changegroup: introduce "raw" versions of some commands

The commands getchangegroup, getlocalchangegroup and getsubset now each
have a version ending in -raw. The raw versions return the chunk generator
from the changegroup packer directly, without wrapping it in a chunkbuffer
and unpacker. This avoids extra chunkbuffers in the bundle2 code path.

Also, the raw versions can be extended to support alternative packers
in the future, to be used from bundle2.

mercurial/changegroup.py

@@ -1,768 +1,793 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.
 
 import weakref
 from i18n import _
 from node import nullrev, nullid, hex, short
 import mdiff, util, dagutil
 import struct, os, bz2, zlib, tempfile
 import discovery, error, phases, branchmap
 
 _CHANGEGROUPV1_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, vfs=None):
     """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:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 fh = open(filename, "wb")
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "wb")
         cleanup = filename
 
         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
         for chunk in cg.getchunks():
             fh.write(z.compress(chunk))
         fh.write(z.flush())
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 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 cg1unpacker(object):
     deltaheader = _CHANGEGROUPV1_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 {'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 {'node': node, 'p1': p1, 'p2': p2, 'cs': cs,
                 'deltabase': deltabase, 'delta': delta}
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # an empty chunkgroup is the end of the changegroup
         # a changegroup has at least 2 chunkgroups (changelog and manifest).
         # after that, 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(self)
                 if not chunk:
                     break
                 empty = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 class cg1packer(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     def __init__(self, repo, bundlecaps=None):
         """Given a source repo, construct a bundler.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle.
         """
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         self._changelog = repo.changelog
         self._manifest = repo.manifest
         reorder = repo.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
         self._repo = repo
         self._reorder = reorder
         self._progress = repo.ui.progress
     def close(self):
         return closechunk()
 
     def fileheader(self, fname):
         return chunkheader(len(fname)) + fname
 
     def group(self, nodelist, revlog, lookup, units=None, 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 units is not None, progress detail will be generated, units specifies
         the type of revlog that is touched (changelog, manifest, etc.).
         """
         # if we don't have any revisions touched by these changesets, bail
         if len(nodelist) == 0:
             yield self.close()
             return
 
         # 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
         total = len(revs) - 1
         msgbundling = _('bundling')
         for r in xrange(len(revs) - 1):
             if units is not None:
                 self._progress(msgbundling, r + 1, unit=units, total=total)
             prev, curr = revs[r], revs[r + 1]
             linknode = lookup(revlog.node(curr))
             for c in self.revchunk(revlog, curr, prev, linknode):
                 yield c
 
         yield self.close()
 
     # filter any nodes that claim to be part of the known set
     def prune(self, revlog, missing, commonrevs, source):
         rr, rl = revlog.rev, revlog.linkrev
         return [n for n in missing if rl(rr(n)) not in commonrevs]
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
         '''yield a sequence of changegroup chunks (strings)'''
         repo = self._repo
         cl = self._changelog
         mf = self._manifest
         reorder = self._reorder
         progress = self._progress
 
         # for progress output
         msgbundling = _('bundling')
 
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
 
         # Callback for the changelog, used to collect changed files and manifest
         # nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.read(x)
             changedfiles.update(c[3])
             # record the first changeset introducing this manifest version
             mfs.setdefault(c[0], x)
             return x
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def lookupmf(x):
             clnode = mfs[x]
             if not fastpathlinkrev:
                 mdata = mf.readfast(x)
                 for f, n in mdata.iteritems():
                     if f in changedfiles:
                         # record the first changeset introducing this filelog
                         # version
                         fnodes[f].setdefault(n, clnode)
             return clnode
 
         for chunk in self.group(clnodes, cl, lookupcl, units=_('changesets'),
                                 reorder=reorder):
             yield chunk
         progress(msgbundling, None)
 
         for f in changedfiles:
             fnodes[f] = {}
         mfnodes = self.prune(mf, mfs, commonrevs, source)
         for chunk in self.group(mfnodes, mf, lookupmf, units=_('manifests'),
                                 reorder=reorder):
             yield chunk
         progress(msgbundling, None)
 
         mfs.clear()
         needed = set(cl.rev(x) for x in clnodes)
 
         def linknodes(filerevlog, fname):
             if fastpathlinkrev:
                 llr = filerevlog.linkrev
                 def genfilenodes():
                     for r in filerevlog:
                         linkrev = llr(r)
                         if linkrev in needed:
                             yield filerevlog.node(r), cl.node(linkrev)
                 fnodes[fname] = dict(genfilenodes())
             return fnodes.get(fname, {})
 
         for chunk in self.generatefiles(changedfiles, linknodes, commonrevs,
                                         source):
             yield chunk
 
         yield self.close()
         progress(msgbundling, None)
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def generatefiles(self, changedfiles, linknodes, commonrevs, source):
         repo = self._repo
         progress = self._progress
         reorder = self._reorder
         msgbundling = _('bundling')
 
         total = len(changedfiles)
         # for progress output
         msgfiles = _('files')
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise util.Abort(_("empty or missing revlog for %s") % fname)
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             filenodes = self.prune(filerevlog, linkrevnodes, commonrevs, source)
             if filenodes:
                 progress(msgbundling, i + 1, item=fname, unit=msgfiles,
                          total=total)
                 yield self.fileheader(fname)
                 for chunk in self.group(filenodes, filerevlog, lookupfilelog,
                                         reorder=reorder):
                     yield chunk
 
     def revchunk(self, revlog, rev, prev, linknode):
         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)
         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)
 
 packermap = {'01': (cg1packer, cg1unpacker)}
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
-def getsubset(repo, outgoing, bundler, source, fastpath=False):
+def getsubsetraw(repo, outgoing, bundler, source, fastpath=False):
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
-    gengroup = bundler.generate(commonrevs, csets, fastpathlinkrev, source)
+    return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
+
+def getsubset(repo, outgoing, bundler, source, fastpath=False):
+    gengroup = getsubsetraw(repo, outgoing, bundler, source, fastpath)
     return cg1unpacker(util.chunkbuffer(gengroup), 'UN')
 
 def changegroupsubset(repo, roots, heads, source):
     """Compute a changegroup consisting of all the nodes that are
     descendants of any of the roots and ancestors of any of the heads.
     Return a chunkbuffer object whose read() method will return
     successive changegroup chunks.
 
     It is fairly complex as determining which filenodes and which
     manifest nodes need to be included for the changeset to be complete
     is non-trivial.
 
