bundle-ng: move group into the bundler

No additional semantic changes made.

contrib/shrink-revlog.py

@@ -1,295 +1,295 b''
 """reorder a revlog (the manifest by default) to save space
 
 Specifically, this topologically sorts the revisions in the revlog so that
 revisions on the same branch are adjacent as much as possible. This is a
 workaround for the fact that Mercurial computes deltas relative to the
 previous revision rather than relative to a parent revision.
 
 This is *not* safe to run on a changelog.
 """
 
 # Originally written by Benoit Boissinot <benoit.boissinot at ens-lyon.org>
 # as a patch to rewrite-log. Cleaned up, refactored, documented, and
 # renamed by Greg Ward <greg at gerg.ca>.
 
 # XXX would be nice to have a way to verify the repository after shrinking,
 # e.g. by comparing "before" and "after" states of random changesets
 # (maybe: export before, shrink, export after, diff).
 
 import os, errno
 from mercurial import revlog, transaction, node, util, scmutil
 from mercurial import changegroup
 from mercurial.i18n import _
 
 
 def postorder(start, edges):
     result = []
     visit = list(start)
     finished = set()
 
     while visit:
         cur = visit[-1]
         for p in edges[cur]:
             # defend against node.nullrev because it's occasionally
             # possible for a node to have parents (null, something)
             # rather than (something, null)
             if p not in finished and p != node.nullrev:
                 visit.append(p)
                 break
         else:
             result.append(cur)
             finished.add(cur)
             visit.pop()
 
     return result
 
 def toposort_reversepostorder(ui, rl):
     # postorder of the reverse directed graph
 
     # map rev to list of parent revs (p2 first)
     parents = {}
     heads = set()
     ui.status(_('reading revs\n'))
     try:
         for rev in rl:
             ui.progress(_('reading'), rev, total=len(rl))
             (p1, p2) = rl.parentrevs(rev)
             if p1 == p2 == node.nullrev:
                 parents[rev] = ()       # root node
             elif p1 == p2 or p2 == node.nullrev:
                 parents[rev] = (p1,)    # normal node
             else:
                 parents[rev] = (p2, p1) # merge node
             heads.add(rev)
             for p in parents[rev]:
                 heads.discard(p)
     finally:
         ui.progress(_('reading'), None)
 
     heads = list(heads)
     heads.sort(reverse=True)
 
     ui.status(_('sorting revs\n'))
     return postorder(heads, parents)
 
 def toposort_postorderreverse(ui, rl):
     # reverse-postorder of the reverse directed graph
 
     children = {}
     roots = set()
     ui.status(_('reading revs\n'))
     try:
         for rev in rl:
             ui.progress(_('reading'), rev, total=len(rl))
             (p1, p2) = rl.parentrevs(rev)
             if p1 == p2 == node.nullrev:
                 roots.add(rev)
             children[rev] = []
             if p1 != node.nullrev:
                 children[p1].append(rev)
             if p2 != node.nullrev:
                 children[p2].append(rev)
     finally:
         ui.progress(_('reading'), None)
 
     roots = list(roots)
     roots.sort()
 
     ui.status(_('sorting revs\n'))
     result = postorder(roots, children)
     result.reverse()
     return result
 
 def writerevs(ui, r1, r2, order, tr):
 
     ui.status(_('writing revs\n'))
 
 
     order = [r1.node(r) for r in order]
 
     # this is a bit ugly, but it works
     count = [0]
     def lookup(revl, x):
         count[0] += 1
         ui.progress(_('writing'), count[0], total=len(order))
         return "%020d" % revl.linkrev(revl.rev(x))
 
     unlookup = lambda x: int(x, 10)
 
     try:
         bundler = changegroup.bundle10()
         bundler.start(lookup)
-        group = util.chunkbuffer(r1.group(order, bundler))
+        group = util.chunkbuffer(bundler.group(order, r1))
         group = changegroup.unbundle10(group, "UN")
         r2.addgroup(group, unlookup, tr)
     finally:
         ui.progress(_('writing'), None)
 
 def report(ui, r1, r2):
     def getsize(r):
         s = 0
         for fn in (r.indexfile, r.datafile):
             try:
                 s += os.stat(fn).st_size
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
         return s
 
     oldsize = float(getsize(r1))
     newsize = float(getsize(r2))
 
     # argh: have to pass an int to %d, because a float >= 2^32
     # blows up under Python 2.5 or earlier
     ui.write(_('old file size: %12d bytes (%6.1f MiB)\n')
              % (int(oldsize), oldsize / 1024 / 1024))
     ui.write(_('new file size: %12d bytes (%6.1f MiB)\n')
              % (int(newsize), newsize / 1024 / 1024))
 
     shrink_percent = (oldsize - newsize) / oldsize * 100
     shrink_factor = oldsize / newsize
     ui.write(_('shrinkage: %.1f%% (%.1fx)\n')
              % (shrink_percent, shrink_factor))
 
 def shrink(ui, repo, **opts):
     """shrink a revlog by reordering revisions
 
     Rewrites all the entries in some revlog of the current repository
     (by default, the manifest log) to save space.
 
     Different sort algorithms have different performance
     characteristics.  Use ``--sort`` to select a sort algorithm so you
     can determine which works best for your data.
     """
 
     if not repo.local():
         raise util.Abort(_('not a local repository: %s') % repo.root)
 
     fn = opts.get('revlog')
     if not fn:
         indexfn = repo.sjoin('00manifest.i')
     else:
         if not fn.endswith('.i'):
             raise util.Abort(_('--revlog option must specify the revlog index '
                                'file (*.i), not %s') % opts.get('revlog'))
 
         indexfn = os.path.realpath(fn)
         store = repo.sjoin('')
         if not indexfn.startswith(store):
             raise util.Abort(_('--revlog option must specify a revlog in %s, '
                                'not %s') % (store, indexfn))
 
     sortname = opts['sort']
     try:
         toposort = globals()['toposort_' + sortname]
     except KeyError:
         raise util.Abort(_('no such toposort algorithm: %s') % sortname)
 
     if not os.path.exists(indexfn):
         raise util.Abort(_('no such file: %s') % indexfn)
     if '00changelog' in indexfn:
         raise util.Abort(_('shrinking the changelog '
                            'will corrupt your repository'))
 
     ui.write(_('shrinking %s\n') % indexfn)
     tmpindexfn = util.mktempcopy(indexfn, emptyok=True)
 
     r1 = revlog.revlog(scmutil.opener(os.getcwd(), audit=False), indexfn)
     r2 = revlog.revlog(scmutil.opener(os.getcwd(), audit=False), tmpindexfn)
 
     datafn, tmpdatafn = r1.datafile, r2.datafile
 
     oldindexfn = indexfn + '.old'
     olddatafn = datafn + '.old'
     if os.path.exists(oldindexfn) or os.path.exists(olddatafn):
         raise util.Abort(_('one or both of\n'
                            '  %s\n'
                            '  %s\n'
                            'exists from a previous run; please clean up '
                            'before running again') % (oldindexfn, olddatafn))
 
     # Don't use repo.transaction(), because then things get hairy with
     # paths: some need to be relative to .hg, and some need to be
     # absolute. Doing it this way keeps things simple: everything is an
     # absolute path.
     lock = repo.lock(wait=False)
     tr = transaction.transaction(ui.warn,
                                  open,
                                  repo.sjoin('journal'))
 
     def ignoremissing(func):
         def f(*args, **kw):
             try:
                 return func(*args, **kw)
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
         return f
 
     try:
         try:
             order = toposort(ui, r1)
 
             suboptimal = 0
             for i in xrange(1, len(order)):
                 parents = [p for p in r1.parentrevs(order[i])
                            if p != node.nullrev]
                 if parents and order[i - 1] not in parents:
                     suboptimal += 1
             ui.note(_('%d suboptimal nodes\n') % suboptimal)
 
             writerevs(ui, r1, r2, order, tr)
             report(ui, r1, r2)
             tr.close()
         except: # re-raises
             # Abort transaction first, so we truncate the files before
             # deleting them.
             tr.abort()
             for fn in (tmpindexfn, tmpdatafn):
                 ignoremissing(os.unlink)(fn)
             raise
         if not opts.get('dry_run'):
             # racy, both files cannot be renamed atomically
             # copy files
             util.oslink(indexfn, oldindexfn)
             ignoremissing(util.oslink)(datafn, olddatafn)
 
