dirstate: add a function to update tracking status while "moving" parents

The `scmutil.dirstateparent` is moving the dirstate parent without touching the
working copy. It is used by history-rewriting operations like amending of
folding.

The function was directly doing the "low level" computation and dirstate
change.  All that logic belong to the dirstate and should be moved there.

For this purpose we introduce a new function that does just that and use it.

Differential Revision: https://phab.mercurial-scm.org/D11012

mercurial/dirstate.py

@@ -1,1448 +1,1497
 # 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
+
+
 @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_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)

mercurial/scmutil.py

@@ -1,2299 +1,2289
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import glob
 import os
 import posixpath
 import re
 import subprocess
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullrev,
     short,
     wdirrev,
 )
 from .pycompat import getattr
 from .thirdparty import attr
 from . import (
     copies as copiesmod,
     encoding,
     error,
     match as matchmod,
     obsolete,
     obsutil,
     pathutil,
     phases,
     policy,
     pycompat,
     requirements as requirementsmod,
     revsetlang,
     similar,
     smartset,
     url,
     util,
     vfs,
 )
 
 from .utils import (
     hashutil,
     procutil,
     stringutil,
 )
 
 if pycompat.iswindows:
     from . import scmwindows as scmplatform
 else:
     from . import scmposix as scmplatform
 
 parsers = policy.importmod('parsers')
 rustrevlog = policy.importrust('revlog')
 
 termsize = scmplatform.termsize
 
 
 @attr.s(slots=True, repr=False)
 class status(object):
     """Struct with a list of files per status.
 
     The 'deleted', 'unknown' and 'ignored' properties are only
     relevant to the working copy.
     """
 
     modified = attr.ib(default=attr.Factory(list))
     added = attr.ib(default=attr.Factory(list))
     removed = attr.ib(default=attr.Factory(list))
     deleted = attr.ib(default=attr.Factory(list))
     unknown = attr.ib(default=attr.Factory(list))
     ignored = attr.ib(default=attr.Factory(list))
     clean = attr.ib(default=attr.Factory(list))
 
     def __iter__(self):
         yield self.modified
         yield self.added
         yield self.removed
         yield self.deleted
         yield self.unknown
         yield self.ignored
         yield self.clean
 
     def __repr__(self):
         return (
             r'<status modified=%s, added=%s, removed=%s, deleted=%s, '
             r'unknown=%s, ignored=%s, clean=%s>'
         ) % tuple(pycompat.sysstr(stringutil.pprint(v)) for v in self)
 
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
 
     missing = set()
 
     for subpath in ctx2.substate:
         if subpath not in ctx1.substate:
             del subpaths[subpath]
             missing.add(subpath)
 
     for subpath, ctx in sorted(pycompat.iteritems(subpaths)):
         yield subpath, ctx.sub(subpath)
 
     # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,
     # status and diff will have an accurate result when it does
     # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared
     # against itself.
     for subpath in missing:
         yield subpath, ctx2.nullsub(subpath, ctx1)
 
 
 def nochangesfound(ui, repo, excluded=None):
     """Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     """
     secretlist = []
     if excluded:
         for n in excluded:
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(
             _(b"no changes found (ignored %d secret changesets)\n")
             % len(secretlist)
         )
     else:
         ui.status(_(b"no changes found\n"))
 