     Another wrinkle is doing the reverse, figuring out which changeset in
     the changegroup a particular filenode or manifestnode belongs to.
     """
     cl = repo.changelog
     if not roots:
         roots = [nullid]
     # TODO: remove call to nodesbetween.
     csets, roots, heads = cl.nodesbetween(roots, heads)
     discbases = []
     for n in roots:
         discbases.extend([p for p in cl.parents(n) if p != nullid])
     outgoing = discovery.outgoing(cl, discbases, heads)
     bundler = cg1packer(repo)
     return getsubset(repo, outgoing, bundler, source)
 
+def getlocalchangegroupraw(repo, source, outgoing, bundlecaps=None):
+    """Like getbundle, but taking a discovery.outgoing as an argument.
+
+    This is only implemented for local repos and reuses potentially
+    precomputed sets in outgoing. Returns a raw changegroup generator."""
+    if not outgoing.missing:
+        return None
+    bundler = cg1packer(repo, bundlecaps)
+    return getsubsetraw(repo, outgoing, bundler, source)
+
 def getlocalchangegroup(repo, source, outgoing, bundlecaps=None):
     """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 = cg1packer(repo, bundlecaps)
     return getsubset(repo, outgoing, bundler, source)
 
 def _computeoutgoing(repo, heads, common):
     """Computes which revs are outgoing given a set of common
     and a set of heads.
 
     This is a separate function so extensions can have access to
     the logic.
 
     Returns a discovery.outgoing object.
     """
     cl = repo.changelog
     if common:
         hasnode = cl.hasnode
         common = [n for n in common if hasnode(n)]
     else:
         common = [nullid]
     if not heads:
         heads = cl.heads()
     return discovery.outgoing(cl, common, heads)
 
+def getchangegroupraw(repo, source, heads=None, common=None, bundlecaps=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. Returns a raw changegroup generator.
+    """
+    outgoing = _computeoutgoing(repo, heads, common)
+    return getlocalchangegroupraw(repo, source, outgoing, bundlecaps=bundlecaps)
+
 def getchangegroup(repo, source, heads=None, common=None, bundlecaps=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.
     """
     outgoing = _computeoutgoing(repo, heads, common)
     return getlocalchangegroup(repo, source, outgoing, bundlecaps=bundlecaps)
 
 def changegroup(repo, basenodes, source):
     # to avoid a race we use changegroupsubset() (issue1320)
     return changegroupsubset(repo, basenodes, repo.heads(), source)
 
 def addchangegroupfiles(repo, source, revmap, trp, pr, needfiles):
     revisions = 0
     files = 0
     while True:
         chunkdata = source.filelogheader()
         if not chunkdata:
             break
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         pr()
         fl = repo.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]
     repo.ui.progress(_('files'), None)
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise util.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files
 
 def addchangegroup(repo, source, srctype, url, emptyok=False,
                    targetphase=phases.draft):
     """Add the changegroup returned by source.read() to this repo.
     srctype is a string like 'push', 'pull', or 'unbundle'.  url is
     the URL of the repo where this changegroup is coming from.
 
     Return an integer summarizing the change to this repo:
     - nothing changed or no source: 0
     - more heads than before: 1+added heads (2..n)
     - fewer heads than before: -1-removed heads (-2..-n)
     - number of heads stays the same: 1
     """
     repo = repo.unfiltered()
     def csmap(x):
         repo.ui.debug("add changeset %s\n" % short(x))
         return len(cl)
 
     def revmap(x):
         return cl.rev(x)
 
     if not source:
         return 0
 
     changesets = files = revisions = 0
     efiles = set()
 
     # write changelog data to temp files so concurrent readers will not see
     # inconsistent view
     cl = repo.changelog
     cl.delayupdate()
     oldheads = cl.heads()
 
     tr = repo.transaction("\n".join([srctype, util.hidepassword(url)]))
     # The transaction could have been created before and already carries source
     # information. In this case we use the top level data. We overwrite the
     # argument because we need to use the top level value (if they exist) in
     # this function.
     srctype = tr.hookargs.setdefault('source', srctype)
     url = tr.hookargs.setdefault('url', url)
     try:
         repo.hook('prechangegroup', throw=True, **tr.hookargs)
 
         trp = weakref.proxy(tr)
         # pull off the changeset group
         repo.ui.status(_("adding changesets\n"))
         clstart = len(cl)
         class prog(object):
             step = _('changesets')
             count = 1
             ui = repo.ui
             total = None
             def __call__(repo):
                 repo.ui.progress(repo.step, repo.count, unit=_('chunks'),
                                  total=repo.total)
                 repo.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(repo[c].files())
         efiles = len(efiles)
         repo.ui.progress(_('changesets'), None)
 
         # pull off the manifest group
         repo.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()
         repo.manifest.addgroup(source, revmap, trp)
         repo.ui.progress(_('manifests'), None)
 
         needfiles = {}
         if repo.ui.configbool('server', 'validate', default=False):
             # validate incoming csets have their manifests
             for cset in xrange(clstart, clend):
                 mfest = repo.changelog.read(repo.changelog.node(cset))[0]
                 mfest = repo.manifest.readdelta(mfest)
                 # store file nodes we must see
                 for f, n in mfest.iteritems():
                     needfiles.setdefault(f, set()).add(n)
 
         # process the files
         repo.ui.status(_("adding file changes\n"))
         pr.step = _('files')
         pr.count = 1
         pr.total = efiles
         source.callback = None
 
         newrevs, newfiles = addchangegroupfiles(repo, source, revmap, trp, pr,
                                                 needfiles)
         revisions += newrevs
         files += newfiles
 
         dh = 0
         if oldheads:
             heads = cl.heads()
             dh = len(heads) - len(oldheads)
             for h in heads:
                 if h not in oldheads and repo[h].closesbranch():
                     dh -= 1
         htext = ""
         if dh:
             htext = _(" (%+d heads)") % dh
 
         repo.ui.status(_("added %d changesets"
                          " with %d changes to %d files%s\n")
                          % (changesets, revisions, files, htext))
         repo.invalidatevolatilesets()
 
         if changesets > 0:
             p = lambda: cl.writepending() and repo.root or ""
             if 'node' not in tr.hookargs:
                 tr.hookargs['node'] = hex(cl.node(clstart))
                 hookargs = dict(tr.hookargs)
             else:
                 hookargs = dict(tr.hookargs)
                 hookargs['node'] = hex(cl.node(clstart))
             repo.hook('pretxnchangegroup', throw=True, pending=p, **hookargs)
 
         added = [cl.node(r) for r in xrange(clstart, clend)]
         publishing = repo.ui.configbool('phases', 'publish', True)
         if srctype in ('push', 'serve'):
             # Old servers can not push the boundary themselves.
             # New servers won't push the boundary if changeset already
             # exists locally as secret
             #
             # We should not use added here but the list of all change in
             # the bundle
             if publishing:
                 phases.advanceboundary(repo, tr, phases.public, srccontent)
             else:
                 # Those changesets have been pushed from the outside, their
                 # phases are going to be pushed alongside. Therefor
                 # `targetphase` is ignored.
                 phases.advanceboundary(repo, tr, phases.draft, srccontent)
                 phases.retractboundary(repo, tr, phases.draft, added)
         elif srctype != 'strip':
             # publishing only alter behavior during push
             #
             # strip should not touch boundary at all
             phases.retractboundary(repo, tr, targetphase, added)
 
         # 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(repo.filtered('served'))
 
             def runhooks():
                 # These hooks run when the lock releases, not when the
                 # transaction closes. So it's possible for the changelog
                 # to have changed since we last saw it.
                 if clstart >= len(repo):
                     return
 
