revlog: recommit 49fd21f32695 with a fix for issue6528

`filelog.size` currently special cases two forms of metadata encoding:
- copy data via the parent order as flag bit
- censor data by peaking into the raw delta
All other forms of metadata encoding including the empty metadata block
are mishandled. In `basefilectx.cmp` the empty metadata block is
explicitly checked to compensate for this.

Restore 49fd21f32695, but disable it for filelog, so that the original
flag bit use contines to work. Document all this mess for now in
preparation of a proper rework.

Differential Revision: https://phab.mercurial-scm.org/D11203

mercurial/context.py

@@ -1,3145 +1,3155 b''
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import errno
 import filecmp
 import os
 import stat
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
     short,
 )
 from .pycompat import (
     getattr,
 )
 from . import (
     dagop,
     encoding,
     error,
     fileset,
     match as matchmod,
     mergestate as mergestatemod,
     metadata,
     obsolete as obsmod,
     patch,
     pathutil,
     phases,
     pycompat,
     repoview,
     scmutil,
     sparse,
     subrepo,
     subrepoutil,
     util,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
 from .dirstateutils import (
     timestamp,
 )
 
 propertycache = util.propertycache
 
 
 class basectx:
     """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 __init__(self, repo):
         self._repo = repo
 
     def __bytes__(self):
         return short(self.node())
 
     __str__ = encoding.strmethod(__bytes__)
 
     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 _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results, if this is
         a working copy context. For non-working copy contexts, it just returns
         the normal manifest."""
         return self.manifest()
 
     def _matchstatus(self, other, match):
         """This internal method provides a way for child objects to override the
         match operator.
         """
         return match
 
     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.
         mf2 = None
         if self.rev() is not None and self.rev() < other.rev():
             mf2 = self._buildstatusmanifest(s)
         mf1 = other._buildstatusmanifest(s)
         if mf2 is None:
             mf2 = self._buildstatusmanifest(s)
 
         modified, added = [], []
         removed = []
         clean = []
         deleted, unknown, ignored = s.deleted, s.unknown, s.ignored
         deletedset = set(deleted)
         d = mf1.diff(mf2, match=match, clean=listclean)
         for fn, value in d.items():
             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 not in self._repo.nodeconstants.wdirfilenodeids:
                 # 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 and (not match or match(fn))
             ]
             ignored = [
                 fn
                 for fn in ignored
                 if fn not in mf1 and (not match or match(fn))
             ]
             # 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 subrepoutil.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 matchfileset(self, cwd, expr, badfn=None):
         return fileset.match(self, cwd, expr, badfn=badfn)
 
     def obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, b'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, b'extinct')
 
     def orphan(self):
         """True if the changeset is not obsolete, but its ancestor is"""
         return self.rev() in obsmod.getrevs(self._repo, b'orphan')
 
     def phasedivergent(self):
         """True if the changeset tries to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be phase-divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, b'phasedivergent')
 
     def contentdivergent(self):
         """Is a successor of a changeset with multiple possible successor sets
 
         Only non-public and non-obsolete changesets may be content-divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, b'contentdivergent')
 
     def isunstable(self):
         """True if the changeset is either orphan, phase-divergent or
         content-divergent"""
         return self.orphan() or self.phasedivergent() or self.contentdivergent()
 
     def instabilities(self):
         """return the list of instabilities affecting this changeset.
 
         Instabilities are returned as strings. possible values are:
         - orphan,
         - phase-divergent,
         - content-divergent.
         """
         instabilities = []
         if self.orphan():
             instabilities.append(b'orphan')
         if self.phasedivergent():
             instabilities.append(b'phase-divergent')
         if self.contentdivergent():
             instabilities.append(b'content-divergent')
         return instabilities
 
     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 self._repo[nullrev]
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.find(path)
             except KeyError:
                 raise error.ManifestLookupError(
                     self._node or b'None', path, _(b'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 or b'None', path, _(b'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 b''
 
     @propertycache
     def _copies(self):
         return metadata.computechangesetcopies(self)
 
     def p1copies(self):
         return self._copies[0]
 
     def p2copies(self):
         return self._copies[1]
 
     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=None,
         include=None,
         exclude=None,
         default=b'glob',
         listsubrepos=False,
         badfn=None,
         cwd=None,
     ):
         r = self._repo
         if not cwd:
             cwd = r.getcwd()
         return matchmod.match(
             r.root,
             cwd,
             pats,
             include,
             exclude,
             default,
             auditor=r.nofsauditor,
             ctx=self,
             listsubrepos=listsubrepos,
             badfn=badfn,
         )
 
     def diff(
         self,
         ctx2=None,
         match=None,
         changes=None,
         opts=None,
         losedatafn=None,
         pathfn=None,
         copy=None,
         copysourcematch=None,
         hunksfilterfn=None,
     ):
         """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]
         return patch.diff(
             self._repo,
             ctx2,
             self,
             match=match,
             changes=changes,
             opts=opts,
             losedatafn=losedatafn,
             pathfn=pathfn,
             copy=copy,
             copysourcematch=copysourcematch,
             hunksfilterfn=hunksfilterfn,
         )
 
     def dirs(self):
         return self._manifest.dirs()
 
     def hasdir(self, dir):
         return self._manifest.hasdir(dir)
 
     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.
 
         ctx1.status(ctx2) returns the status of change from ctx1 to ctx2
 
         Returns a mercurial.scmutils.status object.
 
         Data can be accessed using either tuple notation:
 
             (modified, added, removed, deleted, unknown, ignored, clean)
 
         or direct attribute access:
 
             s.modified, s.added, ...
         """
 
         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 = self._repo.narrowmatch(match)
         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 k in (
                     'modified',
                     'added',
                     'removed',
                     'deleted',
                     'unknown',
                     'ignored',
                     'clean',
                 ):
                     rfiles, sfiles = getattr(r, k), getattr(s, k)
                     rfiles.extend(b"%s/%s" % (subpath, f) for f in sfiles)
 
         r.modified.sort()
         r.added.sort()
         r.removed.sort()
         r.deleted.sort()
         r.unknown.sort()
         r.ignored.sort()
         r.clean.sort()
 
         return r
 
     def mergestate(self, clean=False):
         """Get a mergestate object for this context."""
         raise NotImplementedError(
             '%s does not implement mergestate()' % self.__class__
         )
 
     def isempty(self):
         return not (
             len(self.parents()) > 1
             or self.branch() != self.p1().branch()
             or self.closesbranch()
             or self.files()
         )
 
 
 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, rev, node, maybe_filtered=True):
         super(changectx, self).__init__(repo)
         self._rev = rev
         self._node = node
         # When maybe_filtered is True, the revision might be affected by
         # changelog filtering and operation through the filtered changelog must be used.
         #
         # When maybe_filtered is False, the revision has already been checked
         # against filtering and is not filtered. Operation through the
         # unfiltered changelog might be used in some case.
         self._maybe_filtered = maybe_filtered
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     __bool__ = __nonzero__
 
     @propertycache
     def _changeset(self):
         if self._maybe_filtered:
             repo = self._repo
         else:
             repo = self._repo.unfiltered()
         return repo.changelog.changelogrevision(self.rev())
 
     @propertycache
     def _manifest(self):
         return self._manifestctx.read()
 
     @property
     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
         if self._maybe_filtered:
             cl = repo.changelog
         else:
             cl = repo.unfiltered().changelog
 
         p1, p2 = cl.parentrevs(self._rev)
         if p2 == nullrev:
             return [changectx(repo, p1, cl.node(p1), maybe_filtered=False)]
         return [
             changectx(repo, p1, cl.node(p1), maybe_filtered=False),
             changectx(repo, p2, cl.node(p2), maybe_filtered=False),
         ]
 
     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 filesmodified(self):
         modified = set(self.files())
         modified.difference_update(self.filesadded())
         modified.difference_update(self.filesremoved())
         return sorted(modified)
 
     def filesadded(self):
         filesadded = self._changeset.filesadded
         compute_on_none = True
         if self._repo.filecopiesmode == b'changeset-sidedata':
             compute_on_none = False
         else:
             source = self._repo.ui.config(b'experimental', b'copies.read-from')
             if source == b'changeset-only':
                 compute_on_none = False
             elif source != b'compatibility':
                 # filelog mode, ignore any changelog content
                 filesadded = None
         if filesadded is None:
             if compute_on_none:
                 filesadded = metadata.computechangesetfilesadded(self)
             else:
                 filesadded = []
         return filesadded
 
     def filesremoved(self):
         filesremoved = self._changeset.filesremoved
         compute_on_none = True
         if self._repo.filecopiesmode == b'changeset-sidedata':
             compute_on_none = False
         else:
             source = self._repo.ui.config(b'experimental', b'copies.read-from')
             if source == b'changeset-only':
                 compute_on_none = False
             elif source != b'compatibility':
                 # filelog mode, ignore any changelog content
                 filesremoved = None
         if filesremoved is None:
             if compute_on_none:
                 filesremoved = metadata.computechangesetfilesremoved(self)
             else:
                 filesremoved = []
         return filesremoved
 
     @propertycache
     def _copies(self):
         p1copies = self._changeset.p1copies
         p2copies = self._changeset.p2copies
         compute_on_none = True
         if self._repo.filecopiesmode == b'changeset-sidedata':
             compute_on_none = False
         else:
             source = self._repo.ui.config(b'experimental', b'copies.read-from')
             # If config says to get copy metadata only from changeset, then
             # return that, defaulting to {} if there was no copy metadata.  In
             # compatibility mode, we return copy data from the changeset if it
             # was recorded there, and otherwise we fall back to getting it from
             # the filelogs (below).
             #
             # If we are in compatiblity mode and there is not data in the
             # changeset), we get the copy metadata from the filelogs.
             #
             # otherwise, when config said to read only from filelog, we get the
             # copy metadata from the filelogs.
             if source == b'changeset-only':
                 compute_on_none = False
             elif source != b'compatibility':
                 # filelog mode, ignore any changelog content
                 p1copies = p2copies = None
         if p1copies is None:
             if compute_on_none:
                 p1copies, p2copies = super(changectx, self)._copies
             else:
                 if p1copies is None:
                     p1copies = {}
         if p2copies is None:
             p2copies = {}
         return p1copies, p2copies
 
     def description(self):
         return self._changeset.description
 
     def branch(self):
         return encoding.tolocal(self._changeset.extra.get(b"branch"))
 
     def closesbranch(self):
         return b'close' in self._changeset.extra
 
     def extra(self):
         """Return a dict of extra information."""
         return self._changeset.extra
 
     def tags(self):
         """Return a list of byte tag names"""
         return self._repo.nodetags(self._node)
 
     def bookmarks(self):
         """Return a list of byte bookmark names."""
         return self._repo.nodebookmarks(self._node)
 
     def fast_rank(self):
         repo = self._repo
         if self._maybe_filtered:
             cl = repo.changelog
         else:
             cl = repo.unfiltered().changelog
         return cl.fast_rank(self._rev)
 
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
 
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, b'visible')
 
     def isinmemory(self):
         return False
 
     def children(self):
         """return list of changectx contexts for each child changeset.
 
         This returns only the immediate child changesets. Use descendants() to
         recursively walk children.
         """
         c = self._repo.changelog.children(self._node)
         return [self._repo[x] for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors([self._rev]):
             yield self._repo[a]
 
     def descendants(self):
         """Recursively yield all children of the changeset.
 
         For just the immediate children, use children()
         """
         for d in self._repo.changelog.descendants([self._rev]):
             yield 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 = self._repo.nodeconstants.nullid
         elif len(cahs) == 1:
             anc = cahs[0]
         else:
             # experimental config: merge.preferancestor
             for r in self._repo.ui.configlist(b'merge', b'preferancestor'):
                 try:
                     ctx = scmutil.revsymbol(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(
                     (
                         _(b"note: using %s as ancestor of %s and %s\n")
                         % (short(anc), short(self._node), short(n2))
                     )
                     + b''.join(
                         _(
                             b"      alternatively, use --config "
                             b"merge.preferancestor=%s\n"
                         )
                         % short(n)
                         for n in sorted(cahs)
                         if n != anc
                     )
                 )
         return self._repo[anc]
 
     def isancestorof(self, other):
         """True if this changeset is an ancestor of other"""
         return self._repo.changelog.isancestorrev(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 + b'/') for s in self.substate):
                 return
             match.bad(fn, _(b'no such file in rev %s') % self)
 
         m = matchmod.badmatch(self._repo.narrowmatch(match), bad)
         return self._manifest.walk(m)
 
     def matches(self, match):
         return self.walk(match)
 
 
 class basefilectx:
     """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,
     """
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if '_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
 
     __bool__ = __nonzero__
 
     def __bytes__(self):
         try:
             return b"%s@%s" % (self.path(), self._changectx)
         except error.LookupError:
             return b"%s@???" % self.path()
 
     __str__ = encoding.strmethod(__bytes__)
 
     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
 
     @propertycache
     def _flags(self):
         return self._changectx.flags(self._path)
 
     def flags(self):
         return self._flags
 
     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 obsolete(self):
         return self._changectx.obsolete()
 
     def instabilities(self):
         return self._changectx.instabilities()
 
     def manifest(self):
         return self._changectx.manifest()
 
     def changectx(self):
         return self._changectx
 
     def renamed(self):
         return self._copied
 
     def copysource(self):
         return self._copied and self._copied[0]
 
     def repo(self):
         return self._repo
 
     def size(self):
         return len(self.data())
 
     def path(self):
         return self._path
 
     def isbinary(self):
         try:
             return stringutil.binary(self.data())
         except IOError:
             return False
 
     def isexec(self):
         return b'x' in self.flags()
 
     def islink(self):
         return b'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 self._filenode is None:
             raise error.ProgrammingError(
                 b'filectx.cmp() must be reimplemented if not backed by revlog'
             )
 
         if fctx._filenode is None:
             if self._repo._encodefilterpats:
                 # can't rely on size() because wdir content may be decoded
                 return self._filelog.cmp(self._filenode, fctx.data())
+            # filelog.size() has two special cases:
+            # - censored metadata
+            # - copy/rename tracking
+            # The first is detected by peaking into the delta,
+            # the second is detected by abusing parent order
+            # in the revlog index as flag bit. This leaves files using
+            # the dummy encoding and non-standard meta attributes.
+            # The following check is a special case for the empty
+            # metadata block used if the raw file content starts with '\1\n'.
+            # Cases of arbitrary metadata flags are currently mishandled.
             if self.size() - 4 == fctx.size():
                 # size() can match:
                 # if file data starts with '\1\n', empty metadata block is
                 # prepended, which adds 4 bytes to filelog.size().
                 return self._filelog.cmp(self._filenode, fctx.data())
         if self.size() == fctx.size() or self.flags() == b'l':
             # size() matches: need to compare content
             # issue6456: Always compare symlinks because size can represent
             # encrypted string for EXT-4 encryption(fscrypt).
             return self._filelog.cmp(self._filenode, fctx.data())
 
         # size() differs
         return True
 
     def _adjustlinkrev(self, srcrev, inclusive=False, stoprev=None):
         """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
         :stoprev: an optional revision to stop the walk at. If no introduction
                   of this file content could be found before this floor
                   revision, the function will returns "None" and stops its
                   iteration.
         """
         repo = self._repo
         cl = repo.unfiltered().changelog
         mfl = repo.manifestlog
         # fetch the linkrev
         lkr = self.linkrev()
         if srcrev == lkr:
             return lkr
         # 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:
                 if stoprev is not None and a < stoprev:
                     return None
                 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 isintroducedafter(self, changelogrev):
         """True if a filectx has been introduced after a given floor revision"""
         if self.linkrev() >= changelogrev:
             return True
         introrev = self._introrev(stoprev=changelogrev)
         if introrev is None:
             return False
         return introrev >= changelogrev
 
     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.
         """
         return self._introrev()
 
     def _introrev(self, stoprev=None):
         """
         Same as `introrev` but, with an extra argument to limit changelog
         iteration range in some internal usecase.
 