 
 def callcatch(ui, func):
     """call func() with global exception handling
 
     return func() if no exception happens. otherwise do some error handling
     and return an exit code accordingly. does not handle all exceptions.
     """
     coarse_exit_code = -1
     detailed_exit_code = -1
     try:
         try:
             return func()
         except:  # re-raises
             ui.traceback()
             raise
     # Global exception handling, alphabetically
     # Mercurial-specific first, followed by built-in and library exceptions
     except error.LockHeld as inst:
         detailed_exit_code = 20
         if inst.errno == errno.ETIMEDOUT:
             reason = _(b'timed out waiting for lock held by %r') % (
                 pycompat.bytestr(inst.locker)
             )
         else:
             reason = _(b'lock held by %r') % inst.locker
         ui.error(
             _(b"abort: %s: %s\n")
             % (inst.desc or stringutil.forcebytestr(inst.filename), reason)
         )
         if not inst.locker:
             ui.error(_(b"(lock might be very busy)\n"))
     except error.LockUnavailable as inst:
         detailed_exit_code = 20
         ui.error(
             _(b"abort: could not lock %s: %s\n")
             % (
                 inst.desc or stringutil.forcebytestr(inst.filename),
                 encoding.strtolocal(inst.strerror),
             )
         )
     except error.RepoError as inst:
         ui.error(_(b"abort: %s\n") % inst)
         if inst.hint:
             ui.error(_(b"(%s)\n") % inst.hint)
     except error.ResponseError as inst:
         ui.error(_(b"abort: %s") % inst.args[0])
         msg = inst.args[1]
         if isinstance(msg, type(u'')):
             msg = pycompat.sysbytes(msg)
         if msg is None:
             ui.error(b"\n")
         elif not isinstance(msg, bytes):
             ui.error(b" %r\n" % (msg,))
         elif not msg:
             ui.error(_(b" empty string\n"))
         else:
             ui.error(b"\n%r\n" % pycompat.bytestr(stringutil.ellipsis(msg)))
     except error.CensoredNodeError as inst:
         ui.error(_(b"abort: file censored %s\n") % inst)
     except error.WdirUnsupported:
         ui.error(_(b"abort: working directory revision cannot be specified\n"))
     except error.Error as inst:
         if inst.detailed_exit_code is not None:
             detailed_exit_code = inst.detailed_exit_code
         if inst.coarse_exit_code is not None:
             coarse_exit_code = inst.coarse_exit_code
         ui.error(inst.format())
     except error.WorkerError as inst:
         # Don't print a message -- the worker already should have
         return inst.status_code
     except ImportError as inst:
         ui.error(_(b"abort: %s\n") % stringutil.forcebytestr(inst))
         m = stringutil.forcebytestr(inst).split()[-1]
         if m in b"mpatch bdiff".split():
             ui.error(_(b"(did you forget to compile extensions?)\n"))
         elif m in b"zlib".split():
             ui.error(_(b"(is your Python install correct?)\n"))
     except util.urlerr.httperror as inst:
         detailed_exit_code = 100
         ui.error(_(b"abort: %s\n") % stringutil.forcebytestr(inst))
     except util.urlerr.urlerror as inst:
         detailed_exit_code = 100
         try:  # usually it is in the form (errno, strerror)
             reason = inst.reason.args[1]
         except (AttributeError, IndexError):
             # it might be anything, for example a string
             reason = inst.reason
         if isinstance(reason, pycompat.unicode):
             # SSLError of Python 2.7.9 contains a unicode
             reason = encoding.unitolocal(reason)
         ui.error(_(b"abort: error: %s\n") % stringutil.forcebytestr(reason))
     except (IOError, OSError) as inst:
         if (
             util.safehasattr(inst, b"args")
             and inst.args
             and inst.args[0] == errno.EPIPE
         ):
             pass
         elif getattr(inst, "strerror", None):  # common IOError or OSError
             if getattr(inst, "filename", None) is not None:
                 ui.error(
                     _(b"abort: %s: '%s'\n")
                     % (
                         encoding.strtolocal(inst.strerror),
                         stringutil.forcebytestr(inst.filename),
                     )
                 )
             else:
                 ui.error(_(b"abort: %s\n") % encoding.strtolocal(inst.strerror))
         else:  # suspicious IOError
             raise
     except MemoryError:
         ui.error(_(b"abort: out of memory\n"))
     except SystemExit as inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         detailed_exit_code = 254
         coarse_exit_code = inst.code
 
     if ui.configbool(b'ui', b'detailed-exit-code'):
         return detailed_exit_code
     else:
         return coarse_exit_code
 
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in [b'tip', b'.', b'null']:
         raise error.InputError(_(b"the name '%s' is reserved") % lbl)
     for c in (b':', b'\0', b'\n', b'\r'):
         if c in lbl:
             raise error.InputError(
                 _(b"%r cannot be used in a name") % pycompat.bytestr(c)
             )
     try:
         int(lbl)
         raise error.InputError(_(b"cannot use an integer as a name"))
     except ValueError:
         pass
     if lbl.strip() != lbl:
         raise error.InputError(
             _(b"leading or trailing whitespace in name %r") % lbl
         )
 
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if b'\r' in f or b'\n' in f:
         raise error.InputError(
             _(b"'\\n' and '\\r' disallowed in filenames: %r")
             % pycompat.bytestr(f)
         )
 
