discovery: move code to create outgoing from roots and heads

changegroup.changegroupsubset() contained somewhat low-level code for
constructing an "outgoing" instance from a list of roots and heads
nodes. It feels like discovery.py is a more appropriate location for
this code.

This code can definitely be optimized, as outgoing.missing will
recompute the set of changesets we've already discovered from
cl.between(). But code shouldn't be refactored during a move, so
I've simply inserted a TODO calling attention to that.

mercurial/changegroup.py

@@ -1,1065 +1,1055 b''
 # 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, extras=None):
         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.extras = extras or {}
         self.callback = None
 
     # These methods (compressed, read, seek, tell) all appear to only
     # be used by bundlerepo, but it's a little hard to tell.
     def compressed(self):
         return self._type is not None
     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, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def 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,
                         {'clcount': len(outgoing.missing)})
 
 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)
+    outgoing = discovery.outgoingbetween(repo, roots, 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

mercurial/discovery.py

@@ -1,417 +1,438 b''
 # discovery.py - protocol changeset discovery functions
 #
 # Copyright 2010 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
 
 from .i18n import _
 from .node import (
     nullid,
     short,
 )
 
 from . import (
     bookmarks,
     branchmap,
     error,
     obsolete,
     phases,
     setdiscovery,
     treediscovery,
     util,
 )
 
 def findcommonincoming(repo, remote, heads=None, force=False):
     """Return a tuple (common, anyincoming, heads) used to identify the common
     subset of nodes between repo and remote.
 
     "common" is a list of (at least) the heads of the common subset.
     "anyincoming" is testable as a boolean indicating if any nodes are missing
       locally. If remote does not support getbundle, this actually is a list of
       roots of the nodes that would be incoming, to be supplied to
       changegroupsubset. No code except for pull should be relying on this fact
       any longer.
     "heads" is either the supplied heads, or else the remote's heads.
 
     If you pass heads and they are all known locally, the response lists just
     these heads in "common" and in "heads".
 
     Please use findcommonoutgoing to compute the set of outgoing nodes to give
     extensions a good hook into outgoing.
     """
 
     if not remote.capable('getbundle'):
         return treediscovery.findcommonincoming(repo, remote, heads, force)
 
     if heads:
         allknown = True
         knownnode = repo.changelog.hasnode # no nodemap until it is filtered
         for h in heads:
             if not knownnode(h):
                 allknown = False
                 break
         if allknown:
             return (heads, False, heads)
 
     res = setdiscovery.findcommonheads(repo.ui, repo, remote,
                                        abortwhenunrelated=not force)
     common, anyinc, srvheads = res
     return (list(common), anyinc, heads or list(srvheads))
 
 class outgoing(object):
     '''Represents the set of nodes present in a local repo but not in a
     (possibly) remote one.
 
     Members:
 
       missing is a list of all nodes present in local but not in remote.
       common is a list of all nodes shared between the two repos.
       excluded is the list of missing changeset that shouldn't be sent remotely.
       missingheads is the list of heads of missing.
       commonheads is the list of heads of common.
 
     The sets are computed on demand from the heads, unless provided upfront
     by discovery.'''
 
     def __init__(self, revlog, commonheads, missingheads):
         self.commonheads = commonheads
         self.missingheads = missingheads
         self._revlog = revlog
         self._common = None
         self._missing = None
         self.excluded = []
 
     def _computecommonmissing(self):
         sets = self._revlog.findcommonmissing(self.commonheads,
                                               self.missingheads)
         self._common, self._missing = sets
 
     @util.propertycache
     def common(self):
         if self._common is None:
             self._computecommonmissing()
         return self._common
 
     @util.propertycache
     def missing(self):
         if self._missing is None:
             self._computecommonmissing()
         return self._missing
 
+def outgoingbetween(repo, roots, heads):
+    """create an ``outgoing`` consisting of nodes between roots and heads
+
+    The ``missing`` nodes will be descendants of any of the ``roots`` and
+    ancestors of any of the ``heads``, both are which are defined as a list
+    of binary nodes.
+    """
+    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.
+    # TODO populate attributes on outgoing instance instead of setting
+    # discbases.
+    csets, roots, heads = cl.nodesbetween(roots, heads)
+    included = set(csets)
+    discbases = [n for n in discbases if n not in included]
+    return outgoing(cl, discbases, heads)
+
 def findcommonoutgoing(repo, other, onlyheads=None, force=False,
                        commoninc=None, portable=False):
     '''Return an outgoing instance to identify the nodes present in repo but
     not in other.
 
