# upgrade.py - functions for in place upgrade of Mercurial repository

#

# Copyright (c) 2016-present, Gregory Szorc

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import stat

import tempfile

from .i18n import _

from . import (

    changelog,

    error,

    localrepo,

    manifest,

    revlog,

    scmutil,

    util,

    vfs as vfsmod,

)

def requiredsourcerequirements(repo):

    """Obtain requirements required to be present to upgrade a repo.

    An upgrade will not be allowed if the repository doesn't have the

    requirements returned by this function.

    """

    return set([

        # Introduced in Mercurial 0.9.2.

        'revlogv1',

        # Introduced in Mercurial 0.9.2.

        'store',

    ])

def blocksourcerequirements(repo):

    """Obtain requirements that will prevent an upgrade from occurring.

    An upgrade cannot be performed if the source repository contains a

    requirements in the returned set.

    """

    return set([

        # The upgrade code does not yet support these experimental features.

        # This is an artificial limitation.

        'manifestv2',

        'treemanifest',

        # This was a precursor to generaldelta and was never enabled by default.

        # It should (hopefully) not exist in the wild.

        'parentdelta',

        # Upgrade should operate on the actual store, not the shared link.

        'shared',

    ])

def supportremovedrequirements(repo):

    """Obtain requirements that can be removed during an upgrade.

    If an upgrade were to create a repository that dropped a requirement,

    the dropped requirement must appear in the returned set for the upgrade

    to be allowed.

    """

    return set()

def supporteddestrequirements(repo):

    """Obtain requirements that upgrade supports in the destination.

    If the result of the upgrade would create requirements not in this set,

    the upgrade is disallowed.

    Extensions should monkeypatch this to add their custom requirements.

    """

    return set([

        'dotencode',

        'fncache',

        'generaldelta',

        'revlogv1',

        'store',

    ])

def allowednewrequirements(repo):

    """Obtain requirements that can be added to a repository during upgrade.

    This is used to disallow proposed requirements from being added when

    they weren't present before.

    We use a list of allowed requirement additions instead of a list of known

    bad additions because the whitelist approach is safer and will prevent

    future, unknown requirements from accidentally being added.

    """

    return set([

        'dotencode',

        'fncache',

        'generaldelta',

    ])

deficiency = 'deficiency'

optimisation = 'optimization'

class improvement(object):

    """Represents an improvement that can be made as part of an upgrade.

    The following attributes are defined on each instance:

    name

       Machine-readable string uniquely identifying this improvement. It

       will be mapped to an action later in the upgrade process.

    type

       Either ``deficiency`` or ``optimisation``. A deficiency is an obvious

       problem. An optimization is an action (sometimes optional) that

       can be taken to further improve the state of the repository.

    description

       Message intended for humans explaining the improvement in more detail,

       including the implications of it. For ``deficiency`` types, should be

       worded in the present tense. For ``optimisation`` types, should be

       worded in the future tense.

    upgrademessage

       Message intended for humans explaining what an upgrade addressing this

       issue will do. Should be worded in the future tense.

    """

        self.name = name

        self.type = type

        self.description = description

        self.upgrademessage = upgrademessage

    def __eq__(self, other):

        if not isinstance(other, improvement):

            # This is what python tell use to do

            return NotImplemented

        return self.name == other.name

    def __ne__(self, other):

        return not self == other

    def __hash__(self):

        return hash(self.name)

def finddeficiencies(repo):

    """returns a list of deficiencies that the repo suffer from"""

    newreporeqs = localrepo.newreporequirements(repo)

    deficiencies = []

    # We could detect lack of revlogv1 and store here, but they were added

    # in 0.9.2 and we don't support upgrading repos without these

    # requirements, so let's not bother.

    if 'fncache' not in repo.requirements:

            name='fncache',

            description=_('long and reserved filenames may not work correctly; '

                          'repository performance is sub-optimal'),

            upgrademessage=_('repository will be more resilient to storing '

                             'certain paths and performance of certain '

                             'operations should be improved'),

            fromdefault=True,

            fromconfig='fncache' in newreporeqs))

    if 'dotencode' not in repo.requirements:

            name='dotencode',

            description=_('storage of filenames beginning with a period or '

                          'space may not work correctly'),

            upgrademessage=_('repository will be better able to store files '

                             'beginning with a space or period'),

            fromdefault=True,

            fromconfig='dotencode' in newreporeqs))

    if 'generaldelta' not in repo.requirements:

            name='generaldelta',

            description=_('deltas within internal storage are unable to '

                          'choose optimal revisions; repository is larger and '

                          'slower than it could be; interaction with other '

                          'repositories may require extra network and CPU '

                          'resources, making "hg push" and "hg pull" slower'),

            upgrademessage=_('repository storage will be able to create '

                             'optimal deltas; new repository data will be '

                             'smaller and read times should decrease; '