         If `stoprev` is set, the `introrev` will not be searched past that
         `stoprev` revision and "None" might be returned. This is useful to
         limit the iteration range.
         """
         toprev = None
         attrs = vars(self)
         if '_changeid' in attrs:
             # We have a cached value already
             toprev = self._changeid
         elif '_changectx' in attrs:
             # We know which changelog entry we are coming from
             toprev = self._changectx.rev()
 
         if toprev is not None:
             return self._adjustlinkrev(toprev, inclusive=True, stoprev=stoprev)
         elif '_descendantrev' in attrs:
             introrev = self._adjustlinkrev(self._descendantrev, stoprev=stoprev)
             # be nice and cache the result of the computation
             if introrev is not None:
                 self._changeid = introrev
             return introrev
         else:
             return self.linkrev()
 
     def introfilectx(self):
         """Return filectx having identical contents, but pointing to the
         changeset revision where this filectx was introduced"""
         introrev = self.introrev()
         if self.rev() == introrev:
             return self
         return self.filectx(self.filenode(), changeid=introrev)
 
     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 != self._repo.nodeconstants.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, skiprevs=None, diffopts=None):
         """Returns a list of annotateline objects for each line in the file
 
         - line.fctx is the filectx of the node where that line was last changed
         - line.lineno is the line number at the first appearance in the managed
           file
         - line.text is the data on that line (including newline character)
         """
         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.introfilectx()
         if getattr(base, '_ancestrycontext', None) is None:
             # it is safe to use an unfiltered repository here because we are
             # walking ancestors only.
             cl = self._repo.unfiltered().changelog
             if base.rev() 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([base.rev()], inclusive=True)
             base._ancestrycontext = ac
 
         return dagop.annotate(
             base, parents, skiprevs=skiprevs, diffopts=diffopts
         )
 
     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
 
     def decodeddata(self):
         """Returns `data()` after running repository decoding filters.
 
         This is often equivalent to how the data would be expressed on disk.
         """
         return self._repo.wwritedata(self.path(), self.data())
 
 
 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 must be a revision number, if specified.
         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
         ), b"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 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 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.rawdata(self._filenode)
 
     def rawflags(self):
         """low-level revlog flags"""
         return self._filelog.flags(self._filerev)
 
     def data(self):
         try:
             return self._filelog.read(self._filenode)
         except error.CensoredNodeError:
             if self._repo.ui.config(b"censor", b"policy") == b"ignore":
                 return b""
             raise error.Abort(
                 _(b"censored node: %s") % short(self._filenode),
                 hint=_(b"set censor.policy to ignore errors"),
             )
 
     def size(self):
         return self._filelog.size(self._filerev)
 
     @propertycache
     def _copied(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 None
 
         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
         ]
 
 
 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=b"",
         user=None,
         date=None,
         extra=None,
         changes=None,
         branch=None,
     ):
         super(committablectx, self).__init__(repo)
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = dateutil.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = changes
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if branch is not None:
             self._extra[b'branch'] = encoding.fromlocal(branch)
         if not self._extra.get(b'branch'):
             self._extra[b'branch'] = b'default'
 
     def __bytes__(self):
         return bytes(self._parents[0]) + b"+"
 
     def hex(self):
         self._repo.nodeconstants.wdirhex
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     @propertycache
     def _status(self):
         return self._repo.status()
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         ui = self._repo.ui
         date = ui.configdate(b'devel', b'default-date')
         if date is None:
             date = dateutil.makedate()
         return date
 
     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
 
     filesmodified = modified
     filesadded = added
     filesremoved = removed
 
     def branch(self):
         return encoding.tolocal(self._extra[b'branch'])
 
     def closesbranch(self):
         return b'close' in self._extra
 
     def extra(self):
         return self._extra
 
     def isinmemory(self):
         return False
 
     def tags(self):
         return []
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.newcommitphase(self._repo.ui)
         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 b''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return b''
 
     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 ancestors(self):
         for p in self._parents:
             yield p
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]
         ):
             yield 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.
 
         """
 
     def dirty(self, missing=False, merge=True, branch=True):
         return False
 
 
 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=b"", user=None, date=None, extra=None, changes=None
     ):
         branch = None
         if not extra or b'branch' not in extra:
             try:
                 branch = repo.dirstate.branch()
             except UnicodeDecodeError:
                 raise error.Abort(_(b'branch name not in UTF-8!'))
         super(workingctx, self).__init__(
             repo, text, user, date, extra, changes, branch=branch
         )
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d.get_entry(f).tracked:
                 yield f
 
     def __contains__(self, key):
         return self._repo.dirstate.get_entry(key).tracked
 
     def hex(self):
         return self._repo.nodeconstants.wdirhex
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == self._repo.nodeconstants.nullid:
             p = p[:-1]
         # use unfiltered repo to delay/avoid loading obsmarkers
         unfi = self._repo.unfiltered()
         return [
             changectx(
                 self._repo, unfi.changelog.rev(n), n, maybe_filtered=False
             )
             for n in p
         ]
 
     def setparents(self, p1node, p2node=None):
         if p2node is None:
             p2node = self._repo.nodeconstants.nullid
         dirstate = self._repo.dirstate
         with dirstate.parentchange():
             copies = dirstate.setparents(p1node, p2node)
             pctx = self._repo[p1node]
             if copies:
                 # Adjust copy records, the dirstate cannot do it, it
                 # requires access to parents manifests. Preserve them
                 # only for entries added to first parent.
                 for f in copies:
                     if f not in pctx and copies[f] in pctx:
                         dirstate.copy(copies[f], f)
             if p2node == self._repo.nodeconstants.nullid:
                 for f, s in sorted(dirstate.copies().items()):
                     if f not in pctx and s not in pctx:
                         dirstate.copy(None, f)
 
     def _fileinfo(self, path):
         # populate __dict__['_manifest'] as workingctx has no _manifestdelta
         self._manifest
         return super(workingctx, self)._fileinfo(path)
 
     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 b''  # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     def flags(self, path):
         try:
             return self._flagfunc(path)
         except OSError:
             return b''
 
     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(missing=missing):
                 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=b""):
         with self._repo.wlock():
             ui, ds = self._repo.ui, self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             lstat = self._repo.wvfs.lstat
             for f in list:
                 # ds.pathto() returns an absolute file when this is invoked from
                 # the keyword extension.  That gets flagged as non-portable on
                 # Windows, since it contains the drive letter and colon.
                 scmutil.checkportable(ui, os.path.join(prefix, f))
                 try:
                     st = lstat(f)
                 except OSError:
                     ui.warn(_(b"%s does not exist!\n") % uipath(f))
                     rejected.append(f)
                     continue
                 limit = ui.configbytes(b'ui', b'large-file-limit')
                 if limit != 0 and st.st_size > limit:
                     ui.warn(
                         _(
                             b"%s: up to %d MB of RAM may be required "
                             b"to manage this file\n"
                             b"(use 'hg revert %s' to cancel the "
                             b"pending addition)\n"
                         )
                         % (f, 3 * st.st_size // 1000000, uipath(f))
                     )
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(
                         _(
                             b"%s not added: only files and symlinks "
                             b"supported currently\n"
                         )
                         % uipath(f)
                     )
                     rejected.append(f)
                 elif not ds.set_tracked(f):
                     ui.warn(_(b"%s already tracked!\n") % uipath(f))
             return rejected
 
     def forget(self, files, prefix=b""):
         with self._repo.wlock():
             ds = self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             for f in files:
                 if not ds.set_untracked(f):
                     self._repo.ui.warn(_(b"%s not tracked!\n") % uipath(f))
                     rejected.append(f)
             return rejected
 
     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(
                 _(b"%s does not exist!\n") % self._repo.dirstate.pathto(dest)
             )
             return
         if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
             self._repo.ui.warn(
                 _(b"copy failed: %s is not a file or a symbolic link\n")
                 % self._repo.dirstate.pathto(dest)
             )
         else:
             with self._repo.wlock():
                 ds = self._repo.dirstate
                 ds.set_tracked(dest)
                 ds.copy(source, dest)
 
     def match(
         self,
         pats=None,
         include=None,
         exclude=None,
         default=b'glob',
         listsubrepos=False,
         badfn=None,
         cwd=None,
     ):
         r = self._repo
         if not cwd:
             cwd = r.getcwd()
 
         # Only a case insensitive filesystem needs magic to translate user input
         # to actual case in the filesystem.
         icasefs = not util.fscasesensitive(r.root)
         return matchmod.match(
             r.root,
             cwd,
             pats,
             include,
             exclude,
             default,
             auditor=r.auditor,
             ctx=self,
             listsubrepos=listsubrepos,
             badfn=badfn,
             icasefs=icasefs,
         )
 
     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) == b'l':
                 d = self[f].data()
                 if (
                     d == b''
                     or len(d) >= 1024
                     or b'\n' in d
                     or stringutil.binary(d)
                 ):
                     self._repo.ui.debug(
                         b'ignoring suspect symlink placeholder "%s"\n' % f
                     )
                     continue
             sane.append(f)
         return sane
 
     def _checklookup(self, files, mtime_boundary):
         # check for any possibly clean files
         if not files:
             return [], [], [], []
 
         modified = []
         deleted = []
         clean = []
         fixup = []
         pctx = self._parents[0]
         # do a full compare of any files that might have changed
         for f in sorted(files):
             try:
                 # This will return True for a file that got replaced by a
                 # directory in the interim, but fixing that is pretty hard.
                 if (
                     f not in pctx
                     or self.flags(f) != pctx.flags(f)
                     or pctx[f].cmp(self[f])
                 ):
                     modified.append(f)
                 elif mtime_boundary is None:
                     clean.append(f)
                 else:
                     s = self[f].lstat()
                     mode = s.st_mode
                     size = s.st_size
                     file_mtime = timestamp.reliable_mtime_of(s, mtime_boundary)
                     if file_mtime is not None:
                         cache_info = (mode, size, file_mtime)
                         fixup.append((f, cache_info))
                     else:
                         clean.append(f)
             except (IOError, OSError):
                 # A file become inaccessible in between? Mark it as deleted,
                 # matching dirstate behavior (issue5584).
                 # The dirstate has more complex behavior around whether a
                 # missing file matches a directory, etc, but we don't need to
                 # bother with that: if f has made it to this point, we're sure
                 # it's in the dirstate.
                 deleted.append(f)
 
         return modified, deleted, clean, fixup
 
     def _poststatusfixup(self, status, fixup):
         """update dirstate for files that are actually clean"""
         poststatus = self._repo.postdsstatus()
         if fixup or poststatus or self._repo.dirstate._dirty:
             try:
                 oldid = self._repo.dirstate.identity()
 
                 # 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):
                     dirstate = self._repo.dirstate
                     if dirstate.identity() == oldid:
                         if fixup:
                             if dirstate.pendingparentchange():
                                 normal = lambda f, pfd: dirstate.update_file(
                                     f, p1_tracked=True, wc_tracked=True
                                 )
                             else:
                                 normal = dirstate.set_clean
                             for f, pdf in fixup:
                                 normal(f, pdf)
                             # write changes out explicitly, because nesting
                             # wlock at runtime may prevent 'wlock.release()'
                             # after this block from doing so for subsequent
                             # changing files
                             tr = self._repo.currenttransaction()
                             self._repo.dirstate.write(tr)
 
                         if poststatus:
                             for ps in poststatus:
                                 ps(self, status)
                     else:
                         # in this case, writing changes out breaks
                         # consistency, because .hg/dirstate was
                         # already changed simultaneously after last
                         # caching (see also issue5584 for detail)
                         self._repo.ui.debug(
                             b'skip updating dirstate: identity mismatch\n'
                         )
             except error.LockError:
                 pass
             finally:
                 # Even if the wlock couldn't be grabbed, clear out the list.
                 self._repo.clearpostdsstatus()
 
     def _dirstatestatus(self, match, ignored=False, clean=False, unknown=False):
         '''Gets the status from the dirstate -- internal use only.'''
         subrepos = []
         if b'.hgsub' in self:
             subrepos = sorted(self.substate)
         cmp, s, mtime_boundary = self._repo.dirstate.status(
             match, subrepos, ignored=ignored, clean=clean, unknown=unknown
         )
 
         # check for any possibly clean files
         fixup = []
         if cmp:
             modified2, deleted2, clean_set, fixup = self._checklookup(
                 cmp, mtime_boundary
             )
             s.modified.extend(modified2)
             s.deleted.extend(deleted2)
 
             if clean_set and clean:
                 s.clean.extend(clean_set)
             if fixup and clean:
                 s.clean.extend((f for f, _ in fixup))
 
         self._poststatusfixup(s, 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
 
     @propertycache
     def _copies(self):
         p1copies = {}
         p2copies = {}
         parents = self._repo.dirstate.parents()
         p1manifest = self._repo[parents[0]].manifest()
         p2manifest = self._repo[parents[1]].manifest()
         changedset = set(self.added()) | set(self.modified())
         narrowmatch = self._repo.narrowmatch()
         for dst, src in self._repo.dirstate.copies().items():
             if dst not in changedset or not narrowmatch(dst):
                 continue
             if src in p1manifest:
                 p1copies[dst] = src
             elif src in p2manifest:
                 p2copies[dst] = src
         return p1copies, p2copies
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the values in self._status
 
         This reuse the file nodeid from parent, but we use special node
         identifiers for added and modified files. This is used by manifests
         merge to see that files are different and by update logic to avoid
         deleting newly added files.
         """
         return self._buildstatusmanifest(self._status)
 
     def _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results."""
         parents = self.parents()
 
         man = parents[0].manifest().copy()
 
         ff = self._flagfunc
         for i, l in (
             (self._repo.nodeconstants.addednodeid, status.added),
             (self._repo.nodeconstants.modifiednodeid, status.modified),
         ):
             for f in l:
                 man[f] = i
                 try:
                     man.setflag(f, ff(f))
                 except OSError:
                     pass
 
         for f in status.deleted + status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     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[b'.']:
             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.
         """
         if other != self._repo[b'.']:
 
