dirstate: add a `set_untracked` method for "hg remove"-like usage

This is a step further toward clarifying the semantic of various dirstate call.
See the justification for adding `set_tracked` for details.

Differential Revision: https://phab.mercurial-scm.org/D11019

hgext/largefiles/lfutil.py

@@ -1,787 +1,790
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''largefiles utility code: must not import other modules in this package.'''
 from __future__ import absolute_import
 
 import contextlib
 import copy
 import os
 import stat
 
 from mercurial.i18n import _
 from mercurial.node import hex
 from mercurial.pycompat import open
 
 from mercurial import (
     dirstate,
     encoding,
     error,
     httpconnection,
     match as matchmod,
     pycompat,
     requirements,
     scmutil,
     sparse,
     util,
     vfs as vfsmod,
 )
 from mercurial.utils import hashutil
 
 shortname = b'.hglf'
 shortnameslash = shortname + b'/'
 longname = b'largefiles'
 
 # -- Private worker functions ------------------------------------------
 
 
 @contextlib.contextmanager
 def lfstatus(repo, value=True):
     oldvalue = getattr(repo, 'lfstatus', False)
     repo.lfstatus = value
     try:
         yield
     finally:
         repo.lfstatus = oldvalue
 
 
 def getminsize(ui, assumelfiles, opt, default=10):
     lfsize = opt
     if not lfsize and assumelfiles:
         lfsize = ui.config(longname, b'minsize', default=default)
     if lfsize:
         try:
             lfsize = float(lfsize)
         except ValueError:
             raise error.Abort(
                 _(b'largefiles: size must be number (not %s)\n') % lfsize
             )
     if lfsize is None:
         raise error.Abort(_(b'minimum size for largefiles must be specified'))
     return lfsize
 
 
 def link(src, dest):
     """Try to create hardlink - if that fails, efficiently make a copy."""
     util.makedirs(os.path.dirname(dest))
     try:
         util.oslink(src, dest)
     except OSError:
         # if hardlinks fail, fallback on atomic copy
         with open(src, b'rb') as srcf, util.atomictempfile(dest) as dstf:
             for chunk in util.filechunkiter(srcf):
                 dstf.write(chunk)
         os.chmod(dest, os.stat(src).st_mode)
 
 
 def usercachepath(ui, hash):
     """Return the correct location in the "global" largefiles cache for a file
     with the given hash.
     This cache is used for sharing of largefiles across repositories - both
     to preserve download bandwidth and storage space."""
     return os.path.join(_usercachedir(ui), hash)
 
 
 def _usercachedir(ui, name=longname):
     '''Return the location of the "global" largefiles cache.'''
     path = ui.configpath(name, b'usercache')
     if path:
         return path
 
     hint = None
 
     if pycompat.iswindows:
         appdata = encoding.environ.get(
             b'LOCALAPPDATA', encoding.environ.get(b'APPDATA')
         )
         if appdata:
             return os.path.join(appdata, name)
 
         hint = _(b"define %s or %s in the environment, or set %s.usercache") % (
             b"LOCALAPPDATA",
             b"APPDATA",
             name,
         )
     elif pycompat.isdarwin:
         home = encoding.environ.get(b'HOME')
         if home:
             return os.path.join(home, b'Library', b'Caches', name)
 
         hint = _(b"define %s in the environment, or set %s.usercache") % (
             b"HOME",
             name,
         )
     elif pycompat.isposix:
         path = encoding.environ.get(b'XDG_CACHE_HOME')
         if path:
             return os.path.join(path, name)
         home = encoding.environ.get(b'HOME')
         if home:
             return os.path.join(home, b'.cache', name)
 
         hint = _(b"define %s or %s in the environment, or set %s.usercache") % (
             b"XDG_CACHE_HOME",
             b"HOME",
             name,
         )
     else:
         raise error.Abort(
             _(b'unknown operating system: %s\n') % pycompat.osname
         )
 
     raise error.Abort(_(b'unknown %s usercache location') % name, hint=hint)
 
 
 def inusercache(ui, hash):
     path = usercachepath(ui, hash)
     return os.path.exists(path)
 
 
 def findfile(repo, hash):
     """Return store path of the largefile with the specified hash.
     As a side effect, the file might be linked from user cache.
     Return None if the file can't be found locally."""
     path, exists = findstorepath(repo, hash)
     if exists:
         repo.ui.note(_(b'found %s in store\n') % hash)
         return path
     elif inusercache(repo.ui, hash):
         repo.ui.note(_(b'found %s in system cache\n') % hash)
         path = storepath(repo, hash)
         link(usercachepath(repo.ui, hash), path)
         return path
     return None
 
 
 class largefilesdirstate(dirstate.dirstate):
     def __getitem__(self, key):
         return super(largefilesdirstate, self).__getitem__(unixpath(key))
 
     def set_tracked(self, f):
         return super(largefilesdirstate, self).set_tracked(unixpath(f))
 
+    def set_untracked(self, f):
+        return super(largefilesdirstate, self).set_untracked(unixpath(f))
+
     def normal(self, f):
         return super(largefilesdirstate, self).normal(unixpath(f))
 
     def remove(self, f):
         return super(largefilesdirstate, self).remove(unixpath(f))
 
     def add(self, f):
         return super(largefilesdirstate, self).add(unixpath(f))
 
     def drop(self, f):
         return super(largefilesdirstate, self).drop(unixpath(f))
 
     def forget(self, f):
         return super(largefilesdirstate, self).forget(unixpath(f))
 
     def normallookup(self, f):
         return super(largefilesdirstate, self).normallookup(unixpath(f))
 
     def _ignore(self, f):
         return False
 
     def write(self, tr=False):
         # (1) disable PENDING mode always
         #     (lfdirstate isn't yet managed as a part of the transaction)
         # (2) avoid develwarn 'use dirstate.write with ....'
         super(largefilesdirstate, self).write(None)
 
 
 def openlfdirstate(ui, repo, create=True):
     """
     Return a dirstate object that tracks largefiles: i.e. its root is
     the repo root, but it is saved in .hg/largefiles/dirstate.
     """
     vfs = repo.vfs
     lfstoredir = longname
     opener = vfsmod.vfs(vfs.join(lfstoredir))
     use_dirstate_v2 = requirements.DIRSTATE_V2_REQUIREMENT in repo.requirements
     lfdirstate = largefilesdirstate(
         opener,
         ui,
         repo.root,
         repo.dirstate._validate,
         lambda: sparse.matcher(repo),
         repo.nodeconstants,
         use_dirstate_v2,
     )
 