                             'interacting with other repositories using this '

                             'storage model should require less network and '

                             'CPU resources, making "hg push" and "hg pull" '

                             'faster'),

            fromdefault=True,

            fromconfig='generaldelta' in newreporeqs))

    # Mercurial 4.0 changed changelogs to not use delta chains. Search for

    # changelogs with deltas.

    cl = repo.changelog

    for rev in cl:

        chainbase = cl.chainbase(rev)

        if chainbase != rev:

                name='removecldeltachain',

                description=_('changelog storage is using deltas instead of '

                              'raw entries; changelog reading and any '

                              'operation relying on changelog data are slower '

                              'than they could be'),

                upgrademessage=_('changelog storage will be reformated to '

                                 'store raw entries; changelog reading will be '

                                 'faster; changelog size may be reduced'),

                fromdefault=True,

                fromconfig=True))

            break

    return deficiencies

def findoptimizations(repo):

    """Determine optimisation that could be used during upgrade"""

    # These are unconditionally added. There is logic later that figures out

    # which ones to apply.

    optimizations = []

    optimizations.append(improvement(

        name='redeltaparent',

        type=optimisation,

        description=_('deltas within internal storage will be recalculated to '

                      'choose an optimal base revision where this was not '

                      'already done; the size of the repository may shrink and '

                      'various operations may become faster; the first time '

                      'this optimization is performed could slow down upgrade '

                      'execution considerably; subsequent invocations should '

                      'not run noticeably slower'),

        upgrademessage=_('deltas within internal storage will choose a new '

                         'base revision if needed')))

    optimizations.append(improvement(

        name='redeltamultibase',

        type=optimisation,

        description=_('deltas within internal storage will be recalculated '

                      'against multiple base revision and the smallest '

                      'difference will be used; the size of the repository may '

                      'shrink significantly when there are many merges; this '

                      'optimization will slow down execution in proportion to '

                      'the number of merges in the repository and the amount '

                      'of files in the repository; this slow down should not '

                      'be significant unless there are tens of thousands of '

                      'files and thousands of merges'),

        upgrademessage=_('deltas within internal storage will choose an '

                         'optimal delta by computing deltas against multiple '

                         'parents; may slow down execution time '

                         'significantly')))

    optimizations.append(improvement(

        name='redeltaall',

        type=optimisation,

        description=_('deltas within internal storage will always be '

                      'recalculated without reusing prior deltas; this will '

                      'likely make execution run several times slower; this '

                      'optimization is typically not needed'),

        upgrademessage=_('deltas within internal storage will be fully '

                         'recomputed; this will likely drastically slow down '

                         'execution time')))

    return optimizations

def determineactions(repo, deficiencies, sourcereqs, destreqs):

    """Determine upgrade actions that will be performed.

    Given a list of improvements as returned by ``finddeficiencies`` and

    ``findoptimizations``, determine the list of upgrade actions that

    will be performed.

    The role of this function is to filter improvements if needed, apply

    recommended optimizations from the improvements list that make sense,

    etc.

    Returns a list of action names.

    """

    newactions = []

    knownreqs = supporteddestrequirements(repo)

    for d in deficiencies:

        name = d.name

        # If the action is a requirement that doesn't show up in the

        # destination requirements, prune the action.

        if name in knownreqs and name not in destreqs:

            continue

        newactions.append(d)

    # FUTURE consider adding some optimizations here for certain transitions.

    # e.g. adding generaldelta could schedule parent redeltas.

    return newactions

def _revlogfrompath(repo, path):

    """Obtain a revlog from a repo path.

    An instance of the appropriate class is returned.

    """

    if path == '00changelog.i':

        return changelog.changelog(repo.svfs)

    elif path.endswith('00manifest.i'):

        mandir = path[:-len('00manifest.i')]

        return manifest.manifestrevlog(repo.svfs, dir=mandir)

    else:

        # Filelogs don't do anything special with settings. So we can use a

        # vanilla revlog.

        return revlog.revlog(repo.svfs, path)

def _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse, aggressivemergedeltas):

    """Copy revlogs between 2 repos."""

    revcount = 0

    srcsize = 0

    srcrawsize = 0

    dstsize = 0

    fcount = 0

    frevcount = 0

    fsrcsize = 0

    frawsize = 0

    fdstsize = 0

    mcount = 0

    mrevcount = 0

    msrcsize = 0

    mrawsize = 0

    mdstsize = 0

    crevcount = 0

    csrcsize = 0

    crawsize = 0

    cdstsize = 0

    # Perform a pass to collect metadata. This validates we can open all

    # source files and allows a unified progress bar to be displayed.

    for unencoded, encoded, size in srcrepo.store.walk():

        if unencoded.endswith('.d'):

            continue

        rl = _revlogfrompath(srcrepo, unencoded)

        revcount += len(rl)

