dirstate-v2: Add support when Rust is not enabled

This wires into `dirstatemap` the parser and serializer added in previous
changesets. The memory representation is still the same, with a flat `dict`
for `DirstateItem`s and another one for copy sources. Serialization always
creates a new dirstate-v2 data file and does not support (when Rust is not
enabled) appending to an existing one, since we don’t keep track of which
tree nodes are new or modified. Instead the tree is reconstructed during
serialization.

Differential Revision: https://phab.mercurial-scm.org/D11520

mercurial/dirstate.py

@@ -1,1513 +1,1511 b''
 # dirstate.py - working directory tracking 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 __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import os
 import stat
 
 from .i18n import _
 from .pycompat import delattr
 
 from hgdemandimport import tracing
 
 from . import (
     dirstatemap,
     encoding,
     error,
     match as matchmod,
     pathutil,
     policy,
     pycompat,
     scmutil,
     sparse,
     util,
 )
 
 from .interfaces import (
     dirstate as intdirstate,
     util as interfaceutil,
 )
 
 parsers = policy.importmod('parsers')
 rustmod = policy.importrust('dirstate')
 
-SUPPORTS_DIRSTATE_V2 = rustmod is not None
-
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = dirstatemap.rangemask
 
 DirstateItem = dirstatemap.DirstateItem
 
 
 class repocache(filecache):
     """filecache for files in .hg/"""
 
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
 
     def join(self, obj, fname):
         return obj._join(fname)
 
 
 def _getfsnow(vfs):
     '''Get "now" timestamp on filesystem'''
     tmpfd, tmpname = vfs.mkstemp()
     try:
         return os.fstat(tmpfd)[stat.ST_MTIME]
     finally:
         os.close(tmpfd)
         vfs.unlink(tmpname)
 
 
 def requires_parents_change(func):
     def wrap(self, *args, **kwargs):
         if not self.pendingparentchange():
             msg = 'calling `%s` outside of a parentchange context'
             msg %= func.__name__
             raise error.ProgrammingError(msg)
         return func(self, *args, **kwargs)
 
     return wrap
 
 
 def requires_no_parents_change(func):
     def wrap(self, *args, **kwargs):
         if self.pendingparentchange():
             msg = 'calling `%s` inside of a parentchange context'
             msg %= func.__name__
             raise error.ProgrammingError(msg)
         return func(self, *args, **kwargs)
 
     return wrap
 
 
 @interfaceutil.implementer(intdirstate.idirstate)
 class dirstate(object):
     def __init__(
         self,
         opener,
         ui,
         root,
         validate,
         sparsematchfn,
         nodeconstants,
         use_dirstate_v2,
     ):
         """Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         """
         self._use_dirstate_v2 = use_dirstate_v2
         self._nodeconstants = nodeconstants
         self._opener = opener
         self._validate = validate
         self._root = root
         self._sparsematchfn = sparsematchfn
         # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
         # UNC path pointing to root share (issue4557)
         self._rootdir = pathutil.normasprefix(root)
         self._dirty = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
         self._parentwriters = 0
         self._filename = b'dirstate'
         self._pendingfilename = b'%s.pending' % self._filename
         self._plchangecallbacks = {}
         self._origpl = None
         self._mapcls = dirstatemap.dirstatemap
         # Access and cache cwd early, so we don't access it for the first time
         # after a working-copy update caused it to not exist (accessing it then
         # raises an exception).
         self._cwd
 
     def prefetch_parents(self):
         """make sure the parents are loaded
 
         Used to avoid a race condition.
         """
         self._pl
 
     @contextlib.contextmanager
     def parentchange(self):
         """Context manager for handling dirstate parents.
 
         If an exception occurs in the scope of the context manager,
         the incoherent dirstate won't be written when wlock is
         released.
         """
         self._parentwriters += 1
         yield
         # Typically we want the "undo" step of a context manager in a
         # finally block so it happens even when an exception
         # occurs. In this case, however, we only want to decrement
         # parentwriters if the code in the with statement exits
         # normally, so we don't have a try/finally here on purpose.
         self._parentwriters -= 1
 
     def pendingparentchange(self):
         """Returns true if the dirstate is in the middle of a set of changes
         that modify the dirstate parent.
         """
         return self._parentwriters > 0
 
     @propertycache
     def _map(self):
         """Return the dirstate contents (see documentation for dirstatemap)."""
         self._map = self._mapcls(
             self._ui,
             self._opener,
             self._root,
             self._nodeconstants,
             self._use_dirstate_v2,
         )
         return self._map
 
     @property
     def _sparsematcher(self):
         """The matcher for the sparse checkout.
 
         The working directory may not include every file from a manifest. The
         matcher obtained by this property will match a path if it is to be
         included in the working directory.
         """
         # TODO there is potential to cache this property. For now, the matcher
         # is resolved on every access. (But the called function does use a
         # cache to keep the lookup fast.)
         return self._sparsematchfn()
 
     @repocache(b'branch')
     def _branch(self):
         try:
             return self._opener.read(b"branch").strip() or b"default"
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return b"default"
 
     @property
     def _pl(self):
         return self._map.parents()
 
     def hasdir(self, d):
         return self._map.hastrackeddir(d)
 
     @rootcache(b'.hgignore')
     def _ignore(self):
         files = self._ignorefiles()
         if not files:
             return matchmod.never()
 
         pats = [b'include:%s' % f for f in files]
         return matchmod.match(self._root, b'', [], pats, warn=self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool(b'ui', b'slash') and pycompat.ossep != b'/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return bool(util.checkexec(self._root))
 
     @propertycache
     def _checkcase(self):
         return not util.fscasesensitive(self._join(b'.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
 
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return b'l'
                     if util.statisexec(st):
                         return b'x'
                 except OSError:
                     pass
                 return b''
 
             return f
 
         fallback = buildfallback()
         if self._checklink:
 
             def f(x):
                 if os.path.islink(self._join(x)):
                     return b'l'
                 if b'x' in fallback(x):
                     return b'x'
                 return b''
 
             return f
         if self._checkexec:
 
             def f(x):
                 if b'l' in fallback(x):
                     return b'l'
                 if util.isexec(self._join(x)):
                     return b'x'
                 return b''
 
             return f
         else:
             return fallback
 
     @propertycache
     def _cwd(self):
         # internal config: ui.forcecwd
         forcecwd = self._ui.config(b'ui', b'forcecwd')
         if forcecwd:
             return forcecwd
         return encoding.getcwd()
 
     def getcwd(self):
         """Return the path from which a canonical path is calculated.
 
         This path should be used to resolve file patterns or to convert
         canonical paths back to file paths for display. It shouldn't be
         used to get real file paths. Use vfs functions instead.
         """
         cwd = self._cwd
         if cwd == self._root:
             return b''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += pycompat.ossep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep) :]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.pconvert(path)
         return path
 
     def __getitem__(self, key):
         """Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
 
         XXX The "state" is a bit obscure to be in the "public" API. we should
         consider migrating all user of this to going through the dirstate entry
         instead.
         """
         msg = b"don't use dirstate[file], use dirstate.get_entry(file)"
         util.nouideprecwarn(msg, b'6.1', stacklevel=2)
         entry = self._map.get(key)
         if entry is not None:
             return entry.state
         return b'?'
 
     def get_entry(self, path):
         """return a DirstateItem for the associated path"""
         entry = self._map.get(path)
         if entry is None:
             return DirstateItem()
         return entry
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         return iter(sorted(self._map))
 
     def items(self):
         return pycompat.iteritems(self._map)
 
     iteritems = items
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     @property
     def in_merge(self):
         """True if a merge is in progress"""
         return self._pl[1] != self._nodeconstants.nullid
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=None):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, "merged" entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         if p2 is None:
             p2 = self._nodeconstants.nullid
         if self._parentwriters == 0:
             raise ValueError(
                 b"cannot set dirstate parent outside of "
                 b"dirstate.parentchange context manager"
             )
 
         self._dirty = True
         oldp2 = self._pl[1]
         if self._origpl is None:
             self._origpl = self._pl
         nullid = self._nodeconstants.nullid
         # True if we need to fold p2 related state back to a linear case
         fold_p2 = oldp2 != nullid and p2 == nullid
         return self._map.setparents(p1, p2, fold_p2=fold_p2)
 
     def setbranch(self, branch):
         self.__class__._branch.set(self, encoding.fromlocal(branch))
         f = self._opener(b'branch', b'w', atomictemp=True, checkambig=True)
         try:
             f.write(self._branch + b'\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache[b'_branch']
             if ce:
                 ce.refresh()
         except:  # re-raises
             f.discard()
             raise
 
     def invalidate(self):
         """Causes the next access to reread the dirstate.
 
         This is different from localrepo.invalidatedirstate() because it always
         rereads the dirstate. Use localrepo.invalidatedirstate() if you want to
         check whether the dirstate has changed before rereading it."""
 
         for a in ("_map", "_branch", "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
         self._parentwriters = 0
         self._origpl = None
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._map.copymap[dest] = source
         else:
             self._map.copymap.pop(dest, None)
 
     def copied(self, file):
         return self._map.copymap.get(file, None)
 
     def copies(self):
         return self._map.copymap
 
     @requires_no_parents_change
     def set_tracked(self, filename):
         """a "public" method for generic code to mark a file as tracked
 
         This function is to be called outside of "update/merge" case. For
         example by a command like `hg add X`.
 
         return True the file was previously untracked, False otherwise.
         """
         self._dirty = True
         entry = self._map.get(filename)
         if entry is None or not entry.tracked:
             self._check_new_tracked_filename(filename)
         return self._map.set_tracked(filename)
 
     @requires_no_parents_change
     def set_untracked(self, filename):
         """a "public" method for generic code to mark a file as untracked
 
         This function is to be called outside of "update/merge" case. For
         example by a command like `hg remove X`.
 
         return True the file was previously tracked, False otherwise.
         """
         ret = self._map.set_untracked(filename)
         if ret:
             self._dirty = True
         return ret
 
     @requires_no_parents_change
     def set_clean(self, filename, parentfiledata=None):
         """record that the current state of the file on disk is known to be clean"""
         self._dirty = True
         if parentfiledata:
             (mode, size, mtime) = parentfiledata
         else:
             (mode, size, mtime) = self._get_filedata(filename)
         if not self._map[filename].tracked:
             self._check_new_tracked_filename(filename)
         self._map.set_clean(filename, mode, size, mtime)
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     @requires_no_parents_change
     def set_possibly_dirty(self, filename):
         """record that the current state of the file on disk is unknown"""
         self._dirty = True
         self._map.set_possibly_dirty(filename)
 
     @requires_parents_change
     def update_file_p1(
         self,
         filename,
         p1_tracked,
     ):
         """Set a file as tracked in the parent (or not)
 
         This is to be called when adjust the dirstate to a new parent after an history
         rewriting operation.
 
         It should not be called during a merge (p2 != nullid) and only within
         a `with dirstate.parentchange():` context.
         """
         if self.in_merge:
             msg = b'update_file_reference should not be called when merging'
             raise error.ProgrammingError(msg)
         entry = self._map.get(filename)
         if entry is None:
             wc_tracked = False
         else:
             wc_tracked = entry.tracked
         if not (p1_tracked or wc_tracked):
             # the file is no longer relevant to anyone
             if self._map.get(filename) is not None:
                 self._map.reset_state(filename)
                 self._dirty = True
         elif (not p1_tracked) and wc_tracked:
             if entry is not None and entry.added:
                 return  # avoid dropping copy information (maybe?)
 
         parentfiledata = None
         if wc_tracked and p1_tracked:
             parentfiledata = self._get_filedata(filename)
 
         self._map.reset_state(
             filename,
             wc_tracked,
             p1_tracked,
             # the underlying reference might have changed, we will have to
             # check it.
             has_meaningful_mtime=False,
             parentfiledata=parentfiledata,
         )
         if (
             parentfiledata is not None
             and parentfiledata[2] > self._lastnormaltime
         ):
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = parentfiledata[2]
 
     @requires_parents_change
     def update_file(
         self,
         filename,
         wc_tracked,
         p1_tracked,
         p2_info=False,
         possibly_dirty=False,
         parentfiledata=None,
     ):
         """update the information about a file in the dirstate
 
         This is to be called when the direstates parent changes to keep track
         of what is the file situation in regards to the working copy and its parent.
 
         This function must be called within a `dirstate.parentchange` context.
 
         note: the API is at an early stage and we might need to adjust it
         depending of what information ends up being relevant and useful to
         other processing.
         """
 
         # note: I do not think we need to double check name clash here since we
         # are in a update/merge case that should already have taken care of
         # this. The test agrees
 
         self._dirty = True
 
         need_parent_file_data = (
             not possibly_dirty and not p2_info and wc_tracked and p1_tracked
         )
 
         if need_parent_file_data and parentfiledata is None:
             parentfiledata = self._get_filedata(filename)
 
         self._map.reset_state(
             filename,
             wc_tracked,
             p1_tracked,
             p2_info=p2_info,
             has_meaningful_mtime=not possibly_dirty,
             parentfiledata=parentfiledata,
         )
         if (
             parentfiledata is not None
             and parentfiledata[2] > self._lastnormaltime
         ):
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = parentfiledata[2]
 
     def _check_new_tracked_filename(self, filename):
         scmutil.checkfilename(filename)
         if self._map.hastrackeddir(filename):
             msg = _(b'directory %r already in dirstate')
             msg %= pycompat.bytestr(filename)
             raise error.Abort(msg)
         # shadows
         for d in pathutil.finddirs(filename):
             if self._map.hastrackeddir(d):
                 break
             entry = self._map.get(d)
             if entry is not None and not entry.removed:
                 msg = _(b'file %r in dirstate clashes with %r')
                 msg %= (pycompat.bytestr(d), pycompat.bytestr(filename))
                 raise error.Abort(msg)
 
     def _get_filedata(self, filename):
         """returns"""
         s = os.lstat(self._join(filename))
         mode = s.st_mode
         size = s.st_size
         mtime = s[stat.ST_MTIME]
         return (mode, size, mtime)
 
     def _discoverpath(self, path, normed, ignoremissing, exists, storemap):
         if exists is None:
             exists = os.path.lexists(os.path.join(self._root, path))
         if not exists:
             # Maybe a path component exists
             if not ignoremissing and b'/' in path:
                 d, f = path.rsplit(b'/', 1)
                 d = self._normalize(d, False, ignoremissing, None)
                 folded = d + b"/" + f
             else:
                 # No path components, preserve original case
                 folded = path
         else:
             # recursively normalize leading directory components
             # against dirstate
             if b'/' in normed:
                 d, f = normed.rsplit(b'/', 1)
                 d = self._normalize(d, False, ignoremissing, True)
                 r = self._root + b"/" + d
                 folded = d + b"/" + util.fspath(f, r)
             else:
                 folded = util.fspath(normed, self._root)
             storemap[normed] = folded
 
         return folded
 
     def _normalizefile(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 folded = self._discoverpath(
                     path, normed, ignoremissing, exists, self._map.filefoldmap
                 )
         return folded
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             folded = self._map.dirfoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 # store discovered result in dirfoldmap so that future
                 # normalizefile calls don't start matching directories
                 folded = self._discoverpath(
                     path, normed, ignoremissing, exists, self._map.dirfoldmap
                 )
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         """
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         """
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map.clear()
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         if changedfiles is None:
             # Rebuild entire dirstate
             to_lookup = allfiles
             to_drop = []
             lastnormaltime = self._lastnormaltime
             self.clear()
             self._lastnormaltime = lastnormaltime
         elif len(changedfiles) < 10:
             # Avoid turning allfiles into a set, which can be expensive if it's
             # large.
             to_lookup = []
             to_drop = []
             for f in changedfiles:
                 if f in allfiles:
                     to_lookup.append(f)
                 else:
                     to_drop.append(f)
         else:
             changedfilesset = set(changedfiles)
             to_lookup = changedfilesset & set(allfiles)
             to_drop = changedfilesset - to_lookup
 
         if self._origpl is None:
             self._origpl = self._pl
         self._map.setparents(parent, self._nodeconstants.nullid)
 
         for f in to_lookup:
 
             if self.in_merge:
                 self.set_tracked(f)
             else:
                 self._map.reset_state(
                     f,
                     wc_tracked=True,
                     p1_tracked=True,
                 )
         for f in to_drop:
             self._map.reset_state(f)
 
         self._dirty = True
 
     def identity(self):
         """Return identity of dirstate itself to detect changing in storage
 
         If identity of previous dirstate is equal to this, writing
         changes based on the former dirstate out can keep consistency.
         """
         return self._map.identity
 
     def write(self, tr):
         if not self._dirty:
             return
 
         filename = self._filename
         if tr:
             # 'dirstate.write()' is not only for writing in-memory
             # changes out, but also for dropping ambiguous timestamp.
             # delayed writing re-raise "ambiguous timestamp issue".
             # See also the wiki page below for detail:
             # https://www.mercurial-scm.org/wiki/DirstateTransactionPlan
 
             # record when mtime start to be ambiguous
             now = _getfsnow(self._opener)
 
             # delay writing in-memory changes out
             tr.addfilegenerator(
                 b'dirstate',
                 (self._filename,),
                 lambda f: self._writedirstate(tr, f, now=now),
                 location=b'plain',
             )
             return
 
         st = self._opener(filename, b"w", atomictemp=True, checkambig=True)
         self._writedirstate(tr, st)
 
     def addparentchangecallback(self, category, callback):
         """add a callback to be called when the wd parents are changed
 
         Callback will be called with the following arguments:
             dirstate, (oldp1, oldp2), (newp1, newp2)
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._plchangecallbacks[category] = callback
 
     def _writedirstate(self, tr, st, now=None):
         # notify callbacks about parents change
         if self._origpl is not None and self._origpl != self._pl:
             for c, callback in sorted(
                 pycompat.iteritems(self._plchangecallbacks)
             ):
                 callback(self, self._origpl, self._pl)
             self._origpl = None
 
         if now is None:
             # use the modification time of the newly created temporary file as the
             # filesystem's notion of 'now'
             now = util.fstat(st)[stat.ST_MTIME] & _rangemask
 
         # enough 'delaywrite' prevents 'pack_dirstate' from dropping
         # timestamp of each entries in dirstate, because of 'now > mtime'
         delaywrite = self._ui.configint(b'debug', b'dirstate.delaywrite')
         if delaywrite > 0:
             # do we have any files to delay for?
             for f, e in pycompat.iteritems(self._map):
                 if e.need_delay(now):
                     import time  # to avoid useless import
 
                     # rather than sleep n seconds, sleep until the next
                     # multiple of n seconds
                     clock = time.time()
                     start = int(clock) - (int(clock) % delaywrite)
                     end = start + delaywrite
                     time.sleep(end - clock)
                     now = end  # trust our estimate that the end is near now
                     break
 
         self._map.write(tr, st, now)
         self._lastnormaltime = 0
         self._dirty = False
 
     def _dirignore(self, f):
         if self._ignore(f):
             return True
         for p in pathutil.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def _ignorefiles(self):
         files = []
         if os.path.exists(self._join(b'.hgignore')):
             files.append(self._join(b'.hgignore'))
         for name, path in self._ui.configitems(b"ui"):
             if name == b'ignore' or name.startswith(b'ignore.'):
                 # we need to use os.path.join here rather than self._join
                 # because path is arbitrary and user-specified
                 files.append(os.path.join(self._rootdir, util.expandpath(path)))
         return files
 
     def _ignorefileandline(self, f):
         files = collections.deque(self._ignorefiles())
         visited = set()
         while files:
             i = files.popleft()
             patterns = matchmod.readpatternfile(
                 i, self._ui.warn, sourceinfo=True
             )
             for pattern, lineno, line in patterns:
                 kind, p = matchmod._patsplit(pattern, b'glob')
                 if kind == b"subinclude":
                     if p not in visited:
                         files.append(p)
                     continue
                 m = matchmod.match(
                     self._root, b'', [], [pattern], warn=self._ui.warn
                 )
                 if m(f):
                     return (i, lineno, line)
             visited.add(i)
         return (None, -1, b"")
 
     def _walkexplicit(self, match, subrepos):
         """Get stat data about the files explicitly specified by match.
 
         Return a triple (results, dirsfound, dirsnotfound).
         - results is a mapping from filename to stat result. It also contains
           listings mapping subrepos and .hg to None.
         - dirsfound is a list of files found to be directories.
         - dirsnotfound is a list of files that the dirstate thinks are
           directories and that were not found."""
 
         def badtype(mode):
             kind = _(b'unknown')
             if stat.S_ISCHR(mode):
                 kind = _(b'character device')
             elif stat.S_ISBLK(mode):
                 kind = _(b'block device')
             elif stat.S_ISFIFO(mode):
                 kind = _(b'fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _(b'socket')
             elif stat.S_ISDIR(mode):
                 kind = _(b'directory')
             return _(b'unsupported file type (type is %s)') % kind
 
         badfn = match.bad
         dmap = self._map
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         dirsfound = []
         foundadd = dirsfound.append
         dirsnotfound = []
         notfoundadd = dirsnotfound.append
 
         if not match.isexact() and self._checkcase:
             normalize = self._normalize
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + b"/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or b'' in files:
             files = [b'']
             # constructing the foldmap is expensive, so don't do it for the
             # common case where files is ['']
             normalize = None
         results = dict.fromkeys(subrepos)
         results[b'.hg'] = None
 
         for ff in files:
             if normalize:
                 nf = normalize(ff, False, True)
             else:
                 nf = ff
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     if nf in dmap:
                         # file replaced by dir on disk but still in dirstate
                         results[nf] = None
                     foundadd((nf, ff))
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError as inst:  # nf not found on disk - it is dirstate only
                 if nf in dmap:  # does it exactly match a missing file?
                     results[nf] = None
                 else:  # does it match a missing directory?
                     if self._map.hasdir(nf):
                         notfoundadd(nf)
                     else:
                         badfn(ff, encoding.strtolocal(inst.strerror))
 
         # match.files() may contain explicitly-specified paths that shouldn't
         # be taken; drop them from the list of files found. dirsfound/notfound
         # aren't filtered here because they will be tested later.
         if match.anypats():
             for f in list(results):
                 if f == b'.hg' or f in subrepos:
                     # keep sentinel to disable further out-of-repo walks
                     continue
                 if not match(f):
                     del results[f]
 
         # Case insensitive filesystems cannot rely on lstat() failing to detect
         # a case-only rename.  Prune the stat object for any file that does not
         # match the case in the filesystem, if there are multiple files that
         # normalize to the same path.
         if match.isexact() and self._checkcase:
             normed = {}
 
             for f, st in pycompat.iteritems(results):
                 if st is None:
                     continue
 
                 nc = util.normcase(f)
                 paths = normed.get(nc)
 
                 if paths is None:
                     paths = set()
                     normed[nc] = paths
 
                 paths.add(f)
 
             for norm, paths in pycompat.iteritems(normed):
                 if len(paths) > 1:
                     for path in paths:
                         folded = self._discoverpath(
                             path, norm, True, None, self._map.dirfoldmap
                         )
                         if path != folded:
                             results[path] = None
 
         return results, dirsfound, dirsnotfound
 
     def walk(self, match, subrepos, unknown, ignored, full=True):
         """
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         If full is False, maybe skip some known-clean files.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
 
         """
         # full is a flag that extensions that hook into walk can use -- this
         # implementation doesn't use it at all. This satisfies the contract
         # because we only guarantee a "maybe".
 