     # If the largefiles dirstate does not exist, populate and create
     # it. This ensures that we create it on the first meaningful
     # largefiles operation in a new clone.
     if create and not vfs.exists(vfs.join(lfstoredir, b'dirstate')):
         matcher = getstandinmatcher(repo)
         standins = repo.dirstate.walk(
             matcher, subrepos=[], unknown=False, ignored=False
         )
 
         if len(standins) > 0:
             vfs.makedirs(lfstoredir)
 
         for standin in standins:
             lfile = splitstandin(standin)
             lfdirstate.normallookup(lfile)
     return lfdirstate
 
 
 def lfdirstatestatus(lfdirstate, repo):
     pctx = repo[b'.']
     match = matchmod.always()
     unsure, s = lfdirstate.status(
         match, subrepos=[], ignored=False, clean=False, unknown=False
     )
     modified, clean = s.modified, s.clean
     for lfile in unsure:
         try:
             fctx = pctx[standin(lfile)]
         except LookupError:
             fctx = None
         if not fctx or readasstandin(fctx) != hashfile(repo.wjoin(lfile)):
             modified.append(lfile)
         else:
             clean.append(lfile)
             lfdirstate.normal(lfile)
     return s
 
 
 def listlfiles(repo, rev=None, matcher=None):
     """return a list of largefiles in the working copy or the
     specified changeset"""
 
     if matcher is None:
         matcher = getstandinmatcher(repo)
 
     # ignore unknown files in working directory
     return [
         splitstandin(f)
         for f in repo[rev].walk(matcher)
         if rev is not None or repo.dirstate[f] != b'?'
     ]
 
 
 def instore(repo, hash, forcelocal=False):
     '''Return true if a largefile with the given hash exists in the store'''
     return os.path.exists(storepath(repo, hash, forcelocal))
 
 
 def storepath(repo, hash, forcelocal=False):
     """Return the correct location in the repository largefiles store for a
     file with the given hash."""
     if not forcelocal and repo.shared():
         return repo.vfs.reljoin(repo.sharedpath, longname, hash)
     return repo.vfs.join(longname, hash)
 
 
 def findstorepath(repo, hash):
     """Search through the local store path(s) to find the file for the given
     hash.  If the file is not found, its path in the primary store is returned.
     The return value is a tuple of (path, exists(path)).
     """
     # For shared repos, the primary store is in the share source.  But for
     # backward compatibility, force a lookup in the local store if it wasn't
     # found in the share source.
     path = storepath(repo, hash, False)
 
     if instore(repo, hash):
         return (path, True)
     elif repo.shared() and instore(repo, hash, True):
         return storepath(repo, hash, True), True
 
     return (path, False)
 
 
 def copyfromcache(repo, hash, filename):
     """Copy the specified largefile from the repo or system cache to
     filename in the repository. Return true on success or false if the
     file was not found in either cache (which should not happened:
     this is meant to be called only after ensuring that the needed
     largefile exists in the cache)."""
     wvfs = repo.wvfs
     path = findfile(repo, hash)
     if path is None:
         return False
     wvfs.makedirs(wvfs.dirname(wvfs.join(filename)))
     # The write may fail before the file is fully written, but we
     # don't use atomic writes in the working copy.
     with open(path, b'rb') as srcfd, wvfs(filename, b'wb') as destfd:
         gothash = copyandhash(util.filechunkiter(srcfd), destfd)
     if gothash != hash:
         repo.ui.warn(
             _(b'%s: data corruption in %s with hash %s\n')
             % (filename, path, gothash)
         )
         wvfs.unlink(filename)
         return False
     return True
 
 
 def copytostore(repo, ctx, file, fstandin):
     wvfs = repo.wvfs
     hash = readasstandin(ctx[fstandin])
     if instore(repo, hash):
         return
     if wvfs.exists(file):
         copytostoreabsolute(repo, wvfs.join(file), hash)
     else:
         repo.ui.warn(
             _(b"%s: largefile %s not available from local store\n")
             % (file, hash)
         )
 
 
 def copyalltostore(repo, node):
     '''Copy all largefiles in a given revision to the store'''
 
     ctx = repo[node]
     for filename in ctx.files():
         realfile = splitstandin(filename)
         if realfile is not None and filename in ctx.manifest():
             copytostore(repo, ctx, realfile, filename)
 
 
 def copytostoreabsolute(repo, file, hash):
     if inusercache(repo.ui, hash):
         link(usercachepath(repo.ui, hash), storepath(repo, hash))
     else:
         util.makedirs(os.path.dirname(storepath(repo, hash)))
         with open(file, b'rb') as srcf:
             with util.atomictempfile(
                 storepath(repo, hash), createmode=repo.store.createmode
             ) as dstf:
                 for chunk in util.filechunkiter(srcf):
                     dstf.write(chunk)
         linktousercache(repo, hash)
 
 
 def linktousercache(repo, hash):
     """Link / copy the largefile with the specified hash from the store
     to the cache."""
     path = usercachepath(repo.ui, hash)
     link(storepath(repo, hash), path)
 
 
 def getstandinmatcher(repo, rmatcher=None):
     '''Return a match object that applies rmatcher to the standin directory'''
     wvfs = repo.wvfs
     standindir = shortname
 
