engine: make hook point for extension a public function

Well there are no private public functions in Python, but we generally treat
functions and variables starting with `_` as private ones.

A function which needs to be overrided in extension should be a public one.

Differential Revision: https://phab.mercurial-scm.org/D9672

hgext/lfs/wrapper.py

@@ -1,550 +1,550 b''
 # wrapper.py - methods wrapping core mercurial logic
 #
 # 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.
 
 from __future__ import absolute_import
 
 import hashlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid, short
 from mercurial.pycompat import (
     getattr,
     setattr,
 )
 
 from mercurial import (
     bundle2,
     changegroup,
     cmdutil,
     context,
     error,
     exchange,
     exthelper,
     localrepo,
     pycompat,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
     wireprotov1server,
 )
 
 from mercurial.upgrade_utils import (
     actions as upgrade_actions,
     engine as upgrade_engine,
 )
 
 from mercurial.interfaces import repository
 
 from mercurial.utils import (
     storageutil,
     stringutil,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
 eh = exthelper.exthelper()
 
 
 @eh.wrapfunction(localrepo, b'makefilestorage')
 def localrepomakefilestorage(orig, requirements, features, **kwargs):
     if b'lfs' in requirements:
         features.add(repository.REPO_FEATURE_LFS)
 
     return orig(requirements=requirements, features=features, **kwargs)
 
 
 @eh.wrapfunction(changegroup, b'allsupportedversions')
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add(b'03')
     return versions
 
 
 @eh.wrapfunction(wireprotov1server, b'_capabilities')
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     if util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         # Advertise a slightly different capability when lfs is *required*, so
         # that the client knows it MUST load the extension.  If lfs is not
         # required on the server, there's no reason to autoload the extension
         # on the client.
         if b'lfs' in repo.requirements:
             caps.append(b'lfs-serve')
 
         caps.append(b'lfs')
     return caps
 
 
 def bypasscheckhash(self, text):
     return False
 
 
 def readfromstore(self, text):
     """Read filelog content from local blobstore transform for flagprocessor.
 
     Default tranform for flagprocessor, returning contents from blobstore.
     Returns a 2-typle (text, validatehash) where validatehash is True as the
     contents of the blobstore should be checked using checkhash.
     """
     p = pointer.deserialize(text)
     oid = p.oid()
     store = self.opener.lfslocalblobstore
     if not store.has(oid):
         p.filename = self.filename
         self.opener.lfsremoteblobstore.readbatch([p], store)
 
     # The caller will validate the content
     text = store.read(oid, verify=False)
 
     # pack hg filelog metadata
     hgmeta = {}
     for k in p.keys():
         if k.startswith(b'x-hg-'):
             name = k[len(b'x-hg-') :]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith(b'\1\n'):
         text = storageutil.packmeta(hgmeta, text)
 
     return (text, True, {})
 
 
 def writetostore(self, text, sidedata):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = storageutil.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
 
     # git-lfs only supports sha256
     oid = hex(hashlib.sha256(text).digest())
     self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = b'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size=b'%d' % len(text))
 
     # by default, we expect the content to be binary. however, LFS could also
     # be used for non-binary content. add a special entry for non-binary data.
     # this will be used by filectx.isbinary().
     if not stringutil.binary(text):
         # not hg filelog metadata (affecting commit hash), no "x-hg-" prefix
         metadata[b'x-is-binary'] = b'0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         for k, v in pycompat.iteritems(hgmeta):
             metadata[b'x-hg-%s' % k] = v
 
     rawtext = metadata.serialize()
     return (rawtext, False)
 