             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(
                         b'%s: %s\n' % (self._repo.dirstate.pathto(f), msg)
                     )
 
             match.bad = bad
         return match
 
     def walk(self, match):
         '''Generates matching file names.'''
         return sorted(
             self._repo.dirstate.walk(
                 self._repo.narrowmatch(match),
                 subrepos=sorted(self.substate),
                 unknown=True,
                 ignored=False,
             )
         )
 
     def matches(self, match):
         match = self._repo.narrowmatch(match)
         ds = self._repo.dirstate
         return sorted(f for f in ds.matches(match) if ds.get_entry(f).tracked)
 
     def markcommitted(self, node):
         with self._repo.dirstate.parentchange():
             for f in self.modified() + self.added():
                 self._repo.dirstate.update_file(
                     f, p1_tracked=True, wc_tracked=True
                 )
             for f in self.removed():
                 self._repo.dirstate.update_file(
                     f, p1_tracked=False, wc_tracked=False
                 )
             self._repo.dirstate.setparents(node)
             self._repo._quick_access_changeid_invalidate()
 
             sparse.aftercommit(self._repo, node)
 
         # 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())
 
     def mergestate(self, clean=False):
         if clean:
             return mergestatemod.mergestate.clean(self._repo)
         return mergestatemod.mergestate.read(self._repo)
 
 
 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
 
     __bool__ = __nonzero__
 
     def linkrev(self):
         # linked to self._changectx no matter if file is modified or not
         return self.rev()
 
     def renamed(self):
         path = self.copysource()
         if not path:
             return None
         return (
             path,
             self._changectx._parents[0]._manifest.get(
                 path, self._repo.nodeconstants.nullid
             ),
         )
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
 
         def filenode(ctx, path):
             return ctx._manifest.get(path, self._repo.nodeconstants.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 != self._repo.nodeconstants.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 copysource(self):
         return self._repo.dirstate.copied(self._path)
 
     def size(self):
         return self._repo.wvfs.lstat(self._path).st_size
 
     def lstat(self):
         return self._repo.wvfs.lstat(self._path)
 
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (self._repo.wvfs.lstat(self._path)[stat.ST_MTIME], tz)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
     def exists(self):
         return self._repo.wvfs.exists(self._path)
 
     def lexists(self):
         return self._repo.wvfs.lexists(self._path)
 
     def audit(self):
         return self._repo.wvfs.audit(self._path)
 
     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"""
         rmdir = self._repo.ui.configbool(b'experimental', b'removeemptydirs')
         self._repo.wvfs.unlinkpath(
             self._path, ignoremissing=ignoremissing, rmdir=rmdir
         )
 
     def write(self, data, flags, backgroundclose=False, **kwargs):
         """wraps repo.wwrite"""
         return self._repo.wwrite(
             self._path, data, flags, backgroundclose=backgroundclose, **kwargs
         )
 
     def markcopied(self, src):
         """marks this file a copy of `src`"""
         self._repo.dirstate.copy(src, self._path)
 
     def clearunknown(self):
         """Removes conflicting items in the working directory so that
         ``write()`` can be called successfully.
         """
         wvfs = self._repo.wvfs
         f = self._path
         wvfs.audit(f)
         if self._repo.ui.configbool(
             b'experimental', b'merge.checkpathconflicts'
         ):
             # remove files under the directory as they should already be
             # warned and backed up
             if wvfs.isdir(f) and not wvfs.islink(f):
                 wvfs.rmtree(f, forcibly=True)
             for p in reversed(list(pathutil.finddirs(f))):
                 if wvfs.isfileorlink(p):
                     wvfs.unlink(p)
                     break
         else:
             # don't remove files if path conflicts are not processed
             if wvfs.isdir(f) and not wvfs.islink(f):
                 wvfs.removedirs(f)
 
     def setflags(self, l, x):
         self._repo.wvfs.setflags(self._path, l, x)
 
 
 class overlayworkingctx(committablectx):
     """Wraps another mutable context with a write-back cache that can be
     converted into a commit context.
 
     self._cache[path] maps to a dict with keys: {
         'exists': bool?
         'date': date?
         'data': str?
         'flags': str?
         'copied': str? (path or None)
     }
     If `exists` is True, `flags` must be non-None and 'date' is non-None. If it
     is `False`, the file was deleted.
     """
 
     def __init__(self, repo):
         super(overlayworkingctx, self).__init__(repo)
         self.clean()
 
     def setbase(self, wrappedctx):
         self._wrappedctx = wrappedctx
         self._parents = [wrappedctx]
         # Drop old manifest cache as it is now out of date.
         # This is necessary when, e.g., rebasing several nodes with one
         # ``overlayworkingctx`` (e.g. with --collapse).
         util.clearcachedproperty(self, b'_manifest')
 
     def setparents(self, p1node, p2node=None):
         if p2node is None:
             p2node = self._repo.nodeconstants.nullid
         assert p1node == self._wrappedctx.node()
         self._parents = [self._wrappedctx, self._repo.unfiltered()[p2node]]
 
     def data(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 if self._cache[path][b'data'] is not None:
                     return self._cache[path][b'data']
                 else:
                     # Must fallback here, too, because we only set flags.
                     return self._wrappedctx[path].data()
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % path
                 )
         else:
             return self._wrappedctx[path].data()
 
     @propertycache
     def _manifest(self):
         parents = self.parents()
         man = parents[0].manifest().copy()
 
         flag = self._flagfunc
         for path in self.added():
             man[path] = self._repo.nodeconstants.addednodeid
             man.setflag(path, flag(path))
         for path in self.modified():
             man[path] = self._repo.nodeconstants.modifiednodeid
             man.setflag(path, flag(path))
         for path in self.removed():
             del man[path]
         return man
 
     @propertycache
     def _flagfunc(self):
         def f(path):
             return self._cache[path][b'flags']
 
         return f
 
     def files(self):
         return sorted(self.added() + self.modified() + self.removed())
 
     def modified(self):
         return [
             f
             for f in self._cache.keys()
             if self._cache[f][b'exists'] and self._existsinparent(f)
         ]
 
     def added(self):
         return [
             f
             for f in self._cache.keys()
             if self._cache[f][b'exists'] and not self._existsinparent(f)
         ]
 
     def removed(self):
         return [
             f
             for f in self._cache.keys()
             if not self._cache[f][b'exists'] and self._existsinparent(f)
         ]
 
     def p1copies(self):
         copies = {}
         narrowmatch = self._repo.narrowmatch()
         for f in self._cache.keys():
             if not narrowmatch(f):
                 continue
             copies.pop(f, None)  # delete if it exists
             source = self._cache[f][b'copied']
             if source:
                 copies[f] = source
         return copies
 
     def p2copies(self):
         copies = {}
         narrowmatch = self._repo.narrowmatch()
         for f in self._cache.keys():
             if not narrowmatch(f):
                 continue
             copies.pop(f, None)  # delete if it exists
             source = self._cache[f][b'copied']
             if source:
                 copies[f] = source
         return copies
 
     def isinmemory(self):
         return True
 
     def filedate(self, path):
         if self.isdirty(path):
             return self._cache[path][b'date']
         else:
             return self._wrappedctx[path].date()
 
     def markcopied(self, path, origin):
         self._markdirty(
             path,
             exists=True,
             date=self.filedate(path),
             flags=self.flags(path),
             copied=origin,
         )
 
     def copydata(self, path):
         if self.isdirty(path):
             return self._cache[path][b'copied']
         else:
             return None
 
     def flags(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 return self._cache[path][b'flags']
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % path
                 )
         else:
             return self._wrappedctx[path].flags()
 
     def __contains__(self, key):
         if key in self._cache:
             return self._cache[key][b'exists']
         return key in self.p1()
 
     def _existsinparent(self, path):
         try:
             # ``commitctx` raises a ``ManifestLookupError`` if a path does not
             # exist, unlike ``workingctx``, which returns a ``workingfilectx``
             # with an ``exists()`` function.
             self._wrappedctx[path]
             return True
         except error.ManifestLookupError:
             return False
 
     def _auditconflicts(self, path):
         """Replicates conflict checks done by wvfs.write().
 
         Since we never write to the filesystem and never call `applyupdates` in
         IMM, we'll never check that a path is actually writable -- e.g., because
         it adds `a/foo`, but `a` is actually a file in the other commit.
         """
 
         def fail(path, component):
             # p1() is the base and we're receiving "writes" for p2()'s
             # files.
             if b'l' in self.p1()[component].flags():
                 raise error.Abort(
                     b"error: %s conflicts with symlink %s "
                     b"in %d." % (path, component, self.p1().rev())
                 )
             else:
                 raise error.Abort(
                     b"error: '%s' conflicts with file '%s' in "
                     b"%d." % (path, component, self.p1().rev())
                 )
 
         # Test that each new directory to be created to write this path from p2
         # is not a file in p1.
         components = path.split(b'/')
         for i in pycompat.xrange(len(components)):
             component = b"/".join(components[0:i])
             if component in self:
                 fail(path, component)
 
         # Test the other direction -- that this path from p2 isn't a directory
         # in p1 (test that p1 doesn't have any paths matching `path/*`).
         match = self.match([path], default=b'path')
         mfiles = list(self.p1().manifest().walk(match))
         if len(mfiles) > 0:
             if len(mfiles) == 1 and mfiles[0] == path:
                 return
             # omit the files which are deleted in current IMM wctx
             mfiles = [m for m in mfiles if m in self]
             if not mfiles:
                 return
             raise error.Abort(
                 b"error: file '%s' cannot be written because "
                 b" '%s/' is a directory in %s (containing %d "
                 b"entries: %s)"
                 % (path, path, self.p1(), len(mfiles), b', '.join(mfiles))
             )
 
     def write(self, path, data, flags=b'', **kwargs):
         if data is None:
             raise error.ProgrammingError(b"data must be non-None")
         self._auditconflicts(path)
         self._markdirty(
             path, exists=True, data=data, date=dateutil.makedate(), flags=flags
         )
 
     def setflags(self, path, l, x):
         flag = b''
         if l:
             flag = b'l'
         elif x:
             flag = b'x'
         self._markdirty(path, exists=True, date=dateutil.makedate(), flags=flag)
 
     def remove(self, path):
         self._markdirty(path, exists=False)
 
     def exists(self, path):
         """exists behaves like `lexists`, but needs to follow symlinks and
         return False if they are broken.
         """
         if self.isdirty(path):
             # If this path exists and is a symlink, "follow" it by calling
             # exists on the destination path.
             if (
                 self._cache[path][b'exists']
                 and b'l' in self._cache[path][b'flags']
             ):
                 return self.exists(self._cache[path][b'data'].strip())
             else:
                 return self._cache[path][b'exists']
 
         return self._existsinparent(path)
 
     def lexists(self, path):
         """lexists returns True if the path exists"""
         if self.isdirty(path):
             return self._cache[path][b'exists']
 
         return self._existsinparent(path)
 
     def size(self, path):
         if self.isdirty(path):
             if self._cache[path][b'exists']:
                 return len(self._cache[path][b'data'])
             else:
                 raise error.ProgrammingError(
                     b"No such file or directory: %s" % path
                 )
         return self._wrappedctx[path].size()
 
     def tomemctx(
         self,
         text,
         branch=None,
         extra=None,
         date=None,
         parents=None,
         user=None,
         editor=None,
     ):
         """Converts this ``overlayworkingctx`` into a ``memctx`` ready to be
         committed.
 
         ``text`` is the commit message.
         ``parents`` (optional) are rev numbers.
         """
         # Default parents to the wrapped context if not passed.
         if parents is None:
             parents = self.parents()
             if len(parents) == 1:
                 parents = (parents[0], None)
 
         # ``parents`` is passed as rev numbers; convert to ``commitctxs``.
         if parents[1] is None:
             parents = (self._repo[parents[0]], None)
         else:
             parents = (self._repo[parents[0]], self._repo[parents[1]])
 
         files = self.files()
 
         def getfile(repo, memctx, path):
             if self._cache[path][b'exists']:
                 return memfilectx(
                     repo,
                     memctx,
                     path,
                     self._cache[path][b'data'],
                     b'l' in self._cache[path][b'flags'],
                     b'x' in self._cache[path][b'flags'],
                     self._cache[path][b'copied'],
                 )
             else:
                 # Returning None, but including the path in `files`, is
                 # necessary for memctx to register a deletion.
                 return None
 
         if branch is None:
             branch = self._wrappedctx.branch()
 
         return memctx(
             self._repo,
             parents,
             text,
             files,
             getfile,
             date=date,
             extra=extra,
             user=user,
             branch=branch,
             editor=editor,
         )
 
     def tomemctx_for_amend(self, precursor):
         extra = precursor.extra().copy()
         extra[b'amend_source'] = precursor.hex()
         return self.tomemctx(
             text=precursor.description(),
             branch=precursor.branch(),
             extra=extra,
             date=precursor.date(),
             user=precursor.user(),
         )
 
     def isdirty(self, path):
         return path in self._cache
 
     def clean(self):
         self._mergestate = None
         self._cache = {}
 
     def _compact(self):
         """Removes keys from the cache that are actually clean, by comparing
         them with the underlying context.
 