     # no warnings about missing files or directories
     badfn = lambda f, msg: None
 
     if rmatcher and not rmatcher.always():
         pats = [wvfs.join(standindir, pat) for pat in rmatcher.files()]
         if not pats:
             pats = [wvfs.join(standindir)]
         match = scmutil.match(repo[None], pats, badfn=badfn)
     else:
         # no patterns: relative to repo root
         match = scmutil.match(repo[None], [wvfs.join(standindir)], badfn=badfn)
     return match
 
 
 def composestandinmatcher(repo, rmatcher):
     """Return a matcher that accepts standins corresponding to the
     files accepted by rmatcher. Pass the list of files in the matcher
     as the paths specified by the user."""
     smatcher = getstandinmatcher(repo, rmatcher)
     isstandin = smatcher.matchfn
 
     def composedmatchfn(f):
         return isstandin(f) and rmatcher.matchfn(splitstandin(f))
 
     smatcher.matchfn = composedmatchfn
 
     return smatcher
 
 
 def standin(filename):
     """Return the repo-relative path to the standin for the specified big
     file."""
     # Notes:
     # 1) Some callers want an absolute path, but for instance addlargefiles
     #    needs it repo-relative so it can be passed to repo[None].add().  So
     #    leave it up to the caller to use repo.wjoin() to get an absolute path.
     # 2) Join with '/' because that's what dirstate always uses, even on
     #    Windows. Change existing separator to '/' first in case we are
     #    passed filenames from an external source (like the command line).
     return shortnameslash + util.pconvert(filename)
 
 
 def isstandin(filename):
     """Return true if filename is a big file standin. filename must be
     in Mercurial's internal form (slash-separated)."""
     return filename.startswith(shortnameslash)
 
 
 def splitstandin(filename):
     # Split on / because that's what dirstate always uses, even on Windows.
     # Change local separator to / first just in case we are passed filenames
     # from an external source (like the command line).
     bits = util.pconvert(filename).split(b'/', 1)
     if len(bits) == 2 and bits[0] == shortname:
         return bits[1]
     else:
         return None
 
 
 def updatestandin(repo, lfile, standin):
     """Re-calculate hash value of lfile and write it into standin
 
     This assumes that "lfutil.standin(lfile) == standin", for efficiency.
     """
     file = repo.wjoin(lfile)
     if repo.wvfs.exists(lfile):
         hash = hashfile(file)
         executable = getexecutable(file)
         writestandin(repo, standin, hash, executable)
     else:
         raise error.Abort(_(b'%s: file not found!') % lfile)
 
 
 def readasstandin(fctx):
     """read hex hash from given filectx of standin file
 
     This encapsulates how "standin" data is stored into storage layer."""
     return fctx.data().strip()
 
 
 def writestandin(repo, standin, hash, executable):
     '''write hash to <repo.root>/<standin>'''
     repo.wwrite(standin, hash + b'\n', executable and b'x' or b'')
 
 
 def copyandhash(instream, outfile):
     """Read bytes from instream (iterable) and write them to outfile,
     computing the SHA-1 hash of the data along the way. Return the hash."""
     hasher = hashutil.sha1(b'')
     for data in instream:
         hasher.update(data)
         outfile.write(data)
     return hex(hasher.digest())
 
 
 def hashfile(file):
     if not os.path.exists(file):
         return b''
     with open(file, b'rb') as fd:
         return hexsha1(fd)
 
 
 def getexecutable(filename):
     mode = os.stat(filename).st_mode
     return (
         (mode & stat.S_IXUSR)
         and (mode & stat.S_IXGRP)
         and (mode & stat.S_IXOTH)
     )
 
 
 def urljoin(first, second, *arg):
     def join(left, right):
         if not left.endswith(b'/'):
             left += b'/'
         if right.startswith(b'/'):
             right = right[1:]
         return left + right
 
     url = join(first, second)
     for a in arg:
         url = join(url, a)
     return url
 
 
 def hexsha1(fileobj):
     """hexsha1 returns the hex-encoded sha1 sum of the data in the file-like
     object data"""
     h = hashutil.sha1()
     for chunk in util.filechunkiter(fileobj):
         h.update(chunk)
     return hex(h.digest())
 
 
 def httpsendfile(ui, filename):
     return httpconnection.httpsendfile(ui, filename, b'rb')
 
 
 def unixpath(path):
     '''Return a version of path normalized for use with the lfdirstate.'''
     return util.pconvert(os.path.normpath(path))
 
 
 def islfilesrepo(repo):
     '''Return true if the repo is a largefile repo.'''
     if b'largefiles' in repo.requirements and any(
         shortnameslash in f[1] for f in repo.store.datafiles()
     ):
         return True
 
     return any(openlfdirstate(repo.ui, repo, False))
 
 
 class storeprotonotcapable(Exception):
     def __init__(self, storetypes):
         self.storetypes = storetypes
 
 
 def getstandinsstate(repo):
     standins = []
     matcher = getstandinmatcher(repo)
     wctx = repo[None]
     for standin in repo.dirstate.walk(
         matcher, subrepos=[], unknown=False, ignored=False
     ):
         lfile = splitstandin(standin)
         try:
             hash = readasstandin(wctx[standin])
         except IOError:
             hash = None
         standins.append((lfile, hash))
     return standins
 
 
 def synclfdirstate(repo, lfdirstate, lfile, normallookup):
     lfstandin = standin(lfile)
     if lfstandin in repo.dirstate:
         stat = repo.dirstate._map[lfstandin]
         state, mtime = stat.state, stat.mtime
     else:
         state, mtime = b'?', -1
     if state == b'n':
         if normallookup or mtime < 0 or not repo.wvfs.exists(lfile):
             # state 'n' doesn't ensure 'clean' in this case
             lfdirstate.normallookup(lfile)
         else:
             lfdirstate.normal(lfile)
     elif state == b'm':
         lfdirstate.normallookup(lfile)
     elif state == b'r':
         lfdirstate.remove(lfile)
     elif state == b'a':
         lfdirstate.add(lfile)
     elif state == b'?':
         lfdirstate.drop(lfile)
 
 
 def markcommitted(orig, ctx, node):
     repo = ctx.repo()
 
     orig(node)
 