 
 def _islfs(rlog, node=None, rev=None):
     if rev is None:
         if node is None:
             # both None - likely working copy content where node is not ready
             return False
         rev = rlog.rev(node)
     else:
         node = rlog.node(rev)
     if node == nullid:
         return False
     flags = rlog.flags(rev)
     return bool(flags & revlog.REVIDX_EXTSTORED)
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogaddrevision(
     orig,
     self,
     text,
     transaction,
     link,
     p1,
     p2,
     cachedelta=None,
     node=None,
     flags=revlog.REVIDX_DEFAULT_FLAGS,
     **kwds
 ):
     # The matcher isn't available if reposetup() wasn't called.
     lfstrack = self._revlog.opener.options.get(b'lfstrack')
 
     if lfstrack:
         textlen = len(text)
         # exclude hg rename meta from file size
         meta, offset = storageutil.parsemeta(text)
         if offset:
             textlen -= offset
 
         if lfstrack(self._revlog.filename, textlen):
             flags |= revlog.REVIDX_EXTSTORED
 
     return orig(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=cachedelta,
         node=node,
         flags=flags,
         **kwds
     )
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogrenamed(orig, self, node):
     if _islfs(self._revlog, node):
         rawtext = self._revlog.rawdata(node)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if b'x-hg-copy' in metadata and b'x-hg-copyrev' in metadata:
             return metadata[b'x-hg-copy'], bin(metadata[b'x-hg-copyrev'])
         else:
             return False
     return orig(self, node)
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogsize(orig, self, rev):
     if _islfs(self._revlog, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self._revlog.rawdata(rev)
         metadata = pointer.deserialize(rawtext)
         return int(metadata[b'size'])
     return orig(self, rev)
 
 
 @eh.wrapfunction(revlog, b'_verify_revision')
 def _verify_revision(orig, rl, skipflags, state, node):
     if _islfs(rl, node=node):
         rawtext = rl.rawdata(node)
         metadata = pointer.deserialize(rawtext)
 
         # Don't skip blobs that are stored locally, as local verification is
         # relatively cheap and there's no other way to verify the raw data in
         # the revlog.
         if rl.opener.lfslocalblobstore.has(metadata.oid()):
             skipflags &= ~revlog.REVIDX_EXTSTORED
         elif skipflags & revlog.REVIDX_EXTSTORED:
             # The wrapped method will set `skipread`, but there's enough local
             # info to check renames.
             state[b'safe_renamed'].add(node)
 
     orig(rl, skipflags, state, node)
 
 
 @eh.wrapfunction(context.basefilectx, b'cmp')
 def filectxcmp(orig, self, fctx):
     """returns True if text is different than fctx"""
     # some fctx (ex. hg-git) is not based on basefilectx and do not have islfs
     if self.islfs() and getattr(fctx, 'islfs', lambda: False)():
         # fast path: check LFS oid
         p1 = pointer.deserialize(self.rawdata())
         p2 = pointer.deserialize(fctx.rawdata())
         return p1.oid() != p2.oid()
     return orig(self, fctx)
 
 
 @eh.wrapfunction(context.basefilectx, b'isbinary')
 def filectxisbinary(orig, self):
     if self.islfs():
         # fast path: use lfs metadata to answer isbinary
         metadata = pointer.deserialize(self.rawdata())
         # if lfs metadata says nothing, assume it's binary by default
         return bool(int(metadata.get(b'x-is-binary', 1)))
     return orig(self)
 
 
 def filectxislfs(self):
     return _islfs(self.filelog()._revlog, self.filenode())
 
 
 @eh.wrapfunction(cmdutil, b'_updatecatformatter')
 def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
     orig(fm, ctx, matcher, path, decode)
     fm.data(rawdata=ctx[path].rawdata())
 
 
 @eh.wrapfunction(scmutil, b'wrapconvertsink')
 def convertsink(orig, sink):
     sink = orig(sink)
     if sink.repotype == b'hg':
 
         class lfssink(sink.__class__):
             def putcommit(
                 self,
                 files,
                 copies,
                 parents,
                 commit,
                 source,
                 revmap,
                 full,
                 cleanp2,
             ):
                 pc = super(lfssink, self).putcommit
                 node = pc(
                     files,
                     copies,
                     parents,
                     commit,
                     source,
                     revmap,
                     full,
                     cleanp2,
                 )
 
                 if b'lfs' not in self.repo.requirements:
                     ctx = self.repo[node]
 