         This can occur during the merge process, e.g. by passing --tool :local
         to resolve a conflict.
         """
         keys = []
         # This won't be perfect, but can help performance significantly when
         # using things like remotefilelog.
         scmutil.prefetchfiles(
             self.repo(),
             [
                 (
                     self.p1().rev(),
                     scmutil.matchfiles(self.repo(), self._cache.keys()),
                 )
             ],
         )
 
         for path in self._cache.keys():
             cache = self._cache[path]
             try:
                 underlying = self._wrappedctx[path]
                 if (
                     underlying.data() == cache[b'data']
                     and underlying.flags() == cache[b'flags']
                 ):
                     keys.append(path)
             except error.ManifestLookupError:
                 # Path not in the underlying manifest (created).
                 continue
 
         for path in keys:
             del self._cache[path]
         return keys
 
     def _markdirty(
         self, path, exists, data=None, date=None, flags=b'', copied=None
     ):
         # data not provided, let's see if we already have some; if not, let's
         # grab it from our underlying context, so that we always have data if
         # the file is marked as existing.
         if exists and data is None:
             oldentry = self._cache.get(path) or {}
             data = oldentry.get(b'data')
             if data is None:
                 data = self._wrappedctx[path].data()
 
         self._cache[path] = {
             b'exists': exists,
             b'data': data,
             b'date': date,
             b'flags': flags,
             b'copied': copied,
         }
         util.clearcachedproperty(self, b'_manifest')
 
     def filectx(self, path, filelog=None):
         return overlayworkingfilectx(
             self._repo, path, parent=self, filelog=filelog
         )
 
     def mergestate(self, clean=False):
         if clean or self._mergestate is None:
             self._mergestate = mergestatemod.memmergestate(self._repo)
         return self._mergestate
 
 
 class overlayworkingfilectx(committablefilectx):
     """Wrap a ``workingfilectx`` but intercepts all writes into an in-memory
     cache, which can be flushed through later by calling ``flush()``."""
 
     def __init__(self, repo, path, filelog=None, parent=None):
         super(overlayworkingfilectx, self).__init__(repo, path, filelog, parent)
         self._repo = repo
         self._parent = parent
         self._path = path
 
     def cmp(self, fctx):
         return self.data() != fctx.data()
 
     def changectx(self):
         return self._parent
 
     def data(self):
         return self._parent.data(self._path)
 
     def date(self):
         return self._parent.filedate(self._path)
 
     def exists(self):
         return self.lexists()
 
     def lexists(self):
         return self._parent.exists(self._path)
 
     def copysource(self):
         return self._parent.copydata(self._path)
 
     def size(self):
         return self._parent.size(self._path)
 
     def markcopied(self, origin):
         self._parent.markcopied(self._path, origin)
 
     def audit(self):
         pass
 
     def flags(self):
         return self._parent.flags(self._path)
 
     def setflags(self, islink, isexec):
         return self._parent.setflags(self._path, islink, isexec)
 
     def write(self, data, flags, backgroundclose=False, **kwargs):
         return self._parent.write(self._path, data, flags, **kwargs)
 
     def remove(self, ignoremissing=False):
         return self._parent.remove(self._path)
 
     def clearunknown(self):
         pass
 
 
 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=b"", user=None, date=None, extra=None
     ):
         super(workingcommitctx, self).__init__(
             repo, text, user, date, extra, changes
         )
 
     def _dirstatestatus(self, match, 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.
         """
         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
 
 
 def memfilefromctx(ctx):
     """Given a context return a memfilectx for ctx[path]
 
     This is a convenience method for building a memctx based on another
     context.
     """
 
     def getfilectx(repo, memctx, path):
         fctx = ctx[path]
         copysource = fctx.copysource()
         return memfilectx(
             repo,
             memctx,
             path,
             fctx.data(),
             islink=fctx.islink(),
             isexec=fctx.isexec(),
             copysource=copysource,
         )
 
     return getfilectx
 
 
 def memfilefrompatch(patchstore):
     """Given a patch (e.g. patchstore object) return a memfilectx
 
     This is a convenience method for building a memctx based on a patchstore.
     """
 
     def getfilectx(repo, memctx, path):
         data, mode, copysource = patchstore.getfile(path)
         if data is None:
             return None
         islink, isexec = mode
         return memfilectx(
             repo,
             memctx,
             path,
             data,
             islink=islink,
             isexec=isexec,
             copysource=copysource,
         )
 
     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 return None for recent
     Mercurial. 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 dateutil.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,
         branch=None,
         editor=None,
     ):
         super(memctx, self).__init__(
             repo, text, user, date, extra, branch=branch
         )
         self._rev = None
         self._node = None
         parents = [(p or self._repo.nodeconstants.nullid) for p in parents]
         p1, p2 = parents
         self._parents = [self._repo[p] for p in (p1, p2)]
         files = sorted(set(files))
         self._files = files
         self.substate = {}
 
         if isinstance(filectxfn, patch.filestore):
             filectxfn = memfilefrompatch(filectxfn)
         elif not callable(filectxfn):
             # if store is not callable, wrap it in a function
             filectxfn = memfilefromctx(filectxfn)
 
         # memoizing increases performance for e.g. vcs convert scenarios.
         self._filectxfn = makecachingfilectxfn(filectxfn)
 
         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:
             man[f] = self._repo.nodeconstants.modifiednodeid
 
         for f in self._status.added:
             man[f] = self._repo.nodeconstants.addednodeid
 
         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.rev() != nullrev:
             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, [], [], [], [])
 
     def parents(self):
         if self._parents[1].rev() == nullrev:
             return [self._parents[0]]
         return self._parents
 
 
 class memfilectx(committablefilectx):
     """memfilectx represents an in-memory file to commit.
 
     See memctx and committablefilectx for more details.
     """
 
     def __init__(
         self,
         repo,
         changectx,
         path,
         data,
         islink=False,
         isexec=False,
         copysource=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, changectx)
         self._data = data
         if islink:
             self._flags = b'l'
         elif isexec:
             self._flags = b'x'
         else:
             self._flags = b''
         self._copysource = copysource
 
     def copysource(self):
         return self._copysource
 
     def cmp(self, fctx):
         return self.data() != fctx.data()
 
     def data(self):
         return self._data
 
     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, **kwargs):
         """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
     dateutil.parsedate() and defaults to current date, extra is a dictionary of
     metadata or is left empty.
     """
 
     def __init__(
         self,
         repo,
         originalctx,
         parents=None,
         text=None,
         user=None,
         date=None,
         extra=None,
         editor=None,
     ):
         if text is None:
             text = originalctx.description()
         super(metadataonlyctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         self._originalctx = originalctx
         self._manifestnode = originalctx.manifestnode()
         if parents is None:
             parents = originalctx.parents()
         else:
             parents = [repo[p] for p in parents if p is not None]
         parents = parents[:]
         while len(parents) < 2:
             parents.append(repo[nullrev])
         p1, p2 = self._parents = parents
 
         # sanity check to ensure that the reused manifest parents are
         # manifests of our commit parents
         mp1, mp2 = self.manifestctx().parents
         if p1 != self._repo.nodeconstants.nullid and p1.manifestnode() != mp1:
             raise RuntimeError(
                 r"can't reuse the manifest: its p1 "
                 r"doesn't match the new ctx p1"
             )
         if p2 != self._repo.nodeconstants.nullid and p2.manifestnode() != mp2:
             raise RuntimeError(
                 r"can't reuse the manifest: "
                 r"its p2 doesn't match the new ctx p2"
             )
 
         self._files = originalctx.files()
         self.substate = {}
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def manifestnode(self):
         return self._manifestnode
 
     @property
     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.rev() != nullrev:
             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 f in self:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 
 class arbitraryfilectx:
     """Allows you to use filectx-like functions on a file in an arbitrary
     location on disk, possibly not in the working directory.
     """
 
     def __init__(self, path, repo=None):
         # Repo is optional because contrib/simplemerge uses this class.
         self._repo = repo
         self._path = path
 
     def cmp(self, fctx):
         # filecmp follows symlinks whereas `cmp` should not, so skip the fast
         # path if either side is a symlink.
         symlinks = b'l' in self.flags() or b'l' in fctx.flags()
         if not symlinks and isinstance(fctx, workingfilectx) and self._repo:
             # Add a fast-path for merge if both sides are disk-backed.
             # Note that filecmp uses the opposite return values (True if same)
             # from our cmp functions (True if different).
             return not filecmp.cmp(self.path(), self._repo.wjoin(fctx.path()))
         return self.data() != fctx.data()
 
     def path(self):
         return self._path
 
     def flags(self):
         return b''
 
     def data(self):
         return util.readfile(self._path)
 
     def decodeddata(self):
         return util.readfile(self._path)
 
     def remove(self):
         util.unlink(self._path)
 
     def write(self, data, flags, **kwargs):
         assert not flags
         util.writefile(self._path, data)

mercurial/filelog.py

@@ -1,293 +1,295 b''
 # filelog.py - file history class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 from .i18n import _
 from .node import nullrev
 from . import (
     error,
     revlog,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .utils import storageutil
 from .revlogutils import (
     constants as revlog_constants,
     rewrite,
 )
 
 
 @interfaceutil.implementer(repository.ifilestorage)
 class filelog:
     def __init__(self, opener, path):
         self._revlog = revlog.revlog(
             opener,
             # XXX should use the unencoded path
             target=(revlog_constants.KIND_FILELOG, path),
             radix=b'/'.join((b'data', path)),
             censorable=True,
+            canonical_parent_order=False,  # see comment in revlog.py
         )
         # Full name of the user visible file, relative to the repository root.
         # Used by LFS.
         self._revlog.filename = path
         self.nullid = self._revlog.nullid
         opts = opener.options
         self._fix_issue6528 = opts.get(b'issue6528.fix-incoming', True)
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def hasnode(self, node):
         if node in (self.nullid, nullrev):
             return False
 
         try:
             self._revlog.rev(node)
             return True
         except (TypeError, ValueError, IndexError, error.LookupError):
             return False
 
     def revs(self, start=0, stop=None):
         return self._revlog.revs(start=start, stop=stop)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, node):
         return storageutil.fileidlookup(
             self._revlog, node, self._revlog.display_id
         )
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def commonancestorsheads(self, node1, node2):
         return self._revlog.commonancestorsheads(node1, node2)
 
     # Used by dagop.blockdescendants().
     def descendants(self, revs):
         return self._revlog.descendants(revs)
 
     def heads(self, start=None, stop=None):
         return self._revlog.heads(start, stop)
 
     # Used by hgweb, children extension.
     def children(self, node):
         return self._revlog.children(node)
 
     def iscensored(self, rev):
         return self._revlog.iscensored(rev)
 
     def revision(self, node, _df=None):
         return self._revlog.revision(node, _df=_df)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
             sidedata_helpers=sidedata_helpers,
         )
 
     def addrevision(
         self,
         revisiondata,
         transaction,
         linkrev,
         p1,
         p2,
         node=None,
         flags=revlog.REVIDX_DEFAULT_FLAGS,
         cachedelta=None,
     ):
         return self._revlog.addrevision(
             revisiondata,
             transaction,
             linkrev,
             p1,
             p2,
             node=node,
             flags=flags,
             cachedelta=cachedelta,
         )
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         maybemissingparents=False,
     ):
         if maybemissingparents:
             raise error.Abort(
                 _(
                     b'revlog storage does not support missing '
                     b'parents write mode'
                 )
             )
 
         with self._revlog._writing(transaction):
 
             if self._fix_issue6528:
                 deltas = rewrite.filter_delta_issue6528(self._revlog, deltas)
 
             return self._revlog.addgroup(
                 deltas,
                 linkmapper,
                 transaction,
                 addrevisioncb=addrevisioncb,
                 duplicaterevisioncb=duplicaterevisioncb,
             )
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def censorrevision(self, tr, node, tombstone=b''):
         return self._revlog.censorrevision(tr, node, tombstone=tombstone)
 
     def files(self):
         return self._revlog.files()
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith(b'\1\n'):
             text = storageutil.packmeta(meta, text)
         rev = self.addrevision(text, transaction, link, p1, p2)
         return self.node(rev)
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
         if self.iscensored(rev):
             return 0
 
         # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
+        # XXX See also basefilectx.cmp.
         return self._revlog.size(rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         return not storageutil.filedataequivalent(self, node, text)
 
     def verifyintegrity(self, state):
         return self._revlog.verifyintegrity(state)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     # Used by repo upgrade.
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, filelog):
             raise error.ProgrammingError(b'expected filelog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
 
 class narrowfilelog(filelog):
     """Filelog variation to be used with narrow stores."""
 
     def __init__(self, opener, path, narrowmatch):
         super(narrowfilelog, self).__init__(opener, path)
         self._narrowmatch = narrowmatch
 
     def renamed(self, node):
         res = super(narrowfilelog, self).renamed(node)
 
         # Renames that come from outside the narrowspec are problematic
         # because we may lack the base text for the rename. This can result
         # in code attempting to walk the ancestry or compute a diff
         # encountering a missing revision. We address this by silently
         # removing rename metadata if the source file is outside the
         # narrow spec.
         #
         # A better solution would be to see if the base revision is available,
         # rather than assuming it isn't.
         #
         # An even better solution would be to teach all consumers of rename
         # metadata that the base revision may not be available.
         #
         # TODO consider better ways of doing this.
         if res and not self._narrowmatch(res[0]):
             return None
 
         return res
 
     def size(self, rev):
         # Because we have a custom renamed() that may lie, we need to call
         # the base renamed() to report accurate results.
         node = self.node(rev)
         if super(narrowfilelog, self).renamed(node):
             return len(self.read(node))
         else:
             return super(narrowfilelog, self).size(rev)
 
     def cmp(self, node, text):
         # We don't call `super` because narrow parents can be buggy in case of a
         # ambiguous dirstate. Always take the slow path until there is a better
         # fix, see issue6150.
 
         # Censored files compare against the empty file.
         if self.iscensored(self.rev(node)):
             return text != b''
 
         return self.read(node) != text

mercurial/revlog.py

@@ -1,3307 +1,3322 b''
 # revlog.py - storage back-end for mercurial
 # coding: utf8
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 
 import binascii
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
     wdirrev,
 )
 from .i18n import _
 from .pycompat import getattr
 from .revlogutils.constants import (
     ALL_KINDS,
     CHANGELOGV2,
     COMP_MODE_DEFAULT,
     COMP_MODE_INLINE,
     COMP_MODE_PLAIN,
     ENTRY_RANK,
     FEATURES_BY_VERSION,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     KIND_CHANGELOG,
     RANK_UNKNOWN,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
     SUPPORTED_FLAGS,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_HASCOPIESINFO,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
 )
 from .thirdparty import attr
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     revlogutils,
     templatefilters,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     docket as docketutil,
     flagutil,
     nodemap as nodemaputil,
     randomaccessfile,
     revlogv0,
     rewrite,
     sidedata as sidedatautil,
 )
 from .utils import (
     storageutil,
     stringutil,
 )
 
 # blanked usage of all the name to prevent pyflakes constraints
 # We need these name available in the module for extensions.
 
 REVLOGV0
 REVLOGV1
 REVLOGV2
 CHANGELOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_HASCOPIESINFO
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod('parsers')
 rustancestor = policy.importrust('ancestor')
 rustdagop = policy.importrust('dagop')
 rustrevlog = policy.importrust('revlog')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 
 def _verify_revision(rl, skipflags, state, node):
     """Verify the integrity of the given revlog ``node`` while providing a hook
     point for extensions to influence the operation."""
     if skipflags:
         state[b'skipread'].add(node)
     else:
         # Side-effect: read content and verify hash.
         rl.revision(node)
 
 
 # True if a fast implementation for persistent-nodemap is available
 #
 # We also consider we have a "fast" implementation in "pure" python because
 # people using pure don't really have performance consideration (and a
 # wheelbarrow of other slowness source)
 HAS_FAST_PERSISTENT_NODEMAP = rustrevlog is not None or util.safehasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta:
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     sidedata = attr.ib()
     protocol_flags = attr.ib()
     linknode = attr.ib(default=None)
 
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class revlogproblem:
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 
 def parse_index_v1(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline)
     return index, cache
 
 
 def parse_index_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, format=REVLOGV2)
     return index, cache
 
 
 def parse_index_cl_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, format=CHANGELOGV2)
     return index, cache
 
 
 if util.safehasattr(parsers, 'parse_index_devel_nodemap'):
 
     def parse_index_v1_nodemap(data, inline):
         index, cache = parsers.parse_index_devel_nodemap(data, inline)
         return index, cache
 
 
 else:
     parse_index_v1_nodemap = None
 
 
 def parse_index_v1_mixed(data, inline):
     index, cache = parse_index_v1(data, inline)
     return rustrevlog.MixedIndex(index), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 FILE_TOO_SHORT_MSG = _(
     b'cannot read from revlog %s;'
     b'  expected %d bytes from offset %d, data size is %d'
 )
 
 
 class revlog:
     """
     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.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
 
     `concurrencychecker` is an optional function that receives 3 arguments: a
     file handle, a filename, and an expected position. It should check whether
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
 
     See mercurial/revlogutils/contants.py for details about the content of an
     index entry.
     """
 
     _flagserrorclass = error.RevlogError
 
     def __init__(
         self,
         opener,
         target,
         radix,
         postfix=None,  # only exist for `tmpcensored` now
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
         trypending=False,
+        canonical_parent_order=True,
     ):
         """
         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.
 
