changegroup: don't send empty subdirectory manifest groups

When grafting/rebasing, it is common for multiple changesets to make
the same change to a subdirectory. When writing the revlog for the
directory, the revlog code already takes care of not writing the entry
again. In 0c2a088ffcc5 (changegroup: prune subdirectory dirlogs too,
2016-02-12), I added the corresponding code in changegroup (not
sending entries the client already has), but I forgot to avoid sending
the entire changegroup if no nodes remained in the pruned
set. Although that's harmless besides the wasted network traffic, the
receiving side was checking for it (copied from the changegroup code
for handling files). This resulted in the client crashing with:

  abort: received dir revlog group is empty

Fix by simply not emitting a changegroup for the directory if there
were no changes is it. This matches how files are handled.

mercurial/changegroup.py

@@ -1,1062 +1,1063
 # 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,
     nullid,
     nullrev,
     short,
 )
 
 from . import (
     branchmap,
     dagutil,
     discovery,
     error,
     mdiff,
     phases,
     util,
 )
 
 _CHANGEGROUPV1_DELTA_HEADER = "20s20s20s20s"
 _CHANGEGROUPV2_DELTA_HEADER = "20s20s20s20s20s"
 _CHANGEGROUPV3_DELTA_HEADER = ">20s20s20s20s20sH"
 
 def readexactly(stream, n):
     '''read n bytes from stream.read and abort if less was available'''
     s = stream.read(n)
     if len(s) < n:
         raise error.Abort(_("stream ended unexpectedly"
                            " (got %d bytes, expected %d)")
                           % (len(s), n))
     return s
 
 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 combineresults(results):
     """logic to combine 0 or more addchangegroup results into one"""
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 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:
                 fh = open(filename, "wb")
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "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):
         if alg == 'UN':
             alg = None # get more modern without breaking too much
         if not alg in util.decompressors:
             raise error.Abort(_('unknown stream compression type: %s')
                              % alg)
         if alg == 'BZ':
             alg = '_truncatedBZ'
         self._stream = util.decompressors[alg](fh)
         self._type = alg
         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
     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': node, 'p1': p1, 'p2': p2, 'cs': cs,
                 'deltabase': deltabase, 'delta': delta, 'flags': 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.
         """
         # an empty chunkgroup is the end of the changegroup
         # a changegroup has at least 2 chunkgroups (changelog and manifest).
         # after that, changegroup versions 1 and 2 have a series of groups
         # with one group per file. changegroup 3 has a series of directory
         # manifests before the files.
         count = 0
         emptycount = 0
         while emptycount < self._grouplistcount:
             empty = True
             count += 1
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     if empty and count > 2:
                         emptycount += 1
                     break
                 empty = 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()
         repo.manifest.addgroup(self, revmap, trp)
         repo.ui.progress(_('manifests'), None)
         self.callback = None
 
     def apply(self, repo, srctype, url, emptyok=False,
               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:
             with repo.transaction("\n".join([srctype,
                                              util.hidepassword(url)])) as tr:
                 # The transaction could have been created before and already
                 # carries 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, **tr.hookargs)
 
                 # write changelog data to temp files so concurrent readers
                 # will not see an inconsistent view
                 cl = repo.changelog
                 cl.delayupdate(tr)
                 oldheads = 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()
                 srccontent = cl.addgroup(self, csmap, trp,
                                          addrevisioncb=onchangelog)
                 efiles = len(efiles)
 
                 if not (srccontent or emptyok):
                     raise error.Abort(_("received changelog group is empty"))
                 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', default=False):
                     # validate incoming csets have their manifests
                     for cset in xrange(clstart, clend):
                         mfnode = repo.changelog.read(
                             repo.changelog.node(cset))[0]
                         mfest = repo.manifest.readdelta(mfnode)
                         # store file nodes 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
 
                 dh = 0
                 if oldheads:
                     heads = cl.heads()
                     dh = len(heads) - len(oldheads)
                     for h in heads:
                         if h not in oldheads and repo[h].closesbranch():
                             dh -= 1
                 htext = ""
                 if dh:
                     htext = _(" (%+d heads)") % dh
 