                     # The file list may contain removed files, so check for
                     # membership before assuming it is in the context.
                     if any(f in ctx and ctx[f].islfs() for f, n in files):
                         self.repo.requirements.add(b'lfs')
                         scmutil.writereporequirements(self.repo)
 
                 return node
 
         sink.__class__ = lfssink
 
     return sink
 
 
 # bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
 # options and blob stores are passed from othervfs to the new readonlyvfs.
 @eh.wrapfunction(vfsmod.readonlyvfs, b'__init__')
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith(b'lfs'):
             self.options[k] = v
     # also copy lfs blobstores. note: this can run before reposetup, so lfs
     # blobstore attributes are not always ready at this time.
     for name in [b'lfslocalblobstore', b'lfsremoteblobstore']:
         if util.safehasattr(othervfs, name):
             setattr(self, name, getattr(othervfs, name))
 
 
 def _prefetchfiles(repo, revmatches):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     if not util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         return
 
     pointers = []
     oids = set()
     localstore = repo.svfs.lfslocalblobstore
 
     for rev, match in revmatches:
         ctx = repo[rev]
         for f in ctx.walk(match):
             p = pointerfromctx(ctx, f)
             if p and p.oid() not in oids and not localstore.has(p.oid()):
                 p.filename = f
                 pointers.append(p)
                 oids.add(p.oid())
 
     if pointers:
         # Recalculating the repo store here allows 'paths.default' that is set
         # on the repo by a clone command to be used for the update.
         blobstore.remote(repo).readbatch(pointers, localstore)
 
 
 def _canskipupload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, b'lfsremoteblobstore'):
         return True
 
     # if remotestore is a null store, upload is a no-op and can be skipped
     return isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 
 def candownload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, b'lfsremoteblobstore'):
         return False
 
     # if remotestore is a null store, downloads will lead to nothing
     return not isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 
 def uploadblobsfromrevs(repo, revs):
     """upload lfs blobs introduced by revs
 
     Note: also used by other extensions e. g. infinitepush. avoid renaming.
     """
     if _canskipupload(repo):
         return
     pointers = extractpointers(repo, revs)
     uploadblobs(repo, pointers)
 
 
 def prepush(pushop):
     """Prepush hook.
 
     Read through the revisions to push, looking for filelog entries that can be
     deserialized into metadata so that we can block the push on their upload to
     the remote blobstore.
     """
     return uploadblobsfromrevs(pushop.repo, pushop.outgoing.missing)
 
 
 @eh.wrapfunction(exchange, b'push')
 def push(orig, repo, remote, *args, **kwargs):
     """bail on push if the extension isn't enabled on remote when needed, and
     update the remote store based on the destination path."""
     if b'lfs' in repo.requirements:
         # If the remote peer is for a local repo, the requirement tests in the
         # base class method enforce lfs support.  Otherwise, some revisions in
         # this repo use lfs, and the remote repo needs the extension loaded.
         if not remote.local() and not remote.capable(b'lfs'):
             # This is a copy of the message in exchange.push() when requirements
             # are missing between local repos.
             m = _(b"required features are not supported in the destination: %s")
             raise error.Abort(
                 m % b'lfs', hint=_(b'enable the lfs extension on the server')
             )
 
         # Repositories where this extension is disabled won't have the field.
         # But if there's a requirement, then the extension must be loaded AND
         # there may be blobs to push.
         remotestore = repo.svfs.lfsremoteblobstore
         try:
             repo.svfs.lfsremoteblobstore = blobstore.remote(repo, remote.url())
             return orig(repo, remote, *args, **kwargs)
         finally:
             repo.svfs.lfsremoteblobstore = remotestore
     else:
         return orig(repo, remote, *args, **kwargs)
 
