lfs: move the 'supportedoutgoingversions' handling to changegroup.py

This handling already exists here for the narrow extension.  We still need to
either figure out how to enable changegroup v3 without the extension, or figure
out how to let the server detect that the client doesn't have it loaded, and
emit a user friendly error[1].  I can't tell if D1944 is the appropriate vehicle
for the latter.

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109550.html

hgext/lfs/__init__.py

@@ -1,390 +1,387
 # lfs - hash-preserving large file support using Git-LFS protocol
 #
 # 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.
 
 """lfs - large file support (EXPERIMENTAL)
 
 This extension allows large files to be tracked outside of the normal
 repository storage and stored on a centralized server, similar to the
 ``largefiles`` extension.  The ``git-lfs`` protocol is used when
 communicating with the server, so existing git infrastructure can be
 harnessed.  Even though the files are stored outside of the repository,
 they are still integrity checked in the same manner as normal files.
 
 The files stored outside of the repository are downloaded on demand,
 which reduces the time to clone, and possibly the local disk usage.
 This changes fundamental workflows in a DVCS, so careful thought
 should be given before deploying it.  :hg:`convert` can be used to
 convert LFS repositories to normal repositories that no longer
 require this extension, and do so without changing the commit hashes.
 This allows the extension to be disabled if the centralized workflow
 becomes burdensome.  However, the pre and post convert clones will
 not be able to communicate with each other unless the extension is
 enabled on both.
 
 To start a new repository, or to add LFS files to an existing one, just
 create an ``.hglfs`` file as described below in the root directory of
 the repository.  Typically, this file should be put under version
 control, so that the settings will propagate to other repositories with
 push and pull.  During any commit, Mercurial will consult this file to
 determine if an added or modified file should be stored externally.  The
 type of storage depends on the characteristics of the file at each
 commit.  A file that is near a size threshold may switch back and forth
 between LFS and normal storage, as needed.
 
 Alternately, both normal repositories and largefile controlled
 repositories can be converted to LFS by using :hg:`convert` and the
 ``lfs.track`` config option described below.  The ``.hglfs`` file
 should then be created and added, to control subsequent LFS selection.
 The hashes are also unchanged in this case.  The LFS and non-LFS
 repositories can be distinguished because the LFS repository will
 abort any command if this extension is disabled.
 
 Committed LFS files are held locally, until the repository is pushed.
 Prior to pushing the normal repository data, the LFS files that are
 tracked by the outgoing commits are automatically uploaded to the
 configured central server.  No LFS files are transferred on
 :hg:`pull` or :hg:`clone`.  Instead, the files are downloaded on
 demand as they need to be read, if a cached copy cannot be found
 locally.  Both committing and downloading an LFS file will link the
 file to a usercache, to speed up future access.  See the `usercache`
 config setting described below.
 
 .hglfs::
 
     The extension reads its configuration from a versioned ``.hglfs``
     configuration file found in the root of the working directory. The
     ``.hglfs`` file uses the same syntax as all other Mercurial
     configuration files. It uses a single section, ``[track]``.
 
     The ``[track]`` section specifies which files are stored as LFS (or
     not). Each line is keyed by a file pattern, with a predicate value.
     The first file pattern match is used, so put more specific patterns
     first.  The available predicates are ``all()``, ``none()``, and
     ``size()``. See "hg help filesets.size" for the latter.
 
     Example versioned ``.hglfs`` file::
 
       [track]
       # No Makefile or python file, anywhere, will be LFS
       **Makefile = none()
       **.py = none()
 
       **.zip = all()
       **.exe = size(">1MB")
 
       # Catchall for everything not matched above
       ** = size(">10MB")
 
 Configs::
 
     [lfs]
     # Remote endpoint. Multiple protocols are supported:
     # - http(s)://user:[e-mail]/path
     #   git-lfs endpoint
     # - file:///tmp/path
     #   local filesystem, usually for testing
     # if unset, lfs will prompt setting this when it must use this value.
     # (default: unset)
     url = https://example.com/repo.git/info/lfs
 
     # Which files to track in LFS.  Path tests are "**.extname" for file
     # extensions, and "path:under/some/directory" for path prefix.  Both
     # are relative to the repository root.
     # File size can be tested with the "size()" fileset, and tests can be
     # joined with fileset operators.  (See "hg help filesets.operators".)
     #
     # Some examples:
     # - all()                       # everything
     # - none()                      # nothing
     # - size(">20MB")               # larger than 20MB
     # - !**.txt                     # anything not a *.txt file
     # - **.zip | **.tar.gz | **.7z  # some types of compressed files
     # - path:bin                    # files under "bin" in the project root
     # - (**.php & size(">2MB")) | (**.js & size(">5MB")) | **.tar.gz
     #     | (path:bin & !path:/bin/README) | size(">1GB")
     # (default: none())
     #
     # This is ignored if there is a tracked '.hglfs' file, and this setting
     # will eventually be deprecated and removed.
     track = size(">10M")
 
     # how many times to retry before giving up on transferring an object
     retry = 5
 
     # the local directory to store lfs files for sharing across local clones.
     # If not set, the cache is located in an OS specific cache location.
     usercache = /path/to/global/cache
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 
 from mercurial import (
     bundle2,
     changegroup,
     cmdutil,
     config,
     context,
     error,
     exchange,
     extensions,
     filelog,
     fileset,
     hg,
     localrepo,
     minifileset,
     node,
     pycompat,
     registrar,
     revlog,
     scmutil,
     templateutil,
     upgrade,
     util,
     vfs as vfsmod,
     wireproto,
 )
 
 from . import (
     blobstore,
     wrapper,
 )
 