                 # forcefully update the on-disk branch cache
                 repo.ui.debug("updating the branch cache\n")
                 repo.hook("changegroup", **hookargs)
 
                 for n in added:
                     args = hookargs.copy()
                     args['node'] = hex(n)
                     repo.hook("incoming", **args)
 
                 newheads = [h for h in repo.heads() if h not in oldheads]
                 repo.ui.log("incoming",
                             "%s incoming changes - new heads: %s\n",
                             len(added),
                             ', '.join([hex(c[:6]) for c in newheads]))
             repo._afterlock(runhooks)
 
     finally:
         tr.release()
     # never return 0 here:
     if dh < 0:
         return dh - 1
     else:
         return dh + 1

mercurial/exchange.py

@@ -1,1270 +1,1271 b''
 # exchange.py - utility to exchange data between repos.
 #
 # 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 i18n import _
 from node import hex, nullid
 import errno, urllib
 import util, scmutil, changegroup, base85, error
 import discovery, phases, obsolete, bookmarks as bookmod, bundle2, pushkey
 
 def readbundle(ui, fh, fname, vfs=None):
     header = changegroup.readexactly(fh, 4)
 
     alg = None
     if not fname:
         fname = "stream"
         if not header.startswith('HG') and header.startswith('\0'):
             fh = changegroup.headerlessfixup(fh, header)
             header = "HG10"
             alg = 'UN'
     elif vfs:
         fname = vfs.join(fname)
 
     magic, version = header[0:2], header[2:4]
 
     if magic != 'HG':
         raise util.Abort(_('%s: not a Mercurial bundle') % fname)
     if version == '10':
         if alg is None:
             alg = changegroup.readexactly(fh, 2)
         return changegroup.cg1unpacker(fh, alg)
     elif version == '2Y':
         return bundle2.unbundle20(ui, fh, header=magic + version)
     else:
         raise util.Abort(_('%s: unknown bundle version %s') % (fname, version))
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if markers:
         remoteversions = bundle2.obsmarkersversion(bundler.capabilities)
         version = obsolete.commonversion(remoteversions)
         if version is None:
             raise ValueError('bundler do not support common obsmarker format')
         stream = obsolete.encodemarkers(markers, True, version=version)
         return bundler.newpart('B2X:OBSMARKERS', data=stream)
     return None
 
 class pushoperation(object):
     """A object that represent a single push operation
 
     It purpose is to carry push related state and very common operation.
 
     A new should be created at the beginning of each push and discarded
     afterward.
     """
 
     def __init__(self, repo, remote, force=False, revs=None, newbranch=False,
                  bookmarks=()):
         # repo we push from
         self.repo = repo
         self.ui = repo.ui
         # repo we push to
         self.remote = remote
         # force option provided
         self.force = force
         # revs to be pushed (None is "all")
         self.revs = revs
         # bookmark explicitly pushed
         self.bookmarks = bookmarks
         # allow push of new branch
         self.newbranch = newbranch
         # did a local lock get acquired?
         self.locallocked = None
         # step already performed
         # (used to check what steps have been already performed through bundle2)
         self.stepsdone = set()
         # Integer version of the changegroup push result
         # - 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()
         self.cgresult = None
         # Boolean value for the bookmark push
         self.bkresult = None
         # discover.outgoing object (contains common and outgoing data)
         self.outgoing = None
         # all remote heads before the push
         self.remoteheads = None
         # testable as a boolean indicating if any nodes are missing locally.
         self.incoming = None
         # phases changes that must be pushed along side the changesets
         self.outdatedphases = None
         # phases changes that must be pushed if changeset push fails
         self.fallbackoutdatedphases = None
         # outgoing obsmarkers
         self.outobsmarkers = set()
         # outgoing bookmarks
         self.outbookmarks = []
 
     @util.propertycache
     def futureheads(self):
         """future remote heads if the changeset push succeeds"""
         return self.outgoing.missingheads
 
     @util.propertycache
     def fallbackheads(self):
         """future remote heads if the changeset push fails"""
         if self.revs is None:
             # not target to push, all common are relevant
             return self.outgoing.commonheads
         unfi = self.repo.unfiltered()
         # 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(self.outgoing.common)
         nm = self.repo.changelog.nodemap
         cheads = [node for node in self.revs if nm[node] in common]
         # and
         # * commonheads parents on missing
         revset = unfi.set('%ln and parents(roots(%ln))',
                          self.outgoing.commonheads,
                          self.outgoing.missing)
         cheads.extend(c.node() for c in revset)
         return cheads
 
     @property
     def commonheads(self):
         """set of all common heads after changeset bundle push"""
         if self.cgresult:
             return self.futureheads
         else:
             return self.fallbackheads
 
 # mapping of message used when pushing bookmark
 bookmsgmap = {'update': (_("updating bookmark %s\n"),
                          _('updating bookmark %s failed!\n')),
               'export': (_("exporting bookmark %s\n"),
                          _('exporting bookmark %s failed!\n')),
               'delete': (_("deleting remote bookmark %s\n"),
                          _('deleting remote bookmark %s failed!\n')),
               }
 
 
 def push(repo, remote, force=False, revs=None, newbranch=False, bookmarks=()):
     '''Push outgoing changesets (limited by revs) from a local
     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()
     '''
     pushop = pushoperation(repo, remote, force, revs, newbranch, bookmarks)
     if pushop.remote.local():
         missing = (set(pushop.repo.requirements)
                    - pushop.remote.local().supported)
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise util.Abort(msg)
 
     # 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 pushop.remote.canpush():
         raise util.Abort(_("destination does not support push"))
     # get local lock as we might write phase data
     locallock = None
     try:
         locallock = pushop.repo.lock()
         pushop.locallocked = True
     except IOError, err:
         pushop.locallocked = False
         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
         pushop.ui.debug(msg)
     try:
         pushop.repo.checkpush(pushop)
         lock = None
         unbundle = pushop.remote.capable('unbundle')
         if not unbundle:
             lock = pushop.remote.lock()
         try:
             _pushdiscovery(pushop)
             if (pushop.repo.ui.configbool('experimental', 'bundle2-exp',
                                           False)
                 and pushop.remote.capable('bundle2-exp')):
                 _pushbundle2(pushop)
             _pushchangeset(pushop)
             _pushsyncphase(pushop)
             _pushobsolete(pushop)
             _pushbookmark(pushop)
         finally:
             if lock is not None:
                 lock.release()
     finally:
         if locallock is not None:
             locallock.release()
 
     return pushop
 
 # list of steps to perform discovery before push
 pushdiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pushdiscoverymapping = {}
 
 def pushdiscovery(stepname):
     """decorator for function performing discovery before push
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pushdiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pushdiscoverymapping
         pushdiscoverymapping[stepname] = func
         pushdiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pushdiscovery(pushop):
     """Run all discovery steps"""
     for stepname in pushdiscoveryorder:
         step = pushdiscoverymapping[stepname]
         step(pushop)
 
