revlog: add 'raw' argument to revision and _addrevision

This patch introduces a new 'raw' argument (defaults to False) to revlog's
revision() and _addrevision() methods.
When the 'raw' argument is set to True, it indicates the revision data should be
handled as raw data by the flagprocessor.

Note: Given revlog.addgroup() calls are restricted to changegroup generation, we
can always set raw to True when calling revlog._addrevision() from
revlog.addgroup().

mercurial/bundlerepo.py

@@ -1,554 +1,554 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[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.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from __future__ import absolute_import
 
 import os
 import shutil
 import tempfile
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     node as nodemod,
     pathutil,
     phases,
     pycompat,
     revlog,
     scmutil,
     util,
 )
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, bundle, linkmapper):
         # How it works:
         # To retrieve a revision, we need to know the offset of the revision in
         # the bundle (an unbundle object). We store this offset in the index
         # (start). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = scmutil.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = bundle
         n = len(self)
         self.repotiprev = n - 1
         chain = None
         self.bundlerevs = set() # used by 'bundle()' revset expression
         getchunk = lambda: bundle.deltachunk(chain)
         for chunkdata in iter(getchunk, {}):
             node = chunkdata['node']
             p1 = chunkdata['p1']
             p2 = chunkdata['p2']
             cs = chunkdata['cs']
             deltabase = chunkdata['deltabase']
             delta = chunkdata['delta']
 
             size = len(delta)
             start = bundle.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 chain = node
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             for p in (p1, p2):
                 if p not in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
 
             if deltabase not in self.nodemap:
                 raise LookupError(deltabase, self.indexfile,
                                   _('unknown delta base'))
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, 0), size, -1, baserev, link,
                  self.rev(p1), self.rev(p2), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             chain = node
             n += 1
 
     def _chunk(self, rev):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                               self.revision(self.node(rev2)))
 
-    def revision(self, nodeorrev):
+    def revision(self, nodeorrev, raw=False):
         """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 = self.rev(node)
 
         if node == nullid:
             return ""
 
         text = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._cache and self._cache[1] == iterrev:
                 text = self._cache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if text is None:
             text = self.baserevision(iterrev)
 
         while chain:
             delta = self._chunk(chain.pop())
             text = mdiff.patches(text, [delta])
 
         self.checkhash(text, node, rev=rev)
         self._cache = (node, rev, text)
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use bundlerevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev)
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, bundle):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
 
         # This bypasses filtering on changelog.node() and rev() because we need
         # revision text of the bundle base even if it is hidden.
         oldfilter = self.filteredrevs
         try:
             self.filteredrevs = ()
             return changelog.changelog.revision(self, nodeorrev)
         finally:
             self.filteredrevs = oldfilter
 
 class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
     def __init__(self, opener, bundle, linkmapper, dirlogstarts=None, dir=''):
         manifest.manifestrevlog.__init__(self, opener, dir=dir)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
         if dirlogstarts is None:
             dirlogstarts = {}
             if self.bundle.version == "03":
                 dirlogstarts = _getfilestarts(self.bundle)
         self._dirlogstarts = dirlogstarts
         self._linkmapper = linkmapper
 
     def baserevision(self, nodeorrev):
         node = nodeorrev
         if isinstance(node, int):
             node = self.node(node)
 
         if node in self.fulltextcache:
             result = self.fulltextcache[node].tostring()
         else:
             result = manifest.manifestrevlog.revision(self, nodeorrev)
         return result
 
     def dirlog(self, d):
         if d in self._dirlogstarts:
             self.bundle.seek(self._dirlogstarts[d])
             return bundlemanifest(
                 self.opener, self.bundle, self._linkmapper,
                 self._dirlogstarts, dir=d)
         return super(bundlemanifest, self).dirlog(d)
 
 class bundlefilelog(bundlerevlog, filelog.filelog):
     def __init__(self, opener, path, bundle, linkmapper):
         filelog.filelog.__init__(self, opener, path)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev)
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
         if util.safehasattr(self, 'opener'):
             self.opener = scmutil.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 def _getfilestarts(bundle):
     bundlefilespos = {}
     for chunkdata in iter(bundle.filelogheader, {}):
         fname = chunkdata['filename']
         bundlefilespos[fname] = bundle.tell()
         for chunk in iter(lambda: bundle.deltachunk(None), {}):
             pass
     return bundlefilespos
 
 class bundlerepository(localrepo.localrepository):
     def __init__(self, ui, path, bundlename):
         def _writetempbundle(read, suffix, header=''):
             """Write a temporary file to disk
 
             This is closure because we need to make sure this tracked by
             self.tempfile for cleanup purposes."""
             fdtemp, temp = self.vfs.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un")
             self.tempfile = temp
 
             with os.fdopen(fdtemp, 'wb') as fptemp:
                 fptemp.write(header)
                 while True:
                     chunk = read(2**18)
                     if not chunk:
                         break
                     fptemp.write(chunk)
 
             return self.vfs.open(self.tempfile, mode="rb")
         self._tempparent = None
         try:
             localrepo.localrepository.__init__(self, ui, path)
         except error.RepoError:
             self._tempparent = tempfile.mkdtemp()
             localrepo.instance(ui, self._tempparent, 1)
             localrepo.localrepository.__init__(self, ui, self._tempparent)
         self.ui.setconfig('phases', 'publish', False, 'bundlerepo')
 
         if path:
             self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
         else:
             self._url = 'bundle:' + bundlename
 
         self.tempfile = None
         f = util.posixfile(bundlename, "rb")
         self.bundlefile = self.bundle = exchange.readbundle(ui, f, bundlename)
 
         if isinstance(self.bundle, bundle2.unbundle20):
             cgstream = None
             for part in self.bundle.iterparts():
                 if part.type == 'changegroup':
                     if cgstream is not None:
                         raise NotImplementedError("can't process "
                                                   "multiple changegroups")
                     cgstream = part
                     version = part.params.get('version', '01')
                     legalcgvers = changegroup.supportedincomingversions(self)
                     if version not in legalcgvers:
                         msg = _('Unsupported changegroup version: %s')
                         raise error.Abort(msg % version)
                     if self.bundle.compressed():
                         cgstream = _writetempbundle(part.read,
                                                     ".cg%sun" % version)
 
             if cgstream is None:
                 raise error.Abort(_('No changegroups found'))
             cgstream.seek(0)
 
             self.bundle = changegroup.getunbundler(version, cgstream, 'UN')
 
         elif self.bundle.compressed():
             f = _writetempbundle(self.bundle.read, '.hg10un', header='HG10UN')
             self.bundlefile = self.bundle = exchange.readbundle(ui, f,
                                                                 bundlename,
                                                                 self.vfs)
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(self, None, phases.draft,
                                [ctx.node() for ctx in self[self.firstnewrev:]])
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self.bundle.changelogheader()
         c = bundlechangelog(self.svfs, self.bundle)
         self.manstart = self.bundle.tell()
         return c
 
     def _constructmanifest(self):
         self.bundle.seek(self.manstart)
         # consume the header if it exists
         self.bundle.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         m = bundlemanifest(self.svfs, self.bundle, linkmapper)
         self.filestart = self.bundle.tell()
         return m
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifestlog
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self.bundlefilespos:
             self.bundle.seek(self.filestart)
             self.bundlefilespos = _getfilestarts(self.bundle)
 
         if f in self.bundlefilespos:
             self.bundle.seek(self.bundlefilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self.bundle, linkmapper)
         else:
             return filelog.filelog(self.svfs, f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self.bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return pycompat.getcwd() # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=nullid):
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _("setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % nodemod.hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % nodemod.hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config("bundle", "mainreporoot", "")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(pycompat.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = pycompat.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == 'bundle':
         s = path.split("+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
     return bundlerepository(ui, repopath, bundlename)
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                      force=False):
     '''obtains a bundle of changes incoming from other
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "other" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "other" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                        force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], other.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = other.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if other repo is not local)
 
         # developer config: devel.legacy.exchange
         legexc = ui.configlist('devel', 'legacy.exchange')
         forcebundle1 = 'bundle2' not in legexc and 'bundle1' in legexc
         canbundle2 = (not forcebundle1
                       and other.capable('getbundle')
                       and other.capable('bundle2'))
         if canbundle2:
             kwargs = {}
             kwargs['common'] = common
             kwargs['heads'] = rheads
             kwargs['bundlecaps'] = exchange.caps20to10(repo)
             kwargs['cg'] = True
             b2 = other.getbundle('incoming', **kwargs)
             fname = bundle = changegroup.writechunks(ui, b2._forwardchunks(),
                                                      bundlename)
         else:
             if other.capable('getbundle'):
                 cg = other.getbundle('incoming', common=common, heads=rheads)
             elif onlyheads is None and not other.capable('changegroupsubset'):
                 # compat with older servers when pulling all remote heads
                 cg = other.changegroup(incoming, "incoming")
                 rheads = None
             else:
                 cg = other.changegroupsubset(incoming, rheads, 'incoming')
             if localrepo:
                 bundletype = "HG10BZ"
             else:
                 bundletype = "HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename,
                                                      bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = bundlerepository(repo.baseui, repo.root,
                                                       fname)
             # this repo contains local and other now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev:]]
         remotephases = other.listkeys('phases')
 
         pullop = exchange.pulloperation(bundlerepo, other, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         other.close()
 
     return (localrepo, csets, cleanup)

mercurial/changegroup.py

@@ -1,1044 +1,1044 b''
 # changegroup.py - Mercurial changegroup manipulation functions
 #
 #  Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import struct
 import tempfile
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
     short,
 )
 
 from . import (
     branchmap,
     dagutil,
     discovery,
     error,
     mdiff,
     phases,
     util,
 )
 
 _CHANGEGROUPV1_DELTA_HEADER = "20s20s20s20s"
 _CHANGEGROUPV2_DELTA_HEADER = "20s20s20s20s20s"
 _CHANGEGROUPV3_DELTA_HEADER = ">20s20s20s20s20sH"
 
 def readexactly(stream, n):
     '''read n bytes from stream.read and abort if less was available'''
     s = stream.read(n)
     if len(s) < n:
         raise error.Abort(_("stream ended unexpectedly"
                            " (got %d bytes, expected %d)")
                           % (len(s), n))
     return s
 
 def getchunk(stream):
     """return the next chunk from stream as a string"""
     d = readexactly(stream, 4)
     l = struct.unpack(">l", d)[0]
     if l <= 4:
         if l:
             raise error.Abort(_("invalid chunk length %d") % l)
         return ""
     return readexactly(stream, l - 4)
 
 def chunkheader(length):
     """return a changegroup chunk header (string)"""
     return struct.pack(">l", length + 4)
 
 def closechunk():
     """return a changegroup chunk header (string) for a zero-length chunk"""
     return struct.pack(">l", 0)
 
 def combineresults(results):
     """logic to combine 0 or more addchangegroup results into one"""
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 def writechunks(ui, chunks, filename, vfs=None):
     """Write chunks to a file and return its filename.
 
     The stream is assumed to be a bundle file.
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     """
     fh = None
     cleanup = None
     try:
         if filename:
             if vfs:
                 fh = vfs.open(filename, "wb")
             else:
                 # Increase default buffer size because default is usually
                 # small (4k is common on Linux).
                 fh = open(filename, "wb", 131072)
         else:
             fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
             fh = os.fdopen(fd, "wb")
         cleanup = filename
         for c in chunks:
             fh.write(c)
         cleanup = None
         return filename
     finally:
         if fh is not None:
             fh.close()
         if cleanup is not None:
             if filename and vfs:
                 vfs.unlink(cleanup)
             else:
                 os.unlink(cleanup)
 
 class cg1unpacker(object):
     """Unpacker for cg1 changegroup streams.
 
     A changegroup unpacker handles the framing of the revision data in
     the wire format. Most consumers will want to use the apply()
     method to add the changes from the changegroup to a repository.
 
     If you're forwarding a changegroup unmodified to another consumer,
     use getchunks(), which returns an iterator of changegroup
     chunks. This is mostly useful for cases where you need to know the
     data stream has ended by observing the end of the changegroup.
 
     deltachunk() is useful only if you're applying delta data. Most
     consumers should prefer apply() instead.
 
     A few other public methods exist. Those are used only for
     bundlerepo and some debug commands - their use is discouraged.
     """
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '01'
     _grouplistcount = 1 # One list of files after the manifests
 
     def __init__(self, fh, alg, extras=None):
         if alg is None:
             alg = 'UN'
         if alg not in util.compengines.supportedbundletypes:
             raise error.Abort(_('unknown stream compression type: %s')
                              % alg)
         if alg == 'BZ':
             alg = '_truncatedBZ'
 
         compengine = util.compengines.forbundletype(alg)
         self._stream = compengine.decompressorreader(fh)
         self._type = alg
         self.extras = extras or {}
         self.callback = None
 
     # These methods (compressed, read, seek, tell) all appear to only
     # be used by bundlerepo, but it's a little hard to tell.
     def compressed(self):
         return self._type is not None and 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 error.Abort(_("invalid chunk length %d") % l)
             return 0
         if self.callback:
             self.callback()
         return l - 4
 
     def changelogheader(self):
         """v10 does not have a changelog header chunk"""
         return {}
 
     def manifestheader(self):
         """v10 does not have a manifest header chunk"""
         return {}
 
     def filelogheader(self):
         """return the header of the filelogs chunk, v10 only has the filename"""
         l = self._chunklength()
         if not l:
             return {}
         fname = readexactly(self._stream, l)
         return {'filename': fname}
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, cs = headertuple
         if prevnode is None:
             deltabase = p1
         else:
             deltabase = prevnode
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
     def deltachunk(self, prevnode):
         l = self._chunklength()
         if not l:
             return {}
         headerdata = readexactly(self._stream, self.deltaheadersize)
         header = struct.unpack(self.deltaheader, headerdata)
         delta = readexactly(self._stream, l - self.deltaheadersize)
         node, p1, p2, deltabase, cs, flags = self._deltaheader(header, prevnode)
         return {'node': node, 'p1': p1, 'p2': p2, 'cs': cs,
                 'deltabase': deltabase, 'delta': delta, 'flags': flags}
 
     def getchunks(self):
         """returns all the chunks contains in the bundle
 
         Used when you need to forward the binary stream to a file or another
         network API. To do so, it parse the changegroup data, otherwise it will
         block in case of sshrepo because it don't know the end of the stream.
         """
         # an empty chunkgroup is the end of the changegroup
         # a changegroup has at least 2 chunkgroups (changelog and manifest).
         # after that, changegroup versions 1 and 2 have a series of groups
         # with one group per file. changegroup 3 has a series of directory
         # manifests before the files.
         count = 0
         emptycount = 0
         while emptycount < self._grouplistcount:
             empty = True
             count += 1
             while True:
                 chunk = getchunk(self)
                 if not chunk:
                     if empty and count > 2:
                         emptycount += 1
                     break
                 empty = False
                 yield chunkheader(len(chunk))
                 pos = 0
                 while pos < len(chunk):
                     next = pos + 2**20
                     yield chunk[pos:next]
                     pos = next
             yield closechunk()
 
     def _unpackmanifests(self, repo, revmap, trp, prog, numchanges):
         # We know that we'll never have more manifests than we had
         # changesets.
         self.callback = prog(_('manifests'), numchanges)
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         self.manifestheader()
         repo.manifestlog._revlog.addgroup(self, revmap, trp)
         repo.ui.progress(_('manifests'), None)
         self.callback = None
 
     def apply(self, repo, srctype, url, emptyok=False,
               targetphase=phases.draft, expectedtotal=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         repo = repo.unfiltered()
         def csmap(x):
             repo.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         changesets = files = revisions = 0
 
         try:
             with repo.transaction("\n".join([srctype,
                                              util.hidepassword(url)])) as tr:
                 # The transaction could have been created before and already
                 # carries source information. In this case we use the top
                 # level data. We overwrite the argument because we need to use
                 # the top level value (if they exist) in this function.
                 srctype = tr.hookargs.setdefault('source', srctype)
                 url = tr.hookargs.setdefault('url', url)
                 repo.hook('prechangegroup', throw=True, **tr.hookargs)
 
                 # write changelog data to temp files so concurrent readers
                 # will not see an inconsistent view
                 cl = repo.changelog
                 cl.delayupdate(tr)
                 oldheads = cl.heads()
 
                 trp = weakref.proxy(tr)
                 # pull off the changeset group
                 repo.ui.status(_("adding changesets\n"))
                 clstart = len(cl)
                 class prog(object):
                     def __init__(self, step, total):
                         self._step = step
                         self._total = total
                         self._count = 1
                     def __call__(self):
                         repo.ui.progress(self._step, self._count,
                                          unit=_('chunks'), total=self._total)
                         self._count += 1
                 self.callback = prog(_('changesets'), expectedtotal)
 
                 efiles = set()
                 def onchangelog(cl, node):
                     efiles.update(cl.readfiles(node))
 
                 self.changelogheader()
                 srccontent = cl.addgroup(self, csmap, trp,
                                          addrevisioncb=onchangelog)
                 efiles = len(efiles)
 
                 if not (srccontent or emptyok):
                     raise error.Abort(_("received changelog group is empty"))
                 clend = len(cl)
                 changesets = clend - clstart
                 repo.ui.progress(_('changesets'), None)
                 self.callback = None
 
                 # pull off the manifest group
                 repo.ui.status(_("adding manifests\n"))
                 self._unpackmanifests(repo, revmap, trp, prog, changesets)
 
                 needfiles = {}
                 if repo.ui.configbool('server', 'validate', default=False):
                     cl = repo.changelog
                     ml = repo.manifestlog
                     # validate incoming csets have their manifests
                     for cset in xrange(clstart, clend):
                         mfnode = cl.changelogrevision(cset).manifest
                         mfest = ml[mfnode].readdelta()
                         # store file nodes we must see
                         for f, n in mfest.iteritems():
                             needfiles.setdefault(f, set()).add(n)
 