                 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, **hookargs)
 
                 added = [cl.node(r) for r in xrange(clstart, clend)]
                 publishing = repo.publishing()
                 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 publishing:
                         phases.advanceboundary(repo, tr, phases.public,
                                                srccontent)
                     else:
                         # Those changesets have been pushed from the
                         # outside, their phases are going to be pushed
                         # alongside. Therefor `targetphase` is
                         # ignored.
                         phases.advanceboundary(repo, tr, phases.draft,
                                                srccontent)
                         phases.retractboundary(repo, tr, phases.draft, added)
                 elif srctype != 'strip':
                     # publishing only alter behavior during push
                     #
                     # strip should not touch boundary at all
                     phases.retractboundary(repo, tr, targetphase, added)
 
                 if changesets > 0:
                     if srctype != 'strip':
                         # During strip, branchcache is invalid but
                         # coming call to `destroyed` will repair it.
                         # In other case we can safely update cache on
                         # disk.
                         branchmap.updatecache(repo.filtered('served'))
 
                     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
 
                         # forcefully update the on-disk branch cache
                         repo.ui.debug("updating the branch cache\n")
                         repo.hook("changegroup", **hookargs)
 
                         for n in added:
                             args = hookargs.copy()
                             args['node'] = hex(n)
                             del args['node_last']
                             repo.hook("incoming", **args)
 
                         newheads = [h for h in repo.heads()
                                     if h not in oldheads]
                         repo.ui.log("incoming",
                                     "%s 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 dh < 0:
             return dh - 1
         else:
             return dh + 1
 
 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)
         while True:
             chunkdata = self.filelogheader()
             if not chunkdata:
                 break
             # If we get here, there are directory manifests in the changegroup
             d = chunkdata["filename"]
             repo.ui.debug("adding %s revisions\n" % d)
             dirlog = repo.manifest.dirlog(d)
             if not dirlog.addgroup(self, 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.
         """
         # 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', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.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.manifest,
                                 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):
             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):
         repo = self._repo
         dirlog = repo.manifest.dirlog
         tmfnodes = {'': mfs}
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def makelookupmflinknode(dir):
             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 = tmfnodes[dir][x]
                 mdata = dirlog(dir).readshallowfast(x)
                 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 = min(tmfnodes)
             nodes = tmfnodes[dir]
             prunednodes = self.prune(dirlog(dir), nodes, commonrevs)
+            if not dir or prunednodes:
             for x in self._packmanifests(dir, prunednodes,
                                          makelookupmflinknode(dir)):
                 size += len(x)
                 yield x
             del tmfnodes[dir]
         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):
         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)
             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)
             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)
         # avoid storing full revisions; pick prev in those cases
         # also pick prev when we can't be sure remote has dp
         if dp == nullrev or (dp != p1 and dp != p2 and dp != prev):
             return prev
         return dp
 
     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)
         for chunk in self.group(mfnodes, self._repo.manifest.dirlog(dir),
                                 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(ui):
     versions = set(_packermap.keys())
     versions.discard('03')
     if (ui.configbool('experimental', 'changegroup3') or
         ui.configbool('experimental', 'treemanifest')):
         versions.add('03')
     return versions
 
 # Changegroup versions that can be applied to the repo
 def supportedincomingversions(repo):
     versions = allsupportedversions(repo.ui)
     if 'treemanifest' in repo.requirements:
         versions.add('03')
     return versions
 
 # Changegroup versions that can be created from the repo
 def supportedoutgoingversions(repo):
     versions = allsupportedversions(repo.ui)
     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')
         versions.add('03')
     return versions
 
 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):
     return _packermap[version][1](fh, alg)
 
 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 getsubsetraw(repo, outgoing, bundler, source, fastpath=False):
     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 getsubset(repo, outgoing, bundler, source, fastpath=False):
     gengroup = getsubsetraw(repo, outgoing, bundler, source, fastpath)
     return getunbundler(bundler.version, util.chunkbuffer(gengroup), None)
 
 def changegroupsubset(repo, roots, heads, source, version='01'):
     """Compute a changegroup consisting of all the nodes that are
     descendants of any of the roots and ancestors of any of the heads.
     Return a chunkbuffer object whose read() method will return
     successive changegroup chunks.
 