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif unknown:
             ignore = self._ignore
             dirignore = self._dirignore
         else:
             # if not unknown and not ignored, drop dir recursion and step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         matchtdir = match.traversedir
         dmap = self._map
         listdir = util.listdir
         lstat = os.lstat
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
 
         exact = skipstep3 = False
         if match.isexact():  # match.exact
             exact = True
             dirignore = util.always  # skip step 2
         elif match.prefix():  # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             normalizefile = self._normalizefile
             skipstep3 = False
         else:
             normalize = self._normalize
             normalizefile = None
 
         # step 1: find all explicit files
         results, work, dirsnotfound = self._walkexplicit(match, subrepos)
         if matchtdir:
             for d in work:
                 matchtdir(d[0])
             for d in dirsnotfound:
                 matchtdir(d)
 
         skipstep3 = skipstep3 and not (work or dirsnotfound)
         work = [d for d in work if not dirignore(d[0])]
 
         # step 2: visit subdirectories
         def traverse(work, alreadynormed):
             wadd = work.append
             while work:
                 tracing.counter('dirstate.walk work', len(work))
                 nd = work.pop()
                 visitentries = match.visitchildrenset(nd)
                 if not visitentries:
                     continue
                 if visitentries == b'this' or visitentries == b'all':
                     visitentries = None
                 skip = None
                 if nd != b'':
                     skip = b'.hg'
                 try:
                     with tracing.log('dirstate.walk.traverse listdir %s', nd):
                         entries = listdir(join(nd), stat=True, skip=skip)
                 except OSError as inst:
                     if inst.errno in (errno.EACCES, errno.ENOENT):
                         match.bad(
                             self.pathto(nd), encoding.strtolocal(inst.strerror)
                         )
                         continue
                     raise
                 for f, kind, st in entries:
                     # Some matchers may return files in the visitentries set,
                     # instead of 'this', if the matcher explicitly mentions them
                     # and is not an exactmatcher. This is acceptable; we do not
                     # make any hard assumptions about file-or-directory below
                     # based on the presence of `f` in visitentries. If
                     # visitchildrenset returned a set, we can always skip the
                     # entries *not* in the set it provided regardless of whether
                     # they're actually a file or a directory.
                     if visitentries and f not in visitentries:
                         continue
                     if normalizefile:
                         # even though f might be a directory, we're only
                         # interested in comparing it to files currently in the
                         # dmap -- therefore normalizefile is enough
                         nf = normalizefile(
                             nd and (nd + b"/" + f) or f, True, True
                         )
                     else:
                         nf = nd and (nd + b"/" + f) or f
                     if nf not in results:
                         if kind == dirkind:
                             if not ignore(nf):
                                 if matchtdir:
                                     matchtdir(nf)
                                 wadd(nf)
                             if nf in dmap and (matchalways or matchfn(nf)):
                                 results[nf] = None
                         elif kind == regkind or kind == lnkkind:
                             if nf in dmap:
                                 if matchalways or matchfn(nf):
                                     results[nf] = st
                             elif (matchalways or matchfn(nf)) and not ignore(
                                 nf
                             ):
                                 # unknown file -- normalize if necessary
                                 if not alreadynormed:
                                     nf = normalize(nf, False, True)
                                 results[nf] = st
                         elif nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
 
         for nd, d in work:
             # alreadynormed means that processwork doesn't have to do any
             # expensive directory normalization
             alreadynormed = not normalize or nd == d
             traverse([d], alreadynormed)
 
         for s in subrepos:
             del results[s]
         del results[b'.hg']
 
         # step 3: visit remaining files from dmap
         if not skipstep3 and not exact:
             # If a dmap file is not in results yet, it was either
             # a) not matching matchfn b) ignored, c) missing, or d) under a
             # symlink directory.
             if not results and matchalways:
                 visit = [f for f in dmap]
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked all dirs under the roots
                 # that wasn't ignored, and everything that matched was stat'ed
                 # and is already in results.
                 # The rest must thus be ignored or under a symlink.
                 audit_path = pathutil.pathauditor(self._root, cached=True)
 
                 for nf in iter(visit):
                     # If a stat for the same file was already added with a
                     # different case, don't add one for this, since that would
                     # make it appear as if the file exists under both names
                     # on disk.
                     if (
                         normalizefile
                         and normalizefile(nf, True, True) in results
                     ):
                         results[nf] = None
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     elif audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                             # file was just ignored, no links, and exists
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         # which we in this case report as missing
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat and check everything we missed.
                 iv = iter(visit)
                 for st in util.statfiles([join(i) for i in visit]):
                     results[next(iv)] = st
         return results
 
     def _rust_status(self, matcher, list_clean, list_ignored, list_unknown):
         # Force Rayon (Rust parallelism library) to respect the number of
         # workers. This is a temporary workaround until Rust code knows
         # how to read the config file.
         numcpus = self._ui.configint(b"worker", b"numcpus")
         if numcpus is not None:
             encoding.environ.setdefault(b'RAYON_NUM_THREADS', b'%d' % numcpus)
 
         workers_enabled = self._ui.configbool(b"worker", b"enabled", True)
         if not workers_enabled:
             encoding.environ[b"RAYON_NUM_THREADS"] = b"1"
 
         (
             lookup,
             modified,
             added,
             removed,
             deleted,
             clean,
             ignored,
             unknown,
             warnings,
             bad,
             traversed,
             dirty,
         ) = rustmod.status(
             self._map._map,
             matcher,
             self._rootdir,
             self._ignorefiles(),
             self._checkexec,
             self._lastnormaltime,
             bool(list_clean),
             bool(list_ignored),
             bool(list_unknown),
             bool(matcher.traversedir),
         )
 
         self._dirty |= dirty
 
         if matcher.traversedir:
             for dir in traversed:
                 matcher.traversedir(dir)
 
         if self._ui.warn:
             for item in warnings:
                 if isinstance(item, tuple):
                     file_path, syntax = item
                     msg = _(b"%s: ignoring invalid syntax '%s'\n") % (
                         file_path,
                         syntax,
                     )
                     self._ui.warn(msg)
                 else:
                     msg = _(b"skipping unreadable pattern file '%s': %s\n")
                     self._ui.warn(
                         msg
                         % (
                             pathutil.canonpath(
                                 self._rootdir, self._rootdir, item
                             ),
                             b"No such file or directory",
                         )
                     )
 
         for (fn, message) in bad:
             matcher.bad(fn, encoding.strtolocal(message))
 
         status = scmutil.status(
             modified=modified,
             added=added,
             removed=removed,
             deleted=deleted,
             unknown=unknown,
             ignored=ignored,
             clean=clean,
         )
         return (lookup, status)
 
     def status(self, match, subrepos, ignored, clean, unknown):
         """Determine the status of the working copy relative to the
         dirstate and return a pair of (unsure, status), where status is of type
         scmutil.status and:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           status.modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           status.clean:
             files that have definitely not been modified since the
             dirstate was written
         """
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         dmap.preload()
 
         use_rust = True
 
         allowed_matchers = (
             matchmod.alwaysmatcher,
             matchmod.exactmatcher,
             matchmod.includematcher,
         )
 
         if rustmod is None:
             use_rust = False
         elif self._checkcase:
             # Case-insensitive filesystems are not handled yet
             use_rust = False
         elif subrepos:
             use_rust = False
         elif sparse.enabled:
             use_rust = False
         elif not isinstance(match, allowed_matchers):
             # Some matchers have yet to be implemented
             use_rust = False
 
         if use_rust:
             try:
                 return self._rust_status(
                     match, listclean, listignored, listunknown
                 )
             except rustmod.FallbackError:
                 pass
 
         def noop(f):
             pass
 
         dcontains = dmap.__contains__
         dget = dmap.__getitem__
         ladd = lookup.append  # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append if listunknown else noop
         iadd = ignored.append if listignored else noop
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append if listclean else noop
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         copymap = self._map.copymap
         lastnormaltime = self._lastnormaltime
 
         # We need to do full walks when either
         # - we're listing all clean files, or
         # - match.traversedir does something, because match.traversedir should
         #   be called for every dir in the working dir
         full = listclean or match.traversedir is not None
         for fn, st in pycompat.iteritems(
             self.walk(match, subrepos, listunknown, listignored, full=full)
         ):
             if not dcontains(fn):
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 else:
                     uadd(fn)
                 continue
 
             # This is equivalent to 'state, mode, size, time = dmap[fn]' but not
             # written like that for performance reasons. dmap[fn] is not a
             # Python tuple in compiled builds. The CPython UNPACK_SEQUENCE
             # opcode has fast paths when the value to be unpacked is a tuple or
             # a list, but falls back to creating a full-fledged iterator in
             # general. That is much slower than simply accessing and storing the
             # tuple members one by one.
             t = dget(fn)
             mode = t.mode
             size = t.size
             time = t.mtime
 
             if not st and t.tracked:
                 dadd(fn)
             elif t.p2_info:
                 madd(fn)
             elif t.added:
                 aadd(fn)
             elif t.removed:
                 radd(fn)
             elif t.tracked:
                 if (
                     size >= 0
                     and (
                         (size != st.st_size and size != st.st_size & _rangemask)
                         or ((mode ^ st.st_mode) & 0o100 and checkexec)
                     )
                     or fn in copymap
                 ):
                     if stat.S_ISLNK(st.st_mode) and size != st.st_size:
                         # issue6456: Size returned may be longer due to
                         # encryption on EXT-4 fscrypt, undecided.
                         ladd(fn)
                     else:
                         madd(fn)
                 elif (
                     time != st[stat.ST_MTIME]
                     and time != st[stat.ST_MTIME] & _rangemask
                 ):
                     ladd(fn)
                 elif st[stat.ST_MTIME] == lastnormaltime:
                     # fn may have just been marked as normal and it may have
                     # changed in the same second without changing its size.
                     # This can happen if we quickly do multiple commits.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
         status = scmutil.status(
             modified, added, removed, deleted, unknown, ignored, clean
         )
         return (lookup, status)
 
     def matches(self, match):
         """
         return files in the dirstate (in whatever state) filtered by match
         """
         dmap = self._map
         if rustmod is not None:
             dmap = self._map._map
 
         if match.always():
             return dmap.keys()
         files = match.files()
         if match.isexact():
             # fast path -- filter the other way around, since typically files is
             # much smaller than dmap
             return [f for f in files if f in dmap]
         if match.prefix() and all(fn in dmap for fn in files):
             # fast path -- all the values are known to be files, so just return
             # that
             return list(files)
         return [f for f in dmap if match(f)]
 
     def _actualfilename(self, tr):
         if tr:
             return self._pendingfilename
         else:
             return self._filename
 
     def savebackup(self, tr, backupname):
         '''Save current dirstate into backup file'''
         filename = self._actualfilename(tr)
         assert backupname != filename
 
         # use '_writedirstate' instead of 'write' to write changes certainly,
         # because the latter omits writing out if transaction is running.
         # output file will be used to create backup of dirstate at this point.
         if self._dirty or not self._opener.exists(filename):
             self._writedirstate(
                 tr,
                 self._opener(filename, b"w", atomictemp=True, checkambig=True),
             )
 
         if tr:
             # ensure that subsequent tr.writepending returns True for
             # changes written out above, even if dirstate is never
             # changed after this
             tr.addfilegenerator(
                 b'dirstate',
                 (self._filename,),
                 lambda f: self._writedirstate(tr, f),
                 location=b'plain',
             )
 
             # ensure that pending file written above is unlinked at
             # failure, even if tr.writepending isn't invoked until the
             # end of this transaction
             tr.registertmp(filename, location=b'plain')
 
         self._opener.tryunlink(backupname)
         # hardlink backup is okay because _writedirstate is always called
         # with an "atomictemp=True" file.
         util.copyfile(
             self._opener.join(filename),
             self._opener.join(backupname),
             hardlink=True,
         )
 
     def restorebackup(self, tr, backupname):
         '''Restore dirstate by backup file'''
         # this "invalidate()" prevents "wlock.release()" from writing
         # changes of dirstate out after restoring from backup file
         self.invalidate()
         filename = self._actualfilename(tr)
         o = self._opener
         if util.samefile(o.join(backupname), o.join(filename)):
             o.unlink(backupname)
         else:
             o.rename(backupname, filename, checkambig=True)
 
     def clearbackup(self, tr, backupname):
         '''Clear backup file'''
         self._opener.unlink(backupname)
 
     def verify(self, m1, m2):
         """check the dirstate content again the parent manifest and yield errors"""
         missing_from_p1 = b"%s in state %s, but not in manifest1\n"
         unexpected_in_p1 = b"%s in state %s, but also in manifest1\n"
         missing_from_ps = b"%s in state %s, but not in either manifest\n"
         missing_from_ds = b"%s in manifest1, but listed as state %s\n"
         for f, entry in self.items():
             state = entry.state
             if state in b"nr" and f not in m1:
                 yield (missing_from_p1, f, state)
             if state in b"a" and f in m1:
                 yield (unexpected_in_p1, f, state)
             if state in b"m" and f not in m1 and f not in m2:
                 yield (missing_from_ps, f, state)
         for f in m1:
             state = self.get_entry(f).state
             if state not in b"nrm":
                 yield (missing_from_ds, f, state)

mercurial/dirstatemap.py

@@ -1,732 +1,733 b''
 # dirstatemap.py
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 
 from .i18n import _
 
 from . import (
     error,
     pathutil,
     policy,
     pycompat,
     txnutil,
     util,
 )
 
 from .dirstateutils import (
     docket as docketmod,
     v2,
 )
 
 parsers = policy.importmod('parsers')
 rustmod = policy.importrust('dirstate')
 
 propertycache = util.propertycache
 
 if rustmod is None:
     DirstateItem = parsers.DirstateItem
 else:
     DirstateItem = rustmod.DirstateItem
 
 rangemask = 0x7FFFFFFF
 
 
 class _dirstatemapcommon(object):
     """
     Methods that are identical for both implementations of the dirstatemap
     class, with and without Rust extensions enabled.
     """
 
     # please pytype
 
     _map = None
     copymap = None
 
     def __init__(self, ui, opener, root, nodeconstants, use_dirstate_v2):
         self._use_dirstate_v2 = use_dirstate_v2
         self._nodeconstants = nodeconstants
         self._ui = ui
         self._opener = opener
         self._root = root
         self._filename = b'dirstate'
         self._nodelen = 20  # Also update Rust code when changing this!
         self._parents = None
         self._dirtyparents = False
         self._docket = None
 
         # for consistent view between _pl() and _read() invocations
         self._pendingmode = None
 
     def preload(self):
         """Loads the underlying data, if it's not already loaded"""
         self._map
 
     def get(self, key, default=None):
         return self._map.get(key, default)
 
     def __len__(self):
         return len(self._map)
 
     def __iter__(self):
         return iter(self._map)
 
     def __contains__(self, key):
         return key in self._map
 
     def __getitem__(self, item):
         return self._map[item]
 
     ### sub-class utility method
     #
     # Use to allow for generic implementation of some method while still coping
     # with minor difference between implementation.
 
     def _dirs_incr(self, filename, old_entry=None):
         """incremente the dirstate counter if applicable
 
         This might be a no-op for some subclass who deal with directory
         tracking in a different way.
         """
 
     def _dirs_decr(self, filename, old_entry=None, remove_variant=False):
         """decremente the dirstate counter if applicable
 
         This might be a no-op for some subclass who deal with directory
         tracking in a different way.
         """
 
     def _refresh_entry(self, f, entry):
         """record updated state of an entry"""
 
     def _insert_entry(self, f, entry):
         """add a new dirstate entry (or replace an unrelated one)
 
         The fact it is actually new is the responsability of the caller
         """
 
     def _drop_entry(self, f):
         """remove any entry for file f
 
         This should also drop associated copy information
 
         The fact we actually need to drop it is the responsability of the caller"""
 
     ### method to manipulate the entries
 
     def set_possibly_dirty(self, filename):
         """record that the current state of the file on disk is unknown"""
         entry = self[filename]
         entry.set_possibly_dirty()
         self._refresh_entry(filename, entry)
 
     def set_clean(self, filename, mode, size, mtime):
         """mark a file as back to a clean state"""
         entry = self[filename]
         mtime = mtime & rangemask
         size = size & rangemask
         entry.set_clean(mode, size, mtime)
         self._refresh_entry(filename, entry)
         self.copymap.pop(filename, None)
 
     def set_tracked(self, filename):
         new = False
         entry = self.get(filename)
         if entry is None:
             self._dirs_incr(filename)
             entry = DirstateItem(
                 wc_tracked=True,
             )
 
             self._insert_entry(filename, entry)
             new = True
         elif not entry.tracked:
             self._dirs_incr(filename, entry)
             entry.set_tracked()
             self._refresh_entry(filename, entry)
             new = True
         else:
             # XXX This is probably overkill for more case, but we need this to
             # fully replace the `normallookup` call with `set_tracked` one.
             # Consider smoothing this in the future.
             entry.set_possibly_dirty()
             self._refresh_entry(filename, entry)
         return new
 
     def set_untracked(self, f):
         """Mark a file as no longer tracked in the dirstate map"""
         entry = self.get(f)
         if entry is None:
             return False
         else:
             self._dirs_decr(f, old_entry=entry, remove_variant=not entry.added)
             if not entry.p2_info:
                 self.copymap.pop(f, None)
             entry.set_untracked()
             self._refresh_entry(f, entry)
             return True
 
     def reset_state(
         self,
         filename,
         wc_tracked=False,
         p1_tracked=False,
         p2_info=False,
         has_meaningful_mtime=True,
         has_meaningful_data=True,
         parentfiledata=None,
     ):
         """Set a entry to a given state, diregarding all previous state
 
         This is to be used by the part of the dirstate API dedicated to
         adjusting the dirstate after a update/merge.
 
         note: calling this might result to no entry existing at all if the
         dirstate map does not see any point at having one for this file
         anymore.
         """
         # copy information are now outdated
         # (maybe new information should be in directly passed to this function)
         self.copymap.pop(filename, None)
 
         if not (p1_tracked or p2_info or wc_tracked):
             old_entry = self._map.get(filename)
             self._drop_entry(filename)
             self._dirs_decr(filename, old_entry=old_entry)
             return
 
         old_entry = self._map.get(filename)
         self._dirs_incr(filename, old_entry)
         entry = DirstateItem(
             wc_tracked=wc_tracked,
             p1_tracked=p1_tracked,
             p2_info=p2_info,
             has_meaningful_mtime=has_meaningful_mtime,
             parentfiledata=parentfiledata,
         )
         self._insert_entry(filename, entry)
 
     ### disk interaction
 
     def _opendirstatefile(self):
         fp, mode = txnutil.trypending(self._root, self._opener, self._filename)
         if self._pendingmode is not None and self._pendingmode != mode:
             fp.close()
             raise error.Abort(
                 _(b'working directory state may be changed parallelly')
             )
         self._pendingmode = mode
         return fp
 
     def _readdirstatefile(self, size=-1):
         try:
             with self._opendirstatefile() as fp:
                 return fp.read(size)
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             # File doesn't exist, so the current state is empty
             return b''
 
     @property
     def docket(self):
         if not self._docket:
             if not self._use_dirstate_v2:
                 raise error.ProgrammingError(
                     b'dirstate only has a docket in v2 format'
                 )
             self._docket = docketmod.DirstateDocket.parse(
                 self._readdirstatefile(), self._nodeconstants
             )
         return self._docket
 
     def write_v2_no_append(self, tr, st, meta, packed):
         old_docket = self.docket
         new_docket = docketmod.DirstateDocket.with_new_uuid(
             self.parents(), len(packed), meta
         )
         data_filename = new_docket.data_filename()
         if tr:
             tr.add(data_filename, 0)
         self._opener.write(data_filename, packed)
         # Write the new docket after the new data file has been
         # written. Because `st` was opened with `atomictemp=True`,
         # the actual `.hg/dirstate` file is only affected on close.
         st.write(new_docket.serialize())
         st.close()
         # Remove the old data file after the new docket pointing to
         # the new data file was written.
         if old_docket.uuid:
             data_filename = old_docket.data_filename()
             unlink = lambda _tr=None: self._opener.unlink(data_filename)
             if tr:
                 category = b"dirstate-v2-clean-" + old_docket.uuid
                 tr.addpostclose(category, unlink)
             else:
                 unlink()
         self._docket = new_docket
 
     ### reading/setting parents
 
     def parents(self):
         if not self._parents:
             if self._use_dirstate_v2:
                 self._parents = self.docket.parents
             else:
                 read_len = self._nodelen * 2
                 st = self._readdirstatefile(read_len)
                 l = len(st)
                 if l == read_len:
                     self._parents = (
                         st[: self._nodelen],
                         st[self._nodelen : 2 * self._nodelen],
                     )
                 elif l == 0:
                     self._parents = (
                         self._nodeconstants.nullid,
                         self._nodeconstants.nullid,
                     )
                 else:
                     raise error.Abort(
                         _(b'working directory state appears damaged!')
                     )
 
         return self._parents
 
 
 class dirstatemap(_dirstatemapcommon):
     """Map encapsulating the dirstate's contents.
 
     The dirstate contains the following state:
 
     - `identity` is the identity of the dirstate file, which can be used to
       detect when changes have occurred to the dirstate file.
 
     - `parents` is a pair containing the parents of the working copy. The
       parents are updated by calling `setparents`.
 
     - the state map maps filenames to tuples of (state, mode, size, mtime),
       where state is a single character representing 'normal', 'added',
       'removed', or 'merged'. It is read by treating the dirstate as a
       dict.  File state is updated by calling various methods (see each
       documentation for details):
 
       - `reset_state`,
       - `set_tracked`
       - `set_untracked`
       - `set_clean`
       - `set_possibly_dirty`
 
     - `copymap` maps destination filenames to their source filename.
 
     The dirstate also provides the following views onto the state:
 
     - `filefoldmap` is a dict mapping normalized filenames to the denormalized
       form that they appear as in the dirstate.
 
     - `dirfoldmap` is a dict mapping normalized directory names to the
       denormalized form that they appear as in the dirstate.
     """
 
-    def __init__(self, ui, opener, root, nodeconstants, use_dirstate_v2):
-        super(dirstatemap, self).__init__(
-            ui, opener, root, nodeconstants, use_dirstate_v2
-        )
-        if self._use_dirstate_v2:
-            msg = "Dirstate V2 not supportedi"
-            msg += "(should have detected unsupported requirement)"
-            raise error.ProgrammingError(msg)
-
     ### Core data storage and access
 
     @propertycache
     def _map(self):
         self._map = {}
         self.read()
         return self._map
 
     @propertycache
     def copymap(self):
         self.copymap = {}
         self._map
         return self.copymap
 
     def clear(self):
         self._map.clear()
         self.copymap.clear()
         self.setparents(self._nodeconstants.nullid, self._nodeconstants.nullid)
         util.clearcachedproperty(self, b"_dirs")
         util.clearcachedproperty(self, b"_alldirs")
         util.clearcachedproperty(self, b"filefoldmap")
         util.clearcachedproperty(self, b"dirfoldmap")
 
     def items(self):
         return pycompat.iteritems(self._map)
 
     # forward for python2,3 compat
     iteritems = items
 
     def debug_iter(self, all):
         """
         Return an iterator of (filename, state, mode, size, mtime) tuples
 
         `all` is unused when Rust is not enabled
         """
         for (filename, item) in self.items():
             yield (filename, item.state, item.mode, item.size, item.mtime)
 
     def keys(self):
         return self._map.keys()
 
     ### reading/setting parents
 
     def setparents(self, p1, p2, fold_p2=False):
         self._parents = (p1, p2)
         self._dirtyparents = True
         copies = {}
         if fold_p2:
             for f, s in pycompat.iteritems(self._map):
                 # Discard "merged" markers when moving away from a merge state
                 if s.p2_info:
                     source = self.copymap.pop(f, None)
                     if source:
                         copies[f] = source
                     s.drop_merge_data()
         return copies
 
     ### disk interaction
 
     def read(self):
         # ignore HG_PENDING because identity is used only for writing
         self.identity = util.filestat.frompath(
             self._opener.join(self._filename)
         )
 
-        try:
-            fp = self._opendirstatefile()
-            try:
-                st = fp.read()
-            finally:
-                fp.close()
-        except IOError as err:
-            if err.errno != errno.ENOENT:
-                raise
-            return
+        if self._use_dirstate_v2:
+            if not self.docket.uuid:
+                return
+            st = self._opener.read(self.docket.data_filename())
+        else:
+            st = self._readdirstatefile()
+
         if not st:
             return
 
+        # TODO: adjust this estimate for dirstate-v2
         if util.safehasattr(parsers, b'dict_new_presized'):
             # Make an estimate of the number of files in the dirstate based on
             # its size. This trades wasting some memory for avoiding costly
             # resizes. Each entry have a prefix of 17 bytes followed by one or
             # two path names. Studies on various large-scale real-world repositories
             # found 54 bytes a reasonable upper limit for the average path names.
             # Copy entries are ignored for the sake of this estimate.
             self._map = parsers.dict_new_presized(len(st) // 71)
 
         # Python's garbage collector triggers a GC each time a certain number
         # of container objects (the number being defined by
         # gc.get_threshold()) are allocated. parse_dirstate creates a tuple
         # for each file in the dirstate. The C version then immediately marks
         # them as not to be tracked by the collector. However, this has no
         # effect on when GCs are triggered, only on what objects the GC looks
         # into. This means that O(number of files) GCs are unavoidable.
         # Depending on when in the process's lifetime the dirstate is parsed,
         # this can get very expensive. As a workaround, disable GC while
         # parsing the dirstate.
         #
         # (we cannot decorate the function directly since it is in a C module)
-        parse_dirstate = util.nogc(parsers.parse_dirstate)
-        p = parse_dirstate(self._map, self.copymap, st)
+        if self._use_dirstate_v2:
+            p = self.docket.parents
+            meta = self.docket.tree_metadata
+            parse_dirstate = util.nogc(v2.parse_dirstate)
+            parse_dirstate(self._map, self.copymap, st, meta)
+        else:
+            parse_dirstate = util.nogc(parsers.parse_dirstate)
+            p = parse_dirstate(self._map, self.copymap, st)
         if not self._dirtyparents:
             self.setparents(*p)
 
         # Avoid excess attribute lookups by fast pathing certain checks
         self.__contains__ = self._map.__contains__
         self.__getitem__ = self._map.__getitem__
         self.get = self._map.get
 
-    def write(self, _tr, st, now):
-        d = parsers.pack_dirstate(self._map, self.copymap, self.parents(), now)
-        st.write(d)
-        st.close()
+    def write(self, tr, st, now):
+        if self._use_dirstate_v2:
+            packed, meta = v2.pack_dirstate(self._map, self.copymap, now)
+            self.write_v2_no_append(tr, st, meta, packed)
+        else:
+            packed = parsers.pack_dirstate(
+                self._map, self.copymap, self.parents(), now
+            )
+            st.write(packed)
+            st.close()
         self._dirtyparents = False
 
     @propertycache
     def identity(self):
         self._map
         return self.identity
 
     ### code related to maintaining and accessing "extra" property
     # (e.g. "has_dir")
 
     def _dirs_incr(self, filename, old_entry=None):
         """incremente the dirstate counter if applicable"""
         if (
             old_entry is None or old_entry.removed
         ) and "_dirs" in self.__dict__:
             self._dirs.addpath(filename)
         if old_entry is None and "_alldirs" in self.__dict__:
             self._alldirs.addpath(filename)
 
     def _dirs_decr(self, filename, old_entry=None, remove_variant=False):
         """decremente the dirstate counter if applicable"""
         if old_entry is not None:
             if "_dirs" in self.__dict__ and not old_entry.removed:
                 self._dirs.delpath(filename)
             if "_alldirs" in self.__dict__ and not remove_variant:
                 self._alldirs.delpath(filename)
         elif remove_variant and "_alldirs" in self.__dict__:
             self._alldirs.addpath(filename)
         if "filefoldmap" in self.__dict__:
             normed = util.normcase(filename)
             self.filefoldmap.pop(normed, None)
 
     @propertycache
     def filefoldmap(self):
         """Returns a dictionary mapping normalized case paths to their
         non-normalized versions.
         """
         try:
             makefilefoldmap = parsers.make_file_foldmap
         except AttributeError:
             pass
         else:
             return makefilefoldmap(
                 self._map, util.normcasespec, util.normcasefallback
             )
 
         f = {}
         normcase = util.normcase
         for name, s in pycompat.iteritems(self._map):
             if not s.removed:
                 f[normcase(name)] = name
         f[b'.'] = b'.'  # prevents useless util.fspath() invocation
         return f
 
     @propertycache
     def dirfoldmap(self):
         f = {}
         normcase = util.normcase
         for name in self._dirs:
             f[normcase(name)] = name
         return f
 
     def hastrackeddir(self, d):
         """
         Returns True if the dirstate contains a tracked (not removed) file
         in this directory.
         """
         return d in self._dirs
 
     def hasdir(self, d):
         """
         Returns True if the dirstate contains a file (tracked or removed)
         in this directory.
         """
         return d in self._alldirs
 
     @propertycache
     def _dirs(self):
         return pathutil.dirs(self._map, only_tracked=True)
 
     @propertycache
     def _alldirs(self):
         return pathutil.dirs(self._map)
 
     ### code related to manipulation of entries and copy-sources
 
     def _refresh_entry(self, f, entry):
         if not entry.any_tracked:
             self._map.pop(f, None)
 
     def _insert_entry(self, f, entry):
         self._map[f] = entry
 
     def _drop_entry(self, f):
         self._map.pop(f, None)
         self.copymap.pop(f, None)
 
 
 if rustmod is not None:
 
     class dirstatemap(_dirstatemapcommon):
 
         ### Core data storage and access
 
         @propertycache
         def _map(self):
             """
             Fills the Dirstatemap when called.
             """
             # ignore HG_PENDING because identity is used only for writing
             self.identity = util.filestat.frompath(
                 self._opener.join(self._filename)
             )
 
             if self._use_dirstate_v2:
                 if self.docket.uuid:
                     # TODO: use mmap when possible
                     data = self._opener.read(self.docket.data_filename())
                 else:
                     data = b''
                 self._map = rustmod.DirstateMap.new_v2(
                     data, self.docket.data_size, self.docket.tree_metadata
                 )
                 parents = self.docket.parents
             else:
                 self._map, parents = rustmod.DirstateMap.new_v1(
                     self._readdirstatefile()
                 )
 
             if parents and not self._dirtyparents:
                 self.setparents(*parents)
 
             self.__contains__ = self._map.__contains__
             self.__getitem__ = self._map.__getitem__
             self.get = self._map.get
             return self._map
 
         @property
         def copymap(self):
             return self._map.copymap()
 
         def debug_iter(self, all):
             """
             Return an iterator of (filename, state, mode, size, mtime) tuples
 
             `all`: also include with `state == b' '` dirstate tree nodes that
             don't have an associated `DirstateItem`.
 