                 # process the files
                 repo.ui.status(_("adding file changes\n"))
                 newrevs, newfiles = _addchangegroupfiles(
                     repo, self, revmap, trp, efiles, needfiles)
                 revisions += newrevs
                 files += newfiles
 
                 dh = 0
                 if oldheads:
                     heads = cl.heads()
                     dh = len(heads) - len(oldheads)
                     for h in heads:
                         if h not in oldheads and repo[h].closesbranch():
                             dh -= 1
                 htext = ""
                 if dh:
                     htext = _(" (%+d heads)") % dh
 
                 repo.ui.status(_("added %d changesets"
                                  " with %d changes to %d files%s\n")
                                  % (changesets, revisions, files, htext))
                 repo.invalidatevolatilesets()
 
                 if changesets > 0:
                     if 'node' not in tr.hookargs:
                         tr.hookargs['node'] = hex(cl.node(clstart))
                         tr.hookargs['node_last'] = hex(cl.node(clend - 1))
                         hookargs = dict(tr.hookargs)
                     else:
                         hookargs = dict(tr.hookargs)
                         hookargs['node'] = hex(cl.node(clstart))
                         hookargs['node_last'] = hex(cl.node(clend - 1))
                     repo.hook('pretxnchangegroup', throw=True, **hookargs)
 
                 added = [cl.node(r) for r in xrange(clstart, clend)]
                 publishing = repo.publishing()
                 if srctype in ('push', 'serve'):
                     # Old servers can not push the boundary themselves.
                     # New servers won't push the boundary if changeset already
                     # exists locally as secret
                     #
                     # We should not use added here but the list of all change in
                     # the bundle
                     if publishing:
                         phases.advanceboundary(repo, tr, phases.public,
                                                srccontent)
                     else:
                         # Those changesets have been pushed from the
                         # outside, their phases are going to be pushed
                         # alongside. Therefor `targetphase` is
                         # ignored.
                         phases.advanceboundary(repo, tr, phases.draft,
                                                srccontent)
                         phases.retractboundary(repo, tr, phases.draft, added)
                 elif srctype != 'strip':
                     # publishing only alter behavior during push
                     #
                     # strip should not touch boundary at all
                     phases.retractboundary(repo, tr, targetphase, added)
 
                 if changesets > 0:
                     if srctype != 'strip':
                         # During strip, branchcache is invalid but
                         # coming call to `destroyed` will repair it.
                         # In other case we can safely update cache on
                         # disk.
                         repo.ui.debug('updating the branch cache\n')
                         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
 
                         repo.hook("changegroup", **hookargs)
 
                         for n in added:
                             args = hookargs.copy()
                             args['node'] = hex(n)
                             del args['node_last']
                             repo.hook("incoming", **args)
 
                         newheads = [h for h in repo.heads()
                                     if h not in oldheads]
                         repo.ui.log("incoming",
                                     "%s incoming changes - new heads: %s\n",
                                     len(added),
                                     ', '.join([hex(c[:6]) for c in newheads]))
 
                     tr.addpostclose('changegroup-runhooks-%020i' % clstart,
                                     lambda tr: repo._afterlock(runhooks))
         finally:
             repo.ui.flush()
         # never return 0 here:
         if dh < 0:
             return dh - 1
         else:
             return dh + 1
 
 class cg2unpacker(cg1unpacker):
     """Unpacker for cg2 streams.
 
     cg2 streams add support for generaldelta, so the delta header
     format is slightly different. All other features about the data
     remain the same.
     """
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '02'
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs = headertuple
         flags = 0
         return node, p1, p2, deltabase, cs, flags
 
 class cg3unpacker(cg2unpacker):
     """Unpacker for cg3 streams.
 
     cg3 streams add support for exchanging treemanifests and revlog
     flags. It adds the revlog flags to the delta header and an empty chunk
     separating manifests and files.
     """
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
     deltaheadersize = struct.calcsize(deltaheader)
     version = '03'
     _grouplistcount = 2 # One list of manifests and one list of files
 
     def _deltaheader(self, headertuple, prevnode):
         node, p1, p2, deltabase, cs, flags = headertuple
         return node, p1, p2, deltabase, cs, flags
 
     def _unpackmanifests(self, repo, revmap, trp, prog, numchanges):
         super(cg3unpacker, self)._unpackmanifests(repo, revmap, trp, prog,
                                                   numchanges)
         for chunkdata in iter(self.filelogheader, {}):
             # If we get here, there are directory manifests in the changegroup
             d = chunkdata["filename"]
             repo.ui.debug("adding %s revisions\n" % d)
             dirlog = repo.manifestlog._revlog.dirlog(d)
             if not dirlog.addgroup(self, revmap, trp):
                 raise error.Abort(_("received dir revlog group is empty"))
 
 class headerlessfixup(object):
     def __init__(self, fh, h):
         self._h = h
         self._fh = fh
     def read(self, n):
         if self._h:
             d, self._h = self._h[:n], self._h[n:]
             if len(d) < n:
                 d += readexactly(self._fh, n - len(d))
             return d
         return readexactly(self._fh, n)
 
 class cg1packer(object):
     deltaheader = _CHANGEGROUPV1_DELTA_HEADER
     version = '01'
     def __init__(self, repo, bundlecaps=None):
         """Given a source repo, construct a bundler.
 
         bundlecaps is optional and can be used to specify the set of
         capabilities which can be used to build the bundle.
         """
         # Set of capabilities we can use to build the bundle.
         if bundlecaps is None:
             bundlecaps = set()
         self._bundlecaps = bundlecaps
         # experimental config: bundle.reorder
         reorder = repo.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
         self._repo = repo
         self._reorder = reorder
         self._progress = repo.ui.progress
         if self._repo.ui.verbose and not self._repo.ui.debugflag:
             self._verbosenote = self._repo.ui.note
         else:
             self._verbosenote = lambda s: None
 
     def close(self):
         return closechunk()
 
     def fileheader(self, fname):
         return chunkheader(len(fname)) + fname
 
     # Extracted both for clarity and for overriding in extensions.
     def _sortgroup(self, revlog, nodelist, lookup):
         """Sort nodes for change group and turn them into revnums."""
         # for generaldelta revlogs, we linearize the revs; this will both be
         # much quicker and generate a much smaller bundle
         if (revlog._generaldelta and self._reorder is None) or self._reorder:
             dag = dagutil.revlogdag(revlog)
             return dag.linearize(set(revlog.rev(n) for n in nodelist))
         else:
             return sorted([revlog.rev(n) for n in nodelist])
 
     def group(self, nodelist, revlog, lookup, units=None):
         """Calculate a delta group, yielding a sequence of changegroup chunks
         (strings).
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. The first delta is
         first parent(nodelist[0]) -> nodelist[0], the receiver is
         guaranteed to have this parent as it has all history before
         these changesets. In the case firstparent is nullrev the
         changegroup starts with a full revision.
 
         If units is not None, progress detail will be generated, units specifies
         the type of revlog that is touched (changelog, manifest, etc.).
         """
         # if we don't have any revisions touched by these changesets, bail
         if len(nodelist) == 0:
             yield self.close()
             return
 
         revs = self._sortgroup(revlog, nodelist, lookup)
 
         # add the parent of the first rev
         p = revlog.parentrevs(revs[0])[0]
         revs.insert(0, p)
 
         # build deltas
         total = len(revs) - 1
         msgbundling = _('bundling')
         for r in xrange(len(revs) - 1):
             if units is not None:
                 self._progress(msgbundling, r + 1, unit=units, total=total)
             prev, curr = revs[r], revs[r + 1]
             linknode = lookup(revlog.node(curr))
             for c in self.revchunk(revlog, curr, prev, linknode):
                 yield c
 
         if units is not None:
             self._progress(msgbundling, None)
         yield self.close()
 
     # filter any nodes that claim to be part of the known set
     def prune(self, revlog, missing, commonrevs):
         rr, rl = revlog.rev, revlog.linkrev
         return [n for n in missing if rl(rr(n)) not in commonrevs]
 
     def _packmanifests(self, dir, mfnodes, lookuplinknode):
         """Pack flat manifests into a changegroup stream."""
         assert not dir
         for chunk in self.group(mfnodes, self._repo.manifestlog._revlog,
                                 lookuplinknode, units=_('manifests')):
             yield chunk
 
     def _manifestsdone(self):
         return ''
 
     def generate(self, commonrevs, clnodes, fastpathlinkrev, source):
         '''yield a sequence of changegroup chunks (strings)'''
         repo = self._repo
         cl = repo.changelog
 
         clrevorder = {}
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
 
         # Callback for the changelog, used to collect changed files and manifest
         # nodes.
         # Returns the linkrev node (identity in the changelog case).
         def lookupcl(x):
             c = cl.read(x)
             clrevorder[x] = len(clrevorder)
             n = c[0]
             # record the first changeset introducing this manifest version
             mfs.setdefault(n, x)
             # Record a complete list of potentially-changed files in
             # this manifest.
             changedfiles.update(c[3])
             return x
 
         self._verbosenote(_('uncompressed size of bundle content:\n'))
         size = 0
         for chunk in self.group(clnodes, cl, lookupcl, units=_('changesets')):
             size += len(chunk)
             yield chunk
         self._verbosenote(_('%8.i (changelog)\n') % size)
 
         # We need to make sure that the linkrev in the changegroup refers to
         # the first changeset that introduced the manifest or file revision.
         # The fastpath is usually safer than the slowpath, because the filelogs
         # are walked in revlog order.
         #
         # When taking the slowpath with reorder=None and the manifest revlog
         # uses generaldelta, the manifest may be walked in the "wrong" order.
         # Without 'clrevorder', we would get an incorrect linkrev (see fix in
         # cc0ff93d0c0c).
         #
         # When taking the fastpath, we are only vulnerable to reordering
         # of the changelog itself. The changelog never uses generaldelta, so
         # it is only reordered when reorder=True. To handle this case, we
         # simply take the slowpath, which already has the 'clrevorder' logic.
         # This was also fixed in cc0ff93d0c0c.
         fastpathlinkrev = fastpathlinkrev and not self._reorder
         # Treemanifests don't work correctly with fastpathlinkrev
         # either, because we don't discover which directory nodes to
         # send along with files. This could probably be fixed.
         fastpathlinkrev = fastpathlinkrev and (
             'treemanifest' not in repo.requirements)
 
         for chunk in self.generatemanifests(commonrevs, clrevorder,
                 fastpathlinkrev, mfs, fnodes):
             yield chunk
         mfs.clear()
         clrevs = set(cl.rev(x) for x in clnodes)
 
         if not fastpathlinkrev:
             def linknodes(unused, fname):
                 return fnodes.get(fname, {})
         else:
             cln = cl.node
             def linknodes(filerevlog, fname):
                 llr = filerevlog.linkrev
                 fln = filerevlog.node
                 revs = ((r, llr(r)) for r in filerevlog)
                 return dict((fln(r), cln(lr)) for r, lr in revs if lr in clrevs)
 
         for chunk in self.generatefiles(changedfiles, linknodes, commonrevs,
                                         source):
             yield chunk
 
         yield self.close()
 
         if clnodes:
             repo.hook('outgoing', node=hex(clnodes[0]), source=source)
 
     def generatemanifests(self, commonrevs, clrevorder, fastpathlinkrev, mfs,
                           fnodes):
         repo = self._repo
         mfl = repo.manifestlog
         dirlog = mfl._revlog.dirlog
         tmfnodes = {'': mfs}
 
         # Callback for the manifest, used to collect linkrevs for filelog
         # revisions.
         # Returns the linkrev node (collected in lookupcl).
         def makelookupmflinknode(dir):
             if fastpathlinkrev:
                 assert not dir
                 return mfs.__getitem__
 
             def lookupmflinknode(x):
                 """Callback for looking up the linknode for manifests.
 
                 Returns the linkrev node for the specified manifest.
 
                 SIDE EFFECT:
 
                 1) fclnodes gets populated with the list of relevant
                    file nodes if we're not using fastpathlinkrev
                 2) When treemanifests are in use, collects treemanifest nodes
                    to send
 
                 Note that this means manifests must be completely sent to
                 the client before you can trust the list of files and
                 treemanifests to send.
                 """
                 clnode = tmfnodes[dir][x]
                 mdata = mfl.get(dir, x).readfast(shallow=True)
                 for p, n, fl in mdata.iterentries():
                     if fl == 't': # subdirectory manifest
                         subdir = dir + p + '/'
                         tmfclnodes = tmfnodes.setdefault(subdir, {})
                         tmfclnode = tmfclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[tmfclnode]:
                             tmfclnodes[n] = clnode
                     else:
                         f = dir + p
                         fclnodes = fnodes.setdefault(f, {})
                         fclnode = fclnodes.setdefault(n, clnode)
                         if clrevorder[clnode] < clrevorder[fclnode]:
                             fclnodes[n] = clnode
                 return clnode
             return lookupmflinknode
 
         size = 0
         while tmfnodes:
             dir = min(tmfnodes)
             nodes = tmfnodes[dir]
             prunednodes = self.prune(dirlog(dir), nodes, commonrevs)
             if not dir or prunednodes:
                 for x in self._packmanifests(dir, prunednodes,
                                              makelookupmflinknode(dir)):
                     size += len(x)
                     yield x
             del tmfnodes[dir]
         self._verbosenote(_('%8.i (manifests)\n') % size)
         yield self._manifestsdone()
 
     # The 'source' parameter is useful for extensions
     def generatefiles(self, changedfiles, linknodes, commonrevs, source):
         repo = self._repo
         progress = self._progress
         msgbundling = _('bundling')
 
         total = len(changedfiles)
         # for progress output
         msgfiles = _('files')
         for i, fname in enumerate(sorted(changedfiles)):
             filerevlog = repo.file(fname)
             if not filerevlog:
                 raise error.Abort(_("empty or missing revlog for %s") % fname)
 
             linkrevnodes = linknodes(filerevlog, fname)
             # Lookup for filenodes, we collected the linkrev nodes above in the
             # fastpath case and with lookupmf in the slowpath case.
             def lookupfilelog(x):
                 return linkrevnodes[x]
 
             filenodes = self.prune(filerevlog, linkrevnodes, commonrevs)
             if filenodes:
                 progress(msgbundling, i + 1, item=fname, unit=msgfiles,
                          total=total)
                 h = self.fileheader(fname)
                 size = len(h)
                 yield h
                 for chunk in self.group(filenodes, filerevlog, lookupfilelog):
                     size += len(chunk)
                     yield chunk
                 self._verbosenote(_('%8.i  %s\n') % (size, fname))
         progress(msgbundling, None)
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         return prev
 
     def revchunk(self, revlog, rev, prev, linknode):
         node = revlog.node(rev)
         p1, p2 = revlog.parentrevs(rev)
         base = self.deltaparent(revlog, rev, p1, p2, prev)
 
         prefix = ''
         if revlog.iscensored(base) or revlog.iscensored(rev):
             try:
-                delta = revlog.revision(node)
+                delta = revlog.revision(node, raw=True)
             except error.CensoredNodeError as e:
                 delta = e.tombstone
             if base == nullrev:
                 prefix = mdiff.trivialdiffheader(len(delta))
             else:
                 baselen = revlog.rawsize(base)
                 prefix = mdiff.replacediffheader(baselen, len(delta))
         elif base == nullrev:
-            delta = revlog.revision(node)
+            delta = revlog.revision(node, raw=True)
             prefix = mdiff.trivialdiffheader(len(delta))
         else:
             delta = revlog.revdiff(base, rev)
         p1n, p2n = revlog.parents(node)
         basenode = revlog.node(base)
         flags = revlog.flags(rev)
         meta = self.builddeltaheader(node, p1n, p2n, basenode, linknode, flags)
         meta += prefix
         l = len(meta) + len(delta)
         yield chunkheader(l)
         yield meta
         yield delta
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         # do nothing with basenode, it is implicitly the previous one in HG10
         # do nothing with flags, it is implicitly 0 for cg1 and cg2
         return struct.pack(self.deltaheader, node, p1n, p2n, linknode)
 
 class cg2packer(cg1packer):
     version = '02'
     deltaheader = _CHANGEGROUPV2_DELTA_HEADER
 
     def __init__(self, repo, bundlecaps=None):
         super(cg2packer, self).__init__(repo, bundlecaps)
         if self._reorder is None:
             # Since generaldelta is directly supported by cg2, reordering
             # generally doesn't help, so we disable it by default (treating
             # bundle.reorder=auto just like bundle.reorder=False).
             self._reorder = False
 
     def deltaparent(self, revlog, rev, p1, p2, prev):
         dp = revlog.deltaparent(rev)
         if dp == nullrev and revlog.storedeltachains:
             # Avoid sending full revisions when delta parent is null. Pick prev
             # in that case. It's tempting to pick p1 in this case, as p1 will
             # be smaller in the common case. However, computing a delta against
             # p1 may require resolving the raw text of p1, which could be
             # expensive. The revlog caches should have prev cached, meaning
             # less CPU for changegroup generation. There is likely room to add
             # a flag and/or config option to control this behavior.
             return prev
         elif dp == nullrev:
             # revlog is configured to use full snapshot for a reason,
             # stick to full snapshot.
             return nullrev
         elif dp not in (p1, p2, prev):
             # Pick prev when we can't be sure remote has the base revision.
             return prev
         else:
             return dp
 
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         # Do nothing with flags, it is implicitly 0 in cg1 and cg2
         return struct.pack(self.deltaheader, node, p1n, p2n, basenode, linknode)
 
 class cg3packer(cg2packer):
     version = '03'
     deltaheader = _CHANGEGROUPV3_DELTA_HEADER
 
     def _packmanifests(self, dir, mfnodes, lookuplinknode):
         if dir:
             yield self.fileheader(dir)
 
         dirlog = self._repo.manifestlog._revlog.dirlog(dir)
         for chunk in self.group(mfnodes, dirlog, lookuplinknode,
                                 units=_('manifests')):
             yield chunk
 
     def _manifestsdone(self):
         return self.close()
 
     def builddeltaheader(self, node, p1n, p2n, basenode, linknode, flags):
         return struct.pack(
             self.deltaheader, node, p1n, p2n, basenode, linknode, flags)
 