 
 # when writing a bundle via "hg bundle" command, upload related LFS blobs
 @eh.wrapfunction(bundle2, b'writenewbundle')
 def writenewbundle(
     orig, ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
 ):
     """upload LFS blobs added by outgoing revisions on 'hg bundle'"""
     uploadblobsfromrevs(repo, outgoing.missing)
     return orig(
         ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
     )
 
 
 def extractpointers(repo, revs):
     """return a list of lfs pointers added by given revs"""
     repo.ui.debug(b'lfs: computing set of blobs to upload\n')
     pointers = {}
 
     makeprogress = repo.ui.makeprogress
     with makeprogress(
         _(b'lfs search'), _(b'changesets'), len(revs)
     ) as progress:
         for r in revs:
             ctx = repo[r]
             for p in pointersfromctx(ctx).values():
                 pointers[p.oid()] = p
             progress.increment()
         return sorted(pointers.values(), key=lambda p: p.oid())
 
 
 def pointerfromctx(ctx, f, removed=False):
     """return a pointer for the named file from the given changectx, or None if
     the file isn't LFS.
 
     Optionally, the pointer for a file deleted from the context can be returned.
     Since no such pointer is actually stored, and to distinguish from a non LFS
     file, this pointer is represented by an empty dict.
     """
     _ctx = ctx
     if f not in ctx:
         if not removed:
             return None
         if f in ctx.p1():
             _ctx = ctx.p1()
         elif f in ctx.p2():
             _ctx = ctx.p2()
         else:
             return None
     fctx = _ctx[f]
     if not _islfs(fctx.filelog()._revlog, fctx.filenode()):
         return None
     try:
         p = pointer.deserialize(fctx.rawdata())
         if ctx == _ctx:
             return p
         return {}
     except pointer.InvalidPointer as ex:
         raise error.Abort(
             _(b'lfs: corrupted pointer (%s@%s): %s\n')
             % (f, short(_ctx.node()), ex)
         )
 
 
 def pointersfromctx(ctx, removed=False):
     """return a dict {path: pointer} for given single changectx.
 
     If ``removed`` == True and the LFS file was removed from ``ctx``, the value
     stored for the path is an empty dict.
     """
     result = {}
     m = ctx.repo().narrowmatch()
 
     # TODO: consider manifest.fastread() instead
     for f in ctx.files():
         if not m(f):
             continue
         p = pointerfromctx(ctx, f, removed=removed)
         if p is not None:
             result[f] = p
     return result
 
 
 def uploadblobs(repo, pointers):
     """upload given pointers from local blobstore"""
     if not pointers:
         return
 
     remoteblob = repo.svfs.lfsremoteblobstore
     remoteblob.writebatch(pointers, repo.svfs.lfslocalblobstore)
 
 
[e-mail](upgrade_engine, b'_finishdatamigration')
[e-mail](upgrade_engine, b'finishdatamigration')
 def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
     orig(ui, srcrepo, dstrepo, requirements)
 
     # Skip if this hasn't been passed to reposetup()
     if util.safehasattr(
         srcrepo.svfs, b'lfslocalblobstore'
     ) and util.safehasattr(dstrepo.svfs, b'lfslocalblobstore'):
         srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
         dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs
 
         for dirpath, dirs, files in srclfsvfs.walk():
             for oid in files:
                 ui.write(_(b'copying lfs blob %s\n') % oid)
                 lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 
 @eh.wrapfunction(upgrade_actions, b'preservedrequirements')
 @eh.wrapfunction(upgrade_actions, b'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if b'lfs' in repo.requirements:
         reqs.add(b'lfs')
     return reqs

mercurial/upgrade_utils/engine.py

@@ -1,520 +1,520 b''
 # 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
 
 from ..i18n import _
 from ..pycompat import getattr
 from .. import (
     changelog,
     error,
     filelog,
     manifest,
     metadata,
     pycompat,
     requirements,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
 )
 
