrules,
            reset,
        ]
    )
    if count > 1:
        raise error.Abort(_(b"too many flags specified"))

    if count == 0:
        if repo.vfs.exists(b'sparse'):
            ui.status(repo.vfs.read(b"sparse") + b"\n")
            temporaryincludes = sparse.readtemporaryincludes(repo)
            if temporaryincludes:
                ui.status(
                    _(b"Temporarily Included Files (for merge/rebase):\n")
                )
                ui.status((b"\n".join(temporaryincludes) + b"\n"))
            return
        else:
            raise error.Abort(
                _(
                    b'the debugsparse command is only supported on'
                    b' sparse repositories'
                )
            )

    if include or exclude or delete or reset or enableprofile or disableprofile:
        sparse.updateconfig(
            repo,
            pats,
            opts,
            include=include,
            exclude=exclude,
            reset=reset,
            delete=delete,
            enableprofile=enableprofile,
            disableprofile=disableprofile,
            force=force,
        )

    if importrules:
        sparse.importfromfiles(repo, opts, pats, force=force)

    if clearrules:
        sparse.clearrules(repo, force=force)

    if refresh:
        try:
            wlock = repo.wlock()
            fcounts = map(
                len,
                sparse.refreshwdir(
                    repo, repo.status(), sparse.matcher(repo), force=force
                ),
            )
            sparse.printchanges(
                ui,
                opts,
                added=fcounts[0],
                dropped=fcounts[1],
                conflicting=fcounts[2],
            )
        finally:
            wlock.release()