 _packermap = {'01': (cg1packer, cg1unpacker),
              # cg2 adds support for exchanging generaldelta
              '02': (cg2packer, cg2unpacker),
              # cg3 adds support for exchanging revlog flags and treemanifests
              '03': (cg3packer, cg3unpacker),
 }
 
 def allsupportedversions(repo):
     versions = set(_packermap.keys())
     if not (repo.ui.configbool('experimental', 'changegroup3') or
             repo.ui.configbool('experimental', 'treemanifest') or
             'treemanifest' in repo.requirements):
         versions.discard('03')
     return versions
 
 # Changegroup versions that can be applied to the repo
 def supportedincomingversions(repo):
     return allsupportedversions(repo)
 
 # Changegroup versions that can be created from the repo
 def supportedoutgoingversions(repo):
     versions = allsupportedversions(repo)
     if 'treemanifest' in repo.requirements:
         # Versions 01 and 02 support only flat manifests and it's just too
         # expensive to convert between the flat manifest and tree manifest on
         # the fly. Since tree manifests are hashed differently, all of history
         # would have to be converted. Instead, we simply don't even pretend to
         # support versions 01 and 02.
         versions.discard('01')
         versions.discard('02')
     return versions
 
 def safeversion(repo):
     # Finds the smallest version that it's safe to assume clients of the repo
     # will support. For example, all hg versions that support generaldelta also
     # support changegroup 02.
     versions = supportedoutgoingversions(repo)
     if 'generaldelta' in repo.requirements:
         versions.discard('01')
     assert versions
     return min(versions)
 
 def getbundler(version, repo, bundlecaps=None):
     assert version in supportedoutgoingversions(repo)
     return _packermap[version][0](repo, bundlecaps)
 
 def getunbundler(version, fh, alg, extras=None):
     return _packermap[version][1](fh, alg, extras=extras)
 
 def _changegroupinfo(repo, nodes, source):
     if repo.ui.verbose or source == 'bundle':
         repo.ui.status(_("%d changesets found\n") % len(nodes))
     if repo.ui.debugflag:
         repo.ui.debug("list of changesets:\n")
         for node in nodes:
             repo.ui.debug("%s\n" % hex(node))
 
 def getsubsetraw(repo, outgoing, bundler, source, fastpath=False):
     repo = repo.unfiltered()
     commonrevs = outgoing.common
     csets = outgoing.missing
     heads = outgoing.missingheads
     # We go through the fast path if we get told to, or if all (unfiltered
     # heads have been requested (since we then know there all linkrevs will
     # be pulled by the client).
     heads.sort()
     fastpathlinkrev = fastpath or (
             repo.filtername is None and heads == sorted(repo.heads()))
 
     repo.hook('preoutgoing', throw=True, source=source)
     _changegroupinfo(repo, csets, source)
     return bundler.generate(commonrevs, csets, fastpathlinkrev, source)
 
 def getsubset(repo, outgoing, bundler, source, fastpath=False):
     gengroup = getsubsetraw(repo, outgoing, bundler, source, fastpath)
     return getunbundler(bundler.version, util.chunkbuffer(gengroup), None,
                         {'clcount': len(outgoing.missing)})
 
 def changegroupsubset(repo, roots, heads, source, version='01'):
     """Compute a changegroup consisting of all the nodes that are
     descendants of any of the roots and ancestors of any of the heads.
     Return a chunkbuffer object whose read() method will return
     successive changegroup chunks.
 
     It is fairly complex as determining which filenodes and which
     manifest nodes need to be included for the changeset to be complete
     is non-trivial.
 
     Another wrinkle is doing the reverse, figuring out which changeset in
     the changegroup a particular filenode or manifestnode belongs to.
     """
     outgoing = discovery.outgoing(repo, missingroots=roots, missingheads=heads)
     bundler = getbundler(version, repo)
     return getsubset(repo, outgoing, bundler, source)
 
 def getlocalchangegroupraw(repo, source, outgoing, bundlecaps=None,
                            version='01'):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing. Returns a raw changegroup generator."""
     if not outgoing.missing:
         return None
     bundler = getbundler(version, repo, bundlecaps)
     return getsubsetraw(repo, outgoing, bundler, source)
 
 def getlocalchangegroup(repo, source, outgoing, bundlecaps=None,
                         version='01'):
     """Like getbundle, but taking a discovery.outgoing as an argument.
 
     This is only implemented for local repos and reuses potentially
     precomputed sets in outgoing."""
     if not outgoing.missing:
         return None
     bundler = getbundler(version, repo, bundlecaps)
     return getsubset(repo, outgoing, bundler, source)
 
 def getchangegroup(repo, source, outgoing, bundlecaps=None,
                    version='01'):
     """Like changegroupsubset, but returns the set difference between the
     ancestors of heads and the ancestors common.
 
     If heads is None, use the local heads. If common is None, use [nullid].
 
     The nodes in common might not all be known locally due to the way the
     current discovery protocol works.
     """
     return getlocalchangegroup(repo, source, outgoing, bundlecaps=bundlecaps,
                                version=version)
 
 def changegroup(repo, basenodes, source):
     # to avoid a race we use changegroupsubset() (issue1320)
     return changegroupsubset(repo, basenodes, repo.heads(), source)
 
 def _addchangegroupfiles(repo, source, revmap, trp, expectedfiles, needfiles):
     revisions = 0
     files = 0
     for chunkdata in iter(source.filelogheader, {}):
         files += 1
         f = chunkdata["filename"]
         repo.ui.debug("adding %s revisions\n" % f)
         repo.ui.progress(_('files'), files, unit=_('files'),
                          total=expectedfiles)
         fl = repo.file(f)
         o = len(fl)
         try:
             if not fl.addgroup(source, revmap, trp):
                 raise error.Abort(_("received file revlog group is empty"))
         except error.CensoredBaseError as e:
             raise error.Abort(_("received delta base is censored: %s") % e)
         revisions += len(fl) - o
         if f in needfiles:
             needs = needfiles[f]
             for new in xrange(o, len(fl)):
                 n = fl.node(new)
                 if n in needs:
                     needs.remove(n)
                 else:
                     raise error.Abort(
                         _("received spurious file revlog entry"))
             if not needs:
                 del needfiles[f]
     repo.ui.progress(_('files'), None)
 
     for f, needs in needfiles.iteritems():
         fl = repo.file(f)
         for n in needs:
             try:
                 fl.rev(n)
             except error.LookupError:
                 raise error.Abort(
                     _('missing file data for %s:%s - run hg verify') %
                     (f, hex(n)))
 
     return revisions, files

mercurial/context.py

@@ -1,2111 +1,2114 b''
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 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 __future__ import absolute_import
 
 import errno
 import os
 import re
 import stat
 
 from .i18n import _
 from .node import (
     addednodeid,
     bin,
     hex,
     modifiednodeid,
     newnodeid,
     nullid,
     nullrev,
     short,
     wdirid,
 )
 from . import (
     encoding,
     error,
     fileset,
     match as matchmod,
     mdiff,
     obsolete as obsmod,
     patch,
     phases,
     repoview,
     revlog,
     scmutil,
     subrepo,
     util,
 )
 
 propertycache = util.propertycache
 
 nonascii = re.compile(r'[^\x21-\x7f]').search
 
 class basectx(object):
     """A basectx object represents the common logic for its children:
     changectx: read-only context that is already present in the repo,
     workingctx: a context that represents the working directory and can
                 be committed,
     memctx: a context that represents changes in-memory and can also
             be committed."""
     def __new__(cls, repo, changeid='', *args, **kwargs):
         if isinstance(changeid, basectx):
             return changeid
 
         o = super(basectx, cls).__new__(cls)
 
         o._repo = repo
         o._rev = nullrev
         o._node = nullid
 
         return o
 
     def __str__(self):
         return short(self.node())
 
     def __int__(self):
         return self.rev()
 
     def __repr__(self):
         return "<%s %s>" % (type(self).__name__, str(self))
 
     def __eq__(self, other):
         try:
             return type(self) == type(other) and self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         return iter(self._manifest)
 
     def _manifestmatches(self, match, s):
         """generate a new manifest filtered by the match argument
 
         This method is for internal use only and mainly exists to provide an
         object oriented way for other contexts to customize the manifest
         generation.
         """
         return self.manifest().matches(match)
 
     def _matchstatus(self, other, match):
         """return match.always if match is none
 
         This internal method provides a way for child objects to override the
         match operator.
         """
         return match or matchmod.always(self._repo.root, self._repo.getcwd())
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context"""
         # Load earliest manifest first for caching reasons. More specifically,
         # if you have revisions 1000 and 1001, 1001 is probably stored as a
         # delta against 1000. Thus, if you read 1000 first, we'll reconstruct
         # 1000 and cache it so that when you read 1001, we just need to apply a
         # delta to what's in the cache. So that's one full reconstruction + one
         # delta application.
         if self.rev() is not None and self.rev() < other.rev():
             self.manifest()
         mf1 = other._manifestmatches(match, s)
         mf2 = self._manifestmatches(match, s)
 
         modified, added = [], []
         removed = []
         clean = []
         deleted, unknown, ignored = s.deleted, s.unknown, s.ignored
         deletedset = set(deleted)
         d = mf1.diff(mf2, clean=listclean)
         for fn, value in d.iteritems():
             if fn in deletedset:
                 continue
             if value is None:
                 clean.append(fn)
                 continue
             (node1, flag1), (node2, flag2) = value
             if node1 is None:
                 added.append(fn)
             elif node2 is None:
                 removed.append(fn)
             elif flag1 != flag2:
                 modified.append(fn)
             elif node2 != newnodeid:
                 # When comparing files between two commits, we save time by
                 # not comparing the file contents when the nodeids differ.
                 # Note that this means we incorrectly report a reverted change
                 # to a file as a modification.
                 modified.append(fn)
             elif self[fn].cmp(other[fn]):
                 modified.append(fn)
             else:
                 clean.append(fn)
 
         if removed:
             # need to filter files if they are already reported as removed
             unknown = [fn for fn in unknown if fn not in mf1]
             ignored = [fn for fn in ignored if fn not in mf1]
             # if they're deleted, don't report them as removed
             removed = [fn for fn in removed if fn not in deletedset]
 
         return scmutil.status(modified, added, removed, deleted, unknown,
                               ignored, clean)
 
     @propertycache
     def substate(self):
         return subrepo.state(self, self._repo.ui)
 
     def subrev(self, subpath):
         return self.substate[subpath][1]
 
     def rev(self):
         return self._rev
     def node(self):
         return self._node
     def hex(self):
         return hex(self.node())
     def manifest(self):
         return self._manifest
     def manifestctx(self):
         return self._manifestctx
     def repo(self):
         return self._repo
     def phasestr(self):
         return phases.phasenames[self.phase()]
     def mutable(self):
         return self.phase() > phases.public
 
     def getfileset(self, expr):
         return fileset.getfileset(self, expr)
 
     def obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, 'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, 'extinct')
 
     def unstable(self):
         """True if the changeset is not obsolete but it's ancestor are"""
         return self.rev() in obsmod.getrevs(self._repo, 'unstable')
 
     def bumped(self):
         """True if the changeset try to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be bumped.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'bumped')
 
     def divergent(self):
         """Is a successors of a changeset with multiple possible successors set
 
         Only non-public and non-obsolete changesets may be divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'divergent')
 
     def troubled(self):
         """True if the changeset is either unstable, bumped or divergent"""
         return self.unstable() or self.bumped() or self.divergent()
 
     def troubles(self):
         """return the list of troubles affecting this changesets.
 
         Troubles are returned as strings. possible values are:
         - unstable,
         - bumped,
         - divergent.
         """
         troubles = []
         if self.unstable():
             troubles.append('unstable')
         if self.bumped():
             troubles.append('bumped')
         if self.divergent():
             troubles.append('divergent')
         return troubles
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         parents = self._parents
         if len(parents) == 2:
             return parents[1]
         return changectx(self._repo, nullrev)
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.ManifestLookupError(self._node, path,
                                                 _('not found in manifest'))
         if '_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return (self._manifestdelta[path],
                         self._manifestdelta.flags(path))
         mfl = self._repo.manifestlog
         try:
             node, flag = mfl[self._changeset.manifest].find(path)
         except KeyError:
             raise error.ManifestLookupError(self._node, path,
                                             _('not found in manifest'))
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return ''
 
     def sub(self, path, allowcreate=True):
         '''return a subrepo for the stored revision of path, never wdir()'''
         return subrepo.subrepo(self, path, allowcreate=allowcreate)
 
     def nullsub(self, path, pctx):
         return subrepo.nullsubrepo(self, path, pctx)
 
     def workingsub(self, path):
         '''return a subrepo for the stored revision, or wdir if this is a wdir
         context.
         '''
         return subrepo.subrepo(self, path, allowwdir=True)
 
     def match(self, pats=[], include=None, exclude=None, default='glob',
               listsubrepos=False, badfn=None):
         r = self._repo
         return matchmod.match(r.root, r.getcwd(), pats,
                               include, exclude, default,
                               auditor=r.nofsauditor, ctx=self,
                               listsubrepos=listsubrepos, badfn=badfn)
 
     def diff(self, ctx2=None, match=None, **opts):
         """Returns a diff generator for the given contexts and matcher"""
         if ctx2 is None:
             ctx2 = self.p1()
         if ctx2 is not None:
             ctx2 = self._repo[ctx2]
         diffopts = patch.diffopts(self._repo.ui, opts)
         return patch.diff(self._repo, ctx2, self, match=match, opts=diffopts)
 
     def dirs(self):
         return self._manifest.dirs()
 
     def hasdir(self, dir):
         return self._manifest.hasdir(dir)
 
     def dirty(self, missing=False, merge=True, branch=True):
         return False
 
     def status(self, other=None, match=None, listignored=False,
                listclean=False, listunknown=False, listsubrepos=False):
         """return status of files between two nodes or node and working
         directory.
 
         If other is None, compare this node with working directory.
 
         returns (modified, added, removed, deleted, unknown, ignored, clean)
         """
 
         ctx1 = self
         ctx2 = self._repo[other]
 
         # This next code block is, admittedly, fragile logic that tests for
         # reversing the contexts and wouldn't need to exist if it weren't for
         # the fast (and common) code path of comparing the working directory
         # with its first parent.
         #
         # What we're aiming for here is the ability to call:
         #
         # workingctx.status(parentctx)
         #
         # If we always built the manifest for each context and compared those,
         # then we'd be done. But the special case of the above call means we
         # just copy the manifest of the parent.
         reversed = False
         if (not isinstance(ctx1, changectx)
             and isinstance(ctx2, changectx)):
             reversed = True
             ctx1, ctx2 = ctx2, ctx1
 
         match = ctx2._matchstatus(ctx1, match)
         r = scmutil.status([], [], [], [], [], [], [])
         r = ctx2._buildstatus(ctx1, r, match, listignored, listclean,
                               listunknown)
 
         if reversed:
             # Reverse added and removed. Clear deleted, unknown and ignored as
             # these make no sense to reverse.
             r = scmutil.status(r.modified, r.removed, r.added, [], [], [],
                                r.clean)
 
         if listsubrepos:
             for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
                 try:
                     rev2 = ctx2.subrev(subpath)
                 except KeyError:
                     # A subrepo that existed in node1 was deleted between
                     # node1 and node2 (inclusive). Thus, ctx2's substate
                     # won't contain that subpath. The best we can do ignore it.
                     rev2 = None
                 submatch = matchmod.subdirmatcher(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)
 
         for l in r:
             l.sort()
 
         return r
 
 
 def makememctx(repo, parents, text, user, date, branch, files, store,
                editor=None, extra=None):
     def getfilectx(repo, memctx, path):
         data, mode, copied = store.getfile(path)
         if data is None:
             return None
         islink, isexec = mode
         return memfilectx(repo, path, data, islink=islink, isexec=isexec,
                                   copied=copied, memctx=memctx)
     if extra is None:
         extra = {}
     if branch:
         extra['branch'] = encoding.fromlocal(branch)
     ctx = memctx(repo, parents, text, files, getfilectx, user,
                  date, extra, editor)
     return ctx
 
 class changectx(basectx):
     """A changecontext object makes access to data related to a particular
     changeset convenient. It represents a read-only context already present in
     the repo."""
     def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
 
         # since basectx.__new__ already took care of copying the object, we
         # don't need to do anything in __init__, so we just exit here
         if isinstance(changeid, basectx):
             return
 
         if changeid == '':
             changeid = '.'
         self._repo = repo
 
         try:
             if isinstance(changeid, int):
                 self._node = repo.changelog.node(changeid)
                 self._rev = changeid
                 return
             if isinstance(changeid, long):
                 changeid = str(changeid)
             if changeid == 'null':
                 self._node = nullid
                 self._rev = nullrev
                 return
             if changeid == 'tip':
                 self._node = repo.changelog.tip()
                 self._rev = repo.changelog.rev(self._node)
                 return
             if changeid == '.' or changeid == repo.dirstate.p1():
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 self._node = repo.dirstate.p1()
                 self._rev = repo.unfiltered().changelog.rev(self._node)
                 return
             if len(changeid) == 20:
                 try:
                     self._node = changeid
                     self._rev = repo.changelog.rev(changeid)
                     return
                 except error.FilteredRepoLookupError:
                     raise
                 except LookupError:
                     pass
 
             try:
                 r = int(changeid)
                 if str(r) != changeid:
                     raise ValueError
                 l = len(repo.changelog)
                 if r < 0:
                     r += l
                 if r < 0 or r >= l:
                     raise ValueError
                 self._rev = r
                 self._node = repo.changelog.node(r)
                 return
             except error.FilteredIndexError:
                 raise
             except (ValueError, OverflowError, IndexError):
                 pass
 
             if len(changeid) == 40:
                 try:
                     self._node = bin(changeid)
                     self._rev = repo.changelog.rev(self._node)
                     return
                 except error.FilteredLookupError:
                     raise
                 except (TypeError, LookupError):
                     pass
 