             # rename
             util.rename(tmpindexfn, indexfn)
             try:
                 os.chmod(tmpdatafn, os.stat(datafn).st_mode)
                 util.rename(tmpdatafn, datafn)
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 ignoremissing(os.unlink)(datafn)
         else:
             for fn in (tmpindexfn, tmpdatafn):
                 ignoremissing(os.unlink)(fn)
     finally:
         lock.release()
 
     if not opts.get('dry_run'):
         ui.write(
             _('note: old revlog saved in:\n'
               '  %s\n'
               '  %s\n'
               '(You can delete those files when you are satisfied that your\n'
               'repository is still sane.  '
               'Running \'hg verify\' is strongly recommended.)\n')
             % (oldindexfn, olddatafn))
 
 cmdtable = {
     'shrink': (shrink,
                [('', 'revlog', '',
                  _('the revlog to shrink (.i)')),
                 ('n', 'dry-run', None,
                  _('do not shrink, simulate only')),
                 ('', 'sort', 'reversepostorder',
                  _('name of sort algorithm to use')),
                 ],
                _('hg shrink [--revlog PATH]'))
 }
 
 if __name__ == "__main__":
     print "shrink-revlog.py is now an extension (see hg help extensions)"

mercurial/changegroup.py

@@ -1,258 +1,299 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 i18n import _
 from node import nullrev
-import mdiff, util
+import mdiff, util, dagutil
 import struct, os, bz2, zlib, tempfile
 
 _BUNDLE10_DELTA_HEADER = "20s20s20s20s"
 
 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 util.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 util.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)
 
 class nocompress(object):
     def compress(self, x):
         return x
     def flush(self):
         return ""
 
 bundletypes = {
     "": ("", nocompress), # only when using unbundle on ssh and old http servers
                           # since the unification ssh accepts a header but there
                           # is no capability signaling it.
     "HG10UN": ("HG10UN", nocompress),
     "HG10BZ": ("HG10", lambda: bz2.BZ2Compressor()),
     "HG10GZ": ("HG10GZ", lambda: zlib.compressobj()),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = ['HG10GZ', 'HG10BZ', 'HG10UN']
 
 def writebundle(cg, filename, bundletype):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     fh = None
     cleanup = None
     try:
         if filename:
             fh = open(filename, "wb")
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "wb")
         cleanup = filename
 
         header, compressor = bundletypes[bundletype]
         fh.write(header)
         z = compressor()
 
         # parse the changegroup data, otherwise we will block
         # in case of sshrepo because we 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, an empty chunkgroup is the end of the changegroup
         empty = False
         count = 0
         while not empty or count <= 2:
             empty = True
             count += 1
             while True:
                 chunk = getchunk(cg)
                 if not chunk:
                     break
                 empty = False
                 fh.write(z.compress(chunkheader(len(chunk))))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     fh.write(z.compress(chunk[pos:next]))
                     pos = next
             fh.write(z.compress(closechunk()))
         fh.write(z.flush())
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             os.unlink(cleanup)
 
 def decompressor(fh, alg):
     if alg == 'UN':
         return fh
     elif alg == 'GZ':
         def generator(f):
             zd = zlib.decompressobj()
             for chunk in util.filechunkiter(f):
                 yield zd.decompress(chunk)
     elif alg == 'BZ':
         def generator(f):
             zd = bz2.BZ2Decompressor()
             zd.decompress("BZ")
             for chunk in util.filechunkiter(f, 4096):
                 yield zd.decompress(chunk)
     else:
         raise util.Abort("unknown bundle compression '%s'" % alg)
     return util.chunkbuffer(generator(fh))
 
 class unbundle10(object):
     deltaheader = _BUNDLE10_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     def __init__(self, fh, alg):
         self._stream = decompressor(fh, alg)
         self._type = alg
         self.callback = None
     def compressed(self):
         return self._type != 'UN'
     def read(self, l):
         return self._stream.read(l)
     def seek(self, pos):
         return self._stream.seek(pos)
     def tell(self):
         return self._stream.tell()
     def close(self):
         return self._stream.close()
 
     def chunklength(self):
         d = readexactly(self._stream, 4)
         l = struct.unpack(">l", d)[0]
         if l <= 4:
             if l:
                 raise util.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 dict(filename=fname)
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         return node, p1, p2, deltabase, cs
 
     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 = self._deltaheader(header, prevnode)
         return dict(node=node, p1=p1, p2=p2, cs=cs,
                     deltabase=deltabase, delta=delta)
 
 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)
 
 def readbundle(fh, fname):
     header = readexactly(fh, 6)
 
     if not fname:
         fname = "stream"
         if not header.startswith('HG') and header.startswith('\0'):
             fh = headerlessfixup(fh, header)
             header = "HG10UN"
 
     magic, version, alg = header[0:2], header[2:4], header[4:6]
 
     if magic != 'HG':
         raise util.Abort(_('%s: not a Mercurial bundle') % fname)
     if version != '10':
         raise util.Abort(_('%s: unknown bundle version %s') % (fname, version))
     return unbundle10(fh, alg)
 
 class bundle10(object):
     deltaheader = _BUNDLE10_DELTA_HEADER
     def __init__(self):
         pass
     def start(self, lookup):
         self._lookup = lookup
     def close(self):
         return closechunk()
+
     def fileheader(self, fname):
         return chunkheader(len(fname)) + fname
+
+    def group(self, nodelist, revlog, reorder=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 we don't have any revisions touched by these changesets, bail
+        if len(nodelist) == 0:
+            yield self.close()
+            return
+
+        # for generaldelta revlogs, we linearize the revs; this will both be
+        # much quicker and generate a much smaller bundle
+        if (revlog._generaldelta and reorder is not False) or reorder:
+            dag = dagutil.revlogdag(revlog)
+            revs = set(revlog.rev(n) for n in nodelist)
+            revs = dag.linearize(revs)
+        else:
+            revs = sorted([revlog.rev(n) for n in nodelist])
+
+        # add the parent of the first rev
+        p = revlog.parentrevs(revs[0])[0]
+        revs.insert(0, p)
+
+        # build deltas
+        for r in xrange(len(revs) - 1):
+            prev, curr = revs[r], revs[r + 1]
+            for c in self.revchunk(revlog, curr, prev):
+                yield c
+
+        yield self.close()
+
+
     def revchunk(self, revlog, rev, prev):
         node = revlog.node(rev)
         p1, p2 = revlog.parentrevs(rev)
         base = prev
 
         prefix = ''
         if base == nullrev:
             delta = revlog.revision(node)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             delta = revlog.revdiff(base, rev)
         linknode = self._lookup(revlog, node)
         p1n, p2n = revlog.parents(node)
         basenode = revlog.node(base)
         meta = self.builddeltaheader(node, p1n, p2n, basenode, linknode)
         meta += prefix
         l = len(meta) + len(delta)
         yield chunkheader(l)
         yield meta
         yield delta
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode):
         # do nothing with basenode, it is implicitly the previous one in HG10
         return struct.pack(self.deltaheader, node, p1n, p2n, linknode)

mercurial/localrepo.py

@@ -1,2613 +1,2613 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 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 node import hex, nullid, short
 from i18n import _
 import peer, changegroup, subrepo, discovery, pushkey, obsolete, repoview
 import changelog, dirstate, filelog, manifest, context, bookmarks, phases
 import lock, transaction, store, encoding
 import scmutil, util, extensions, hook, error, revset
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 from lock import release
 import weakref, errno, os, time, inspect
 import branchmap
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
 class repofilecache(filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
 
     def __get__(self, repo, type=None):
         return super(repofilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(repofilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(repofilecache, self).__delete__(repo.unfiltered())
 
 class storecache(repofilecache):
     """filecache for files in the store"""
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 class unfilteredpropertycache(propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         return super(unfilteredpropertycache, self).__get__(repo.unfiltered())
 
 class filteredpropertycache(propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 MODERNCAPS = set(('lookup', 'branchmap', 'pushkey', 'known', 'getbundle'))
 LEGACYCAPS = MODERNCAPS.union(set(['changegroupsubset']))
 
 class localpeer(peer.peerrepository):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=MODERNCAPS):
         peer.peerrepository.__init__(self)
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
         self.requirements = repo.requirements
         self.supportedformats = repo.supportedformats
 
     def close(self):
         self._repo.close()
 
     def _capabilities(self):
         return self._caps
 
     def local(self):
         return self._repo
 
     def canpush(self):
         return True
 
     def url(self):
         return self._repo.url()
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def getbundle(self, source, heads=None, common=None):
         return self._repo.getbundle(source, heads=heads, common=common)
 