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = b"%s: %s" % (msg, procutil.shellquote(f))
             if abort:
                 raise error.InputError(msg)
             ui.warn(_(b"warning: %s\n") % msg)
 
 
 def checkportabilityalert(ui):
     """check if the user's config requests nothing, a warning, or abort for
     non-portable filenames"""
     val = ui.config(b'ui', b'portablefilenames')
     lval = val.lower()
     bval = stringutil.parsebool(val)
     abort = pycompat.iswindows or lval == b'abort'
     warn = bval or lval == b'warn'
     if bval is None and not (warn or abort or lval == b'ignore'):
         raise error.ConfigError(
             _(b"ui.portablefilenames value is invalid ('%s')") % val
         )
     return abort, warn
 
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = b'\0'.join(dirstate)
         self._loweredfiles = set(encoding.lower(allfiles).split(b'\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _(b'possible case-folding collision for %s') % f
             if self._abort:
                 raise error.Abort(msg)
             self._ui.warn(_(b"warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 
 def filteredhash(repo, maxrev):
     """build hash of filtered revisions in the current repoview.
 
     Multiple caches perform up-to-date validation by checking that the
     tiprev and tipnode stored in the cache file match the current repository.
     However, this is not sufficient for validating repoviews because the set
     of revisions in the view may change without the repository tiprev and
     tipnode changing.
 
     This function hashes all the revs filtered from the view and returns
     that SHA-1 digest.
     """
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
     key = cl._filteredrevs_hashcache.get(maxrev)
     if not key:
         revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
         if revs:
             s = hashutil.sha1()
             for rev in revs:
                 s.update(b'%d;' % rev)
             key = s.digest()
             cl._filteredrevs_hashcache[maxrev] = key
     return key
 
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     """yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs"""
 
     def errhandler(err):
         if err.filename == path:
             raise err
 
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
 
         def adddir(dirlst, dirname):
             dirstat = os.stat(dirname)
             match = any(samestat(dirstat, lstdirstat) for lstdirstat in dirlst)
             if not match:
                 dirlst.append(dirstat)
             return not match
 
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if b'.hg' in dirs:
             yield root  # found a repository
             qroot = os.path.join(root, b'.hg', b'patches')
             if os.path.isdir(os.path.join(qroot, b'.hg')):
                 yield qroot  # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove(b'.hg')
             else:
                 dirs[:] = []  # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 
 def binnode(ctx):
     """Return binary node id for a given basectx"""
     node = ctx.node()
     if node is None:
         return ctx.repo().nodeconstants.wdirid
     return node
 
 
 def intrev(ctx):
     """Return integer for a given basectx that can be used in comparison or
     arithmetic operation"""
     rev = ctx.rev()
     if rev is None:
         return wdirrev
     return rev
 
 
 def formatchangeid(ctx):
     """Format changectx as '{rev}:{node|formatnode}', which is the default
     template provided by logcmdutil.changesettemplater"""
     repo = ctx.repo()
     return formatrevnode(repo.ui, intrev(ctx), binnode(ctx))
 
 
 def formatrevnode(ui, rev, node):
     """Format given revision and node depending on the current verbosity"""
     if ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     return b'%d:%s' % (rev, hexfunc(node))
 
 
 def resolvehexnodeidprefix(repo, prefix):
     if prefix.startswith(b'x'):
         prefix = prefix[1:]
     try:
         # Uses unfiltered repo because it's faster when prefix is ambiguous/
         # This matches the shortesthexnodeidprefix() function below.
         node = repo.unfiltered().changelog._partialmatch(prefix)
     except error.AmbiguousPrefixLookupError:
         revset = repo.ui.config(
             b'experimental', b'revisions.disambiguatewithin'
         )
         if revset:
             # Clear config to avoid infinite recursion
             configoverrides = {
                 (b'experimental', b'revisions.disambiguatewithin'): None
             }
             with repo.ui.configoverride(configoverrides):
                 revs = repo.anyrevs([revset], user=True)
                 matches = []
                 for rev in revs:
                     node = repo.changelog.node(rev)
                     if hex(node).startswith(prefix):
                         matches.append(node)
                 if len(matches) == 1:
                     return matches[0]
         raise
     if node is None:
         return
     repo.changelog.rev(node)  # make sure node isn't filtered
     return node
 