 
 def _revlogfrompath(repo, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if path == b'00changelog.i':
         return changelog.changelog(repo.svfs)
     elif path.endswith(b'00manifest.i'):
         mandir = path[: -len(b'00manifest.i')]
         return manifest.manifestrevlog(repo.svfs, tree=mandir)
     else:
         # reverse of "/".join(("data", path + ".i"))
         return filelog.filelog(repo.svfs, path[5:-2])
 
 
 def _copyrevlog(tr, destrepo, oldrl, unencodedname):
     """copy all relevant files for `oldrl` into `destrepo` store
 
     Files are copied "as is" without any transformation. The copy is performed
     without extra checks. Callers are responsible for making sure the copied
     content is compatible with format of the destination repository.
     """
     oldrl = getattr(oldrl, '_revlog', oldrl)
     newrl = _revlogfrompath(destrepo, unencodedname)
     newrl = getattr(newrl, '_revlog', newrl)
 
     oldvfs = oldrl.opener
     newvfs = newrl.opener
     oldindex = oldvfs.join(oldrl.indexfile)
     newindex = newvfs.join(newrl.indexfile)
     olddata = oldvfs.join(oldrl.datafile)
     newdata = newvfs.join(newrl.datafile)
 
     with newvfs(newrl.indexfile, b'w'):
         pass  # create all the directories
 
     util.copyfile(oldindex, newindex)
     copydata = oldrl.opener.exists(oldrl.datafile)
     if copydata:
         util.copyfile(olddata, newdata)
 
     if not (
         unencodedname.endswith(b'00changelog.i')
         or unencodedname.endswith(b'00manifest.i')
     ):
         destrepo.svfs.fncache.add(unencodedname)
         if copydata:
             destrepo.svfs.fncache.add(unencodedname[:-2] + b'.d')
 
 
 UPGRADE_CHANGELOG = b"changelog"
 UPGRADE_MANIFEST = b"manifest"
 UPGRADE_FILELOGS = b"all-filelogs"
 
 UPGRADE_ALL_REVLOGS = frozenset(
     [UPGRADE_CHANGELOG, UPGRADE_MANIFEST, UPGRADE_FILELOGS]
 )
 
 
 def getsidedatacompanion(srcrepo, dstrepo):
     sidedatacompanion = None
     removedreqs = srcrepo.requirements - dstrepo.requirements
     addedreqs = dstrepo.requirements - srcrepo.requirements
     if requirements.SIDEDATA_REQUIREMENT in removedreqs:
 
         def sidedatacompanion(rl, rev):
             rl = getattr(rl, '_revlog', rl)
             if rl.flags(rev) & revlog.REVIDX_SIDEDATA:
                 return True, (), {}, 0, 0
             return False, (), {}, 0, 0
 
     elif requirements.COPIESSDC_REQUIREMENT in addedreqs:
         sidedatacompanion = metadata.getsidedataadder(srcrepo, dstrepo)
     elif requirements.COPIESSDC_REQUIREMENT in removedreqs:
         sidedatacompanion = metadata.getsidedataremover(srcrepo, dstrepo)
     return sidedatacompanion
 
 
 def matchrevlog(revlogfilter, entry):
     """check if a revlog is selected for cloning.
 
     In other words, are there any updates which need to be done on revlog
     or it can be blindly copied.
 