     # TODO We might want to move the next two calls into legacypeer and add
     # unbundle instead.
 
     def lock(self):
         return self._repo.lock()
 
     def addchangegroup(self, cg, source, url):
         return self._repo.addchangegroup(cg, source, url)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         localpeer.__init__(self, repo, caps=LEGACYCAPS)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def changegroup(self, basenodes, source):
         return self._repo.changegroup(basenodes, source)
 
     def changegroupsubset(self, bases, heads, source):
         return self._repo.changegroupsubset(bases, heads, source)
 
 class localrepository(object):
 
     supportedformats = set(('revlogv1', 'generaldelta'))
     supported = supportedformats | set(('store', 'fncache', 'shared',
                                         'dotencode'))
     openerreqs = set(('revlogv1', 'generaldelta'))
     requirements = ['revlogv1']
     filtername = None
 
     def _baserequirements(self, create):
         return self.requirements[:]
 
     def __init__(self, baseui, path=None, create=False):
         self.wvfs = scmutil.vfs(path, expandpath=True, realpath=True)
         self.wopener = self.wvfs
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
         self.auditor = scmutil.pathauditor(self.root, self._checknested)
         self.vfs = scmutil.vfs(self.path)
         self.opener = self.vfs
         self.baseui = baseui
         self.ui = baseui.copy()
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if not self.vfs.isdir():
             if create:
                 if not self.wvfs.exists():
                     self.wvfs.makedirs()
                 self.vfs.makedir(notindexed=True)
                 requirements = self._baserequirements(create)
                 if self.ui.configbool('format', 'usestore', True):
                     self.vfs.mkdir("store")
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                         if self.ui.configbool('format', 'dotencode', True):
                             requirements.append('dotencode')
                     # create an invalid changelog
                     self.vfs.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'generaldelta', False):
                     requirements.append("generaldelta")
                 requirements = set(requirements)
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 requirements = scmutil.readrequires(self.vfs, self.supported)
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = set()
 
         self.sharedpath = self.path
         try:
             vfs = scmutil.vfs(self.vfs.read("sharedpath").rstrip('\n'),
                               realpath=True)
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, scmutil.vfs)
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sopener = self.svfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self._applyrequirements(requirements)
         if create:
             self._writerequirements()
 
 
         self._branchcaches = {}
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
     def close(self):
         pass
 
     def _restrictcapabilities(self, caps):
         return caps
 
     def _applyrequirements(self, requirements):
         self.requirements = requirements
         self.sopener.options = dict((r, 1) for r in requirements
                                            if r in self.openerreqs)
 
     def _writerequirements(self):
         reqfile = self.opener("requires", "w")
         for r in sorted(self.requirements):
             reqfile.write("%s\n" % r)
         reqfile.close()
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name):
         """Return a filtered version of a repository"""
         # build a new class with the mixin and the current class
         # (possibly subclass of the repo)
         class proxycls(repoview.repoview, self.unfiltered().__class__):
             pass
         return proxycls(self, name)
 
     @repofilecache('bookmarks')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @repofilecache('bookmarks.current')
     def _bookmarkcurrent(self):
         return bookmarks.readcurrent(self)
 
     def bookmarkheads(self, bookmark):
         name = bookmark.split('@', 1)[0]
         heads = []
         for mark, n in self._bookmarks.iteritems():
             if mark.split('@', 1)[0] == name:
                 heads.append(n)
         return heads
 
     @storecache('phaseroots')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         store = obsolete.obsstore(self.sopener)
         if store and not obsolete._enabled:
             # message is rare enough to not be translated
             msg = 'obsolete feature not enabled but %i markers found!\n'
             self.ui.warn(msg % len(list(store)))
         return store
 
     @storecache('00changelog.i')
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         return c
 
     @storecache('00manifest.i')
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @repofilecache('dirstate')
     def dirstate(self):
         warned = [0]
         def validate(node):
             try:
                 self.changelog.rev(node)
                 return node
             except error.LookupError:
                 if not warned[0]:
                     warned[0] = True
                     self.ui.warn(_("warning: ignoring unknown"
                                    " working parent %s!\n") % short(node))
                 return nullid
 
         return dirstate.dirstate(self.opener, self.ui, self.root, validate)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Return a list of revisions matching the given revset'''
         expr = revset.formatspec(expr, *args)
         m = revset.match(None, expr)
         return [r for r in m(self, list(self))]
 
     def set(self, expr, *args):
         '''
         Yield a context for each matching revision, after doing arg
         replacement via revset.formatspec
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     @unfilteredmethod
     def _tag(self, names, node, message, local, user, date, extra={}):
         if isinstance(names, str):
             names = (names,)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if (self._tagscache.tagtypes and
                     name in self._tagscache.tagtypes):
                     old = self.tags().get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError, e:
             if e.errno != errno.ENOENT:
                 raise
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         fp.close()
 
         self.invalidatecaches()
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         if not local:
             for x in self.status()[:5]:
                 if '.hgtags' in x:
                     raise util.Abort(_('working copy of .hgtags is changed '
                                        '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 r = self.changelog.rev(n)
                 l.append((r, t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
 
     def _branchtip(self, heads):
         '''return the tipmost branch head in heads'''
         tip = heads[-1]
         for h in reversed(heads):
             if not self[h].closesbranch():
                 tip = h
                 break
         return tip
 
     def branchtip(self, branch):
         '''return the tip node for a given branch'''
         if branch not in self.branchmap():
             raise error.RepoLookupError(_("unknown branch '%s'") % branch)
         return self._branchtip(self.branchmap()[branch])
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             bt[bn] = self._branchtip(heads)
         return bt
 
     def lookup(self, key):
         return self[key].node()
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def known(self, nodes):
         nm = self.changelog.nodemap
         pc = self._phasecache
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or pc.phase(self, r) >= phases.secret)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def cancopy(self):
         return self.local() # so statichttprepo's override of local() works
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def setparents(self, p1, p2=nullid):
         copies = self.dirstate.setparents(p1, p2)
         pctx = self[p1]
         if copies:
             # Adjust copy records, the dirstate cannot do it, it
             # requires access to parents manifests. Preserve them
             # only for entries added to first parent.
             for f in copies:
                 if f not in pctx and copies[f] in pctx:
                     self.dirstate.copy(copies[f], f)
         if p2 == nullid:
             for f, s in sorted(self.dirstate.copies().items()):
                 if f not in pctx and s not in pctx:
                     self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return self.wvfs.islink(f)
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
         return self.filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wopener.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener.write(filename, data)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def transaction(self, desc):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found - run hg recover"))
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
 
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [vfs.join(undoname(x)) for vfs, x in self._journalfiles()]
 
     def _writejournal(self, desc):
         self.opener.write("journal.dirstate",
                           self.opener.tryread("dirstate"))
         self.opener.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.opener.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.opener.write("journal.bookmarks",
                           self.opener.tryread("bookmarks"))
         self.sopener.write("journal.phaseroots",
                            self.sopener.tryread("phaseroots"))
 
     def recover(self):
         lock = self.lock()
         try:
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"),
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 return self._rollback(dryrun, force)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force):
         ui = self.ui
         try:
             args = self.opener.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise util.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         transaction.rollback(self.sopener, self.sjoin('undo'), ui.warn)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks')
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots')
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             self.vfs.rename('undo.dirstate', 'dirstate')
             try:
                 branch = self.opener.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             self.dirstate.invalidate()
             parents = tuple([p.rev() for p in self.parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._branchcaches.clear()
         self.invalidatevolatilesets()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self):
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in self._filecache:
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
 
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def _afterlock(self, callback):
         """add a callback to the current repository lock.
 
         The callback will be executed on lock release."""
         l = self._lockref and self._lockref()
         if l:
             l.postrelease.append(callback)
         else:
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.store.write()
             if hasunfilteredcache(self, '_phasecache'):
                 self._phasecache.write()
             for k, ce in self._filecache.items():
                 if k == 'dirstate' or k not in self.__dict__:
                     continue
                 ce.refresh()
 
         l = self._lock(self.sjoin("lock"), wait, unlock,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.dirstate.write()
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.join("wlock"), wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self[None].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             commitsubs = set()
             newstate = wctx.substate.copy()
             # only manage subrepos and .hgsubstate if .hgsub is present
             if '.hgsub' in wctx:
                 # we'll decide whether to track this ourselves, thanks
                 if '.hgsubstate' in changes[0]:
                     changes[0].remove('.hgsubstate')
                 if '.hgsubstate' in changes[2]:
                     changes[2].remove('.hgsubstate')
 
                 # compare current state to last committed state
                 # build new substate based on last committed state
                 oldstate = wctx.p1().substate
                 for s in sorted(newstate.keys()):
                     if not match(s):
                         # ignore working copy, use old state if present
                         if s in oldstate:
                             newstate[s] = oldstate[s]
                             continue
                         if not force:
                             raise util.Abort(
                                 _("commit with new subrepo %s excluded") % s)
                     if wctx.sub(s).dirty(True):
                         if not self.ui.configbool('ui', 'commitsubrepos'):
                             raise util.Abort(
                                 _("uncommitted changes in subrepo %s") % s,
                                 hint=_("use --subrepos for recursive commit"))
                         subs.append(s)
                         commitsubs.add(s)
                     else:
                         bs = wctx.sub(s).basestate()
                         newstate[s] = (newstate[s][0], bs, newstate[s][2])
                         if oldstate.get(s, (None, None, None))[1] != bs:
                             subs.append(s)
 
                 # check for removed subrepos
                 for p in wctx.parents():
                     r = [s for s in p.substate if s not in newstate]
                     subs += [s for s in r if match(s)]
                 if subs:
                     if (not match('.hgsub') and
                         '.hgsub' in (wctx.modified() + wctx.added())):
                         raise util.Abort(
                             _("can't commit subrepos without .hgsub"))
                     changes[0].insert(0, '.hgsubstate')
 
             elif '.hgsub' in changes[2]:
                 # clean up .hgsubstate when .hgsub is removed
                 if ('.hgsubstate' in wctx and
                     '.hgsubstate' not in changes[0] + changes[1] + changes[2]):
                     changes[2].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     f = self.dirstate.normalize(f)
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
 
             if (not force and not extra.get("close") and not merge
                 and not cctx.files()
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             if merge and cctx.deleted():
                 raise util.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                        "(see hg help resolve)"))
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepo.writestate(self, newstate)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
         finally:
             wlock.release()
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             self.hook("commit", node=node, parent1=parent1, parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = list(ctx.removed())
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.files():
                 m1 = p1.manifest().copy()
                 m2 = p2.manifest()
 