 @pushdiscovery('changeset')
 def _pushdiscoverychangeset(pushop):
     """discover the changeset that need to be pushed"""
     unfi = pushop.repo.unfiltered()
     fci = discovery.findcommonincoming
     commoninc = fci(unfi, pushop.remote, force=pushop.force)
     common, inc, remoteheads = commoninc
     fco = discovery.findcommonoutgoing
     outgoing = fco(unfi, pushop.remote, onlyheads=pushop.revs,
                    commoninc=commoninc, force=pushop.force)
     pushop.outgoing = outgoing
     pushop.remoteheads = remoteheads
     pushop.incoming = inc
 
 @pushdiscovery('phase')
 def _pushdiscoveryphase(pushop):
     """discover the phase that needs to be pushed
 
     (computed for both success and failure case for changesets push)"""
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     remotephases = pushop.remote.listkeys('phases')
     publishing = remotephases.get('publishing', False)
     ana = phases.analyzeremotephases(pushop.repo,
                                      pushop.fallbackheads,
                                      remotephases)
     pheads, droots = ana
     extracond = ''
     if not publishing:
         extracond = ' and public()'
     revset = 'heads((%%ln::%%ln) %s)' % extracond
     # 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
     fallback = list(unfi.set(revset, droots, pushop.fallbackheads))
     if not outgoing.missing:
         future = fallback
     else:
         # adds changeset we are going to push as draft
         #
         # should not be necessary for publishing server, but because of an
         # issue fixed in xxxxx we have to do it anyway.
         fdroots = list(unfi.set('roots(%ln  + %ln::)',
                        outgoing.missing, droots))
         fdroots = [f.node() for f in fdroots]
         future = list(unfi.set(revset, fdroots, pushop.futureheads))
     pushop.outdatedphases = future
     pushop.fallbackoutdatedphases = fallback
 
 @pushdiscovery('obsmarker')
 def _pushdiscoveryobsmarkers(pushop):
     if (obsolete.isenabled(pushop.repo, obsolete.exchangeopt)
         and pushop.repo.obsstore
         and 'obsolete' in pushop.remote.listkeys('namespaces')):
         repo = pushop.repo
         # very naive computation, that can be quite expensive on big repo.
         # However: evolution is currently slow on them anyway.
         nodes = (c.node() for c in repo.set('::%ln', pushop.futureheads))
         pushop.outobsmarkers = pushop.repo.obsstore.relevantmarkers(nodes)
 
 @pushdiscovery('bookmarks')
 def _pushdiscoverybookmarks(pushop):
     ui = pushop.ui
     repo = pushop.repo.unfiltered()
     remote = pushop.remote
     ui.debug("checking for updated bookmarks\n")
     ancestors = ()
     if pushop.revs:
         revnums = map(repo.changelog.rev, pushop.revs)
         ancestors = repo.changelog.ancestors(revnums, inclusive=True)
     remotebookmark = remote.listkeys('bookmarks')
 
     explicit = set(pushop.bookmarks)
 
     comp = bookmod.compare(repo, repo._bookmarks, remotebookmark, srchex=hex)
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = comp
     for b, scid, dcid in advsrc:
         if b in explicit:
             explicit.remove(b)
         if not ancestors or repo[scid].rev() in ancestors:
             pushop.outbookmarks.append((b, dcid, scid))
     # search added bookmark
     for b, scid, dcid in addsrc:
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, '', scid))
     # search for overwritten bookmark
     for b, scid, dcid in advdst + diverge + differ:
         if b in explicit:
             explicit.remove(b)
             pushop.outbookmarks.append((b, dcid, scid))
     # search for bookmark to delete
     for b, scid, dcid in adddst:
         if b in explicit:
             explicit.remove(b)
             # treat as "deleted locally"
             pushop.outbookmarks.append((b, dcid, ''))
     # identical bookmarks shouldn't get reported
     for b, scid, dcid in same:
         if b in explicit:
             explicit.remove(b)
 
     if explicit:
         explicit = sorted(explicit)
         # we should probably list all of them
         ui.warn(_('bookmark %s does not exist on the local '
                   'or remote repository!\n') % explicit[0])
         pushop.bkresult = 2
 
     pushop.outbookmarks.sort()
 
 def _pushcheckoutgoing(pushop):
     outgoing = pushop.outgoing
     unfi = pushop.repo.unfiltered()
     if not outgoing.missing:
         # nothing to push
         scmutil.nochangesfound(unfi.ui, unfi, outgoing.excluded)
         return False
     # something to push
     if not pushop.force:
         # if repo.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 = {"unstable": _("push includes unstable changeset: %s!"),
                    "bumped": _("push includes bumped changeset: %s!"),
                    "divergent": _("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)
         newbm = pushop.ui.configlist('bookmarks', 'pushing')
         discovery.checkheads(unfi, pushop.remote, outgoing,
                              pushop.remoteheads,
                              pushop.newbranch,
                              bool(pushop.incoming),
                              newbm)
     return True
 
 # List of names of steps to perform for an outgoing bundle2, order matters.
 b2partsgenorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 b2partsgenmapping = {}
 
 def b2partsgenerator(stepname):
     """decorator for function generating bundle2 part
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the b2partsgenmapping dictionary directly."""
     def dec(func):
         assert stepname not in b2partsgenmapping
         b2partsgenmapping[stepname] = func
         b2partsgenorder.append(stepname)
         return func
     return dec
 
 @b2partsgenerator('changeset')
 def _pushb2ctx(pushop, bundler):
     """handle changegroup push through bundle2
 
     addchangegroup result is stored in the ``pushop.cgresult`` attribute.
     """
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     # Send known heads to the server for race detection.
     if not _pushcheckoutgoing(pushop):
         return
     pushop.repo.prepushoutgoinghooks(pushop.repo,
                                      pushop.remote,
                                      pushop.outgoing)
     if not pushop.force:
         bundler.newpart('B2X:CHECK:HEADS', data=iter(pushop.remoteheads))
-    cg = changegroup.getlocalchangegroup(pushop.repo, 'push', pushop.outgoing)
-    cgpart = bundler.newpart('B2X:CHANGEGROUP', data=cg.getchunks())
+    cg = changegroup.getlocalchangegroupraw(pushop.repo, 'push',
+                                            pushop.outgoing)
+    cgpart = bundler.newpart('B2X:CHANGEGROUP', data=cg)
     def handlereply(op):
         """extract addchangegroup returns from server reply"""
         cgreplies = op.records.getreplies(cgpart.id)
         assert len(cgreplies['changegroup']) == 1
         pushop.cgresult = cgreplies['changegroup'][0]['return']
     return handlereply
 