     # ATTENTION: "ctx.files()" may differ from "repo[node].files()"
     # because files coming from the 2nd parent are omitted in the latter.
     #
     # The former should be used to get targets of "synclfdirstate",
     # because such files:
     # - are marked as "a" by "patch.patch()" (e.g. via transplant), and
     # - have to be marked as "n" after commit, but
     # - aren't listed in "repo[node].files()"
 
     lfdirstate = openlfdirstate(repo.ui, repo)
     for f in ctx.files():
         lfile = splitstandin(f)
         if lfile is not None:
             synclfdirstate(repo, lfdirstate, lfile, False)
     lfdirstate.write()
 
     # As part of committing, copy all of the largefiles into the cache.
     #
     # Using "node" instead of "ctx" implies additional "repo[node]"
     # lookup while copyalltostore(), but can omit redundant check for
     # files comming from the 2nd parent, which should exist in store
     # at merging.
     copyalltostore(repo, node)
 
 
 def getlfilestoupdate(oldstandins, newstandins):
     changedstandins = set(oldstandins).symmetric_difference(set(newstandins))
     filelist = []
     for f in changedstandins:
         if f[0] not in filelist:
             filelist.append(f[0])
     return filelist
 
 
 def getlfilestoupload(repo, missing, addfunc):
     makeprogress = repo.ui.makeprogress
     with makeprogress(
         _(b'finding outgoing largefiles'),
         unit=_(b'revisions'),
         total=len(missing),
     ) as progress:
         for i, n in enumerate(missing):
             progress.update(i)
             parents = [p for p in repo[n].parents() if p != repo.nullid]
 
             with lfstatus(repo, value=False):
                 ctx = repo[n]
 
             files = set(ctx.files())
             if len(parents) == 2:
                 mc = ctx.manifest()
                 mp1 = ctx.p1().manifest()
                 mp2 = ctx.p2().manifest()
                 for f in mp1:
                     if f not in mc:
                         files.add(f)
                 for f in mp2:
                     if f not in mc:
                         files.add(f)
                 for f in mc:
                     if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                         files.add(f)
             for fn in files:
                 if isstandin(fn) and fn in ctx:
                     addfunc(fn, readasstandin(ctx[fn]))
 
 
 def updatestandinsbymatch(repo, match):
     """Update standins in the working directory according to specified match
 
     This returns (possibly modified) ``match`` object to be used for
     subsequent commit process.
     """
 
     ui = repo.ui
 
     # Case 1: user calls commit with no specific files or
     # include/exclude patterns: refresh and commit all files that
     # are "dirty".
     if match is None or match.always():
         # Spend a bit of time here to get a list of files we know
         # are modified so we can compare only against those.
         # It can cost a lot of time (several seconds)
         # otherwise to update all standins if the largefiles are
         # large.
         lfdirstate = openlfdirstate(ui, repo)
         dirtymatch = matchmod.always()
         unsure, s = lfdirstate.status(
             dirtymatch, subrepos=[], ignored=False, clean=False, unknown=False
         )
         modifiedfiles = unsure + s.modified + s.added + s.removed
         lfiles = listlfiles(repo)
         # this only loops through largefiles that exist (not
         # removed/renamed)
         for lfile in lfiles:
             if lfile in modifiedfiles:
                 fstandin = standin(lfile)
                 if repo.wvfs.exists(fstandin):
                     # this handles the case where a rebase is being
                     # performed and the working copy is not updated
                     # yet.
                     if repo.wvfs.exists(lfile):
                         updatestandin(repo, lfile, fstandin)
 
         return match
 
     lfiles = listlfiles(repo)
     match._files = repo._subdirlfs(match.files(), lfiles)
 
     # Case 2: user calls commit with specified patterns: refresh
     # any matching big files.
     smatcher = composestandinmatcher(repo, match)
     standins = repo.dirstate.walk(
         smatcher, subrepos=[], unknown=False, ignored=False
     )
 
     # No matching big files: get out of the way and pass control to
     # the usual commit() method.
     if not standins:
         return match
 
     # Refresh all matching big files.  It's possible that the
     # commit will end up failing, in which case the big files will
     # stay refreshed.  No harm done: the user modified them and
     # asked to commit them, so sooner or later we're going to
     # refresh the standins.  Might as well leave them refreshed.
     lfdirstate = openlfdirstate(ui, repo)
     for fstandin in standins:
         lfile = splitstandin(fstandin)
         if lfdirstate[lfile] != b'r':
             updatestandin(repo, lfile, fstandin)
 
     # Cook up a new matcher that only matches regular files or
     # standins corresponding to the big files requested by the
     # user.  Have to modify _files to prevent commit() from
     # complaining "not tracked" for big files.
     match = copy.copy(match)
     origmatchfn = match.matchfn
 
     # Check both the list of largefiles and the list of
     # standins because if a largefile was removed, it
     # won't be in the list of largefiles at this point
     match._files += sorted(standins)
 
     actualfiles = []
     for f in match._files:
         fstandin = standin(f)
 
         # For largefiles, only one of the normal and standin should be
         # committed (except if one of them is a remove).  In the case of a
         # standin removal, drop the normal file if it is unknown to dirstate.
         # Thus, skip plain largefile names but keep the standin.
         if f in lfiles or fstandin in standins:
             if repo.dirstate[fstandin] != b'r':
                 if repo.dirstate[f] != b'r':
                     continue
             elif repo.dirstate[f] == b'?':
                 continue
 
         actualfiles.append(f)
     match._files = actualfiles
 
     def matchfn(f):
         if origmatchfn(f):
             return f not in lfiles
         else:
             return f in standins
 
     match.matchfn = matchfn
 
     return match
 
 
 class automatedcommithook(object):
     """Stateful hook to update standins at the 1st commit of resuming
 
     For efficiency, updating standins in the working directory should
     be avoided while automated committing (like rebase, transplant and
     so on), because they should be updated before committing.
 