             # lookup bookmarks through the name interface
             try:
                 self._node = repo.names.singlenode(repo, changeid)
                 self._rev = repo.changelog.rev(self._node)
                 return
             except KeyError:
                 pass
             except error.FilteredRepoLookupError:
                 raise
             except error.RepoLookupError:
                 pass
 
             self._node = repo.unfiltered().changelog._partialmatch(changeid)
             if self._node is not None:
                 self._rev = repo.changelog.rev(self._node)
                 return
 
             # lookup failed
             # check if it might have come from damaged dirstate
             #
             # XXX we could avoid the unfiltered if we had a recognizable
             # exception for filtered changeset access
             if changeid in repo.unfiltered().dirstate.parents():
                 msg = _("working directory has unknown parent '%s'!")
                 raise error.Abort(msg % short(changeid))
             try:
                 if len(changeid) == 20 and nonascii(changeid):
                     changeid = hex(changeid)
             except TypeError:
                 pass
         except (error.FilteredIndexError, error.FilteredLookupError,
                 error.FilteredRepoLookupError):
             if repo.filtername.startswith('visible'):
                 msg = _("hidden revision '%s'") % changeid
                 hint = _('use --hidden to access hidden revisions')
                 raise error.FilteredRepoLookupError(msg, hint=hint)
             msg = _("filtered revision '%s' (not in '%s' subset)")
             msg %= (changeid, repo.filtername)
             raise error.FilteredRepoLookupError(msg)
         except IndexError:
             pass
         raise error.RepoLookupError(
             _("unknown revision '%s'") % changeid)
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.changelogrevision(self.rev())
 
     @propertycache
     def _manifest(self):
         return self._manifestctx.read()
 
     @propertycache
     def _manifestctx(self):
         return self._repo.manifestlog[self._changeset.manifest]
 
     @propertycache
     def _manifestdelta(self):
         return self._manifestctx.readdelta()
 
     @propertycache
     def _parents(self):
         repo = self._repo
         p1, p2 = repo.changelog.parentrevs(self._rev)
         if p2 == nullrev:
             return [changectx(repo, p1)]
         return [changectx(repo, p1), changectx(repo, p2)]
 
     def changeset(self):
         c = self._changeset
         return (
             c.manifest,
             c.user,
             c.date,
             c.files,
             c.description,
             c.extra,
         )
     def manifestnode(self):
         return self._changeset.manifest
 
     def user(self):
         return self._changeset.user
     def date(self):
         return self._changeset.date
     def files(self):
         return self._changeset.files
     def description(self):
         return self._changeset.description
     def branch(self):
         return encoding.tolocal(self._changeset.extra.get("branch"))
     def closesbranch(self):
         return 'close' in self._changeset.extra
     def extra(self):
         return self._changeset.extra
     def tags(self):
         return self._repo.nodetags(self._node)
     def bookmarks(self):
         return self._repo.nodebookmarks(self._node)
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, 'visible')
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors([self._rev]):
             yield changectx(self._repo, a)
 
     def descendants(self):
         for d in self._repo.changelog.descendants([self._rev]):
             yield changectx(self._repo, d)
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
     def ancestor(self, c2, warn=False):
         """return the "best" ancestor context of self and c2
 
         If there are multiple candidates, it will show a message and check
         merge.preferancestor configuration before falling back to the
         revlog ancestor."""
         # deal with workingctxs
         n2 = c2._node
         if n2 is None:
             n2 = c2._parents[0]._node
         cahs = self._repo.changelog.commonancestorsheads(self._node, n2)
         if not cahs:
             anc = nullid
         elif len(cahs) == 1:
             anc = cahs[0]
         else:
             # experimental config: merge.preferancestor
             for r in self._repo.ui.configlist('merge', 'preferancestor', ['*']):
                 try:
                     ctx = changectx(self._repo, r)
                 except error.RepoLookupError:
                     continue
                 anc = ctx.node()
                 if anc in cahs:
                     break
             else:
                 anc = self._repo.changelog.ancestor(self._node, n2)
             if warn:
                 self._repo.ui.status(
                     (_("note: using %s as ancestor of %s and %s\n") %
                      (short(anc), short(self._node), short(n2))) +
                     ''.join(_("      alternatively, use --config "
                               "merge.preferancestor=%s\n") %
                             short(n) for n in sorted(cahs) if n != anc))
         return changectx(self._repo, anc)
 
     def descendant(self, other):
         """True if other is descendant of this changeset"""
         return self._repo.changelog.descendant(self._rev, other._rev)
 
     def walk(self, match):
         '''Generates matching file names.'''
 
         # Wrap match.bad method to have message with nodeid
         def bad(fn, msg):
             # The manifest doesn't know about subrepos, so don't complain about
             # paths into valid subrepos.
             if any(fn == s or fn.startswith(s + '/')
                    for s in self.substate):
                 return
             match.bad(fn, _('no such file in rev %s') % self)
 
         m = matchmod.badmatch(match, bad)
         return self._manifest.walk(m)
 
     def matches(self, match):
         return self.walk(match)
 
 class basefilectx(object):
     """A filecontext object represents the common logic for its children:
     filectx: read-only access to a filerevision that is already present
              in the repo,
     workingfilectx: a filecontext that represents files from the working
                     directory,
     memfilectx: a filecontext that represents files in-memory."""
     def __new__(cls, repo, path, *args, **kwargs):
         return super(basefilectx, cls).__new__(cls)
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if '_changeid' in self.__dict__:
             return self._changeid
         elif '_changectx' in self.__dict__:
             return self._changectx.rev()
         elif '_descendantrev' in self.__dict__:
             # this file context was created from a revision with a known
             # descendant, we can (lazily) correct for linkrev aliases
             return self._adjustlinkrev(self._descendantrev)
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if '_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     def __str__(self):
         try:
             return "%s@%s" % (self.path(), self._changectx)
         except error.LookupError:
             return "%s@???" % self.path()
 
     def __repr__(self):
         return "<%s %s>" % (type(self).__name__, str(self))
 
     def __hash__(self):
         try:
             return hash((self._path, self._filenode))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (type(self) == type(other) and self._path == other._path
                     and self._filenode == other._filenode)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filerev(self):
         return self._filerev
     def filenode(self):
         return self._filenode
     def flags(self):
         return self._changectx.flags(self._path)
     def filelog(self):
         return self._filelog
     def rev(self):
         return self._changeid
     def linkrev(self):
         return self._filelog.linkrev(self._filerev)
     def node(self):
         return self._changectx.node()
     def hex(self):
         return self._changectx.hex()
     def user(self):
         return self._changectx.user()
     def date(self):
         return self._changectx.date()
     def files(self):
         return self._changectx.files()
     def description(self):
         return self._changectx.description()
     def branch(self):
         return self._changectx.branch()
     def extra(self):
         return self._changectx.extra()
     def phase(self):
         return self._changectx.phase()
     def phasestr(self):
         return self._changectx.phasestr()
     def manifest(self):
         return self._changectx.manifest()
     def changectx(self):
         return self._changectx
     def repo(self):
         return self._repo
 
     def path(self):
         return self._path
 
     def isbinary(self):
         try:
             return util.binary(self.data())
         except IOError:
             return False
     def isexec(self):
         return 'x' in self.flags()
     def islink(self):
         return 'l' in self.flags()
 
     def isabsent(self):
         """whether this filectx represents a file not in self._changectx
 
         This is mainly for merge code to detect change/delete conflicts. This is
         expected to be True for all subclasses of basectx."""
         return False
 
     _customcmp = False
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         if fctx._customcmp:
             return fctx.cmp(self)
 
         if (fctx._filenode is None
             and (self._repo._encodefilterpats
                  # if file data starts with '\1\n', empty metadata block is
                  # prepended, which adds 4 bytes to filelog.size().
                  or self.size() - 4 == fctx.size())
             or self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
 
         return True
 
     def _adjustlinkrev(self, srcrev, inclusive=False):
         """return the first ancestor of <srcrev> introducing <fnode>
 
         If the linkrev of the file revision does not point to an ancestor of
         srcrev, we'll walk down the ancestors until we find one introducing
         this file revision.
 
         :srcrev: the changeset revision we search ancestors from
         :inclusive: if true, the src revision will also be checked
         """
         repo = self._repo
         cl = repo.unfiltered().changelog
         mfl = repo.manifestlog
         # fetch the linkrev
         lkr = self.linkrev()
         # hack to reuse ancestor computation when searching for renames
         memberanc = getattr(self, '_ancestrycontext', None)
         iteranc = None
         if srcrev is None:
             # wctx case, used by workingfilectx during mergecopy
             revs = [p.rev() for p in self._repo[None].parents()]
             inclusive = True # we skipped the real (revless) source
         else:
             revs = [srcrev]
         if memberanc is None:
             memberanc = iteranc = cl.ancestors(revs, lkr,
                                                inclusive=inclusive)
         # check if this linkrev is an ancestor of srcrev
         if lkr not in memberanc:
             if iteranc is None:
                 iteranc = cl.ancestors(revs, lkr, inclusive=inclusive)
             fnode = self._filenode
             path = self._path
             for a in iteranc:
                 ac = cl.read(a) # get changeset data (we avoid object creation)
                 if path in ac[3]: # checking the 'files' field.
                     # The file has been touched, check if the content is
                     # similar to the one we search for.
                     if fnode == mfl[ac[0]].readfast().get(path):
                         return a
             # In theory, we should never get out of that loop without a result.
             # But if manifest uses a buggy file revision (not children of the
             # one it replaces) we could. Such a buggy situation will likely
             # result is crash somewhere else at to some point.
         return lkr
 
     def introrev(self):
         """return the rev of the changeset which introduced this file revision
 
         This method is different from linkrev because it take into account the
         changeset the filectx was created from. It ensures the returned
         revision is one of its ancestors. This prevents bugs from
         'linkrev-shadowing' when a file revision is used by multiple
         changesets.
         """
         lkr = self.linkrev()
         attrs = vars(self)
         noctx = not ('_changeid' in attrs or '_changectx' in attrs)
         if noctx or self.rev() == lkr:
             return self.linkrev()
         return self._adjustlinkrev(self.rev(), inclusive=True)
 
     def _parentfilectx(self, path, fileid, filelog):
         """create parent filectx keeping ancestry info for _adjustlinkrev()"""
         fctx = filectx(self._repo, path, fileid=fileid, filelog=filelog)
         if '_changeid' in vars(self) or '_changectx' in vars(self):
             # If self is associated with a changeset (probably explicitly
             # fed), ensure the created filectx is associated with a
             # changeset that is an ancestor of self.changectx.
             # This lets us later use _adjustlinkrev to get a correct link.
             fctx._descendantrev = self.rev()
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         elif '_descendantrev' in vars(self):
             # Otherwise propagate _descendantrev if we have one associated.
             fctx._descendantrev = self._descendantrev
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         return fctx
 
     def parents(self):
         _path = self._path
         fl = self._filelog
         parents = self._filelog.parents(self._filenode)
         pl = [(_path, node, fl) for node in parents if node != nullid]
 
         r = fl.renamed(self._filenode)
         if r:
             # - In the simple rename case, both parent are nullid, pl is empty.
             # - In case of merge, only one of the parent is null id and should
             # be replaced with the rename information. This parent is -always-
             # the first one.
             #
             # As null id have always been filtered out in the previous list
             # comprehension, inserting to 0 will always result in "replacing
             # first nullid parent with rename information.
             pl.insert(0, (r[0], r[1], self._repo.file(r[0])))
 
         return [self._parentfilectx(path, fnode, l) for path, fnode, l in pl]
 
     def p1(self):
         return self.parents()[0]
 
     def p2(self):
         p = self.parents()
         if len(p) == 2:
             return p[1]
         return filectx(self._repo, self._path, fileid=-1, filelog=self._filelog)
 
     def annotate(self, follow=False, linenumber=False, diffopts=None):
         '''returns a list of tuples of ((ctx, number), line) for each line
         in the file, where ctx is the filectx of the node where
         that line was last changed; if linenumber parameter is true, number is
         the line number at the first appearance in the managed file, otherwise,
         number has a fixed value of False.
         '''
 
         def lines(text):
             if text.endswith("\n"):
                 return text.count("\n")
             return text.count("\n") + int(bool(text))
 
         if linenumber:
             def decorate(text, rev):
                 return ([(rev, i) for i in xrange(1, lines(text) + 1)], text)
         else:
             def decorate(text, rev):
                 return ([(rev, False)] * lines(text), text)
 
         def pair(parent, child):
             blocks = mdiff.allblocks(parent[1], child[1], opts=diffopts)
             for (a1, a2, b1, b2), t in blocks:
                 # Changed blocks ('!') or blocks made only of blank lines ('~')
                 # belong to the child.
                 if t == '=':
                     child[0][b1:b2] = parent[0][a1:a2]
             return child
 
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
 
         def parents(f):
             # Cut _descendantrev here to mitigate the penalty of lazy linkrev
             # adjustment. Otherwise, p._adjustlinkrev() would walk changelog
             # from the topmost introrev (= srcrev) down to p.linkrev() if it
             # isn't an ancestor of the srcrev.
             f._changeid
             pl = f.parents()
 
             # Don't return renamed parents if we aren't following.
             if not follow:
                 pl = [p for p in pl if p.path() == f.path()]
 
             # renamed filectx won't have a filelog yet, so set it
             # from the cache to save time
             for p in pl:
                 if not '_filelog' in p.__dict__:
                     p._filelog = getlog(p.path())
 
             return pl
 
         # use linkrev to find the first changeset where self appeared
         base = self
         introrev = self.introrev()
         if self.rev() != introrev:
             base = self.filectx(self.filenode(), changeid=introrev)
         if getattr(base, '_ancestrycontext', None) is None:
             cl = self._repo.changelog
             if introrev is None:
                 # wctx is not inclusive, but works because _ancestrycontext
                 # is used to test filelog revisions
                 ac = cl.ancestors([p.rev() for p in base.parents()],
                                   inclusive=True)
             else:
                 ac = cl.ancestors([introrev], inclusive=True)
             base._ancestrycontext = ac
 
         # This algorithm would prefer to be recursive, but Python is a
         # bit recursion-hostile. Instead we do an iterative
         # depth-first search.
 
         # 1st DFS pre-calculates pcache and needed
         visit = [base]
         pcache = {}
         needed = {base: 1}
         while visit:
             f = visit.pop()
             if f in pcache:
                 continue
             pl = parents(f)
             pcache[f] = pl
             for p in pl:
                 needed[p] = needed.get(p, 0) + 1
                 if p not in pcache:
                     visit.append(p)
 
         # 2nd DFS does the actual annotate
         visit[:] = [base]
         hist = {}
         while visit:
             f = visit[-1]
             if f in hist:
                 visit.pop()
                 continue
 
             ready = True
             pl = pcache[f]
             for p in pl:
                 if p not in hist:
                     ready = False
                     visit.append(p)
             if ready:
                 visit.pop()
                 curr = decorate(f.data(), f)
                 for p in pl:
                     curr = pair(hist[p], curr)
                     if needed[p] == 1:
                         del hist[p]
                         del needed[p]
                     else:
                         needed[p] -= 1
 
                 hist[f] = curr
                 del pcache[f]
 
         return zip(hist[base][0], hist[base][1].splitlines(True))
 
     def ancestors(self, followfirst=False):
         visit = {}
         c = self
         if followfirst:
             cut = 1
         else:
             cut = None
 
         while True:
             for parent in c.parents()[:cut]:
                 visit[(parent.linkrev(), parent.filenode())] = parent
             if not visit:
                 break
             c = visit.pop(max(visit))
             yield c
 
 class filectx(basefilectx):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
     def __init__(self, repo, path, changeid=None, fileid=None,
                  filelog=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (changeid is not None
                 or fileid is not None
                 or changectx is not None), \
                 ("bad args: changeid=%r, fileid=%r, changectx=%r"
                  % (changeid, fileid, changectx))
 
         if filelog is not None:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         try:
             return changectx(self._repo, self._changeid)
         except error.FilteredRepoLookupError:
             # Linkrev may point to any revision in the repository.  When the
             # repository is filtered this may lead to `filectx` trying to build
             # `changectx` for filtered revision. In such case we fallback to
             # creating `changectx` on the unfiltered version of the reposition.
             # This fallback should not be an issue because `changectx` from
             # `filectx` are not used in complex operations that care about
             # filtering.
             #
             # This fallback is a cheap and dirty fix that prevent several
             # crashes. It does not ensure the behavior is correct. However the
             # behavior was not correct before filtering either and "incorrect
             # behavior" is seen as better as "crash"
             #
             # Linkrevs have several serious troubles with filtering that are
             # complicated to solve. Proper handling of the issue here should be
             # considered when solving linkrev issue are on the table.
             return changectx(self._repo.unfiltered(), self._changeid)
 
     def filectx(self, fileid, changeid=None):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(self._repo, self._path, fileid=fileid,
                        filelog=self._filelog, changeid=changeid)
 