         `target`: a (KIND, ID) tuple that identify the content stored in
         this revlog. It help the rest of the code to understand what the revlog
         is about without having to resort to heuristic and index filename
         analysis. Note: that this must be reliably be set by normal code, but
         that test, debug, or performance measurement code might not set this to
         accurate value.
         """
         self.upperboundcomp = upperboundcomp
 
         self.radix = radix
 
         self._docket_file = None
         self._indexfile = None
         self._datafile = None
         self._sidedatafile = None
         self._nodemap_file = None
         self.postfix = postfix
         self._trypending = trypending
         self.opener = opener
         if persistentnodemap:
             self._nodemap_file = nodemaputil.get_nodemap_file(self)
 
         assert target[0] in ALL_KINDS
         assert len(target) == 2
         self.target = target
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._mmaplargeindex = mmaplargeindex
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = 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, b'')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = None
         self._docket = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._compengine = b'zlib'
         self._compengineopts = {}
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self.hassidedata = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
 
         # 3-tuple of file handles being used for active writing.
         self._writinghandles = None
         # prevent nesting of addgroup
         self._adding_group = None
 
         self._loadindex()
 
         self._concurrencychecker = concurrencychecker
 
+        # parent order is supposed to be semantically irrelevant, so we
+        # normally resort parents to ensure that the first parent is non-null,
+        # if there is a non-null parent at all.
+        # filelog abuses the parent order as flag to mark some instances of
+        # meta-encoded files, so allow it to disable this behavior.
+        self.canonical_parent_order = canonical_parent_order
+
     def _init_opts(self):
         """process options (from above/config) to setup associated default revlog mode
 
         These values might be affected when actually reading on disk information.
 
         The relevant values are returned for use in _loadindex().
 
         * newversionflags:
             version header to use if we need to create a new revlog
 
         * mmapindexthreshold:
             minimal index size for start to use mmap
 
         * force_nodemap:
             force the usage of a "development" version of the nodemap code
         """
         mmapindexthreshold = None
         opts = self.opener.options
 
         if b'changelogv2' in opts and self.revlog_kind == KIND_CHANGELOG:
             new_header = CHANGELOGV2
         elif b'revlogv2' in opts:
             new_header = REVLOGV2
         elif b'revlogv1' in opts:
             new_header = REVLOGV1 | FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 new_header |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             new_header = REVLOGV0
         else:
             new_header = REVLOG_DEFAULT_VERSION
 
         if b'chunkcachesize' in opts:
             self._chunkcachesize = opts[b'chunkcachesize']
         if b'maxchainlen' in opts:
             self._maxchainlen = opts[b'maxchainlen']
         if b'deltabothparents' in opts:
             self._deltabothparents = opts[b'deltabothparents']
         self._lazydelta = bool(opts.get(b'lazydelta', True))
         self._lazydeltabase = False
         if self._lazydelta:
             self._lazydeltabase = bool(opts.get(b'lazydeltabase', False))
         if b'compengine' in opts:
             self._compengine = opts[b'compengine']
         if b'zlib.level' in opts:
             self._compengineopts[b'zlib.level'] = opts[b'zlib.level']
         if b'zstd.level' in opts:
             self._compengineopts[b'zstd.level'] = opts[b'zstd.level']
         if b'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts[b'maxdeltachainspan']
         if self._mmaplargeindex and b'mmapindexthreshold' in opts:
             mmapindexthreshold = opts[b'mmapindexthreshold']
         self._sparserevlog = bool(opts.get(b'sparse-revlog', False))
         withsparseread = bool(opts.get(b'with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if b'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts[b'sparse-read-density-threshold']
         if b'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts[b'sparse-read-min-gap-size']
         if opts.get(b'enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in opts.get(b'flagprocessors', {}).items():
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % self._chunkcachesize
             )
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % self._chunkcachesize
             )
         force_nodemap = opts.get(b'devel-force-nodemap', False)
         return new_header, mmapindexthreshold, force_nodemap
 
     def _get_data(self, filepath, mmap_threshold, size=None):
         """return a file content with or without mmap
 
         If the file is missing return the empty string"""
         try:
             with self.opener(filepath) as fp:
                 if mmap_threshold is not None:
                     file_size = self.opener.fstat(fp).st_size
                     if file_size >= mmap_threshold:
                         if size is not None:
                             # avoid potentiel mmap crash
                             size = min(file_size, size)
                         # TODO: should .close() to release resources without
                         # relying on Python GC
                         if size is None:
                             return util.buffer(util.mmapread(fp))
                         else:
                             return util.buffer(util.mmapread(fp, size))
                 if size is None:
                     return fp.read()
                 else:
                     return fp.read(size)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return b''
 
     def _loadindex(self, docket=None):
 
         new_header, mmapindexthreshold, force_nodemap = self._init_opts()
 
         if self.postfix is not None:
             entry_point = b'%s.i.%s' % (self.radix, self.postfix)
         elif self._trypending and self.opener.exists(b'%s.i.a' % self.radix):
             entry_point = b'%s.i.a' % self.radix
         else:
             entry_point = b'%s.i' % self.radix
 
         if docket is not None:
             self._docket = docket
             self._docket_file = entry_point
         else:
             entry_data = b''
             self._initempty = True
             entry_data = self._get_data(entry_point, mmapindexthreshold)
             if len(entry_data) > 0:
                 header = INDEX_HEADER.unpack(entry_data[:4])[0]
                 self._initempty = False
             else:
                 header = new_header
 
             self._format_flags = header & ~0xFFFF
             self._format_version = header & 0xFFFF
 
             supported_flags = SUPPORTED_FLAGS.get(self._format_version)
             if supported_flags is None:
                 msg = _(b'unknown version (%d) in revlog %s')
                 msg %= (self._format_version, self.display_id)
                 raise error.RevlogError(msg)
             elif self._format_flags & ~supported_flags:
                 msg = _(b'unknown flags (%#04x) in version %d revlog %s')
                 display_flag = self._format_flags >> 16
                 msg %= (display_flag, self._format_version, self.display_id)
                 raise error.RevlogError(msg)
 
             features = FEATURES_BY_VERSION[self._format_version]
             self._inline = features[b'inline'](self._format_flags)
             self._generaldelta = features[b'generaldelta'](self._format_flags)
             self.hassidedata = features[b'sidedata']
 
             if not features[b'docket']:
                 self._indexfile = entry_point
                 index_data = entry_data
             else:
                 self._docket_file = entry_point
                 if self._initempty:
                     self._docket = docketutil.default_docket(self, header)
                 else:
                     self._docket = docketutil.parse_docket(
                         self, entry_data, use_pending=self._trypending
                     )
 
         if self._docket is not None:
             self._indexfile = self._docket.index_filepath()
             index_data = b''
             index_size = self._docket.index_end
             if index_size > 0:
                 index_data = self._get_data(
                     self._indexfile, mmapindexthreshold, size=index_size
                 )
                 if len(index_data) < index_size:
                     msg = _(b'too few index data for %s: got %d, expected %d')
                     msg %= (self.display_id, len(index_data), index_size)
                     raise error.RevlogError(msg)
 
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
             # the logic for persistent nodemap will be dealt with within the
             # main docket, so disable it for now.
             self._nodemap_file = None
 
         if self._docket is not None:
             self._datafile = self._docket.data_filepath()
             self._sidedatafile = self._docket.sidedata_filepath()
         elif self.postfix is None:
             self._datafile = b'%s.d' % self.radix
         else:
             self._datafile = b'%s.d.%s' % (self.radix, self.postfix)
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self._generaldelta:
             self._sparserevlog = False
 
         self._storedeltachains = True
 
         devel_nodemap = (
             self._nodemap_file
             and force_nodemap
             and parse_index_v1_nodemap is not None
         )
 
         use_rust_index = False
         if rustrevlog is not None:
             if self._nodemap_file is not None:
                 use_rust_index = True
             else:
                 use_rust_index = self.opener.options.get(b'rust.index')
 
         self._parse_index = parse_index_v1
         if self._format_version == REVLOGV0:
             self._parse_index = revlogv0.parse_index_v0
         elif self._format_version == REVLOGV2:
             self._parse_index = parse_index_v2
         elif self._format_version == CHANGELOGV2:
             self._parse_index = parse_index_cl_v2
         elif devel_nodemap:
             self._parse_index = parse_index_v1_nodemap
         elif use_rust_index:
             self._parse_index = parse_index_v1_mixed
         try:
             d = self._parse_index(index_data, self._inline)
             index, chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self._nodemap_file is not None
                 and util.safehasattr(index, 'update_nodemap_data')
             )
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
                     docket = nodemap_data[0]
                     if (
                         len(d[0]) > docket.tip_rev
                         and d[0][docket.tip_rev][7] == docket.tip_node
                     ):
                         # no changelog tampering
                         self._nodemap_docket = docket
                         index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
                 _(b"index %s is corrupted") % self.display_id
             )
         self.index = index
         self._segmentfile = randomaccessfile.randomaccessfile(
             self.opener,
             (self._indexfile if self._inline else self._datafile),
             self._chunkcachesize,
             chunkcache,
         )
         self._segmentfile_sidedata = randomaccessfile.randomaccessfile(
             self.opener,
             self._sidedatafile,
             self._chunkcachesize,
         )
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def revlog_kind(self):
         return self.target[0]
 
     @util.propertycache
     def display_id(self):
         """The public facing "ID" of the revlog that we use in message"""
         # Maybe we should build a user facing representation of
         # revlog.target instead of using `self.radix`
         return self.radix
 
     def _get_decompressor(self, t):
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(self._compengineopts)
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
         return compressor
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     @util.propertycache
     def _decompressor(self):
         """the default decompressor"""
         if self._docket is None:
             return None
         t = self._docket.default_compression_header
         c = self._get_decompressor(t)
         return c.decompress
 
     def _indexfp(self):
         """file object for the revlog's index file"""
         return self.opener(self._indexfile, mode=b"r")
 
     def __index_write_fp(self):
         # You should not use this directly and use `_writing` instead
         try:
             f = self.opener(
                 self._indexfile, mode=b"r+", checkambig=self._checkambig
             )
             if self._docket is None:
                 f.seek(0, os.SEEK_END)
             else:
                 f.seek(self._docket.index_end, os.SEEK_SET)
             return f
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return self.opener(
                 self._indexfile, mode=b"w+", checkambig=self._checkambig
             )
 
     def __index_new_fp(self):
         # You should not use this unless you are upgrading from inline revlog
         return self.opener(
             self._indexfile,
             mode=b"w",
             checkambig=self._checkambig,
             atomictemp=True,
         )
 
     def _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self._datafile, mode=mode)
 
     @contextlib.contextmanager
     def _sidedatareadfp(self):
         """file object suitable to read sidedata"""
         if self._writinghandles:
             yield self._writinghandles[2]
         else:
             with self.opener(self._sidedatafile) as fp:
                 yield fp
 
     def tiprev(self):
         return len(self.index) - 1
 
     def tip(self):
         return self.node(self.tiprev())
 
     def __contains__(self, rev):
         return 0 <= rev < len(self)
 
     def __len__(self):
         return len(self.index)
 
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
 
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         return storageutil.iterrevs(len(self), start=start, stop=stop)
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if (self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS) or (
             self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS
         ):
             return False
         return True
 
     def update_caches(self, transaction):
         if self._nodemap_file is not None:
             if transaction is None:
                 nodemaputil.update_persistent_nodemap(self)
             else:
                 nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
         self._pcache = {}
         self._nodemap_docket = None
         self.index.clearcaches()
         # The python code is the one responsible for validating the docket, we
         # end up having to refresh it here.
         use_nodemap = (
             not self._inline
             and self._nodemap_file is not None
             and util.safehasattr(self.index, 'update_nodemap_data')
         )
         if use_nodemap:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
                 self.index.update_nodemap_data(*nodemap_data)
 
     def rev(self, node):
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if (
                 node == self.nodeconstants.wdirid
                 or node in self.nodeconstants.wdirfilenodeids
             ):
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.display_id, _(b'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 sidedata_cut_off(self, rev):
         sd_cut_off = self.index[rev][8]
         if sd_cut_off != 0:
             return sd_cut_off
         # This is some annoying dance, because entries without sidedata
         # currently use 0 as their ofsset. (instead of previous-offset +
         # previous-size)
         #
         # We should reconsider this sidedata → 0 sidata_offset policy.
         # In the meantime, we need this.
         while 0 <= rev:
             e = self.index[rev]
             if e[9] != 0:
                 return e[8] + e[9]
             rev -= 1
         return 0
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def sidedata_length(self, rev):
         if not self.hassidedata:
             return 0
         return self.index[rev][9]
 
     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.rawdata(rev)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (flagutil.REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev))
 
     def fast_rank(self, rev):
         """Return the rank of a revision if already known, or None otherwise.
 
         The rank of a revision is the size of the sub-graph it defines as a
         head. Equivalently, the rank of a revision `r` is the size of the set
         `ancestors(r)`, `r` included.
 