 
 def mayberevnum(repo, prefix):
     """Checks if the given prefix may be mistaken for a revision number"""
     try:
         i = int(prefix)
         # if we are a pure int, then starting with zero will not be
         # confused as a rev; or, obviously, if the int is larger
         # than the value of the tip rev. We still need to disambiguate if
         # prefix == '0', since that *is* a valid revnum.
         if (prefix != b'0' and prefix[0:1] == b'0') or i >= len(repo):
             return False
         return True
     except ValueError:
         return False
 
 
 def shortesthexnodeidprefix(repo, node, minlength=1, cache=None):
     """Find the shortest unambiguous prefix that matches hexnode.
 
     If "cache" is not None, it must be a dictionary that can be used for
     caching between calls to this method.
     """
     # _partialmatch() of filtered changelog could take O(len(repo)) time,
     # which would be unacceptably slow. so we look for hash collision in
     # unfiltered space, which means some hashes may be slightly longer.
 
     minlength = max(minlength, 1)
 
     def disambiguate(prefix):
         """Disambiguate against revnums."""
         if repo.ui.configbool(b'experimental', b'revisions.prefixhexnode'):
             if mayberevnum(repo, prefix):
                 return b'x' + prefix
             else:
                 return prefix
 
         hexnode = hex(node)
         for length in range(len(prefix), len(hexnode) + 1):
             prefix = hexnode[:length]
             if not mayberevnum(repo, prefix):
                 return prefix
 
     cl = repo.unfiltered().changelog
     revset = repo.ui.config(b'experimental', b'revisions.disambiguatewithin')
     if revset:
         revs = None
         if cache is not None:
             revs = cache.get(b'disambiguationrevset')
         if revs is None:
             revs = repo.anyrevs([revset], user=True)
             if cache is not None:
                 cache[b'disambiguationrevset'] = revs
         if cl.rev(node) in revs:
             hexnode = hex(node)
             nodetree = None
             if cache is not None:
                 nodetree = cache.get(b'disambiguationnodetree')
             if not nodetree:
                 if util.safehasattr(parsers, 'nodetree'):
                     # The CExt is the only implementation to provide a nodetree
                     # class so far.
                     index = cl.index
                     if util.safehasattr(index, 'get_cindex'):
                         # the rust wrapped need to give access to its internal index
                         index = index.get_cindex()
                     nodetree = parsers.nodetree(index, len(revs))
                     for r in revs:
                         nodetree.insert(r)
                     if cache is not None:
                         cache[b'disambiguationnodetree'] = nodetree
             if nodetree is not None:
                 length = max(nodetree.shortest(node), minlength)
                 prefix = hexnode[:length]
                 return disambiguate(prefix)
             for length in range(minlength, len(hexnode) + 1):
                 matches = []
                 prefix = hexnode[:length]
                 for rev in revs:
                     otherhexnode = repo[rev].hex()
                     if prefix == otherhexnode[:length]:
                         matches.append(otherhexnode)
                 if len(matches) == 1:
                     return disambiguate(prefix)
 
     try:
         return disambiguate(cl.shortest(node, minlength))
     except error.LookupError:
         raise error.RepoLookupError()
 
 
 def isrevsymbol(repo, symbol):
     """Checks if a symbol exists in the repo.
 
     See revsymbol() for details. Raises error.AmbiguousPrefixLookupError if the
     symbol is an ambiguous nodeid prefix.
     """
     try:
         revsymbol(repo, symbol)
         return True
     except error.RepoLookupError:
         return False
 
 
 def revsymbol(repo, symbol):
     """Returns a context given a single revision symbol (as string).
 
     This is similar to revsingle(), but accepts only a single revision symbol,
     i.e. things like ".", "tip", "1234", "deadbeef", "my-bookmark" work, but
     not "max(public())".
     """
     if not isinstance(symbol, bytes):
         msg = (
             b"symbol (%s of type %s) was not a string, did you mean "
             b"repo[symbol]?" % (symbol, type(symbol))
         )
         raise error.ProgrammingError(msg)
     try:
         if symbol in (b'.', b'tip', b'null'):
             return repo[symbol]
 
         try:
             r = int(symbol)
             if b'%d' % r != symbol:
                 raise ValueError
             l = len(repo.changelog)
             if r < 0:
                 r += l
             if r < 0 or r >= l and r != wdirrev:
                 raise ValueError
             return repo[r]
         except error.FilteredIndexError:
             raise
         except (ValueError, OverflowError, IndexError):
             pass
 
         if len(symbol) == 2 * repo.nodeconstants.nodelen:
             try:
                 node = bin(symbol)
                 rev = repo.changelog.rev(node)
                 return repo[rev]
             except error.FilteredLookupError:
                 raise
             except (TypeError, LookupError):
                 pass
 