             """
             return self._map.debug_iter(all)
 
         def clear(self):
             self._map.clear()
             self.setparents(
                 self._nodeconstants.nullid, self._nodeconstants.nullid
             )
             util.clearcachedproperty(self, b"_dirs")
             util.clearcachedproperty(self, b"_alldirs")
             util.clearcachedproperty(self, b"dirfoldmap")
 
         def items(self):
             return self._map.items()
 
         # forward for python2,3 compat
         iteritems = items
 
         def keys(self):
             return iter(self._map)
 
         ### reading/setting parents
 
         def setparents(self, p1, p2, fold_p2=False):
             self._parents = (p1, p2)
             self._dirtyparents = True
             copies = {}
             if fold_p2:
                 # Collect into an intermediate list to avoid a `RuntimeError`
                 # exception due to mutation during iteration.
                 # TODO: move this the whole loop to Rust where `iter_mut`
                 # enables in-place mutation of elements of a collection while
                 # iterating it, without mutating the collection itself.
                 files_with_p2_info = [
                     f for f, s in self._map.items() if s.p2_info
                 ]
                 rust_map = self._map
                 for f in files_with_p2_info:
                     e = rust_map.get(f)
                     source = self.copymap.pop(f, None)
                     if source:
                         copies[f] = source
                     e.drop_merge_data()
                     rust_map.set_dirstate_item(f, e)
             return copies
 
         ### disk interaction
 
         @propertycache
         def identity(self):
             self._map
             return self.identity
 
         def write(self, tr, st, now):
             if not self._use_dirstate_v2:
                 p1, p2 = self.parents()
                 packed = self._map.write_v1(p1, p2, now)
                 st.write(packed)
                 st.close()
                 self._dirtyparents = False
                 return
 
             # We can only append to an existing data file if there is one
             can_append = self.docket.uuid is not None
             packed, meta, append = self._map.write_v2(now, can_append)
             if append:
                 docket = self.docket
                 data_filename = docket.data_filename()
                 if tr:
                     tr.add(data_filename, docket.data_size)
                 with self._opener(data_filename, b'r+b') as fp:
                     fp.seek(docket.data_size)
                     assert fp.tell() == docket.data_size
                     written = fp.write(packed)
                     if written is not None:  # py2 may return None
                         assert written == len(packed), (written, len(packed))
                 docket.data_size += len(packed)
                 docket.parents = self.parents()
                 docket.tree_metadata = meta
                 st.write(docket.serialize())
                 st.close()
             else:
                 self.write_v2_no_append(tr, st, meta, packed)
             # Reload from the newly-written file
             util.clearcachedproperty(self, b"_map")
             self._dirtyparents = False
 
         ### code related to maintaining and accessing "extra" property
         # (e.g. "has_dir")
 
         @propertycache
         def filefoldmap(self):
             """Returns a dictionary mapping normalized case paths to their
             non-normalized versions.
             """
             return self._map.filefoldmapasdict()
 
         def hastrackeddir(self, d):
             return self._map.hastrackeddir(d)
 
         def hasdir(self, d):
             return self._map.hasdir(d)
 
         @propertycache
         def dirfoldmap(self):
             f = {}
             normcase = util.normcase
             for name in self._map.tracked_dirs():
                 f[normcase(name)] = name
             return f
 
         ### code related to manipulation of entries and copy-sources
 
         def _refresh_entry(self, f, entry):
             if not entry.any_tracked:
                 self._map.drop_item_and_copy_source(f)
             else:
                 self._map.addfile(f, entry)
 
         def _insert_entry(self, f, entry):
             self._map.addfile(f, entry)
 
         def _drop_entry(self, f):
             self._map.drop_item_and_copy_source(f)
 
         def __setitem__(self, key, value):
             assert isinstance(value, DirstateItem)
             self._map.set_dirstate_item(key, value)

mercurial/localrepo.py

@@ -1,3881 +1,3871 b''
 # localrepo.py - read/write repository 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 __future__ import absolute_import
 
 import errno
 import functools
 import os
 import random
 import sys
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
 )
 from .pycompat import (
     delattr,
     getattr,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     bundlecaches,
     changegroup,
     color,
     commit,
     context,
     dirstate,
     dirstateguard,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     match as matchmod,
     mergestate as mergestatemod,
     mergeutil,
     namespaces,
     narrowspec,
     obsolete,
     pathutil,
     phases,
     pushkey,
     pycompat,
     rcutil,
     repoview,
     requirements as requirementsmod,
     revlog,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store as storemod,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
     wireprototypes,
 )
 
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 
 from .utils import (
     hashutil,
     procutil,
     stringutil,
     urlutil,
 )
 
 from .revlogutils import (
     concurrency_checker as revlogchecker,
     constants as revlogconst,
     sidedata as sidedatamod,
 )
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # set of (path, vfs-location) tuples. vfs-location is:
 # - 'plain for vfs relative paths
 # - '' for svfs relative paths
 _cachedfiles = set()
 
 
 class _basefilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered"""
 
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         # proxy to unfiltered __dict__ since filtered repo has no entry
         unfi = repo.unfiltered()
         try:
             return unfi.__dict__[self.sname]
         except KeyError:
             pass
         return super(_basefilecache, self).__get__(unfi, type)
 
     def set(self, repo, value):
         return super(_basefilecache, self).set(repo.unfiltered(), value)
 
 
 class repofilecache(_basefilecache):
     """filecache for files in .hg but outside of .hg/store"""
 
     def __init__(self, *paths):
         super(repofilecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, b'plain'))
 
     def join(self, obj, fname):
         return obj.vfs.join(fname)
 
 
 class storecache(_basefilecache):
     """filecache for files in the store"""
 
     def __init__(self, *paths):
         super(storecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, b''))
 
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 
 class changelogcache(storecache):
     """filecache for the changelog"""
 
     def __init__(self):
         super(changelogcache, self).__init__()
         _cachedfiles.add((b'00changelog.i', b''))
         _cachedfiles.add((b'00changelog.n', b''))
 
     def tracked_paths(self, obj):
         paths = [self.join(obj, b'00changelog.i')]
         if obj.store.opener.options.get(b'persistent-nodemap', False):
             paths.append(self.join(obj, b'00changelog.n'))
         return paths
 
 
 class manifestlogcache(storecache):
     """filecache for the manifestlog"""
 
     def __init__(self):
         super(manifestlogcache, self).__init__()
         _cachedfiles.add((b'00manifest.i', b''))
         _cachedfiles.add((b'00manifest.n', b''))
 
     def tracked_paths(self, obj):
         paths = [self.join(obj, b'00manifest.i')]
         if obj.store.opener.options.get(b'persistent-nodemap', False):
             paths.append(self.join(obj, b'00manifest.n'))
         return paths
 
 
 class mixedrepostorecache(_basefilecache):
     """filecache for a mix files in .hg/store and outside"""
 
     def __init__(self, *pathsandlocations):
         # scmutil.filecache only uses the path for passing back into our
         # join(), so we can safely pass a list of paths and locations
         super(mixedrepostorecache, self).__init__(*pathsandlocations)
         _cachedfiles.update(pathsandlocations)
 
     def join(self, obj, fnameandlocation):
         fname, location = fnameandlocation
         if location == b'plain':
             return obj.vfs.join(fname)
         else:
             if location != b'':
                 raise error.ProgrammingError(
                     b'unexpected location: %s' % location
                 )
             return obj.sjoin(fname)
 
 
 def isfilecached(repo, name):
     """check if a repo has already cached "name" filecache-ed property
 
     This returns (cachedobj-or-None, iscached) tuple.
     """
     cacheentry = repo.unfiltered()._filecache.get(name, None)
     if not cacheentry:
         return None, False
     return cacheentry.obj, True
 
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
 
     @functools.wraps(orig)
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
 
     return wrapper
 
 
 moderncaps = {
     b'lookup',
     b'branchmap',
     b'pushkey',
     b'known',
     b'getbundle',
     b'unbundle',
 }
 legacycaps = moderncaps.union({b'changegroupsubset'})
 
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class localcommandexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError(
                 b'callcommand() cannot be used after sendcommands()'
             )
 
         if self._closed:
             raise error.ProgrammingError(
                 b'callcommand() cannot be used after close()'
             )
 
         # We don't need to support anything fancy. Just call the named
         # method on the peer and return a resolved future.
         fn = getattr(self._peer, pycompat.sysstr(command))
 
         f = pycompat.futures.Future()
 
         try:
             result = fn(**pycompat.strkwargs(args))
         except Exception:
             pycompat.future_set_exception_info(f, sys.exc_info()[1:])
         else:
             f.set_result(result)
 
         return f
 
     def sendcommands(self):
         self._sent = True
 
     def close(self):
         self._closed = True
 
 
 @interfaceutil.implementer(repository.ipeercommands)
 class localpeer(repository.peer):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=None):
         super(localpeer, self).__init__()
 
         if caps is None:
             caps = moderncaps.copy()
         self._repo = repo.filtered(b'served')
         self.ui = repo.ui
 
         if repo._wanted_sidedata:
             formatted = bundle2.format_remote_wanted_sidedata(repo)
             caps.add(b'exp-wanted-sidedata=' + formatted)
 
         self._caps = repo._restrictcapabilities(caps)
 
     # Begin of _basepeer interface.
 
     def url(self):
         return self._repo.url()
 
     def local(self):
         return self._repo
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         self._repo.close()
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def capabilities(self):
         return self._caps
 
     def clonebundles(self):
         return self._repo.tryread(bundlecaches.CB_MANIFEST_FILE)
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         """Used to test argument passing over the wire"""
         return b"%s %s %s %s %s" % (
             one,
             two,
             pycompat.bytestr(three),
             pycompat.bytestr(four),
             pycompat.bytestr(five),
         )
 
     def getbundle(
         self,
         source,
         heads=None,
         common=None,
         bundlecaps=None,
         remote_sidedata=None,
         **kwargs
     ):
         chunks = exchange.getbundlechunks(
             self._repo,
             source,
             heads=heads,
             common=common,
             bundlecaps=bundlecaps,
             remote_sidedata=remote_sidedata,
             **kwargs
         )[1]
         cb = util.chunkbuffer(chunks)
 
         if exchange.bundle2requested(bundlecaps):
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler(b'01', cb, None)
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def stream_out(self):
         raise error.Abort(_(b'cannot perform stream clone against local peer'))
 
     def unbundle(self, bundle, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 bundle = exchange.readbundle(self.ui, bundle, None)
                 ret = exchange.unbundle(self._repo, bundle, heads, b'push', url)
                 if util.safehasattr(ret, b'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(
                 _(b'push failed:'), stringutil.forcebytestr(exc)
             )
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def commandexecutor(self):
         return localcommandexecutor(self)
 
     # End of peer interface.
 
 
 @interfaceutil.implementer(repository.ipeerlegacycommands)
 class locallegacypeer(localpeer):
     """peer extension which implements legacy methods too; used for tests with
     restricted capabilities"""
 
     def __init__(self, repo):
         super(locallegacypeer, self).__init__(repo, caps=legacycaps)
 
     # Begin of baselegacywirecommands interface.
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def changegroup(self, nodes, source):
         outgoing = discovery.outgoing(
             self._repo, missingroots=nodes, ancestorsof=self._repo.heads()
         )
         return changegroup.makechangegroup(self._repo, outgoing, b'01', source)
 
     def changegroupsubset(self, bases, heads, source):
         outgoing = discovery.outgoing(
             self._repo, missingroots=bases, ancestorsof=heads
         )
         return changegroup.makechangegroup(self._repo, outgoing, b'01', source)
 
     # End of baselegacywirecommands interface.
 
 
 # Functions receiving (ui, features) that extensions can register to impact
 # the ability to load repositories with custom requirements. Only
 # functions defined in loaded extensions are called.
 #
 # The function receives a set of requirement strings that the repository
 # is capable of opening. Functions will typically add elements to the
 # set to reflect that the extension knows how to handle that requirements.
 featuresetupfuncs = set()
 
 
 def _getsharedvfs(hgvfs, requirements):
     """returns the vfs object pointing to root of shared source
     repo for a shared repository
 
     hgvfs is vfs pointing at .hg/ of current repo (shared one)
     requirements is a set of requirements of current repo (shared one)
     """
     # The ``shared`` or ``relshared`` requirements indicate the
     # store lives in the path contained in the ``.hg/sharedpath`` file.
     # This is an absolute path for ``shared`` and relative to
     # ``.hg/`` for ``relshared``.
     sharedpath = hgvfs.read(b'sharedpath').rstrip(b'\n')
     if requirementsmod.RELATIVE_SHARED_REQUIREMENT in requirements:
         sharedpath = util.normpath(hgvfs.join(sharedpath))
 
     sharedvfs = vfsmod.vfs(sharedpath, realpath=True)
 
     if not sharedvfs.exists():
         raise error.RepoError(
             _(b'.hg/sharedpath points to nonexistent directory %s')
             % sharedvfs.base
         )
     return sharedvfs
 
 
 def _readrequires(vfs, allowmissing):
     """reads the require file present at root of this vfs
     and return a set of requirements
 
     If allowmissing is True, we suppress ENOENT if raised"""
     # requires file contains a newline-delimited list of
     # features/capabilities the opener (us) must have in order to use
     # the repository. This file was introduced in Mercurial 0.9.2,
     # which means very old repositories may not have one. We assume
     # a missing file translates to no requirements.
     try:
         requirements = set(vfs.read(b'requires').splitlines())
     except IOError as e:
         if not (allowmissing and e.errno == errno.ENOENT):
             raise
         requirements = set()
     return requirements
 
 
 def makelocalrepository(baseui, path, intents=None):
     """Create a local repository object.
 
     Given arguments needed to construct a local repository, this function
     performs various early repository loading functionality (such as
     reading the ``.hg/requires`` and ``.hg/hgrc`` files), validates that
     the repository can be opened, derives a type suitable for representing
     that repository, and returns an instance of it.
 
     The returned object conforms to the ``repository.completelocalrepository``
     interface.
 
     The repository type is derived by calling a series of factory functions
     for each aspect/interface of the final repository. These are defined by
     ``REPO_INTERFACES``.
 
     Each factory function is called to produce a type implementing a specific
     interface. The cumulative list of returned types will be combined into a
     new type and that type will be instantiated to represent the local
     repository.
 
     The factory functions each receive various state that may be consulted
     as part of deriving a type.
 
     Extensions should wrap these factory functions to customize repository type
     creation. Note that an extension's wrapped function may be called even if
     that extension is not loaded for the repo being constructed. Extensions
     should check if their ``__name__`` appears in the
     ``extensionmodulenames`` set passed to the factory function and no-op if
     not.
     """
     ui = baseui.copy()
     # Prevent copying repo configuration.
     ui.copy = baseui.copy
 
     # Working directory VFS rooted at repository root.
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     # Main VFS for .hg/ directory.
     hgpath = wdirvfs.join(b'.hg')
     hgvfs = vfsmod.vfs(hgpath, cacheaudited=True)
     # Whether this repository is shared one or not
     shared = False
     # If this repository is shared, vfs pointing to shared repo
     sharedvfs = None
 
     # The .hg/ path should exist and should be a directory. All other
     # cases are errors.
     if not hgvfs.isdir():
         try:
             hgvfs.stat()
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
         except ValueError as e:
             # Can be raised on Python 3.8 when path is invalid.
             raise error.Abort(
                 _(b'invalid path %s: %s') % (path, stringutil.forcebytestr(e))
             )
 
         raise error.RepoError(_(b'repository %s not found') % path)
 
     requirements = _readrequires(hgvfs, True)
     shared = (
         requirementsmod.SHARED_REQUIREMENT in requirements
         or requirementsmod.RELATIVE_SHARED_REQUIREMENT in requirements
     )
     storevfs = None
     if shared:
         # This is a shared repo
         sharedvfs = _getsharedvfs(hgvfs, requirements)
         storevfs = vfsmod.vfs(sharedvfs.join(b'store'))
     else:
         storevfs = vfsmod.vfs(hgvfs.join(b'store'))
 
     # if .hg/requires contains the sharesafe requirement, it means
     # there exists a `.hg/store/requires` too and we should read it
     # NOTE: presence of SHARESAFE_REQUIREMENT imply that store requirement
     # is present. We never write SHARESAFE_REQUIREMENT for a repo if store
     # is not present, refer checkrequirementscompat() for that
     #
     # However, if SHARESAFE_REQUIREMENT is not present, it means that the
     # repository was shared the old way. We check the share source .hg/requires
     # for SHARESAFE_REQUIREMENT to detect whether the current repository needs
     # to be reshared
     hint = _(b"see `hg help config.format.use-share-safe` for more information")
     if requirementsmod.SHARESAFE_REQUIREMENT in requirements:
 
         if (
             shared
             and requirementsmod.SHARESAFE_REQUIREMENT
             not in _readrequires(sharedvfs, True)
         ):
             mismatch_warn = ui.configbool(
                 b'share', b'safe-mismatch.source-not-safe.warn'
             )
             mismatch_config = ui.config(
                 b'share', b'safe-mismatch.source-not-safe'
             )
             if mismatch_config in (
                 b'downgrade-allow',
                 b'allow',
                 b'downgrade-abort',
             ):
                 # prevent cyclic import localrepo -> upgrade -> localrepo
                 from . import upgrade
 
                 upgrade.downgrade_share_to_non_safe(
                     ui,
                     hgvfs,
                     sharedvfs,
                     requirements,
                     mismatch_config,
                     mismatch_warn,
                 )
             elif mismatch_config == b'abort':
                 raise error.Abort(
                     _(b"share source does not support share-safe requirement"),
                     hint=hint,
                 )
             else:
                 raise error.Abort(
                     _(
                         b"share-safe mismatch with source.\nUnrecognized"
                         b" value '%s' of `share.safe-mismatch.source-not-safe`"
                         b" set."
                     )
                     % mismatch_config,
                     hint=hint,
                 )
         else:
             requirements |= _readrequires(storevfs, False)
     elif shared:
         sourcerequires = _readrequires(sharedvfs, False)
         if requirementsmod.SHARESAFE_REQUIREMENT in sourcerequires:
             mismatch_config = ui.config(b'share', b'safe-mismatch.source-safe')
             mismatch_warn = ui.configbool(
                 b'share', b'safe-mismatch.source-safe.warn'
             )
             if mismatch_config in (
                 b'upgrade-allow',
                 b'allow',
                 b'upgrade-abort',
             ):
                 # prevent cyclic import localrepo -> upgrade -> localrepo
                 from . import upgrade
 
                 upgrade.upgrade_share_to_safe(
                     ui,
                     hgvfs,
                     storevfs,
                     requirements,
                     mismatch_config,
                     mismatch_warn,
                 )
             elif mismatch_config == b'abort':
                 raise error.Abort(
                     _(
                         b'version mismatch: source uses share-safe'
                         b' functionality while the current share does not'
                     ),
                     hint=hint,
                 )
             else:
                 raise error.Abort(
                     _(
                         b"share-safe mismatch with source.\nUnrecognized"
                         b" value '%s' of `share.safe-mismatch.source-safe` set."
                     )
                     % mismatch_config,
                     hint=hint,
                 )
 
     # The .hg/hgrc file may load extensions or contain config options
     # that influence repository construction. Attempt to load it and
     # process any new extensions that it may have pulled in.
     if loadhgrc(ui, wdirvfs, hgvfs, requirements, sharedvfs):
         afterhgrcload(ui, wdirvfs, hgvfs, requirements)
         extensions.loadall(ui)
         extensions.populateui(ui)
 
     # Set of module names of extensions loaded for this repository.
     extensionmodulenames = {m.__name__ for n, m in extensions.extensions(ui)}
 
     supportedrequirements = gathersupportedrequirements(ui)
 
     # We first validate the requirements are known.
     ensurerequirementsrecognized(requirements, supportedrequirements)
 
     # Then we validate that the known set is reasonable to use together.
     ensurerequirementscompatible(ui, requirements)
 
     # TODO there are unhandled edge cases related to opening repositories with
     # shared storage. If storage is shared, we should also test for requirements
     # compatibility in the pointed-to repo. This entails loading the .hg/hgrc in
     # that repo, as that repo may load extensions needed to open it. This is a
     # bit complicated because we don't want the other hgrc to overwrite settings
     # in this hgrc.
     #
     # This bug is somewhat mitigated by the fact that we copy the .hg/requires
     # file when sharing repos. But if a requirement is added after the share is
     # performed, thereby introducing a new requirement for the opener, we may
     # will not see that and could encounter a run-time error interacting with
     # that shared store since it has an unknown-to-us requirement.
 
     # At this point, we know we should be capable of opening the repository.
     # Now get on with doing that.
 
     features = set()
 
     # The "store" part of the repository holds versioned data. How it is
     # accessed is determined by various requirements. If `shared` or
     # `relshared` requirements are present, this indicates current repository
     # is a share and store exists in path mentioned in `.hg/sharedpath`
     if shared:
         storebasepath = sharedvfs.base
         cachepath = sharedvfs.join(b'cache')
         features.add(repository.REPO_FEATURE_SHARED_STORAGE)
     else:
         storebasepath = hgvfs.base
         cachepath = hgvfs.join(b'cache')
     wcachepath = hgvfs.join(b'wcache')
 
     # The store has changed over time and the exact layout is dictated by
     # requirements. The store interface abstracts differences across all
     # of them.
     store = makestore(
         requirements,
         storebasepath,
         lambda base: vfsmod.vfs(base, cacheaudited=True),
     )
     hgvfs.createmode = store.createmode
 
     storevfs = store.vfs
     storevfs.options = resolvestorevfsoptions(ui, requirements, features)
 
     if (
         requirementsmod.REVLOGV2_REQUIREMENT in requirements
         or requirementsmod.CHANGELOGV2_REQUIREMENT in requirements
     ):
         features.add(repository.REPO_FEATURE_SIDE_DATA)
         # the revlogv2 docket introduced race condition that we need to fix
         features.discard(repository.REPO_FEATURE_STREAM_CLONE)
 
     # The cache vfs is used to manage cache files.
     cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
     cachevfs.createmode = store.createmode
     # The cache vfs is used to manage cache files related to the working copy
     wcachevfs = vfsmod.vfs(wcachepath, cacheaudited=True)
     wcachevfs.createmode = store.createmode
 
     # Now resolve the type for the repository object. We do this by repeatedly
     # calling a factory function to produces types for specific aspects of the
     # repo's operation. The aggregate returned types are used as base classes
     # for a dynamically-derived type, which will represent our new repository.
 
     bases = []
     extrastate = {}
 
     for iface, fn in REPO_INTERFACES:
         # We pass all potentially useful state to give extensions tons of
         # flexibility.
         typ = fn()(
             ui=ui,
             intents=intents,
             requirements=requirements,
             features=features,
             wdirvfs=wdirvfs,
             hgvfs=hgvfs,
             store=store,
             storevfs=storevfs,
             storeoptions=storevfs.options,
             cachevfs=cachevfs,
             wcachevfs=wcachevfs,
             extensionmodulenames=extensionmodulenames,
             extrastate=extrastate,
             baseclasses=bases,
         )
 
         if not isinstance(typ, type):
             raise error.ProgrammingError(
                 b'unable to construct type for %s' % iface
             )
 
         bases.append(typ)
 
     # type() allows you to use characters in type names that wouldn't be
     # recognized as Python symbols in source code. We abuse that to add
     # rich information about our constructed repo.
     name = pycompat.sysstr(
         b'derivedrepo:%s<%s>' % (wdirvfs.base, b','.join(sorted(requirements)))
     )
 
     cls = type(name, tuple(bases), {})
 
     return cls(
         baseui=baseui,
         ui=ui,
         origroot=path,
         wdirvfs=wdirvfs,
         hgvfs=hgvfs,
         requirements=requirements,
         supportedrequirements=supportedrequirements,
         sharedpath=storebasepath,
         store=store,
         cachevfs=cachevfs,
         wcachevfs=wcachevfs,
         features=features,
         intents=intents,
     )
 
 
 def loadhgrc(ui, wdirvfs, hgvfs, requirements, sharedvfs=None):
     """Load hgrc files/content into a ui instance.
 