 # 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 = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('experimental', 'lfs.user-agent',
     default=None,
 )
 configitem('experimental', 'lfs.worker-enable',
     default=False,
 )
 
 configitem('lfs', 'url',
     default=None,
 )
 configitem('lfs', 'usercache',
     default=None,
 )
 # Deprecated
 configitem('lfs', 'threshold',
     default=None,
 )
 configitem('lfs', 'track',
     default='none()',
 )
 configitem('lfs', 'retry',
     default=5,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 templatekeyword = registrar.templatekeyword()
 filesetpredicate = registrar.filesetpredicate()
 
 def featuresetup(ui, supported):
     # don't die on seeing a repo with the lfs requirement
     supported |= {'lfs'}
 
 def uisetup(ui):
     localrepo.localrepository.featuresetupfuncs.add(featuresetup)
 
 def reposetup(ui, repo):
     # Nothing to do with a remote repo
     if not repo.local():
         return
 
     repo.svfs.lfslocalblobstore = blobstore.local(repo)
     repo.svfs.lfsremoteblobstore = blobstore.remote(repo)
 
     class lfsrepo(repo.__class__):
         @localrepo.unfilteredmethod
         def commitctx(self, ctx, error=False):
             repo.svfs.options['lfstrack'] = _trackedmatcher(self)
             return super(lfsrepo, self).commitctx(ctx, error)
 
     repo.__class__ = lfsrepo
 
     if 'lfs' not in repo.requirements:
         def checkrequireslfs(ui, repo, **kwargs):
             if 'lfs' not in repo.requirements:
                 last = kwargs.get(r'node_last')
                 _bin = node.bin
                 if last:
                     s = repo.set('%n:%n', _bin(kwargs[r'node']), _bin(last))
                 else:
                     s = repo.set('%n', _bin(kwargs[r'node']))
             for ctx in s:
                 # TODO: is there a way to just walk the files in the commit?
                 if any(ctx[f].islfs() for f in ctx.files() if f in ctx):
                     repo.requirements.add('lfs')
                     repo._writerequirements()
                     repo.prepushoutgoinghooks.add('lfs', wrapper.prepush)
                     break
 
         ui.setconfig('hooks', 'commit.lfs', checkrequireslfs, 'lfs')
         ui.setconfig('hooks', 'pretxnchangegroup.lfs', checkrequireslfs, 'lfs')
     else:
         repo.prepushoutgoinghooks.add('lfs', wrapper.prepush)
 
 def _trackedmatcher(repo):
     """Return a function (path, size) -> bool indicating whether or not to
     track a given file with lfs."""
     if not repo.wvfs.exists('.hglfs'):
         # No '.hglfs' in wdir.  Fallback to config for now.
         trackspec = repo.ui.config('lfs', 'track')
 
         # deprecated config: lfs.threshold
         threshold = repo.ui.configbytes('lfs', 'threshold')
         if threshold:
             fileset.parse(trackspec)  # make sure syntax errors are confined
             trackspec = "(%s) | size('>%d')" % (trackspec, threshold)
 
         return minifileset.compile(trackspec)
 
     data = repo.wvfs.tryread('.hglfs')
     if not data:
         return lambda p, s: False
 
     # Parse errors here will abort with a message that points to the .hglfs file
     # and line number.
     cfg = config.config()
     cfg.parse('.hglfs', data)
 
     try:
         rules = [(minifileset.compile(pattern), minifileset.compile(rule))
                  for pattern, rule in cfg.items('track')]
     except error.ParseError as e:
         # The original exception gives no indicator that the error is in the
         # .hglfs file, so add that.
 
         # TODO: See if the line number of the file can be made available.
         raise error.Abort(_('parse error in .hglfs: %s') % e)
 
     def _match(path, size):
         for pat, rule in rules:
             if pat(path, size):
                 return rule(path, size)
 
         return False
 
     return _match
 
 def wrapfilelog(filelog):
     wrapfunction = extensions.wrapfunction
 
     wrapfunction(filelog, 'addrevision', wrapper.filelogaddrevision)
     wrapfunction(filelog, 'renamed', wrapper.filelogrenamed)
     wrapfunction(filelog, 'size', wrapper.filelogsize)
 
 def extsetup(ui):
     wrapfilelog(filelog.filelog)
 
     wrapfunction = extensions.wrapfunction
 
     wrapfunction(cmdutil, '_updatecatformatter', wrapper._updatecatformatter)
     wrapfunction(scmutil, 'wrapconvertsink', wrapper.convertsink)
 
     wrapfunction(upgrade, '_finishdatamigration',
                  wrapper.upgradefinishdatamigration)
 
     wrapfunction(upgrade, 'preservedrequirements',
                  wrapper.upgraderequirements)
 
     wrapfunction(upgrade, 'supporteddestrequirements',
                  wrapper.upgraderequirements)
 
     wrapfunction(changegroup,
-                 'supportedoutgoingversions',
-                 wrapper.supportedoutgoingversions)
-    wrapfunction(changegroup,
                  'allsupportedversions',
                  wrapper.allsupportedversions)
 
     wrapfunction(exchange, 'push', wrapper.push)
     wrapfunction(wireproto, '_capabilities', wrapper._capabilities)
 
     wrapfunction(context.basefilectx, 'cmp', wrapper.filectxcmp)
     wrapfunction(context.basefilectx, 'isbinary', wrapper.filectxisbinary)
     context.basefilectx.islfs = wrapper.filectxislfs
 
     revlog.addflagprocessor(
         revlog.REVIDX_EXTSTORED,
         (
             wrapper.readfromstore,
             wrapper.writetostore,
             wrapper.bypasscheckhash,
         ),
     )
 
     wrapfunction(hg, 'clone', wrapper.hgclone)
     wrapfunction(hg, 'postshare', wrapper.hgpostshare)
 
     scmutil.fileprefetchhooks.add('lfs', wrapper._prefetchfiles)
 
     # Make bundle choose changegroup3 instead of changegroup2. This affects
     # "hg bundle" command. Note: it does not cover all bundle formats like
     # "packed1". Using "packed1" with lfs will likely cause trouble.
     names = [k for k, v in exchange._bundlespeccgversions.items() if v == '02']
     for k in names:
         exchange._bundlespeccgversions[k] = '03'
 
     # bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
     # options and blob stores are passed from othervfs to the new readonlyvfs.
     wrapfunction(vfsmod.readonlyvfs, '__init__', wrapper.vfsinit)
 
