lfs: allow non-lfs exchanges when the extension is only enabled on one side

Once the 'lfs' requirement is added, the extension must be loaded on both sides,
and changegroup3 used.  But there's no reason that I can see for bailing with
cryptic errors if lfs is not required, but randomly enabled somewhere.

hgext/lfs/wrapper.py

@@ -1,323 +1,324
 # 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 ..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 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)
 
     # 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 = hashlib.sha256(text).hexdigest()
     self.opener.lfslocalblobstore.write(oid, text, verify=False)
 
     # 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"""
     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 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 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

tests/test-lfs-serve.t

@@ -1,299 +1,279
 #testcases lfsremote-on lfsremote-off
 #require serve
 
 This test splits `hg serve` with and without using the extension into separate
 tests cases.  The tests are broken down as follows, where "LFS"/"No-LFS"
 indicates whether or not there are commits that use an LFS file, and "D"/"E"
 indicates whether or not the extension is loaded.  The "X" cases are not tested
 individually, because the lfs requirement causes the process to bail early if
 the extension is disabled.
 
 .                        Server
 .
 .                    No-LFS        LFS
 .            +----------------------------+
 .            |   ||  D  |  E  |  D  |  E  |
 .            |---++=======================|
 .  C         | D || N/A | #1  |  X  | #4  |
 .  l    No   +---++-----------------------|
 .  i    LFS  | E || #2  | #2  |  X  | #5  |
 .  e         +---++-----------------------|
 .  n         | D ||  X  |  X  |  X  |  X  |
 .  t    LFS  |---++-----------------------|
 .            | E || #3  | #3  |  X  | #6  |
 .            |---++-----------------------+
 
   $ hg init server
   $ SERVER_REQUIRES="$TESTTMP/server/.hg/requires"
 
 Skip the experimental.changegroup3=True config.  Failure to agree on this comes
 first, and causes a "ValueError: no common changegroup version" or "abort:
 HTTP Error 500: Internal Server Error", if the extension is only loaded on one
 side.  If that *is* enabled, the subsequent failure is "abort: missing processor
 for flag '0x2000'!" if the extension is only loaded on one side (possibly also
 masked by the Internal Server Error message).
   $ cat >> $HGRCPATH <<EOF
   > [lfs]
   > url=file:$TESTTMP/dummy-remote/
   > threshold=10
   > [web]
   > allow_push=*
   > push_ssl=False
   > EOF
 
 #if lfsremote-on
   $ hg --config extensions.lfs= -R server \
   >    serve -p $HGPORT -d --pid-file=hg.pid --errorlog=$TESTTMP/errors.log
 #else
   $ hg --config extensions.lfs=! -R server \
   >    serve -p $HGPORT -d --pid-file=hg.pid --errorlog=$TESTTMP/errors.log
 #endif
 
   $ cat hg.pid >> $DAEMON_PIDS
   $ hg clone -q http://localhost:$HGPORT client
   $ grep 'lfs' client/.hg/requires $SERVER_REQUIRES
   [1]
 
 --------------------------------------------------------------------------------
 Case #1: client with non-lfs content and the extension disabled; server with
 non-lfs content, and the extension enabled.
 
   $ cd client
   $ echo 'non-lfs' > nonlfs.txt
   $ hg ci -Aqm 'non-lfs'
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   [1]
 
 #if lfsremote-on
 
   $ hg push -q
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   [1]
 
-TODO: fail more gracefully, or don't mandate changegroup3 for non-lfs repos.
-
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client1_clone
-  abort: HTTP Error 500: Internal Server Error
-  [255]
   $ grep 'lfs' $TESTTMP/client1_clone/.hg/requires $SERVER_REQUIRES
-  grep: $TESTTMP/client1_clone/.hg/requires: $ENOENT$
-  [2]
-
-TODO: fail more gracefully, or don't mandate changegroup3 for non-lfs repos.
+  [1]
 