     If onlyheads is given, only nodes ancestral to nodes in onlyheads
     (inclusive) are included. If you already know the local repo's heads,
     passing them in onlyheads is faster than letting them be recomputed here.
 
     If commoninc is given, it must be the result of a prior call to
     findcommonincoming(repo, other, force) to avoid recomputing it here.
 
     If portable is given, compute more conservative common and missingheads,
     to make bundles created from the instance more portable.'''
     # declare an empty outgoing object to be filled later
     og = outgoing(repo.changelog, None, None)
 
     # get common set if not provided
     if commoninc is None:
         commoninc = findcommonincoming(repo, other, force=force)
     og.commonheads, _any, _hds = commoninc
 
     # compute outgoing
     mayexclude = (repo._phasecache.phaseroots[phases.secret] or repo.obsstore)
     if not mayexclude:
         og.missingheads = onlyheads or repo.heads()
     elif onlyheads is None:
         # use visible heads as it should be cached
         og.missingheads = repo.filtered("served").heads()
         og.excluded = [ctx.node() for ctx in repo.set('secret() or extinct()')]
     else:
         # compute common, missing and exclude secret stuff
         sets = repo.changelog.findcommonmissing(og.commonheads, onlyheads)
         og._common, allmissing = sets
         og._missing = missing = []
         og.excluded = excluded = []
         for node in allmissing:
             ctx = repo[node]
             if ctx.phase() >= phases.secret or ctx.extinct():
                 excluded.append(node)
             else:
                 missing.append(node)
         if len(missing) == len(allmissing):
             missingheads = onlyheads
         else: # update missing heads
             missingheads = phases.newheads(repo, onlyheads, excluded)
         og.missingheads = missingheads
     if portable:
         # recompute common and missingheads as if -r<rev> had been given for
         # each head of missing, and --base <rev> for each head of the proper
         # ancestors of missing
         og._computecommonmissing()
         cl = repo.changelog
         missingrevs = set(cl.rev(n) for n in og._missing)
         og._common = set(cl.ancestors(missingrevs)) - missingrevs
         commonheads = set(og.commonheads)
         og.missingheads = [h for h in og.missingheads if h not in commonheads]
 
     return og
 
 def _headssummary(repo, remote, outgoing):
     """compute a summary of branch and heads status before and after push
 
     return {'branch': ([remoteheads], [newheads], [unsyncedheads])} mapping
 
     - branch: the branch name
     - remoteheads: the list of remote heads known locally
                    None if the branch is new
     - newheads: the new remote heads (known locally) with outgoing pushed
     - unsyncedheads: the list of remote heads unknown locally.
     """
     cl = repo.changelog
     headssum = {}
     # A. Create set of branches involved in the push.
     branches = set(repo[n].branch() for n in outgoing.missing)
     remotemap = remote.branchmap()
     newbranches = branches - set(remotemap)
     branches.difference_update(newbranches)
 
     # A. register remote heads
     remotebranches = set()
     for branch, heads in remote.branchmap().iteritems():
         remotebranches.add(branch)
         known = []
         unsynced = []
         knownnode = cl.hasnode # do not use nodemap until it is filtered
         for h in heads:
             if knownnode(h):
                 known.append(h)
             else:
                 unsynced.append(h)
         headssum[branch] = (known, list(known), unsynced)
     # B. add new branch data
     missingctx = list(repo[n] for n in outgoing.missing)
     touchedbranches = set()
     for ctx in missingctx:
         branch = ctx.branch()
         touchedbranches.add(branch)
         if branch not in headssum:
             headssum[branch] = (None, [], [])
 