     But the 1st commit of resuming automated committing (e.g. ``rebase
     --continue``) should update them, because largefiles may be
     modified manually.
     """
 
     def __init__(self, resuming):
         self.resuming = resuming
 
     def __call__(self, repo, match):
         if self.resuming:
             self.resuming = False  # avoids updating at subsequent commits
             return updatestandinsbymatch(repo, match)
         else:
             return match
 
 
 def getstatuswriter(ui, repo, forcibly=None):
     """Return the function to write largefiles specific status out
 
     If ``forcibly`` is ``None``, this returns the last element of
     ``repo._lfstatuswriters`` as "default" writer function.
 
     Otherwise, this returns the function to always write out (or
     ignore if ``not forcibly``) status.
     """
     if forcibly is None and util.safehasattr(repo, b'_largefilesenabled'):
         return repo._lfstatuswriters[-1]
     else:
         if forcibly:
             return ui.status  # forcibly WRITE OUT
         else:
             return lambda *msg, **opts: None  # forcibly IGNORE

hgext/narrow/narrowdirstate.py

@@ -1,72 +1,76
 # narrowdirstate.py - extensions to mercurial dirstate to support narrow clones
 #
 # Copyright 2017 Google, Inc.
 #
 # 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
 
 from mercurial.i18n import _
 from mercurial import error
 
 
 def wrapdirstate(repo, dirstate):
     """Add narrow spec dirstate ignore, block changes outside narrow spec."""
 
     def _editfunc(fn):
         def _wrapper(self, *args, **kwargs):
             narrowmatch = repo.narrowmatch()
             for f in args:
                 if f is not None and not narrowmatch(f) and f not in self:
                     raise error.Abort(
                         _(
                             b"cannot track '%s' - it is outside "
                             + b"the narrow clone"
                         )
                         % f
                     )
             return fn(self, *args, **kwargs)
 
         return _wrapper
 
     class narrowdirstate(dirstate.__class__):
         # Prevent adding/editing/copying/deleting files that are outside the
         # sparse checkout
         @_editfunc
         def normal(self, *args, **kwargs):
             return super(narrowdirstate, self).normal(*args, **kwargs)
 
         @_editfunc
         def set_tracked(self, *args):
             return super(narrowdirstate, self).set_tracked(*args)
 
         @_editfunc
+        def set_untracked(self, *args):
+            return super(narrowdirstate, self).set_untracked(*args)
+
+        @_editfunc
         def add(self, *args):
             return super(narrowdirstate, self).add(*args)
 
         @_editfunc
         def normallookup(self, *args):
             return super(narrowdirstate, self).normallookup(*args)
 
         @_editfunc
         def copy(self, *args):
             return super(narrowdirstate, self).copy(*args)
 
         @_editfunc
         def remove(self, *args):
             return super(narrowdirstate, self).remove(*args)
 
         @_editfunc
         def merge(self, *args):
             return super(narrowdirstate, self).merge(*args)
 
         def rebuild(self, parent, allfiles, changedfiles=None):
             if changedfiles is None:
                 # Rebuilding entire dirstate, let's filter allfiles to match the
                 # narrowspec.
                 allfiles = [f for f in allfiles if repo.narrowmatch()(f)]
             super(narrowdirstate, self).rebuild(parent, allfiles, changedfiles)
 
     dirstate.__class__ = narrowdirstate
     return dirstate

hgext/sparse.py

@@ -1,441 +1,442
 # sparse.py - allow sparse checkouts of the working directory
 #
 # Copyright 2014 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """allow sparse checkouts of the working directory (EXPERIMENTAL)
 
 (This extension is not yet protected by backwards compatibility
 guarantees. Any aspect may break in future releases until this
 notice is removed.)
 
 This extension allows the working directory to only consist of a
 subset of files for the revision. This allows specific files or
 directories to be explicitly included or excluded. Many repository
 operations have performance proportional to the number of files in
 the working directory. So only realizing a subset of files in the
 working directory can improve performance.
 
 Sparse Config Files
 -------------------
 
 The set of files that are part of a sparse checkout are defined by
 a sparse config file. The file defines 3 things: includes (files to
 include in the sparse checkout), excludes (files to exclude from the
 sparse checkout), and profiles (links to other config files).
 
 The file format is newline delimited. Empty lines and lines beginning
 with ``#`` are ignored.
 
 Lines beginning with ``%include `` denote another sparse config file
 to include. e.g. ``%include tests.sparse``. The filename is relative
 to the repository root.
 
 The special lines ``[include]`` and ``[exclude]`` denote the section
 for includes and excludes that follow, respectively. It is illegal to
 have ``[include]`` after ``[exclude]``.
 
 Non-special lines resemble file patterns to be added to either includes
 or excludes. The syntax of these lines is documented by :hg:`help patterns`.
 Patterns are interpreted as ``glob:`` by default and match against the
 root of the repository.
 
 Exclusion patterns take precedence over inclusion patterns. So even
 if a file is explicitly included, an ``[exclude]`` entry can remove it.
 