+    def rawdata(self):
+        return self._filelog.revision(self._filenode, raw=True)
+
     def data(self):
         try:
             return self._filelog.read(self._filenode)
         except error.CensoredNodeError:
             if self._repo.ui.config("censor", "policy", "abort") == "ignore":
                 return ""
             raise error.Abort(_("censored node: %s") % short(self._filenode),
                              hint=_("set censor.policy to ignore errors"))
 
     def size(self):
         return self._filelog.size(self._filerev)
 
     def renamed(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return renamed
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [filectx(self._repo, self._path, fileid=x,
                         filelog=self._filelog) for x in c]
 
 def blockancestors(fctx, fromline, toline):
     """Yield ancestors of `fctx` with respect to the block of lines within
     `fromline`-`toline` range.
     """
     def changesrange(fctx1, fctx2, linerange2):
         """Return `(diffinrange, linerange1)` where `diffinrange` is True
         if diff from fctx2 to fctx1 has changes in linerange2 and
         `linerange1` is the new line range for fctx1.
         """
         diffopts = patch.diffopts(fctx._repo.ui)
         blocks = mdiff.allblocks(fctx1.data(), fctx2.data(), diffopts)
         filteredblocks, linerange1 = mdiff.blocksinrange(blocks, linerange2)
         diffinrange = any(stype == '!' for _, stype in filteredblocks)
         return diffinrange, linerange1
 
     visit = {(fctx.linkrev(), fctx.filenode()): (fctx, (fromline, toline))}
     while visit:
         c, linerange2 = visit.pop(max(visit))
         pl = c.parents()
         if not pl:
             # The block originates from the initial revision.
             yield c
             continue
         inrange = False
         for p in pl:
             inrangep, linerange1 = changesrange(p, c, linerange2)
             inrange = inrange or inrangep
             if linerange1[0] == linerange1[1]:
                 # Parent's linerange is empty, meaning that the block got
                 # introduced in this revision; no need to go futher in this
                 # branch.
                 continue
             visit[p.linkrev(), p.filenode()] = p, linerange1
         if inrange:
             yield c
 
 class committablectx(basectx):
     """A committablectx object provides common functionality for a context that
     wants the ability to commit, e.g. workingctx or memctx."""
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = util.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = changes
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if 'branch' not in self._extra:
             try:
                 branch = encoding.fromlocal(self._repo.dirstate.branch())
             except UnicodeDecodeError:
                 raise error.Abort(_('branch name not in UTF-8!'))
             self._extra['branch'] = branch
         if self._extra['branch'] == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __nonzero__(self):
         return True
 
     def _buildflagfunc(self):
         # Create a fallback function for getting file flags when the
         # filesystem doesn't support them
 
         copiesget = self._repo.dirstate.copies().get
         parents = self.parents()
         if len(parents) < 2:
             # when we have one parent, it's easy: copy from parent
             man = parents[0].manifest()
             def func(f):
                 f = copiesget(f, f)
                 return man.flags(f)
         else:
             # merges are tricky: we try to reconstruct the unstored
             # result from the merge (issue1802)
             p1, p2 = parents
             pa = p1.ancestor(p2)
             m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
 
             def func(f):
                 f = copiesget(f, f) # may be wrong for merges with copies
                 fl1, fl2, fla = m1.flags(f), m2.flags(f), ma.flags(f)
                 if fl1 == fl2:
                     return fl1
                 if fl1 == fla:
                     return fl2
                 if fl2 == fla:
                     return fl1
                 return '' # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the values in self._status
 
         This reuse the file nodeid from parent, but we append an extra letter
         when modified. Modified files get an extra 'm' while added files get
         an extra 'a'. This is used by manifests merge to see that files
         are different and by update logic to avoid deleting newly added files.
         """
         parents = self.parents()
 
         man = parents[0].manifest().copy()
 
         ff = self._flagfunc
         for i, l in ((addednodeid, self._status.added),
                      (modifiednodeid, self._status.modified)):
             for f in l:
                 man[f] = i
                 try:
                     man.setflag(f, ff(f))
                 except OSError:
                     pass
 
         for f in self._status.deleted + self._status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         return self._repo.status()
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         return util.makedate()
 
     def subrev(self, subpath):
         return None
 
     def manifestnode(self):
         return None
     def user(self):
         return self._user or self._repo.ui.username()
     def date(self):
         return self._date
     def description(self):
         return self._text
     def files(self):
         return sorted(self._status.modified + self._status.added +
                       self._status.removed)
 
     def modified(self):
         return self._status.modified
     def added(self):
         return self._status.added
     def removed(self):
         return self._status.removed
     def deleted(self):
         return self._status.deleted
     def branch(self):
         return encoding.tolocal(self._extra['branch'])
     def closesbranch(self):
         return 'close' in self._extra
     def extra(self):
         return self._extra
 
     def tags(self):
         return []
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.draft # default phase to draft
         for p in self.parents():
             phase = max(phase, p.phase())
         return phase
 
     def hidden(self):
         return False
 
     def children(self):
         return []
 
     def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return ''
 
     def ancestor(self, c2):
         """return the "best" ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
     def walk(self, match):
         '''Generates matching file names.'''
         return sorted(self._repo.dirstate.walk(match, sorted(self.substate),
                                                True, False))
 
     def matches(self, match):
         return sorted(self._repo.dirstate.matches(match))
 
     def ancestors(self):
         for p in self._parents:
             yield p
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]):
             yield changectx(self._repo, a)
 
     def markcommitted(self, node):
         """Perform post-commit cleanup necessary after committing this ctx
 
         Specifically, this updates backing stores this working context
         wraps to reflect the fact that the changes reflected by this
         workingctx have been committed.  For example, it marks
         modified and added files as normal in the dirstate.
 
         """
 
         self._repo.dirstate.beginparentchange()
         for f in self.modified() + self.added():
             self._repo.dirstate.normal(f)
         for f in self.removed():
             self._repo.dirstate.drop(f)
         self._repo.dirstate.setparents(node)
         self._repo.dirstate.endparentchange()
 
         # write changes out explicitly, because nesting wlock at
         # runtime may prevent 'wlock.release()' in 'repo.commit()'
         # from immediately doing so for subsequent changing files
         self._repo.dirstate.write(self._repo.currenttransaction())
 
 class workingctx(committablectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         super(workingctx, self).__init__(repo, text, user, date, extra, changes)
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d[f] != 'r':
                 yield f
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     def hex(self):
         return hex(wdirid)
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(self._repo, path, workingctx=self,
                               filelog=filelog)
 
     def dirty(self, missing=False, merge=True, branch=True):
         "check whether a working directory is modified"
         # check subrepos first
         for s in sorted(self.substate):
             if self.sub(s).dirty():
                 return True
         # check current working dir
         return ((merge and self.p2()) or
                 (branch and self.branch() != self.p1().branch()) or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
     def add(self, list, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         with self._repo.wlock():
             ui, ds = self._repo.ui, self._repo.dirstate
             rejected = []
             lstat = self._repo.wvfs.lstat
             for f in list:
                 scmutil.checkportable(ui, join(f))
                 try:
                     st = lstat(f)
                 except OSError:
                     ui.warn(_("%s does not exist!\n") % join(f))
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     ui.warn(_("%s: up to %d MB of RAM may be required "
                               "to manage this file\n"
                               "(use 'hg revert %s' to cancel the "
                               "pending addition)\n")
                               % (f, 3 * st.st_size // 1000000, join(f)))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(_("%s not added: only files and symlinks "
                               "supported currently\n") % join(f))
                     rejected.append(f)
                 elif ds[f] in 'amn':
                     ui.warn(_("%s already tracked!\n") % join(f))
                 elif ds[f] == 'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
 
     def forget(self, files, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         with self._repo.wlock():
             rejected = []
             for f in files:
                 if f not in self._repo.dirstate:
                     self._repo.ui.warn(_("%s not tracked!\n") % join(f))
                     rejected.append(f)
                 elif self._repo.dirstate[f] != 'a':
                     self._repo.dirstate.remove(f)
                 else:
                     self._repo.dirstate.drop(f)
             return rejected
 
     def undelete(self, list):
         pctxs = self.parents()
         with self._repo.wlock():
             for f in list:
                 if self._repo.dirstate[f] != 'r':
                     self._repo.ui.warn(_("%s not removed!\n") % f)
                 else:
                     fctx = f in pctxs[0] and pctxs[0][f] or pctxs[1][f]
                     t = fctx.data()
                     self._repo.wwrite(f, t, fctx.flags())
                     self._repo.dirstate.normal(f)
 
     def copy(self, source, dest):
         try:
             st = self._repo.wvfs.lstat(dest)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             self._repo.ui.warn(_("%s does not exist!\n") % dest)
             return
         if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
             self._repo.ui.warn(_("copy failed: %s is not a file or a "
                                  "symbolic link\n") % dest)
         else:
             with self._repo.wlock():
                 if self._repo.dirstate[dest] in '?':
                     self._repo.dirstate.add(dest)
                 elif self._repo.dirstate[dest] in 'r':
                     self._repo.dirstate.normallookup(dest)
                 self._repo.dirstate.copy(source, dest)
 
     def match(self, pats=[], include=None, exclude=None, default='glob',
               listsubrepos=False, badfn=None):
         r = self._repo
 
         # Only a case insensitive filesystem needs magic to translate user input
         # to actual case in the filesystem.
         if not util.fscasesensitive(r.root):
             return matchmod.icasefsmatcher(r.root, r.getcwd(), pats, include,
                                            exclude, default, r.auditor, self,
                                            listsubrepos=listsubrepos,
                                            badfn=badfn)
         return matchmod.match(r.root, r.getcwd(), pats,
                               include, exclude, default,
                               auditor=r.auditor, ctx=self,
                               listsubrepos=listsubrepos, badfn=badfn)
 
     def _filtersuspectsymlink(self, files):
         if not files or self._repo.dirstate._checklink:
             return files
 
         # 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 files:
             if self.flags(f) == 'l':
                 d = self[f].data()
                 if d == '' or len(d) >= 1024 or '\n' in d or util.binary(d):
                     self._repo.ui.debug('ignoring suspect symlink placeholder'
                                         ' "%s"\n' % f)
                     continue
             sane.append(f)
         return sane
 
     def _checklookup(self, files):
         # check for any possibly clean files
         if not files:
             return [], []
 
         modified = []
         fixup = []
         pctx = self._parents[0]
         # do a full compare of any files that might have changed
         for f in sorted(files):
             if (f not in pctx or self.flags(f) != pctx.flags(f)
                 or pctx[f].cmp(self[f])):
                 modified.append(f)
             else:
                 fixup.append(f)
 
         # update dirstate for files that are actually clean
         if fixup:
             try:
                 # updating the dirstate is optional
                 # so we don't wait on the lock
                 # wlock can invalidate the dirstate, so cache normal _after_
                 # taking the lock
                 with self._repo.wlock(False):
                     normal = self._repo.dirstate.normal
                     for f in fixup:
                         normal(f)
                     # write changes out explicitly, because nesting
                     # wlock at runtime may prevent 'wlock.release()'
                     # after this block from doing so for subsequent
                     # changing files
                     self._repo.dirstate.write(self._repo.currenttransaction())
             except error.LockError:
                 pass
         return modified, fixup
 
     def _manifestmatches(self, match, s):
         """Slow path for workingctx
 
         The fast path is when we compare the working directory to its parent
         which means this function is comparing with a non-parent; therefore we
         need to build a manifest and return what matches.
         """
         mf = self._repo['.']._manifestmatches(match, s)
         for f in s.modified + s.added:
             mf[f] = newnodeid
             mf.setflag(f, self.flags(f))
         for f in s.removed:
             if f in mf:
                 del mf[f]
         return mf
 
     def _dirstatestatus(self, match=None, ignored=False, clean=False,
                         unknown=False):
         '''Gets the status from the dirstate -- internal use only.'''
         listignored, listclean, listunknown = ignored, clean, unknown
         match = match or matchmod.always(self._repo.root, self._repo.getcwd())
         subrepos = []
         if '.hgsub' in self:
             subrepos = sorted(self.substate)
         cmp, s = self._repo.dirstate.status(match, subrepos, listignored,
                                             listclean, listunknown)
 
         # check for any possibly clean files
         if cmp:
             modified2, fixup = self._checklookup(cmp)
             s.modified.extend(modified2)
 
             # update dirstate for files that are actually clean
             if fixup and listclean:
                 s.clean.extend(fixup)
 
         if match.always():
             # cache for performance
             if s.unknown or s.ignored or s.clean:
                 # "_status" is cached with list*=False in the normal route
                 self._status = scmutil.status(s.modified, s.added, s.removed,
                                               s.deleted, [], [], [])
             else:
                 self._status = s
 
         return s
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context
 
         This includes logic for maintaining the fast path of status when
         comparing the working directory against its parent, which is to skip
         building a new manifest if self (working directory) is not comparing
         against its parent (repo['.']).
         """
         s = self._dirstatestatus(match, listignored, listclean, listunknown)
         # Filter out symlinks that, in the case of FAT32 and NTFS filesystems,
         # might have accidentally ended up with the entire contents of the file
         # they are supposed to be linking to.
         s.modified[:] = self._filtersuspectsymlink(s.modified)
         if other != self._repo['.']:
             s = super(workingctx, self)._buildstatus(other, s, match,
                                                      listignored, listclean,
                                                      listunknown)
         return s
 
     def _matchstatus(self, other, match):
         """override the match method with a filter for directory patterns
 
         We use inheritance to customize the match.bad method only in cases of
         workingctx since it belongs only to the working directory when
         comparing against the parent changeset.
 
         If we aren't comparing against the working directory's parent, then we
         just use the default match object sent to us.
         """
         superself = super(workingctx, self)
         match = superself._matchstatus(other, match)
         if other != self._repo['.']:
             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 other and not other.hasdir(f):
                     self._repo.ui.warn('%s: %s\n' %
                                        (self._repo.dirstate.pathto(f), msg))
             match.bad = bad
         return match
 
 class committablefilectx(basefilectx):
     """A committablefilectx provides common functionality for a file context
     that wants the ability to commit, e.g. workingfilectx or memfilectx."""
     def __init__(self, repo, path, filelog=None, ctx=None):
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog is not None:
             self._filelog = filelog
         if ctx:
             self._changectx = ctx
 
     def __nonzero__(self):
         return True
 
     def linkrev(self):
         # linked to self._changectx no matter if file is modified or not
         return self.rev()
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [self._parentfilectx(p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def children(self):
         return []
 
 class workingfilectx(committablefilectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
     def __init__(self, repo, path, filelog=None, workingctx=None):
         super(workingfilectx, self).__init__(repo, path, filelog, workingctx)
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def data(self):
         return self._repo.wread(self._path)
     def renamed(self):
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def size(self):
         return self._repo.wvfs.lstat(self._path).st_size
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (self._repo.wvfs.lstat(self._path).st_mtime, tz)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         # fctx should be a filectx (not a workingfilectx)
         # invert comparison to reuse the same code path
         return fctx.cmp(self)
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         util.unlinkpath(self._repo.wjoin(self._path), ignoremissing)
 
     def write(self, data, flags):
         """wraps repo.wwrite"""
         self._repo.wwrite(self._path, data, flags)
 
 class workingcommitctx(workingctx):
     """A workingcommitctx object makes access to data related to
     the revision being committed convenient.
 
     This hides changes in the working directory, if they aren't
     committed in this context.
     """
     def __init__(self, repo, changes,
                  text="", user=None, date=None, extra=None):
         super(workingctx, self).__init__(repo, text, user, date, extra,
                                          changes)
 
     def _dirstatestatus(self, match=None, ignored=False, clean=False,
                         unknown=False):
         """Return matched files only in ``self._status``
 
         Uncommitted files appear "clean" via this context, even if
         they aren't actually so in the working directory.
         """
         match = match or matchmod.always(self._repo.root, self._repo.getcwd())
         if clean:
             clean = [f for f in self._manifest if f not in self._changedset]
         else:
             clean = []
         return scmutil.status([f for f in self._status.modified if match(f)],
                               [f for f in self._status.added if match(f)],
                               [f for f in self._status.removed if match(f)],
                               [], [], [], clean)
 
     @propertycache
     def _changedset(self):
         """Return the set of files changed in this context
         """
         changed = set(self._status.modified)
         changed.update(self._status.added)
         changed.update(self._status.removed)
         return changed
 
 def makecachingfilectxfn(func):
     """Create a filectxfn that caches based on the path.
 
     We can't use util.cachefunc because it uses all arguments as the cache
     key and this creates a cycle since the arguments include the repo and
     memctx.
     """
     cache = {}
 
     def getfilectx(repo, memctx, path):
         if path not in cache:
             cache[path] = func(repo, memctx, path)
         return cache[path]
 
     return getfilectx
 
 class memctx(committablectx):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn raises an
     IOError. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by util.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
 
     # Mercurial <= 3.1 expects the filectxfn to raise IOError for missing files.
     # Extensions that need to retain compatibility across Mercurial 3.1 can use
     # this field to determine what to do in filectxfn.
     _returnnoneformissingfiles = True
 
     def __init__(self, repo, parents, text, files, filectxfn, user=None,
                  date=None, extra=None, editor=False):
         super(memctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [changectx(self._repo, p) for p in (p1, p2)]
         files = sorted(set(files))
         self._files = files
         self.substate = {}
 
         # if store is not callable, wrap it in a function
         if not callable(filectxfn):
             def getfilectx(repo, memctx, path):
                 fctx = filectxfn[path]
                 # this is weird but apparently we only keep track of one parent
                 # (why not only store that instead of a tuple?)
                 copied = fctx.renamed()
                 if copied:
                     copied = copied[0]
                 return memfilectx(repo, path, fctx.data(),
                                   islink=fctx.islink(), isexec=fctx.isexec(),
                                   copied=copied, memctx=memctx)
             self._filectxfn = getfilectx
         else:
             # memoizing increases performance for e.g. vcs convert scenarios.
             self._filectxfn = makecachingfilectxfn(filectxfn)
 
         if extra:
             self._extra = extra.copy()
         else:
             self._extra = {}
 
         if self._extra.get('branch', '') == '':
             self._extra['branch'] = 'default'
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory
 
         Returns None if file doesn't exist and should be removed."""
         return self._filectxfn(self._repo, self, path)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @propertycache
     def _manifest(self):
         """generate a manifest based on the return values of filectxfn"""
 
         # keep this simple for now; just worry about p1
         pctx = self._parents[0]
         man = pctx.manifest().copy()
 
         for f in self._status.modified:
             p1node = nullid
             p2node = nullid
             p = pctx[f].parents() # if file isn't in pctx, check p2?
             if len(p) > 0:
                 p1node = p[0].filenode()
                 if len(p) > 1:
                     p2node = p[1].filenode()
             man[f] = revlog.hash(self[f].data(), p1node, p2node)
 
         for f in self._status.added:
             man[f] = revlog.hash(self[f].data(), nullid, nullid)
 
         for f in self._status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified at construction
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "memctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif self[f]:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 class memfilectx(committablefilectx):
     """memfilectx represents an in-memory file to commit.
 