                 # check in files
                 new = {}
                 changed = []
                 linkrev = len(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                                   changed)
                         m1.set(f, fctx.flags())
                     except OSError, inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError, inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                             raise
                         else:
                             removed.append(f)
 
                 # update manifest
                 m1.update(new)
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m1]
                 for f in drop:
                     del m1[f]
                 mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                        p2.manifestnode(), (new, drop))
                 files = changed + removed
             else:
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             # set the new commit is proper phase
             targetphase = phases.newcommitphase(self.ui)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.retractboundary(self, targetphase, [n])
             tr.close()
             branchmap.updatecache(self.filtered('served'))
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # update the 'served' branch cache to help read only server process
         # Thanks to branchcache collaboration this is done from the nearest
         # filtered subset and it is expected to be fast.
         branchmap.updatecache(self.filtered('served'))
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         """return status of files between two nodes or node and working
         directory.
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             if match.always():
                 return mf
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or matchmod.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 # 'f' may be a directory pattern from 'match.files()',
                 # so 'f not in ctx1' is not enough
                 if f not in ctx1 and f not in ctx1.dirs():
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             subrepos = []
             if '.hgsub' in self.dirstate:
                 subrepos = sorted(ctx2.substate)
             s = self.dirstate.status(match, subrepos, listignored,
                                      listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f])):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     if listclean:
                         clean += fixup
 
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             withflags = mf1.withflags() | mf2.withflags()
             for fn, mf2node in mf2.iteritems():
                 if fn in mf1:
                     if (fn not in deleted and
                         ((fn in withflags and mf1.flags(fn) != mf2.flags(fn)) or
                          (mf1[fn] != mf2node and
                           (mf2node or ctx1[fn].cmp(ctx2[fn]))))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 elif fn not in deleted:
                     added.append(fn)
             removed = mf1.keys()
 
         if working and modified and not self.dirstate._checklink:
             # Symlink placeholders may get non-symlink-like contents
             # via user error or dereferencing by NFS or Samba servers,
             # so we filter out any placeholders that don't look like a
             # symlink
             sane = []
             for f in modified:
                 if ctx2.flags(f) == 'l':
                     d = ctx2[f].data()
                     if len(d) >= 1024 or '\n' in d or util.binary(d):
                         self.ui.debug('ignoring suspect symlink placeholder'
                                       ' "%s"\n' % f)
                         continue
                 sane.append(f)
             modified = sane
 
         r = modified, added, removed, deleted, unknown, ignored, clean
 
         if listsubrepos:
             for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
                 if working:
                     rev2 = None
                 else:
                     rev2 = ctx2.substate[subpath][1]
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self.ui.status(_("skipping missing subrepository: %s\n")
                                    % subpath)
 
         for l in r:
             l.sort()
         return r
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if not self[h].closesbranch()]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def pull(self, remote, heads=None, force=False):
         # don't open transaction for nothing or you break future useful
         # rollback call
         tr = None
         trname = 'pull\n' + util.hidepassword(remote.url())
         lock = self.lock()
         try:
             tmp = discovery.findcommonincoming(self, remote, heads=heads,
                                                force=force)
             common, fetch, rheads = tmp
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 added = []
                 result = 0
             else:
                 tr = self.transaction(trname)
                 if heads is None and list(common) == [nullid]:
                     self.ui.status(_("requesting all changes\n"))
                 elif heads is None and remote.capable('changegroupsubset'):
                     # issue1320, avoid a race if remote changed after discovery
                     heads = rheads
 
                 if remote.capable('getbundle'):
                     cg = remote.getbundle('pull', common=common,
                                           heads=heads or rheads)
                 elif heads is None:
                     cg = remote.changegroup(fetch, 'pull')
                 elif not remote.capable('changegroupsubset'):
                     raise util.Abort(_("partial pull cannot be done because "
                                            "other repository doesn't support "
                                            "changegroupsubset."))
                 else:
                     cg = remote.changegroupsubset(fetch, heads, 'pull')
                 # we use unfiltered changelog here because hidden revision must
                 # be taken in account for phase synchronization. They may
                 # becomes public and becomes visible again.
                 cl = self.unfiltered().changelog
                 clstart = len(cl)
                 result = self.addchangegroup(cg, 'pull', remote.url())
                 clend = len(cl)
                 added = [cl.node(r) for r in xrange(clstart, clend)]
 
             # compute target subset
             if heads is None:
                 # We pulled every thing possible
                 # sync on everything common
                 subset = common + added
             else:
                 # We pulled a specific subset
                 # sync on this subset
                 subset = heads
 
             # Get remote phases data from remote
             remotephases = remote.listkeys('phases')
             publishing = bool(remotephases.get('publishing', False))
             if remotephases and not publishing:
                 # remote is new and unpublishing
                 pheads, _dr = phases.analyzeremotephases(self, subset,
                                                          remotephases)
                 phases.advanceboundary(self, phases.public, pheads)
                 phases.advanceboundary(self, phases.draft, subset)
             else:
                 # Remote is old or publishing all common changesets
                 # should be seen as public
                 phases.advanceboundary(self, phases.public, subset)
 
             def gettransaction():
                 if tr is None:
                     return self.transaction(trname)
                 return tr
 
             obstr = obsolete.syncpull(self, remote, gettransaction)
             if obstr is not None:
                 tr = obstr
 
             if tr is not None:
                 tr.close()
         finally:
             if tr is not None:
                 tr.release()
             lock.release()
 
         return result
 
     def checkpush(self, force, revs):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
         pass
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         '''Push outgoing changesets (limited by revs) from the current
         repository to remote. Return an integer:
           - None means nothing to push
           - 0 means HTTP error
           - 1 means we pushed and remote head count is unchanged *or*
             we have outgoing changesets but refused to push
           - other values as described by addchangegroup()
         '''
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if not remote.canpush():
             raise util.Abort(_("destination does not support push"))
         unfi = self.unfiltered()
         def localphasemove(nodes, phase=phases.public):
             """move <nodes> to <phase> in the local source repo"""
             if locallock is not None:
                 phases.advanceboundary(self, phase, nodes)
             else:
                 # repo is not locked, do not change any phases!
                 # Informs the user that phases should have been moved when
                 # applicable.
                 actualmoves = [n for n in nodes if phase < self[n].phase()]
                 phasestr = phases.phasenames[phase]
                 if actualmoves:
                     self.ui.status(_('cannot lock source repo, skipping local'
                                      ' %s phase update\n') % phasestr)
         # get local lock as we might write phase data
         locallock = None
         try:
             locallock = self.lock()
         except IOError, err:
             if err.errno != errno.EACCES:
                 raise
             # source repo cannot be locked.
             # We do not abort the push, but just disable the local phase
             # synchronisation.
             msg = 'cannot lock source repository: %s\n' % err
             self.ui.debug(msg)
         try:
             self.checkpush(force, revs)
             lock = None
             unbundle = remote.capable('unbundle')
             if not unbundle:
                 lock = remote.lock()
             try:
                 # discovery
                 fci = discovery.findcommonincoming
                 commoninc = fci(unfi, remote, force=force)
                 common, inc, remoteheads = commoninc
                 fco = discovery.findcommonoutgoing
                 outgoing = fco(unfi, remote, onlyheads=revs,
                                commoninc=commoninc, force=force)
 
 
                 if not outgoing.missing:
                     # nothing to push
                     scmutil.nochangesfound(unfi.ui, unfi, outgoing.excluded)
                     ret = None
                 else:
                     # something to push
                     if not force:
                         # if self.obsstore == False --> no obsolete
                         # then, save the iteration
                         if unfi.obsstore:
                             # this message are here for 80 char limit reason
                             mso = _("push includes obsolete changeset: %s!")
                             mst = "push includes %s changeset: %s!"
                             # plain versions for i18n tool to detect them
                             _("push includes unstable changeset: %s!")
                             _("push includes bumped changeset: %s!")
                             _("push includes divergent changeset: %s!")
                             # If we are to push if there is at least one
                             # obsolete or unstable changeset in missing, at
                             # least one of the missinghead will be obsolete or
                             # unstable. So checking heads only is ok
                             for node in outgoing.missingheads:
                                 ctx = unfi[node]
                                 if ctx.obsolete():
                                     raise util.Abort(mso % ctx)
                                 elif ctx.troubled():
                                     raise util.Abort(_(mst)
                                                      % (ctx.troubles()[0],
                                                         ctx))
                         discovery.checkheads(unfi, remote, outgoing,
                                              remoteheads, newbranch,
                                              bool(inc))
 