     # C drop data about untouched branches:
     for branch in remotebranches - touchedbranches:
         del headssum[branch]
 
     # D. Update newmap with outgoing changes.
     # This will possibly add new heads and remove existing ones.
     newmap = branchmap.branchcache((branch, heads[1])
                                  for branch, heads in headssum.iteritems()
                                  if heads[0] is not None)
     newmap.update(repo, (ctx.rev() for ctx in missingctx))
     for branch, newheads in newmap.iteritems():
         headssum[branch][1][:] = newheads
     return headssum
 
 def _oldheadssummary(repo, remoteheads, outgoing, inc=False):
     """Compute branchmapsummary for repo without branchmap support"""
 
     # 1-4b. old servers: Check for new topological heads.
     # Construct {old,new}map with branch = None (topological branch).
     # (code based on update)
     knownnode = repo.changelog.hasnode # no nodemap until it is filtered
     oldheads = set(h for h in remoteheads if knownnode(h))
     # all nodes in outgoing.missing are children of either:
     # - an element of oldheads
     # - another element of outgoing.missing
     # - nullrev
     # This explains why the new head are very simple to compute.
     r = repo.set('heads(%ln + %ln)', oldheads, outgoing.missing)
     newheads = list(c.node() for c in r)
     # set some unsynced head to issue the "unsynced changes" warning
     if inc:
         unsynced = set([None])
     else:
         unsynced = set()
     return {None: (oldheads, newheads, unsynced)}
 
 def _nowarnheads(pushop):
     # Compute newly pushed bookmarks. We don't warn about bookmarked heads.
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     localbookmarks = repo._bookmarks
     remotebookmarks = remote.listkeys('bookmarks')
     bookmarkedheads = set()
 
     # internal config: bookmarks.pushing
     newbookmarks = [localbookmarks.expandname(b)
                     for b in pushop.ui.configlist('bookmarks', 'pushing')]
 
     for bm in localbookmarks:
         rnode = remotebookmarks.get(bm)
         if rnode and rnode in repo:
             lctx, rctx = repo[bm], repo[rnode]
             if bookmarks.validdest(repo, rctx, lctx):
                 bookmarkedheads.add(lctx.node())
         else:
             if bm in newbookmarks and bm not in remotebookmarks:
                 bookmarkedheads.add(repo[bm].node())
 
     return bookmarkedheads
 
 def checkheads(pushop):
     """Check that a push won't add any outgoing head
 
     raise Abort error and display ui message as needed.
     """
 
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     outgoing = pushop.outgoing
     remoteheads = pushop.remoteheads
     newbranch = pushop.newbranch
     inc = bool(pushop.incoming)
 
     # Check for each named branch if we're creating new remote heads.
     # To be a remote head after push, node must be either:
     # - unknown locally
     # - a local outgoing head descended from update
     # - a remote head that's known locally and not
     #   ancestral to an outgoing head
     if remoteheads == [nullid]:
         # remote is empty, nothing to check.
         return
 
     if remote.capable('branchmap'):
         headssum = _headssummary(repo, remote, outgoing)
     else:
         headssum = _oldheadssummary(repo, remoteheads, outgoing, inc)
     newbranches = [branch for branch, heads in headssum.iteritems()
                    if heads[0] is None]
     # 1. Check for new branches on the remote.
     if newbranches and not newbranch:  # new branch requires --new-branch
         branchnames = ', '.join(sorted(newbranches))
         raise error.Abort(_("push creates new remote branches: %s!")
                            % branchnames,
                          hint=_("use 'hg push --new-branch' to create"
                                 " new remote branches"))
 