     See memctx and committablefilectx for more details.
     """
     def __init__(self, repo, path, data, islink=False,
                  isexec=False, copied=None, memctx=None):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         super(memfilectx, self).__init__(repo, path, None, memctx)
         self._data = data
         self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
         self._copied = None
         if copied:
             self._copied = (copied, nullid)
 
     def data(self):
         return self._data
     def size(self):
         return len(self.data())
     def flags(self):
         return self._flags
     def renamed(self):
         return self._copied
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         # need to figure out what to do here
         del self._changectx[self._path]
 
     def write(self, data, flags):
         """wraps repo.wwrite"""
         self._data = data
 
 class metadataonlyctx(committablectx):
     """Like memctx but it's reusing the manifest of different commit.
     Intended to be used by lightweight operations that are creating
     metadata-only changes.
 
     Revision information is supplied at initialization time.  'repo' is the
     current localrepo, 'ctx' is original revision which manifest we're reuisng
     'parents' is a sequence of two parent revisions identifiers (pass None for
     every missing parent), 'text' is the commit.
 
     user receives the committer name and defaults to current repository
     username, date is the commit date in any format supported by
     util.parsedate() and defaults to current date, extra is a dictionary of
     metadata or is left empty.
     """
     def __new__(cls, repo, originalctx, *args, **kwargs):
         return super(metadataonlyctx, cls).__new__(cls, repo)
 
     def __init__(self, repo, originalctx, parents, text, user=None, date=None,
                  extra=None, editor=False):
         super(metadataonlyctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         self._originalctx = originalctx
         self._manifestnode = originalctx.manifestnode()
         parents = [(p or nullid) for p in parents]
         p1, p2 = self._parents = [changectx(self._repo, p) for p in parents]
 
         # sanity check to ensure that the reused manifest parents are
         # manifests of our commit parents
         mp1, mp2 = self.manifestctx().parents
         if p1 != nullid and p1.manifestctx().node() != mp1:
             raise RuntimeError('can\'t reuse the manifest: '
                                'its p1 doesn\'t match the new ctx p1')
         if p2 != nullid and p2.manifestctx().node() != mp2:
             raise RuntimeError('can\'t reuse the manifest: '
                                'its p2 doesn\'t match the new ctx p2')
 
         self._files = originalctx.files()
         self.substate = {}
 
         if extra:
             self._extra = extra.copy()
         else:
             self._extra = {}
 
         if self._extra.get('branch', '') == '':
             self._extra['branch'] = 'default'
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def manifestnode(self):
         return self._manifestnode
 
     @propertycache
     def _manifestctx(self):
         return self._repo.manifestlog[self._manifestnode]
 
     def filectx(self, path, filelog=None):
         return self._originalctx.filectx(path, filelog=filelog)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @property
     def _manifest(self):
         return self._originalctx.manifest()
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified in the ``origctx``
         and parents manifests.
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "metadataonlyctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif self[f]:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])

mercurial/debugcommands.py

@@ -1,851 +1,851 b''
 # debugcommands.py - command processing for debug* commands
 #
 # Copyright 2005-2016 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import operator
 import os
 import random
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     short,
 )
 from . import (
     bundle2,
     changegroup,
     cmdutil,
     commands,
     context,
     dagparser,
     dagutil,
     error,
     exchange,
     extensions,
     fileset,
     hg,
     localrepo,
     lock as lockmod,
     pycompat,
     revlog,
     scmutil,
     setdiscovery,
     simplemerge,
     streamclone,
     treediscovery,
     util,
 )
 
 release = lockmod.release
 
 # We reuse the command table from commands because it is easier than
 # teaching dispatch about multiple tables.
 command = cmdutil.command(commands.table)
 
 @command('debugancestor', [], _('[INDEX] REV1 REV2'), optionalrepo=True)
 def debugancestor(ui, repo, *args):
     """find the ancestor revision of two revisions in a given index"""
     if len(args) == 3:
         index, rev1, rev2 = args
         r = revlog.revlog(scmutil.opener(pycompat.getcwd(), audit=False), index)
         lookup = r.lookup
     elif len(args) == 2:
         if not repo:
             raise error.Abort(_('there is no Mercurial repository here '
                                 '(.hg not found)'))
         rev1, rev2 = args
         r = repo.changelog
         lookup = repo.lookup
     else:
         raise error.Abort(_('either two or three arguments required'))
     a = r.ancestor(lookup(rev1), lookup(rev2))
     ui.write('%d:%s\n' % (r.rev(a), hex(a)))
 
 @command('debugapplystreamclonebundle', [], 'FILE')
 def debugapplystreamclonebundle(ui, repo, fname):
     """apply a stream clone bundle file"""
     f = hg.openpath(ui, fname)
     gen = exchange.readbundle(ui, f, fname)
     gen.apply(repo)
 
 @command('debugbuilddag',
     [('m', 'mergeable-file', None, _('add single file mergeable changes')),
     ('o', 'overwritten-file', None, _('add single file all revs overwrite')),
     ('n', 'new-file', None, _('add new file at each rev'))],
     _('[OPTION]... [TEXT]'))
 def debugbuilddag(ui, repo, text=None,
                   mergeable_file=False,
                   overwritten_file=False,
                   new_file=False):
     """builds a repo with a given DAG from scratch in the current empty repo
 
     The description of the DAG is read from stdin if not given on the
     command line.
 
     Elements:
 
      - "+n" is a linear run of n nodes based on the current default parent
      - "." is a single node based on the current default parent
      - "$" resets the default parent to null (implied at the start);
            otherwise the default parent is always the last node created
      - "<p" sets the default parent to the backref p
      - "*p" is a fork at parent p, which is a backref
      - "*p1/p2" is a merge of parents p1 and p2, which are backrefs
      - "/p2" is a merge of the preceding node and p2
      - ":tag" defines a local tag for the preceding node
      - "@branch" sets the named branch for subsequent nodes
      - "#...\\n" is a comment up to the end of the line
 
     Whitespace between the above elements is ignored.
 
     A backref is either
 
      - a number n, which references the node curr-n, where curr is the current
        node, or
      - the name of a local tag you placed earlier using ":tag", or
      - empty to denote the default parent.
 
     All string valued-elements are either strictly alphanumeric, or must
     be enclosed in double quotes ("..."), with "\\" as escape character.
     """
 
     if text is None:
         ui.status(_("reading DAG from stdin\n"))
         text = ui.fin.read()
 
     cl = repo.changelog
     if len(cl) > 0:
         raise error.Abort(_('repository is not empty'))
 
     # determine number of revs in DAG
     total = 0
     for type, data in dagparser.parsedag(text):
         if type == 'n':
             total += 1
 
     if mergeable_file:
         linesperrev = 2
         # make a file with k lines per rev
         initialmergedlines = [str(i) for i in xrange(0, total * linesperrev)]
         initialmergedlines.append("")
 
     tags = []
 
     wlock = lock = tr = None
     try:
         wlock = repo.wlock()
         lock = repo.lock()
         tr = repo.transaction("builddag")
 
         at = -1
         atbranch = 'default'
         nodeids = []
         id = 0
         ui.progress(_('building'), id, unit=_('revisions'), total=total)
         for type, data in dagparser.parsedag(text):
             if type == 'n':
                 ui.note(('node %s\n' % str(data)))
                 id, ps = data
 
                 files = []
                 fctxs = {}
 
                 p2 = None
                 if mergeable_file:
                     fn = "mf"
                     p1 = repo[ps[0]]
                     if len(ps) > 1:
                         p2 = repo[ps[1]]
                         pa = p1.ancestor(p2)
                         base, local, other = [x[fn].data() for x in (pa, p1,
                                                                      p2)]
                         m3 = simplemerge.Merge3Text(base, local, other)
                         ml = [l.strip() for l in m3.merge_lines()]
                         ml.append("")
                     elif at > 0:
                         ml = p1[fn].data().split("\n")
                     else:
                         ml = initialmergedlines
                     ml[id * linesperrev] += " r%i" % id
                     mergedtext = "\n".join(ml)
                     files.append(fn)
                     fctxs[fn] = context.memfilectx(repo, fn, mergedtext)
 
                 if overwritten_file:
                     fn = "of"
                     files.append(fn)
                     fctxs[fn] = context.memfilectx(repo, fn, "r%i\n" % id)
 
                 if new_file:
                     fn = "nf%i" % id
                     files.append(fn)
                     fctxs[fn] = context.memfilectx(repo, fn, "r%i\n" % id)
                     if len(ps) > 1:
                         if not p2:
                             p2 = repo[ps[1]]
                         for fn in p2:
                             if fn.startswith("nf"):
                                 files.append(fn)
                                 fctxs[fn] = p2[fn]
 
                 def fctxfn(repo, cx, path):
                     return fctxs.get(path)
 
                 if len(ps) == 0 or ps[0] < 0:
                     pars = [None, None]
                 elif len(ps) == 1:
                     pars = [nodeids[ps[0]], None]
                 else:
                     pars = [nodeids[p] for p in ps]
                 cx = context.memctx(repo, pars, "r%i" % id, files, fctxfn,
                                     date=(id, 0),
                                     user="debugbuilddag",
                                     extra={'branch': atbranch})
                 nodeid = repo.commitctx(cx)
                 nodeids.append(nodeid)
                 at = id
             elif type == 'l':
                 id, name = data
                 ui.note(('tag %s\n' % name))
                 tags.append("%s %s\n" % (hex(repo.changelog.node(id)), name))
             elif type == 'a':
                 ui.note(('branch %s\n' % data))
                 atbranch = data
             ui.progress(_('building'), id, unit=_('revisions'), total=total)
         tr.close()
 
         if tags:
             repo.vfs.write("localtags", "".join(tags))
     finally:
         ui.progress(_('building'), None)
         release(tr, lock, wlock)
 
 def _debugchangegroup(ui, gen, all=None, indent=0, **opts):
     indent_string = ' ' * indent
     if all:
         ui.write(("%sformat: id, p1, p2, cset, delta base, len(delta)\n")
                  % indent_string)
 
         def showchunks(named):
             ui.write("\n%s%s\n" % (indent_string, named))
             chain = None
             for chunkdata in iter(lambda: gen.deltachunk(chain), {}):
                 node = chunkdata['node']
                 p1 = chunkdata['p1']
                 p2 = chunkdata['p2']
                 cs = chunkdata['cs']
                 deltabase = chunkdata['deltabase']
                 delta = chunkdata['delta']
                 ui.write("%s%s %s %s %s %s %s\n" %
                          (indent_string, hex(node), hex(p1), hex(p2),
                           hex(cs), hex(deltabase), len(delta)))
                 chain = node
 
         chunkdata = gen.changelogheader()
         showchunks("changelog")
         chunkdata = gen.manifestheader()
         showchunks("manifest")
         for chunkdata in iter(gen.filelogheader, {}):
             fname = chunkdata['filename']
             showchunks(fname)
     else:
         if isinstance(gen, bundle2.unbundle20):
             raise error.Abort(_('use debugbundle2 for this file'))
         chunkdata = gen.changelogheader()
         chain = None
         for chunkdata in iter(lambda: gen.deltachunk(chain), {}):
             node = chunkdata['node']
             ui.write("%s%s\n" % (indent_string, hex(node)))
             chain = node
 
 def _debugbundle2(ui, gen, all=None, **opts):
     """lists the contents of a bundle2"""
     if not isinstance(gen, bundle2.unbundle20):
         raise error.Abort(_('not a bundle2 file'))
     ui.write(('Stream params: %s\n' % repr(gen.params)))
     for part in gen.iterparts():
         ui.write('%s -- %r\n' % (part.type, repr(part.params)))
         if part.type == 'changegroup':
             version = part.params.get('version', '01')
             cg = changegroup.getunbundler(version, part, 'UN')
             _debugchangegroup(ui, cg, all=all, indent=4, **opts)
 
 @command('debugbundle',
         [('a', 'all', None, _('show all details')),
          ('', 'spec', None, _('print the bundlespec of the bundle'))],
         _('FILE'),
         norepo=True)
 def debugbundle(ui, bundlepath, all=None, spec=None, **opts):
     """lists the contents of a bundle"""
     with hg.openpath(ui, bundlepath) as f:
         if spec:
             spec = exchange.getbundlespec(ui, f)
             ui.write('%s\n' % spec)
             return
 
         gen = exchange.readbundle(ui, f, bundlepath)
         if isinstance(gen, bundle2.unbundle20):
             return _debugbundle2(ui, gen, all=all, **opts)
         _debugchangegroup(ui, gen, all=all, **opts)
 
 @command('debugcheckstate', [], '')
 def debugcheckstate(ui, repo):
     """validate the correctness of the current dirstate"""
     parent1, parent2 = repo.dirstate.parents()
     m1 = repo[parent1].manifest()
     m2 = repo[parent2].manifest()
     errors = 0
     for f in repo.dirstate:
         state = repo.dirstate[f]
         if state in "nr" and f not in m1:
             ui.warn(_("%s in state %s, but not in manifest1\n") % (f, state))
             errors += 1
         if state in "a" and f in m1:
             ui.warn(_("%s in state %s, but also in manifest1\n") % (f, state))
             errors += 1
         if state in "m" and f not in m1 and f not in m2:
             ui.warn(_("%s in state %s, but not in either manifest\n") %
                     (f, state))
             errors += 1
     for f in m1:
         state = repo.dirstate[f]
         if state not in "nrm":
             ui.warn(_("%s in manifest1, but listed as state %s") % (f, state))
             errors += 1
     if errors:
         error = _(".hg/dirstate inconsistent with current parent's manifest")
         raise error.Abort(error)
 
 @command('debugcommands', [], _('[COMMAND]'), norepo=True)
 def debugcommands(ui, cmd='', *args):
     """list all available commands and options"""
     for cmd, vals in sorted(commands.table.iteritems()):
         cmd = cmd.split('|')[0].strip('^')
         opts = ', '.join([i[1] for i in vals[1]])
         ui.write('%s: %s\n' % (cmd, opts))
 
 @command('debugcomplete',
     [('o', 'options', None, _('show the command options'))],
     _('[-o] CMD'),
     norepo=True)
 def debugcomplete(ui, cmd='', **opts):
     """returns the completion list associated with the given command"""
 
     if opts.get('options'):
         options = []
         otables = [commands.globalopts]
         if cmd:
             aliases, entry = cmdutil.findcmd(cmd, commands.table, False)
             otables.append(entry[1])
         for t in otables:
             for o in t:
                 if "(DEPRECATED)" in o[3]:
                     continue
                 if o[0]:
                     options.append('-%s' % o[0])
                 options.append('--%s' % o[1])
         ui.write("%s\n" % "\n".join(options))
         return
 
     cmdlist, unused_allcmds = cmdutil.findpossible(cmd, commands.table)
     if ui.verbose:
         cmdlist = [' '.join(c[0]) for c in cmdlist.values()]
     ui.write("%s\n" % "\n".join(sorted(cmdlist)))
 
 @command('debugcreatestreamclonebundle', [], 'FILE')
 def debugcreatestreamclonebundle(ui, repo, fname):
     """create a stream clone bundle file
 
     Stream bundles are special bundles that are essentially archives of
     revlog files. They are commonly used for cloning very quickly.
     """
     requirements, gen = streamclone.generatebundlev1(repo)
     changegroup.writechunks(ui, gen, fname)
 
     ui.write(_('bundle requirements: %s\n') % ', '.join(sorted(requirements)))
 
 @command('debugdag',
     [('t', 'tags', None, _('use tags as labels')),
     ('b', 'branches', None, _('annotate with branch names')),
     ('', 'dots', None, _('use dots for runs')),
     ('s', 'spaces', None, _('separate elements by spaces'))],
     _('[OPTION]... [FILE [REV]...]'),
     optionalrepo=True)
 def debugdag(ui, repo, file_=None, *revs, **opts):
     """format the changelog or an index DAG as a concise textual description
 
     If you pass a revlog index, the revlog's DAG is emitted. If you list
     revision numbers, they get labeled in the output as rN.
 