 @b2partsgenerator('phase')
 def _pushb2phases(pushop, bundler):
     """handle phase push through bundle2"""
     if 'phases' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     if not 'b2x:pushkey' in b2caps:
         return
     pushop.stepsdone.add('phases')
     part2node = []
     enc = pushkey.encode
     for newremotehead in pushop.outdatedphases:
         part = bundler.newpart('b2x:pushkey')
         part.addparam('namespace', enc('phases'))
         part.addparam('key', enc(newremotehead.hex()))
         part.addparam('old', enc(str(phases.draft)))
         part.addparam('new', enc(str(phases.public)))
         part2node.append((part.id, newremotehead))
     def handlereply(op):
         for partid, node in part2node:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             msg = None
             if not results:
                 msg = _('server ignored update of %s to public!\n') % node
             elif not int(results[0]['return']):
                 msg = _('updating %s to public failed!\n') % node
             if msg is not None:
                 pushop.ui.warn(msg)
     return handlereply
 
 @b2partsgenerator('obsmarkers')
 def _pushb2obsmarkers(pushop, bundler):
     if 'obsmarkers' in pushop.stepsdone:
         return
     remoteversions = bundle2.obsmarkersversion(bundler.capabilities)
     if obsolete.commonversion(remoteversions) is None:
         return
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         buildobsmarkerspart(bundler, pushop.outobsmarkers)
 
 @b2partsgenerator('bookmarks')
 def _pushb2bookmarks(pushop, bundler):
     """handle phase push through bundle2"""
     if 'bookmarks' in pushop.stepsdone:
         return
     b2caps = bundle2.bundle2caps(pushop.remote)
     if 'b2x:pushkey' not in b2caps:
         return
     pushop.stepsdone.add('bookmarks')
     part2book = []
     enc = pushkey.encode
     for book, old, new in pushop.outbookmarks:
         part = bundler.newpart('b2x:pushkey')
         part.addparam('namespace', enc('bookmarks'))
         part.addparam('key', enc(book))
         part.addparam('old', enc(old))
         part.addparam('new', enc(new))
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
         part2book.append((part.id, book, action))
 
 
     def handlereply(op):
         ui = pushop.ui
         for partid, book, action in part2book:
             partrep = op.records.getreplies(partid)
             results = partrep['pushkey']
             assert len(results) <= 1
             if not results:
                 pushop.ui.warn(_('server ignored bookmark %s update\n') % book)
             else:
                 ret = int(results[0]['return'])
                 if ret:
                     ui.status(bookmsgmap[action][0] % book)
                 else:
                     ui.warn(bookmsgmap[action][1] % book)
                     if pushop.bkresult is not None:
                         pushop.bkresult = 1
     return handlereply
 
 
 def _pushbundle2(pushop):
     """push data to the remote using bundle2
 
     The only currently supported type of data is changegroup but this will
     evolve in the future."""
     bundler = bundle2.bundle20(pushop.ui, bundle2.bundle2caps(pushop.remote))
     # create reply capability
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(pushop.repo))
     bundler.newpart('b2x:replycaps', data=capsblob)
     replyhandlers = []
     for partgenname in b2partsgenorder:
         partgen = b2partsgenmapping[partgenname]
         ret = partgen(pushop, bundler)
         if callable(ret):
             replyhandlers.append(ret)
     # do not push if nothing to push
     if bundler.nbparts <= 1:
         return
     stream = util.chunkbuffer(bundler.getchunks())
     try:
         reply = pushop.remote.unbundle(stream, ['force'], 'push')
     except error.BundleValueError, exc:
         raise util.Abort('missing support for %s' % exc)
     try:
         op = bundle2.processbundle(pushop.repo, reply)
     except error.BundleValueError, exc:
         raise util.Abort('missing support for %s' % exc)
     for rephand in replyhandlers:
         rephand(op)
 
 def _pushchangeset(pushop):
     """Make the actual push of changeset bundle to remote repo"""
     if 'changesets' in pushop.stepsdone:
         return
     pushop.stepsdone.add('changesets')
     if not _pushcheckoutgoing(pushop):
         return
     pushop.repo.prepushoutgoinghooks(pushop.repo,
                                      pushop.remote,
                                      pushop.outgoing)
     outgoing = pushop.outgoing
     unbundle = pushop.remote.capable('unbundle')
     # TODO: get bundlecaps from remote
     bundlecaps = None
     # create a changegroup from local
     if pushop.revs is None and not (outgoing.excluded
                             or pushop.repo.changelog.filteredrevs):
         # push everything,
         # use the fast path, no race possible on push
         bundler = changegroup.cg1packer(pushop.repo, bundlecaps)
         cg = changegroup.getsubset(pushop.repo,
                                    outgoing,
                                    bundler,
                                    'push',
                                    fastpath=True)
     else:
         cg = changegroup.getlocalchangegroup(pushop.repo, 'push', outgoing,
                                         bundlecaps)
 
     # 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 pushop.force:
             remoteheads = ['force']
         else:
             remoteheads = pushop.remoteheads
         # ssh: return remote's addchangegroup()
         # http: return remote's addchangegroup() or 0 for error
         pushop.cgresult = pushop.remote.unbundle(cg, remoteheads,
                                             pushop.repo.url())
     else:
         # we return an integer indicating remote head count
         # change
         pushop.cgresult = pushop.remote.addchangegroup(cg, 'push',
                                                        pushop.repo.url())
 
 def _pushsyncphase(pushop):
     """synchronise phase information locally and remotely"""
     cheads = pushop.commonheads
     # even when we don't push, exchanging phase data is useful
     remotephases = pushop.remote.listkeys('phases')
     if (pushop.ui.configbool('ui', '_usedassubrepo', False)
         and remotephases    # server supports phases
         and pushop.cgresult 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 reply from non-publishing
         _localphasemove(pushop, cheads)
         # don't push any phase data as there is nothing to push
     else:
         ana = phases.analyzeremotephases(pushop.repo, cheads,
                                          remotephases)
         pheads, droots = ana
         ### Apply remote phase on local
         if remotephases.get('publishing', False):
             _localphasemove(pushop, cheads)
         else: # publish = False
             _localphasemove(pushop, pheads)
             _localphasemove(pushop, cheads, phases.draft)
         ### Apply local phase on remote
 
         if pushop.cgresult:
             if 'phases' in pushop.stepsdone:
                 # phases already pushed though bundle2
                 return
             outdated = pushop.outdatedphases
         else:
             outdated = pushop.fallbackoutdatedphases
 
         pushop.stepsdone.add('phases')
 