     It is fairly complex as determining which filenodes and which
     manifest nodes need to be included for the changeset to be complete
     is non-trivial.
 
     Another wrinkle is doing the reverse, figuring out which changeset in
     the changegroup a particular filenode or manifestnode belongs to.
     """
     cl = repo.changelog
     if not roots:
         roots = [nullid]
     discbases = []
     for n in roots:
         discbases.extend([p for p in cl.parents(n) if p != nullid])
     # TODO: remove call to nodesbetween.
     csets, roots, heads = cl.nodesbetween(roots, heads)
     included = set(csets)
     discbases = [n for n in discbases if n not in included]
     outgoing = discovery.outgoing(cl, discbases, heads)
     bundler = getbundler(version, repo)
     return getsubset(repo, outgoing, bundler, source)
 
 def getlocalchangegroupraw(repo, source, outgoing, bundlecaps=None,
                            version='01'):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing. Returns a raw changegroup generator."""
     if not outgoing.missing:
         return None
     bundler = getbundler(version, repo, bundlecaps)
     return getsubsetraw(repo, outgoing, bundler, source)
 
 def getlocalchangegroup(repo, source, outgoing, bundlecaps=None,
                         version='01'):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing."""
     if not outgoing.missing:
         return None
     bundler = getbundler(version, repo, bundlecaps)
     return getsubset(repo, outgoing, bundler, source)
 
 def computeoutgoing(repo, heads, common):
     """Computes which revs are outgoing given a set of common
     and a set of heads.
 
     This is a separate function so extensions can have access to
     the logic.
 
     Returns a discovery.outgoing object.
     """
     cl = repo.changelog
     if common:
         hasnode = cl.hasnode
         common = [n for n in common if hasnode(n)]
     else:
         common = [nullid]
     if not heads:
         heads = cl.heads()
     return discovery.outgoing(cl, common, heads)
 
 def getchangegroup(repo, source, heads=None, common=None, bundlecaps=None,
                    version='01'):
     """Like changegroupsubset, but returns the set difference between the
     ancestors of heads and the ancestors common.
 
     If heads is None, use the local heads. If common is None, use [nullid].
 
     The nodes in common might not all be known locally due to the way the
     current discovery protocol works.
     """
     outgoing = computeoutgoing(repo, heads, common)
     return getlocalchangegroup(repo, source, outgoing, bundlecaps=bundlecaps,
                                version=version)
 
 def changegroup(repo, basenodes, source):
     # to avoid a race we use changegroupsubset() (issue1320)
     return changegroupsubset(repo, basenodes, repo.heads(), source)
 
 def _addchangegroupfiles(repo, source, revmap, trp, expectedfiles, needfiles):
     revisions = 0
     files = 0
     while True:
         chunkdata = source.filelogheader()
         if not chunkdata:
             break
         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:
             if not fl.addgroup(source, 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

tests/test-treemanifest.t

@@ -1,744 +1,786
 #require killdaemons
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > usegeneraldelta=yes
   > [ui]
   > ssh=python "$TESTDIR/dummyssh"
   > EOF
 
 Set up repo
 
   $ hg --config experimental.treemanifest=True init repo
   $ cd repo
 
 Requirements get set on init
 
   $ grep treemanifest .hg/requires
   treemanifest
 
 Without directories, looks like any other repo
 
   $ echo 0 > a
   $ echo 0 > b
   $ hg ci -Aqm initial
   $ hg debugdata -m 0
   a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
 
 Submanifest is stored in separate revlog
 
   $ mkdir dir1
   $ echo 1 > dir1/a
   $ echo 1 > dir1/b
   $ echo 1 > e
   $ hg ci -Aqm 'add dir1'
   $ hg debugdata -m 1
   a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   dir1\x008b3ffd73f901e83304c83d33132c8e774ceac44et (esc)
   e\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   $ hg debugdata --dir dir1 0
   a\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   b\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
 