 For example, say you have a repository with 3 directories, ``frontend/``,
 ``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond
 to different projects and it is uncommon for someone working on one
 to need the files for the other. But ``tools/`` contains files shared
 between both projects. Your sparse config files may resemble::
 
   # frontend.sparse
   frontend/**
   tools/**
 
   # backend.sparse
   backend/**
   tools/**
 
 Say the backend grows in size. Or there's a directory with thousands
 of files you wish to exclude. You can modify the profile to exclude
 certain files::
 
   [include]
   backend/**
   tools/**
 
   [exclude]
   tools/tests/**
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial.pycompat import setattr
 from mercurial import (
     commands,
     dirstate,
     error,
     extensions,
     logcmdutil,
     match as matchmod,
     merge as mergemod,
     pycompat,
     registrar,
     sparse,
     util,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 
 def extsetup(ui):
     sparse.enabled = True
 
     _setupclone(ui)
     _setuplog(ui)
     _setupadd(ui)
     _setupdirstate(ui)
 
 
 def replacefilecache(cls, propname, replacement):
     """Replace a filecache property with a new class. This allows changing the
     cache invalidation condition."""
     origcls = cls
     assert callable(replacement)
     while cls is not object:
         if propname in cls.__dict__:
             orig = cls.__dict__[propname]
             setattr(cls, propname, replacement(orig))
             break
         cls = cls.__bases__[0]
 
     if cls is object:
         raise AttributeError(
             _(b"type '%s' has no property '%s'") % (origcls, propname)
         )
 
 
 def _setuplog(ui):
     entry = commands.table[b'log|history']
     entry[1].append(
         (
             b'',
             b'sparse',
             None,
             b"limit to changesets affecting the sparse checkout",
         )
     )
 
     def _initialrevs(orig, repo, wopts):
         revs = orig(repo, wopts)
         if wopts.opts.get(b'sparse'):
             sparsematch = sparse.matcher(repo)
 
             def ctxmatch(rev):
                 ctx = repo[rev]
                 return any(f for f in ctx.files() if sparsematch(f))
 
             revs = revs.filter(ctxmatch)
         return revs
 
     extensions.wrapfunction(logcmdutil, b'_initialrevs', _initialrevs)
 
 
 def _clonesparsecmd(orig, ui, repo, *args, **opts):
     include_pat = opts.get('include')
     exclude_pat = opts.get('exclude')
     enableprofile_pat = opts.get('enable_profile')
     narrow_pat = opts.get('narrow')
     include = exclude = enableprofile = False
     if include_pat:
         pat = include_pat
         include = True
     if exclude_pat:
         pat = exclude_pat
         exclude = True
     if enableprofile_pat:
         pat = enableprofile_pat
         enableprofile = True
     if sum([include, exclude, enableprofile]) > 1:
         raise error.Abort(_(b"too many flags specified."))
     # if --narrow is passed, it means they are includes and excludes for narrow
     # clone
     if not narrow_pat and (include or exclude or enableprofile):
 
         def clonesparse(orig, ctx, *args, **kwargs):
             sparse.updateconfig(
                 ctx.repo().unfiltered(),
                 pat,
                 {},
                 include=include,
                 exclude=exclude,
                 enableprofile=enableprofile,
                 usereporootpaths=True,
             )
             return orig(ctx, *args, **kwargs)
 
         extensions.wrapfunction(mergemod, b'update', clonesparse)
     return orig(ui, repo, *args, **opts)
 
 
 def _setupclone(ui):
     entry = commands.table[b'clone']
     entry[1].append((b'', b'enable-profile', [], b'enable a sparse profile'))
     entry[1].append((b'', b'include', [], b'include sparse pattern'))
     entry[1].append((b'', b'exclude', [], b'exclude sparse pattern'))
     extensions.wrapcommand(commands.table, b'clone', _clonesparsecmd)
 
 
 def _setupadd(ui):
     entry = commands.table[b'add']
     entry[1].append(
         (
             b's',
             b'sparse',
             None,
             b'also include directories of added files in sparse config',
         )
     )
 
     def _add(orig, ui, repo, *pats, **opts):
         if opts.get('sparse'):
             dirs = set()
             for pat in pats:
                 dirname, basename = util.split(pat)
                 dirs.add(dirname)
             sparse.updateconfig(repo, list(dirs), opts, include=True)
         return orig(ui, repo, *pats, **opts)
 
     extensions.wrapcommand(commands.table, b'add', _add)
 
 
 def _setupdirstate(ui):
     """Modify the dirstate to prevent stat'ing excluded files,
     and to prevent modifications to files outside the checkout.
     """
 
     def walk(orig, self, match, subrepos, unknown, ignored, full=True):
         # hack to not exclude explicitly-specified paths so that they can
         # be warned later on e.g. dirstate.add()
         em = matchmod.exact(match.files())
         sm = matchmod.unionmatcher([self._sparsematcher, em])
         match = matchmod.intersectmatchers(match, sm)
         return orig(self, match, subrepos, unknown, ignored, full)
 
     extensions.wrapfunction(dirstate.dirstate, b'walk', walk)
 
     # dirstate.rebuild should not add non-matching files
     def _rebuild(orig, self, parent, allfiles, changedfiles=None):
         matcher = self._sparsematcher
         if not matcher.always():
             allfiles = [f for f in allfiles if matcher(f)]
             if changedfiles:
                 changedfiles = [f for f in changedfiles if matcher(f)]
 
             if changedfiles is not None:
                 # In _rebuild, these files will be deleted from the dirstate
                 # when they are not found to be in allfiles
                 dirstatefilestoremove = {f for f in self if not matcher(f)}
                 changedfiles = dirstatefilestoremove.union(changedfiles)
 
         return orig(self, parent, allfiles, changedfiles)
 
     extensions.wrapfunction(dirstate.dirstate, b'rebuild', _rebuild)
 
     # Prevent adding files that are outside the sparse checkout
     editfuncs = [
         b'normal',
         b'set_tracked',
+        b'set_untracked',
         b'add',
         b'normallookup',
         b'copy',
         b'remove',
         b'merge',
     ]
     hint = _(
         b'include file with `hg debugsparse --include <pattern>` or use '
         + b'`hg add -s <file>` to include file directory while adding'
     )
     for func in editfuncs:
 
         def _wrapper(orig, self, *args, **kwargs):
             sparsematch = self._sparsematcher
             if not sparsematch.always():
                 for f in args:
                     if f is not None and not sparsematch(f) and f not in self:
                         raise error.Abort(
                             _(
                                 b"cannot add '%s' - it is outside "
                                 b"the sparse checkout"
                             )
                             % f,
                             hint=hint,
                         )
             return orig(self, *args, **kwargs)
 
         extensions.wrapfunction(dirstate.dirstate, func, _wrapper)
 