     This is called during repository opening to load any additional
     config files or settings relevant to the current repository.
 
     Returns a bool indicating whether any additional configs were loaded.
 
     Extensions should monkeypatch this function to modify how per-repo
     configs are loaded. For example, an extension may wish to pull in
     configs from alternate files or sources.
 
     sharedvfs is vfs object pointing to source repo if the current one is a
     shared one
     """
     if not rcutil.use_repo_hgrc():
         return False
 
     ret = False
     # first load config from shared source if we has to
     if requirementsmod.SHARESAFE_REQUIREMENT in requirements and sharedvfs:
         try:
             ui.readconfig(sharedvfs.join(b'hgrc'), root=sharedvfs.base)
             ret = True
         except IOError:
             pass
 
     try:
         ui.readconfig(hgvfs.join(b'hgrc'), root=wdirvfs.base)
         ret = True
     except IOError:
         pass
 
     try:
         ui.readconfig(hgvfs.join(b'hgrc-not-shared'), root=wdirvfs.base)
         ret = True
     except IOError:
         pass
 
     return ret
 
 
 def afterhgrcload(ui, wdirvfs, hgvfs, requirements):
     """Perform additional actions after .hg/hgrc is loaded.
 
     This function is called during repository loading immediately after
     the .hg/hgrc file is loaded and before per-repo extensions are loaded.
 
     The function can be used to validate configs, automatically add
     options (including extensions) based on requirements, etc.
     """
 
     # Map of requirements to list of extensions to load automatically when
     # requirement is present.
     autoextensions = {
         b'git': [b'git'],
         b'largefiles': [b'largefiles'],
         b'lfs': [b'lfs'],
     }
 
     for requirement, names in sorted(autoextensions.items()):
         if requirement not in requirements:
             continue
 
         for name in names:
             if not ui.hasconfig(b'extensions', name):
                 ui.setconfig(b'extensions', name, b'', source=b'autoload')
 
 
 def gathersupportedrequirements(ui):
     """Determine the complete set of recognized requirements."""
     # Start with all requirements supported by this file.
     supported = set(localrepository._basesupported)
 
-    if dirstate.SUPPORTS_DIRSTATE_V2:
-        supported.add(requirementsmod.DIRSTATE_V2_REQUIREMENT)
-
     # Execute ``featuresetupfuncs`` entries if they belong to an extension
     # relevant to this ui instance.
     modules = {m.__name__ for n, m in extensions.extensions(ui)}
 
     for fn in featuresetupfuncs:
         if fn.__module__ in modules:
             fn(ui, supported)
 
     # Add derived requirements from registered compression engines.
     for name in util.compengines:
         engine = util.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
 
     return supported
 
 
 def ensurerequirementsrecognized(requirements, supported):
     """Validate that a set of local requirements is recognized.
 
     Receives a set of requirements. Raises an ``error.RepoError`` if there
     exists any requirement in that set that currently loaded code doesn't
     recognize.
 
     Returns a set of supported requirements.
     """
     missing = set()
 
     for requirement in requirements:
         if requirement in supported:
             continue
 
         if not requirement or not requirement[0:1].isalnum():
             raise error.RequirementError(_(b'.hg/requires file is corrupt'))
 
         missing.add(requirement)
 
     if missing:
         raise error.RequirementError(
             _(b'repository requires features unknown to this Mercurial: %s')
             % b' '.join(sorted(missing)),
             hint=_(
                 b'see https://mercurial-scm.org/wiki/MissingRequirement '
                 b'for more information'
             ),
         )
 
 
 def ensurerequirementscompatible(ui, requirements):
     """Validates that a set of recognized requirements is mutually compatible.
 
     Some requirements may not be compatible with others or require
     config options that aren't enabled. This function is called during
     repository opening to ensure that the set of requirements needed
     to open a repository is sane and compatible with config options.
 
     Extensions can monkeypatch this function to perform additional
     checking.
 
     ``error.RepoError`` should be raised on failure.
     """
     if (
         requirementsmod.SPARSE_REQUIREMENT in requirements
         and not sparse.enabled
     ):
         raise error.RepoError(
             _(
                 b'repository is using sparse feature but '
                 b'sparse is not enabled; enable the '
                 b'"sparse" extensions to access'
             )
         )
 
 
 def makestore(requirements, path, vfstype):
     """Construct a storage object for a repository."""
     if requirementsmod.STORE_REQUIREMENT in requirements:
         if requirementsmod.FNCACHE_REQUIREMENT in requirements:
             dotencode = requirementsmod.DOTENCODE_REQUIREMENT in requirements
             return storemod.fncachestore(path, vfstype, dotencode)
 
         return storemod.encodedstore(path, vfstype)
 
     return storemod.basicstore(path, vfstype)
 
 
 def resolvestorevfsoptions(ui, requirements, features):
     """Resolve the options to pass to the store vfs opener.
 
     The returned dict is used to influence behavior of the storage layer.
     """
     options = {}
 
     if requirementsmod.TREEMANIFEST_REQUIREMENT in requirements:
         options[b'treemanifest'] = True
 
     # experimental config: format.manifestcachesize
     manifestcachesize = ui.configint(b'format', b'manifestcachesize')
     if manifestcachesize is not None:
         options[b'manifestcachesize'] = manifestcachesize
 
     # In the absence of another requirement superseding a revlog-related
     # requirement, we have to assume the repo is using revlog version 0.
     # This revlog format is super old and we don't bother trying to parse
     # opener options for it because those options wouldn't do anything
     # meaningful on such old repos.
     if (
         requirementsmod.REVLOGV1_REQUIREMENT in requirements
         or requirementsmod.REVLOGV2_REQUIREMENT in requirements
     ):
         options.update(resolverevlogstorevfsoptions(ui, requirements, features))
     else:  # explicitly mark repo as using revlogv0
         options[b'revlogv0'] = True
 
     if requirementsmod.COPIESSDC_REQUIREMENT in requirements:
         options[b'copies-storage'] = b'changeset-sidedata'
     else:
         writecopiesto = ui.config(b'experimental', b'copies.write-to')
         copiesextramode = (b'changeset-only', b'compatibility')
         if writecopiesto in copiesextramode:
             options[b'copies-storage'] = b'extra'
 
     return options
 
 
 def resolverevlogstorevfsoptions(ui, requirements, features):
     """Resolve opener options specific to revlogs."""
 
     options = {}
     options[b'flagprocessors'] = {}
 
     if requirementsmod.REVLOGV1_REQUIREMENT in requirements:
         options[b'revlogv1'] = True
     if requirementsmod.REVLOGV2_REQUIREMENT in requirements:
         options[b'revlogv2'] = True
     if requirementsmod.CHANGELOGV2_REQUIREMENT in requirements:
         options[b'changelogv2'] = True
 
     if requirementsmod.GENERALDELTA_REQUIREMENT in requirements:
         options[b'generaldelta'] = True
 
     # experimental config: format.chunkcachesize
     chunkcachesize = ui.configint(b'format', b'chunkcachesize')
     if chunkcachesize is not None:
         options[b'chunkcachesize'] = chunkcachesize
 
     deltabothparents = ui.configbool(
         b'storage', b'revlog.optimize-delta-parent-choice'
     )
     options[b'deltabothparents'] = deltabothparents
 
     issue6528 = ui.configbool(b'storage', b'revlog.issue6528.fix-incoming')
     options[b'issue6528.fix-incoming'] = issue6528
 
     lazydelta = ui.configbool(b'storage', b'revlog.reuse-external-delta')
     lazydeltabase = False
     if lazydelta:
         lazydeltabase = ui.configbool(
             b'storage', b'revlog.reuse-external-delta-parent'
         )
     if lazydeltabase is None:
         lazydeltabase = not scmutil.gddeltaconfig(ui)
     options[b'lazydelta'] = lazydelta
     options[b'lazydeltabase'] = lazydeltabase
 
     chainspan = ui.configbytes(b'experimental', b'maxdeltachainspan')
     if 0 <= chainspan:
         options[b'maxdeltachainspan'] = chainspan
 
     mmapindexthreshold = ui.configbytes(b'experimental', b'mmapindexthreshold')
     if mmapindexthreshold is not None:
         options[b'mmapindexthreshold'] = mmapindexthreshold
 
     withsparseread = ui.configbool(b'experimental', b'sparse-read')
     srdensitythres = float(
         ui.config(b'experimental', b'sparse-read.density-threshold')
     )
     srmingapsize = ui.configbytes(b'experimental', b'sparse-read.min-gap-size')
     options[b'with-sparse-read'] = withsparseread
     options[b'sparse-read-density-threshold'] = srdensitythres
     options[b'sparse-read-min-gap-size'] = srmingapsize
 
     sparserevlog = requirementsmod.SPARSEREVLOG_REQUIREMENT in requirements
     options[b'sparse-revlog'] = sparserevlog
     if sparserevlog:
         options[b'generaldelta'] = True
 
     maxchainlen = None
     if sparserevlog:
         maxchainlen = revlogconst.SPARSE_REVLOG_MAX_CHAIN_LENGTH
     # experimental config: format.maxchainlen
     maxchainlen = ui.configint(b'format', b'maxchainlen', maxchainlen)
     if maxchainlen is not None:
         options[b'maxchainlen'] = maxchainlen
 
     for r in requirements:
         # we allow multiple compression engine requirement to co-exist because
         # strickly speaking, revlog seems to support mixed compression style.
         #
         # The compression used for new entries will be "the last one"
         prefix = r.startswith
         if prefix(b'revlog-compression-') or prefix(b'exp-compression-'):
             options[b'compengine'] = r.split(b'-', 2)[2]
 
     options[b'zlib.level'] = ui.configint(b'storage', b'revlog.zlib.level')
     if options[b'zlib.level'] is not None:
         if not (0 <= options[b'zlib.level'] <= 9):
             msg = _(b'invalid value for `storage.revlog.zlib.level` config: %d')
             raise error.Abort(msg % options[b'zlib.level'])
     options[b'zstd.level'] = ui.configint(b'storage', b'revlog.zstd.level')
     if options[b'zstd.level'] is not None:
         if not (0 <= options[b'zstd.level'] <= 22):
             msg = _(b'invalid value for `storage.revlog.zstd.level` config: %d')
             raise error.Abort(msg % options[b'zstd.level'])
 
     if requirementsmod.NARROW_REQUIREMENT in requirements:
         options[b'enableellipsis'] = True
 
     if ui.configbool(b'experimental', b'rust.index'):
         options[b'rust.index'] = True
     if requirementsmod.NODEMAP_REQUIREMENT in requirements:
         slow_path = ui.config(
             b'storage', b'revlog.persistent-nodemap.slow-path'
         )
         if slow_path not in (b'allow', b'warn', b'abort'):
             default = ui.config_default(
                 b'storage', b'revlog.persistent-nodemap.slow-path'
             )
             msg = _(
                 b'unknown value for config '
                 b'"storage.revlog.persistent-nodemap.slow-path": "%s"\n'
             )
             ui.warn(msg % slow_path)
             if not ui.quiet:
                 ui.warn(_(b'falling back to default value: %s\n') % default)
             slow_path = default
 
         msg = _(
             b"accessing `persistent-nodemap` repository without associated "
             b"fast implementation."
         )
         hint = _(
             b"check `hg help config.format.use-persistent-nodemap` "
             b"for details"
         )
         if not revlog.HAS_FAST_PERSISTENT_NODEMAP:
             if slow_path == b'warn':
                 msg = b"warning: " + msg + b'\n'
                 ui.warn(msg)
                 if not ui.quiet:
                     hint = b'(' + hint + b')\n'
                     ui.warn(hint)
             if slow_path == b'abort':
                 raise error.Abort(msg, hint=hint)
         options[b'persistent-nodemap'] = True
     if ui.configbool(b'storage', b'revlog.persistent-nodemap.mmap'):
         options[b'persistent-nodemap.mmap'] = True
     if ui.configbool(b'devel', b'persistent-nodemap'):
         options[b'devel-force-nodemap'] = True
 
     return options
 
 
 def makemain(**kwargs):
     """Produce a type conforming to ``ilocalrepositorymain``."""
     return localrepository
 
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlogfilestorage(object):
     """File storage when using revlogs."""
 
     def file(self, path):
         if path.startswith(b'/'):
             path = path[1:]
 
         return filelog.filelog(self.svfs, path)
 
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlognarrowfilestorage(object):
     """File storage when using revlogs and narrow files."""
 
     def file(self, path):
         if path.startswith(b'/'):
             path = path[1:]
 
         return filelog.narrowfilelog(self.svfs, path, self._storenarrowmatch)
 
 
 def makefilestorage(requirements, features, **kwargs):
     """Produce a type conforming to ``ilocalrepositoryfilestorage``."""
     features.add(repository.REPO_FEATURE_REVLOG_FILE_STORAGE)
     features.add(repository.REPO_FEATURE_STREAM_CLONE)
 
     if requirementsmod.NARROW_REQUIREMENT in requirements:
         return revlognarrowfilestorage
     else:
         return revlogfilestorage
 
 
 # List of repository interfaces and factory functions for them. Each
 # will be called in order during ``makelocalrepository()`` to iteratively
 # derive the final type for a local repository instance. We capture the
 # function as a lambda so we don't hold a reference and the module-level
 # functions can be wrapped.
 REPO_INTERFACES = [
     (repository.ilocalrepositorymain, lambda: makemain),
     (repository.ilocalrepositoryfilestorage, lambda: makefilestorage),
 ]
 
 
 @interfaceutil.implementer(repository.ilocalrepositorymain)
 class localrepository(object):
     """Main class for representing local repositories.
 
     All local repositories are instances of this class.
 
     Constructed on its own, instances of this class are not usable as
     repository objects. To obtain a usable repository object, call
     ``hg.repository()``, ``localrepo.instance()``, or
     ``localrepo.makelocalrepository()``. The latter is the lowest-level.
     ``instance()`` adds support for creating new repositories.
     ``hg.repository()`` adds more extension integration, including calling
     ``reposetup()``. Generally speaking, ``hg.repository()`` should be
     used.
     """
 
     # obsolete experimental requirements:
     #  - manifestv2: An experimental new manifest format that allowed
     #    for stem compression of long paths. Experiment ended up not
     #    being successful (repository sizes went up due to worse delta
     #    chains), and the code was deleted in 4.6.
     supportedformats = {
         requirementsmod.REVLOGV1_REQUIREMENT,
         requirementsmod.GENERALDELTA_REQUIREMENT,
         requirementsmod.TREEMANIFEST_REQUIREMENT,
         requirementsmod.COPIESSDC_REQUIREMENT,
         requirementsmod.REVLOGV2_REQUIREMENT,
         requirementsmod.CHANGELOGV2_REQUIREMENT,
         requirementsmod.SPARSEREVLOG_REQUIREMENT,
         requirementsmod.NODEMAP_REQUIREMENT,
         bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT,
         requirementsmod.SHARESAFE_REQUIREMENT,
+        requirementsmod.DIRSTATE_V2_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         requirementsmod.STORE_REQUIREMENT,
         requirementsmod.FNCACHE_REQUIREMENT,
         requirementsmod.SHARED_REQUIREMENT,
         requirementsmod.RELATIVE_SHARED_REQUIREMENT,
         requirementsmod.DOTENCODE_REQUIREMENT,
         requirementsmod.SPARSE_REQUIREMENT,
         requirementsmod.INTERNAL_PHASE_REQUIREMENT,
     }
 
     # list of prefix for file which can be written without 'wlock'
     # Extensions should extend this list when needed
     _wlockfreeprefix = {
         # We migh consider requiring 'wlock' for the next
         # two, but pretty much all the existing code assume
         # wlock is not needed so we keep them excluded for
         # now.
         b'hgrc',
         b'requires',
         # XXX cache is a complicatged business someone
         # should investigate this in depth at some point
         b'cache/',
         # XXX shouldn't be dirstate covered by the wlock?
         b'dirstate',
         # XXX bisect was still a bit too messy at the time
         # this changeset was introduced. Someone should fix
         # the remainig bit and drop this line
         b'bisect.state',
     }
 
     def __init__(
         self,
         baseui,
         ui,
         origroot,
         wdirvfs,
         hgvfs,
         requirements,
         supportedrequirements,
         sharedpath,
         store,
         cachevfs,
         wcachevfs,
         features,
         intents=None,
     ):
         """Create a new local repository instance.
 
         Most callers should use ``hg.repository()``, ``localrepo.instance()``,
         or ``localrepo.makelocalrepository()`` for obtaining a new repository
         object.
 
         Arguments:
 
         baseui
            ``ui.ui`` instance that ``ui`` argument was based off of.
 
         ui
            ``ui.ui`` instance for use by the repository.
 
         origroot
            ``bytes`` path to working directory root of this repository.
 
         wdirvfs
            ``vfs.vfs`` rooted at the working directory.
 
         hgvfs
            ``vfs.vfs`` rooted at .hg/
 
         requirements
            ``set`` of bytestrings representing repository opening requirements.
 
         supportedrequirements
            ``set`` of bytestrings representing repository requirements that we
            know how to open. May be a supetset of ``requirements``.
 
         sharedpath
            ``bytes`` Defining path to storage base directory. Points to a
            ``.hg/`` directory somewhere.
 
         store
            ``store.basicstore`` (or derived) instance providing access to
            versioned storage.
 
         cachevfs
            ``vfs.vfs`` used for cache files.
 
         wcachevfs
            ``vfs.vfs`` used for cache files related to the working copy.
 
         features
            ``set`` of bytestrings defining features/capabilities of this
            instance.
 
         intents
            ``set`` of system strings indicating what this repo will be used
            for.
         """
         self.baseui = baseui
         self.ui = ui
         self.origroot = origroot
         # vfs rooted at working directory.
         self.wvfs = wdirvfs
         self.root = wdirvfs.base
         # vfs rooted at .hg/. Used to access most non-store paths.
         self.vfs = hgvfs
         self.path = hgvfs.base
         self.requirements = requirements
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
         self.supported = supportedrequirements
         self.sharedpath = sharedpath
         self.store = store
         self.cachevfs = cachevfs
         self.wcachevfs = wcachevfs
         self.features = features
 
         self.filtername = None
 
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             self.vfs.audit = self._getvfsward(self.vfs.audit)
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
 
         color.setup(self.ui)
 
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             if util.safehasattr(self.svfs, b'vfs'):  # this is filtervfs
                 self.svfs.vfs.audit = self._getsvfsward(self.svfs.vfs.audit)
             else:  # standard vfs
                 self.svfs.audit = self._getsvfsward(self.svfs.audit)
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = branchmap.BranchMapCache()
         self._revbranchcache = None
         self._filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # post-dirstate-status hooks
         self._postdsstatus = []
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
         # Key to signature value.
         self._sparsesignaturecache = {}
         # Signature to cached matcher instance.
         self._sparsematchercache = {}
 
         self._extrafilterid = repoview.extrafilter(ui)
 
         self.filecopiesmode = None
         if requirementsmod.COPIESSDC_REQUIREMENT in self.requirements:
             self.filecopiesmode = b'changeset-sidedata'
 
         self._wanted_sidedata = set()
         self._sidedata_computers = {}
         sidedatamod.set_sidedata_spec_for_repo(self)
 
     def _getvfsward(self, origfunc):
         """build a ward for self.vfs"""
         rref = weakref.ref(self)
 
         def checkvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if (
                 repo is None
                 or not util.safehasattr(repo, b'_wlockref')
                 or not util.safehasattr(repo, b'_lockref')
             ):
                 return
             if mode in (None, b'r', b'rb'):
                 return
             if path.startswith(repo.path):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.path) + 1 :]
             if path.startswith(b'cache/'):
                 msg = b'accessing cache with vfs instead of cachevfs: "%s"'
                 repo.ui.develwarn(msg % path, stacklevel=3, config=b"cache-vfs")
             # path prefixes covered by 'lock'
             vfs_path_prefixes = (
                 b'journal.',
                 b'undo.',
                 b'strip-backup/',
                 b'cache/',
             )
             if any(path.startswith(prefix) for prefix in vfs_path_prefixes):
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn(
                         b'write with no lock: "%s"' % path,
                         stacklevel=3,
                         config=b'check-locks',
                     )
             elif repo._currentlock(repo._wlockref) is None:
                 # rest of vfs files are covered by 'wlock'
                 #
                 # exclude special files
                 for prefix in self._wlockfreeprefix:
                     if path.startswith(prefix):
                         return
                 repo.ui.develwarn(
                     b'write with no wlock: "%s"' % path,
                     stacklevel=3,
                     config=b'check-locks',
                 )
             return ret
 
         return checkvfs
 
     def _getsvfsward(self, origfunc):
         """build a ward for self.svfs"""
         rref = weakref.ref(self)
 
         def checksvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if repo is None or not util.safehasattr(repo, b'_lockref'):
                 return
             if mode in (None, b'r', b'rb'):
                 return
             if path.startswith(repo.sharedpath):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.sharedpath) + 1 :]
             if repo._currentlock(repo._lockref) is None:
                 repo.ui.develwarn(
                     b'write with no lock: "%s"' % path, stacklevel=4
                 )
             return ret
 
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool(b'experimental', b'bundle2-advertise'):
             caps = set(caps)
             capsblob = bundle2.encodecaps(
                 bundle2.getrepocaps(self, role=b'client')
             )
             caps.add(b'bundle2=' + urlreq.quote(capsblob))
         if self.ui.configbool(b'experimental', b'narrow'):
             caps.add(wireprototypes.NARROWCAP)
         return caps
 
     # Don't cache auditor/nofsauditor, or you'll end up with reference cycle:
     # self -> auditor -> self._checknested -> self
 
     @property
     def auditor(self):
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested)
 
     @property
     def nofsauditor(self):
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         return pathutil.pathauditor(
             self.root, callback=self._checknested, realfs=False, cached=True
         )
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1 :]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = b'/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1 :])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self)  # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository
 
         The `name` parameter is the identifier of the requested view. This
         will return a repoview object set "exactly" to the specified view.
 
         This function does not apply recursive filtering to a repository. For
         example calling `repo.filtered("served")` will return a repoview using
         the "served" view, regardless of the initial view used by `repo`.
 
         In other word, there is always only one level of `repoview` "filtering".
         """
         if self._extrafilterid is not None and b'%' not in name:
             name = name + b'%' + self._extrafilterid
 
         cls = repoview.newtype(self.unfiltered().__class__)
         return cls(self, name, visibilityexceptions)
 
     @mixedrepostorecache(
         (b'bookmarks', b'plain'),
         (b'bookmarks.current', b'plain'),
         (b'bookmarks', b''),
         (b'00changelog.i', b''),
     )
     def _bookmarks(self):
         # Since the multiple files involved in the transaction cannot be
         # written atomically (with current repository format), there is a race
         # condition here.
         #
         # 1) changelog content A is read
         # 2) outside transaction update changelog to content B
         # 3) outside transaction update bookmark file referring to content B
         # 4) bookmarks file content is read and filtered against changelog-A
         #
         # When this happens, bookmarks against nodes missing from A are dropped.
         #
         # Having this happening during read is not great, but it become worse
         # when this happen during write because the bookmarks to the "unknown"
         # nodes will be dropped for good. However, writes happen within locks.
         # This locking makes it possible to have a race free consistent read.
         # For this purpose data read from disc before locking  are
         # "invalidated" right after the locks are taken. This invalidations are
         # "light", the `filecache` mechanism keep the data in memory and will
         # reuse them if the underlying files did not changed. Not parsing the
         # same data multiple times helps performances.
         #
         # Unfortunately in the case describe above, the files tracked by the
         # bookmarks file cache might not have changed, but the in-memory
         # content is still "wrong" because we used an older changelog content
         # to process the on-disk data. So after locking, the changelog would be
         # refreshed but `_bookmarks` would be preserved.
         # Adding `00changelog.i` to the list of tracked file is not
         # enough, because at the time we build the content for `_bookmarks` in
         # (4), the changelog file has already diverged from the content used
         # for loading `changelog` in (1)
         #
         # To prevent the issue, we force the changelog to be explicitly
         # reloaded while computing `_bookmarks`. The data race can still happen
         # without the lock (with a narrower window), but it would no longer go
         # undetected during the lock time refresh.
         #
         # The new schedule is as follow
         #
         # 1) filecache logic detect that `_bookmarks` needs to be computed
         # 2) cachestat for `bookmarks` and `changelog` are captured (for book)
         # 3) We force `changelog` filecache to be tested
         # 4) cachestat for `changelog` are captured (for changelog)
         # 5) `_bookmarks` is computed and cached
         #
         # The step in (3) ensure we have a changelog at least as recent as the
         # cache stat computed in (1). As a result at locking time:
         #  * if the changelog did not changed since (1) -> we can reuse the data
         #  * otherwise -> the bookmarks get refreshed.
         self._refreshchangelog()
         return bookmarks.bmstore(self)
 
     def _refreshchangelog(self):
         """make sure the in memory changelog match the on-disk one"""
         if 'changelog' in vars(self) and self.currenttransaction() is None:
             del self.changelog
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     # _phasesets depend on changelog. what we need is to call
     # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache(b'phaseroots', b'00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache(b'obsstore')
     def obsstore(self):
         return obsolete.makestore(self.ui, self)
 
     @changelogcache()
     def changelog(repo):
         # load dirstate before changelog to avoid race see issue6303
         repo.dirstate.prefetch_parents()
         return repo.store.changelog(
             txnutil.mayhavepending(repo.root),
             concurrencychecker=revlogchecker.get_checker(repo.ui, b'changelog'),
         )
 
     @manifestlogcache()
     def manifestlog(self):
         return self.store.manifestlog(self, self._storenarrowmatch)
 
     @repofilecache(b'dirstate')
     def dirstate(self):
         return self._makedirstate()
 
     def _makedirstate(self):
         """Extension point for wrapping the dirstate per-repo."""
         sparsematchfn = lambda: sparse.matcher(self)
         v2_req = requirementsmod.DIRSTATE_V2_REQUIREMENT
         use_dirstate_v2 = v2_req in self.requirements
 
         return dirstate.dirstate(
             self.vfs,
             self.ui,
             self.root,
             self._dirstatevalidate,
             sparsematchfn,
             self.nodeconstants,
             use_dirstate_v2,
         )
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(
                     _(b"warning: ignoring unknown working parent %s!\n")
                     % short(node)
                 )
             return self.nullid
 
     @storecache(narrowspec.FILENAME)
     def narrowpats(self):
         """matcher patterns for this repository's narrowspec
 
         A tuple of (includes, excludes).
         """
         return narrowspec.load(self)
 
     @storecache(narrowspec.FILENAME)
     def _storenarrowmatch(self):
         if requirementsmod.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(self):
         if requirementsmod.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always()
         narrowspec.checkworkingcopynarrowspec(self)
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     def narrowmatch(self, match=None, includeexact=False):
         """matcher corresponding the the repo's narrowspec
 
         If `match` is given, then that will be intersected with the narrow
         matcher.
 