     # when writing a bundle via "hg bundle" command, upload related LFS blobs
     wrapfunction(bundle2, 'writenewbundle', wrapper.writenewbundle)
 
 @filesetpredicate('lfs()', callstatus=True)
 def lfsfileset(mctx, x):
     """File that uses LFS storage."""
     # i18n: "lfs" is a keyword
     fileset.getargs(x, 0, 0, _("lfs takes no arguments"))
     return [f for f in mctx.subset
             if wrapper.pointerfromctx(mctx.ctx, f, removed=True) is not None]
 
 @templatekeyword('lfs_files', requires={'ctx'})
 def lfsfiles(context, mapping):
     """List of strings. All files modified, added, or removed by this
     changeset."""
     ctx = context.resource(mapping, 'ctx')
 
     pointers = wrapper.pointersfromctx(ctx, removed=True) # {path: pointer}
     files = sorted(pointers.keys())
 
     def pointer(v):
         # In the file spec, version is first and the other keys are sorted.
         sortkeyfunc = lambda x: (x[0] != 'version', x)
         items = sorted(pointers[v].iteritems(), key=sortkeyfunc)
         return util.sortdict(items)
 
     makemap = lambda v: {
         'file': v,
         'lfsoid': pointers[v].oid() if pointers[v] else None,
         'lfspointer': templateutil.hybriddict(pointer(v)),
     }
 
     # TODO: make the separator ', '?
     f = templateutil._showcompatlist(context, mapping, 'lfs_file', files)
     return templateutil.hybrid(f, files, makemap, pycompat.identity)
 
 @command('debuglfsupload',
          [('r', 'rev', [], _('upload large files introduced by REV'))])
 def debuglfsupload(ui, repo, **opts):
     """upload lfs blobs added by the working copy parent or given revisions"""
     revs = opts.get(r'rev', [])
     pointers = wrapper.extractpointers(repo, scmutil.revrange(repo, revs))
     wrapper.uploadblobs(repo, pointers)

hgext/lfs/wrapper.py

@@ -1,395 +1,387
 # 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 import (
     error,
     filelog,
     revlog,
     util,
 )
 
 from mercurial.utils import (
     stringutil,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
-def supportedoutgoingversions(orig, repo):
-    versions = orig(repo)
-    if 'lfs' in repo.requirements:
-        versions.discard('01')
-        versions.discard('02')
-    versions.add('03')
-    return versions
-
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add('03')
     return versions
 
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     # XXX: change to 'lfs=serve' when separate git server isn't required?
     caps.append('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('x-hg-'):
             name = k[len('x-hg-'):]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith('\1\n'):
         text = filelog.packmeta(hgmeta, text)
 
     return (text, True)
 
 def writetostore(self, text):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = filelog.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 = 'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size='%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['x-is-binary'] = '0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         for k, v in hgmeta.iteritems():
             metadata['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)
 
 def filelogaddrevision(orig, self, text, transaction, link, p1, p2,
                        cachedelta=None, node=None,
                        flags=revlog.REVIDX_DEFAULT_FLAGS, **kwds):
     textlen = len(text)
     # exclude hg rename meta from file size
     meta, offset = filelog.parsemeta(text)
     if offset:
         textlen -= offset
 
     lfstrack = self.opener.options['lfstrack']
 
     if lfstrack(self.filename, textlen):
         flags |= revlog.REVIDX_EXTSTORED
 
     return orig(self, text, transaction, link, p1, p2, cachedelta=cachedelta,
                 node=node, flags=flags, **kwds)
 
 def filelogrenamed(orig, self, node):
     if _islfs(self, node):
         rawtext = self.revision(node, raw=True)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if 'x-hg-copy' in metadata and 'x-hg-copyrev' in metadata:
             return metadata['x-hg-copy'], bin(metadata['x-hg-copyrev'])
         else:
             return False
     return orig(self, node)
 
 def filelogsize(orig, self, rev):
     if _islfs(self, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self.revision(rev, raw=True)
         metadata = pointer.deserialize(rawtext)
         return int(metadata['size'])
     return orig(self, rev)
 
 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)
 
 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('x-is-binary', 1)))
     return orig(self)
 
 def filectxislfs(self):
     return _islfs(self.filelog(), self.filenode())
 
 def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
     orig(fm, ctx, matcher, path, decode)
     fm.data(rawdata=ctx[path].rawdata())
 
 def convertsink(orig, sink):
     sink = orig(sink)
     if sink.repotype == '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 '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('lfs')
                         self.repo._writerequirements()
 
                         # Permanently enable lfs locally
                         self.repo.vfs.append(
                             'hgrc', util.tonativeeol('\n[extensions]\nlfs=\n'))
 
                 return node
 
         sink.__class__ = lfssink
 
     return sink
 
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith('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 ['lfslocalblobstore', 'lfsremoteblobstore']:
         if util.safehasattr(othervfs, name):
             setattr(self, name, getattr(othervfs, name))
 
 def hgclone(orig, ui, opts, *args, **kwargs):
     result = orig(ui, opts, *args, **kwargs)
 
     if result is not None:
         sourcerepo, destrepo = result
         repo = destrepo.local()
 
         # When cloning to a remote repo (like through SSH), no repo is available
         # from the peer.  Therefore the hgrc can't be updated.
         if not repo:
             return result
 
         # If lfs is required for this repo, permanently enable it locally
         if 'lfs' in repo.requirements:
             repo.vfs.append('hgrc',
                             util.tonativeeol('\n[extensions]\nlfs=\n'))
 
     return result
 
 def hgpostshare(orig, sourcerepo, destrepo, bookmarks=True, defaultpath=None):
     orig(sourcerepo, destrepo, bookmarks, defaultpath)
 