 Can add nested directories
 
   $ mkdir dir1/dir1
   $ echo 2 > dir1/dir1/a
   $ echo 2 > dir1/dir1/b
   $ mkdir dir1/dir2
   $ echo 2 > dir1/dir2/a
   $ echo 2 > dir1/dir2/b
   $ hg ci -Aqm 'add dir1/dir1'
   $ hg files -r .
   a
   b
   dir1/a (glob)
   dir1/b (glob)
   dir1/dir1/a (glob)
   dir1/dir1/b (glob)
   dir1/dir2/a (glob)
   dir1/dir2/b (glob)
   e
 
 Revision is not created for unchanged directory
 
   $ mkdir dir2
   $ echo 3 > dir2/a
   $ hg add dir2
   adding dir2/a (glob)
   $ hg debugindex --dir dir1 > before
   $ hg ci -qm 'add dir2'
   $ hg debugindex --dir dir1 > after
   $ diff before after
   $ rm before after
 
 Removing directory does not create an revlog entry
 
   $ hg rm dir1/dir1
   removing dir1/dir1/a (glob)
   removing dir1/dir1/b (glob)
   $ hg debugindex --dir dir1/dir1 > before
   $ hg ci -qm 'remove dir1/dir1'
   $ hg debugindex --dir dir1/dir1 > after
   $ diff before after
   $ rm before after
 
 Check that hg files (calls treemanifest.walk()) works
 without loading all directory revlogs
 
   $ hg co 'desc("add dir2")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ mv .hg/store/meta/dir2 .hg/store/meta/dir2-backup
   $ hg files -r . dir1
   dir1/a (glob)
   dir1/b (glob)
   dir1/dir1/a (glob)
   dir1/dir1/b (glob)
   dir1/dir2/a (glob)
   dir1/dir2/b (glob)
 
 Check that status between revisions works (calls treemanifest.matches())
 without loading all directory revlogs
 
   $ hg status --rev 'desc("add dir1")' --rev . dir1
   A dir1/dir1/a
   A dir1/dir1/b
   A dir1/dir2/a
   A dir1/dir2/b
   $ mv .hg/store/meta/dir2-backup .hg/store/meta/dir2
 
 Merge creates 2-parent revision of directory revlog
 
   $ echo 5 > dir1/a
   $ hg ci -Aqm 'modify dir1/a'
   $ hg co '.^'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 6 > dir1/b
   $ hg ci -Aqm 'modify dir1/b'
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'conflict-free merge involving dir1/'
   $ cat dir1/a
   5
   $ cat dir1/b
   6
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      54     -1       1 8b3ffd73f901 000000000000 000000000000
        1        54      68      0       2 68e9d057c5a8 8b3ffd73f901 000000000000
        2       122      12      1       4 4698198d2624 68e9d057c5a8 000000000000
        3       134      55      1       5 44844058ccce 68e9d057c5a8 000000000000
        4       189      55      1       6 bf3d9b744927 68e9d057c5a8 000000000000
        5       244      55      4       7 dde7c0af2a03 bf3d9b744927 44844058ccce
 
 Merge keeping directory from parent 1 does not create revlog entry. (Note that
 dir1's manifest does change, but only because dir1/a's filelog changes.)
 
   $ hg co 'desc("add dir2")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 8 > dir2/a
   $ hg ci -m 'modify dir2/a'
   created new head
 
   $ hg debugindex --dir dir2 > before
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg revert -r 'desc("modify dir2/a")' .
   reverting dir1/a (glob)
   $ hg ci -m 'merge, keeping parent 1'
   $ hg debugindex --dir dir2 > after
   $ diff before after
   $ rm before after
 
 Merge keeping directory from parent 2 does not create revlog entry. (Note that
 dir2's manifest does change, but only because dir2/a's filelog changes.)
 