 
 @command(
     b'debugsparse',
     [
         (b'I', b'include', False, _(b'include files in the sparse checkout')),
         (b'X', b'exclude', False, _(b'exclude files in the sparse checkout')),
         (b'd', b'delete', False, _(b'delete an include/exclude rule')),
         (
             b'f',
             b'force',
             False,
             _(b'allow changing rules even with pending changes'),
         ),
         (b'', b'enable-profile', False, _(b'enables the specified profile')),
         (b'', b'disable-profile', False, _(b'disables the specified profile')),
         (b'', b'import-rules', False, _(b'imports rules from a file')),
         (b'', b'clear-rules', False, _(b'clears local include/exclude rules')),
         (
             b'',
             b'refresh',
             False,
             _(b'updates the working after sparseness changes'),
         ),
         (b'', b'reset', False, _(b'makes the repo full again')),
     ]
     + commands.templateopts,
     _(b'[--OPTION] PATTERN...'),
     helpbasic=True,
 )
 def debugsparse(ui, repo, *pats, **opts):
     """make the current checkout sparse, or edit the existing checkout
 
     The sparse command is used to make the current checkout sparse.
     This means files that don't meet the sparse condition will not be
     written to disk, or show up in any working copy operations. It does
     not affect files in history in any way.
 
     Passing no arguments prints the currently applied sparse rules.
 
     --include and --exclude are used to add and remove files from the sparse
     checkout. The effects of adding an include or exclude rule are applied
     immediately. If applying the new rule would cause a file with pending
     changes to be added or removed, the command will fail. Pass --force to
     force a rule change even with pending changes (the changes on disk will
     be preserved).
 
     --delete removes an existing include/exclude rule. The effects are
     immediate.
 
     --refresh refreshes the files on disk based on the sparse rules. This is
     only necessary if .hg/sparse was changed by hand.
 
     --enable-profile and --disable-profile accept a path to a .hgsparse file.
     This allows defining sparse checkouts and tracking them inside the
     repository. This is useful for defining commonly used sparse checkouts for
     many people to use. As the profile definition changes over time, the sparse
     checkout will automatically be updated appropriately, depending on which
     changeset is checked out. Changes to .hgsparse are not applied until they
     have been committed.
 
     --import-rules accepts a path to a file containing rules in the .hgsparse
     format, allowing you to add --include, --exclude and --enable-profile rules
     in bulk. Like the --include, --exclude and --enable-profile switches, the
     changes are applied immediately.
 
     --clear-rules removes all local include and exclude rules, while leaving
     any enabled profiles in place.
 
     Returns 0 if editing the sparse checkout succeeds.
     """
     opts = pycompat.byteskwargs(opts)
     include = opts.get(b'include')
     exclude = opts.get(b'exclude')
     force = opts.get(b'force')
     enableprofile = opts.get(b'enable_profile')
     disableprofile = opts.get(b'disable_profile')
     importrules = opts.get(b'import_rules')
     clearrules = opts.get(b'clear_rules')
     delete = opts.get(b'delete')
     refresh = opts.get(b'refresh')
     reset = opts.get(b'reset')
     count = sum(
         [
             include,
             exclude,
             enableprofile,
             disableprofile,
             delete,
             importrules,
             refresh,
             clearrules,
             reset,
         ]
     )
     if count > 1:
         raise error.Abort(_(b"too many flags specified"))
 
     if count == 0:
         if repo.vfs.exists(b'sparse'):
             ui.status(repo.vfs.read(b"sparse") + b"\n")
             temporaryincludes = sparse.readtemporaryincludes(repo)
             if temporaryincludes:
                 ui.status(
                     _(b"Temporarily Included Files (for merge/rebase):\n")
                 )
                 ui.status((b"\n".join(temporaryincludes) + b"\n"))
             return
         else:
             raise error.Abort(
                 _(
                     b'the debugsparse command is only supported on'
                     b' sparse repositories'
                 )
             )
 
     if include or exclude or delete or reset or enableprofile or disableprofile:
         sparse.updateconfig(
             repo,
             pats,
             opts,
             include=include,
             exclude=exclude,
             reset=reset,
             delete=delete,
             enableprofile=enableprofile,
             disableprofile=disableprofile,
             force=force,
         )
 
     if importrules:
         sparse.importfromfiles(repo, opts, pats, force=force)
 
     if clearrules:
         sparse.clearrules(repo, force=force)
 
     if refresh:
         try:
             wlock = repo.wlock()
             fcounts = map(
                 len,
                 sparse.refreshwdir(
                     repo, repo.status(), sparse.matcher(repo), force=force
                 ),
             )
             sparse.printchanges(
                 ui,
                 opts,
                 added=fcounts[0],
                 dropped=fcounts[1],
                 conflicting=fcounts[2],
             )
         finally:
             wlock.release()

mercurial/dirstate.py

@@ -1,1526 +1,1545
 # 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 = parsers.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._updatedfiles = set()
         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.
         """
         entry = self._map.get(key)
         if entry is not None:
             return entry.state
         return b'?'
 