         This method returns the rank retrieved from the revlog in constant
         time. It makes no attempt at computing unknown values for versions of
         the revlog which do not persist the rank.
         """
         rank = self.index[rev][ENTRY_RANK]
         if self._format_version != CHANGELOGV2 or rank == RANK_UNKNOWN:
             return None
         if rev == nullrev:
             return 0  # convention
         return rank
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
-        return entry[5], entry[6]
+        if self.canonical_parent_order and entry[5] == nullrev:
+            return entry[6], entry[5]
+        else:
+            return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # 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
+        # inline node() to avoid function call overhead
+        if self.canonical_parent_order and d[5] == self.nullid:
+            return i[d[6]][7], i[d[5]][7]
+        else:
+            return i[d[5]][7], i[d[6]][7]
 
     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.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         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 revision order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         # first, make sure start revisions aren't filtered
         revs = list(revs)
         checkrev = self.node
         for r in revs:
             checkrev(r)
         # and we're sure ancestors aren't filtered as well
 
         if rustancestor is not None and self.index.rust_ext_compat:
             lazyancestors = rustancestor.LazyAncestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     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 = [self.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:
             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]
 
         if rustancestor is not None and self.index.rust_ext_compat:
             return rustancestor.MissingAncestors(self.index, common)
         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 = [self.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 = [self.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],
                 [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 == self.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 != self.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 = [self.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.items() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevs()
             except AttributeError:
                 return self._headrevs()
         if rustdagop is not None and self.index.rust_ext_compat:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     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 [self.nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = {self.rev(n) for n in stop or []}
 
         revs = dagop.headrevssubset(
             self.revs, self.parentrevs, startrev=start, stoprevs=stoprevs
         )
 
         return [self.node(rev) for rev in revs]
 
     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 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)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError):  # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::(<roots> and <roots>::<heads>)))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(
                 minroot, heads, roots, includepath
             )
         except AttributeError:
             return dagop._reachablerootspure(
                 self.parentrevs, minroot, roots, heads, includepath
             )
 
     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 self.nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == self.nodeconstants.nodelen:
             # 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 error.LookupError:
                 pass  # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if b"%d" % 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) == 2 * self.nodeconstants.nodelen:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = self.nodeconstants.wdirhex.startswith(id)
         ambiguous = False
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     ambiguous = True
                 else:
                     return partial
             elif maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             else:
                 return None
         except error.RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 ambiguous = True
             # 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 ambiguous:
             raise error.AmbiguousPrefixLookupError(
                 id, self.display_id, _(b'ambiguous identifier')
             )
 
         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 self.nodeconstants.nullhex.startswith(id):
                     nl.append(self.nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.display_id, _(b'ambiguous identifier')
                     )
                 if maybewdir:
                     raise error.WdirUnsupported
                 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 error.LookupError(id, self.display_id, _(b'no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
 
         def isvalid(prefix):
             try:
                 matchednode = self._partialmatch(prefix)
             except error.AmbiguousPrefixLookupError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if matchednode is None:
                 raise error.LookupError(node, self.display_id, _(b'no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == b'f' for c in pycompat.iterbytestr(prefix))
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != self.nodeconstants.wdirid:
                     raise error.LookupError(
                         node, self.display_id, _(b'no node')
                     )
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == self.nodeconstants.wdirid:
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, len(hexnode) + 1):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     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 storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def _getsegmentforrevs(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.index.entry_size
             end += (endrev + 1) * self.index.entry_size
         length = end - start
 
         return start, self._segmentfile.read_chunk(start, length, 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.
         """
         compression_mode = self.index[rev][10]
         data = self._getsegmentforrevs(rev, rev, df=df)[1]
         if compression_mode == COMP_MODE_PLAIN:
             return data
         elif compression_mode == COMP_MODE_DEFAULT:
             return self._decompressor(data)
         elif compression_mode == COMP_MODE_INLINE:
             return self.decompress(data)
         else:
             msg = b'unknown compression mode %d'
             msg %= compression_mode
             raise error.RevlogError(msg)
 
     def _chunks(self, revs, df=None, targetsize=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.index.entry_size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = deltautil.slicechunk(
                 self, revs, targetsize=targetsize
             )
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, 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 revschunk]
 
             decomp = self.decompress
             # self._decompressor might be None, but will not be used in that case
             def_decomp = self._decompressor
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 comp_mode = self.index[rev][10]
                 c = buffer(data, chunkstart - offset, chunklength)
                 if comp_mode == COMP_MODE_PLAIN:
                     ladd(c)
                 elif comp_mode == COMP_MODE_INLINE:
                     ladd(decomp(c))
                 elif comp_mode == COMP_MODE_DEFAULT:
                     ladd(def_decomp(c))
                 else:
                     msg = b'unknown compression mode %d'
                     msg %= comp_mode
                     raise error.RevlogError(msg)
 
         return l
 
     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 issnapshot(self, rev):
         """tells whether rev is a snapshot"""
         if not self._sparserevlog:
             return self.deltaparent(rev) == nullrev
         elif util.safehasattr(self.index, b'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         p2 = entry[6]
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     def snapshotdepth(self, rev):
         """number of snapshot in the chain before this one"""
         if not self.issnapshot(rev):
             raise error.ProgrammingError(b'revision %d not a snapshot')
         return len(self._deltachain(rev)[0]) - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def revision(self, nodeorrev, _df=None):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df)
 
     def sidedata(self, nodeorrev, _df=None):
         """a map of extra data related to the changeset but not part of the hash
 
         This function currently return a dictionary. However, more advanced
         mapping object will likely be used in the future for a more
         efficient/lazy code.
         """
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
         else:
             rev = self.rev(nodeorrev)
         return self._sidedata(rev)
 
     def _revisiondata(self, nodeorrev, _df=None, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == self.nullid:
             return b""
 
         # ``rawtext`` is the text as stored inside the revlog. Might be the
         # revision or might need to be processed to retrieve the revision.
         rev, rawtext, validated = self._rawtext(node, rev, _df=_df)
 
         if raw and validated:
             # if we don't want to process the raw text and that raw
             # text is cached, we can exit early.
             return rawtext
         if rev is None:
             rev = self.rev(node)
         # the revlog's flag for this revision
         # (usually alter its state or content)
         flags = self.flags(rev)
 
         if validated and flags == REVIDX_DEFAULT_FLAGS:
             # no extra flags set, no flag processor runs, text = rawtext
             return rawtext
 
         if raw:
             validatehash = flagutil.processflagsraw(self, rawtext, flags)
             text = rawtext
         else:
             r = flagutil.processflagsread(self, rawtext, flags)
             text, validatehash = r
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._revisioncache = (node, rev, rawtext)
 
         return text
 
     def _rawtext(self, node, rev, _df=None):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
 
         # revision in the cache (could be useful to apply delta)
         cachedrev = None
         # An intermediate text to apply deltas to
         basetext = None
 
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 return (rev, self._revisioncache[2], True)
             cachedrev = self._revisioncache[1]
 
         if rev is None:
             rev = self.rev(node)
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             basetext = self._revisioncache[2]
 
         # drop cache to save memory, the caller is expected to
         # update self._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         bins = self._chunks(chain, df=_df, targetsize=targetsize)
         if basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext  # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         index_entry = self.index[rev]
         sidedata_offset = index_entry[8]
         sidedata_size = index_entry[9]
 
         if self._inline:
             sidedata_offset += self.index.entry_size * (1 + rev)
         if sidedata_size == 0:
             return {}
 
         if self._docket.sidedata_end < sidedata_offset + sidedata_size:
             filename = self._sidedatafile
             end = self._docket.sidedata_end
             offset = sidedata_offset
             length = sidedata_size
             m = FILE_TOO_SHORT_MSG % (filename, length, offset, end)
             raise error.RevlogError(m)
 
         comp_segment = self._segmentfile_sidedata.read_chunk(
             sidedata_offset, sidedata_size
         )
 
         comp = self.index[rev][11]
         if comp == COMP_MODE_PLAIN:
             segment = comp_segment
         elif comp == COMP_MODE_DEFAULT:
             segment = self._decompressor(comp_segment)
         elif comp == COMP_MODE_INLINE:
             segment = self.decompress(comp_segment)
         else:
             msg = b'unknown compression mode %d'
             msg %= comp
             raise error.RevlogError(msg)
 
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def rawdata(self, nodeorrev, _df=None):
         """return an uncompressed raw data of a given node or revision number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df, raw=True)
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return storageutil.hashrevisionsha1(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.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 # Clear the revision cache on hash failure. The revision cache
                 # only stores the raw revision and clearing the cache does have
                 # the side-effect that we won't have a cache hit when the raw
                 # revision data is accessed. But this case should be rare and
                 # it is extra work to teach the cache about the hash
                 # verification state.
                 if self._revisioncache and self._revisioncache[0] == node:
                     self._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(
                     _(b"integrity check failed on %s:%s")
                     % (self.display_id, pycompat.bytestr(revornode))
                 )
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.display_id, node, text)
             raise
 
     def _enforceinlinesize(self, tr):
         """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.
         """
         tiprev = len(self) - 1
         total_size = self.start(tiprev) + self.length(tiprev)
         if not self._inline or total_size < _maxinline:
             return
 
         troffset = tr.findoffset(self._indexfile)
         if troffset is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self._indexfile
             )
         trindex = None
         tr.add(self._datafile, 0)
 
         existing_handles = False
         if self._writinghandles is not None:
             existing_handles = True
             fp = self._writinghandles[0]
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
             self._segmentfile.writing_handle = None
             # No need to deal with sidedata writing handle as it is only
             # relevant with revlog-v2 which is never inline, not reaching
             # this code
 
         new_dfh = self._datafp(b'w+')
         new_dfh.truncate(0)  # drop any potentially existing data
         try:
             with self._indexfp() as read_ifh:
                 for r in self:
                     new_dfh.write(self._getsegmentforrevs(r, r, df=read_ifh)[1])
                     if (
                         trindex is None
                         and troffset
                         <= self.start(r) + r * self.index.entry_size
                     ):
                         trindex = r
                 new_dfh.flush()
 
             if trindex is None:
                 trindex = 0
 
             with self.__index_new_fp() as fp:
                 self._format_flags &= ~FLAG_INLINE_DATA
                 self._inline = False
                 for i in self:
                     e = self.index.entry_binary(i)
                     if i == 0 and self._docket is None:
                         header = self._format_flags | self._format_version
                         header = self.index.pack_header(header)
                         e = header + e
                     fp.write(e)
                 if self._docket is not None:
                     self._docket.index_end = fp.tell()
 
                 # There is a small transactional race here. If the rename of
                 # the index fails, we should remove the datafile. It is more
                 # important to ensure that the data file is not truncated
                 # when the index is replaced as otherwise data is lost.
                 tr.replace(self._datafile, self.start(trindex))
 
                 # the temp file replace the real index when we exit the context
                 # manager
 
             tr.replace(self._indexfile, trindex * self.index.entry_size)
             nodemaputil.setup_persistent_nodemap(tr, self)
             self._segmentfile = randomaccessfile.randomaccessfile(
                 self.opener,
                 self._datafile,
                 self._chunkcachesize,
             )
 
             if existing_handles:
                 # switched from inline to conventional reopen the index
                 ifh = self.__index_write_fp()
                 self._writinghandles = (ifh, new_dfh, None)
                 self._segmentfile.writing_handle = new_dfh
                 new_dfh = None
                 # No need to deal with sidedata writing handle as it is only
                 # relevant with revlog-v2 which is never inline, not reaching
                 # this code
         finally:
             if new_dfh is not None:
                 new_dfh.close()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     @contextlib.contextmanager
     def reading(self):
         """Context manager that keeps data and sidedata files open for reading"""
         with self._segmentfile.reading():
             with self._segmentfile_sidedata.reading():
                 yield
 
     @contextlib.contextmanager
     def _writing(self, transaction):
         if self._trypending:
             msg = b'try to write in a `trypending` revlog: %s'
             msg %= self.display_id
             raise error.ProgrammingError(msg)
         if self._writinghandles is not None:
             yield
         else:
             ifh = dfh = sdfh = None
             try:
                 r = len(self)
                 # opening the data file.
                 dsize = 0
                 if r:
                     dsize = self.end(r - 1)
                 dfh = None
                 if not self._inline:
                     try:
                         dfh = self._datafp(b"r+")
                         if self._docket is None:
                             dfh.seek(0, os.SEEK_END)
                         else:
                             dfh.seek(self._docket.data_end, os.SEEK_SET)
                     except IOError as inst:
                         if inst.errno != errno.ENOENT:
                             raise
                         dfh = self._datafp(b"w+")
                     transaction.add(self._datafile, dsize)
                 if self._sidedatafile is not None:
                     # revlog-v2 does not inline, help Pytype
                     assert dfh is not None
                     try:
                         sdfh = self.opener(self._sidedatafile, mode=b"r+")
                         dfh.seek(self._docket.sidedata_end, os.SEEK_SET)
                     except IOError as inst:
                         if inst.errno != errno.ENOENT:
                             raise
                         sdfh = self.opener(self._sidedatafile, mode=b"w+")
                     transaction.add(
                         self._sidedatafile, self._docket.sidedata_end
                     )
 
                 # opening the index file.
                 isize = r * self.index.entry_size
                 ifh = self.__index_write_fp()
                 if self._inline:
                     transaction.add(self._indexfile, dsize + isize)
                 else:
                     transaction.add(self._indexfile, isize)
                 # exposing all file handle for writing.
                 self._writinghandles = (ifh, dfh, sdfh)
                 self._segmentfile.writing_handle = ifh if self._inline else dfh
                 self._segmentfile_sidedata.writing_handle = sdfh
                 yield
                 if self._docket is not None:
                     self._write_docket(transaction)
             finally:
                 self._writinghandles = None
                 self._segmentfile.writing_handle = None
                 self._segmentfile_sidedata.writing_handle = None
                 if dfh is not None:
                     dfh.close()
                 if sdfh is not None:
                     sdfh.close()
                 # closing the index file last to avoid exposing referent to
                 # potential unflushed data content.
                 if ifh is not None:
                     ifh.close()
 
     def _write_docket(self, transaction):
         """write the current docket on disk
 
         Exist as a method to help changelog to implement transaction logic
 
         We could also imagine using the same transaction logic for all revlog
         since docket are cheap."""
         self._docket.write(transaction)
 
     def addrevision(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=None,
         node=None,
         flags=REVIDX_DEFAULT_FLAGS,
         deltacomputer=None,
         sidedata=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)
         flags - the known flags to set on the revision
         deltacomputer - an optional deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise error.RevlogError(
                 _(b"attempted to add linkrev -1 to %s") % self.display_id
             )
 
         if sidedata is None:
             sidedata = {}
         elif sidedata and not self.hassidedata:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _(
                     b"%s: size of %d bytes exceeds maximum revlog storage of 2GiB"
                 )
                 % (self.display_id, len(rawtext))
             )
 
         node = node or self.hash(rawtext, p1, p2)
         rev = self.index.get_rev(node)
         if rev is not None:
             return rev
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
             sidedata=sidedata,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         with self._writing(transaction):
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return b'', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return b'', compressed
 
         if data[0:1] == b'\0':
             return b'', data
         return b'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == b'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(
                     _(b'revlog decompress error: %s')
                     % stringutil.forcebytestr(e)
                 )
         # '\0' is more common than 'u' so it goes first.
         elif t == b'\0':
             return data
         elif t == b'u':
             return util.buffer(data, 1)
 
         compressor = self._get_decompressor(t)
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         alwayscache=False,
         deltacomputer=None,
         sidedata=None,
     ):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == self.nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self.display_id
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%s: attempt to add wdir revision") % self.display_id
             )
         if self._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
 
         if self._inline:
             fh = self._writinghandles[0]
         else:
             fh = self._writinghandles[1]
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
 
         offset = self._get_data_offset(prev)
 
         if self._concurrencychecker:
             ifh, dfh, sdfh = self._writinghandles
             # XXX no checking for the sidedata file
             if self._inline:
                 # offset is "as if" it were in the .d file, so we need to add on
                 # the size of the entry metadata.
                 self._concurrencychecker(
                     ifh, self._indexfile, offset + curr * self.index.entry_size
                 )
             else:
                 # Entries in the .i are a consistent size.
                 self._concurrencychecker(
                     ifh, self._indexfile, curr * self.index.entry_size
                 )
                 self._concurrencychecker(dfh, self._datafile, offset)
 