                     # create a changegroup from local
                     if revs is None and not outgoing.excluded:
                         # push everything,
                         # use the fast path, no race possible on push
                         bundler = changegroup.bundle10()
                         cg = self._changegroup(outgoing.missing, bundler,
                                                'push')
                     else:
                         cg = self.getlocalbundle('push', outgoing)
 
                     # apply changegroup to remote
                     if unbundle:
                         # local repo finds heads on server, finds out what
                         # revs it must push. once revs transferred, if server
                         # finds it has different heads (someone else won
                         # commit/push race), server aborts.
                         if force:
                             remoteheads = ['force']
                         # ssh: return remote's addchangegroup()
                         # http: return remote's addchangegroup() or 0 for error
                         ret = remote.unbundle(cg, remoteheads, 'push')
                     else:
                         # we return an integer indicating remote head count
                         # change
                         ret = remote.addchangegroup(cg, 'push', self.url())
 
                 if ret:
                     # push succeed, synchronize target of the push
                     cheads = outgoing.missingheads
                 elif revs is None:
                     # All out push fails. synchronize all common
                     cheads = outgoing.commonheads
                 else:
                     # I want cheads = heads(::missingheads and ::commonheads)
                     # (missingheads is revs with secret changeset filtered out)
                     #
                     # This can be expressed as:
                     #     cheads = ( (missingheads and ::commonheads)
                     #              + (commonheads and ::missingheads))"
                     #              )
                     #
                     # while trying to push we already computed the following:
                     #     common = (::commonheads)
                     #     missing = ((commonheads::missingheads) - commonheads)
                     #
                     # We can pick:
                     # * missingheads part of common (::commonheads)
                     common = set(outgoing.common)
                     cheads = [node for node in revs if node in common]
                     # and
                     # * commonheads parents on missing
                     revset = unfi.set('%ln and parents(roots(%ln))',
                                      outgoing.commonheads,
                                      outgoing.missing)
                     cheads.extend(c.node() for c in revset)
                 # even when we don't push, exchanging phase data is useful
                 remotephases = remote.listkeys('phases')
                 if (self.ui.configbool('ui', '_usedassubrepo', False)
                     and remotephases    # server supports phases
                     and ret is None # nothing was pushed
                     and remotephases.get('publishing', False)):
                     # When:
                     # - this is a subrepo push
                     # - and remote support phase
                     # - and no changeset was pushed
                     # - and remote is publishing
                     # We may be in issue 3871 case!
                     # We drop the possible phase synchronisation done by
                     # courtesy to publish changesets possibly locally draft
                     # on the remote.
                     remotephases = {'publishing': 'True'}
                 if not remotephases: # old server or public only repo
                     localphasemove(cheads)
                     # don't push any phase data as there is nothing to push
                 else:
                     ana = phases.analyzeremotephases(self, cheads, remotephases)
                     pheads, droots = ana
                     ### Apply remote phase on local
                     if remotephases.get('publishing', False):
                         localphasemove(cheads)
                     else: # publish = False
                         localphasemove(pheads)
                         localphasemove(cheads, phases.draft)
                     ### Apply local phase on remote
 
                     # Get the list of all revs draft on remote by public here.
                     # XXX Beware that revset break if droots is not strictly
                     # XXX root we may want to ensure it is but it is costly
                     outdated =  unfi.set('heads((%ln::%ln) and public())',
                                          droots, cheads)
                     for newremotehead in outdated:
                         r = remote.pushkey('phases',
                                            newremotehead.hex(),
                                            str(phases.draft),
                                            str(phases.public))
                         if not r:
                             self.ui.warn(_('updating %s to public failed!\n')
                                             % newremotehead)
                 self.ui.debug('try to push obsolete markers to remote\n')
                 obsolete.syncpush(self, remote)
             finally:
                 if lock is not None:
                     lock.release()
         finally:
             if locallock is not None:
                 locallock.release()
 
         self.ui.debug("checking for updated bookmarks\n")
         rb = remote.listkeys('bookmarks')
         for k in rb.keys():
             if k in unfi._bookmarks:
                 nr, nl = rb[k], hex(self._bookmarks[k])
                 if nr in unfi:
                     cr = unfi[nr]
                     cl = unfi[nl]
                     if bookmarks.validdest(unfi, cr, cl):
                         r = remote.pushkey('bookmarks', k, nr, nl)
                         if r:
                             self.ui.status(_("updating bookmark %s\n") % k)
                         else:
                             self.ui.warn(_('updating bookmark %s'
                                            ' failed!\n') % k)
 
         return ret
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug("list of changesets:\n")
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source):
         """Compute a changegroup consisting of all the nodes that are
         descendants of any of the bases 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 = self.changelog
         if not bases:
             bases = [nullid]
         csets, bases, heads = cl.nodesbetween(bases, heads)
         # We assume that all ancestors of bases are known
         common = cl.ancestors([cl.rev(n) for n in bases])
         bundler = changegroup.bundle10()
         return self._changegroupsubset(common, csets, heads, bundler, source)
 
     def getlocalbundle(self, source, outgoing):
         """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 = changegroup.bundle10()
         return self._changegroupsubset(outgoing.common,
                                        outgoing.missing,
                                        outgoing.missingheads,
                                        bundler,
                                        source)
 
     def getbundle(self, source, heads=None, common=None):
         """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.
         """
         cl = self.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 self.getlocalbundle(source,
                                    discovery.outgoing(cl, common, heads))
 
     @unfilteredmethod
     def _changegroupsubset(self, commonrevs, csets, heads, bundler, source):
 
         cl = self.changelog
         mf = self.manifest
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
         fstate = ['', {}]
         count = [0, 0]
 
         # can we go through the fast path ?
         heads.sort()
         if heads == sorted(self.heads()):
             return self._changegroup(csets, bundler, source)
 
         # slow path
         self.hook('preoutgoing', throw=True, source=source)
         self.changegroupinfo(csets, source)
 
         # filter any nodes that claim to be part of the known set
         def prune(revlog, missing):
             rr, rl = revlog.rev, revlog.linkrev
             return [n for n in missing
                     if rl(rr(n)) not in commonrevs]
 
         progress = self.ui.progress
         _bundling = _('bundling')
         _changesets = _('changesets')
         _manifests = _('manifests')
         _files = _('files')
 
         def lookup(revlog, x):
             if revlog == cl:
                 c = cl.read(x)
                 changedfiles.update(c[3])
                 mfs.setdefault(c[0], x)
                 count[0] += 1
                 progress(_bundling, count[0],
                          unit=_changesets, total=count[1])
                 return x
             elif revlog == mf:
                 clnode = mfs[x]
                 mdata = mf.readfast(x)
                 for f, n in mdata.iteritems():
                     if f in changedfiles:
                         fnodes[f].setdefault(n, clnode)
                 count[0] += 1
                 progress(_bundling, count[0],
                          unit=_manifests, total=count[1])
                 return clnode
             else:
                 progress(_bundling, count[0], item=fstate[0],
                          unit=_files, total=count[1])
                 return fstate[1][x]
 
         bundler.start(lookup)
         reorder = self.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
 
         def gengroup():
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             count[:] = [0, len(csets)]
-            for chunk in cl.group(csets, bundler, reorder=reorder):
+            for chunk in bundler.group(csets, cl, reorder=reorder):
                 yield chunk
             progress(_bundling, None)
 
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             for f in changedfiles:
                 fnodes[f] = {}
             count[:] = [0, len(mfs)]
-            for chunk in mf.group(prune(mf, mfs), bundler, reorder=reorder):
+            for chunk in bundler.group(prune(mf, mfs), mf, reorder=reorder):
                 yield chunk
             progress(_bundling, None)
 
             mfs.clear()
 
             # Go through all our files in order sorted by name.
             count[:] = [0, len(changedfiles)]
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s")
                                      % fname)
                 fstate[0] = fname
                 fstate[1] = fnodes.pop(fname, {})
 
                 nodelist = prune(filerevlog, fstate[1])
                 if nodelist:
                     count[0] += 1
                     yield bundler.fileheader(fname)
-                    for chunk in filerevlog.group(nodelist, bundler, reorder):
+                    for chunk in bundler.group(nodelist, filerevlog, reorder):
                         yield chunk
 