   $ hg co 'desc("modify dir2/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg debugindex --dir dir1 > before
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg revert -r 'desc("modify dir1/a")' .
   reverting dir2/a (glob)
   $ hg ci -m 'merge, keeping parent 2'
   created new head
   $ hg debugindex --dir dir1 > after
   $ diff before after
   $ rm before after
 
 Create flat source repo for tests with mixed flat/tree manifests
 
   $ cd ..
   $ hg init repo-flat
   $ cd repo-flat
 
 Create a few commits with flat manifest
 
   $ echo 0 > a
   $ echo 0 > b
   $ echo 0 > e
   $ for d in dir1 dir1/dir1 dir1/dir2 dir2
   > do
   >   mkdir $d
   >   echo 0 > $d/a
   >   echo 0 > $d/b
   > done
   $ hg ci -Aqm initial
 
   $ echo 1 > a
   $ echo 1 > dir1/a
   $ echo 1 > dir1/dir1/a
   $ hg ci -Aqm 'modify on branch 1'
 
   $ hg co 0
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 2 > b
   $ echo 2 > dir1/b
   $ echo 2 > dir1/dir1/b
   $ hg ci -Aqm 'modify on branch 2'
 
   $ hg merge 1
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'merge of flat manifests to new flat manifest'
 
   $ hg serve -p $HGPORT -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
 
 Create clone with tree manifests enabled
 
   $ cd ..
   $ hg clone --config experimental.treemanifest=1 \
   >   http://localhost:$HGPORT repo-mixed -r 1
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 14 changes to 11 files
   updating to branch default
   11 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd repo-mixed
   $ test -d .hg/store/meta
   [1]
   $ grep treemanifest .hg/requires
   treemanifest
 
 Should be possible to push updates from flat to tree manifest repo
 
   $ hg -R ../repo-flat push ssh://user@dummy/repo-mixed
   pushing to ssh://user@dummy/repo-mixed
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 2 changesets with 3 changes to 3 files
 
 Commit should store revlog per directory
 
   $ hg co 1
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 3 > a
   $ echo 3 > dir1/a
   $ echo 3 > dir1/dir1/a
   $ hg ci -m 'first tree'
   created new head
   $ find .hg/store/meta | sort
   .hg/store/meta
   .hg/store/meta/dir1
   .hg/store/meta/dir1/00manifest.i
   .hg/store/meta/dir1/dir1
   .hg/store/meta/dir1/dir1/00manifest.i
   .hg/store/meta/dir1/dir2
   .hg/store/meta/dir1/dir2/00manifest.i
   .hg/store/meta/dir2
   .hg/store/meta/dir2/00manifest.i
 
 Merge of two trees
 
   $ hg co 2
   6 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 1
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'merge of flat manifests to new tree manifest'
   created new head
   $ hg diff -r 3
 
 Parent of tree root manifest should be flat manifest, and two for merge
 
   $ hg debugindex -m
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      80     -1       0 40536115ed9e 000000000000 000000000000
        1        80      83      0       1 f3376063c255 40536115ed9e 000000000000
        2       163      89      0       2 5d9b9da231a2 40536115ed9e 000000000000
        3       252      83      2       3 d17d663cbd8a 5d9b9da231a2 f3376063c255
        4       335     124      1       4 51e32a8c60ee f3376063c255 000000000000
        5       459     126      2       5 cc5baa78b230 5d9b9da231a2 f3376063c255
 
 
 Status across flat/tree boundary should work
 
   $ hg status --rev '.^' --rev .
   M a
   M dir1/a
   M dir1/dir1/a
 
 
 Turning off treemanifest config has no effect
 
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0     127     -1       4 064927a0648a 000000000000 000000000000
        1       127     111      0       5 25ecb8cb8618 000000000000 000000000000
   $ echo 2 > dir1/a
   $ hg --config experimental.treemanifest=False ci -qm 'modify dir1/a'
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0     127     -1       4 064927a0648a 000000000000 000000000000
        1       127     111      0       5 25ecb8cb8618 000000000000 000000000000
        2       238      55      1       6 5b16163a30c6 25ecb8cb8618 000000000000
 
 Stripping and recovering changes should work
 
   $ hg st --change tip
   M dir1/a
   $ hg --config extensions.strip= strip tip
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   saved backup bundle to $TESTTMP/repo-mixed/.hg/strip-backup/51cfd7b1e13b-78a2f3ed-backup.hg (glob)
   $ hg unbundle -q .hg/strip-backup/*
   $ hg st --change tip
   M dir1/a
 