   $ hg init $TESTTMP/client1_pull
   $ hg -R $TESTTMP/client1_pull pull -q http://localhost:$HGPORT
-  abort: HTTP Error 500: Internal Server Error
-  [255]
   $ grep 'lfs' $TESTTMP/client1_pull/.hg/requires $SERVER_REQUIRES
   [1]
 
   $ hg identify http://localhost:$HGPORT
   d437e1d24fbd
 
 #endif
 
 --------------------------------------------------------------------------------
 Case #2: client with non-lfs content and the extension enabled; server with
 non-lfs content, and the extension state controlled by #testcases.
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > lfs =
   > EOF
   $ echo 'non-lfs' > nonlfs2.txt
   $ hg ci -Aqm 'non-lfs file with lfs client'
 
-TODO: fail more gracefully here
-  $ hg push -q 2>&1 | grep '^[A-Z]' || true
-  Traceback (most recent call last): (lfsremote-off !)
-  ValueError: no common changegroup version (lfsremote-off !)
+Since no lfs content has been added yet, the push is allowed, even when the
+extension is not enabled remotely.
+
+  $ hg push -q
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   [1]
 
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client2_clone
   $ grep 'lfs' $TESTTMP/client2_clone/.hg/requires $SERVER_REQUIRES
   [1]
 
   $ hg init $TESTTMP/client2_pull
   $ hg -R $TESTTMP/client2_pull pull -q http://localhost:$HGPORT
   $ grep 'lfs' $TESTTMP/client2_pull/.hg/requires $SERVER_REQUIRES
   [1]
 
-XXX: The difference here is the push failed above when the extension isn't
-enabled on the server.  The extension shouldn't need to mess with changegroup
-versions if there is no lfs content.  But the requirement needs to be
-consistently added before that can be ratcheted back.
   $ hg identify http://localhost:$HGPORT
-  1477875038c6 (lfsremote-on !)
-  000000000000 (lfsremote-off !)
+  1477875038c6
 
 --------------------------------------------------------------------------------
 Case #3: client with lfs content and the extension enabled; server with
 non-lfs content, and the extension state controlled by #testcases.  The server
 should have an 'lfs' requirement after it picks up its first commit with a blob.
 
   $ echo 'this is a big lfs file' > lfs.bin
   $ hg ci -Aqm 'lfs'
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   .hg/requires:lfs
 
 TODO: fail more gracefully here
   $ hg push -q 2>&1 | grep '^[A-Z]' || true
   Traceback (most recent call last): (lfsremote-off !)
   ValueError: no common changegroup version (lfsremote-off !)
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   .hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs (lfsremote-on !)
 
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client3_clone
   $ grep 'lfs' $TESTTMP/client3_clone/.hg/requires $SERVER_REQUIRES || true
   $TESTTMP/client3_clone/.hg/requires:lfs (lfsremote-on !)
   $TESTTMP/server/.hg/requires:lfs (lfsremote-on !)
 
   $ hg init $TESTTMP/client3_pull
   $ hg -R $TESTTMP/client3_pull pull -q http://localhost:$HGPORT
   $ grep 'lfs' $TESTTMP/client3_pull/.hg/requires $SERVER_REQUIRES || true
   $TESTTMP/client3_pull/.hg/requires:lfs (lfsremote-on !)
   $TESTTMP/server/.hg/requires:lfs (lfsremote-on !)
 
-XXX: The difference here is the push failed above when the extension isn't
-enabled on the server.  The extension shouldn't need to mess with changegroup
-versions if there is no lfs content.  But the requirement needs to be
-consistently added before that can be ratcheted back.
+The difference here is the push failed above when the extension isn't
+enabled on the server.
   $ hg identify http://localhost:$HGPORT
   8374dc4052cb (lfsremote-on !)
-  000000000000 (lfsremote-off !)
+  1477875038c6 (lfsremote-off !)
 
 Don't bother testing the lfsremote-off cases- the server won't be able
 to launch if there's lfs content and the extension is disabled.
 