     # If lfs is required for this repo, permanently enable it locally
     if 'lfs' in destrepo.requirements:
         destrepo.vfs.append('hgrc', util.tonativeeol('\n[extensions]\nlfs=\n'))
 
 def _prefetchfiles(repo, ctx, files):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     pointers = []
     localstore = repo.svfs.lfslocalblobstore
 
     for f in files:
         p = pointerfromctx(ctx, f)
         if p and not localstore.has(p.oid()):
             p.filename = f
             pointers.append(p)
 
     if pointers:
         repo.svfs.lfsremoteblobstore.readbatch(pointers, localstore)
 
 def _canskipupload(repo):
     # 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):
     # 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)
 
 def push(orig, repo, remote, *args, **kwargs):
     """bail on push if the extension isn't enabled on remote when needed"""
     if '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('lfs'):
             # This is a copy of the message in exchange.push() when requirements
             # are missing between local repos.
             m = _("required features are not supported in the destination: %s")
             raise error.Abort(m % 'lfs',
                               hint=_('enable the lfs extension on the server'))
     return orig(repo, remote, *args, **kwargs)
 
 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('lfs: computing set of blobs to upload\n')
     pointers = {}
     for r in revs:
         ctx = repo[r]
         for p in pointersfromctx(ctx).values():
             pointers[p.oid()] = p
     return sorted(pointers.values())
 
 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(), fctx.filenode()):
         return None
     try:
         p = pointer.deserialize(fctx.rawdata())
         if ctx == _ctx:
             return p
         return {}
     except pointer.InvalidPointer as ex:
         raise error.Abort(_('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 = {}
     for f in ctx.files():
         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)
 
 def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
     orig(ui, srcrepo, dstrepo, requirements)
 
     srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
     dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs
 
     for dirpath, dirs, files in srclfsvfs.walk():
         for oid in files:
             ui.write(_('copying lfs blob %s\n') % oid)
             lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if 'lfs' in repo.requirements:
         reqs.add('lfs')
     return reqs

mercurial/changegroup.py

@@ -1,1014 +1,1022
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 Matt Mackall <[e-mail]>
 #
 # 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 os
 import struct
 import tempfile
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
     short,
 )
 
 from . import (
     dagutil,
     error,
     mdiff,
     phases,
     pycompat,
     util,
 )
 
 from .utils import (
     stringutil,
 )
 
 _CHANGEGROUPV1_DELTA_HEADER = "20s20s20s20s"
 _CHANGEGROUPV2_DELTA_HEADER = "20s20s20s20s20s"
 _CHANGEGROUPV3_DELTA_HEADER = ">20s20s20s20s20sH"
 
+LFS_REQUIREMENT = 'lfs'
+
 # When narrowing is finalized and no longer subject to format changes,
 # we should move this to just "narrow" or similar.
 NARROW_REQUIREMENT = 'narrowhg-experimental'
 
 readexactly = util.readexactly
 
 def getchunk(stream):
     """return the next chunk from stream as a string"""
     d = readexactly(stream, 4)
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         if l:
             raise error.Abort(_("invalid chunk length %d") % l)
         return ""
     return readexactly(stream, l - 4)
 
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 def writechunks(ui, chunks, filename, vfs=None):
     """Write chunks to a file and return its filename.
 
     The stream is assumed to be a bundle file.
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     """
     fh = None
     cleanup = None
     try:
         if filename:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 # Increase default buffer size because default is usually
                 # small (4k is common on Linux).
                 fh = open(filename, "wb", 131072)
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, r"wb")
         cleanup = filename
         for c in chunks:
             fh.write(c)
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 class cg1unpacker(object):
     """Unpacker for cg1 changegroup streams.
 
     A changegroup unpacker handles the framing of the revision data in
     the wire format. Most consumers will want to use the apply()
     method to add the changes from the changegroup to a repository.
 
     If you're forwarding a changegroup unmodified to another consumer,
     use getchunks(), which returns an iterator of changegroup
     chunks. This is mostly useful for cases where you need to know the
     data stream has ended by observing the end of the changegroup.
 
     deltachunk() is useful only if you're applying delta data. Most
     consumers should prefer apply() instead.
 
     A few other public methods exist. Those are used only for
     bundlerepo and some debug commands - their use is discouraged.
     """
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '01'
     _grouplistcount = 1 # One list of files after the manifests
 
     def __init__(self, fh, alg, extras=None):
         if alg is None:
             alg = 'UN'
         if alg not in util.compengines.supportedbundletypes:
             raise error.Abort(_('unknown stream compression type: %s')
                              % alg)
         if alg == 'BZ':
             alg = '_truncatedBZ'
 
         compengine = util.compengines.forbundletype(alg)
         self._stream = compengine.decompressorreader(fh)
         self._type = alg
         self.extras = extras or {}
         self.callback = None
 
     # These methods (compressed, read, seek, tell) all appear to only
     # be used by bundlerepo, but it's a little hard to tell.
     def compressed(self):
         return self._type is not None and self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
     def close(self):
         return self._stream.close()
 
     def _chunklength(self):
         d = readexactly(self._stream, 4)
         l = struct.unpack(">l", d)[0]
         if l <= 4:
             if l:
                 raise error.Abort(_("invalid chunk length %d") % l)
             return 0
         if self.callback:
             self.callback()
         return l - 4
 
     def changelogheader(self):
         """v10 does not have a changelog header chunk"""
         return {}
 
     def manifestheader(self):
         """v10 does not have a manifest header chunk"""
         return {}
 
     def filelogheader(self):
         """return the header of the filelogs chunk, v10 only has the filename"""
         l = self._chunklength()
         if not l:
             return {}
         fname = readexactly(self._stream, l)
         return {'filename': fname}
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
     def deltachunk(self, prevnode):
         l = self._chunklength()
         if not l:
             return {}
         headerdata = readexactly(self._stream, self.deltaheadersize)
         header = struct.unpack(self.deltaheader, headerdata)
         delta = readexactly(self._stream, l - self.deltaheadersize)
         node, p1, p2, deltabase, cs, flags = self._deltaheader(header, prevnode)
         return (node, p1, p2, cs, deltabase, delta, flags)
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # For changegroup 1 and 2, we expect 3 parts: changelog, manifestlog,
         # and a list of filelogs. For changegroup 3, we expect 4 parts:
         # changelog, manifestlog, a list of tree manifestlogs, and a list of
         # filelogs.
         #
         # Changelog and manifestlog parts are terminated with empty chunks. The
         # tree and file parts are a list of entry sections. Each entry section
         # is a series of chunks terminating in an empty chunk. The list of these
         # entry sections is terminated in yet another empty chunk, so we know
         # we've reached the end of the tree/file list when we reach an empty
         # chunk that was proceeded by no non-empty chunks.
 