         # filter heads already turned public by the push
         outdated = [c for c in outdated if c.node() not in pheads]
         b2caps = bundle2.bundle2caps(pushop.remote)
         if 'b2x:pushkey' in b2caps:
             # server supports bundle2, let's do a batched push through it
             #
             # This will eventually be unified with the changesets bundle2 push
             bundler = bundle2.bundle20(pushop.ui, b2caps)
             capsblob = bundle2.encodecaps(bundle2.getrepocaps(pushop.repo))
             bundler.newpart('b2x:replycaps', data=capsblob)
             part2node = []
             enc = pushkey.encode
             for newremotehead in outdated:
                 part = bundler.newpart('b2x:pushkey')
                 part.addparam('namespace', enc('phases'))
                 part.addparam('key', enc(newremotehead.hex()))
                 part.addparam('old', enc(str(phases.draft)))
                 part.addparam('new', enc(str(phases.public)))
                 part2node.append((part.id, newremotehead))
             stream = util.chunkbuffer(bundler.getchunks())
             try:
                 reply = pushop.remote.unbundle(stream, ['force'], 'push')
                 op = bundle2.processbundle(pushop.repo, reply)
             except error.BundleValueError, exc:
                 raise util.Abort('missing support for %s' % exc)
             for partid, node in part2node:
                 partrep = op.records.getreplies(partid)
                 results = partrep['pushkey']
                 assert len(results) <= 1
                 msg = None
                 if not results:
                     msg = _('server ignored update of %s to public!\n') % node
                 elif not int(results[0]['return']):
                     msg = _('updating %s to public failed!\n') % node
                 if msg is not None:
                     pushop.ui.warn(msg)
 
         else:
             # fallback to independent pushkey command
             for newremotehead in outdated:
                 r = pushop.remote.pushkey('phases',
                                           newremotehead.hex(),
                                           str(phases.draft),
                                           str(phases.public))
                 if not r:
                     pushop.ui.warn(_('updating %s to public failed!\n')
                                    % newremotehead)
 
 def _localphasemove(pushop, nodes, phase=phases.public):
     """move <nodes> to <phase> in the local source repo"""
     if pushop.locallocked:
         tr = pushop.repo.transaction('push-phase-sync')
         try:
             phases.advanceboundary(pushop.repo, tr, phase, nodes)
             tr.close()
         finally:
             tr.release()
     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 < pushop.repo[n].phase()]
         phasestr = phases.phasenames[phase]
         if actualmoves:
             pushop.ui.status(_('cannot lock source repo, skipping '
                                'local %s phase update\n') % phasestr)
 
 def _pushobsolete(pushop):
     """utility function to push obsolete markers to a remote"""
     if 'obsmarkers' in pushop.stepsdone:
         return
     pushop.ui.debug('try to push obsolete markers to remote\n')
     repo = pushop.repo
     remote = pushop.remote
     pushop.stepsdone.add('obsmarkers')
     if pushop.outobsmarkers:
         rslts = []
         remotedata = obsolete._pushkeyescape(pushop.outobsmarkers)
         for key in sorted(remotedata, reverse=True):
             # reverse sort to ensure we end with dump0
             data = remotedata[key]
             rslts.append(remote.pushkey('obsolete', key, '', data))
         if [r for r in rslts if not r]:
             msg = _('failed to push some obsolete markers!\n')
             repo.ui.warn(msg)
 
 def _pushbookmark(pushop):
     """Update bookmark position on remote"""
     if pushop.cgresult == 0 or 'bookmarks' in pushop.stepsdone:
         return
     pushop.stepsdone.add('bookmarks')
     ui = pushop.ui
     remote = pushop.remote
 
     for b, old, new in pushop.outbookmarks:
         action = 'update'
         if not old:
             action = 'export'
         elif not new:
             action = 'delete'
         if remote.pushkey('bookmarks', b, old, new):
             ui.status(bookmsgmap[action][0] % b)
         else:
             ui.warn(bookmsgmap[action][1] % b)
             # discovery can have set the value form invalid entry
             if pushop.bkresult is not None:
                 pushop.bkresult = 1
 
 class pulloperation(object):
     """A object that represent a single pull operation
 
     It purpose is to carry push related state and very common operation.
 
     A new should be created at the beginning of each pull and discarded
     afterward.
     """
 
     def __init__(self, repo, remote, heads=None, force=False, bookmarks=()):
         # repo we pull into
         self.repo = repo
         # repo we pull from
         self.remote = remote
         # revision we try to pull (None is "all")
         self.heads = heads
         # bookmark pulled explicitly
         self.explicitbookmarks = bookmarks
         # do we force pull?
         self.force = force
         # the name the pull transaction
         self._trname = 'pull\n' + util.hidepassword(remote.url())
         # hold the transaction once created
         self._tr = None
         # set of common changeset between local and remote before pull
         self.common = None
         # set of pulled head
         self.rheads = None
         # list of missing changeset to fetch remotely
         self.fetch = None
         # remote bookmarks data
         self.remotebookmarks = None
         # result of changegroup pulling (used as return code by pull)
         self.cgresult = None
         # list of step already done
         self.stepsdone = set()
 
     @util.propertycache
     def pulledsubset(self):
         """heads of the set of changeset target by the pull"""
         # compute target subset
         if self.heads is None:
             # We pulled every thing possible
             # sync on everything common
             c = set(self.common)
             ret = list(self.common)
             for n in self.rheads:
                 if n not in c:
                     ret.append(n)
             return ret
         else:
             # We pulled a specific subset
             # sync on this subset
             return self.heads
 
     def gettransaction(self):
         """get appropriate pull transaction, creating it if needed"""
         if self._tr is None:
             self._tr = self.repo.transaction(self._trname)
             self._tr.hookargs['source'] = 'pull'
             self._tr.hookargs['url'] = self.remote.url()
         return self._tr
 
     def closetransaction(self):
         """close transaction if created"""
         if self._tr is not None:
             repo = self.repo
             cl = repo.unfiltered().changelog
             p = cl.writepending() and repo.root or ""
             p = cl.writepending() and repo.root or ""
             repo.hook('b2x-pretransactionclose', throw=True, pending=p,
                       **self._tr.hookargs)
             self._tr.close()
             hookargs = dict(self._tr.hookargs)
             def runhooks():
                 repo.hook('b2x-transactionclose', **hookargs)
             repo._afterlock(runhooks)
 
     def releasetransaction(self):
         """release transaction if created"""
         if self._tr is not None:
             self._tr.release()
 
 def pull(repo, remote, heads=None, force=False, bookmarks=()):
     pullop = pulloperation(repo, remote, heads, force, bookmarks=bookmarks)
     if pullop.remote.local():
         missing = set(pullop.remote.requirements) - pullop.repo.supported
         if missing:
             msg = _("required features are not"
                     " supported in the destination:"
                     " %s") % (', '.join(sorted(missing)))
             raise util.Abort(msg)
 
     pullop.remotebookmarks = remote.listkeys('bookmarks')
     lock = pullop.repo.lock()
     try:
         _pulldiscovery(pullop)
         if (pullop.repo.ui.configbool('experimental', 'bundle2-exp', False)
             and pullop.remote.capable('bundle2-exp')):
             _pullbundle2(pullop)
         _pullchangeset(pullop)
         _pullphase(pullop)
         _pullbookmarks(pullop)
         _pullobsolete(pullop)
         pullop.closetransaction()
     finally:
         pullop.releasetransaction()
         lock.release()
 
     return pullop
 
 # list of steps to perform discovery before pull
 pulldiscoveryorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 pulldiscoverymapping = {}
 
 def pulldiscovery(stepname):
     """decorator for function performing discovery before pull
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated function will be added in order (this
     may matter).
 