         # look up bookmarks through the name interface
         try:
             node = repo.names.singlenode(repo, symbol)
             rev = repo.changelog.rev(node)
             return repo[rev]
         except KeyError:
             pass
 
         node = resolvehexnodeidprefix(repo, symbol)
         if node is not None:
             rev = repo.changelog.rev(node)
             return repo[rev]
 
         raise error.RepoLookupError(_(b"unknown revision '%s'") % symbol)
 
     except error.WdirUnsupported:
         return repo[None]
     except (
         error.FilteredIndexError,
         error.FilteredLookupError,
         error.FilteredRepoLookupError,
     ):
         raise _filterederror(repo, symbol)
 
 
 def _filterederror(repo, changeid):
     """build an exception to be raised about a filtered changeid
 
     This is extracted in a function to help extensions (eg: evolve) to
     experiment with various message variants."""
     if repo.filtername.startswith(b'visible'):
 
         # Check if the changeset is obsolete
         unfilteredrepo = repo.unfiltered()
         ctx = revsymbol(unfilteredrepo, changeid)
 
         # If the changeset is obsolete, enrich the message with the reason
         # that made this changeset not visible
         if ctx.obsolete():
             msg = obsutil._getfilteredreason(repo, changeid, ctx)
         else:
             msg = _(b"hidden revision '%s'") % changeid
 
         hint = _(b'use --hidden to access hidden revisions')
 
         return error.FilteredRepoLookupError(msg, hint=hint)
     msg = _(b"filtered revision '%s' (not in '%s' subset)")
     msg %= (changeid, repo.filtername)
     return error.FilteredRepoLookupError(msg)
 
 
 def revsingle(repo, revspec, default=b'.', localalias=None):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec], localalias=localalias)
     if not l:
         raise error.Abort(_(b'empty revision set'))
     return repo[l.last()]
 
 
 def _pairspec(revspec):
     tree = revsetlang.parse(revspec)
     return tree and tree[0] in (
         b'range',
         b'rangepre',
         b'rangepost',
         b'rangeall',
     )
 
 
 def revpair(repo, revs):
     if not revs:
         return repo[b'.'], repo[None]
 
     l = revrange(repo, revs)
 
     if not l:
         raise error.Abort(_(b'empty revision range'))
 
     first = l.first()
     second = l.last()
 
     if (
         first == second
         and len(revs) >= 2
         and not all(revrange(repo, [r]) for r in revs)
     ):
         raise error.Abort(_(b'empty revision on one side of range'))
 
     # if top-level is range expression, the result must always be a pair
     if first == second and len(revs) == 1 and not _pairspec(revs[0]):
         return repo[first], repo[None]
 
     return repo[first], repo[second]
 
 
 def revrange(repo, specs, localalias=None):
     """Execute 1 to many revsets and return the union.
 
     This is the preferred mechanism for executing revsets using user-specified
     config options, such as revset aliases.
 
     The revsets specified by ``specs`` will be executed via a chained ``OR``
     expression. If ``specs`` is empty, an empty result is returned.
 
     ``specs`` can contain integers, in which case they are assumed to be
     revision numbers.
 
     It is assumed the revsets are already formatted. If you have arguments
     that need to be expanded in the revset, call ``revsetlang.formatspec()``
     and pass the result as an element of ``specs``.
 
     Specifying a single revset is allowed.
 