 Shelving and unshelving should work
 
   $ echo foo >> dir1/a
   $ hg --config extensions.shelve= shelve
   shelved as default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg --config extensions.shelve= unshelve
   unshelving change 'default'
   $ hg diff --nodates
   diff -r 708a273da119 dir1/a
   --- a/dir1/a
   +++ b/dir1/a
   @@ -1,1 +1,2 @@
    1
   +foo
 
 Pushing from treemanifest repo to an empty repo makes that a treemanifest repo
 
   $ cd ..
   $ hg init empty-repo
   $ cat << EOF >> empty-repo/.hg/hgrc
   > [experimental]
   > changegroup3=yes
   > EOF
   $ grep treemanifest empty-repo/.hg/requires
   [1]
   $ hg push -R repo -r 0 empty-repo
   pushing to empty-repo
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 2 changes to 2 files
   $ grep treemanifest empty-repo/.hg/requires
   treemanifest
 
 Pushing to an empty repo works
 
   $ hg --config experimental.treemanifest=1 init clone
   $ grep treemanifest clone/.hg/requires
   treemanifest
   $ hg push -R repo clone
   pushing to clone
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 11 changesets with 15 changes to 10 files (+3 heads)
   $ grep treemanifest clone/.hg/requires
   treemanifest
   $ hg -R clone verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   10 files, 11 changesets, 15 total revisions
 
 Create deeper repo with tree manifests.
 
   $ hg --config experimental.treemanifest=True init deeprepo
   $ cd deeprepo
 
   $ mkdir .A
   $ mkdir b
   $ mkdir b/bar
   $ mkdir b/bar/orange
   $ mkdir b/bar/orange/fly
   $ mkdir b/foo
   $ mkdir b/foo/apple
   $ mkdir b/foo/apple/bees
 
   $ touch .A/one.txt
   $ touch .A/two.txt
   $ touch b/bar/fruits.txt
   $ touch b/bar/orange/fly/gnat.py
   $ touch b/bar/orange/fly/housefly.txt
   $ touch b/foo/apple/bees/flower.py
   $ touch c.txt
   $ touch d.py
 
   $ hg ci -Aqm 'initial'
 
 We'll see that visitdir works by removing some treemanifest revlogs and running
 the files command with various parameters.
 
 Test files from the root.
 
   $ hg files -r .
   .A/one.txt (glob)
   .A/two.txt (glob)
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   b/foo/apple/bees/flower.py (glob)
   c.txt
   d.py
 
 Excludes with a glob should not exclude everything from the glob's root
 
   $ hg files -r . -X 'b/fo?' b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store .hg/store-copy
 
 Test files for a subdirectory.
 
   $ rm -r .hg/store/meta/~2e_a
   $ hg files -r . b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   b/foo/apple/bees/flower.py (glob)
   $ cp -r .hg/store-copy/. .hg/store
 
 Test files with just includes and excludes.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/bar/orange/fly
   $ rm -r .hg/store/meta/b/foo/apple/bees
   $ hg files -r . -I path:b/bar -X path:b/bar/orange/fly -I path:b/foo -X path:b/foo/apple/bees
   b/bar/fruits.txt (glob)
   $ cp -r .hg/store-copy/. .hg/store
 
 Test files for a subdirectory, excluding a directory within it.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ hg files -r . -X path:b/foo b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store-copy/. .hg/store
 
 Test files for a sub directory, including only a directory within it, and
 including an unrelated directory.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ hg files -r . -I path:b/bar/orange -I path:a b
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store-copy/. .hg/store
 
 Test files for a pattern, including a directory, and excluding a directory
 within that.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ rm -r .hg/store/meta/b/bar/orange
   $ hg files -r . glob:**.txt -I path:b/bar -X path:b/bar/orange
   b/bar/fruits.txt (glob)
   $ cp -r .hg/store-copy/. .hg/store
 