     The store entry is checked against the passed filter"""
     if entry.endswith(b'00changelog.i'):
         return UPGRADE_CHANGELOG in revlogfilter
     elif entry.endswith(b'00manifest.i'):
         return UPGRADE_MANIFEST in revlogfilter
     return UPGRADE_FILELOGS in revlogfilter
 
 
 def _perform_clone(
     ui,
     dstrepo,
     tr,
     old_revlog,
     unencoded,
     upgrade_op,
     sidedatacompanion,
     oncopiedrevision,
 ):
     """ returns the new revlog object created"""
     newrl = None
     if matchrevlog(upgrade_op.revlogs_to_process, unencoded):
         ui.note(
             _(b'cloning %d revisions from %s\n') % (len(old_revlog), unencoded)
         )
         newrl = _revlogfrompath(dstrepo, unencoded)
         old_revlog.clone(
             tr,
             newrl,
             addrevisioncb=oncopiedrevision,
             deltareuse=upgrade_op.delta_reuse_mode,
             forcedeltabothparents=upgrade_op.force_re_delta_both_parents,
             sidedatacompanion=sidedatacompanion,
         )
     else:
         msg = _(b'blindly copying %s containing %i revisions\n')
         ui.note(msg % (unencoded, len(old_revlog)))
         _copyrevlog(tr, dstrepo, old_revlog, unencoded)
 
         newrl = _revlogfrompath(dstrepo, unencoded)
     return newrl
 
 
 def _clonerevlogs(
     ui,
     srcrepo,
     dstrepo,
     tr,
     upgrade_op,
 ):
     """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
 
     alldatafiles = list(srcrepo.store.walk())
     # mapping of data files which needs to be cloned
     # key is unencoded filename
     # value is revlog_object_from_srcrepo
     manifests = {}
     changelogs = {}
     filelogs = {}
 
     # 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 alldatafiles:
         if unencoded.endswith(b'.d'):
             continue
 
         rl = _revlogfrompath(srcrepo, unencoded)
 
         info = rl.storageinfo(
             exclusivefiles=True,
             revisionscount=True,
             trackedsize=True,
             storedsize=True,
         )
 
         revcount += info[b'revisionscount'] or 0
         datasize = info[b'storedsize'] or 0
         rawsize = info[b'trackedsize'] or 0
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if isinstance(rl, changelog.changelog):
             changelogs[unencoded] = rl
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif isinstance(rl, manifest.manifestrevlog):
             manifests[unencoded] = rl
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif isinstance(rl, filelog.filelog):
             filelogs[unencoded] = rl
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError(b'unknown revlog type')
 
     if not revcount:
         return
 
     ui.status(
         _(
             b'migrating %d total revisions (%d in filelogs, %d in manifests, '
             b'%d in changelog)\n'
         )
         % (revcount, frevcount, mrevcount, crevcount)
     )
     ui.status(
         _(b'migrating %s in store; %s tracked data\n')
         % ((util.bytecount(srcsize), util.bytecount(srcrawsize)))
     )
 
     # Used to keep track of progress.
     progress = None
 
     def oncopiedrevision(rl, rev, node):
         progress.increment()
 
     sidedatacompanion = getsidedatacompanion(srcrepo, dstrepo)
 
     # Migrating filelogs
     ui.status(
         _(
             b'migrating %d filelogs containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             fcount,
             frevcount,
             util.bytecount(fsrcsize),
             util.bytecount(frawsize),
         )
     )
     progress = srcrepo.ui.makeprogress(_(b'file revisions'), total=frevcount)
     for unencoded, oldrl in sorted(filelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         fdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d filelog revisions across %d '
             b'filelogs; change in size: %s\n'
         )
         % (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
     )
 
     # Migrating manifests
     ui.status(
         _(
             b'migrating %d manifests containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             mcount,
             mrevcount,
             util.bytecount(msrcsize),
             util.bytecount(mrawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'manifest revisions'), total=mrevcount
     )
     for unencoded, oldrl in sorted(manifests.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         mdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d manifest revisions across %d '
             b'manifests; change in size: %s\n'
         )
         % (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
     )
 