     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 directories(self):
         return self._map.directories()
 
     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
         self._map.setparents(p1, p2)
         copies = {}
         if (
             oldp2 != self._nodeconstants.nullid
             and p2 == self._nodeconstants.nullid
         ):
             candidatefiles = self._map.non_normal_or_other_parent_paths()
 
             for f in candidatefiles:
                 s = self._map.get(f)
                 if s is None:
                     continue
 
                 # Discard "merged" markers when moving away from a merge state
                 if s.merged:
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self.normallookup(f)
                 # Also fix up otherparent markers
                 elif s.from_p2:
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self._add(f)
         return copies
 
     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._updatedfiles.clear()
         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
             self._updatedfiles.add(source)
             self._updatedfiles.add(dest)
         elif self._map.copymap.pop(dest, None):
             self._updatedfiles.add(dest)
 
     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.
         """
         entry = self._map.get(filename)
         if entry is None:
             self._add(filename)
             return True
         elif not entry.tracked:
             self.normallookup(filename)
             return True
         return False
 
+    @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.
+        """
+        entry = self._map.get(filename)
+        if entry is None:
+            return False
+        elif entry.added:
+            self._drop(filename)
+            return True
+        else:
+            self._remove(filename)
+            return True
+
     @requires_parents_change
     def update_file_reference(
         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 p1_tracked and wc_tracked:
             # the underlying reference might have changed, we will have to
             # check it.
             self.normallookup(filename)
         elif not (p1_tracked or wc_tracked):
             # the file is no longer relevant to anyone
             self._drop(filename)
         elif (not p1_tracked) and wc_tracked:
             if not entry.added:
                 self._add(filename)
         elif p1_tracked and not wc_tracked:
             if entry is None or not entry.removed:
                 self._remove(filename)
         else:
             assert False, 'unreachable'
 
     def _addpath(
         self,
         f,
         mode=0,
         size=None,
         mtime=None,
         added=False,
         merged=False,
         from_p2=False,
         possibly_dirty=False,
     ):
         entry = self._map.get(f)
         if added or entry is not None and entry.removed:
             scmutil.checkfilename(f)
             if self._map.hastrackeddir(f):
                 msg = _(b'directory %r already in dirstate')
                 msg %= pycompat.bytestr(f)
                 raise error.Abort(msg)
             # shadows
             for d in pathutil.finddirs(f):
                 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(f))
                     raise error.Abort(msg)
         self._dirty = True
         self._updatedfiles.add(f)
         self._map.addfile(
             f,
             mode=mode,
             size=size,
             mtime=mtime,
             added=added,
             merged=merged,
             from_p2=from_p2,
             possibly_dirty=possibly_dirty,
         )
 
     def normal(self, f, parentfiledata=None):
         """Mark a file normal and clean.
 
         parentfiledata: (mode, size, mtime) of the clean file
 
         parentfiledata should be computed from memory (for mode,
         size), as or close as possible from the point where we
         determined the file was clean, to limit the risk of the
         file having been changed by an external process between the
         moment where the file was determined to be clean and now."""
         if parentfiledata:
             (mode, size, mtime) = parentfiledata
         else:
             s = os.lstat(self._join(f))
             mode = s.st_mode
             size = s.st_size
             mtime = s[stat.ST_MTIME]
         self._addpath(f, mode=mode, size=size, mtime=mtime)
         self._map.copymap.pop(f, None)
         if f in self._map.nonnormalset:
             self._map.nonnormalset.remove(f)
         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
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self.in_merge:
             # if there is a merge going on and the file was either
             # "merged" or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map.get(f)
             if entry is not None:
                 # XXX this should probably be dealt with a a lower level
                 # (see `merged_removed` and `from_p2_removed`)
                 if entry.merged_removed or entry.from_p2_removed:
                     source = self._map.copymap.get(f)
                     if entry.merged_removed:
                         self.merge(f)
                     elif entry.from_p2_removed:
                         self.otherparent(f)
                     if source is not None:
                         self.copy(source, f)
                     return
                 elif entry.merged or entry.from_p2:
                     return
         self._addpath(f, possibly_dirty=True)
         self._map.copymap.pop(f, None)
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if not self.in_merge:
             msg = _(b"setting %r to other parent only allowed in merges") % f
             raise error.Abort(msg)
         entry = self._map.get(f)
         if entry is not None and entry.tracked:
             # merge-like
             self._addpath(f, merged=True)
         else:
             # add-like
             self._addpath(f, from_p2=True)
         self._map.copymap.pop(f, None)
 
     def add(self, f):
         '''Mark a file added.'''
         self._add(f)
 
     def _add(self, filename):
         """internal function to mark a file as added"""
         self._addpath(filename, added=True)
         self._map.copymap.pop(filename, None)
 
     def remove(self, f):
         '''Mark a file removed'''
         self._remove(f)
 
     def _remove(self, filename):
         """internal function to mark a file removed"""
         self._dirty = True
         self._updatedfiles.add(filename)
         self._map.removefile(filename, in_merge=self.in_merge)
 
     def merge(self, f):
         '''Mark a file merged.'''
         if not self.in_merge:
             return self.normallookup(f)
         return self.otherparent(f)
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         self._drop(f)
 
     def _drop(self, filename):
         """internal function to drop a file from the dirstate"""
         if self._map.dropfile(filename):
             self._dirty = True
             self._updatedfiles.add(filename)
             self._map.copymap.pop(filename, None)
 
     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._updatedfiles.clear()
         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:
             self.normallookup(f)
         for f in to_drop:
             self._drop(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
 
             # emulate dropping timestamp in 'parsers.pack_dirstate'
             now = _getfsnow(self._opener)
             self._map.clearambiguoustimes(self._updatedfiles, now)
 
             # emulate that all 'dirstate.normal' results are written out
             self._lastnormaltime = 0
             self._updatedfiles.clear()
 
             # delay writing in-memory changes out
             tr.addfilegenerator(
                 b'dirstate',
                 (self._filename,),
                 self._writedirstate,
                 location=b'plain',
             )
             return
 
         st = self._opener(filename, b"w", atomictemp=True, checkambig=True)
         self._writedirstate(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, st):
         # 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
         # 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(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._rustmap,
             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.merged:
                 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 t.from_p2
                     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._rustmap
 
         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(
                 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,),
                 self._writedirstate,
                 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)