 Add some more changes to the deep repo
   $ echo narf >> b/bar/fruits.txt
   $ hg ci -m narf
   $ echo troz >> b/bar/orange/fly/gnat.py
   $ hg ci -m troz
 
 Verify works
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Dirlogs are included in fncache
   $ grep meta/.A/00manifest.i .hg/store/fncache
   meta/.A/00manifest.i
 
 Rebuilt fncache includes dirlogs
   $ rm .hg/store/fncache
   $ hg debugrebuildfncache
   adding data/.A/one.txt.i
   adding data/.A/two.txt.i
   adding data/b/bar/fruits.txt.i
   adding data/b/bar/orange/fly/gnat.py.i
   adding data/b/bar/orange/fly/housefly.txt.i
   adding data/b/foo/apple/bees/flower.py.i
   adding data/c.txt.i
   adding data/d.py.i
   adding meta/.A/00manifest.i
   adding meta/b/00manifest.i
   adding meta/b/bar/00manifest.i
   adding meta/b/bar/orange/00manifest.i
   adding meta/b/bar/orange/fly/00manifest.i
   adding meta/b/foo/00manifest.i
   adding meta/b/foo/apple/00manifest.i
   adding meta/b/foo/apple/bees/00manifest.i
   16 items added, 0 removed from fncache
 
 Finish first server
   $ killdaemons.py
 
 Back up the recently added revlogs
   $ cp -r .hg/store .hg/store-newcopy
 
 Verify reports missing dirlog
   $ rm .hg/store/meta/b/00manifest.*
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
    0: empty or missing b/
    b/@0: parent-directory manifest refers to unknown revision 67688a370455
    b/@1: parent-directory manifest refers to unknown revision f38e85d334c5
    b/@2: parent-directory manifest refers to unknown revision 99c9792fd4b0
   warning: orphan revlog 'meta/b/bar/00manifest.i'
   warning: orphan revlog 'meta/b/bar/orange/00manifest.i'
   warning: orphan revlog 'meta/b/bar/orange/fly/00manifest.i'
   warning: orphan revlog 'meta/b/foo/00manifest.i'
   warning: orphan revlog 'meta/b/foo/apple/00manifest.i'
   warning: orphan revlog 'meta/b/foo/apple/bees/00manifest.i'
   crosschecking files in changesets and manifests
    b/bar/fruits.txt@0: in changeset but not in manifest
    b/bar/orange/fly/gnat.py@0: in changeset but not in manifest
    b/bar/orange/fly/housefly.txt@0: in changeset but not in manifest
    b/foo/apple/bees/flower.py@0: in changeset but not in manifest
   checking files
   8 files, 3 changesets, 10 total revisions
   6 warnings encountered!
   8 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -r .hg/store-newcopy/. .hg/store
 
 Verify reports missing dirlog entry
   $ mv -f .hg/store-copy/meta/b/00manifest.* .hg/store/meta/b/
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
    b/@1: parent-directory manifest refers to unknown revision f38e85d334c5
    b/@2: parent-directory manifest refers to unknown revision 99c9792fd4b0
    b/bar/@?: rev 1 points to unexpected changeset 1
    b/bar/@?: 5e03c4ee5e4a not in parent-directory manifest
    b/bar/@?: rev 2 points to unexpected changeset 2
    b/bar/@?: 1b16940d66d6 not in parent-directory manifest
    b/bar/orange/@?: rev 1 points to unexpected changeset 2
    (expected None)
    b/bar/orange/fly/@?: rev 1 points to unexpected changeset 2
    (expected None)
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
   2 warnings encountered!
   8 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
   $ cp -r .hg/store-newcopy/. .hg/store
 