     You can only use this decorator for a new step, if you want to wrap a step
     from an extension, change the pulldiscovery dictionary directly."""
     def dec(func):
         assert stepname not in pulldiscoverymapping
         pulldiscoverymapping[stepname] = func
         pulldiscoveryorder.append(stepname)
         return func
     return dec
 
 def _pulldiscovery(pullop):
     """Run all discovery steps"""
     for stepname in pulldiscoveryorder:
         step = pulldiscoverymapping[stepname]
         step(pullop)
 
 @pulldiscovery('changegroup')
 def _pulldiscoverychangegroup(pullop):
     """discovery phase for the pull
 
     Current handle changeset discovery only, will change handle all discovery
     at some point."""
     tmp = discovery.findcommonincoming(pullop.repo.unfiltered(),
                                        pullop.remote,
                                        heads=pullop.heads,
                                        force=pullop.force)
     pullop.common, pullop.fetch, pullop.rheads = tmp
 
 def _pullbundle2(pullop):
     """pull data using bundle2
 
     For now, the only supported data are changegroup."""
     remotecaps = bundle2.bundle2caps(pullop.remote)
     kwargs = {'bundlecaps': caps20to10(pullop.repo)}
     # pulling changegroup
     pullop.stepsdone.add('changegroup')
 
     kwargs['common'] = pullop.common
     kwargs['heads'] = pullop.heads or pullop.rheads
     kwargs['cg'] = pullop.fetch
     if 'b2x:listkeys' in remotecaps:
         kwargs['listkeys'] = ['phase', 'bookmarks']
     if not pullop.fetch:
         pullop.repo.ui.status(_("no changes found\n"))
         pullop.cgresult = 0
     else:
         if pullop.heads is None and list(pullop.common) == [nullid]:
             pullop.repo.ui.status(_("requesting all changes\n"))
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         remoteversions = bundle2.obsmarkersversion(remotecaps)
         if obsolete.commonversion(remoteversions) is not None:
             kwargs['obsmarkers'] = True
             pullop.stepsdone.add('obsmarkers')
     _pullbundle2extraprepare(pullop, kwargs)
     if kwargs.keys() == ['format']:
         return # nothing to pull
     bundle = pullop.remote.getbundle('pull', **kwargs)
     try:
         op = bundle2.processbundle(pullop.repo, bundle, pullop.gettransaction)
     except error.BundleValueError, exc:
         raise util.Abort('missing support for %s' % exc)
 
     if pullop.fetch:
         changedheads = 0
         pullop.cgresult = 1
         for cg in op.records['changegroup']:
             ret = cg['return']
             # If any changegroup result is 0, return 0
             if ret == 0:
                 pullop.cgresult = 0
                 break
             if ret < -1:
                 changedheads += ret + 1
             elif ret > 1:
                 changedheads += ret - 1
         if changedheads > 0:
             pullop.cgresult = 1 + changedheads
         elif changedheads < 0:
             pullop.cgresult = -1 + changedheads
 
     # processing phases change
     for namespace, value in op.records['listkeys']:
         if namespace == 'phases':
             _pullapplyphases(pullop, value)
 
     # processing bookmark update
     for namespace, value in op.records['listkeys']:
         if namespace == 'bookmarks':
             pullop.remotebookmarks = value
             _pullbookmarks(pullop)
 
 def _pullbundle2extraprepare(pullop, kwargs):
     """hook function so that extensions can extend the getbundle call"""
     pass
 
 def _pullchangeset(pullop):
     """pull changeset from unbundle into the local repo"""
     # We delay the open of the transaction as late as possible so we
     # don't open transaction for nothing or you break future useful
     # rollback call
     if 'changegroup' in pullop.stepsdone:
         return
     pullop.stepsdone.add('changegroup')
     if not pullop.fetch:
             pullop.repo.ui.status(_("no changes found\n"))
             pullop.cgresult = 0
             return
     pullop.gettransaction()
     if pullop.heads is None and list(pullop.common) == [nullid]:
         pullop.repo.ui.status(_("requesting all changes\n"))
     elif pullop.heads is None and pullop.remote.capable('changegroupsubset'):
         # issue1320, avoid a race if remote changed after discovery
         pullop.heads = pullop.rheads
 
     if pullop.remote.capable('getbundle'):
         # TODO: get bundlecaps from remote
         cg = pullop.remote.getbundle('pull', common=pullop.common,
                                      heads=pullop.heads or pullop.rheads)
     elif pullop.heads is None:
         cg = pullop.remote.changegroup(pullop.fetch, 'pull')
     elif not pullop.remote.capable('changegroupsubset'):
         raise util.Abort(_("partial pull cannot be done because "
                            "other repository doesn't support "
                            "changegroupsubset."))
     else:
         cg = pullop.remote.changegroupsubset(pullop.fetch, pullop.heads, 'pull')
     pullop.cgresult = changegroup.addchangegroup(pullop.repo, cg, 'pull',
                                                  pullop.remote.url())
 
 def _pullphase(pullop):
     # Get remote phases data from remote
     if 'phases' in pullop.stepsdone:
         return
     remotephases = pullop.remote.listkeys('phases')
     _pullapplyphases(pullop, remotephases)
 
 def _pullapplyphases(pullop, remotephases):
     """apply phase movement from observed remote state"""
     if 'phases' in pullop.stepsdone:
         return
     pullop.stepsdone.add('phases')
     publishing = bool(remotephases.get('publishing', False))
     if remotephases and not publishing:
         # remote is new and unpublishing
         pheads, _dr = phases.analyzeremotephases(pullop.repo,
                                                  pullop.pulledsubset,
                                                  remotephases)
         dheads = pullop.pulledsubset
     else:
         # Remote is old or publishing all common changesets
         # should be seen as public
         pheads = pullop.pulledsubset
         dheads = []
     unfi = pullop.repo.unfiltered()
     phase = unfi._phasecache.phase
     rev = unfi.changelog.nodemap.get
     public = phases.public
     draft = phases.draft
 
     # exclude changesets already public locally and update the others
     pheads = [pn for pn in pheads if phase(unfi, rev(pn)) > public]
     if pheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, public, pheads)
 
     # exclude changesets already draft locally and update the others
     dheads = [pn for pn in dheads if phase(unfi, rev(pn)) > draft]
     if dheads:
         tr = pullop.gettransaction()
         phases.advanceboundary(pullop.repo, tr, draft, dheads)
 
 def _pullbookmarks(pullop):
     """process the remote bookmark information to update the local one"""
     if 'bookmarks' in pullop.stepsdone:
         return
     pullop.stepsdone.add('bookmarks')
     repo = pullop.repo
     remotebookmarks = pullop.remotebookmarks
     bookmod.updatefromremote(repo.ui, repo, remotebookmarks,
                              pullop.remote.url(),
                              pullop.gettransaction,
                              explicit=pullop.explicitbookmarks)
 
 def _pullobsolete(pullop):
     """utility function to pull obsolete markers from a remote
 
     The `gettransaction` is function that return the pull transaction, creating
     one if necessary. We return the transaction to inform the calling code that
     a new transaction have been created (when applicable).
 
