lfs: allow to run 'debugupgraderepo' on repo with largefiles

The extensions wrap the necessary function to ensure the 'lfs' requirements
won't be dropped.

It is now possible to run `hg debugupgraderepo` on a repository with lfs.

hgext/lfs/__init__.py

@@ -1,191 +1,198
 # 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)
 
 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/lfs
 
     # size of a file to make it use LFS
     threshold = 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,
     context,
     exchange,
     extensions,
     filelog,
     hg,
     localrepo,
     registrar,
     revlog,
     scmutil,
+    upgrade,
     vfs as vfsmod,
 )
 
 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('lfs', 'url',
     default=configitem.dynamicdefault,
 )
 configitem('lfs', 'usercache',
     default=None,
 )
 configitem('lfs', 'threshold',
     default=None,
 )
 configitem('lfs', 'retry',
     default=5,
 )
 # Deprecated
 configitem('lfs', 'remotestore',
     default=None,
 )
 # Deprecated
 configitem('lfs', 'dummy',
     default=None,
 )
 # Deprecated
 configitem('lfs', 'git-lfs',
     default=None,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 templatekeyword = registrar.templatekeyword()
 
 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
 
     threshold = repo.ui.configbytes('lfs', 'threshold')
 
     repo.svfs.options['lfsthreshold'] = threshold
     repo.svfs.lfslocalblobstore = blobstore.local(repo)
     repo.svfs.lfsremoteblobstore = blobstore.remote(repo)
 
     # Push hook
     repo.prepushoutgoinghooks.add('lfs', wrapper.prepush)
 
     if 'lfs' not in repo.requirements:
         def checkrequireslfs(ui, repo, **kwargs):
             if 'lfs' not in repo.requirements:
                 ctx = repo[kwargs['node']]
                 # TODO: is there a way to just walk the files in the commit?
                 if any(ctx[f].islfs() for f in ctx.files()):
                     repo.requirements.add('lfs')
                     repo._writerequirements()
 
         ui.setconfig('hooks', 'commit.lfs', checkrequireslfs, 'lfs')
 
 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(scmutil, 'wrapconvertsink', wrapper.convertsink)
 
+    wrapfunction(upgrade, 'preservedrequirements',
+                 wrapper.upgraderequirements)
+
+    wrapfunction(upgrade, 'supporteddestrequirements',
+                 wrapper.upgraderequirements)
+
     wrapfunction(changegroup,
                  'supportedoutgoingversions',
                  wrapper.supportedoutgoingversions)
     wrapfunction(changegroup,
                  'allsupportedversions',
                  wrapper.allsupportedversions)
 
     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)
 
     # 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)
 
 @templatekeyword('lfs_files')
 def lfsfiles(repo, ctx, **args):
     """List of strings. LFS files added or modified by the changeset."""
     pointers = wrapper.pointersfromctx(ctx) # {path: pointer}
     return sorted(pointers.keys())
 
 @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('rev', [])
     pointers = wrapper.extractpointers(repo, scmutil.revrange(repo, revs))
     wrapper.uploadblobs(repo, pointers)

hgext/lfs/wrapper.py

@@ -1,304 +1,310
 # 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, nullid, short
 
 from mercurial import (
     error,
     filelog,
     revlog,
     util,
 )
 
 from . import (
     blobstore,
     pointer,
 )
 
 def supportedoutgoingversions(orig, repo):
     versions = orig(repo)
     versions.discard('01')
     versions.discard('02')
     versions.add('03')
     return versions
 
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add('03')
     return versions
 
 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 = getattr(self, 'indexfile', None)
         self.opener.lfsremoteblobstore.readbatch([p], store)
     text = store.read(oid)
 
     # 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 = hashlib.sha256(text).hexdigest()
     self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = 'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size=str(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 util.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):
     threshold = self.opener.options['lfsthreshold']
     textlen = len(text)
     # exclude hg rename meta from file size
     meta, offset = filelog.parsemeta(text)
     if offset:
         textlen -= offset
 
     if threshold and textlen > threshold:
         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 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
                         with self.repo.vfs('hgrc', 'a', text=True) as fp:
                             fp.write('\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:
             with repo.vfs('hgrc', 'a', text=True) as fp:
                 fp.write('\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:
         with destrepo.vfs('hgrc', 'a', text=True) as fp:
             fp.write('\n[extensions]\nlfs=\n')
 
 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 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"""
     ui = repo.ui
     if ui.debugflag:
         ui.write(_('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 pointers.values()
 
 def pointersfromctx(ctx):
     """return a dict {path: pointer} for given single changectx"""
     result = {}
     for f in ctx.files():
         if f not in ctx:
             continue
         fctx = ctx[f]
         if not _islfs(fctx.filelog(), fctx.filenode()):
             continue
         try:
             result[f] = pointer.deserialize(fctx.rawdata())
         except pointer.InvalidPointer as ex:
             raise error.Abort(_('lfs: corrupted pointer (%s@%s): %s\n')
                               % (f, short(ctx.node()), ex))
     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 upgraderequirements(orig, repo):
+    reqs = orig(repo)
+    if 'lfs' in repo.requirements:
+        reqs.add('lfs')
+    return reqs