         parts = 0
         while parts < 2 + self._grouplistcount:
             noentries = True
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     # The first two empty chunks represent the end of the
                     # changelog and the manifestlog portions. The remaining
                     # empty chunks represent either A) the end of individual
                     # tree or file entries in the file list, or B) the end of
                     # the entire list. It's the end of the entire list if there
                     # were no entries (i.e. noentries is True).
                     if parts < 2:
                         parts += 1
                     elif noentries:
                         parts += 1
                     break
                 noentries = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
     def _unpackmanifests(self, repo, revmap, trp, prog, numchanges):
         # We know that we'll never have more manifests than we had
         # changesets.
         self.callback = prog(_('manifests'), numchanges)
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         self.manifestheader()
         deltas = self.deltaiter()
         repo.manifestlog._revlog.addgroup(deltas, revmap, trp)
         repo.ui.progress(_('manifests'), None)
         self.callback = None
 
     def apply(self, repo, tr, srctype, url, targetphase=phases.draft,
               expectedtotal=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         repo = repo.unfiltered()
         def csmap(x):
             repo.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         changesets = files = revisions = 0
 
         try:
             # The transaction may already carry source information. In this
             # case we use the top level data. We overwrite the argument
             # because we need to use the top level value (if they exist)
             # in this function.
             srctype = tr.hookargs.setdefault('source', srctype)
             url = tr.hookargs.setdefault('url', url)
             repo.hook('prechangegroup',
                       throw=True, **pycompat.strkwargs(tr.hookargs))
 
             # write changelog data to temp files so concurrent readers
             # will not see an inconsistent view
             cl = repo.changelog
             cl.delayupdate(tr)
             oldheads = set(cl.heads())
 
             trp = weakref.proxy(tr)
             # pull off the changeset group
             repo.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 def __init__(self, step, total):
                     self._step = step
                     self._total = total
                     self._count = 1
                 def __call__(self):
                     repo.ui.progress(self._step, self._count, unit=_('chunks'),
                                      total=self._total)
                     self._count += 1
             self.callback = prog(_('changesets'), expectedtotal)
 
             efiles = set()
             def onchangelog(cl, node):
                 efiles.update(cl.readfiles(node))
 
             self.changelogheader()
             deltas = self.deltaiter()
             cgnodes = cl.addgroup(deltas, csmap, trp, addrevisioncb=onchangelog)
             efiles = len(efiles)
 
             if not cgnodes:
                 repo.ui.develwarn('applied empty changegroup',
                                   config='warn-empty-changegroup')
             clend = len(cl)
             changesets = clend - clstart
             repo.ui.progress(_('changesets'), None)
             self.callback = None
 
             # pull off the manifest group
             repo.ui.status(_("adding manifests\n"))
             self._unpackmanifests(repo, revmap, trp, prog, changesets)
 
             needfiles = {}
             if repo.ui.configbool('server', 'validate'):
                 cl = repo.changelog
                 ml = repo.manifestlog
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfnode = cl.changelogrevision(cset).manifest
                     mfest = ml[mfnode].readdelta()
                     # store file cgnodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             repo.ui.status(_("adding file changes\n"))
             newrevs, newfiles = _addchangegroupfiles(
                 repo, self, revmap, trp, efiles, needfiles)
             revisions += newrevs
             files += newfiles
 
             deltaheads = 0
             if oldheads:
                 heads = cl.heads()
                 deltaheads = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and repo[h].closesbranch():
                         deltaheads -= 1
             htext = ""
             if deltaheads:
                 htext = _(" (%+d heads)") % deltaheads
 
             repo.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
             repo.invalidatevolatilesets()
 
             if changesets > 0:
                 if 'node' not in tr.hookargs:
                     tr.hookargs['node'] = hex(cl.node(clstart))
                     tr.hookargs['node_last'] = hex(cl.node(clend - 1))
                     hookargs = dict(tr.hookargs)
                 else:
                     hookargs = dict(tr.hookargs)
                     hookargs['node'] = hex(cl.node(clstart))
                     hookargs['node_last'] = hex(cl.node(clend - 1))
                 repo.hook('pretxnchangegroup',
                           throw=True, **pycompat.strkwargs(hookargs))
 
             added = [cl.node(r) for r in xrange(clstart, clend)]
             phaseall = None
             if srctype in ('push', 'serve'):
                 # Old servers can not push the boundary themselves.
                 # New servers won't push the boundary if changeset already
                 # exists locally as secret
                 #
                 # We should not use added here but the list of all change in
                 # the bundle
                 if repo.publishing():
                     targetphase = phaseall = phases.public
                 else:
                     # closer target phase computation
 
                     # Those changesets have been pushed from the
                     # outside, their phases are going to be pushed
                     # alongside. Therefor `targetphase` is
                     # ignored.
                     targetphase = phaseall = phases.draft
             if added:
                 phases.registernew(repo, tr, targetphase, added)
             if phaseall is not None:
                 phases.advanceboundary(repo, tr, phaseall, cgnodes)
 
             if changesets > 0:
 
                 def runhooks():
                     # These hooks run when the lock releases, not when the
                     # transaction closes. So it's possible for the changelog
                     # to have changed since we last saw it.
                     if clstart >= len(repo):
                         return
 
                     repo.hook("changegroup", **pycompat.strkwargs(hookargs))
 
                     for n in added:
                         args = hookargs.copy()
                         args['node'] = hex(n)
                         del args['node_last']
                         repo.hook("incoming", **pycompat.strkwargs(args))
 
                     newheads = [h for h in repo.heads()
                                 if h not in oldheads]
                     repo.ui.log("incoming",
                                 "%d incoming changes - new heads: %s\n",
                                 len(added),
                                 ', '.join([hex(c[:6]) for c in newheads]))
 
                 tr.addpostclose('changegroup-runhooks-%020i' % clstart,
                                 lambda tr: repo._afterlock(runhooks))
         finally:
             repo.ui.flush()
         # never return 0 here:
         if deltaheads < 0:
             ret = deltaheads - 1
         else:
             ret = deltaheads + 1
         return ret
 
     def deltaiter(self):
         """
         returns an iterator of the deltas in this changegroup
 