         If `includeexact` is True, then any exact matches from `match` will
         be included even if they're outside the narrowspec.
         """
         if match:
             if includeexact and not self._narrowmatch.always():
                 # do not exclude explicitly-specified paths so that they can
                 # be warned later on
                 em = matchmod.exact(match.files())
                 nm = matchmod.unionmatcher([self._narrowmatch, em])
                 return matchmod.intersectmatchers(match, nm)
             return matchmod.intersectmatchers(match, self._narrowmatch)
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         narrowspec.save(self, newincludes, newexcludes)
         self.invalidate(clearfilecache=True)
 
     @unfilteredpropertycache
     def _quick_access_changeid_null(self):
         return {
             b'null': (nullrev, self.nodeconstants.nullid),
             nullrev: (nullrev, self.nodeconstants.nullid),
             self.nullid: (nullrev, self.nullid),
         }
 
     @unfilteredpropertycache
     def _quick_access_changeid_wc(self):
         # also fast path access to the working copy parents
         # however, only do it for filter that ensure wc is visible.
         quick = self._quick_access_changeid_null.copy()
         cl = self.unfiltered().changelog
         for node in self.dirstate.parents():
             if node == self.nullid:
                 continue
             rev = cl.index.get_rev(node)
             if rev is None:
                 # unknown working copy parent case:
                 #
                 #   skip the fast path and let higher code deal with it
                 continue
             pair = (rev, node)
             quick[rev] = pair
             quick[node] = pair
             # also add the parents of the parents
             for r in cl.parentrevs(rev):
                 if r == nullrev:
                     continue
                 n = cl.node(r)
                 pair = (r, n)
                 quick[r] = pair
                 quick[n] = pair
         p1node = self.dirstate.p1()
         if p1node != self.nullid:
             quick[b'.'] = quick[p1node]
         return quick
 
     @unfilteredmethod
     def _quick_access_changeid_invalidate(self):
         if '_quick_access_changeid_wc' in vars(self):
             del self.__dict__['_quick_access_changeid_wc']
 
     @property
     def _quick_access_changeid(self):
         """an helper dictionnary for __getitem__ calls
 
         This contains a list of symbol we can recognise right away without
         further processing.
         """
         if self.filtername in repoview.filter_has_wc:
             return self._quick_access_changeid_wc
         return self._quick_access_changeid_null
 
     def __getitem__(self, changeid):
         # dealing with special cases
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, context.basectx):
             return changeid
 
         # dealing with multiple revisions
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [
                 self[i]
                 for i in pycompat.xrange(*changeid.indices(len(self)))
                 if i not in self.changelog.filteredrevs
             ]
 
         # dealing with some special values
         quick_access = self._quick_access_changeid.get(changeid)
         if quick_access is not None:
             rev, node = quick_access
             return context.changectx(self, rev, node, maybe_filtered=False)
         if changeid == b'tip':
             node = self.changelog.tip()
             rev = self.changelog.rev(node)
             return context.changectx(self, rev, node)
 
         # dealing with arbitrary values
         try:
             if isinstance(changeid, int):
                 node = self.changelog.node(changeid)
                 rev = changeid
             elif changeid == b'.':
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 node = self.dirstate.p1()
                 rev = self.unfiltered().changelog.rev(node)
             elif len(changeid) == self.nodeconstants.nodelen:
                 try:
                     node = changeid
                     rev = self.changelog.rev(changeid)
                 except error.FilteredLookupError:
                     changeid = hex(changeid)  # for the error message
                     raise
                 except LookupError:
                     # check if it might have come from damaged dirstate
                     #
                     # XXX we could avoid the unfiltered if we had a recognizable
                     # exception for filtered changeset access
                     if (
                         self.local()
                         and changeid in self.unfiltered().dirstate.parents()
                     ):
                         msg = _(b"working directory has unknown parent '%s'!")
                         raise error.Abort(msg % short(changeid))
                     changeid = hex(changeid)  # for the error message
                     raise
 
             elif len(changeid) == 2 * self.nodeconstants.nodelen:
                 node = bin(changeid)
                 rev = self.changelog.rev(node)
             else:
                 raise error.ProgrammingError(
                     b"unsupported changeid '%s' of type %s"
                     % (changeid, pycompat.bytestr(type(changeid)))
                 )
 
             return context.changectx(self, rev, node)
 
         except (error.FilteredIndexError, error.FilteredLookupError):
             raise error.FilteredRepoLookupError(
                 _(b"filtered revision '%s'") % pycompat.bytestr(changeid)
             )
         except (IndexError, LookupError):
             raise error.RepoLookupError(
                 _(b"unknown revision '%s'") % pycompat.bytestr(changeid)
             )
         except error.WdirUnsupported:
             return context.workingctx(self)
 
     def __contains__(self, changeid):
         """True if the given changeid exists"""
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         # no need to pay the cost of repoview.changelog
         unfi = self.unfiltered()
         return len(unfi.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         """Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revsetlang.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()`` or
         ``repo.anyrevs([expr], user=True)``.
 
         Returns a smartset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         """
         tree = revsetlang.spectree(expr, *args)
         return revset.makematcher(tree)(self)
 
     def set(self, expr, *args):
         """Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         """
         for r in self.revs(expr, *args):
             yield self[r]
 
     def anyrevs(self, specs, user=False, localalias=None):
         """Find revisions matching one of the given revsets.
 
         Revset aliases from the configuration are not expanded by default. To
         expand user aliases, specify ``user=True``. To provide some local
         definitions overriding user aliases, set ``localalias`` to
         ``{name: definitionstring}``.
         """
         if specs == [b'null']:
             return revset.baseset([nullrev])
         if specs == [b'.']:
             quick_data = self._quick_access_changeid.get(b'.')
             if quick_data is not None:
                 return revset.baseset([quick_data[0]])
         if user:
             m = revset.matchany(
                 self.ui,
                 specs,
                 lookup=revset.lookupfn(self),
                 localalias=localalias,
             )
         else:
             m = revset.matchany(None, specs, localalias=localalias)
         return m(self)
 
     def url(self):
         return b'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @filteredpropertycache
     def _tagscache(self):
         """Returns a tagscache object that contains various tags related
         caches."""
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         rev = self.changelog.rev
         for k, v in pycompat.iteritems(tags):
             try:
                 # ignore tags to unknown nodes
                 rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         """Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object."""
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         # map tag name to (node, hist)
         alltags = tagsmod.findglobaltags(self.ui, self)
         # map tag name to tag type
         tagtypes = {tag: b'global' for tag in alltags}
 
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in pycompat.iteritems(alltags):
             if node != self.nullid:
                 tags[encoding.tolocal(name)] = node
         tags[b'tip'] = self.changelog.tip()
         tagtypes = {
             encoding.tolocal(name): value
             for (name, value) in pycompat.iteritems(tagtypes)
         }
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         """
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         """
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in pycompat.iteritems(self.tags()):
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in pycompat.iteritems(self._tagscache.tags):
                 nodetagscache.setdefault(n, []).append(t)
             for tags in pycompat.itervalues(nodetagscache):
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         return self._bookmarks.names(node)
 
     def branchmap(self):
         """returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number"""
         return self._branchcaches[self]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def register_changeset(self, rev, changelogrevision):
         self.revbranchcache().setdata(rev, changelogrevision)
 
     def branchtip(self, branch, ignoremissing=False):
         """return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         """
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_(b"unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         node = scmutil.revsymbol(self, key).node()
         if node is None:
             raise error.RepoLookupError(_(b"unknown revision '%s'") % key)
         return node
 
     def lookupbranch(self, key):
         if self.branchmap().hasbranch(key):
             return key
 
         return scmutil.revsymbol(self, key).branch()
 
     def known(self, nodes):
         cl = self.changelog
         get_rev = cl.index.get_rev
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = get_rev(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool(b'phases', b'publish', untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered(b'visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return b'store'
         return None
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def setparents(self, p1, p2=None):
         if p2 is None:
             p2 = self.nullid
         self[None].setparents(p1, p2)
         self._quick_access_changeid_invalidate()
 
     def filectx(self, path, changeid=None, fileid=None, changectx=None):
         """changeid must be a changeset revision, if specified.
         fileid can be a file revision or node."""
         return context.filectx(
             self, path, changeid, fileid, changectx=changectx
         )
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def _loadfilter(self, filter):
         if filter not in self._filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == b'!':
                     continue
                 mf = matchmod.match(self.root, b'', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in pycompat.iteritems(self._datafilters):
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name) :].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: procutil.filter(s, c)
                     fn.__name__ = 'commandfilter'
                 # Wrap old filters not supporting keyword arguments
                 if not pycompat.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, oldfn=oldfn, **kwargs: oldfn(s, c)
                     fn.__name__ = 'compat-' + oldfn.__name__
                 l.append((mf, fn, params))
             self._filterpats[filter] = l
         return self._filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug(
                     b"filtering %s through %s\n"
                     % (filename, cmd or pycompat.sysbytes(fn.__name__))
                 )
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter(b'encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter(b'decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self.wvfs.islink(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False, **kwargs):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if b'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(
                 filename, data, backgroundclose=backgroundclose, **kwargs
             )
             if b'x' in flags:
                 self.wvfs.setflags(filename, False, True)
             else:
                 self.wvfs.setflags(filename, False, False)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if self.ui.configbool(b'devel', b'all-warnings') or self.ui.configbool(
             b'devel', b'check-locks'
         ):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError(b'transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest(name=desc)
 
         # abort here if the journal already exists
         if self.svfs.exists(b"journal"):
             raise error.RepoError(
                 _(b"abandoned transaction found"),
                 hint=_(b"run 'hg recover' to clean up transaction"),
             )
 
         idbase = b"%.40f#%f" % (random.random(), time.time())
         ha = hex(hashutil.sha1(idbase).digest())
         txnid = b'TXN:' + ha
         self.hook(b'pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {b'plain': self.vfs, b'store': self.svfs}  # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         # Code to track tag movement
         #
         # Since tags are all handled as file content, it is actually quite hard
         # to track these movement from a code perspective. So we fallback to a
         # tracking at the repository level. One could envision to track changes
         # to the '.hgtags' file through changegroup apply but that fails to
         # cope with case where transaction expose new heads without changegroup
         # being involved (eg: phase movement).
         #
         # For now, We gate the feature behind a flag since this likely comes
         # with performance impacts. The current code run more often than needed
         # and do not use caches as much as it could.  The current focus is on
         # the behavior of the feature so we disable it by default. The flag
         # will be removed when we are happy with the performance impact.
         #
         # Once this feature is no longer experimental move the following
         # documentation to the appropriate help section:
         #
         # The ``HG_TAG_MOVED`` variable will be set if the transaction touched
         # tags (new or changed or deleted tags). In addition the details of
         # these changes are made available in a file at:
         #     ``REPOROOT/.hg/changes/tags.changes``.
         # Make sure you check for HG_TAG_MOVED before reading that file as it
         # might exist from a previous transaction even if no tag were touched
         # in this one. Changes are recorded in a line base format::
         #
         #     <action> <hex-node> <tag-name>\n
         #
         # Actions are defined as follow:
         #   "-R": tag is removed,
         #   "+A": tag is added,
         #   "-M": tag is moved (old value),
         #   "+M": tag is moved (new value),
         tracktags = lambda x: None
         # experimental config: experimental.hook-track-tags
         shouldtracktags = self.ui.configbool(
             b'experimental', b'hook-track-tags'
         )
         if desc != b'strip' and shouldtracktags:
             oldheads = self.changelog.headrevs()
 
             def tracktags(tr2):
                 repo = reporef()
                 assert repo is not None  # help pytype
                 oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads)
                 newheads = repo.changelog.headrevs()
                 newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads)
                 # notes: we compare lists here.
                 # As we do it only once buiding set would not be cheaper
                 changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes)
                 if changes:
                     tr2.hookargs[b'tag_moved'] = b'1'
                     with repo.vfs(
                         b'changes/tags.changes', b'w', atomictemp=True
                     ) as changesfile:
                         # note: we do not register the file to the transaction
                         # because we needs it to still exist on the transaction
                         # is close (for txnclose hooks)
                         tagsmod.writediff(changesfile, changes)
 
         def validate(tr2):
             """will run pre-closing hooks"""
             # XXX the transaction API is a bit lacking here so we take a hacky
             # path for now
             #
             # We cannot add this as a "pending" hooks since the 'tr.hookargs'
             # dict is copied before these run. In addition we needs the data
             # available to in memory hooks too.
             #
             # Moreover, we also need to make sure this runs before txnclose
             # hooks and there is no "pending" mechanism that would execute
             # logic only if hooks are about to run.
             #
             # Fixing this limitation of the transaction is also needed to track
             # other families of changes (bookmarks, phases, obsolescence).
             #
             # This will have to be fixed before we remove the experimental
             # gating.
             tracktags(tr2)
             repo = reporef()
             assert repo is not None  # help pytype
 
             singleheadopt = (b'experimental', b'single-head-per-branch')
             singlehead = repo.ui.configbool(*singleheadopt)
             if singlehead:
                 singleheadsub = repo.ui.configsuboptions(*singleheadopt)[1]
                 accountclosed = singleheadsub.get(
                     b"account-closed-heads", False
                 )
                 if singleheadsub.get(b"public-changes-only", False):
                     filtername = b"immutable"
                 else:
                     filtername = b"visible"
                 scmutil.enforcesinglehead(
                     repo, tr2, desc, accountclosed, filtername
                 )
             if hook.hashook(repo.ui, b'pretxnclose-bookmark'):
                 for name, (old, new) in sorted(
                     tr.changes[b'bookmarks'].items()
                 ):
                     args = tr.hookargs.copy()
                     args.update(bookmarks.preparehookargs(name, old, new))
                     repo.hook(
                         b'pretxnclose-bookmark',
                         throw=True,
                         **pycompat.strkwargs(args)
                     )
             if hook.hashook(repo.ui, b'pretxnclose-phase'):
                 cl = repo.unfiltered().changelog
                 for revs, (old, new) in tr.changes[b'phases']:
                     for rev in revs:
                         args = tr.hookargs.copy()
                         node = hex(cl.node(rev))
                         args.update(phases.preparehookargs(node, old, new))
                         repo.hook(
                             b'pretxnclose-phase',
                             throw=True,
                             **pycompat.strkwargs(args)
                         )
 
             repo.hook(
                 b'pretxnclose', throw=True, **pycompat.strkwargs(tr.hookargs)
             )
 
         def releasefn(tr, success):
             repo = reporef()
             if repo is None:
                 # If the repo has been GC'd (and this release function is being
                 # called from transaction.__del__), there's not much we can do,
                 # so just leave the unfinished transaction there and let the
                 # user run `hg recover`.
                 return
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 narrowspec.restorebackup(self, b'journal.narrowspec')
                 narrowspec.restorewcbackup(self, b'journal.narrowspec.dirstate')
                 repo.dirstate.restorebackup(None, b'journal.dirstate')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(
             rp,
             self.svfs,
             vfsmap,
             b"journal",
             b"undo",
             aftertrans(renames),
             self.store.createmode,
             validator=validate,
             releasefn=releasefn,
             checkambigfiles=_cachedfiles,
             name=desc,
         )
         tr.changes[b'origrepolen'] = len(self)
         tr.changes[b'obsmarkers'] = set()
         tr.changes[b'phases'] = []
         tr.changes[b'bookmarks'] = {}
 
         tr.hookargs[b'txnid'] = txnid
         tr.hookargs[b'txnname'] = desc
         tr.hookargs[b'changes'] = tr.changes
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize(b'flush-fncache', self.store.write)
 
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run"""
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hookfunc(unused_success):
                 repo = reporef()
                 assert repo is not None  # help pytype
 
                 if hook.hashook(repo.ui, b'txnclose-bookmark'):
                     bmchanges = sorted(tr.changes[b'bookmarks'].items())
                     for name, (old, new) in bmchanges:
                         args = tr.hookargs.copy()
                         args.update(bookmarks.preparehookargs(name, old, new))
                         repo.hook(
                             b'txnclose-bookmark',
                             throw=False,
                             **pycompat.strkwargs(args)
                         )
 
                 if hook.hashook(repo.ui, b'txnclose-phase'):
                     cl = repo.unfiltered().changelog
                     phasemv = sorted(
                         tr.changes[b'phases'], key=lambda r: r[0][0]
                     )
                     for revs, (old, new) in phasemv:
                         for rev in revs:
                             args = tr.hookargs.copy()
                             node = hex(cl.node(rev))
                             args.update(phases.preparehookargs(node, old, new))
                             repo.hook(
                                 b'txnclose-phase',
                                 throw=False,
                                 **pycompat.strkwargs(args)
                             )
 
                 repo.hook(
                     b'txnclose', throw=False, **pycompat.strkwargs(hookargs)
                 )
 
             repo = reporef()
             assert repo is not None  # help pytype
             repo._afterlock(hookfunc)
 
         tr.addfinalize(b'txnclose-hook', txnclosehook)
         # Include a leading "-" to make it happen before the transaction summary
         # reports registered via scmutil.registersummarycallback() whose names
         # are 00-txnreport etc. That way, the caches will be warm when the
         # callbacks run.
         tr.addpostclose(b'-warm-cache', self._buildcacheupdater(tr))
 
         def txnaborthook(tr2):
             """To be run if transaction is aborted"""
             repo = reporef()
             assert repo is not None  # help pytype
             repo.hook(
                 b'txnabort', throw=False, **pycompat.strkwargs(tr2.hookargs)
             )
 
         tr.addabort(b'txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose(b'refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         scmutil.registersummarycallback(self, tr, desc)
         return tr
 
     def _journalfiles(self):
         return (
             (self.svfs, b'journal'),
             (self.svfs, b'journal.narrowspec'),
             (self.vfs, b'journal.narrowspec.dirstate'),
             (self.vfs, b'journal.dirstate'),
             (self.vfs, b'journal.branch'),
             (self.vfs, b'journal.desc'),
             (bookmarks.bookmarksvfs(self), b'journal.bookmarks'),
             (self.svfs, b'journal.phaseroots'),
         )
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     @unfilteredmethod
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, b'journal.dirstate')
         narrowspec.savewcbackup(self, b'journal.narrowspec.dirstate')
         narrowspec.savebackup(self, b'journal.narrowspec')
         self.vfs.write(
             b"journal.branch", encoding.fromlocal(self.dirstate.branch())
         )
         self.vfs.write(b"journal.desc", b"%d\n%s\n" % (len(self), desc))
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         bookmarksvfs.write(
             b"journal.bookmarks", bookmarksvfs.tryread(b"bookmarks")
         )
         self.svfs.write(b"journal.phaseroots", self.svfs.tryread(b"phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists(b"journal"):
                 self.ui.status(_(b"rolling back interrupted transaction\n"))
                 vfsmap = {
                     b'': self.svfs,
                     b'plain': self.vfs,
                 }
                 transaction.rollback(
                     self.svfs,
                     vfsmap,
                     b"journal",
                     self.ui.warn,
                     checkambigfiles=_cachedfiles,
                 )
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_(b"no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists(b"undo"):
                 dsguard = dirstateguard.dirstateguard(self, b'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_(b"no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod  # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read(b'undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = _(
                     b'repository tip rolled back to revision %d'
                     b' (undo %s: %s)\n'
                 ) % (oldtip, desc, detail)
             else:
                 msg = _(
                     b'repository tip rolled back to revision %d (undo %s)\n'
                 ) % (oldtip, desc)
         except IOError:
             msg = _(b'rolling back unknown transaction\n')
             desc = None
 
         if not force and self[b'.'] != self[b'tip'] and desc == b'commit':
             raise error.Abort(
                 _(
                     b'rollback of last commit while not checked out '
                     b'may lose data'
                 ),
                 hint=_(b'use -f to force'),
             )
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {b'plain': self.vfs, b'': self.svfs}
         transaction.rollback(
             self.svfs, vfsmap, b'undo', ui.warn, checkambigfiles=_cachedfiles
         )
         bookmarksvfs = bookmarks.bookmarksvfs(self)
         if bookmarksvfs.exists(b'undo.bookmarks'):
             bookmarksvfs.rename(
                 b'undo.bookmarks', b'bookmarks', checkambig=True
             )
         if self.svfs.exists(b'undo.phaseroots'):
             self.svfs.rename(b'undo.phaseroots', b'phaseroots', checkambig=True)
         self.invalidate()
 
         has_node = self.changelog.index.has_node
         parentgone = any(not has_node(p) for p in parents)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, b'undo.narrowspec')
             narrowspec.restorewcbackup(self, b'undo.narrowspec.dirstate')
             self.dirstate.restorebackup(None, b'undo.dirstate')
             try:
                 branch = self.vfs.read(b'undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(
                     _(
                         b'named branch could not be reset: '
                         b'current branch is still \'%s\'\n'
                     )
                     % self.dirstate.branch()
                 )
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(
                     _(
                         b'working directory now based on '
                         b'revisions %d and %d\n'
                     )
                     % parents
                 )
             else:
                 ui.status(
                     _(b'working directory now based on revision %d\n') % parents
                 )
             mergestatemod.mergestate.clean(self)
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def _buildcacheupdater(self, newtransaction):
         """called during transaction to build the callback updating cache
 
         Lives on the repository to help extension who might want to augment
         this logic. For this purpose, the created transaction is passed to the
         method.
         """
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
 
         def updater(tr):
             repo = reporef()
             assert repo is not None  # help pytype
             repo.updatecaches(tr)
 
         return updater
 
     @unfilteredmethod
     def updatecaches(self, tr=None, full=False, caches=None):
         """warm appropriate caches
 
         If this function is called after a transaction closed. The transaction
         will be available in the 'tr' argument. This can be used to selectively
         update caches relevant to the changes in that transaction.
 
         If 'full' is set, make sure all caches the function knows about have
         up-to-date data. Even the ones usually loaded more lazily.
 