        datasize = 0

        rawsize = 0

        idx = rl.index

        for rev in rl:

            e = idx[rev]

            datasize += e[1]

            rawsize += e[2]

        srcsize += datasize

        srcrawsize += rawsize

        # This is for the separate progress bars.

        if isinstance(rl, changelog.changelog):

            crevcount += len(rl)

            csrcsize += datasize

            crawsize += rawsize

        elif isinstance(rl, manifest.manifestrevlog):

            mcount += 1

            mrevcount += len(rl)

            msrcsize += datasize

            mrawsize += rawsize

        elif isinstance(rl, revlog.revlog):

            fcount += 1

            frevcount += len(rl)

            fsrcsize += datasize

            frawsize += rawsize

    if not revcount:

        return

    ui.write(_('migrating %d total revisions (%d in filelogs, %d in manifests, '

               '%d in changelog)\n') %

             (revcount, frevcount, mrevcount, crevcount))

    ui.write(_('migrating %s in store; %s tracked data\n') % (

             (util.bytecount(srcsize), util.bytecount(srcrawsize))))

    # Used to keep track of progress.

    progress = []

    def oncopiedrevision(rl, rev, node):

        progress[1] += 1

        srcrepo.ui.progress(progress[0], progress[1], total=progress[2])

    # Do the actual copying.

    # FUTURE this operation can be farmed off to worker processes.

    seen = set()

    for unencoded, encoded, size in srcrepo.store.walk():

        if unencoded.endswith('.d'):

            continue

        oldrl = _revlogfrompath(srcrepo, unencoded)

        newrl = _revlogfrompath(dstrepo, unencoded)

        if isinstance(oldrl, changelog.changelog) and 'c' not in seen:

            ui.write(_('finished migrating %d manifest revisions across %d '

                       'manifests; change in size: %s\n') %

                     (mrevcount, mcount, util.bytecount(mdstsize - msrcsize)))

            ui.write(_('migrating changelog containing %d revisions '

                       '(%s in store; %s tracked data)\n') %

                     (crevcount, util.bytecount(csrcsize),

                      util.bytecount(crawsize)))

            seen.add('c')

            progress[:] = [_('changelog revisions'), 0, crevcount]

        elif isinstance(oldrl, manifest.manifestrevlog) and 'm' not in seen:

            ui.write(_('finished migrating %d filelog revisions across %d '

                       'filelogs; change in size: %s\n') %

                     (frevcount, fcount, util.bytecount(fdstsize - fsrcsize)))

            ui.write(_('migrating %d manifests containing %d revisions '

                       '(%s in store; %s tracked data)\n') %

                     (mcount, mrevcount, util.bytecount(msrcsize),

                      util.bytecount(mrawsize)))

            seen.add('m')

            progress[:] = [_('manifest revisions'), 0, mrevcount]

        elif 'f' not in seen:

            ui.write(_('migrating %d filelogs containing %d revisions '

                       '(%s in store; %s tracked data)\n') %

                     (fcount, frevcount, util.bytecount(fsrcsize),

                      util.bytecount(frawsize)))

            seen.add('f')

            progress[:] = [_('file revisions'), 0, frevcount]

        ui.progress(progress[0], progress[1], total=progress[2])

        ui.note(_('cloning %d revisions from %s\n') % (len(oldrl), unencoded))

        oldrl.clone(tr, newrl, addrevisioncb=oncopiedrevision,

                    deltareuse=deltareuse,

                    aggressivemergedeltas=aggressivemergedeltas)

        datasize = 0

        idx = newrl.index

        for rev in newrl:

            datasize += idx[rev][1]

        dstsize += datasize

        if isinstance(newrl, changelog.changelog):

            cdstsize += datasize

        elif isinstance(newrl, manifest.manifestrevlog):

            mdstsize += datasize

        else:

            fdstsize += datasize

    ui.progress(progress[0], None)

    ui.write(_('finished migrating %d changelog revisions; change in size: '

               '%s\n') % (crevcount, util.bytecount(cdstsize - csrcsize)))

    ui.write(_('finished migrating %d total revisions; total change in store '

               'size: %s\n') % (revcount, util.bytecount(dstsize - srcsize)))

def _filterstorefile(srcrepo, dstrepo, requirements, path, mode, st):

    """Determine whether to copy a store file during upgrade.

    This function is called when migrating store files from ``srcrepo`` to

    ``dstrepo`` as part of upgrading a repository.

    Args:

      srcrepo: repo we are copying from

      dstrepo: repo we are copying to

      requirements: set of requirements for ``dstrepo``

      path: store file being examined

      mode: the ``ST_MODE`` file type of ``path``

      st: ``stat`` data structure for ``path``

    Function should return ``True`` if the file is to be copied.

    """

    # Skip revlogs.

    if path.endswith(('.i', '.d')):

        return False

    # Skip transaction related files.

    if path.startswith('undo'):

        return False