     Otherwise, the changelog DAG of the current repo is emitted.
     """
     spaces = opts.get('spaces')
     dots = opts.get('dots')
     if file_:
         rlog = revlog.revlog(scmutil.opener(pycompat.getcwd(), audit=False),
                              file_)
         revs = set((int(r) for r in revs))
         def events():
             for r in rlog:
                 yield 'n', (r, list(p for p in rlog.parentrevs(r)
                                         if p != -1))
                 if r in revs:
                     yield 'l', (r, "r%i" % r)
     elif repo:
         cl = repo.changelog
         tags = opts.get('tags')
         branches = opts.get('branches')
         if tags:
             labels = {}
             for l, n in repo.tags().items():
                 labels.setdefault(cl.rev(n), []).append(l)
         def events():
             b = "default"
             for r in cl:
                 if branches:
                     newb = cl.read(cl.node(r))[5]['branch']
                     if newb != b:
                         yield 'a', newb
                         b = newb
                 yield 'n', (r, list(p for p in cl.parentrevs(r)
                                         if p != -1))
                 if tags:
                     ls = labels.get(r)
                     if ls:
                         for l in ls:
                             yield 'l', (r, l)
     else:
         raise error.Abort(_('need repo for changelog dag'))
 
     for line in dagparser.dagtextlines(events(),
                                        addspaces=spaces,
                                        wraplabels=True,
                                        wrapannotations=True,
                                        wrapnonlinear=dots,
                                        usedots=dots,
                                        maxlinewidth=70):
         ui.write(line)
         ui.write("\n")
 
 @command('debugdata', commands.debugrevlogopts, _('-c|-m|FILE REV'))
 def debugdata(ui, repo, file_, rev=None, **opts):
     """dump the contents of a data file revision"""
     if opts.get('changelog') or opts.get('manifest') or opts.get('dir'):
         if rev is not None:
             raise error.CommandError('debugdata', _('invalid arguments'))
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('debugdata', _('invalid arguments'))
     r = cmdutil.openrevlog(repo, 'debugdata', file_, opts)
     try:
-        ui.write(r.revision(r.lookup(rev)))
+        ui.write(r.revision(r.lookup(rev), raw=True))
     except KeyError:
         raise error.Abort(_('invalid revision identifier %s') % rev)
 
 @command('debugdate',
     [('e', 'extended', None, _('try extended date formats'))],
     _('[-e] DATE [RANGE]'),
     norepo=True, optionalrepo=True)
 def debugdate(ui, date, range=None, **opts):
     """parse and display a date"""
     if opts["extended"]:
         d = util.parsedate(date, util.extendeddateformats)
     else:
         d = util.parsedate(date)
     ui.write(("internal: %s %s\n") % d)
     ui.write(("standard: %s\n") % util.datestr(d))
     if range:
         m = util.matchdate(range)
         ui.write(("match: %s\n") % m(d[0]))
 
 @command('debugdeltachain',
     commands.debugrevlogopts + commands.formatteropts,
     _('-c|-m|FILE'),
     optionalrepo=True)
 def debugdeltachain(ui, repo, file_=None, **opts):
     """dump information about delta chains in a revlog
 
     Output can be templatized. Available template keywords are:
 
     :``rev``:       revision number
     :``chainid``:   delta chain identifier (numbered by unique base)
     :``chainlen``:  delta chain length to this revision
     :``prevrev``:   previous revision in delta chain
     :``deltatype``: role of delta / how it was computed
     :``compsize``:  compressed size of revision
     :``uncompsize``: uncompressed size of revision
     :``chainsize``: total size of compressed revisions in chain
     :``chainratio``: total chain size divided by uncompressed revision size
                     (new delta chains typically start at ratio 2.00)
     :``lindist``:   linear distance from base revision in delta chain to end
                     of this revision
     :``extradist``: total size of revisions not part of this delta chain from
                     base of delta chain to end of this revision; a measurement
                     of how much extra data we need to read/seek across to read
                     the delta chain for this revision
     :``extraratio``: extradist divided by chainsize; another representation of
                     how much unrelated data is needed to load this delta chain
     """
     r = cmdutil.openrevlog(repo, 'debugdeltachain', file_, opts)
     index = r.index
     generaldelta = r.version & revlog.REVLOGGENERALDELTA
 
     def revinfo(rev):
         e = index[rev]
         compsize = e[1]
         uncompsize = e[2]
         chainsize = 0
 
         if generaldelta:
             if e[3] == e[5]:
                 deltatype = 'p1'
             elif e[3] == e[6]:
                 deltatype = 'p2'
             elif e[3] == rev - 1:
                 deltatype = 'prev'
             elif e[3] == rev:
                 deltatype = 'base'
             else:
                 deltatype = 'other'
         else:
             if e[3] == rev:
                 deltatype = 'base'
             else:
                 deltatype = 'prev'
 
         chain = r._deltachain(rev)[0]
         for iterrev in chain:
             e = index[iterrev]
             chainsize += e[1]
 
         return compsize, uncompsize, deltatype, chain, chainsize
 
     fm = ui.formatter('debugdeltachain', opts)
 
     fm.plain('    rev  chain# chainlen     prev   delta       '
              'size    rawsize  chainsize     ratio   lindist extradist '
              'extraratio\n')
 
     chainbases = {}
     for rev in r:
         comp, uncomp, deltatype, chain, chainsize = revinfo(rev)
         chainbase = chain[0]
         chainid = chainbases.setdefault(chainbase, len(chainbases) + 1)
         basestart = r.start(chainbase)
         revstart = r.start(rev)
         lineardist = revstart + comp - basestart
         extradist = lineardist - chainsize
         try:
             prevrev = chain[-2]
         except IndexError:
             prevrev = -1
 
         chainratio = float(chainsize) / float(uncomp)
         extraratio = float(extradist) / float(chainsize)
 
         fm.startitem()
         fm.write('rev chainid chainlen prevrev deltatype compsize '
                  'uncompsize chainsize chainratio lindist extradist '
                  'extraratio',
                  '%7d %7d %8d %8d %7s %10d %10d %10d %9.5f %9d %9d %10.5f\n',
                  rev, chainid, len(chain), prevrev, deltatype, comp,
                  uncomp, chainsize, chainratio, lineardist, extradist,
                  extraratio,
                  rev=rev, chainid=chainid, chainlen=len(chain),
                  prevrev=prevrev, deltatype=deltatype, compsize=comp,
                  uncompsize=uncomp, chainsize=chainsize,
                  chainratio=chainratio, lindist=lineardist,
                  extradist=extradist, extraratio=extraratio)
 
     fm.end()
 
 @command('debugdiscovery',
     [('', 'old', None, _('use old-style discovery')),
     ('', 'nonheads', None,
      _('use old-style discovery with non-heads included')),
     ] + commands.remoteopts,
     _('[-l REV] [-r REV] [-b BRANCH]... [OTHER]'))
 def debugdiscovery(ui, repo, remoteurl="default", **opts):
     """runs the changeset discovery protocol in isolation"""
     remoteurl, branches = hg.parseurl(ui.expandpath(remoteurl),
                                       opts.get('branch'))
     remote = hg.peer(repo, opts, remoteurl)
     ui.status(_('comparing with %s\n') % util.hidepassword(remoteurl))
 
     # make sure tests are repeatable
     random.seed(12323)
 
     def doit(localheads, remoteheads, remote=remote):
         if opts.get('old'):
             if localheads:
                 raise error.Abort('cannot use localheads with old style '
                                  'discovery')
             if not util.safehasattr(remote, 'branches'):
                 # enable in-client legacy support
                 remote = localrepo.locallegacypeer(remote.local())
             common, _in, hds = treediscovery.findcommonincoming(repo, remote,
                                                                 force=True)
             common = set(common)
             if not opts.get('nonheads'):
                 ui.write(("unpruned common: %s\n") %
                          " ".join(sorted(short(n) for n in common)))
                 dag = dagutil.revlogdag(repo.changelog)
                 all = dag.ancestorset(dag.internalizeall(common))
                 common = dag.externalizeall(dag.headsetofconnecteds(all))
         else:
             common, any, hds = setdiscovery.findcommonheads(ui, repo, remote)
         common = set(common)
         rheads = set(hds)
         lheads = set(repo.heads())
         ui.write(("common heads: %s\n") %
                  " ".join(sorted(short(n) for n in common)))
         if lheads <= common:
             ui.write(("local is subset\n"))
         elif rheads <= common:
             ui.write(("remote is subset\n"))
 
     serverlogs = opts.get('serverlog')
     if serverlogs:
         for filename in serverlogs:
             with open(filename, 'r') as logfile:
                 line = logfile.readline()
                 while line:
                     parts = line.strip().split(';')
                     op = parts[1]
                     if op == 'cg':
                         pass
                     elif op == 'cgss':
                         doit(parts[2].split(' '), parts[3].split(' '))
                     elif op == 'unb':
                         doit(parts[3].split(' '), parts[2].split(' '))
                     line = logfile.readline()
     else:
         remoterevs, _checkout = hg.addbranchrevs(repo, remote, branches,
                                                  opts.get('remote_head'))
         localrevs = opts.get('local_head')
         doit(localrevs, remoterevs)
 
 @command('debugextensions', commands.formatteropts, [], norepo=True)
 def debugextensions(ui, **opts):
     '''show information about active extensions'''
     exts = extensions.extensions(ui)
     hgver = util.version()
     fm = ui.formatter('debugextensions', opts)
     for extname, extmod in sorted(exts, key=operator.itemgetter(0)):
         isinternal = extensions.ismoduleinternal(extmod)
         extsource = extmod.__file__
         if isinternal:
             exttestedwith = []  # never expose magic string to users
         else:
             exttestedwith = getattr(extmod, 'testedwith', '').split()
         extbuglink = getattr(extmod, 'buglink', None)
 
         fm.startitem()
 
         if ui.quiet or ui.verbose:
             fm.write('name', '%s\n', extname)
         else:
             fm.write('name', '%s', extname)
             if isinternal or hgver in exttestedwith:
                 fm.plain('\n')
             elif not exttestedwith:
                 fm.plain(_(' (untested!)\n'))
             else:
                 lasttestedversion = exttestedwith[-1]
                 fm.plain(' (%s!)\n' % lasttestedversion)
 
         fm.condwrite(ui.verbose and extsource, 'source',
                  _('  location: %s\n'), extsource or "")
 
         if ui.verbose:
             fm.plain(_('  bundled: %s\n') % ['no', 'yes'][isinternal])
         fm.data(bundled=isinternal)
 
         fm.condwrite(ui.verbose and exttestedwith, 'testedwith',
                      _('  tested with: %s\n'),
                      fm.formatlist(exttestedwith, name='ver'))
 
         fm.condwrite(ui.verbose and extbuglink, 'buglink',
                  _('  bug reporting: %s\n'), extbuglink or "")
 
     fm.end()
 
 @command('debugfileset',
     [('r', 'rev', '', _('apply the filespec on this revision'), _('REV'))],
     _('[-r REV] FILESPEC'))
 def debugfileset(ui, repo, expr, **opts):
     '''parse and apply a fileset specification'''
     ctx = scmutil.revsingle(repo, opts.get('rev'), None)
     if ui.verbose:
         tree = fileset.parse(expr)
         ui.note(fileset.prettyformat(tree), "\n")
 
     for f in ctx.getfileset(expr):
         ui.write("%s\n" % f)
 
 @command('debugfsinfo', [], _('[PATH]'), norepo=True)
 def debugfsinfo(ui, path="."):
     """show information detected about current filesystem"""
     util.writefile('.debugfsinfo', '')
     ui.write(('exec: %s\n') % (util.checkexec(path) and 'yes' or 'no'))
     ui.write(('symlink: %s\n') % (util.checklink(path) and 'yes' or 'no'))
     ui.write(('hardlink: %s\n') % (util.checknlink(path) and 'yes' or 'no'))
     ui.write(('case-sensitive: %s\n') % (util.fscasesensitive('.debugfsinfo')
                                 and 'yes' or 'no'))
     os.unlink('.debugfsinfo')
 
 @command('debuggetbundle',
     [('H', 'head', [], _('id of head node'), _('ID')),
     ('C', 'common', [], _('id of common node'), _('ID')),
     ('t', 'type', 'bzip2', _('bundle compression type to use'), _('TYPE'))],
     _('REPO FILE [-H|-C ID]...'),
     norepo=True)
 def debuggetbundle(ui, repopath, bundlepath, head=None, common=None, **opts):
     """retrieves a bundle from a repo
 
     Every ID must be a full-length hex node id string. Saves the bundle to the
     given file.
     """
     repo = hg.peer(ui, opts, repopath)
     if not repo.capable('getbundle'):
         raise error.Abort("getbundle() not supported by target repository")
     args = {}
     if common:
         args['common'] = [bin(s) for s in common]
     if head:
         args['heads'] = [bin(s) for s in head]
     # TODO: get desired bundlecaps from command line.
     args['bundlecaps'] = None
     bundle = repo.getbundle('debug', **args)
 
     bundletype = opts.get('type', 'bzip2').lower()
     btypes = {'none': 'HG10UN',
               'bzip2': 'HG10BZ',
               'gzip': 'HG10GZ',
               'bundle2': 'HG20'}
     bundletype = btypes.get(bundletype)
     if bundletype not in bundle2.bundletypes:
         raise error.Abort(_('unknown bundle type specified with --type'))
     bundle2.writebundle(ui, bundle, bundlepath, bundletype)
 
 @command('debugignore', [], '[FILE]')
 def debugignore(ui, repo, *files, **opts):
     """display the combined ignore pattern and information about ignored files
 
     With no argument display the combined ignore pattern.
 
     Given space separated file names, shows if the given file is ignored and
     if so, show the ignore rule (file and line number) that matched it.
     """
     ignore = repo.dirstate._ignore
     if not files:
         # Show all the patterns
         includepat = getattr(ignore, 'includepat', None)
         if includepat is not None:
             ui.write("%s\n" % includepat)
         else:
             raise error.Abort(_("no ignore patterns found"))
     else:
         for f in files:
             nf = util.normpath(f)
             ignored = None
             ignoredata = None
             if nf != '.':
                 if ignore(nf):
                     ignored = nf
                     ignoredata = repo.dirstate._ignorefileandline(nf)
                 else:
                     for p in util.finddirs(nf):
                         if ignore(p):
                             ignored = p
                             ignoredata = repo.dirstate._ignorefileandline(p)
                             break
             if ignored:
                 if ignored == nf:
                     ui.write(_("%s is ignored\n") % f)
                 else:
                     ui.write(_("%s is ignored because of "
                                "containing folder %s\n")
                              % (f, ignored))
                 ignorefile, lineno, line = ignoredata
                 ui.write(_("(ignore rule in %s, line %d: '%s')\n")
                          % (ignorefile, lineno, line))
             else:
                 ui.write(_("%s is not ignored\n") % f)
 
 @command('debugindex', commands.debugrevlogopts +
     [('f', 'format', 0, _('revlog format'), _('FORMAT'))],
     _('[-f FORMAT] -c|-m|FILE'),
     optionalrepo=True)
 def debugindex(ui, repo, file_=None, **opts):
     """dump the contents of an index file"""
     r = cmdutil.openrevlog(repo, 'debugindex', file_, opts)
     format = opts.get('format', 0)
     if format not in (0, 1):
         raise error.Abort(_("unknown format %d") % format)
 
     generaldelta = r.version & revlog.REVLOGGENERALDELTA
     if generaldelta:
         basehdr = ' delta'
     else:
         basehdr = '  base'
 
     if ui.debugflag:
         shortfn = hex
     else:
         shortfn = short
 
     # There might not be anything in r, so have a sane default
     idlen = 12
     for i in r:
         idlen = len(shortfn(r.node(i)))
         break
 
     if format == 0:
         ui.write(("   rev    offset  length " + basehdr + " linkrev"
                  " %s %s p2\n") % ("nodeid".ljust(idlen), "p1".ljust(idlen)))
     elif format == 1:
         ui.write(("   rev flag   offset   length"
                  "     size " + basehdr + "   link     p1     p2"
                  " %s\n") % "nodeid".rjust(idlen))
 
     for i in r:
         node = r.node(i)
         if generaldelta:
             base = r.deltaparent(i)
         else:
             base = r.chainbase(i)
         if format == 0:
             try:
                 pp = r.parents(node)
             except Exception:
                 pp = [nullid, nullid]
             ui.write("% 6d % 9d % 7d % 6d % 7d %s %s %s\n" % (
                     i, r.start(i), r.length(i), base, r.linkrev(i),
                     shortfn(node), shortfn(pp[0]), shortfn(pp[1])))
         elif format == 1:
             pr = r.parentrevs(i)
             ui.write("% 6d %04x % 8d % 8d % 8d % 6d % 6d % 6d % 6d %s\n" % (
                     i, r.flags(i), r.start(i), r.length(i), r.rawsize(i),
                     base, r.linkrev(i), pr[0], pr[1], shortfn(node)))
 
 @command('debugindexdot', commands.debugrevlogopts,
     _('-c|-m|FILE'), optionalrepo=True)
 def debugindexdot(ui, repo, file_=None, **opts):
     """dump an index DAG as a graphviz dot file"""
     r = cmdutil.openrevlog(repo, 'debugindexdot', file_, opts)
     ui.write(("digraph G {\n"))
     for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write("\t%d -> %d\n" % (r.rev(pp[0]), i))
         if pp[1] != nullid:
             ui.write("\t%d -> %d\n" % (r.rev(pp[1]), i))
     ui.write("}\n")

mercurial/revlog.py

@@ -1,1822 +1,1832 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.
 """
 
 from __future__ import absolute_import
 
 import collections
 import errno
 import hashlib
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from .i18n import _
 from . import (
     ancestor,
     error,
     mdiff,
     parsers,
     templatefilters,
     util,
 )
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 
 # 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_ISCENSORED = (1 << 15) # revision has censor metadata, must be verified
 REVIDX_DEFAULT_FLAGS = 0
 REVIDX_KNOWN_FLAGS = REVIDX_ISCENSORED
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 RevlogError = error.RevlogError
 LookupError = error.LookupError
 CensoredNodeError = error.CensoredNodeError
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     if (type & ~REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError('unknown revlog index flags')
     return long(long(offset) << 16 | type)
 
 _nullhash = hashlib.sha1(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 = hashlib.sha1(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 as e:
             raise RevlogError(_("revlog decompress error: %s") % str(e))
     if t == 'u':
         return util.buffer(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
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 indexformatv0 = ">4l20s20s20s"
 
 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"
 versionformat = ">I"
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7fffffff
 
 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.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
     """
     def __init__(self, opener, indexfile, checkambig=False):
         """
         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
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         # 3-tuple of (node, rev, text) for a raw revision.
         self._cache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, '')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._aggressivemergedeltas = False
         self.index = []
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         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
             if 'chunkcachesize' in opts:
                 self._chunkcachesize = opts['chunkcachesize']
             if 'maxchainlen' in opts:
                 self._maxchainlen = opts['maxchainlen']
             if 'aggressivemergedeltas' in opts:
                 self._aggressivemergedeltas = opts['aggressivemergedeltas']
             self._lazydeltabase = bool(opts.get('lazydeltabase', False))
 
         if self._chunkcachesize <= 0:
             raise RevlogError(_('revlog chunk cache size %r is not greater '
                                 'than 0') % self._chunkcachesize)
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise RevlogError(_('revlog chunk cache size %r is not a power '
                                 'of 2') % self._chunkcachesize)
 
         indexdata = ''
         self._initempty = True
         try:
             f = self.opener(self.indexfile)
             indexdata = f.read()
             f.close()
             if len(indexdata) > 0:
                 v = struct.unpack(versionformat, indexdata[:4])[0]
                 self._initempty = False
         except IOError as 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.storedeltachains = True
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(indexdata, 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()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = {}
 
     def tip(self):
         return self.node(len(self.index) - 2)
     def __contains__(self, rev):
         return 0 <= rev < len(self)
     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):
         self._cache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, '')
         self._pcache = {}
 
         try:
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except TypeError:
             raise
         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'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     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 chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         base = index[rev][3]
         while base != rev:
             rev = base
             base = index[rev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         return self.index[rev][5:7]
 
     def node(self, rev):
         return self.index[rev][7]
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     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 chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     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.parentrevs, 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
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.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(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     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()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     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]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     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 = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root 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 = [head for head, 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 computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     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 commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.commonancestorsheads(a, b)
         except (AttributeError, OverflowError): # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, a, b)
         return map(self.node, ancs)
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         The implementation of this is trivial but the use of
         commonancestorsheads is not."""
         return a in self.commonancestorsheads(a, b)
 
     def ancestor(self, a, b):
         """calculate the "best" 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:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 return partial
             return None
         except RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise LookupError(id, self.indexfile,
                                   _('ambiguous identifier'))
             # fall through to slow path that filters hidden revisions
         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) and
                       self.hasnode(n)]
                 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):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         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, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
         """
         if df is not None:
             closehandle = False
         else:
             if self._inline:
                 df = self.opener(self.indexfile)
             else:
                 df = self.opener(self.datafile)
             closehandle = True
 