             # Signal that no more groups are left.
             yield bundler.close()
             progress(_bundling, None)
 
             if csets:
                 self.hook('outgoing', node=hex(csets[0]), source=source)
 
         return changegroup.unbundle10(util.chunkbuffer(gengroup()), 'UN')
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     @unfilteredmethod
     def _changegroup(self, nodes, bundler, source):
         """Compute the changegroup of all nodes that we have that a recipient
         doesn't.  Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         nodes is the set of nodes to send"""
 
         cl = self.changelog
         mf = self.manifest
         mfs = {}
         changedfiles = set()
         fstate = ['']
         count = [0, 0]
 
         self.hook('preoutgoing', throw=True, source=source)
         self.changegroupinfo(nodes, source)
 
         revset = set([cl.rev(n) for n in nodes])
 
         def gennodelst(log):
             ln, llr = log.node, log.linkrev
             return [ln(r) for r in log if llr(r) in revset]
 
         progress = self.ui.progress
         _bundling = _('bundling')
         _changesets = _('changesets')
         _manifests = _('manifests')
         _files = _('files')
 
         def lookup(revlog, x):
             if revlog == cl:
                 c = cl.read(x)
                 changedfiles.update(c[3])
                 mfs.setdefault(c[0], x)
                 count[0] += 1
                 progress(_bundling, count[0],
                          unit=_changesets, total=count[1])
                 return x
             elif revlog == mf:
                 count[0] += 1
                 progress(_bundling, count[0],
                          unit=_manifests, total=count[1])
                 return cl.node(revlog.linkrev(revlog.rev(x)))
             else:
                 progress(_bundling, count[0], item=fstate[0],
                     total=count[1], unit=_files)
                 return cl.node(revlog.linkrev(revlog.rev(x)))
 
         bundler.start(lookup)
         reorder = self.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
 
         def gengroup():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
 
             count[:] = [0, len(nodes)]
-            for chunk in cl.group(nodes, bundler, reorder=reorder):
+            for chunk in bundler.group(nodes, cl, reorder=reorder):
                 yield chunk
             progress(_bundling, None)
 
             count[:] = [0, len(mfs)]
-            for chunk in mf.group(gennodelst(mf), bundler, reorder=reorder):
+            for chunk in bundler.group(gennodelst(mf), mf, reorder=reorder):
                 yield chunk
             progress(_bundling, None)
 
             count[:] = [0, len(changedfiles)]
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s")
                                      % fname)
                 fstate[0] = fname
                 nodelist = gennodelst(filerevlog)
                 if nodelist:
                     count[0] += 1
                     yield bundler.fileheader(fname)
-                    for chunk in filerevlog.group(nodelist, bundler, reorder):
+                    for chunk in bundler.group(nodelist, filerevlog, reorder):
                         yield chunk
             yield bundler.close()
             progress(_bundling, None)
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return changegroup.unbundle10(util.chunkbuffer(gengroup()), 'UN')
 
     @unfilteredmethod
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """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
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
         efiles = set()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = cl.heads()
 
         tr = self.transaction("\n".join([srctype, util.hidepassword(url)]))
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 step = _('changesets')
                 count = 1
                 ui = self.ui
                 total = None
                 def __call__(self):
                     self.ui.progress(self.step, self.count, unit=_('chunks'),
                                      total=self.total)
                     self.count += 1
             pr = prog()
             source.callback = pr
 
             source.changelogheader()
             srccontent = cl.addgroup(source, csmap, trp)
             if not (srccontent or emptyok):
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
             for c in xrange(clstart, clend):
                 efiles.update(self[c].files())
             efiles = len(efiles)
             self.ui.progress(_('changesets'), None)
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             pr.step = _('manifests')
             pr.count = 1
             pr.total = changesets # manifests <= changesets
             # 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
             source.manifestheader()
             self.manifest.addgroup(source, revmap, trp)
             self.ui.progress(_('manifests'), None)
 
             needfiles = {}
             if self.ui.configbool('server', 'validate', default=False):
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfest = self.changelog.read(self.changelog.node(cset))[0]
                     mfest = self.manifest.readdelta(mfest)
                     # store file nodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             pr.step = _('files')
             pr.count = 1
             pr.total = efiles
             source.callback = None
 
             while True:
                 chunkdata = source.filelogheader()
                 if not chunkdata:
                     break
                 f = chunkdata["filename"]
                 self.ui.debug("adding %s revisions\n" % f)
                 pr()
                 fl = self.file(f)
                 o = len(fl)
                 if not fl.addgroup(source, revmap, trp):
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
                 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 util.Abort(
                                 _("received spurious file revlog entry"))
                     if not needs:
                         del needfiles[f]
             self.ui.progress(_('files'), None)
 
             for f, needs in needfiles.iteritems():
                 fl = self.file(f)
                 for n in needs:
                     try:
                         fl.rev(n)
                     except error.LookupError:
                         raise util.Abort(
                             _('missing file data for %s:%s - run hg verify') %
                             (f, hex(n)))
 
             dh = 0
             if oldheads:
                 heads = cl.heads()
                 dh = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and self[h].closesbranch():
                         dh -= 1
             htext = ""
             if dh:
                 htext = _(" (%+d heads)") % dh
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
             self.invalidatevolatilesets()
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             added = [cl.node(r) for r in xrange(clstart, clend)]
             publishing = self.ui.configbool('phases', 'publish', True)
             if srctype == 'push':
                 # Old server can not push the boundary themself.
                 # New server won't push the boundary if changeset already
                 # existed locally as secrete
                 #
                 # We should not use added here but the list of all change in
                 # the bundle
                 if publishing:
                     phases.advanceboundary(self, phases.public, srccontent)
                 else:
                     phases.advanceboundary(self, phases.draft, srccontent)
                     phases.retractboundary(self, phases.draft, added)
             elif srctype != 'strip':
                 # publishing only alter behavior during push
                 #
                 # strip should not touch boundary at all
                 phases.retractboundary(self, phases.draft, added)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
 
             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(self.filtered('served'))
                 def runhooks():
                     # forcefully update the on-disk branch cache
                     self.ui.debug("updating the branch cache\n")
                     self.hook("changegroup", node=hex(cl.node(clstart)),
                               source=srctype, url=url)
 
                     for n in added:
                         self.hook("incoming", node=hex(n), source=srctype,
                                   url=url)
 
                     newheads = [h for h in self.heads() if h not in oldheads]
                     self.ui.log("incoming",
                                 "%s incoming changes - new heads: %s\n",
                                 len(added),
                                 ', '.join([hex(c[:6]) for c in newheads]))
                 self._afterlock(runhooks)
 
         finally:
             tr.release()
         # never return 0 here:
         if dh < 0:
             return dh - 1
         else:
             return dh + 1
 
     def stream_in(self, remote, requirements):
         lock = self.lock()
         try:
             # Save remote branchmap. We will use it later
             # to speed up branchcache creation
             rbranchmap = None
             if remote.capable("branchmap"):
                 rbranchmap = remote.branchmap()
 
             fp = remote.stream_out()
             l = fp.readline()
             try:
                 resp = int(l)
             except ValueError:
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             if resp == 1:
                 raise util.Abort(_('operation forbidden by server'))
             elif resp == 2:
                 raise util.Abort(_('locking the remote repository failed'))
             elif resp != 0:
                 raise util.Abort(_('the server sent an unknown error code'))
             self.ui.status(_('streaming all changes\n'))
             l = fp.readline()
             try:
                 total_files, total_bytes = map(int, l.split(' ', 1))
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('unexpected response from remote server:'), l)
             self.ui.status(_('%d files to transfer, %s of data\n') %
                            (total_files, util.bytecount(total_bytes)))
             handled_bytes = 0
             self.ui.progress(_('clone'), 0, total=total_bytes)
             start = time.time()
             for i in xrange(total_files):
                 # XXX doesn't support '\n' or '\r' in filenames
                 l = fp.readline()
                 try:
                     name, size = l.split('\0', 1)
                     size = int(size)
                 except (ValueError, TypeError):
                     raise error.ResponseError(
                         _('unexpected response from remote server:'), l)
                 if self.ui.debugflag:
                     self.ui.debug('adding %s (%s)\n' %
                                   (name, util.bytecount(size)))
                 # for backwards compat, name was partially encoded
                 ofp = self.sopener(store.decodedir(name), 'w')
                 for chunk in util.filechunkiter(fp, limit=size):
                     handled_bytes += len(chunk)
                     self.ui.progress(_('clone'), handled_bytes,
                                      total=total_bytes)
                     ofp.write(chunk)
                 ofp.close()
             elapsed = time.time() - start
             if elapsed <= 0:
                 elapsed = 0.001
             self.ui.progress(_('clone'), None)
             self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                            (util.bytecount(total_bytes), elapsed,
                             util.bytecount(total_bytes / elapsed)))
 