         Useful for passing to the underlying storage system to be stored.
         """
         chain = None
         for chunkdata in iter(lambda: self.deltachunk(chain), {}):
             # Chunkdata: (node, p1, p2, cs, deltabase, delta, flags)
             yield chunkdata
             chain = chunkdata[0]
 
 class cg2unpacker(cg1unpacker):
     """Unpacker for cg2 streams.
 
     cg2 streams add support for generaldelta, so the delta header
     format is slightly different. All other features about the data
     remain the same.
     """
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '02'
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs = headertuple
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
 class cg3unpacker(cg2unpacker):
     """Unpacker for cg3 streams.
 
     cg3 streams add support for exchanging treemanifests and revlog
     flags. It adds the revlog flags to the delta header and an empty chunk
     separating manifests and files.
     """
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '03'
     _grouplistcount = 2 # One list of manifests and one list of files
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs, flags = headertuple
         return node, p1, p2, deltabase, cs, flags
 
     def _unpackmanifests(self, repo, revmap, trp, prog, numchanges):
         super(cg3unpacker, self)._unpackmanifests(repo, revmap, trp, prog,
                                                   numchanges)
         for chunkdata in iter(self.filelogheader, {}):
             # If we get here, there are directory manifests in the changegroup
             d = chunkdata["filename"]
             repo.ui.debug("adding %s revisions\n" % d)
             dirlog = repo.manifestlog._revlog.dirlog(d)
             deltas = self.deltaiter()
             if not dirlog.addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received dir revlog group is empty"))
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 class cg1packer(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     version = '01'
     def __init__(self, repo, bundlecaps=None):
         """Given a source repo, construct a bundler.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle. While bundlecaps is
         unused in core Mercurial, extensions rely on this feature to communicate
         capabilities to customize the changegroup packer.
         """
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         # experimental config: bundle.reorder
         reorder = repo.ui.config('bundle', 'reorder')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = stringutil.parsebool(reorder)
         self._repo = repo
         self._reorder = reorder
         self._progress = repo.ui.progress
         if self._repo.ui.verbose and not self._repo.ui.debugflag:
             self._verbosenote = self._repo.ui.note
         else:
             self._verbosenote = lambda s: None
 
     def close(self):
         return closechunk()
 
     def fileheader(self, fname):
         return chunkheader(len(fname)) + fname
 
     # Extracted both for clarity and for overriding in extensions.
     def _sortgroup(self, revlog, nodelist, lookup):
         """Sort nodes for change group and turn them into revnums."""
         # for generaldelta revlogs, we linearize the revs; this will both be
         # much quicker and generate a much smaller bundle
         if (revlog._generaldelta and self._reorder is None) or self._reorder:
             dag = dagutil.revlogdag(revlog)
             return dag.linearize(set(revlog.rev(n) for n in nodelist))
         else:
             return sorted([revlog.rev(n) for n in nodelist])
 
     def group(self, nodelist, revlog, lookup, units=None):
         """Calculate a delta group, yielding a sequence of changegroup chunks
         (strings).
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. The first delta is
         first parent(nodelist[0]) -> nodelist[0], the receiver is
         guaranteed to have this parent as it has all history before
         these changesets. In the case firstparent is nullrev the
         changegroup starts with a full revision.
 
         If units is not None, progress detail will be generated, units specifies
         the type of revlog that is touched (changelog, manifest, etc.).
         """
         # if we don't have any revisions touched by these changesets, bail
         if len(nodelist) == 0:
             yield self.close()
             return
 
         revs = self._sortgroup(revlog, nodelist, lookup)
 
         # add the parent of the first rev
         p = revlog.parentrevs(revs[0])[0]
         revs.insert(0, p)
 
         # build deltas
         total = len(revs) - 1
         msgbundling = _('bundling')
         for r in xrange(len(revs) - 1):
             if units is not None:
                 self._progress(msgbundling, r + 1, unit=units, total=total)
             prev, curr = revs[r], revs[r + 1]
             linknode = lookup(revlog.node(curr))
             for c in self.revchunk(revlog, curr, prev, linknode):
                 yield c
 
         if units is not None:
             self._progress(msgbundling, None)
         yield self.close()
 
     # filter any nodes that claim to be part of the known set
     def prune(self, revlog, missing, commonrevs):
         rr, rl = revlog.rev, revlog.linkrev
         return [n for n in missing if rl(rr(n)) not in commonrevs]
 
     def _packmanifests(self, dir, mfnodes, lookuplinknode):
         """Pack flat manifests into a changegroup stream."""
         assert not dir
         for chunk in self.group(mfnodes, self._repo.manifestlog._revlog,
                                 lookuplinknode, units=_('manifests')):
             yield chunk
 
     def _manifestsdone(self):
         return ''
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
         '''yield a sequence of changegroup chunks (strings)'''
         repo = self._repo
         cl = repo.changelog
 
         clrevorder = {}
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
 
         # Callback for the changelog, used to collect changed files and manifest
         # nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.read(x)
             clrevorder[x] = len(clrevorder)
             n = c[0]
             # record the first changeset introducing this manifest version
             mfs.setdefault(n, x)
             # Record a complete list of potentially-changed files in
             # this manifest.
             changedfiles.update(c[3])
             return x
 
         self._verbosenote(_('uncompressed size of bundle content:\n'))
         size = 0
         for chunk in self.group(clnodes, cl, lookupcl, units=_('changesets')):
             size += len(chunk)
             yield chunk
         self._verbosenote(_('%8.i (changelog)\n') % size)
 