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(
                 revlog.size(self, cachedelta[0]), cachedelta[1]
             )
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = revlogutils.revisioninfo(
             node,
             p1,
             p2,
             btext,
             textlen,
             cachedelta,
             flags,
         )
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         compression_mode = COMP_MODE_INLINE
         if self._docket is not None:
             default_comp = self._docket.default_compression_header
             r = deltautil.delta_compression(default_comp, deltainfo)
             compression_mode, deltainfo = r
 
         sidedata_compression_mode = COMP_MODE_INLINE
         if sidedata and self.hassidedata:
             sidedata_compression_mode = COMP_MODE_PLAIN
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = self._docket.sidedata_end
             h, comp_sidedata = self.compress(serialized_sidedata)
             if (
                 h != b'u'
                 and comp_sidedata[0:1] != b'\0'
                 and len(comp_sidedata) < len(serialized_sidedata)
             ):
                 assert not h
                 if (
                     comp_sidedata[0:1]
                     == self._docket.default_compression_header
                 ):
                     sidedata_compression_mode = COMP_MODE_DEFAULT
                     serialized_sidedata = comp_sidedata
                 else:
                     sidedata_compression_mode = COMP_MODE_INLINE
                     serialized_sidedata = comp_sidedata
         else:
             serialized_sidedata = b""
             # Don't store the offset if the sidedata is empty, that way
             # we can easily detect empty sidedata and they will be no different
             # than ones we manually add.
             sidedata_offset = 0
 
         rank = RANK_UNKNOWN
         if self._format_version == CHANGELOGV2:
             if (p1r, p2r) == (nullrev, nullrev):
                 rank = 1
             elif p1r != nullrev and p2r == nullrev:
                 rank = 1 + self.fast_rank(p1r)
             elif p1r == nullrev and p2r != nullrev:
                 rank = 1 + self.fast_rank(p2r)
             else:  # merge node
                 if rustdagop is not None and self.index.rust_ext_compat:
                     rank = rustdagop.rank(self.index, p1r, p2r)
                 else:
                     pmin, pmax = sorted((p1r, p2r))
                     rank = 1 + self.fast_rank(pmax)
                     rank += sum(1 for _ in self.findmissingrevs([pmax], [pmin]))
 
         e = revlogutils.entry(
             flags=flags,
             data_offset=offset,
             data_compressed_length=deltainfo.deltalen,
             data_uncompressed_length=textlen,
             data_compression_mode=compression_mode,
             data_delta_base=deltainfo.base,
             link_rev=link,
             parent_rev_1=p1r,
             parent_rev_2=p2r,
             node_id=node,
             sidedata_offset=sidedata_offset,
             sidedata_compressed_length=len(serialized_sidedata),
             sidedata_compression_mode=sidedata_compression_mode,
             rank=rank,
         )
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0 and self._docket is None:
             header = self._format_flags | self._format_version
             header = self.index.pack_header(header)
             entry = header + entry
         self._writeentry(
             transaction,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
             sidedata_offset,
         )
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo, fh)
 
         if type(rawtext) == bytes:  # only accept immutable objects
             self._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return curr
 
     def _get_data_offset(self, prev):
         """Returns the current offset in the (in-transaction) data file.
         Versions < 2 of the revlog can get this 0(1), revlog v2 needs a docket
         file to store that information: since sidedata can be rewritten to the
         end of the data file within a transaction, you can have cases where, for
         example, rev `n` does not have sidedata while rev `n - 1` does, leading
         to `n - 1`'s sidedata being written after `n`'s data.
 
         TODO cache this in a docket file before getting out of experimental."""
         if self._docket is None:
             return self.end(prev)
         else:
             return self._docket.data_end
 
     def _writeentry(
         self, transaction, entry, data, link, offset, sidedata, sidedata_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. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         if self._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
         ifh, dfh, sdfh = self._writinghandles
         if self._docket is None:
             ifh.seek(0, os.SEEK_END)
         else:
             ifh.seek(self._docket.index_end, os.SEEK_SET)
         if dfh:
             if self._docket is None:
                 dfh.seek(0, os.SEEK_END)
             else:
                 dfh.seek(self._docket.data_end, os.SEEK_SET)
         if sdfh:
             sdfh.seek(self._docket.sidedata_end, os.SEEK_SET)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self._datafile, offset)
             if self._sidedatafile:
                 transaction.add(self._sidedatafile, sidedata_offset)
             transaction.add(self._indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 sdfh.write(sidedata)
             ifh.write(entry)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self._indexfile, offset)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             assert not sidedata
             self._enforceinlinesize(transaction)
         if self._docket is not None:
             # revlog-v2 always has 3 writing handles, help Pytype
             wh1 = self._writinghandles[0]
             wh2 = self._writinghandles[1]
             wh3 = self._writinghandles[2]
             assert wh1 is not None
             assert wh2 is not None
             assert wh3 is not None
             self._docket.index_end = wh1.tell()
             self._docket.data_end = wh2.tell()
             self._docket.sidedata_end = wh3.tell()
 
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=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.
         """
 
         if self._adding_group:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         self._adding_group = True
         empty = True
         try:
             with self._writing(transaction):
                 deltacomputer = deltautil.deltacomputer(self)
                 # loop through our set of deltas
                 for data in deltas:
                     (
                         node,
                         p1,
                         p2,
                         linknode,
                         deltabase,
                         delta,
                         flags,
                         sidedata,
                     ) = data
                     link = linkmapper(linknode)
                     flags = flags or REVIDX_DEFAULT_FLAGS
 
                     rev = self.index.get_rev(node)
                     if rev is not None:
                         # this can happen if two branches make the same change
                         self._nodeduplicatecallback(transaction, rev)
                         if duplicaterevisioncb:
                             duplicaterevisioncb(self, rev)
                         empty = False
                         continue
 
                     for p in (p1, p2):
                         if not self.index.has_node(p):
                             raise error.LookupError(
                                 p, self.radix, _(b'unknown parent')
                             )
 
                     if not self.index.has_node(deltabase):
                         raise error.LookupError(
                             deltabase, self.display_id, _(b'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(b">lll")
                         oldlen = self.rawsize(baserev)
                         newlen = len(delta) - hlen
                         if delta[:hlen] != mdiff.replacediffheader(
                             oldlen, newlen
                         ):
                             raise error.CensoredBaseError(
                                 self.display_id, self.node(baserev)
                             )
 
                     if not flags and self._peek_iscensored(baserev, delta):
                         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.
                     rev = self._addrevision(
                         node,
                         None,
                         transaction,
                         link,
                         p1,
                         p2,
                         flags,
                         (baserev, delta),
                         alwayscache=alwayscache,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
 
                     if addrevisioncb:
                         addrevisioncb(self, rev)
                     empty = False
         finally:
             self._adding_group = False
         return not empty
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         return storageutil.deltaiscensored(delta, baserev, self.rawsize)
 
     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.
         """
         return storageutil.resolvestripinfo(
             minlink,
             len(self) - 1,
             self.headrevs(),
             self.linkrev,
             self.parentrevs,
         )
 
     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
         data_end = self.start(rev)
         if not self._inline:
             transaction.add(self._datafile, data_end)
             end = rev * self.index.entry_size
         else:
             end = data_end + (rev * self.index.entry_size)
 
         if self._sidedatafile:
             sidedata_end = self.sidedata_cut_off(rev)
             transaction.add(self._sidedatafile, sidedata_end)
 
         transaction.add(self._indexfile, end)
         if self._docket is not None:
             # XXX we could, leverage the docket while stripping. However it is
             # not powerfull enough at the time of this comment
             self._docket.index_end = end
             self._docket.data_end = data_end
             self._docket.sidedata_end = sidedata_end
             self._docket.write(transaction, stripping=True)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = util.lrucachedict(500)
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
 
         del self.index[rev:-1]
 
     def checksize(self):
         """Check size of index and data files
 
         return a (dd, di) tuple.
         - dd: extra bytes for the "data" file
         - di: extra bytes for the "index" file
 
         A healthy revlog will return (0, 0).
         """
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, io.SEEK_END)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self._indexfile)
             f.seek(0, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self.index.entry_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 self._docket_file is None:
             if not self._inline:
                 res.append(self._datafile)
         else:
             res.append(self._docket_file)
             res.extend(self._docket.old_index_filepaths(include_empty=False))
             if self._docket.data_end:
                 res.append(self._datafile)
             res.extend(self._docket.old_data_filepaths(include_empty=False))
             if self._docket.sidedata_end:
                 res.append(self._sidedatafile)
             res.extend(self._docket.old_sidedata_filepaths(include_empty=False))
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         if nodesorder not in (b'nodes', b'storage', b'linear', None):
             raise error.ProgrammingError(
                 b'unhandled value for nodesorder: %s' % nodesorder
             )
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = b'storage'
 
         if (
             not self._storedeltachains
             and deltamode != repository.CG_DELTAMODE_PREV
         ):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self,
             nodes,
             nodesorder,
             revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self.candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             sidedata_helpers=sidedata_helpers,
         )
 
     DELTAREUSEALWAYS = b'always'
     DELTAREUSESAMEREVS = b'samerevs'
     DELTAREUSENEVER = b'never'
 
     DELTAREUSEFULLADD = b'fulladd'
 
     DELTAREUSEALL = {b'always', b'samerevs', b'never', b'fulladd'}
 
     def clone(
         self,
         tr,
         destrevlog,
         addrevisioncb=None,
         deltareuse=DELTAREUSESAMEREVS,
         forcedeltabothparents=None,
         sidedata_helpers=None,
     ):
         """Copy this revlog to another, possibly with format changes.
 
         The destination revlog will contain the same revisions and nodes.
         However, it may not be bit-for-bit identical due to e.g. delta encoding
         differences.
 
         The ``deltareuse`` argument control how deltas from the existing revlog
         are preserved in the destination revlog. The argument can have the
         following values:
 
         DELTAREUSEALWAYS
            Deltas will always be reused (if possible), even if the destination
            revlog would not select the same revisions for the delta. This is the
            fastest mode of operation.
         DELTAREUSESAMEREVS
            Deltas will be reused if the destination revlog would pick the same
            revisions for the delta. This mode strikes a balance between speed
            and optimization.
         DELTAREUSENEVER
            Deltas will never be reused. This is the slowest mode of execution.
            This mode can be used to recompute deltas (e.g. if the diff/delta
            algorithm changes).
         DELTAREUSEFULLADD
            Revision will be re-added as if their were new content. This is
            slower than DELTAREUSEALWAYS but allow more mechanism to kicks in.
            eg: large file detection and handling.
 
         Delta computation can be slow, so the choice of delta reuse policy can
         significantly affect run time.
 
         The default policy (``DELTAREUSESAMEREVS``) strikes a balance between
         two extremes. Deltas will be reused if they are appropriate. But if the
         delta could choose a better revision, it will do so. This means if you
         are converting a non-generaldelta revlog to a generaldelta revlog,
         deltas will be recomputed if the delta's parent isn't a parent of the
         revision.
 
         In addition to the delta policy, the ``forcedeltabothparents``
         argument controls whether to force compute deltas against both parents
         for merges. By default, the current default is used.
 
         See `revlogutil.sidedata.get_sidedata_helpers` for the doc on
         `sidedata_helpers`.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(
                 _(b'value for deltareuse invalid: %s') % deltareuse
             )
 
         if len(destrevlog):
             raise ValueError(_(b'destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_(b'source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_(b'destination revlog has filtered revisions'))
 
         # lazydelta and lazydeltabase controls whether to reuse a cached delta,
         # if possible.
         oldlazydelta = destrevlog._lazydelta
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             self._clone(
                 tr,
                 destrevlog,
                 addrevisioncb,
                 deltareuse,
                 forcedeltabothparents,
                 sidedata_helpers,
             )
 
         finally:
             destrevlog._lazydelta = oldlazydelta
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
         sidedata_helpers,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         deltacomputer = deltautil.deltacomputer(destrevlog)
         index = self.index
         for rev in self:
             entry = index[rev]
 
             # Some classes override linkrev to take filtered revs into
             # account. Use raw entry from index.
             flags = entry[0] & 0xFFFF
             linkrev = entry[4]
             p1 = index[entry[5]][7]
             p2 = index[entry[6]][7]
             node = entry[7]
 
             # (Possibly) reuse the delta from the revlog if allowed and
             # the revlog chunk is a delta.
             cachedelta = None
             rawtext = None
             if deltareuse == self.DELTAREUSEFULLADD:
                 text = self._revisiondata(rev)
                 sidedata = self.sidedata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 destrevlog.addrevision(
                     text,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     cachedelta=cachedelta,
                     node=node,
                     flags=flags,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
             else:
                 if destrevlog._lazydelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 sidedata = None
                 if not cachedelta:
                     rawtext = self._revisiondata(rev)
                     sidedata = self.sidedata(rev)
                 if sidedata is None:
                     sidedata = self.sidedata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 with destrevlog._writing(tr):
                     destrevlog._addrevision(
                         node,
                         rawtext,
                         tr,
                         linkrev,
                         p1,
                         p2,
                         flags,
                         cachedelta,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
 
             if addrevisioncb:
                 addrevisioncb(self, rev, node)
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if self._format_version == REVLOGV0:
             raise error.RevlogError(
                 _(b'cannot censor with version %d revlogs')
                 % self._format_version
             )
         elif self._format_version == REVLOGV1:
             rewrite.v1_censor(self, tr, censornode, tombstone)
         else:
             rewrite.v2_censor(self, tr, censornode, tombstone)
 
     def verifyintegrity(self, state):
         """Verifies the integrity of the revlog.
 