     # 2. Find heads that we need not warn about
     nowarnheads = _nowarnheads(pushop)
 
     # 3. Check for new heads.
     # If there are more heads after the push than before, a suitable
     # error message, depending on unsynced status, is displayed.
     errormsg = None
     # If there is no obsstore, allfuturecommon won't be used, so no
     # need to compute it.
     if repo.obsstore:
         allmissing = set(outgoing.missing)
         cctx = repo.set('%ld', outgoing.common)
         allfuturecommon = set(c.node() for c in cctx)
         allfuturecommon.update(allmissing)
     for branch, heads in sorted(headssum.iteritems()):
         remoteheads, newheads, unsyncedheads = heads
         candidate_newhs = set(newheads)
         # add unsynced data
         if remoteheads is None:
             oldhs = set()
         else:
             oldhs = set(remoteheads)
         oldhs.update(unsyncedheads)
         candidate_newhs.update(unsyncedheads)
         dhs = None # delta heads, the new heads on branch
         discardedheads = set()
         if not repo.obsstore:
             newhs = candidate_newhs
         else:
             # remove future heads which are actually obsoleted by another
             # pushed element:
             #
             # XXX as above, There are several cases this code does not handle
             # XXX properly
             #
             # (1) if <nh> is public, it won't be affected by obsolete marker
             #     and a new is created
             #
             # (2) if the new heads have ancestors which are not obsolete and
             #     not ancestors of any other heads we will have a new head too.
             #
             # These two cases will be easy to handle for known changeset but
             # much more tricky for unsynced changes.
             #
             # In addition, this code is confused by prune as it only looks for
             # successors of the heads (none if pruned) leading to issue4354
             newhs = set()
             for nh in candidate_newhs:
                 if nh in repo and repo[nh].phase() <= phases.public:
                     newhs.add(nh)
                 else:
                     for suc in obsolete.allsuccessors(repo.obsstore, [nh]):
                         if suc != nh and suc in allfuturecommon:
                             discardedheads.add(nh)
                             break
                     else:
                         newhs.add(nh)
         unsynced = sorted(h for h in unsyncedheads if h not in discardedheads)
         if unsynced:
             if None in unsynced:
                 # old remote, no heads data
                 heads = None
             elif len(unsynced) <= 4 or repo.ui.verbose:
                 heads = ' '.join(short(h) for h in unsynced)
             else:
                 heads = (' '.join(short(h) for h in unsynced[:4]) +
                          ' ' + _("and %s others") % (len(unsynced) - 4))
             if heads is None:
                 repo.ui.status(_("remote has heads that are "
                                  "not known locally\n"))
             elif branch is None:
                 repo.ui.status(_("remote has heads that are "
                                  "not known locally: %s\n") % heads)
             else:
                 repo.ui.status(_("remote has heads on branch '%s' that are "
                                  "not known locally: %s\n") % (branch, heads))
         if remoteheads is None:
             if len(newhs) > 1:
                 dhs = list(newhs)
                 if errormsg is None:
                     errormsg = (_("push creates new branch '%s' "
                                   "with multiple heads") % (branch))
                     hint = _("merge or"
                              " see \"hg help push\" for details about"
                              " pushing new heads")
         elif len(newhs) > len(oldhs):
             # remove bookmarked or existing remote heads from the new heads list
             dhs = sorted(newhs - nowarnheads - oldhs)
         if dhs:
             if errormsg is None:
                 if branch not in ('default', None):
                     errormsg = _("push creates new remote head %s "
                                  "on branch '%s'!") % (short(dhs[0]), branch)
                 elif repo[dhs[0]].bookmarks():
                     errormsg = _("push creates new remote head %s "
                                  "with bookmark '%s'!") % (
                                  short(dhs[0]), repo[dhs[0]].bookmarks()[0])
                 else:
                     errormsg = _("push creates new remote head %s!"
                                  ) % short(dhs[0])
                 if unsyncedheads:
                     hint = _("pull and merge or"
                              " see \"hg help push\" for details about"
                              " pushing new heads")
                 else:
                     hint = _("merge or"
                              " see \"hg help push\" for details about"
                              " pushing new heads")
             if branch is None:
                 repo.ui.note(_("new remote heads:\n"))
             else:
                 repo.ui.note(_("new remote heads on branch '%s':\n") % branch)
             for h in dhs:
                 repo.ui.note((" %s\n") % short(h))
     if errormsg:
         raise error.Abort(errormsg, hint=hint)