         # We need to make sure that the linkrev in the changegroup refers to
         # the first changeset that introduced the manifest or file revision.
         # The fastpath is usually safer than the slowpath, because the filelogs
         # are walked in revlog order.
         #
         # When taking the slowpath with reorder=None and the manifest revlog
         # uses generaldelta, the manifest may be walked in the "wrong" order.
         # Without 'clrevorder', we would get an incorrect linkrev (see fix in
         # cc0ff93d0c0c).
         #
         # When taking the fastpath, we are only vulnerable to reordering
         # of the changelog itself. The changelog never uses generaldelta, so
         # it is only reordered when reorder=True. To handle this case, we
         # simply take the slowpath, which already has the 'clrevorder' logic.
         # This was also fixed in cc0ff93d0c0c.
         fastpathlinkrev = fastpathlinkrev and not self._reorder
         # Treemanifests don't work correctly with fastpathlinkrev
         # either, because we don't discover which directory nodes to
         # send along with files. This could probably be fixed.
         fastpathlinkrev = fastpathlinkrev and (
             'treemanifest' not in repo.requirements)
 
         for chunk in self.generatemanifests(commonrevs, clrevorder,
                 fastpathlinkrev, mfs, fnodes, source):
             yield chunk
         mfs.clear()
         clrevs = set(cl.rev(x) for x in clnodes)
 
         if not fastpathlinkrev:
             def linknodes(unused, fname):
                 return fnodes.get(fname, {})
         else:
             cln = cl.node
             def linknodes(filerevlog, fname):
                 llr = filerevlog.linkrev
                 fln = filerevlog.node
                 revs = ((r, llr(r)) for r in filerevlog)
                 return dict((fln(r), cln(lr)) for r, lr in revs if lr in clrevs)
 
         for chunk in self.generatefiles(changedfiles, linknodes, commonrevs,
                                         source):
             yield chunk
 
         yield self.close()
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def generatemanifests(self, commonrevs, clrevorder, fastpathlinkrev, mfs,
                           fnodes, source):
         """Returns an iterator of changegroup chunks containing manifests.
 
         `source` is unused here, but is used by extensions like remotefilelog to
         change what is sent based in pulls vs pushes, etc.
         """
         repo = self._repo
         mfl = repo.manifestlog
         dirlog = mfl._revlog.dirlog
         tmfnodes = {'': mfs}
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def makelookupmflinknode(dir, nodes):
             if fastpathlinkrev:
                 assert not dir
                 return mfs.__getitem__
 
             def lookupmflinknode(x):
                 """Callback for looking up the linknode for manifests.
 
                 Returns the linkrev node for the specified manifest.
 
                 SIDE EFFECT:
 
                 1) fclnodes gets populated with the list of relevant
                    file nodes if we're not using fastpathlinkrev
                 2) When treemanifests are in use, collects treemanifest nodes
                    to send
 
                 Note that this means manifests must be completely sent to
                 the client before you can trust the list of files and
                 treemanifests to send.
                 """
                 clnode = nodes[x]
                 mdata = mfl.get(dir, x).readfast(shallow=True)
                 for p, n, fl in mdata.iterentries():
                     if fl == 't': # subdirectory manifest
                         subdir = dir + p + '/'
                         tmfclnodes = tmfnodes.setdefault(subdir, {})
                         tmfclnode = tmfclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[tmfclnode]:
                             tmfclnodes[n] = clnode
                     else:
                         f = dir + p
                         fclnodes = fnodes.setdefault(f, {})
                         fclnode = fclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[fclnode]:
                             fclnodes[n] = clnode
                 return clnode
             return lookupmflinknode
 
         size = 0
         while tmfnodes:
             dir, nodes = tmfnodes.popitem()
             prunednodes = self.prune(dirlog(dir), nodes, commonrevs)
             if not dir or prunednodes:
                 for x in self._packmanifests(dir, prunednodes,
                                              makelookupmflinknode(dir, nodes)):
                     size += len(x)
                     yield x
         self._verbosenote(_('%8.i (manifests)\n') % size)
         yield self._manifestsdone()
 
     # The 'source' parameter is useful for extensions
     def generatefiles(self, changedfiles, linknodes, commonrevs, source):
         repo = self._repo
         progress = self._progress
         msgbundling = _('bundling')
 
         total = len(changedfiles)
         # for progress output
         msgfiles = _('files')
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise error.Abort(_("empty or missing revlog for %s") % fname)
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             filenodes = self.prune(filerevlog, linkrevnodes, commonrevs)
             if filenodes:
                 progress(msgbundling, i + 1, item=fname, unit=msgfiles,
                          total=total)
                 h = self.fileheader(fname)
                 size = len(h)
                 yield h
                 for chunk in self.group(filenodes, filerevlog, lookupfilelog):
                     size += len(chunk)
                     yield chunk
                 self._verbosenote(_('%8.i  %s\n') % (size, fname))
         progress(msgbundling, None)
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         if not revlog.candelta(prev, rev):
             raise error.ProgrammingError('cg1 should not be used in this case')
         return prev
 
     def revchunk(self, revlog, rev, prev, linknode):
         node = revlog.node(rev)
         p1, p2 = revlog.parentrevs(rev)
         base = self.deltaparent(revlog, rev, p1, p2, prev)
 
         prefix = ''
         if revlog.iscensored(base) or revlog.iscensored(rev):
             try:
                 delta = revlog.revision(node, raw=True)
             except error.CensoredNodeError as e:
                 delta = e.tombstone
             if base == nullrev:
                 prefix = mdiff.trivialdiffheader(len(delta))
             else:
                 baselen = revlog.rawsize(base)
                 prefix = mdiff.replacediffheader(baselen, len(delta))
         elif base == nullrev:
             delta = revlog.revision(node, raw=True)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             delta = revlog.revdiff(base, rev)
         p1n, p2n = revlog.parents(node)
         basenode = revlog.node(base)
         flags = revlog.flags(rev)
         meta = self.builddeltaheader(node, p1n, p2n, basenode, linknode, flags)
         meta += prefix
         l = len(meta) + len(delta)
         yield chunkheader(l)
         yield meta
         yield delta
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         # do nothing with basenode, it is implicitly the previous one in HG10
         # do nothing with flags, it is implicitly 0 for cg1 and cg2
         return struct.pack(self.deltaheader, node, p1n, p2n, linknode)
 