         Yields ``revlogproblem`` instances describing problems that are
         found.
         """
         dd, di = self.checksize()
         if dd:
             yield revlogproblem(error=_(b'data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_(b'index contains %d extra bytes') % di)
 
         version = self._format_version
 
         # The verifier tells us what version revlog we should be.
         if version != state[b'expectedversion']:
             yield revlogproblem(
                 warning=_(b"warning: '%s' uses revlog format %d; expected %d")
                 % (self.display_id, version, state[b'expectedversion'])
             )
 
         state[b'skipread'] = set()
         state[b'safe_renamed'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see flagutil.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get(b'skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_(b'unpacked size is %d, %d expected') % (l2, l1),
                         node=node,
                     )
 
             except error.CensoredNodeError:
                 if state[b'erroroncensored']:
                     yield revlogproblem(
                         error=_(b'censored file data'), node=node
                     )
                     state[b'skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_(b'unpacking %s: %s')
                     % (short(node), stringutil.forcebytestr(e)),
                     node=node,
                 )
                 state[b'skipread'].add(node)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         d = {}
 
         if exclusivefiles:
             d[b'exclusivefiles'] = [(self.opener, self._indexfile)]
             if not self._inline:
                 d[b'exclusivefiles'].append((self.opener, self._datafile))
 
         if sharedfiles:
             d[b'sharedfiles'] = []
 
         if revisionscount:
             d[b'revisionscount'] = len(self)
 
         if trackedsize:
             d[b'trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d[b'storedsize'] = sum(
                 self.opener.stat(path).st_size for path in self.files()
             )
 
         return d
 
     def rewrite_sidedata(self, transaction, helpers, startrev, endrev):
         if not self.hassidedata:
             return
         # revlog formats with sidedata support does not support inline
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         new_entries = []
         # append the new sidedata
         with self._writing(transaction):
             ifh, dfh, sdfh = self._writinghandles
             dfh.seek(self._docket.sidedata_end, os.SEEK_SET)
 
             current_offset = sdfh.tell()
             for rev in range(startrev, endrev + 1):
                 entry = self.index[rev]
                 new_sidedata, flags = sidedatautil.run_sidedata_helpers(
                     store=self,
                     sidedata_helpers=helpers,
                     sidedata={},
                     rev=rev,
                 )
 
                 serialized_sidedata = sidedatautil.serialize_sidedata(
                     new_sidedata
                 )
 
                 sidedata_compression_mode = COMP_MODE_INLINE
                 if serialized_sidedata and self.hassidedata:
                     sidedata_compression_mode = COMP_MODE_PLAIN
                     h, comp_sidedata = self.compress(serialized_sidedata)
                     if (
                         h != b'u'
                         and comp_sidedata[0] != b'\0'
                         and len(comp_sidedata) < len(serialized_sidedata)
                     ):
                         assert not h
                         if (
                             comp_sidedata[0]
                             == self._docket.default_compression_header
                         ):
                             sidedata_compression_mode = COMP_MODE_DEFAULT
                             serialized_sidedata = comp_sidedata
                         else:
                             sidedata_compression_mode = COMP_MODE_INLINE
                             serialized_sidedata = comp_sidedata
                 if entry[8] != 0 or entry[9] != 0:
                     # rewriting entries that already have sidedata is not
                     # supported yet, because it introduces garbage data in the
                     # revlog.
                     msg = b"rewriting existing sidedata is not supported yet"
                     raise error.Abort(msg)
 
                 # Apply (potential) flags to add and to remove after running
                 # the sidedata helpers
                 new_offset_flags = entry[0] | flags[0] & ~flags[1]
                 entry_update = (
                     current_offset,
                     len(serialized_sidedata),
                     new_offset_flags,
                     sidedata_compression_mode,
                 )
 
                 # the sidedata computation might have move the file cursors around
                 sdfh.seek(current_offset, os.SEEK_SET)
                 sdfh.write(serialized_sidedata)
                 new_entries.append(entry_update)
                 current_offset += len(serialized_sidedata)
                 self._docket.sidedata_end = sdfh.tell()
 
             # rewrite the new index entries
             ifh.seek(startrev * self.index.entry_size)
             for i, e in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, *e)
                 packed = self.index.entry_binary(rev)
                 if rev == 0 and self._docket is None:
                     header = self._format_flags | self._format_version
                     header = self.index.pack_header(header)
                     packed = header + packed
                 ifh.write(packed)

tests/test-narrow-shallow-merges.t

@@ -1,347 +1,347 b''
 #require no-reposimplestore
 
   $ . "$TESTDIR/narrow-library.sh"
 
 create full repo
 
   $ hg init master
   $ cd master
   $ cat >> .hg/hgrc <<EOF
   > [narrow]
   > serveellipses=True
   > EOF
 
   $ mkdir inside
   $ echo 1 > inside/f
   $ hg commit -Aqm 'initial inside'
 
   $ mkdir outside
   $ echo 1 > outside/f
   $ hg commit -Aqm 'initial outside'
 
   $ echo 2a > outside/f
   $ hg commit -Aqm 'outside 2a'
   $ echo 3 > inside/f
   $ hg commit -Aqm 'inside 3'
   $ echo 4a > outside/f
   $ hg commit -Aqm 'outside 4a'
   $ hg update '.~3'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ echo 2b > outside/f
   $ hg commit -Aqm 'outside 2b'
   $ echo 3 > inside/f
   $ hg commit -Aqm 'inside 3'
   $ echo 4b > outside/f
   $ hg commit -Aqm 'outside 4b'
   $ hg update '.~3'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ echo 2c > outside/f
   $ hg commit -Aqm 'outside 2c'
   $ echo 3 > inside/f
   $ hg commit -Aqm 'inside 3'
   $ echo 4c > outside/f
   $ hg commit -Aqm 'outside 4c'
   $ hg update '.~3'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ echo 2d > outside/f
   $ hg commit -Aqm 'outside 2d'
   $ echo 3 > inside/f
   $ hg commit -Aqm 'inside 3'
   $ echo 4d > outside/f
   $ hg commit -Aqm 'outside 4d'
 
   $ hg update -r 'desc("outside 4a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge -r 'desc("outside 4b")' 2>&1 | egrep -v '(warning:|incomplete!)'
   merging outside/f
   0 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   $ echo 5 > outside/f
   $ rm outside/f.orig
   $ hg resolve --mark outside/f
   (no more unresolved files)
   $ hg commit -m 'merge a/b 5'
   $ echo 6 > outside/f
   $ hg commit -Aqm 'outside 6'
 
   $ hg merge -r 'desc("outside 4c")' 2>&1 | egrep -v '(warning:|incomplete!)'
   merging outside/f
   0 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   $ echo 7 > outside/f
   $ rm outside/f.orig
   $ hg resolve --mark outside/f
   (no more unresolved files)
   $ hg commit -Aqm 'merge a/b/c 7'
   $ echo 8 > outside/f
   $ hg commit -Aqm 'outside 8'
 
   $ hg merge -r 'desc("outside 4d")' 2>&1 | egrep -v '(warning:|incomplete!)'
   merging outside/f
   0 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   $ echo 9 > outside/f
   $ rm outside/f.orig
   $ hg resolve --mark outside/f
   (no more unresolved files)
   $ hg commit -Aqm 'merge a/b/c/d 9'
   $ echo 10 > outside/f
   $ hg commit -Aqm 'outside 10'
 
   $ echo 11 > inside/f
   $ hg commit -Aqm 'inside 11'
   $ echo 12 > outside/f
   $ hg commit -Aqm 'outside 12'
 
   $ hg log -G -T '{rev} {node|short} {desc}\n'
   @  21 8d874d57adea outside 12
   |
   o  20 7ef88b4dd4fa inside 11
   |
   o  19 2a20009de83e outside 10
   |
   o    18 3ac1f5779de3 merge a/b/c/d 9
   |\
   | o  17 38a9c2f7e546 outside 8
   | |
   | o    16 094aa62fc898 merge a/b/c 7
   | |\
   | | o  15 f29d083d32e4 outside 6
   | | |
   | | o    14 2dc11382541d merge a/b 5
   | | |\
   o | | |  13 27d07ef97221 outside 4d
   | | | |
   o | | |  12 465567bdfb2d inside 3
   | | | |
   o | | |  11 d1c61993ec83 outside 2d
   | | | |
   | o | |  10 56859a8e33b9 outside 4c
   | | | |
   | o | |  9 bb96a08b062a inside 3
   | | | |
   | o | |  8 b844052e7b3b outside 2c
   |/ / /
   | | o  7 9db2d8fcc2a6 outside 4b
   | | |
   | | o  6 6418167787a6 inside 3
   | | |
   +---o  5 77344f344d83 outside 2b
   | |
   | o  4 9cadde08dc9f outside 4a
   | |
   | o  3 019ef06f125b inside 3
   | |
   | o  2 75e40c075a19 outside 2a
   |/
   o  1 906d6c682641 initial outside
   |
   o  0 9f8e82b51004 initial inside
   
 
 Now narrow and shallow clone this and get a hopefully correct graph
 
   $ cd ..
   $ hg clone --narrow ssh://user@dummy/master narrow --include inside --depth 7
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 8 changesets with 3 changes to 1 files
   new changesets *:* (glob)
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd narrow
 
 To make updating the tests easier, we print the emitted nodes
 sorted. This makes it easier to identify when the same node structure
 has been emitted, just in a different order.
 
   $ hg log -G -T '{rev} {node|short}{if(ellipsis,"...")} {desc}\n'
   @  7 8d874d57adea... outside 12
   |
   o  6 7ef88b4dd4fa inside 11
   |
   o  5 2a20009de83e... outside 10
   |
   o    4 3ac1f5779de3... merge a/b/c/d 9
   |\
   | o  3 465567bdfb2d inside 3
   | |
   | o  2 d1c61993ec83... outside 2d
   |
   o  1 bb96a08b062a inside 3
   |
   o  0 b844052e7b3b... outside 2c
   
 
   $ hg log -T '{if(ellipsis,"...")}{node|short} {p1node|short} {p2node|short} {desc}\n' | sort
-  ...2a20009de83e 000000000000 3ac1f5779de3 outside 10
+  ...2a20009de83e 3ac1f5779de3 000000000000 outside 10
   ...3ac1f5779de3 bb96a08b062a 465567bdfb2d merge a/b/c/d 9
   ...8d874d57adea 7ef88b4dd4fa 000000000000 outside 12
   ...b844052e7b3b 000000000000 000000000000 outside 2c
   ...d1c61993ec83 000000000000 000000000000 outside 2d
   465567bdfb2d d1c61993ec83 000000000000 inside 3
   7ef88b4dd4fa 2a20009de83e 000000000000 inside 11
   bb96a08b062a b844052e7b3b 000000000000 inside 3
 
   $ cd ..
 
 Incremental test case: show a pull can pull in a conflicted merge even if elided
 
   $ hg init pullmaster
   $ cd pullmaster
   $ cat >> .hg/hgrc <<EOF
   > [narrow]
   > serveellipses=True
   > EOF
   $ mkdir inside outside
   $ echo v1 > inside/f
   $ echo v1 > outside/f
   $ hg add inside/f outside/f
   $ hg commit -m init
 
   $ for line in a b c d
   > do
   > hg update -r 0
   > echo v2$line > outside/f
   > hg commit -m "outside 2$line"
   > echo v2$line > inside/f
   > hg commit -m "inside 2$line"
   > echo v3$line > outside/f
   > hg commit -m "outside 3$line"
   > echo v4$line > outside/f
   > hg commit -m "outside 4$line"
   > done
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   created new head
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   created new head
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   created new head
 
   $ cd ..
   $ hg clone --narrow ssh://user@dummy/pullmaster pullshallow \
   >          --include inside --depth 3
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 12 changesets with 5 changes to 1 files (+3 heads)
   new changesets *:* (glob)
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd pullshallow
 
   $ hg log -G -T '{rev} {node|short}{if(ellipsis,"...")} {desc}\n'
   @  11 0ebbd712a0c8... outside 4d
   |
   o  10 0d4c867aeb23 inside 2d
   |
   o  9 e932969c3961... outside 2d
   
   o  8 33d530345455... outside 4c
   |
   o  7 0ce6481bfe07 inside 2c
   |
   o  6 caa65c940632... outside 2c
   
   o  5 3df233defecc... outside 4b
   |
   o  4 7162cc6d11a4 inside 2b
   |
   o  3 f2a632f0082d... outside 2b
   
   o  2 b8a3da16ba49... outside 4a
   |
   o  1 53f543eb8e45 inside 2a
   |
   o  0 1be3e5221c6a... outside 2a
   
   $ hg log -T '{if(ellipsis,"...")}{node|short} {p1node|short} {p2node|short} {desc}\n' | sort
   ...0ebbd712a0c8 0d4c867aeb23 000000000000 outside 4d
   ...1be3e5221c6a 000000000000 000000000000 outside 2a
   ...33d530345455 0ce6481bfe07 000000000000 outside 4c
   ...3df233defecc 7162cc6d11a4 000000000000 outside 4b
   ...b8a3da16ba49 53f543eb8e45 000000000000 outside 4a
   ...caa65c940632 000000000000 000000000000 outside 2c
   ...e932969c3961 000000000000 000000000000 outside 2d
   ...f2a632f0082d 000000000000 000000000000 outside 2b
   0ce6481bfe07 caa65c940632 000000000000 inside 2c
   0d4c867aeb23 e932969c3961 000000000000 inside 2d
   53f543eb8e45 1be3e5221c6a 000000000000 inside 2a
   7162cc6d11a4 f2a632f0082d 000000000000 inside 2b
 
   $ cd ../pullmaster
   $ hg update -r 'desc("outside 4a")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge -r 'desc("outside 4b")' 2>&1 | egrep -v '(warning:|incomplete!)'
   merging inside/f
   merging outside/f
   0 files updated, 0 files merged, 0 files removed, 2 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   $ echo 3 > inside/f
   $ echo 5 > outside/f
   $ rm -f {in,out}side/f.orig
   $ hg resolve --mark inside/f outside/f
   (no more unresolved files)
   $ hg commit -m 'merge a/b 5'
 
   $ hg update -r 'desc("outside 4c")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge -r 'desc("outside 4d")' 2>&1 | egrep -v '(warning:|incomplete!)'
   merging inside/f
   merging outside/f
   0 files updated, 0 files merged, 0 files removed, 2 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   $ echo 3 > inside/f
   $ echo 5 > outside/f
   $ rm -f {in,out}side/f.orig
   $ hg resolve --mark inside/f outside/f
   (no more unresolved files)
   $ hg commit -m 'merge c/d 5'
 
   $ hg update -r 'desc("merge a/b 5")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge -r 'desc("merge c/d 5")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ echo 6 > outside/f
   $ hg commit -m 'outside 6'
   $ echo 7 > outside/f
   $ hg commit -m 'outside 7'
   $ echo 8 > outside/f
   $ hg commit -m 'outside 8'
 
   $ cd ../pullshallow
   $ hg pull --depth 3
   pulling from ssh://user@dummy/pullmaster
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 4 changesets with 3 changes to 1 files (-3 heads)
   new changesets *:* (glob)
   (run 'hg update' to get a working copy)
 
   $ hg log -T '{if(ellipsis,"...")}{node|short} {p1node|short} {p2node|short} {desc}\n' | sort
   ...0ebbd712a0c8 0d4c867aeb23 000000000000 outside 4d
   ...1be3e5221c6a 000000000000 000000000000 outside 2a
   ...33d530345455 0ce6481bfe07 000000000000 outside 4c
   ...3df233defecc 7162cc6d11a4 000000000000 outside 4b
   ...b8a3da16ba49 53f543eb8e45 000000000000 outside 4a
   ...bf545653453e 968003d40c60 000000000000 outside 8
   ...caa65c940632 000000000000 000000000000 outside 2c
   ...e932969c3961 000000000000 000000000000 outside 2d
   ...f2a632f0082d 000000000000 000000000000 outside 2b
   0ce6481bfe07 caa65c940632 000000000000 inside 2c
   0d4c867aeb23 e932969c3961 000000000000 inside 2d
   53f543eb8e45 1be3e5221c6a 000000000000 inside 2a
   67d49c0bdbda b8a3da16ba49 3df233defecc merge a/b 5
   7162cc6d11a4 f2a632f0082d 000000000000 inside 2b
   968003d40c60 67d49c0bdbda e867021d52c2 outside 6
   e867021d52c2 33d530345455 0ebbd712a0c8 merge c/d 5