         The `full` argument can take a special "post-clone" value. In this case
         the cache warming is made after a clone and of the slower cache might
         be skipped, namely the `.fnodetags` one. This argument is 5.8 specific
         as we plan for a cleaner way to deal with this for 5.9.
         """
         if tr is not None and tr.hookargs.get(b'source') == b'strip':
             # During strip, many caches are invalid but
             # later call to `destroyed` will refresh them.
             return
 
         unfi = self.unfiltered()
 
         if full:
             msg = (
                 "`full` argument for `repo.updatecaches` is deprecated\n"
                 "(use `caches=repository.CACHE_ALL` instead)"
             )
             self.ui.deprecwarn(msg, b"5.9")
             caches = repository.CACHES_ALL
             if full == b"post-clone":
                 caches = repository.CACHES_POST_CLONE
             caches = repository.CACHES_ALL
         elif caches is None:
             caches = repository.CACHES_DEFAULT
 
         if repository.CACHE_BRANCHMAP_SERVED in caches:
             if tr is None or tr.changes[b'origrepolen'] < len(self):
                 # accessing the 'served' branchmap should refresh all the others,
                 self.ui.debug(b'updating the branch cache\n')
                 self.filtered(b'served').branchmap()
                 self.filtered(b'served.hidden').branchmap()
 
         if repository.CACHE_CHANGELOG_CACHE in caches:
             self.changelog.update_caches(transaction=tr)
 
         if repository.CACHE_MANIFESTLOG_CACHE in caches:
             self.manifestlog.update_caches(transaction=tr)
 
         if repository.CACHE_REV_BRANCH in caches:
             rbc = unfi.revbranchcache()
             for r in unfi.changelog:
                 rbc.branchinfo(r)
             rbc.write()
 
         if repository.CACHE_FULL_MANIFEST in caches:
             # ensure the working copy parents are in the manifestfulltextcache
             for ctx in self[b'.'].parents():
                 ctx.manifest()  # accessing the manifest is enough
 
         if repository.CACHE_FILE_NODE_TAGS in caches:
             # accessing fnode cache warms the cache
             tagsmod.fnoderevs(self.ui, unfi, unfi.changelog.revs())
 
         if repository.CACHE_TAGS_DEFAULT in caches:
             # accessing tags warm the cache
             self.tags()
         if repository.CACHE_TAGS_SERVED in caches:
             self.filtered(b'served').tags()
 
         if repository.CACHE_BRANCHMAP_ALL in caches:
             # The CACHE_BRANCHMAP_ALL updates lazily-loaded caches immediately,
             # so we're forcing a write to cause these caches to be warmed up
             # even if they haven't explicitly been requested yet (if they've
             # never been used by hg, they won't ever have been written, even if
             # they're a subset of another kind of cache that *has* been used).
             for filt in repoview.filtertable.keys():
                 filtered = self.filtered(filt)
                 filtered.branchmap().write(filtered)
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self._branchcaches.clear()
         self.invalidatevolatilesets()
         self._sparsesignaturecache.clear()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
         self._quick_access_changeid_invalidate()
 
     def invalidatedirstate(self):
         """Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state)."""
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self, clearfilecache=False):
         """Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         """
         unfiltered = self.unfiltered()  # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == b'dirstate':
                 continue
             if (
                 k == b'changelog'
                 and self.currenttransaction()
                 and self.changelog._delayed
             ):
                 # The changelog object may store unwritten revisions. We don't
                 # want to lose them.
                 # TODO: Solve the problem instead of working around it.
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         """Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes."""
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             k = pycompat.sysstr(k)
             if k == 'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(
         self,
         vfs,
         lockname,
         wait,
         releasefn,
         acquirefn,
         desc,
     ):
         timeout = 0
         warntimeout = 0
         if wait:
             timeout = self.ui.configint(b"ui", b"timeout")
             warntimeout = self.ui.configint(b"ui", b"timeout.warn")
         # internal config: ui.signal-safe-lock
         signalsafe = self.ui.configbool(b'ui', b'signal-safe-lock')
 
         l = lockmod.trylock(
             self.ui,
             vfs,
             lockname,
             timeout,
             warntimeout,
             releasefn=releasefn,
             acquirefn=acquirefn,
             desc=desc,
             signalsafe=signalsafe,
         )
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else:  # no lock have been found.
             callback(True)
 
     def lock(self, wait=True):
         """Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard."""
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(
             vfs=self.svfs,
             lockname=b"lock",
             wait=wait,
             releasefn=None,
             acquirefn=self.invalidate,
             desc=_(b'repository %s') % self.origroot,
         )
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         """Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard."""
         l = self._wlockref() if self._wlockref else None
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (
             self.ui.configbool(b'devel', b'all-warnings')
             or self.ui.configbool(b'devel', b'check-locks')
         ):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn(b'"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache[b'dirstate'].refresh()
 
         l = self._lock(
             self.vfs,
             b"wlock",
             wait,
             unlock,
             self.invalidatedirstate,
             _(b'working directory of %s') % self.origroot,
         )
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def checkcommitpatterns(self, wctx, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == b'.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _(b'file not found!'))
                 # Is it a directory that exists or used to exist?
                 if self.wvfs.isdir(f) or wctx.p1().hasdir(f):
                     d = f + b'/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _(b"no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _(b"file not tracked!"))
 
     @unfilteredmethod
     def commit(
         self,
         text=b"",
         user=None,
         date=None,
         match=None,
         force=False,
         editor=None,
         extra=None,
     ):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.InputError(b'%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always()
 
         if not force:
             match.bad = fail
 
         # lock() for recent changelog (see issue4368)
         with self.wlock(), self.lock():
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and not match.always():
                 raise error.Abort(
                     _(
                         b'cannot partially commit a merge '
                         b'(do not specify files or patterns)'
                     )
                 )
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(
                     status.clean
                 )  # mq may commit clean files
 
             # check subrepos
             subs, commitsubs, newstate = subrepoutil.precommit(
                 self.ui, wctx, status, match, force=force
             )
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, match, status, fail)
 
             cctx = context.workingcommitctx(
                 self, status, text, user, date, extra
             )
 
             ms = mergestatemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             # internal config: ui.allowemptycommit
             if cctx.isempty() and not self.ui.configbool(
                 b'ui', b'allowemptycommit'
             ):
                 self.ui.debug(b'nothing to commit, clearing merge state\n')
                 ms.reset()
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_(b"cannot commit merge with missing files"))
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = text != cctx._text
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 uipathfn = scmutil.getuipathfn(self)
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(
                         _(b'committing subrepository %s\n')
                         % uipathfn(subrepoutil.subrelpath(sub))
                     )
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepoutil.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != self.nullid and hex(p2) or b'')
             try:
                 self.hook(
                     b"precommit", throw=True, parent1=hookp1, parent2=hookp2
                 )
                 with self.transaction(b'commit'):
                     ret = self.commitctx(cctx, True)
                     # update bookmarks, dirstate and mergestate
                     bookmarks.update(self, [p1, p2], ret)
                     cctx.markcommitted(ret)
                     ms.reset()
             except:  # re-raises
                 if edited:
                     self.ui.write(
                         _(b'note: commit message saved in %s\n') % msgfn
                     )
                     self.ui.write(
                         _(
                             b"note: use 'hg commit --logfile "
                             b".hg/last-message.txt --edit' to reuse it\n"
                         )
                     )
                 raise
 
         def commithook(unused_success):
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook(
                     b"commit", node=hex(ret), parent1=hookp1, parent2=hookp2
                 )
 
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False, origctx=None):
         return commit.commitctx(self, ctx, error=error, origctx=origctx)
 
     @unfilteredmethod
     def destroying(self):
         """Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         """
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         """Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         """
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # refresh all repository caches
         self.updatecaches()
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def status(
         self,
         node1=b'.',
         node2=None,
         match=None,
         ignored=False,
         clean=False,
         unknown=False,
         listsubrepos=False,
     ):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(
             node2, match, ignored, clean, unknown, listsubrepos
         )
 
     def addpostdsstatus(self, ps):
         """Add a callback to run within the wlock, at the point at which status
         fixups happen.
 
         On status completion, callback(wctx, status) will be called with the
         wlock held, unless the dirstate has changed from underneath or the wlock
         couldn't be grabbed.
 
         Callbacks should not capture and use a cached copy of the dirstate --
         it might change in the meanwhile. Instead, they should access the
         dirstate via wctx.repo().dirstate.
 
         This list is emptied out after each status run -- extensions should
         make sure it adds to this list each time dirstate.status is called.
         Extensions should also make sure they don't call this for statuses
         that don't involve the dirstate.
         """
 
         # The list is located here for uniqueness reasons -- it is actually
         # managed by the workingctx, but that isn't unique per-repo.
         self._postdsstatus.append(ps)
 
     def postdsstatus(self):
         """Used by workingctx to get the list of post-dirstate-status hooks."""
         return self._postdsstatus
 
     def clearpostdsstatus(self):
         """Used by workingctx to clear post-dirstate-status hooks."""
         del self._postdsstatus[:]
 
     def heads(self, start=None):
         if start is None:
             cl = self.changelog
             headrevs = reversed(cl.headrevs())
             return [cl.node(rev) for rev in headrevs]
 
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         """return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         """
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if not branches.hasbranch(branch):
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != self.nullid or p[0] == self.nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != self.nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs = pycompat.strkwargs(hookargs)
             hookargs['namespace'] = namespace
             hookargs['key'] = key
             hookargs['old'] = old
             hookargs['new'] = new
             self.hook(b'prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_(b"pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_(b"(%s)\n") % exc.hint)
             return False
         self.ui.debug(b'pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
 
         def runhook(unused_success):
             self.hook(
                 b'pushkey',
                 namespace=namespace,
                 key=key,
                 old=old,
                 new=new,
                 ret=ret,
             )
 
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook(b'prelistkeys', throw=True, namespace=namespace)
         self.ui.debug(b'listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook(b'listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return b"%s %s %s %s %s" % (
             one,
             two,
             pycompat.bytestr(three),
             pycompat.bytestr(four),
             pycompat.bytestr(five),
         )
 
     def savecommitmessage(self, text):
         fp = self.vfs(b'last-message.txt', b'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1 :])
 
     def register_wanted_sidedata(self, category):
         if repository.REPO_FEATURE_SIDE_DATA not in self.features:
             # Only revlogv2 repos can want sidedata.
             return
         self._wanted_sidedata.add(pycompat.bytestr(category))
 
     def register_sidedata_computer(
         self, kind, category, keys, computer, flags, replace=False
     ):
         if kind not in revlogconst.ALL_KINDS:
             msg = _(b"unexpected revlog kind '%s'.")
             raise error.ProgrammingError(msg % kind)
         category = pycompat.bytestr(category)
         already_registered = category in self._sidedata_computers.get(kind, [])
         if already_registered and not replace:
             msg = _(
                 b"cannot register a sidedata computer twice for category '%s'."
             )
             raise error.ProgrammingError(msg % category)
         if replace and not already_registered:
             msg = _(
                 b"cannot replace a sidedata computer that isn't registered "
                 b"for category '%s'."
             )
             raise error.ProgrammingError(msg % category)
         self._sidedata_computers.setdefault(kind, {})
         self._sidedata_computers[kind][category] = (keys, computer, flags)
 
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
 
     def a():
         for vfs, src, dest in renamefiles:
             # if src and dest refer to a same file, vfs.rename is a no-op,
             # leaving both src and dest on disk. delete dest to make sure
             # the rename couldn't be such a no-op.
             vfs.tryunlink(dest)
             try:
                 vfs.rename(src, dest)
             except OSError as exc:  # journal file does not yet exist
                 if exc.errno != errno.ENOENT:
                     raise
 
     return a
 
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith(b'journal')
     return os.path.join(base, name.replace(b'journal', b'undo', 1))
 
 
 def instance(ui, path, create, intents=None, createopts=None):
     localpath = urlutil.urllocalpath(path)
     if create:
         createrepository(ui, localpath, createopts=createopts)
 
     return makelocalrepository(ui, localpath, intents=intents)
 
 
 def islocal(path):
     return True
 
 
 def defaultcreateopts(ui, createopts=None):
     """Populate the default creation options for a repository.
 
     A dictionary of explicitly requested creation options can be passed
     in. Missing keys will be populated.
     """
     createopts = dict(createopts or {})
 
     if b'backend' not in createopts:
         # experimental config: storage.new-repo-backend
         createopts[b'backend'] = ui.config(b'storage', b'new-repo-backend')
 
     return createopts
 
 
 def clone_requirements(ui, createopts, srcrepo):
     """clone the requirements of a local repo for a local clone
 
     The store requirements are unchanged while the working copy requirements
     depends on the configuration
     """
     target_requirements = set()
     createopts = defaultcreateopts(ui, createopts=createopts)
     for r in newreporequirements(ui, createopts):
         if r in requirementsmod.WORKING_DIR_REQUIREMENTS:
             target_requirements.add(r)
 
     for r in srcrepo.requirements:
         if r not in requirementsmod.WORKING_DIR_REQUIREMENTS:
             target_requirements.add(r)
     return target_requirements
 
 
 def newreporequirements(ui, createopts):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     # If the repo is being created from a shared repository, we copy
     # its requirements.
     if b'sharedrepo' in createopts:
         requirements = set(createopts[b'sharedrepo'].requirements)
         if createopts.get(b'sharedrelative'):
             requirements.add(requirementsmod.RELATIVE_SHARED_REQUIREMENT)
         else:
             requirements.add(requirementsmod.SHARED_REQUIREMENT)
 
         return requirements
 
     if b'backend' not in createopts:
         raise error.ProgrammingError(
             b'backend key not present in createopts; '
             b'was defaultcreateopts() called?'
         )
 
     if createopts[b'backend'] != b'revlogv1':
         raise error.Abort(
             _(
                 b'unable to determine repository requirements for '
                 b'storage backend: %s'
             )
             % createopts[b'backend']
         )
 
     requirements = {requirementsmod.REVLOGV1_REQUIREMENT}
     if ui.configbool(b'format', b'usestore'):
         requirements.add(requirementsmod.STORE_REQUIREMENT)
         if ui.configbool(b'format', b'usefncache'):
             requirements.add(requirementsmod.FNCACHE_REQUIREMENT)
             if ui.configbool(b'format', b'dotencode'):
                 requirements.add(requirementsmod.DOTENCODE_REQUIREMENT)
 
     compengines = ui.configlist(b'format', b'revlog-compression')
     for compengine in compengines:
         if compengine in util.compengines:
             engine = util.compengines[compengine]
             if engine.available() and engine.revlogheader():
                 break
     else:
         raise error.Abort(
             _(
                 b'compression engines %s defined by '
                 b'format.revlog-compression not available'
             )
             % b', '.join(b'"%s"' % e for e in compengines),
             hint=_(
                 b'run "hg debuginstall" to list available '
                 b'compression engines'
             ),
         )
 
     # zlib is the historical default and doesn't need an explicit requirement.
     if compengine == b'zstd':
         requirements.add(b'revlog-compression-zstd')
     elif compengine != b'zlib':
         requirements.add(b'exp-compression-%s' % compengine)
 
     if scmutil.gdinitconfig(ui):
         requirements.add(requirementsmod.GENERALDELTA_REQUIREMENT)
         if ui.configbool(b'format', b'sparse-revlog'):
             requirements.add(requirementsmod.SPARSEREVLOG_REQUIREMENT)
 
     # experimental config: format.exp-dirstate-v2
     # Keep this logic in sync with `has_dirstate_v2()` in `tests/hghave.py`
     if ui.configbool(b'format', b'exp-dirstate-v2'):
-        if dirstate.SUPPORTS_DIRSTATE_V2:
-            requirements.add(requirementsmod.DIRSTATE_V2_REQUIREMENT)
-        else:
-            raise error.Abort(
-                _(
-                    b"dirstate v2 format requested by config "
-                    b"but not supported (requires Rust extensions)"
-                )
-            )
+        requirements.add(requirementsmod.DIRSTATE_V2_REQUIREMENT)
 
     # experimental config: format.exp-use-copies-side-data-changeset
     if ui.configbool(b'format', b'exp-use-copies-side-data-changeset'):
         requirements.add(requirementsmod.CHANGELOGV2_REQUIREMENT)
         requirements.add(requirementsmod.COPIESSDC_REQUIREMENT)
     if ui.configbool(b'experimental', b'treemanifest'):
         requirements.add(requirementsmod.TREEMANIFEST_REQUIREMENT)
 
     changelogv2 = ui.config(b'format', b'exp-use-changelog-v2')
     if changelogv2 == b'enable-unstable-format-and-corrupt-my-data':
         requirements.add(requirementsmod.CHANGELOGV2_REQUIREMENT)
 
     revlogv2 = ui.config(b'experimental', b'revlogv2')
     if revlogv2 == b'enable-unstable-format-and-corrupt-my-data':
         requirements.discard(requirementsmod.REVLOGV1_REQUIREMENT)
         requirements.add(requirementsmod.REVLOGV2_REQUIREMENT)
     # experimental config: format.internal-phase
     if ui.configbool(b'format', b'internal-phase'):
         requirements.add(requirementsmod.INTERNAL_PHASE_REQUIREMENT)
 
     if createopts.get(b'narrowfiles'):
         requirements.add(requirementsmod.NARROW_REQUIREMENT)
 
     if createopts.get(b'lfs'):
         requirements.add(b'lfs')
 
     if ui.configbool(b'format', b'bookmarks-in-store'):
         requirements.add(bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT)
 
     if ui.configbool(b'format', b'use-persistent-nodemap'):
         requirements.add(requirementsmod.NODEMAP_REQUIREMENT)
 
     # if share-safe is enabled, let's create the new repository with the new
     # requirement
     if ui.configbool(b'format', b'use-share-safe'):
         requirements.add(requirementsmod.SHARESAFE_REQUIREMENT)
 
     return requirements
 
 
 def checkrequirementscompat(ui, requirements):
     """Checks compatibility of repository requirements enabled and disabled.
 
     Returns a set of requirements which needs to be dropped because dependend
     requirements are not enabled. Also warns users about it"""
 
     dropped = set()
 
     if requirementsmod.STORE_REQUIREMENT not in requirements:
         if bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT in requirements:
             ui.warn(
                 _(
                     b'ignoring enabled \'format.bookmarks-in-store\' config '
                     b'beacuse it is incompatible with disabled '
                     b'\'format.usestore\' config\n'
                 )
             )
             dropped.add(bookmarks.BOOKMARKS_IN_STORE_REQUIREMENT)
 
         if (
             requirementsmod.SHARED_REQUIREMENT in requirements
             or requirementsmod.RELATIVE_SHARED_REQUIREMENT in requirements
         ):
             raise error.Abort(
                 _(
                     b"cannot create shared repository as source was created"
                     b" with 'format.usestore' config disabled"
                 )
             )
 
         if requirementsmod.SHARESAFE_REQUIREMENT in requirements:
             ui.warn(
                 _(
                     b"ignoring enabled 'format.use-share-safe' config because "
                     b"it is incompatible with disabled 'format.usestore'"
                     b" config\n"
                 )
             )
             dropped.add(requirementsmod.SHARESAFE_REQUIREMENT)
 
     return dropped
 
 
 def filterknowncreateopts(ui, createopts):
     """Filters a dict of repo creation options against options that are known.
 
     Receives a dict of repo creation options and returns a dict of those
     options that we don't know how to handle.
 
     This function is called as part of repository creation. If the
     returned dict contains any items, repository creation will not
     be allowed, as it means there was a request to create a repository
     with options not recognized by loaded code.
 
     Extensions can wrap this function to filter out creation options
     they know how to handle.
     """
     known = {
         b'backend',
         b'lfs',
         b'narrowfiles',
         b'sharedrepo',
         b'sharedrelative',
         b'shareditems',
         b'shallowfilestore',
     }
 
     return {k: v for k, v in createopts.items() if k not in known}
 
 
 def createrepository(ui, path, createopts=None, requirements=None):
     """Create a new repository in a vfs.
 
     ``path`` path to the new repo's working directory.
     ``createopts`` options for the new repository.
     ``requirement`` predefined set of requirements.
                     (incompatible with ``createopts``)
 
     The following keys for ``createopts`` are recognized:
 
     backend
        The storage backend to use.
     lfs
        Repository will be created with ``lfs`` requirement. The lfs extension
        will automatically be loaded when the repository is accessed.
     narrowfiles
        Set up repository to support narrow file storage.
     sharedrepo
        Repository object from which storage should be shared.
     sharedrelative
        Boolean indicating if the path to the shared repo should be
        stored as relative. By default, the pointer to the "parent" repo
        is stored as an absolute path.
     shareditems
        Set of items to share to the new repository (in addition to storage).
     shallowfilestore
        Indicates that storage for files should be shallow (not all ancestor
        revisions are known).
     """
 
     if requirements is not None:
         if createopts is not None:
             msg = b'cannot specify both createopts and requirements'
             raise error.ProgrammingError(msg)
         createopts = {}
     else:
         createopts = defaultcreateopts(ui, createopts=createopts)
 
         unknownopts = filterknowncreateopts(ui, createopts)
 
         if not isinstance(unknownopts, dict):
             raise error.ProgrammingError(
                 b'filterknowncreateopts() did not return a dict'
             )
 
         if unknownopts:
             raise error.Abort(
                 _(
                     b'unable to create repository because of unknown '
                     b'creation option: %s'
                 )
                 % b', '.join(sorted(unknownopts)),
                 hint=_(b'is a required extension not loaded?'),
             )
 
         requirements = newreporequirements(ui, createopts=createopts)
         requirements -= checkrequirementscompat(ui, requirements)
 
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     hgvfs = vfsmod.vfs(wdirvfs.join(b'.hg'))
     if hgvfs.exists():
         raise error.RepoError(_(b'repository %s already exists') % path)
 
     if b'sharedrepo' in createopts:
         sharedpath = createopts[b'sharedrepo'].sharedpath
 
         if createopts.get(b'sharedrelative'):
             try:
                 sharedpath = os.path.relpath(sharedpath, hgvfs.base)
                 sharedpath = util.pconvert(sharedpath)
             except (IOError, ValueError) as e:
                 # ValueError is raised on Windows if the drive letters differ
                 # on each path.
                 raise error.Abort(
                     _(b'cannot calculate relative path'),
                     hint=stringutil.forcebytestr(e),
                 )
 
     if not wdirvfs.exists():
         wdirvfs.makedirs()
 
     hgvfs.makedir(notindexed=True)
     if b'sharedrepo' not in createopts:
         hgvfs.mkdir(b'cache')
     hgvfs.mkdir(b'wcache')
 
     has_store = requirementsmod.STORE_REQUIREMENT in requirements
     if has_store and b'sharedrepo' not in createopts:
         hgvfs.mkdir(b'store')
 
         # We create an invalid changelog outside the store so very old
         # Mercurial versions (which didn't know about the requirements
         # file) encounter an error on reading the changelog. This
         # effectively locks out old clients and prevents them from
         # mucking with a repo in an unknown format.
         #
         # The revlog header has version 65535, which won't be recognized by
         # such old clients.
         hgvfs.append(
             b'00changelog.i',
             b'\0\0\xFF\xFF dummy changelog to prevent using the old repo '
             b'layout',
         )
 
     # Filter the requirements into working copy and store ones
     wcreq, storereq = scmutil.filterrequirements(requirements)
     # write working copy ones
     scmutil.writerequires(hgvfs, wcreq)
     # If there are store requirements and the current repository
     # is not a shared one, write stored requirements
     # For new shared repository, we don't need to write the store
     # requirements as they are already present in store requires
     if storereq and b'sharedrepo' not in createopts:
         storevfs = vfsmod.vfs(hgvfs.join(b'store'), cacheaudited=True)
         scmutil.writerequires(storevfs, storereq)
 
     # Write out file telling readers where to find the shared store.
     if b'sharedrepo' in createopts:
         hgvfs.write(b'sharedpath', sharedpath)
 
     if createopts.get(b'shareditems'):
         shared = b'\n'.join(sorted(createopts[b'shareditems'])) + b'\n'
         hgvfs.write(b'shared', shared)
 
 
 def poisonrepository(repo):
     """Poison a repository instance so it can no longer be used."""
     # Perform any cleanup on the instance.
     repo.close()
 
     # Our strategy is to replace the type of the object with one that
     # has all attribute lookups result in error.
     #
     # But we have to allow the close() method because some constructors
     # of repos call close() on repo references.
     class poisonedrepository(object):
         def __getattribute__(self, item):
             if item == 'close':
                 return object.__getattribute__(self, item)
 
             raise error.ProgrammingError(
                 b'repo instances should not be used after unshare'
             )
 
         def close(self):
             pass
 
     # We may have a repoview, which intercepts __setattr__. So be sure
     # we operate at the lowest level possible.
     object.__setattr__(repo, '__class__', poisonedrepository)

tests/test-dirstate-race.t

@@ -1,244 +1,243 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
   $ hg init repo
   $ cd repo
   $ echo a > a
   $ hg add a
   $ hg commit -m test
 
 Do we ever miss a sub-second change?:
 
   $ for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20; do
   >     hg co -qC 0
   >     echo b > a
   >     hg st
   > done
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
   M a
 
   $ echo test > b
   $ mkdir dir1
   $ echo test > dir1/c
   $ echo test > d
 
   $ echo test > e
 #if execbit
 A directory will typically have the execute bit -- make sure it doesn't get
 confused with a file with the exec bit set
   $ chmod +x e
 #endif
 
   $ hg add b dir1 d e
   adding dir1/c
   $ hg commit -m test2
 
   $ cat >> $TESTTMP/dirstaterace.py << EOF
   > from mercurial import (
   >     context,
   >     extensions,
   > )
   > def extsetup(ui):
   >     extensions.wrapfunction(context.workingctx, '_checklookup', overridechecklookup)
   > def overridechecklookup(orig, self, files):
   >     # make an update that changes the dirstate from underneath
   >     self._repo.ui.system(br"sh '$TESTTMP/dirstaterace.sh'",
   >                          cwd=self._repo.root)
   >     return orig(self, files)
   > EOF
 
   $ hg debugrebuilddirstate
   $ hg debugdirstate
   n   0         -1 unset               a
   n   0         -1 unset               b
   n   0         -1 unset               d
   n   0         -1 unset               dir1/c
   n   0         -1 unset               e
 
 XXX Note that this returns M for files that got replaced by directories. This is
 definitely a bug, but the fix for that is hard and the next status run is fine
 anyway.
 
   $ cat > $TESTTMP/dirstaterace.sh <<EOF
   > rm b && rm -r dir1 && rm d && mkdir d && rm e && mkdir e
   > EOF
 
   $ hg status --config extensions.dirstaterace=$TESTTMP/dirstaterace.py
   M d
   M e
   ! b
   ! dir1/c
   $ hg debugdirstate
   n 644          2 * a (glob)
   n   0         -1 unset               b
   n   0         -1 unset               d
   n   0         -1 unset               dir1/c
   n   0         -1 unset               e
 
   $ hg status
   ! b
   ! d
   ! dir1/c
   ! e
 
   $ rmdir d e
   $ hg update -C -q .
 
 Test that dirstate changes aren't written out at the end of "hg
 status", if .hg/dirstate is already changed simultaneously before
 acquisition of wlock in workingctx._poststatusfixup().
 
 This avoidance is important to keep consistency of dirstate in race
 condition (see issue5584 for detail).
 
   $ hg parents -q
   1:* (glob)
 
   $ hg debugrebuilddirstate
   $ hg debugdirstate
   n   0         -1 unset               a
   n   0         -1 unset               b
   n   0         -1 unset               d
   n   0         -1 unset               dir1/c
   n   0         -1 unset               e
 
   $ cat > $TESTTMP/dirstaterace.sh <<EOF
   > # This script assumes timetable of typical issue5584 case below:
   > #
   > # 1. "hg status" loads .hg/dirstate
   > # 2. "hg status" confirms clean-ness of FILE
   > # 3. "hg update -C 0" updates the working directory simultaneously
   > #    (FILE is removed, and FILE is dropped from .hg/dirstate)
   > # 4. "hg status" acquires wlock
   > #    (.hg/dirstate is re-loaded = no FILE entry in dirstate)
   > # 5. "hg status" marks FILE in dirstate as clean
   > #    (FILE entry is added to in-memory dirstate)
   > # 6. "hg status" writes dirstate changes into .hg/dirstate
   > #    (FILE entry is written into .hg/dirstate)
   > #
   > # To reproduce similar situation easily and certainly, #2 and #3
   > # are swapped.  "hg cat" below ensures #2 on "hg status" side.
   > 
   > hg update -q -C 0
   > hg cat -r 1 b > b
   > EOF
 
 "hg status" below should excludes "e", of which exec flag is set, for
 portability of test scenario, because unsure but missing "e" is
 treated differently in _checklookup() according to runtime platform.
 