 Test cloning a treemanifest repo over http.
   $ hg serve -p $HGPORT -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
 We can clone even with the knob turned off and we'll get a treemanifest repo.
   $ hg clone --config experimental.treemanifest=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deepclone
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
 No server errors.
   $ cat deeprepo/errors.log
 requires got updated to include treemanifest
   $ cat deepclone/.hg/requires | grep treemanifest
   treemanifest
 Tree manifest revlogs exist.
   $ find deepclone/.hg/store/meta | sort
   deepclone/.hg/store/meta
   deepclone/.hg/store/meta/b
   deepclone/.hg/store/meta/b/00manifest.i
   deepclone/.hg/store/meta/b/bar
   deepclone/.hg/store/meta/b/bar/00manifest.i
   deepclone/.hg/store/meta/b/bar/orange
   deepclone/.hg/store/meta/b/bar/orange/00manifest.i
   deepclone/.hg/store/meta/b/bar/orange/fly
   deepclone/.hg/store/meta/b/bar/orange/fly/00manifest.i
   deepclone/.hg/store/meta/b/foo
   deepclone/.hg/store/meta/b/foo/00manifest.i
   deepclone/.hg/store/meta/b/foo/apple
   deepclone/.hg/store/meta/b/foo/apple/00manifest.i
   deepclone/.hg/store/meta/b/foo/apple/bees
   deepclone/.hg/store/meta/b/foo/apple/bees/00manifest.i
   deepclone/.hg/store/meta/~2e_a
   deepclone/.hg/store/meta/~2e_a/00manifest.i
 Verify passes.
   $ cd deepclone
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
   $ cd ..
 
 Create clones using old repo formats to use in later tests
   $ hg clone --config format.usestore=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deeprepo-basicstore
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd deeprepo-basicstore
   $ grep store .hg/requires
   [1]
   $ hg serve -p $HGPORT1 -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
   $ hg clone --config format.usefncache=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deeprepo-encodedstore
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd deeprepo-encodedstore
   $ grep fncache .hg/requires
   [1]
   $ hg serve -p $HGPORT2 -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
 
 Local clone with basicstore
   $ hg clone -U deeprepo-basicstore local-clone-basicstore
   $ hg -R local-clone-basicstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Local clone with encodedstore
   $ hg clone -U deeprepo-encodedstore local-clone-encodedstore
   $ hg -R local-clone-encodedstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Local clone with fncachestore
   $ hg clone -U deeprepo local-clone-fncachestore
   $ hg -R local-clone-fncachestore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with basicstore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT1 stream-clone-basicstore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-basicstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with encodedstore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT2 stream-clone-encodedstore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-encodedstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with fncachestore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT stream-clone-fncachestore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-fncachestore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Packed bundle
   $ hg -R deeprepo debugcreatestreamclonebundle repo-packed.hg
   writing 3349 bytes for 18 files
   bundle requirements: generaldelta, revlogv1, treemanifest
   $ hg debugbundle --spec repo-packed.hg
   none-packed1;requirements%3Dgeneraldelta%2Crevlogv1%2Ctreemanifest
 
 Bundle with changegroup2 is not supported
 
   $ hg -R deeprepo bundle --all -t v2 deeprepo.bundle
   abort: repository does not support bundle version 02
   [255]
+
+Pull does not include changegroup for manifest the client already has from
+other branch
+
+  $ mkdir grafted-dir-repo
+  $ cd grafted-dir-repo
+  $ hg --config experimental.treemanifest=1 init
+  $ mkdir dir
+  $ echo a > dir/file
+  $ echo a > file
+  $ hg ci -Am initial
+  adding dir/file
+  adding file
+  $ echo b > dir/file
+  $ hg ci -m updated
+  $ hg co '.^'
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ hg revert -r tip dir/
+  reverting dir/file (glob)
+  $ echo b > file # to make sure root manifest is sent
+  $ hg ci -m grafted
+  created new head
+  $ cd ..
+
+  $ hg --config experimental.treemanifest=1 clone --pull -r 1 \
+  >   grafted-dir-repo grafted-dir-repo-clone
+  adding changesets
+  adding manifests
+  adding file changes
+  added 2 changesets with 3 changes to 2 files
+  updating to branch default
+  2 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ cd grafted-dir-repo-clone
+  $ hg pull -r 2
+  pulling from $TESTTMP/grafted-dir-repo (glob)
+  searching for changes
+  adding changesets
+  adding manifests
+  adding file changes
+  added 1 changesets with 1 changes to 1 files (+1 heads)
+  (run 'hg heads' to see heads, 'hg merge' to merge)
+