 class cg2packer(cg1packer):
     version = '02'
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
 
     def __init__(self, repo, bundlecaps=None):
         super(cg2packer, self).__init__(repo, bundlecaps)
         if self._reorder is None:
             # Since generaldelta is directly supported by cg2, reordering
             # generally doesn't help, so we disable it by default (treating
             # bundle.reorder=auto just like bundle.reorder=False).
             self._reorder = False
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         dp = revlog.deltaparent(rev)
         if dp == nullrev and revlog.storedeltachains:
             # Avoid sending full revisions when delta parent is null. Pick prev
             # in that case. It's tempting to pick p1 in this case, as p1 will
             # be smaller in the common case. However, computing a delta against
             # p1 may require resolving the raw text of p1, which could be
             # expensive. The revlog caches should have prev cached, meaning
             # less CPU for changegroup generation. There is likely room to add
             # a flag and/or config option to control this behavior.
             base = prev
         elif dp == nullrev:
             # revlog is configured to use full snapshot for a reason,
             # stick to full snapshot.
             base = nullrev
         elif dp not in (p1, p2, prev):
             # Pick prev when we can't be sure remote has the base revision.
             return prev
         else:
             base = dp
         if base != nullrev and not revlog.candelta(base, rev):
             base = nullrev
         return base
 
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         # Do nothing with flags, it is implicitly 0 in cg1 and cg2
         return struct.pack(self.deltaheader, node, p1n, p2n, basenode, linknode)
 
 class cg3packer(cg2packer):
     version = '03'
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
 
     def _packmanifests(self, dir, mfnodes, lookuplinknode):
         if dir:
             yield self.fileheader(dir)
 
         dirlog = self._repo.manifestlog._revlog.dirlog(dir)
         for chunk in self.group(mfnodes, dirlog, lookuplinknode,
                                 units=_('manifests')):
             yield chunk
 
     def _manifestsdone(self):
         return self.close()
 
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         return struct.pack(
             self.deltaheader, node, p1n, p2n, basenode, linknode, flags)
 
 _packermap = {'01': (cg1packer, cg1unpacker),
              # cg2 adds support for exchanging generaldelta
              '02': (cg2packer, cg2unpacker),
              # cg3 adds support for exchanging revlog flags and treemanifests
              '03': (cg3packer, cg3unpacker),
 }
 
 def allsupportedversions(repo):
     versions = set(_packermap.keys())
     if not (repo.ui.configbool('experimental', 'changegroup3') or
             repo.ui.configbool('experimental', 'treemanifest') or
             'treemanifest' in repo.requirements):
         versions.discard('03')
     return versions
 
 # Changegroup versions that can be applied to the repo
 def supportedincomingversions(repo):
     return allsupportedversions(repo)
 
 # Changegroup versions that can be created from the repo
 def supportedoutgoingversions(repo):
     versions = allsupportedversions(repo)
     if 'treemanifest' in repo.requirements:
         # Versions 01 and 02 support only flat manifests and it's just too
         # expensive to convert between the flat manifest and tree manifest on
         # the fly. Since tree manifests are hashed differently, all of history
         # would have to be converted. Instead, we simply don't even pretend to
         # support versions 01 and 02.
         versions.discard('01')
         versions.discard('02')
     if NARROW_REQUIREMENT in repo.requirements:
         # Versions 01 and 02 don't support revlog flags, and we need to
         # support that for stripping and unbundling to work.
         versions.discard('01')
         versions.discard('02')
+    if LFS_REQUIREMENT in repo.requirements:
+        # Versions 01 and 02 don't support revlog flags, and we need to
+        # mark LFS entries with REVIDX_EXTSTORED.
+        versions.discard('01')
+        versions.discard('02')
+
     return versions
 
 def localversion(repo):
     # Finds the best version to use for bundles that are meant to be used
     # locally, such as those from strip and shelve, and temporary bundles.
     return max(supportedoutgoingversions(repo))
 
 def safeversion(repo):
     # Finds the smallest version that it's safe to assume clients of the repo
     # will support. For example, all hg versions that support generaldelta also
     # support changegroup 02.
     versions = supportedoutgoingversions(repo)
     if 'generaldelta' in repo.requirements:
         versions.discard('01')
     assert versions
     return min(versions)
 
 def getbundler(version, repo, bundlecaps=None):
     assert version in supportedoutgoingversions(repo)
     return _packermap[version][0](repo, bundlecaps)
 
 def getunbundler(version, fh, alg, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def makechangegroup(repo, outgoing, version, source, fastpath=False,
                     bundlecaps=None):
     cgstream = makestream(repo, outgoing, version, source,
                           fastpath=fastpath, bundlecaps=bundlecaps)
     return getunbundler(version, util.chunkbuffer(cgstream), None,
                         {'clcount': len(outgoing.missing) })
 
 def makestream(repo, outgoing, version, source, fastpath=False,
                bundlecaps=None):
     bundler = getbundler(version, repo, bundlecaps=bundlecaps)
 
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
     return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
 
 def _addchangegroupfiles(repo, source, revmap, trp, expectedfiles, needfiles):
     revisions = 0
     files = 0
     for chunkdata in iter(source.filelogheader, {}):
         files += 1
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         repo.ui.progress(_('files'), files, unit=_('files'),
                          total=expectedfiles)
         fl = repo.file(f)
         o = len(fl)
         try:
             deltas = source.deltaiter()
             if not fl.addgroup(deltas, revmap, trp):
                 raise error.Abort(_("received file revlog group is empty"))
         except error.CensoredBaseError as e:
             raise error.Abort(_("received delta base is censored: %s") % e)
         revisions += len(fl) - o
         if f in needfiles:
             needs = needfiles[f]
             for new in xrange(o, len(fl)):
                 n = fl.node(new)
                 if n in needs:
                     needs.remove(n)
                 else:
                     raise error.Abort(
                         _("received spurious file revlog entry"))
             if not needs:
                 del needfiles[f]
     repo.ui.progress(_('files'), None)
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise error.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files