     Exists mostly to allow overriding for experimentation purpose"""
     if 'obsmarkers' in pullop.stepsdone:
         return
     pullop.stepsdone.add('obsmarkers')
     tr = None
     if obsolete.isenabled(pullop.repo, obsolete.exchangeopt):
         pullop.repo.ui.debug('fetching remote obsolete markers\n')
         remoteobs = pullop.remote.listkeys('obsolete')
         if 'dump0' in remoteobs:
             tr = pullop.gettransaction()
             for key in sorted(remoteobs, reverse=True):
                 if key.startswith('dump'):
                     data = base85.b85decode(remoteobs[key])
                     pullop.repo.obsstore.mergemarkers(tr, data)
             pullop.repo.invalidatevolatilesets()
     return tr
 
 def caps20to10(repo):
     """return a set with appropriate options to use bundle20 during getbundle"""
     caps = set(['HG2Y'])
     capsblob = bundle2.encodecaps(bundle2.getrepocaps(repo))
     caps.add('bundle2=' + urllib.quote(capsblob))
     return caps
 
 # List of names of steps to perform for a bundle2 for getbundle, order matters.
 getbundle2partsorder = []
 
 # Mapping between step name and function
 #
 # This exists to help extensions wrap steps if necessary
 getbundle2partsmapping = {}
 
 def getbundle2partsgenerator(stepname):
     """decorator for function generating bundle2 part for getbundle
 
     The function is added to the step -> function mapping and appended to the
     list of steps.  Beware that decorated functions will be added in order
     (this may matter).
 
     You can only use this decorator for new steps, if you want to wrap a step
     from an extension, attack the getbundle2partsmapping dictionary directly."""
     def dec(func):
         assert stepname not in getbundle2partsmapping
         getbundle2partsmapping[stepname] = func
         getbundle2partsorder.append(stepname)
         return func
     return dec
 
 def getbundle(repo, source, heads=None, common=None, bundlecaps=None,
               **kwargs):
     """return a full bundle (with potentially multiple kind of parts)
 
     Could be a bundle HG10 or a bundle HG2Y depending on bundlecaps
     passed. For now, the bundle can contain only changegroup, but this will
     changes when more part type will be available for bundle2.
 
     This is different from changegroup.getchangegroup that only returns an HG10
     changegroup bundle. They may eventually get reunited in the future when we
     have a clearer idea of the API we what to query different data.
 
     The implementation is at a very early stage and will get massive rework
     when the API of bundle is refined.
     """
     # bundle10 case
     if bundlecaps is None or 'HG2Y' not in bundlecaps:
         if bundlecaps and not kwargs.get('cg', True):
             raise ValueError(_('request for bundle10 must include changegroup'))
 
         if kwargs:
             raise ValueError(_('unsupported getbundle arguments: %s')
                              % ', '.join(sorted(kwargs.keys())))
         return changegroup.getchangegroup(repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps)
 
     # bundle20 case
     b2caps = {}
     for bcaps in bundlecaps:
         if bcaps.startswith('bundle2='):
             blob = urllib.unquote(bcaps[len('bundle2='):])
             b2caps.update(bundle2.decodecaps(blob))
     bundler = bundle2.bundle20(repo.ui, b2caps)
 
     for name in getbundle2partsorder:
         func = getbundle2partsmapping[name]
         kwargs['heads'] = heads
         kwargs['common'] = common
         func(bundler, repo, source, bundlecaps=bundlecaps, b2caps=b2caps,
              **kwargs)
 
     return util.chunkbuffer(bundler.getchunks())
 
 @getbundle2partsgenerator('changegroup')
 def _getbundlechangegrouppart(bundler, repo, source, bundlecaps=None,
                               b2caps=None, heads=None, common=None, **kwargs):
     """add a changegroup part to the requested bundle"""
     cg = None
     if kwargs.get('cg', True):
         # build changegroup bundle here.
-        cg = changegroup.getchangegroup(repo, source, heads=heads,
+        cg = changegroup.getchangegroupraw(repo, source, heads=heads,
                                         common=common, bundlecaps=bundlecaps)
 
     if cg:
-        bundler.newpart('b2x:changegroup', data=cg.getchunks())
+        bundler.newpart('b2x:changegroup', data=cg)
 
 @getbundle2partsgenerator('listkeys')
 def _getbundlelistkeysparts(bundler, repo, source, bundlecaps=None,
                             b2caps=None, **kwargs):
     """add parts containing listkeys namespaces to the requested bundle"""
     listkeys = kwargs.get('listkeys', ())
     for namespace in listkeys:
         part = bundler.newpart('b2x:listkeys')
         part.addparam('namespace', namespace)
         keys = repo.listkeys(namespace).items()
         part.data = pushkey.encodekeys(keys)
 
 @getbundle2partsgenerator('obsmarkers')
 def _getbundleobsmarkerpart(bundler, repo, source, bundlecaps=None,
                             b2caps=None, heads=None, **kwargs):
     """add an obsolescence markers part to the requested bundle"""
     if kwargs.get('obsmarkers', False):
         if heads is None:
             heads = repo.heads()
         subset = [c.node() for c in repo.set('::%ln', heads)]
         markers = repo.obsstore.relevantmarkers(subset)
         buildobsmarkerspart(bundler, markers)
 
 def check_heads(repo, their_heads, context):
     """check if the heads of a repo have been modified
 
     Used by peer for unbundling.
     """
     heads = repo.heads()
     heads_hash = util.sha1(''.join(sorted(heads))).digest()
     if not (their_heads == ['force'] or their_heads == heads or
             their_heads == ['hashed', heads_hash]):
         # someone else committed/pushed/unbundled while we
         # were transferring data
         raise error.PushRaced('repository changed while %s - '
                               'please try again' % context)
 
 def unbundle(repo, cg, heads, source, url):
     """Apply a bundle to a repo.
 
     this function makes sure the repo is locked during the application and have
     mechanism to check that no push race occurred between the creation of the
     bundle and its application.
 
     If the push was raced as PushRaced exception is raised."""
     r = 0
     # need a transaction when processing a bundle2 stream
     tr = None
     lock = repo.lock()
     try:
         check_heads(repo, heads, 'uploading changes')
         # push can proceed
         if util.safehasattr(cg, 'params'):
             try:
                 tr = repo.transaction('unbundle')
                 tr.hookargs['source'] = source
                 tr.hookargs['url'] = url
                 tr.hookargs['bundle2-exp'] = '1'
                 r = bundle2.processbundle(repo, cg, lambda: tr).reply
                 cl = repo.unfiltered().changelog
                 p = cl.writepending() and repo.root or ""
                 repo.hook('b2x-pretransactionclose', throw=True, pending=p,
                           **tr.hookargs)
                 tr.close()
                 hookargs = dict(tr.hookargs)
                 def runhooks():
                     repo.hook('b2x-transactionclose', **hookargs)
                 repo._afterlock(runhooks)
             except Exception, exc:
                 exc.duringunbundle2 = True
                 raise
         else:
             r = changegroup.addchangegroup(repo, cg, source, url)
     finally:
         if tr is not None:
             tr.release()
         lock.release()
     return r