 - "missing(!)" on POSIX, "pctx[f].cmp(self[f])" raises ENOENT
 - "modified(M)" on Windows, "self.flags(f) != pctx.flags(f)" is True
 
   $ hg status --config extensions.dirstaterace=$TESTTMP/dirstaterace.py --debug -X path:e
   skip updating dirstate: identity mismatch
   M a
   ! d
   ! dir1/c
 
   $ hg parents -q
   0:* (glob)
   $ hg files
   a
   $ hg debugdirstate
   n * * * a (glob)
 
   $ rm b
 
 #if fsmonitor
 
 Create fsmonitor state.
 
   $ hg status
   $ f --type .hg/fsmonitor.state
   .hg/fsmonitor.state: file
 
 Test that invalidating fsmonitor state in the middle (which doesn't require the
 wlock) causes the fsmonitor update to be skipped.
 hg debugrebuilddirstate ensures that the dirstaterace hook will be called, but
 it also invalidates the fsmonitor state. So back it up and restore it.
 
   $ mv .hg/fsmonitor.state .hg/fsmonitor.state.tmp
   $ hg debugrebuilddirstate
   $ mv .hg/fsmonitor.state.tmp .hg/fsmonitor.state
 
   $ cat > $TESTTMP/dirstaterace.sh <<EOF
   > rm .hg/fsmonitor.state
   > EOF
 
   $ hg status --config extensions.dirstaterace=$TESTTMP/dirstaterace.py --debug
   skip updating fsmonitor.state: identity mismatch
   $ f .hg/fsmonitor.state
   .hg/fsmonitor.state: file not found
 
 #endif
 
 Set up a rebase situation for issue5581.
 
   $ echo c2 > a
   $ echo c2 > b
   $ hg add b
   $ hg commit -m c2
   created new head
   $ echo c3 >> a
   $ hg commit -m c3
   $ hg update 2
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo c4 >> a
   $ echo c4 >> b
   $ hg commit -m c4
   created new head
 
 Configure a merge tool that runs status in the middle of the rebase. The goal of
 the status call is to trigger a potential bug if fsmonitor's state is written
 even though the wlock is held by another process. The output of 'hg status' in
 the merge tool goes to /dev/null because we're more interested in the results of
 'hg status' run after the rebase.
 
   $ cat >> $TESTTMP/mergetool-race.sh << EOF
   > echo "custom merge tool"
   > printf "c2\nc3\nc4\n" > \$1
   > hg --cwd "$TESTTMP/repo" status > /dev/null
   > echo "custom merge tool end"
   > EOF
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > rebase =
   > [merge-tools]
   > test.executable=sh
   > test.args=$TESTTMP/mergetool-race.sh \$output
   > EOF
 
   $ hg rebase -s . -d 3 --tool test
   rebasing 4:b08445fd6b2a tip "c4"
   merging a
   custom merge tool
   custom merge tool end
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/* (glob)
 
 This hg status should be empty, whether or not fsmonitor is enabled (issue5581).
 
   $ hg status

tests/test-dirstate-race2.t

@@ -1,45 +1,44 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
 Checking the size/permissions/file-type of files stored in the
 dirstate after an update where the files are changed concurrently
 outside of hg's control.
 
   $ hg init repo
   $ cd repo
   $ echo a > a
   $ hg commit -qAm _
   $ echo aa > a
   $ hg commit -m _
 
   $ hg debugdirstate --no-dates
   n 644          3 (set  |unset)               a (re)
 
   $ cat >> $TESTTMP/dirstaterace.py << EOF
   > from mercurial import (
   >     extensions,
   >     merge,
   > )
   > def extsetup(ui):
   >     extensions.wrapfunction(merge, 'applyupdates', wrap)
   > def wrap(orig, *args, **kwargs):
   >     res = orig(*args, **kwargs)
   >     with open("a", "w"):
   >         pass # just truncate the file
   >     return res
   > EOF
 
 Do an update where file 'a' is changed between hg writing it to disk
 and hg writing the dirstate. The dirstate is correct nonetheless, and
 so hg status correctly shows a as clean.
 
   $ hg up -r 0 --config extensions.race=$TESTTMP/dirstaterace.py
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg debugdirstate --no-dates
   n 644          2 (set  |unset)               a (re)
   $ echo a > a; hg status; hg diff

tests/test-dirstate.t

@@ -1,102 +1,101 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
 ------ Test dirstate._dirs refcounting
 
   $ hg init t
   $ cd t
   $ mkdir -p a/b/c/d
   $ touch a/b/c/d/x
   $ touch a/b/c/d/y
   $ touch a/b/c/d/z
   $ hg ci -Am m
   adding a/b/c/d/x
   adding a/b/c/d/y
   adding a/b/c/d/z
   $ hg mv a z
   moving a/b/c/d/x to z/b/c/d/x
   moving a/b/c/d/y to z/b/c/d/y
   moving a/b/c/d/z to z/b/c/d/z
 
 Test name collisions
 
   $ rm z/b/c/d/x
   $ mkdir z/b/c/d/x
   $ touch z/b/c/d/x/y
   $ hg add z/b/c/d/x/y
   abort: file 'z/b/c/d/x' in dirstate clashes with 'z/b/c/d/x/y'
   [255]
   $ rm -rf z/b/c/d
   $ touch z/b/c/d
   $ hg add z/b/c/d
   abort: directory 'z/b/c/d' already in dirstate
   [255]
 
   $ cd ..
 
 Issue1790: dirstate entry locked into unset if file mtime is set into
 the future
 
 Prepare test repo:
 
   $ hg init u
   $ cd u
   $ echo a > a
   $ hg add
   adding a
   $ hg ci -m1
 
 Set mtime of a into the future:
 
   $ touch -t 203101011200 a
 
 Status must not set a's entry to unset (issue1790):
 
   $ hg status
   $ hg debugstate
   n 644          2 2031-01-01 12:00:00 a
 
 Test modulo storage/comparison of absurd dates:
 
 #if no-aix
   $ touch -t 195001011200 a
   $ hg st
   $ hg debugstate
   n 644          2 2018-01-19 15:14:08 a
 #endif
 
 Verify that exceptions during a dirstate change leave the dirstate
 coherent (issue4353)
 
   $ cat > ../dirstateexception.py <<EOF
   > from __future__ import absolute_import
   > from mercurial import (
   >   error,
   >   extensions,
   >   mergestate as mergestatemod,
   > )
   > 
   > def wraprecordupdates(*args):
   >     raise error.Abort(b"simulated error while recording dirstateupdates")
   > 
   > def reposetup(ui, repo):
   >     extensions.wrapfunction(mergestatemod, 'recordupdates',
   >                             wraprecordupdates)
   > EOF
 
   $ hg rm a
   $ hg commit -m 'rm a'
   $ echo "[extensions]" >> .hg/hgrc
   $ echo "dirstateex=../dirstateexception.py" >> .hg/hgrc
   $ hg up 0
   abort: simulated error while recording dirstateupdates
   [255]
   $ hg log -r . -T '{rev}\n'
   1
   $ hg status
   ? a

tests/test-hgignore.t

@@ -1,417 +1,417 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
   $ hg init ignorerepo
   $ cd ignorerepo
 
 debugignore with no hgignore should be deterministic:
   $ hg debugignore
   <nevermatcher>
 
 Issue562: .hgignore requires newline at end:
 
   $ touch foo
   $ touch bar
   $ touch baz
   $ cat > makeignore.py <<EOF
   > f = open(".hgignore", "w")
   > f.write("ignore\n")
   > f.write("foo\n")
   > # No EOL here
   > f.write("bar")
   > f.close()
   > EOF
 
   $ "$PYTHON" makeignore.py
 
 Should display baz only:
 
   $ hg status
   ? baz
 
   $ rm foo bar baz .hgignore makeignore.py
 
   $ touch a.o
   $ touch a.c
   $ touch syntax
   $ mkdir dir
   $ touch dir/a.o
   $ touch dir/b.o
   $ touch dir/c.o
 
   $ hg add dir/a.o
   $ hg commit -m 0
   $ hg add dir/b.o
 
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "*.o" > .hgignore
   $ hg status
   abort: $TESTTMP/ignorerepo/.hgignore: invalid pattern (relre): *.o (glob)
   [255]
 
 Ensure given files are relative to cwd
 
   $ echo "dir/.*\.o" > .hgignore
   $ hg status -i
   I dir/c.o
 
   $ hg debugignore dir/c.o dir/missing.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   dir/missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   $ cd dir
   $ hg debugignore c.o missing.o
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
 
 For icasefs, inexact matches also work, except for missing files
 
 #if icasefs
   $ hg debugignore c.O missing.O
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.O is not ignored
 #endif
 
   $ cd ..
 
   $ echo ".*\.o" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 Ensure that comments work:
 
   $ touch 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ touch 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
   $ cat <<'EOF' >> .hgignore
   > # full-line comment
   >   # whitespace-only comment line
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\# # (escaped) backslash, then comment
   > ba0\\\#w # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\# # (escaped) backslashes, then comment
   > foo\#b # escaped comment character
   > quux\## escaped comment character at end of name
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? quu0#
   ? quu0\ (no-windows !)
 
   $ cat <<'EOF' > .hgignore
   > .*\.o
   > syntax: glob
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\#* # (escaped) backslash, then comment
   > ba0\\\#w* # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\#* # (escaped) backslashes, then comment
   > foo\#b* # escaped comment character
   > quux\## escaped comment character at end of name
   > quu0[\#]# escaped comment character inside [...]
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? ba1\\wat (no-windows !)
   ? baz\wat (no-windows !)
   ? quu0\ (no-windows !)
 
   $ rm 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ rm 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
 Check that '^\.' does not ignore the root directory:
 
   $ echo "^\." > .hgignore
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
 Test that patterns from ui.ignore options are read:
 
   $ echo > .hgignore
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.other = $TESTTMP/ignorerepo/.hg/testhgignore
   > EOF
   $ echo "glob:**.o" > .hg/testhgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 empty out testhgignore
   $ echo > .hg/testhgignore
 
 Test relative ignore path (issue4473):
 
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.relative = .hg/testhgignorerel
   > EOF
   $ echo "glob:*.o" > .hg/testhgignorerel
   $ cd dir
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
   $ hg debugignore
   <includematcher includes='.*\\.o(?:/|$)'>
 
   $ cd ..
   $ echo > .hg/testhgignorerel
   $ echo "syntax: glob" > .hgignore
   $ echo "re:.*\.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "syntax: invalid" > .hgignore
   $ hg status
   $TESTTMP/ignorerepo/.hgignore: ignoring invalid syntax 'invalid'
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "syntax: glob" > .hgignore
   $ echo "*.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "relglob:syntax*" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
 
   $ echo "relglob:*" > .hgignore
   $ hg status
   A dir/b.o
 
   $ cd dir
   $ hg status .
   A b.o
 
   $ hg debugignore
   <includematcher includes='.*(?:/|$)'>
 
   $ hg debugignore b.o
   b.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: '*') (glob)
 
   $ cd ..
 
 Check patterns that match only the directory
 
 "(fsmonitor !)" below assumes that fsmonitor is enabled with
 "walk_on_invalidate = false" (default), which doesn't involve
 re-walking whole repository at detection of .hgignore change.
 
   $ echo "^dir\$" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o (fsmonitor !)
   ? syntax
 
 Check recursive glob pattern matches no directories (dir/**/c.o matches dir/c.o)
 
   $ echo "syntax: glob" > .hgignore
   $ echo "dir/**/c.o" >> .hgignore
   $ touch dir/c.o
   $ mkdir dir/subdir
   $ touch dir/subdir/c.o
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? syntax
   $ hg debugignore a.c
   a.c is not ignored
   $ hg debugignore dir/c.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 2: 'dir/**/c.o') (glob)
 
 Check rooted globs
 
   $ hg purge --all --config extensions.purge=
   $ echo "syntax: rootglob" > .hgignore
   $ echo "a/*.ext" >> .hgignore
   $ for p in a b/a aa; do mkdir -p $p; touch $p/b.ext; done
   $ hg status -A 'set:**.ext'
   ? aa/b.ext
   ? b/a/b.ext
   I a/b.ext
 
 Check using 'include:' in ignore file
 
   $ hg purge --all --config extensions.purge=
   $ touch foo.included
 
   $ echo ".*.included" > otherignore
   $ hg status -I "include:otherignore"
   ? foo.included
 
   $ echo "include:otherignore" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? otherignore
 
 Check recursive uses of 'include:'
 
   $ echo "include:nested/ignore" >> otherignore
   $ mkdir nested nested/more
   $ echo "glob:*ignore" > nested/ignore
   $ echo "rootglob:a" >> nested/ignore
   $ touch a nested/a nested/more/a
   $ hg status
   A dir/b.o
   ? nested/a
   ? nested/more/a
   $ rm a nested/a nested/more/a
 
   $ cp otherignore goodignore
   $ echo "include:badignore" >> otherignore
   $ hg status
   skipping unreadable pattern file 'badignore': $ENOENT$
   A dir/b.o
 
   $ mv goodignore otherignore
 
 Check using 'include:' while in a non-root directory
 
   $ cd ..
   $ hg -R ignorerepo status
   A dir/b.o
   $ cd ignorerepo
 
 Check including subincludes
 
   $ hg revert -q --all
   $ hg purge --all --config extensions.purge=
   $ echo ".hgignore" > .hgignore
   $ mkdir dir1 dir2
   $ touch dir1/file1 dir1/file2 dir2/file1 dir2/file2
   $ echo "subinclude:dir2/.hgignore" >> .hgignore
   $ echo "glob:file*2" > dir2/.hgignore
   $ hg status
   ? dir1/file1
   ? dir1/file2
   ? dir2/file1
 
 Check including subincludes with other patterns
 
   $ echo "subinclude:dir1/.hgignore" >> .hgignore
 
   $ mkdir dir1/subdir
   $ touch dir1/subdir/file1
   $ echo "rootglob:f?le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir1/subdir/file1
   ? dir2/file1
   $ rm dir1/subdir/file1
 
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir2/file1
 
 Check multiple levels of sub-ignores
 
   $ touch dir1/subdir/subfile1 dir1/subdir/subfile3 dir1/subdir/subfile4
   $ echo "subinclude:subdir/.hgignore" >> dir1/.hgignore
   $ echo "glob:subfil*3" >> dir1/subdir/.hgignore
 
   $ hg status
   ? dir1/file2
   ? dir1/subdir/subfile4
   ? dir2/file1
 
 Check include subignore at the same level
 
   $ mv dir1/subdir/.hgignore dir1/.hgignoretwo
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ echo "subinclude:.hgignoretwo" >> dir1/.hgignore
   $ echo "glob:file*2" > dir1/.hgignoretwo
 
   $ hg status | grep file2
   [1]
   $ hg debugignore dir1/file2
   dir1/file2 is ignored
   (ignore rule in dir2/.hgignore, line 1: 'file*2')
 
 #if windows
 
 Windows paths are accepted on input
 
   $ rm dir1/.hgignore
   $ echo "dir1/file*" >> .hgignore
   $ hg debugignore "dir1\file2"
   dir1/file2 is ignored
   (ignore rule in $TESTTMP\ignorerepo\.hgignore, line 4: 'dir1/file*')
   $ hg up -qC .
 
 #endif
 
-#if dirstate-v2
+#if dirstate-v2 rust
 
 Check the hash of ignore patterns written in the dirstate
+This is an optimization that is only relevant when using the Rust extensions
 
   $ hg status > /dev/null
   $ cat .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=6e315b60f15fb5dfa02be00f3e2c8f923051f5ff
   $ hg debugdirstateignorepatternshash
   6e315b60f15fb5dfa02be00f3e2c8f923051f5ff
 
   $ echo rel > .hg/testhgignorerel
   $ hg status > /dev/null
   $ cat .hg/testhgignore .hg/testhgignorerel .hgignore dir2/.hgignore dir1/.hgignore dir1/.hgignoretwo | $TESTDIR/f --sha1
   sha1=dea19cc7119213f24b6b582a4bae7b0cb063e34e
   $ hg debugdirstateignorepatternshash
   dea19cc7119213f24b6b582a4bae7b0cb063e34e
 
 #endif

tests/test-permissions.t

@@ -1,87 +1,86 b''
 #require unix-permissions no-root reporevlogstore
 
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
   $ hg init t
   $ cd t
 
   $ echo foo > a
   $ hg add a
 
   $ hg commit -m "1"
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 1 changes to 1 files
 
   $ chmod -r .hg/store/data/a.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   abort: Permission denied: '$TESTTMP/t/.hg/store/data/a.i'
   [255]
 
   $ chmod +r .hg/store/data/a.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 1 changesets with 1 changes to 1 files
 
   $ chmod -w .hg/store/data/a.i
 
   $ echo barber > a
   $ hg commit -m "2"
   trouble committing a!
   abort: Permission denied: '$TESTTMP/t/.hg/store/data/a.i'
   [255]
 
   $ chmod -w .
 
   $ hg diff --nodates
   diff -r 2a18120dc1c9 a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -foo
   +barber
 
   $ chmod +w .
 
   $ chmod +w .hg/store/data/a.i
   $ mkdir dir
   $ touch dir/a
   $ hg status
   M a
   ? dir/a
   $ chmod -rx dir
 
 #if no-fsmonitor
 
 (fsmonitor makes "hg status" avoid accessing to "dir")
 
   $ hg status
   dir: Permission denied
   M a
 
 #endif
 
 Reenable perm to allow deletion:
 
   $ chmod +rx dir
 
   $ cd ..

tests/test-purge.t

@@ -1,350 +1,349 b''
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
 init
 
   $ hg init t
   $ cd t
 
 setup
 
   $ echo r1 > r1
   $ hg ci -qAmr1 -d'0 0'
   $ mkdir directory
   $ echo r2 > directory/r2
   $ hg ci -qAmr2 -d'1 0'
   $ echo 'ignored' > .hgignore
   $ hg ci -qAmr3 -d'2 0'
 
 purge without the extension
 
   $ hg st
   $ touch foo
   $ hg purge
   permanently delete 1 unkown files? (yN) n
   abort: removal cancelled
   [250]
   $ hg st
   ? foo
   $ hg purge --no-confirm
   $ hg st
 
 now enabling the extension
 
   $ cat <<EOF >> $HGRCPATH
   > [extensions]
   > purge =
   > EOF
 
 delete an empty directory
 
   $ mkdir empty_dir
   $ hg purge -p -v
   empty_dir
   $ hg purge --confirm
   permanently delete at least 1 empty directories? (yN) n
   abort: removal cancelled
   [250]
   $ hg purge -v
   removing directory empty_dir
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete an untracked directory
 
   $ mkdir untracked_dir
   $ touch untracked_dir/untracked_file1
   $ touch untracked_dir/untracked_file2
   $ hg purge -p
   untracked_dir/untracked_file1
   untracked_dir/untracked_file2
   $ hg purge -v
   removing file untracked_dir/untracked_file1
   removing file untracked_dir/untracked_file2
   removing directory untracked_dir
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete an untracked file
 
   $ touch untracked_file
   $ touch untracked_file_readonly
   $ "$PYTHON" <<EOF
   > import os
   > import stat
   > f = 'untracked_file_readonly'
   > os.chmod(f, stat.S_IMODE(os.stat(f).st_mode) & ~stat.S_IWRITE)
   > EOF
   $ hg purge -p
   untracked_file
   untracked_file_readonly
   $ hg purge --confirm
   permanently delete 2 unkown files? (yN) n
   abort: removal cancelled
   [250]
   $ hg purge -v
   removing file untracked_file
   removing file untracked_file_readonly
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete an untracked file in a tracked directory
 
   $ touch directory/untracked_file
   $ hg purge -p
   directory/untracked_file
   $ hg purge -v
   removing file directory/untracked_file
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete nested directories
 
   $ mkdir -p untracked_directory/nested_directory
   $ hg purge -p
   untracked_directory/nested_directory
   $ hg purge -v
   removing directory untracked_directory/nested_directory
   removing directory untracked_directory
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete nested directories from a subdir
 
   $ mkdir -p untracked_directory/nested_directory
   $ cd directory
   $ hg purge -p
   untracked_directory/nested_directory
   $ hg purge -v
   removing directory untracked_directory/nested_directory
   removing directory untracked_directory
   $ cd ..
   $ ls -A
   .hg
   .hgignore
   directory
   r1
 
 delete only part of the tree
 
   $ mkdir -p untracked_directory/nested_directory
   $ touch directory/untracked_file
   $ cd directory
   $ hg purge -p ../untracked_directory
   untracked_directory/nested_directory
   $ hg purge --confirm
   permanently delete 1 unkown files? (yN) n
   abort: removal cancelled
   [250]
   $ hg purge -v ../untracked_directory
   removing directory untracked_directory/nested_directory
   removing directory untracked_directory
   $ cd ..
   $ ls -A
   .hg
   .hgignore
   directory
   r1
   $ ls directory/untracked_file
   directory/untracked_file
   $ rm directory/untracked_file
 
 skip ignored files if -i or --all not specified
 
   $ touch ignored
   $ hg purge -p
   $ hg purge --confirm
   $ hg purge -v
   $ touch untracked_file
   $ ls
   directory
   ignored
   r1
   untracked_file
   $ hg purge -p -i
   ignored
   $ hg purge --confirm -i
   permanently delete 1 ignored files? (yN) n
   abort: removal cancelled
   [250]
   $ hg purge -v -i
   removing file ignored
   $ ls -A
   .hg
   .hgignore
   directory
   r1
   untracked_file
   $ touch ignored
   $ hg purge -p --all
   ignored
   untracked_file
   $ hg purge --confirm --all
   permanently delete 1 unkown and 1 ignored files? (yN) n
   abort: removal cancelled
   [250]
   $ hg purge -v --all
   removing file ignored
   removing file untracked_file
   $ ls
   directory
   r1
 
 abort with missing files until we support name mangling filesystems
 
   $ touch untracked_file
   $ rm r1
 
 hide error messages to avoid changing the output when the text changes
 
   $ hg purge -p 2> /dev/null
   untracked_file
   $ hg st
   ! r1
   ? untracked_file
 
   $ hg purge -p
   untracked_file
   $ hg purge -v 2> /dev/null
   removing file untracked_file
   $ hg st
   ! r1
 
   $ hg purge -v
   $ hg revert --all --quiet
   $ hg st -a
 
 tracked file in ignored directory (issue621)
 
   $ echo directory >> .hgignore
   $ hg ci -m 'ignore directory'
   $ touch untracked_file
   $ hg purge -p
   untracked_file
   $ hg purge -v
   removing file untracked_file
 
 skip excluded files
 
   $ touch excluded_file
   $ hg purge -p -X excluded_file
   $ hg purge -v -X excluded_file
   $ ls -A
   .hg
   .hgignore
   directory
   excluded_file
   r1
   $ rm excluded_file
 
 skip files in excluded dirs
 
   $ mkdir excluded_dir
   $ touch excluded_dir/file
   $ hg purge -p -X excluded_dir
   $ hg purge -v -X excluded_dir
   $ ls -A
   .hg
   .hgignore
   directory
   excluded_dir
   r1
   $ ls excluded_dir
   file
   $ rm -R excluded_dir
 
 skip excluded empty dirs
 
   $ mkdir excluded_dir
   $ hg purge -p -X excluded_dir
   $ hg purge -v -X excluded_dir
   $ ls -A
   .hg
   .hgignore
   directory
   excluded_dir
   r1
   $ rmdir excluded_dir
 
 skip patterns
 
   $ mkdir .svn
   $ touch .svn/foo
   $ mkdir directory/.svn
   $ touch directory/.svn/foo
   $ hg purge -p -X .svn -X '*/.svn'
   $ hg purge -p -X re:.*.svn
 
   $ rm -R .svn directory r1
 
 only remove files
 
   $ mkdir -p empty_dir dir
   $ touch untracked_file dir/untracked_file
   $ hg purge -p --files
   dir/untracked_file
   untracked_file
   $ hg purge -v --files
   removing file dir/untracked_file
   removing file untracked_file
   $ ls -A
   .hg
   .hgignore
   dir
   empty_dir
   $ ls dir
 
 only remove dirs
 
   $ mkdir -p empty_dir dir
   $ touch untracked_file dir/untracked_file
   $ hg purge -p --dirs
   empty_dir
   $ hg purge -v --dirs
   removing directory empty_dir
   $ ls -A
   .hg
   .hgignore
   dir
   untracked_file
   $ ls dir
   untracked_file
 
 remove both files and dirs
 
   $ mkdir -p empty_dir dir
   $ touch untracked_file dir/untracked_file
   $ hg purge -p --files --dirs
   dir/untracked_file
   untracked_file
   empty_dir
   $ hg purge -v --files --dirs
   removing file dir/untracked_file
   removing file untracked_file
   removing directory empty_dir
   removing directory dir
   $ ls -A
   .hg
   .hgignore
 
   $ cd ..

tests/test-status.t

@@ -1,968 +1,961 b''
 #testcases dirstate-v1 dirstate-v2
 
-#if no-rust
-  $ hg init repo0 --config format.exp-dirstate-v2=1
-  abort: dirstate v2 format requested by config but not supported (requires Rust extensions)
-  [255]
-#endif
-
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
   $ hg init repo1
   $ cd repo1
   $ mkdir a b a/1 b/1 b/2
   $ touch in_root a/in_a b/in_b a/1/in_a_1 b/1/in_b_1 b/2/in_b_2
 
 hg status in repo root:
 
   $ hg status
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
 hg status . in repo root:
 
   $ hg status .
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ hg status --cwd a
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a .
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a ..
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd b
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b .
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   $ hg status --cwd b ..
   ? ../a/1/in_a_1
   ? ../a/in_a
   ? 1/in_b_1
   ? 2/in_b_2
   ? in_b
   ? ../in_root
 
   $ hg status --cwd a/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd a/1 .
   ? in_a_1
   $ hg status --cwd a/1 ..
   ? in_a_1
   ? ../in_a
 
   $ hg status --cwd b/1
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/1 .
   ? in_b_1
   $ hg status --cwd b/1 ..
   ? in_b_1
   ? ../2/in_b_2
   ? ../in_b
 
   $ hg status --cwd b/2
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
   $ hg status --cwd b/2 .
   ? in_b_2
   $ hg status --cwd b/2 ..
   ? ../1/in_b_1
   ? in_b_2
   ? ../in_b
 
 combining patterns with root and patterns without a root works
 
   $ hg st a/in_a re:.*b$
   ? a/in_a
   ? b/in_b
 
 tweaking defaults works
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
   $ HGPLAINEXCEPT=tweakdefaults hg status --cwd a --config ui.tweakdefaults=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root (glob)
 
 relative paths can be requested
 
   $ hg status --cwd a --config ui.relative-paths=yes
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
 
   $ hg status --cwd a . --config ui.relative-paths=legacy
   ? 1/in_a_1
   ? in_a
   $ hg status --cwd a . --config ui.relative-paths=no
   ? a/1/in_a_1
   ? a/in_a
 
 commands.status.relative overrides ui.relative-paths
 
   $ cat >> $HGRCPATH <<EOF
   > [ui]
   > relative-paths = False
   > [commands]
   > status.relative = True
   > EOF
   $ hg status --cwd a
   ? 1/in_a_1
   ? in_a
   ? ../b/1/in_b_1
   ? ../b/2/in_b_2
   ? ../b/in_b
   ? ../in_root
   $ HGPLAIN=1 hg status --cwd a
   ? a/1/in_a_1 (glob)
   ? a/in_a (glob)
   ? b/1/in_b_1 (glob)
   ? b/2/in_b_2 (glob)
   ? b/in_b (glob)
   ? in_root
 
 if relative paths are explicitly off, tweakdefaults doesn't change it
   $ cat >> $HGRCPATH <<EOF
   > [commands]
   > status.relative = False
   > EOF
   $ hg status --cwd a --config ui.tweakdefaults=yes
   ? a/1/in_a_1
   ? a/in_a
   ? b/1/in_b_1
   ? b/2/in_b_2
   ? b/in_b
   ? in_root
 
   $ cd ..
 