 #if lfsremote-on
 
 --------------------------------------------------------------------------------
 Case #4: client with non-lfs content and the extension disabled; server with
 lfs content, and the extension enabled.
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > lfs = !
   > EOF
 
   $ hg init $TESTTMP/client4
   $ cd $TESTTMP/client4
   $ cat >> .hg/hgrc <<EOF
   > [paths]
   > default = http://localhost:$HGPORT
   > EOF
   $ echo 'non-lfs' > nonlfs2.txt
   $ hg ci -Aqm 'non-lfs'
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg push -q --force
   warning: repository is unrelated
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   $TESTTMP/server/.hg/requires:lfs
 
 TODO: fail more gracefully.
 
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client4_clone
   abort: HTTP Error 500: Internal Server Error
   [255]
   $ grep 'lfs' $TESTTMP/client4_clone/.hg/requires $SERVER_REQUIRES
   grep: $TESTTMP/client4_clone/.hg/requires: $ENOENT$
   $TESTTMP/server/.hg/requires:lfs
   [2]
 
 TODO: fail more gracefully.
 
   $ hg init $TESTTMP/client4_pull
   $ hg -R $TESTTMP/client4_pull pull -q http://localhost:$HGPORT
   abort: HTTP Error 500: Internal Server Error
   [255]
   $ grep 'lfs' $TESTTMP/client4_pull/.hg/requires $SERVER_REQUIRES
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg identify http://localhost:$HGPORT
   03b080fa9d93
 
 --------------------------------------------------------------------------------
 Case #5: client with non-lfs content and the extension enabled; server with
 lfs content, and the extension enabled.
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > lfs =
   > EOF
   $ echo 'non-lfs' > nonlfs3.txt
   $ hg ci -Aqm 'non-lfs file with lfs client'
 
   $ hg push -q
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client5_clone
   $ grep 'lfs' $TESTTMP/client5_clone/.hg/requires $SERVER_REQUIRES
   $TESTTMP/client5_clone/.hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg init $TESTTMP/client5_pull
   $ hg -R $TESTTMP/client5_pull pull -q http://localhost:$HGPORT
   $ grep 'lfs' $TESTTMP/client5_pull/.hg/requires $SERVER_REQUIRES
   $TESTTMP/client5_pull/.hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg identify http://localhost:$HGPORT
   c729025cc5e3
 
 --------------------------------------------------------------------------------
 Case #6: client with lfs content and the extension enabled; server with
 lfs content, and the extension enabled.
 
   $ echo 'this is another lfs file' > lfs2.txt
   $ hg ci -Aqm 'lfs file with lfs client'
 
   $ hg push -q
   $ grep 'lfs' .hg/requires $SERVER_REQUIRES
   .hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg clone -q http://localhost:$HGPORT $TESTTMP/client6_clone
   $ grep 'lfs' $TESTTMP/client6_clone/.hg/requires $SERVER_REQUIRES
   $TESTTMP/client6_clone/.hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg init $TESTTMP/client6_pull
   $ hg -R $TESTTMP/client6_pull pull -q http://localhost:$HGPORT
   $ grep 'lfs' $TESTTMP/client6_pull/.hg/requires $SERVER_REQUIRES
   $TESTTMP/client6_pull/.hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
   $ hg identify http://localhost:$HGPORT
   d3b84d50eacb
 
 --------------------------------------------------------------------------------
 Misc: process dies early if a requirement exists and the extension is disabled
 
   $ hg --config extensions.lfs=! summary
   abort: repository requires features unknown to this Mercurial: lfs!
   (see https://mercurial-scm.org/wiki/MissingRequirement for more information)
   [255]
 
 #endif
 
   $ $PYTHON $TESTDIR/killdaemons.py $DAEMON_PIDS
 
 #if lfsremote-on
   $ cat $TESTTMP/errors.log | grep '^[A-Z]'
   Traceback (most recent call last):
   ValueError: no common changegroup version
   Traceback (most recent call last):
   ValueError: no common changegroup version
-  Traceback (most recent call last):
-  ValueError: no common changegroup version
-  Traceback (most recent call last):
-  ValueError: no common changegroup version
 #else
   $ cat $TESTTMP/errors.log
 #endif