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (((offset + length + cachesize) & ~(cachesize - 1))
                       - realoffset)
         df.seek(realoffset)
         d = df.read(reallength)
         if closehandle:
             df.close()
         self._addchunk(realoffset, d)
         if offset != realoffset or reallength != length:
             return util.buffer(d, offset - realoffset, length)
         return d
 
     def _getchunk(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         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, df=df)
 
     def _chunkraw(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self._io.size
             end += (endrev + 1) * self._io.size
         length = end - start
 
         return start, self._getchunk(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return decompress(self._chunkraw(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self._io.size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         try:
             offset, data = self._chunkraw(revs[0], revs[-1], df=df)
         except OverflowError:
             # issue4215 - we can't cache a run of chunks greater than
             # 2G on Windows
             return [self._chunk(rev, df=df) for rev in revs]
 
         for rev in revs:
             chunkstart = start(rev)
             if inline:
                 chunkstart += (rev + 1) * iosize
             chunklength = length(rev)
             ladd(decompress(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         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, _df=None):
+    def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
-        _df is an existing file handle to read from. It is meant to only be
-        used internally.
+        _df - an existing file handle to read from. (internal-only)
+        raw - an optional argument specifying if the revision data is to be
+        treated as raw data when applying flag transforms. 'raw' should be set
+        to True when generating changegroups or in debug commands.
         """
         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))
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             text = self._cache[2]
 
         # drop cache to save memory
         self._cache = None
 
         bins = self._chunks(chain, df=_df)
         if text is None:
             text = str(bins[0])
             bins = bins[1:]
 
         text = mdiff.patches(text, bins)
         self.checkhash(text, node, rev=rev)
         self._cache = (node, rev, text)
         return text
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return hash(text, p1, p2)
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         if p1 is None and p2 is None:
             p1, p2 = self.parents(node)
         if node != self.hash(text, p1, p2):
             revornode = rev
             if revornode is None:
                 revornode = templatefilters.short(hex(node))
             raise RevlogError(_("integrity check failed on %s:%s")
                 % (self.indexfile, revornode))
 
     def checkinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         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]
         if trindex is not None:
             dataoff = self.start(trindex)
         else:
             # revlog was stripped at start of transaction, use all leftover data
             trindex = len(self) - 1
             dataoff = self.end(-2)
 
         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)[1])
         finally:
             df.close()
 
         fp = self.opener(self.indexfile, 'w', atomictemp=True,
                          checkambig=self._checkambig)
         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,
                     node=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 - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         """
         if link == nullrev:
             raise RevlogError(_("attempted to add linkrev -1 to %s")
                               % self.indexfile)
 
         if len(text) > _maxentrysize:
             raise RevlogError(
                 _("%s: size of %d bytes exceeds maximum revlog storage of 2GiB")
                 % (self.indexfile, len(text)))
 
         node = node or self.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+", checkambig=self._checkambig)
         try:
             return self._addrevision(node, text, transaction, link, p1, p2,
                                      REVIDX_DEFAULT_FLAGS, 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 _isgooddelta(self, d, textlen):
         """Returns True if the given delta is good. Good means that it is within
         the disk span, disk size, and chain length bounds that we know to be
         performant."""
         if d is None:
             return False
 
         # - 'dist' is the distance from the base revision -- bounding it limits
         #   the amount of I/O we need to do.
         # - 'compresseddeltalen' is the sum of the total size of deltas we need
         #   to apply -- bounding it limits the amount of CPU we consume.
         dist, l, data, base, chainbase, chainlen, compresseddeltalen = d
         if (dist > textlen * 4 or l > textlen or
             compresseddeltalen > textlen * 2 or
             (self._maxchainlen and chainlen > self._maxchainlen)):
             return False
 
         return True
 
     def _addrevision(self, node, text, transaction, link, p1, p2, flags,
-                     cachedelta, ifh, dfh, alwayscache=False):
+                     cachedelta, ifh, dfh, alwayscache=False, raw=False):
         """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.
+        - raw is optional; if set to True, it indicates the revision data is to
+          be treated by _processflags() as raw. It is usually set by changegroup
+          generation and debug commands.
         """
         btext = [text]
         def buildtext():
             if btext[0] is not None:
                 return btext[0]
             baserev = cachedelta[0]
             delta = cachedelta[1]
             # special case deltas which replace entire base; no need to decode
             # base revision. this neatly avoids censored bases, which throw when
             # they're decoded.
             hlen = struct.calcsize(">lll")
             if delta[:hlen] == mdiff.replacediffheader(self.rawsize(baserev),
                                                        len(delta) - hlen):
                 btext[0] = delta[hlen:]
             else:
                 if self._inline:
                     fh = ifh
                 else:
                     fh = dfh
-                basetext = self.revision(self.node(baserev), _df=fh)
+                basetext = self.revision(self.node(baserev), _df=fh, raw=raw)
                 btext[0] = mdiff.patch(basetext, delta)
+
             try:
                 self.checkhash(btext[0], node, p1=p1, p2=p2)
                 if flags & REVIDX_ISCENSORED:
                     raise RevlogError(_('node %s is not censored') % node)
             except CensoredNodeError:
                 # must pass the censored index flag to add censored revisions
                 if not flags & REVIDX_ISCENSORED:
                     raise
             return btext[0]
 
         def builddelta(rev):
             # can we use the cached delta?
             if cachedelta and cachedelta[0] == rev:
                 delta = cachedelta[1]
             else:
                 t = buildtext()
                 if self.iscensored(rev):
                     # deltas based on a censored revision must replace the
                     # full content in one patch, so delta works everywhere
                     header = mdiff.replacediffheader(self.rawsize(rev), len(t))
                     delta = header + t
                 else:
                     if self._inline:
                         fh = ifh
                     else:
                         fh = dfh
                     ptext = self.revision(self.node(rev), _df=fh)
                     delta = mdiff.textdiff(ptext, t)
             header, data = self.compress(delta)
             deltalen = len(header) + len(data)
             chainbase = self.chainbase(rev)
             dist = deltalen + offset - self.start(chainbase)
             if self._generaldelta:
                 base = rev
             else:
                 base = chainbase
             chainlen, compresseddeltalen = self._chaininfo(rev)
             chainlen += 1
             compresseddeltalen += deltalen
             return (dist, deltalen, (header, data), base,
                     chainbase, chainlen, compresseddeltalen)
 
         curr = len(self)
         prev = curr - 1
         offset = self.end(prev)
         delta = None
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # 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)
 
         # should we try to build a delta?
         if prev != nullrev and self.storedeltachains:
             tested = set()
             # This condition is true most of the time when processing
             # changegroup data into a generaldelta repo. The only time it
             # isn't true is if this is the first revision in a delta chain
             # or if ``format.generaldelta=true`` disabled ``lazydeltabase``.
             if cachedelta and self._generaldelta and self._lazydeltabase:
                 # Assume what we received from the server is a good choice
                 # build delta will reuse the cache
                 candidatedelta = builddelta(cachedelta[0])
                 tested.add(cachedelta[0])
                 if self._isgooddelta(candidatedelta, textlen):
                     delta = candidatedelta
             if delta is None and self._generaldelta:
                 # exclude already lazy tested base if any
                 parents = [p for p in (p1r, p2r)
                            if p != nullrev and p not in tested]
                 if parents and not self._aggressivemergedeltas:
                     # Pick whichever parent is closer to us (to minimize the
                     # chance of having to build a fulltext).
                     parents = [max(parents)]
                 tested.update(parents)
                 pdeltas = []
                 for p in parents:
                     pd = builddelta(p)
                     if self._isgooddelta(pd, textlen):
                         pdeltas.append(pd)
                 if pdeltas:
                     delta = min(pdeltas, key=lambda x: x[1])
             if delta is None and prev not in tested:
                 # other approach failed try against prev to hopefully save us a
                 # fulltext.
                 candidatedelta = builddelta(prev)
                 if self._isgooddelta(candidatedelta, textlen):
                     delta = candidatedelta
         if delta is not None:
             dist, l, data, base, chainbase, chainlen, compresseddeltalen = delta
         else:
             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)
         self._writeentry(transaction, ifh, dfh, entry, data, link, offset)
 
         if alwayscache and text is None:
             text = buildtext()
 
         if type(text) == str: # only accept immutable objects
             self._cache = (node, curr, text)
         self._chainbasecache[curr] = chainbase
         return node
 
     def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         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])
             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)
 
     def addgroup(self, cg, linkmapper, transaction, addrevisioncb=None):
         """
         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.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         # 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+", checkambig=self._checkambig)
         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+")
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
         try:
             # loop through our set of deltas
             chain = None
             for chunkdata in iter(lambda: cg.deltachunk(chain), {}):
                 node = chunkdata['node']
                 p1 = chunkdata['p1']
                 p2 = chunkdata['p2']
                 cs = chunkdata['cs']
                 deltabase = chunkdata['deltabase']
                 delta = chunkdata['delta']
                 flags = chunkdata['flags'] or REVIDX_DEFAULT_FLAGS
 
                 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)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(self.indexfile,
                                                       self.node(baserev))
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
+                # We're only using addgroup() in the context of changegroup
+                # generation so the revision data can always be handled as raw
+                # by the flagprocessor.
                 chain = self._addrevision(node, None, transaction, link,
                                           p1, p2, flags, (baserev, delta),
                                           ifh, dfh,
-                                          alwayscache=bool(addrevisioncb))
+                                          alwayscache=bool(addrevisioncb),
+                                          raw=True)
 
                 if addrevisioncb:
                     addrevisioncb(self, chain)
 
                 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+",
                                       checkambig=self._checkambig)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
         return content
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         return False
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         return False
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         brokenrevs = set()
         strippoint = len(self)
 
         heads = {}
         futurelargelinkrevs = set()
         for head in self.headrevs():
             headlinkrev = self.linkrev(head)
             heads[head] = headlinkrev
             if headlinkrev >= minlink:
                 futurelargelinkrevs.add(headlinkrev)
 
         # This algorithm involves walking down the rev graph, starting at the
         # heads. Since the revs are topologically sorted according to linkrev,
         # once all head linkrevs are below the minlink, we know there are
         # no more revs that could have a linkrev greater than minlink.
         # So we can stop walking.
         while futurelargelinkrevs:
             strippoint -= 1
             linkrev = heads.pop(strippoint)
 
             if linkrev < minlink:
                 brokenrevs.add(strippoint)
             else:
                 futurelargelinkrevs.remove(linkrev)
 
             for p in self.parentrevs(strippoint):
                 if p != nullrev:
                     plinkrev = self.linkrev(p)
                     heads[p] = plinkrev
                     if plinkrev >= minlink:
                         futurelargelinkrevs.add(plinkrev)
 
         return strippoint, brokenrevs
 
     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
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             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._chaininfocache = {}
         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 as 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 as 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

mercurial/unionrepo.py

@@ -1,260 +1,260 b''
 # unionrepo.py - repository class for viewing union of repository changesets
 #
 # Derived from bundlerepo.py
 # Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
 # Copyright 2013 Unity Technologies, Mads Kiilerich <[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.
 
 """Repository class for "in-memory pull" of one local repository to another,
 allowing operations like diff and log with revsets.
 """
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import nullid
 
 from . import (
     changelog,
     cmdutil,
     error,
     filelog,
     localrepo,
     manifest,
     mdiff,
     pathutil,
     pycompat,
     revlog,
     scmutil,
     util,
 )
 
 class unionrevlog(revlog.revlog):
     def __init__(self, opener, indexfile, revlog2, linkmapper):
         # How it works:
         # To retrieve a revision, we just need to know the node id so we can
         # look it up in revlog2.
         #
         # To differentiate a rev in the second revlog from a rev in the revlog,
         # we check revision against repotiprev.
         opener = scmutil.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.revlog2 = revlog2
 
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set() # used by 'bundle()' revset expression
         for rev2 in self.revlog2:
             rev = self.revlog2.index[rev2]
             # rev numbers - in revlog2, very different from self.rev
             _start, _csize, _rsize, base, linkrev, p1rev, p2rev, node = rev
             flags = _start & 0xFFFF
 
             if linkmapper is None: # link is to same revlog
                 assert linkrev == rev2 # we never link back
                 link = n
             else: # rev must be mapped from repo2 cl to unified cl by linkmapper
                 link = linkmapper(linkrev)
 
             if linkmapper is not None: # link is to same revlog
                 base = linkmapper(base)
 
             if node in self.nodemap:
                 # this happens for the common revlog revisions
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             p1node = self.revlog2.node(p1rev)
             p2node = self.revlog2.node(p2rev)
 
             e = (flags, None, None, base,
                  link, self.rev(p1node), self.rev(p2node), node)
             self.index.insert(-1, e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             n += 1
 
     def _chunk(self, rev):
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         return self.revlog2._chunk(self.node(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             return self.revlog2.revdiff(
                 self.revlog2.rev(self.node(rev1)),
                 self.revlog2.rev(self.node(rev2)))
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return self.baserevdiff(rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                               self.revision(self.node(rev2)))
 
-    def revision(self, nodeorrev):
+    def revision(self, nodeorrev, raw=False):
         """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 = self.rev(node)
 
         if node == nullid:
             return ""
 
         if rev > self.repotiprev:
             text = self.revlog2.revision(node)
             self._cache = (node, rev, text)
         else:
             text = self.baserevision(rev)
             # already cached
         return text
 
     def baserevision(self, nodeorrev):
         # Revlog subclasses may override 'revision' method to modify format of
         # content retrieved from revlog. To use unionrevlog with such class one
         # needs to override 'baserevision' and make more specific call here.
         return revlog.revlog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         # Exists for the same purpose as baserevision.
         return revlog.revlog.revdiff(self, rev1, rev2)
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class unionchangelog(unionrevlog, changelog.changelog):
     def __init__(self, opener, opener2):
         changelog.changelog.__init__(self, opener)
         linkmapper = None
         changelog2 = changelog.changelog(opener2)
         unionrevlog.__init__(self, opener, self.indexfile, changelog2,
                              linkmapper)
 
     def baserevision(self, nodeorrev):
         # Although changelog doesn't override 'revision' method, some extensions
         # may replace this class with another that does. Same story with
         # manifest and filelog classes.
         return changelog.changelog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return changelog.changelog.revdiff(self, rev1, rev2)
 
 class unionmanifest(unionrevlog, manifest.manifestrevlog):
     def __init__(self, opener, opener2, linkmapper):
         manifest.manifestrevlog.__init__(self, opener)
         manifest2 = manifest.manifestrevlog(opener2)
         unionrevlog.__init__(self, opener, self.indexfile, manifest2,
                              linkmapper)
 
     def baserevision(self, nodeorrev):
         return manifest.manifestrevlog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return manifest.manifestrevlog.revdiff(self, rev1, rev2)
 
 class unionfilelog(unionrevlog, filelog.filelog):
     def __init__(self, opener, path, opener2, linkmapper, repo):
         filelog.filelog.__init__(self, opener, path)
         filelog2 = filelog.filelog(opener2, path)
         unionrevlog.__init__(self, opener, self.indexfile, filelog2,
                              linkmapper)
         self._repo = repo
 
     def baserevision(self, nodeorrev):
         return filelog.filelog.revision(self, nodeorrev)
 
     def baserevdiff(self, rev1, rev2):
         return filelog.filelog.revdiff(self, rev1, rev2)
 
     def iscensored(self, rev):
         """Check if a revision is censored."""
         if rev <= self.repotiprev:
             return filelog.filelog.iscensored(self, rev)
         node = self.node(rev)
         return self.revlog2.iscensored(self.revlog2.rev(node))
 
 class unionpeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 class unionrepository(localrepo.localrepository):
     def __init__(self, ui, path, path2):
         localrepo.localrepository.__init__(self, ui, path)
         self.ui.setconfig('phases', 'publish', False, 'unionrepo')
 
         self._url = 'union:%s+%s' % (util.expandpath(path),
                                      util.expandpath(path2))
         self.repo2 = localrepo.localrepository(ui, path2)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         return unionchangelog(self.svfs, self.repo2.svfs)
 
     def _clrev(self, rev2):
         """map from repo2 changelog rev to temporary rev in self.changelog"""
         node = self.repo2.changelog.node(rev2)
         return self.changelog.rev(node)
 
     def _constructmanifest(self):
         return unionmanifest(self.svfs, self.repo2.svfs,
                              self.unfiltered()._clrev)
 
     def url(self):
         return self._url
 
     def file(self, f):
         return unionfilelog(self.svfs, f, self.repo2.svfs,
                             self.unfiltered()._clrev, self)
 
     def close(self):
         self.repo2.close()
 
     def cancopy(self):
         return False
 
     def peer(self):
         return unionpeer(self)
 
     def getcwd(self):
         return pycompat.getcwd() # always outside the repo
 
 def instance(ui, path, create):
     if create:
         raise error.Abort(_('cannot create new union repository'))
     parentpath = ui.config("bundle", "mainreporoot", "")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(pycompat.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = pycompat.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     if path.startswith('union:'):
         s = path.split(":", 1)[1].split("+", 1)
         if len(s) == 1:
             repopath, repopath2 = parentpath, s[0]
         else:
             repopath, repopath2 = s
     else:
         repopath, repopath2 = parentpath, path
     return unionrepository(ui, repopath, repopath2)