   $ hg init repo2
   $ cd repo2
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg ci -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch modified added unknown ignored
   $ hg add added
   $ hg remove removed
   $ rm deleted
 
 hg status:
 
   $ hg status
   A added
   R removed
   ! deleted
   ? unknown
 
 hg status modified added removed deleted unknown never-existed ignored:
 
   $ hg status modified added removed deleted unknown never-existed ignored
   never-existed: * (glob)
   A added
   R removed
   ! deleted
   ? unknown
 
   $ hg copy modified copied
 
 hg status -C:
 
   $ hg status -C
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
 
 hg status -A:
 
   $ hg status -A
   A added
   A copied
     modified
   R removed
   ! deleted
   ? unknown
   I ignored
   C .hgignore
   C modified
 
   $ hg status -A -T '{status} {path} {node|shortest}\n'
   A added ffff
   A copied ffff
   R removed ffff
   ! deleted ffff
   ? unknown ffff
   I ignored ffff
   C .hgignore ffff
   C modified ffff
 
   $ hg status -A -Tjson
   [
    {
     "itemtype": "file",
     "path": "added",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "copied",
     "source": "modified",
     "status": "A"
    },
    {
     "itemtype": "file",
     "path": "removed",
     "status": "R"
    },
    {
     "itemtype": "file",
     "path": "deleted",
     "status": "!"
    },
    {
     "itemtype": "file",
     "path": "unknown",
     "status": "?"
    },
    {
     "itemtype": "file",
     "path": "ignored",
     "status": "I"
    },
    {
     "itemtype": "file",
     "path": ".hgignore",
     "status": "C"
    },
    {
     "itemtype": "file",
     "path": "modified",
     "status": "C"
    }
   ]
 
   $ hg status -A -Tpickle > pickle
   >>> from __future__ import print_function
   >>> from mercurial import util
   >>> pickle = util.pickle
   >>> data = sorted((x[b'status'].decode(), x[b'path'].decode()) for x in pickle.load(open("pickle", r"rb")))
   >>> for s, p in data: print("%s %s" % (s, p))
   ! deleted
   ? pickle
   ? unknown
   A added
   A copied
   C .hgignore
   C modified
   I ignored
   R removed
   $ rm pickle
 
   $ echo "^ignoreddir$" > .hgignore
   $ mkdir ignoreddir
   $ touch ignoreddir/file
 
 Test templater support:
 
   $ hg status -AT "[{status}]\t{if(source, '{source} -> ')}{path}\n"
   [M]	.hgignore
   [A]	added
   [A]	modified -> copied
   [R]	removed
   [!]	deleted
   [?]	ignored
   [?]	unknown
   [I]	ignoreddir/file
   [C]	modified
   $ hg status -AT default
   M .hgignore
   A added
   A copied
     modified
   R removed
   ! deleted
   ? ignored
   ? unknown
   I ignoreddir/file
   C modified
   $ hg status -T compact
   abort: "status" not in template map
   [255]
 
 hg status ignoreddir/file:
 
   $ hg status ignoreddir/file
 
 hg status -i ignoreddir/file:
 
   $ hg status -i ignoreddir/file
   I ignoreddir/file
   $ cd ..
 
 Check 'status -q' and some combinations
 
   $ hg init repo3
   $ cd repo3
   $ touch modified removed deleted ignored
   $ echo "^ignored$" > .hgignore
   $ hg commit -A -m 'initial checkin'
   adding .hgignore
   adding deleted
   adding modified
   adding removed
   $ touch added unknown ignored
   $ hg add added
   $ echo "test" >> modified
   $ hg remove removed
   $ rm deleted
   $ hg copy modified copied
 
 Specify working directory revision explicitly, that should be the same as
 "hg status"
 
   $ hg status --change "wdir()"
   M modified
   A added
   A copied
   R removed
   ! deleted
   ? unknown
 
 Run status with 2 different flags.
 Check if result is the same or different.
 If result is not as expected, raise error
 
   $ assert() {
   >     hg status $1 > ../a
   >     hg status $2 > ../b
   >     if diff ../a ../b > /dev/null; then
   >         out=0
   >     else
   >         out=1
   >     fi
   >     if [ $3 -eq 0 ]; then
   >         df="same"
   >     else
   >         df="different"
   >     fi
   >     if [ $out -ne $3 ]; then
   >         echo "Error on $1 and $2, should be $df."
   >     fi
   > }
 
 Assert flag1 flag2 [0-same | 1-different]
 
   $ assert "-q" "-mard"      0
   $ assert "-A" "-marduicC"  0
   $ assert "-qA" "-mardcC"   0
   $ assert "-qAui" "-A"      0
   $ assert "-qAu" "-marducC" 0
   $ assert "-qAi" "-mardicC" 0
   $ assert "-qu" "-u"        0
   $ assert "-q" "-u"         1
   $ assert "-m" "-a"         1
   $ assert "-r" "-d"         1
   $ cd ..
 
   $ hg init repo4
   $ cd repo4
   $ touch modified removed deleted
   $ hg ci -q -A -m 'initial checkin'
   $ touch added unknown
   $ hg add added
   $ hg remove removed
   $ rm deleted
   $ echo x > modified
   $ hg copy modified copied
   $ hg ci -m 'test checkin' -d "1000001 0"
   $ rm *
   $ touch unrelated
   $ hg ci -q -A -m 'unrelated checkin' -d "1000002 0"
 
 hg status --change 1:
 
   $ hg status --change 1
   M modified
   A added
   A copied
   R removed
 
 hg status --change 1 unrelated:
 
   $ hg status --change 1 unrelated
 
 hg status -C --change 1 added modified copied removed deleted:
 
   $ hg status -C --change 1 added modified copied removed deleted
   M modified
   A added
   A copied
     modified
   R removed
 
 hg status -A --change 1 and revset:
 
   $ hg status -A --change '1|1'
   M modified
   A added
   A copied
     modified
   R removed
   C deleted
 
   $ cd ..
 
 hg status with --rev and reverted changes:
 
   $ hg init reverted-changes-repo
   $ cd reverted-changes-repo
   $ echo a > file
   $ hg add file
   $ hg ci -m a
   $ echo b > file
   $ hg ci -m b
 
 reverted file should appear clean
 
   $ hg revert -r 0 .
   reverting file
   $ hg status -A --rev 0
   C file
 
 #if execbit
 reverted file with changed flag should appear modified
 
   $ chmod +x file
   $ hg status -A --rev 0
   M file
 
   $ hg revert -r 0 .
   reverting file
 
 reverted and committed file with changed flag should appear modified
 
   $ hg co -C .
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ chmod +x file
   $ hg ci -m 'change flag'
   $ hg status -A --rev 1 --rev 2
   M file
   $ hg diff -r 1 -r 2
 
 #endif
 
   $ cd ..
 
 hg status of binary file starting with '\1\n', a separator for metadata:
 
   $ hg init repo5
   $ cd repo5
   >>> open("010a", r"wb").write(b"\1\nfoo") and None
   $ hg ci -q -A -m 'initial checkin'
   $ hg status -A
   C 010a
 
   >>> open("010a", r"wb").write(b"\1\nbar") and None
   $ hg status -A
   M 010a
   $ hg ci -q -m 'modify 010a'
   $ hg status -A --rev 0:1
   M 010a
 
   $ touch empty
   $ hg ci -q -A -m 'add another file'
   $ hg status -A --rev 1:2 010a
   C 010a
 
   $ cd ..
 
 test "hg status" with "directory pattern" which matches against files
 only known on target revision.
 
   $ hg init repo6
   $ cd repo6
 
   $ echo a > a.txt
   $ hg add a.txt
   $ hg commit -m '#0'
   $ mkdir -p 1/2/3/4/5
   $ echo b > 1/2/3/4/5/b.txt
   $ hg add 1/2/3/4/5/b.txt
   $ hg commit -m '#1'
 
   $ hg update -C 0 > /dev/null
   $ hg status -A
   C a.txt
 
 the directory matching against specified pattern should be removed,
 because directory existence prevents 'dirstate.walk()' from showing
 warning message about such pattern.
 
   $ test ! -d 1
   $ hg status -A --rev 1 1/2/3/4/5/b.txt
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3/4/5
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1/2/3
   R 1/2/3/4/5/b.txt
   $ hg status -A --rev 1 1
   R 1/2/3/4/5/b.txt
 
   $ hg status --config ui.formatdebug=True --rev 1 1
   status = [
       {
           'itemtype': 'file',
           'path': '1/2/3/4/5/b.txt',
           'status': 'R'
       },
   ]
 
 #if windows
   $ hg --config ui.slash=false status -A --rev 1 1
   R 1\2\3\4\5\b.txt
 #endif
 
   $ cd ..
 
 Status after move overwriting a file (issue4458)
 =================================================
 
 
   $ hg init issue4458
   $ cd issue4458
   $ echo a > a
   $ echo b > b
   $ hg commit -Am base
   adding a
   adding b
 
 
 with --force
 
   $ hg mv b --force a
   $ hg st --copies
   M a
     b
   R b
   $ hg revert --all
   reverting a
   undeleting b
   $ rm *.orig
 
 without force
 
   $ hg rm a
   $ hg st --copies
   R a
   $ hg mv b a
   $ hg st --copies
   M a
     b
   R b
 
 using ui.statuscopies setting
   $ hg st --config ui.statuscopies=true
   M a
     b
   R b
   $ hg st --config ui.statuscopies=false
   M a
   R b
   $ hg st --config ui.tweakdefaults=yes
   M a
     b
   R b
 
 using log status template (issue5155)
   $ hg log -Tstatus -r 'wdir()' -C
   changeset:   2147483647:ffffffffffff
   parent:      0:8c55c58b4c0e
   user:        test
   date:        * (glob)
   files:
   M a
     b
   R b
   
   $ hg log -GTstatus -r 'wdir()' -C
   o  changeset:   2147483647:ffffffffffff
   |  parent:      0:8c55c58b4c0e
   ~  user:        test
      date:        * (glob)
      files:
      M a
        b
      R b
   
 
 Other "bug" highlight, the revision status does not report the copy information.
 This is buggy behavior.
 
   $ hg commit -m 'blah'
   $ hg st --copies --change .
   M a
   R b
 
 using log status template, the copy information is displayed correctly.
   $ hg log -Tstatus -r. -C
   changeset:   1:6685fde43d21
   tag:         tip
   user:        test
   date:        * (glob)
   summary:     blah
   files:
   M a
     b
   R b
   
 
   $ cd ..
 
 Make sure .hg doesn't show up even as a symlink
 
   $ hg init repo0
   $ mkdir symlink-repo0
   $ cd symlink-repo0
   $ ln -s ../repo0/.hg
   $ hg status
 
 If the size hasn’t changed but mtime has, status needs to read the contents
 of the file to check whether it has changed
 
   $ echo 1 > a
   $ echo 1 > b
   $ touch -t 200102030000 a b
   $ hg commit -Aqm '#0'
   $ echo 2 > a
   $ touch -t 200102040000 a b
   $ hg status
   M a
 
 Asking specifically for the status of a deleted/removed file
 
   $ rm a
   $ rm b
   $ hg status a
   ! a
   $ hg rm a
   $ hg rm b
   $ hg status a
   R a
   $ hg commit -qm '#1'
   $ hg status a
   a: $ENOENT$
 
 Check using include flag with pattern when status does not need to traverse
 the working directory (issue6483)
 
   $ cd ..
   $ hg init issue6483
   $ cd issue6483
   $ touch a.py b.rs
   $ hg add a.py b.rs
   $ hg st -aI "*.py"
   A a.py
 
 Also check exclude pattern
 
   $ hg st -aX "*.rs"
   A a.py
 
 issue6335
 When a directory containing a tracked file gets symlinked, as of 5.8
 `hg st` only gives the correct answer about clean (or deleted) files
 if also listing unknowns.
 The tree-based dirstate and status algorithm fix this:
 
-#if symlink no-dirstate-v1
+#if symlink no-dirstate-v1 rust
 
   $ cd ..
   $ hg init issue6335
   $ cd issue6335
   $ mkdir foo
   $ touch foo/a
   $ hg ci -Ama
   adding foo/a
   $ mv foo bar
   $ ln -s bar foo
   $ hg status
   ! foo/a
   ? bar/a
   ? foo
 
-  $ hg status -c  # incorrect output with `dirstate-v1`
+  $ hg status -c  # incorrect output without the Rust implementation
   $ hg status -cu
   ? bar/a
   ? foo
-  $ hg status -d  # incorrect output with `dirstate-v1`
+  $ hg status -d  # incorrect output without the Rust implementation
   ! foo/a
   $ hg status -du
   ! foo/a
   ? bar/a
   ? foo
 
 #endif
 
 
 Create a repo with files in each possible status
 
   $ cd ..
   $ hg init repo7
   $ cd repo7
   $ mkdir subdir
   $ touch clean modified deleted removed
   $ touch subdir/clean subdir/modified subdir/deleted subdir/removed
   $ echo ignored > .hgignore
   $ hg ci -Aqm '#0'
   $ echo 1 > modified
   $ echo 1 > subdir/modified
   $ rm deleted
   $ rm subdir/deleted
   $ hg rm removed
   $ hg rm subdir/removed
   $ touch unknown ignored
   $ touch subdir/unknown subdir/ignored
 
 Check the output
 
   $ hg status
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
 
   $ hg status -mard
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
 
   $ hg status -A
   M modified
   M subdir/modified
   R removed
   R subdir/removed
   ! deleted
   ! subdir/deleted
   ? subdir/unknown
   ? unknown
   I ignored
   I subdir/ignored
   C .hgignore
   C clean
   C subdir/clean
 
 Note: `hg status some-name` creates a patternmatcher which is not supported
 yet by the Rust implementation of status, but includematcher is supported.
 --include is used below for that reason
 
 #if unix-permissions
 
 Not having permission to read a directory that contains tracked files makes
 status emit a warning then behave as if the directory was empty or removed
 entirely:
 
   $ chmod 0 subdir
   $ hg status --include subdir
   subdir: Permission denied
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   $ chmod 755 subdir
 
 #endif
 
 Remove a directory that contains tracked files
 
   $ rm -r subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
 
 … and replace it by a file
 
   $ touch subdir
   $ hg status --include subdir
   R subdir/removed
   ! subdir/clean
   ! subdir/deleted
   ! subdir/modified
   ? subdir
 
 Replaced a deleted or removed file with a directory
 
   $ mkdir deleted removed
   $ touch deleted/1 removed/1
   $ hg status --include deleted --include removed
   R removed
   ! deleted
   ? deleted/1
   ? removed/1
   $ hg add removed/1
   $ hg status --include deleted --include removed
   A removed/1
   R removed
   ! deleted
   ? deleted/1
 
 Deeply nested files in an ignored directory are still listed on request
 
   $ echo ignored-dir >> .hgignore
   $ mkdir ignored-dir
   $ mkdir ignored-dir/subdir
   $ touch ignored-dir/subdir/1
   $ hg status --ignored
   I ignored
   I ignored-dir/subdir/1
 
 Check using include flag while listing ignored composes correctly (issue6514)
 
   $ cd ..
   $ hg init issue6514
   $ cd issue6514
   $ mkdir ignored-folder
   $ touch A.hs B.hs C.hs ignored-folder/other.txt ignored-folder/ctest.hs
   $ cat >.hgignore <<EOF
   > A.hs
   > B.hs
   > ignored-folder/
   > EOF
   $ hg st -i -I 're:.*\.hs$'
   I A.hs
   I B.hs
   I ignored-folder/ctest.hs
 
-#if dirstate-v2
+#if rust dirstate-v2
 
 Check read_dir caching
 
   $ cd ..
   $ hg init repo8
   $ cd repo8
   $ mkdir subdir
   $ touch subdir/a subdir/b
   $ hg ci -Aqm '#0'
 
 The cached mtime is initially unset
 
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 It is still not set when there are unknown files
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
 
 Now the directory is eligible for caching, so its mtime is save in the dirstate
 
   $ rm subdir/unknown
   $ hg status
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
 
 This time the command should be ever so slightly faster since it does not need `read_dir("subdir")`
 
   $ hg status
 
 Creating a new file changes the directory’s mtime, invalidating the cache
 
   $ touch subdir/unknown
   $ hg status
   ? subdir/unknown
 
   $ rm subdir/unknown
   $ hg status
 
 Removing a node from the dirstate resets the cache for its parent directory
 
   $ hg forget subdir/a
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 set                 subdir
   $ hg ci -qm '#1'
   $ hg debugdirstate --all --no-dates | grep '^ '
       0         -1 unset               subdir
   $ hg status
   ? subdir/a
 
 #endif

tests/test-symlinks.t

@@ -1,283 +1,282 b''
 #require symlink
 
 #testcases dirstate-v1 dirstate-v2
 
 #if dirstate-v2
-#require rust
   $ echo '[format]' >> $HGRCPATH
   $ echo 'exp-dirstate-v2=1' >> $HGRCPATH
 #endif
 
 == tests added in 0.7 ==
 
   $ hg init test-symlinks-0.7; cd test-symlinks-0.7;
   $ touch foo; ln -s foo bar; ln -s nonexistent baz
 
 import with add and addremove -- symlink walking should _not_ screwup.
 
   $ hg add
   adding bar
   adding baz
   adding foo
   $ hg forget bar baz foo
   $ hg addremove
   adding bar
   adding baz
   adding foo
 
 commit -- the symlink should _not_ appear added to dir state
 
   $ hg commit -m 'initial'
 
   $ touch bomb
 
 again, symlink should _not_ show up on dir state
 
   $ hg addremove
   adding bomb
 
 Assert screamed here before, should go by without consequence
 
   $ hg commit -m 'is there a bug?'
   $ cd ..
 
 
 == fifo & ignore ==
 
   $ hg init test; cd test;
 
   $ mkdir dir
   $ touch a.c dir/a.o dir/b.o
 
 test what happens if we want to trick hg
 
   $ hg commit -A -m 0
   adding a.c
   adding dir/a.o
   adding dir/b.o
   $ echo "relglob:*.o" > .hgignore
   $ rm a.c
   $ rm dir/a.o
   $ rm dir/b.o
   $ mkdir dir/a.o
   $ ln -s nonexistent dir/b.o
   $ mkfifo a.c
 
 it should show a.c, dir/a.o and dir/b.o deleted
 
   $ hg status
   M dir/b.o
   ! a.c
   ! dir/a.o
   ? .hgignore
   $ hg status a.c
   a.c: unsupported file type (type is fifo)
   ! a.c
   $ cd ..
 
 
 == symlinks from outside the tree ==
 
 test absolute path through symlink outside repo
 
   $ p=`pwd`
   $ hg init x
   $ ln -s x y
   $ cd x
   $ touch f
   $ hg add f
   $ hg status "$p"/y/f
   A f
 
 try symlink outside repo to file inside
 
   $ ln -s x/f ../z
 
 this should fail
 
   $ hg status ../z && { echo hg mistakenly exited with status 0; exit 1; } || :
   abort: ../z not under root '$TESTTMP/x'
   $ cd ..
 
 
 == cloning symlinks ==
   $ hg init clone; cd clone;
 
 try cloning symlink in a subdir
 1. commit a symlink
 
   $ mkdir -p a/b/c
   $ cd a/b/c
   $ ln -s /path/to/symlink/source demo
   $ cd ../../..
   $ hg stat
   ? a/b/c/demo
   $ hg commit -A -m 'add symlink in a/b/c subdir'
   adding a/b/c/demo
 
 2. clone it
 
   $ cd ..
   $ hg clone clone clonedest
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 
 == symlink and git diffs ==
 
 git symlink diff
 
   $ cd clonedest
   $ hg diff --git -r null:tip
   diff --git a/a/b/c/demo b/a/b/c/demo
   new file mode 120000
   --- /dev/null
   +++ b/a/b/c/demo
   @@ -0,0 +1,1 @@
   +/path/to/symlink/source
   \ No newline at end of file
   $ hg export --git tip > ../sl.diff
 
 import git symlink diff
 
   $ hg rm a/b/c/demo
   $ hg commit -m'remove link'
   $ hg import ../sl.diff
   applying ../sl.diff
   $ hg diff --git -r 1:tip
   diff --git a/a/b/c/demo b/a/b/c/demo
   new file mode 120000
   --- /dev/null
   +++ b/a/b/c/demo
   @@ -0,0 +1,1 @@
   +/path/to/symlink/source
   \ No newline at end of file
 
 == symlinks and addremove ==
 
 directory moved and symlinked
 
   $ mkdir foo
   $ touch foo/a
   $ hg ci -Ama
   adding foo/a
   $ mv foo bar
   $ ln -s bar foo
   $ hg status
   ! foo/a
   ? bar/a
   ? foo
 
 now addremove should remove old files
 
   $ hg addremove
   adding bar/a
   adding foo
   removing foo/a
 
 commit and update back
 
   $ hg ci -mb
   $ hg up '.^'
   1 files updated, 0 files merged, 2 files removed, 0 files unresolved
   $ hg up tip
   2 files updated, 0 files merged, 1 files removed, 0 files unresolved
 
   $ cd ..
 
 == root of repository is symlinked ==
 
   $ hg init root
   $ ln -s root link
   $ cd root
   $ echo foo > foo
   $ hg status
   ? foo
   $ hg status ../link
   ? foo
   $ hg add foo
   $ hg cp foo "$TESTTMP/link/bar"
   foo has not been committed yet, so no copy data will be stored for bar.
   $ cd ..
 
 
   $ hg init b
   $ cd b
   $ ln -s nothing dangling
   $ hg commit -m 'commit symlink without adding' dangling
   abort: dangling: file not tracked!
   [10]
   $ hg add dangling
   $ hg commit -m 'add symlink'
 
   $ hg tip -v
   changeset:   0:cabd88b706fc
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   files:       dangling
   description:
   add symlink
   
   
   $ hg manifest --debug
   2564acbe54bbbedfbf608479340b359f04597f80 644 @ dangling
   $ readlink.py dangling
   dangling -> nothing
 
   $ rm dangling
   $ ln -s void dangling
   $ hg commit -m 'change symlink'
   $ readlink.py dangling
   dangling -> void
 
 
 modifying link
 
   $ rm dangling
   $ ln -s empty dangling
   $ readlink.py dangling
   dangling -> empty
 
 
 reverting to rev 0:
 
   $ hg revert -r 0 -a
   reverting dangling
   $ readlink.py dangling
   dangling -> nothing
 
 
 backups:
 
   $ readlink.py *.orig
   dangling.orig -> empty
   $ rm *.orig
   $ hg up -C
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 copies
 
   $ hg cp -v dangling dangling2
   copying dangling to dangling2
   $ hg st -Cmard
   A dangling2
     dangling
   $ readlink.py dangling dangling2
   dangling -> void
   dangling2 -> void
 
 
 Issue995: hg copy -A incorrectly handles symbolic links
 
   $ hg up -C
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ mkdir dir
   $ ln -s dir dirlink
   $ hg ci -qAm 'add dirlink'
   $ mkdir newdir
   $ mv dir newdir/dir
   $ mv dirlink newdir/dirlink
   $ hg mv -A dirlink newdir/dirlink
 
   $ cd ..