             # new requirements = old non-format requirements +
             #                    new format-related
             # requirements from the streamed-in repository
             requirements.update(set(self.requirements) - self.supportedformats)
             self._applyrequirements(requirements)
             self._writerequirements()
 
             if rbranchmap:
                 rbheads = []
                 for bheads in rbranchmap.itervalues():
                     rbheads.extend(bheads)
 
                 if rbheads:
                     rtiprev = max((int(self.changelog.rev(node))
                             for node in rbheads))
                     cache = branchmap.branchcache(rbranchmap,
                                                   self[rtiprev].node(),
                                                   rtiprev)
                     # Try to stick it as low as possible
                     # filter above served are unlikely to be fetch from a clone
                     for candidate in ('base', 'immutable', 'served'):
                         rview = self.filtered(candidate)
                         if cache.validfor(rview):
                             self._branchcaches[candidate] = cache
                             cache.write(rview)
                             break
             self.invalidate()
             return len(self.heads()) + 1
         finally:
             lock.release()
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if not stream:
             # if the server explicitly prefers to stream (for fast LANs)
             stream = remote.capable('stream-preferred')
 
         if stream and not heads:
             # 'stream' means remote revlog format is revlogv1 only
             if remote.capable('stream'):
                 return self.stream_in(remote, set(('revlogv1',)))
             # otherwise, 'streamreqs' contains the remote revlog format
             streamreqs = remote.capable('streamreqs')
             if streamreqs:
                 streamreqs = set(streamreqs.split(','))
                 # if we support it, stream in and adjust our requirements
                 if not streamreqs - self.supportedformats:
                     return self.stream_in(remote, streamreqs)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         self.hook('prepushkey', throw=True, namespace=namespace, key=key,
                   old=old, new=new)
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                   ret=ret)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
     def savecommitmessage(self, text):
         fp = self.opener('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True

mercurial/revlog.py

@@ -1,1340 +1,1302 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 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.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 # import stuff from node for others to import from revlog
 from node import bin, hex, nullid, nullrev
 from i18n import _
-import ancestor, mdiff, parsers, error, util, dagutil
+import ancestor, mdiff, parsers, error, util
 import struct, zlib, errno
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 _sha = util.sha1
 
 # revlog header flags
 REVLOGV0 = 0
 REVLOGNG = 1
 REVLOGNGINLINEDATA = (1 << 16)
 REVLOGGENERALDELTA = (1 << 17)
 REVLOG_DEFAULT_FLAGS = REVLOGNGINLINEDATA
 REVLOG_DEFAULT_FORMAT = REVLOGNG
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGNG_FLAGS = REVLOGNGINLINEDATA | REVLOGGENERALDELTA
 
 # revlog index flags
 REVIDX_KNOWN_FLAGS = 0
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 RevlogError = error.RevlogError
 LookupError = error.LookupError
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     return long(long(offset) << 16 | type)
 
 nullhash = _sha(nullid)
 
 def hash(text, p1, p2):
     """generate a hash from the given text and its parent hashes
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         l = [p1, p2]
         l.sort()
         s = _sha(l[0])
         s.update(l[1])
     s.update(text)
     return s.digest()
 
 def decompress(bin):
     """ decompress the given input """
     if not bin:
         return bin
     t = bin[0]
     if t == '\0':
         return bin
     if t == 'x':
         try:
             return _decompress(bin)
         except zlib.error, e:
             raise RevlogError(_("revlog decompress error: %s") % str(e))
     if t == 'u':
         return bin[1:]
     raise RevlogError(_("unknown compression type %r") % t)
 
 # index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 32 bytes: parent 1 nodeid
 # 32 bytes: parent 2 nodeid
 # 32 bytes: nodeid
 indexformatv0 = ">4l20s20s20s"
 v0shaoffset = 56
 
 class revlogoldio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatv0)
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap =  {nullid: nullrev}
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = _unpack(indexformatv0, cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         # add the magic null revision at -1
         index.append((0, 0, 0, -1, -1, -1, -1, nullid))
 
         return index, nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise RevlogError(_("index entry flags need RevlogNG"))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return _pack(indexformatv0, *e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = ">Qiiiiii20s12x"
 ngshaoffset = 32
 versionformat = ">I"
 
 class revlogio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatng)
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
         p = _pack(indexformatng, *entry)
         if rev == 0:
             p = _pack(versionformat, version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
     """
     def __init__(self, opener, indexfile):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = indexfile[:-2] + ".d"
         self.opener = opener
         self._cache = None
         self._basecache = (0, 0)
         self._chunkcache = (0, '')
         self.index = []
         self._pcache = {}
         self._nodecache = {nullid: nullrev}
         self._nodepos = None
 
         v = REVLOG_DEFAULT_VERSION
         opts = getattr(opener, 'options', None)
         if opts is not None:
             if 'revlogv1' in opts:
                 if 'generaldelta' in opts:
                     v |= REVLOGGENERALDELTA
             else:
                 v = 0
 
         i = ''
         self._initempty = True
         try:
             f = self.opener(self.indexfile)
             i = f.read()
             f.close()
             if len(i) > 0:
                 v = struct.unpack(versionformat, i[:4])[0]
                 self._initempty = False
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.version = v
         self._inline = v & REVLOGNGINLINEDATA
         self._generaldelta = v & REVLOGGENERALDELTA
         flags = v & ~0xFFFF
         fmt = v & 0xFFFF
         if fmt == REVLOGV0 and flags:
             raise RevlogError(_("index %s unknown flags %#04x for format v0")
                               % (self.indexfile, flags >> 16))
         elif fmt == REVLOGNG and flags & ~REVLOGNG_FLAGS:
             raise RevlogError(_("index %s unknown flags %#04x for revlogng")
                               % (self.indexfile, flags >> 16))
         elif fmt > REVLOGNG:
             raise RevlogError(_("index %s unknown format %d")
                               % (self.indexfile, fmt))
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(i, self._inline)
         except (ValueError, IndexError):
             raise RevlogError(_("index %s is corrupted") % (self.indexfile))
         self.index, nodemap, self._chunkcache = d
         if nodemap is not None:
             self.nodemap = self._nodecache = nodemap
         if not self._chunkcache:
             self._chunkclear()
 
     def tip(self):
         return self.node(len(self.index) - 2)
     def __len__(self):
         return len(self.index) - 1
     def __iter__(self):
         return iter(xrange(len(self)))
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         step = 1
         if stop is not None:
             if start > stop:
                 step = -1
             stop += step
         else:
             stop = len(self)
         return xrange(start, stop, step)
 
     @util.propertycache
     def nodemap(self):
         self.rev(self.node(0))
         return self._nodecache
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def clearcaches(self):
         try:
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except RevlogError:
             # parsers.c radix tree lookup failed
             raise LookupError(node, self.indexfile, _('no node'))
         except KeyError:
             # pure python cache lookup failed
             n = self._nodecache
             i = self.index
             p = self._nodepos
             if p is None:
                 p = len(i) - 2
             for r in xrange(p, -1, -1):
                 v = i[r][7]
                 n[v] = r
                 if v == node:
                     self._nodepos = r - 1
                     return r
             raise LookupError(node, self.indexfile, _('no node'))
 
     def node(self, rev):
         return self.index[rev][7]
     def linkrev(self, rev):
         return self.index[rev][4]
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
     def parentrevs(self, rev):
         return self.index[rev][5:7]
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
     def end(self, rev):
         return self.start(rev) + self.length(rev)
     def length(self, rev):
         return self.index[rev][1]
     def chainbase(self, rev):
         index = self.index
         base = index[rev][3]
         while base != rev:
             rev = base
             base = index[rev][3]
         return base
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(self.node(rev))
         return len(t)
     size = rawsize
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse topological order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         return ancestor.lazyancestors(self, revs, stoprev=stoprev,
                                       inclusive=inclusive)
 
     def descendants(self, revs):
         """Generate the descendants of 'revs' in revision order.
 
         Yield a sequence of revision numbers starting with a child of
         some rev in revs, i.e., each revision is *not* considered a
         descendant of itself.  Results are ordered by revision number (a
         topological sort)."""
         first = min(revs)
         if first == nullrev:
             for i in self:
                 yield i
             return
 
         seen = set(revs)
         for i in self.revs(start=first + 1):
             for x in self.parentrevs(i):
                 if x != nullrev and x in seen:
                     seen.add(i)
                     yield i
                     break
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         has = set(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = util.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(r) for r in missing]
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         return ancestor.missingancestors(heads, common, self.parentrevs)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         return [self.node(r) for r in
                 ancestor.missingancestors(heads, common, self.parentrevs)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [n for n in roots if n in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(n) for n in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [n for n, flag in heads.iteritems() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self):
         try:
             return self.index.headrevs()
         except AttributeError:
             return self._headrevs()
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = set([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = set((startrev,))
         heads = set((startrev,))
 
         parentrevs = self.parentrevs
         for r in self.revs(start=startrev + 1):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable.add(r)
                     heads.add(r)
                 if p in heads and p not in stoprevs:
                     heads.remove(p)
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def descendant(self, start, end):
         if start == nullrev:
             return True
         for i in self.descendants([start]):
             if i == end:
                 return True
             elif i > end:
                 break
         return False
 
     def ancestor(self, a, b):
         """calculate the least common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if str(rev) != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, LookupError):
                 pass
 
     def _partialmatch(self, id):
         try:
             return self.index.partialmatch(id)
         except RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             raise LookupError(id, self.indexfile, _("ambiguous identifier"))
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) < 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[:l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [n for n in nl if hex(n).startswith(id)]
                 if len(nl) > 0:
                     if len(nl) == 1:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise LookupError(id, self.indexfile,
                                       _('ambiguous identifier'))
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise LookupError(id, self.indexfile, _('no match found'))
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return hash(text, p1, p2) != node
 
     def _addchunk(self, offset, data):
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _loadchunk(self, offset, length):
         if self._inline:
             df = self.opener(self.indexfile)
         else:
             df = self.opener(self.datafile)
 
         readahead = max(65536, length)
         df.seek(offset)
         d = df.read(readahead)
         df.close()
         self._addchunk(offset, d)
         if readahead > length:
             return util.buffer(d, 0, length)
         return d
 
     def _getchunk(self, offset, length):
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._loadchunk(offset, length)
 
     def _chunkraw(self, startrev, endrev):
         start = self.start(startrev)
         length = self.end(endrev) - start
         if self._inline:
             start += (startrev + 1) * self._io.size
         return self._getchunk(start, length)
 
     def _chunk(self, rev):
         return decompress(self._chunkraw(rev, rev))
 
     def _chunkbase(self, rev):
         return self._chunk(rev)
 
     def _chunkclear(self):
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return str(self._chunk(rev2))
 
         return mdiff.textdiff(self.revision(rev1),
                               self.revision(rev2))
 
     def revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         cachedrev = None
         if node == nullid:
             return ""
         if self._cache:
             if self._cache[0] == node:
                 return self._cache[2]
             cachedrev = self._cache[1]
 