     # Migrating changelog
     ui.status(
         _(
             b'migrating changelog containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             crevcount,
             util.bytecount(csrcsize),
             util.bytecount(crawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'changelog revisions'), total=crevcount
     )
     for unencoded, oldrl in sorted(changelogs.items()):
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             unencoded,
             upgrade_op,
             sidedatacompanion,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         cdstsize += info[b'storedsize'] or 0
     progress.complete()
     ui.status(
         _(
             b'finished migrating %d changelog revisions; change in size: '
             b'%s\n'
         )
         % (crevcount, util.bytecount(cdstsize - csrcsize))
     )
 
     dstsize = fdstsize + mdstsize + cdstsize
     ui.status(
         _(
             b'finished migrating %d total revisions; total change in store '
             b'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((b'.i', b'.d', b'.n', b'.nd')):
         return False
     # Skip transaction related files.
     if path.startswith(b'undo'):
         return False
     # Only copy regular files.
     if mode != stat.S_IFREG:
         return False
     # Skip other skipped files.
     if path in (b'lock', b'fncache'):
         return False
 
     return True
 
 
-def _finishdatamigration(ui, srcrepo, dstrepo, requirements):
+def finishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 
 def upgrade(ui, srcrepo, dstrepo, upgrade_op):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
 
     ui.status(
         _(
             b'(it is safe to interrupt this process any time before '
             b'data migration completes)\n'
         )
     )
 
     with dstrepo.transaction(b'upgrade') as tr:
         _clonerevlogs(
             ui,
             srcrepo,
             dstrepo,
             tr,
             upgrade_op,
         )
 
     # Now copy other files in the store directory.
     # The sorted() makes execution deterministic.
     for p, kind, st in sorted(srcrepo.store.vfs.readdir(b'', stat=True)):
         if not _filterstorefile(
             srcrepo, dstrepo, upgrade_op.new_requirements, p, kind, st
         ):
             continue
 
         srcrepo.ui.status(_(b'copying %s\n') % p)
         src = srcrepo.store.rawvfs.join(p)
         dst = dstrepo.store.rawvfs.join(p)
         util.copyfile(src, dst, copystat=True)
 
-    _finishdatamigration(ui, srcrepo, dstrepo, requirements)
+    finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
     ui.status(_(b'data fully migrated to temporary repository\n'))
 
     backuppath = pycompat.mkdtemp(prefix=b'upgradebackup.', dir=srcrepo.path)
     backupvfs = vfsmod.vfs(backuppath)
 
     # Make a backup of requires file first, as it is the first to be modified.
     util.copyfile(srcrepo.vfs.join(b'requires'), backupvfs.join(b'requires'))
 
     # We install an arbitrary requirement that clients must not support
     # as a mechanism to lock out new clients during the data swap. This is
     # better than allowing a client to continue while the repository is in
     # an inconsistent state.
     ui.status(
         _(
             b'marking source repository as being upgraded; clients will be '
             b'unable to read from repository\n'
         )
     )
     scmutil.writereporequirements(
         srcrepo, srcrepo.requirements | {b'upgradeinprogress'}
     )
 
     ui.status(_(b'starting in-place swap of repository data\n'))
     ui.status(_(b'replaced files will be backed up at %s\n') % backuppath)
 
     # Now swap in the new store directory. Doing it as a rename should make
     # the operation nearly instantaneous and atomic (at least in well-behaved
     # environments).
     ui.status(_(b'replacing store...\n'))
     tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join(b'store'))
     util.rename(dstrepo.spath, srcrepo.spath)
     elapsed = util.timer() - tstart
     ui.status(
         _(
             b'store replacement complete; repository was inconsistent for '
             b'%0.1fs\n'
         )
         % elapsed
     )
 
     # We first write the requirements file. Any new requirements will lock
     # out legacy clients.
     ui.status(
         _(
             b'finalizing requirements file and making repository readable '
             b'again\n'
         )
     )
     scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
 
     # The lock file from the old store won't be removed because nothing has a
     # reference to its new location. So clean it up manually. Alternatively, we
     # could update srcrepo.svfs and other variables to point to the new
     # location. This is simpler.
     backupvfs.unlink(b'store/lock')
 
     return backuppath