         # look up what we need to read
         text = None
         if rev is None:
             rev = self.rev(node)
 
         # check rev flags
         if self.flags(rev) & ~REVIDX_KNOWN_FLAGS:
             raise RevlogError(_('incompatible revision flag %x') %
                               (self.flags(rev) & ~REVIDX_KNOWN_FLAGS))
 
         # build delta chain
         chain = []
         index = self.index # for performance
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != cachedrev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
         chain.reverse()
         base = iterrev
 
         if iterrev == cachedrev:
             # cache hit
             text = self._cache[2]
 
         # drop cache to save memory
         self._cache = None
 
         self._chunkraw(base, rev)
         if text is None:
             text = str(self._chunkbase(base))
 
         bins = [self._chunk(r) for r in chain]
         text = mdiff.patches(text, bins)
 
         text = self._checkhash(text, node, rev)
 
         self._cache = (node, rev, text)
         return text
 
     def _checkhash(self, text, node, rev):
         p1, p2 = self.parents(node)
         if node != hash(text, p1, p2):
             raise RevlogError(_("integrity check failed on %s:%d")
                               % (self.indexfile, rev))
         return text
 
     def checkinlinesize(self, tr, fp=None):
         if not self._inline or (self.start(-2) + self.length(-2)) < _maxinline:
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise RevlogError(_("%s not found in the transaction")
                               % self.indexfile)
 
         trindex = trinfo[2]
         dataoff = self.start(trindex)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
 
         df = self.opener(self.datafile, 'w')
         try:
             for r in self:
                 df.write(self._chunkraw(r, r))
         finally:
             df.close()
 
         fp = self.opener(self.indexfile, 'w', atomictemp=True)
         self.version &= ~(REVLOGNGINLINEDATA)
         self._inline = False
         for i in self:
             e = self._io.packentry(self.index[i], self.node, self.version, i)
             fp.write(e)
 
         # if we don't call close, the temp file will never replace the
         # real index
         fp.close()
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         """
         node = hash(text, p1, p2)
         if node in self.nodemap:
             return node
 
         dfh = None
         if not self._inline:
             dfh = self.opener(self.datafile, "a")
         ifh = self.opener(self.indexfile, "a+")
         try:
             return self._addrevision(node, text, transaction, link, p1, p2,
                                      cachedelta, ifh, dfh)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, text):
         """ generate a possibly-compressed representation of text """
         if not text:
             return ("", text)
         l = len(text)
         bin = None
         if l < 44:
             pass
         elif l > 1000000:
             # zlib makes an internal copy, thus doubling memory usage for
             # large files, so lets do this in pieces
             z = zlib.compressobj()
             p = []
             pos = 0
             while pos < l:
                 pos2 = pos + 2**20
                 p.append(z.compress(text[pos:pos2]))
                 pos = pos2
             p.append(z.flush())
             if sum(map(len, p)) < l:
                 bin = "".join(p)
         else:
             bin = _compress(text)
         if bin is None or len(bin) > l:
             if text[0] == '\0':
                 return ("", text)
             return ('u', text)
         return ("", bin)
 
     def _addrevision(self, node, text, transaction, link, p1, p2,
                      cachedelta, ifh, dfh):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
         invariants:
         - text is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         btext = [text]
         def buildtext():
             if btext[0] is not None:
                 return btext[0]
             # flush any pending writes here so we can read it in revision
             if dfh:
                 dfh.flush()
             ifh.flush()
             basetext = self.revision(self.node(cachedelta[0]))
             btext[0] = mdiff.patch(basetext, cachedelta[1])
             chk = hash(btext[0], p1, p2)
             if chk != node:
                 raise RevlogError(_("consistency error in delta"))
             return btext[0]
 
         def builddelta(rev):
             # can we use the cached delta?
             if cachedelta and cachedelta[0] == rev:
                 delta = cachedelta[1]
             else:
                 t = buildtext()
                 ptext = self.revision(self.node(rev))
                 delta = mdiff.textdiff(ptext, t)
             data = self.compress(delta)
             l = len(data[1]) + len(data[0])
             if basecache[0] == rev:
                 chainbase = basecache[1]
             else:
                 chainbase = self.chainbase(rev)
             dist = l + offset - self.start(chainbase)
             if self._generaldelta:
                 base = rev
             else:
                 base = chainbase
             return dist, l, data, base, chainbase
 
         curr = len(self)
         prev = curr - 1
         base = chainbase = curr
         offset = self.end(prev)
         flags = 0
         d = None
         basecache = self._basecache
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # should we try to build a delta?
         if prev != nullrev:
             if self._generaldelta:
                 if p1r >= basecache[1]:
                     d = builddelta(p1r)
                 elif p2r >= basecache[1]:
                     d = builddelta(p2r)
                 else:
                     d = builddelta(prev)
             else:
                 d = builddelta(prev)
             dist, l, data, base, chainbase = d
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if text is None:
             textlen = mdiff.patchedsize(self.rawsize(cachedelta[0]),
                                         cachedelta[1])
         else:
             textlen = len(text)
         if d is None or dist > textlen * 2:
             text = buildtext()
             data = self.compress(text)
             l = len(data[1]) + len(data[0])
             base = chainbase = curr
 
         e = (offset_type(offset, flags), l, textlen,
              base, link, p1r, p2r, node)
         self.index.insert(-1, e)
         self.nodemap[node] = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             dfh.flush()
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self.checkinlinesize(transaction, ifh)
 
         if type(text) == str: # only accept immutable objects
             self._cache = (node, curr, text)
         self._basecache = (curr, chainbase)
         return node
 
-    def group(self, nodelist, bundler, reorder=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 we don't have any revisions touched by these changesets, bail
-        if len(nodelist) == 0:
-            yield bundler.close()
-            return
-
-        # for generaldelta revlogs, we linearize the revs; this will both be
-        # much quicker and generate a much smaller bundle
-        if (self._generaldelta and reorder is not False) or reorder:
-            dag = dagutil.revlogdag(self)
-            revs = set(self.rev(n) for n in nodelist)
-            revs = dag.linearize(revs)
-        else:
-            revs = sorted([self.rev(n) for n in nodelist])
-
-        # add the parent of the first rev
-        p = self.parentrevs(revs[0])[0]
-        revs.insert(0, p)
-
-        # build deltas
-        for r in xrange(len(revs) - 1):
-            prev, curr = revs[r], revs[r + 1]
-            for c in bundler.revchunk(self, curr, prev):
-                yield c
-
-        yield bundler.close()
-
     def addgroup(self, bundle, linkmapper, transaction):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
         """
 
         # track the base of the current delta log
         content = []
         node = None
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self.opener(self.indexfile, "a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self.opener(self.datafile, "a")
 
         try:
             # loop through our set of deltas
             chain = None
             while True:
                 chunkdata = bundle.deltachunk(chain)
                 if not chunkdata:
                     break
                 node = chunkdata['node']
                 p1 = chunkdata['p1']
                 p2 = chunkdata['p2']
                 cs = chunkdata['cs']
                 deltabase = chunkdata['deltabase']
                 delta = chunkdata['delta']
 
                 content.append(node)
 
                 link = linkmapper(cs)
                 if node in self.nodemap:
                     # this can happen if two branches make the same change
                     chain = node
                     continue
 
                 for p in (p1, p2):
                     if p not in self.nodemap:
                         raise LookupError(p, self.indexfile,
                                           _('unknown parent'))
 
                 if deltabase not in self.nodemap:
                     raise LookupError(deltabase, self.indexfile,
                                       _('unknown delta base'))
 
                 baserev = self.rev(deltabase)
                 chain = self._addrevision(node, None, transaction, link,
                                           p1, p2, (baserev, delta), ifh, dfh)
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self.opener(self.datafile, "a")
                     ifh = self.opener(self.indexfile, "a")
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
         return content
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         for rev in self:
             if self.index[rev][4] >= minlink:
                 break
         else:
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._cache = None
         self._chunkclear()
         for x in xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
 
     def checksize(self):
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             f = self.opener(self.datafile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             dd = actual - expected
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res