     Returns a ``smartset.abstractsmartset`` which is a list-like interface over
     integer revisions.
     """
     allspecs = []
     for spec in specs:
         if isinstance(spec, int):
             spec = revsetlang.formatspec(b'%d', spec)
         allspecs.append(spec)
     return repo.anyrevs(allspecs, user=True, localalias=localalias)
 
 
 def increasingwindows(windowsize=8, sizelimit=512):
     while True:
         yield windowsize
         if windowsize < sizelimit:
             windowsize *= 2
 
 
 def walkchangerevs(repo, revs, makefilematcher, prepare):
     """Iterate over files and the revs in a "windowed" way.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order."""
 
     if not revs:
         return []
     change = repo.__getitem__
 
     def iterate():
         it = iter(revs)
         stopiteration = False
         for windowsize in increasingwindows():
             nrevs = []
             for i in pycompat.xrange(windowsize):
                 rev = next(it, None)
                 if rev is None:
                     stopiteration = True
                     break
                 nrevs.append(rev)
             for rev in sorted(nrevs):
                 ctx = change(rev)
                 prepare(ctx, makefilematcher(ctx))
             for rev in nrevs:
                 yield change(rev)
 
             if stopiteration:
                 break
 
     return iterate()
 
 
 def meaningfulparents(repo, ctx):
     """Return list of meaningful (or all if debug) parentrevs for rev.
 
     For merges (two non-nullrev revisions) both parents are meaningful.
     Otherwise the first parent revision is considered meaningful if it
     is not the preceding revision.
     """
     parents = ctx.parents()
     if len(parents) > 1:
         return parents
     if repo.ui.debugflag:
         return [parents[0], repo[nullrev]]
     if parents[0].rev() >= intrev(ctx) - 1:
         return []
     return parents
 
 
 def getuipathfn(repo, legacyrelativevalue=False, forcerelativevalue=None):
     """Return a function that produced paths for presenting to the user.
 
     The returned function takes a repo-relative path and produces a path
     that can be presented in the UI.
 
     Depending on the value of ui.relative-paths, either a repo-relative or
     cwd-relative path will be produced.
 
     legacyrelativevalue is the value to use if ui.relative-paths=legacy
 
     If forcerelativevalue is not None, then that value will be used regardless
     of what ui.relative-paths is set to.
     """
     if forcerelativevalue is not None:
         relative = forcerelativevalue
     else:
         config = repo.ui.config(b'ui', b'relative-paths')
         if config == b'legacy':
             relative = legacyrelativevalue
         else:
             relative = stringutil.parsebool(config)
             if relative is None:
                 raise error.ConfigError(
                     _(b"ui.relative-paths is not a boolean ('%s')") % config
                 )
 
     if relative:
         cwd = repo.getcwd()
         if cwd != b'':
             # this branch would work even if cwd == b'' (ie cwd = repo
             # root), but its generality makes the returned function slower
             pathto = repo.pathto
             return lambda f: pathto(f, cwd)
     if repo.ui.configbool(b'ui', b'slash'):
         return lambda f: f
     else:
         return util.localpath
 
 
 def subdiruipathfn(subpath, uipathfn):
     '''Create a new uipathfn that treats the file as relative to subpath.'''
     return lambda f: uipathfn(posixpath.join(subpath, f))
 
 
 def anypats(pats, opts):
     """Checks if any patterns, including --include and --exclude were given.
 
     Some commands (e.g. addremove) use this condition for deciding whether to
     print absolute or relative paths.
     """
     return bool(pats or opts.get(b'include') or opts.get(b'exclude'))
 
 
 def expandpats(pats):
     """Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh."""
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 
 def matchandpats(
     ctx, pats=(), opts=None, globbed=False, default=b'relpath', badfn=None
 ):
     """Return a matcher and the patterns that were used.
     The matcher will warn about bad matches, unless an alternate badfn callback
     is provided."""
     if opts is None:
         opts = {}
     if not globbed and default == b'relpath':
         pats = expandpats(pats or [])
 
     uipathfn = getuipathfn(ctx.repo(), legacyrelativevalue=True)
 
     def bad(f, msg):
         ctx.repo().ui.warn(b"%s: %s\n" % (uipathfn(f), msg))
 
     if badfn is None:
         badfn = bad
 
     m = ctx.match(
         pats,
         opts.get(b'include'),
         opts.get(b'exclude'),
         default,
         listsubrepos=opts.get(b'subrepos'),
         badfn=badfn,
     )
 
     if m.always():
         pats = []
     return m, pats
 
 
 def match(
     ctx, pats=(), opts=None, globbed=False, default=b'relpath', badfn=None
 ):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default, badfn=badfn)[0]
 
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always()
 
 
 def matchfiles(repo, files, badfn=None):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(files, badfn=badfn)
 
 
 def parsefollowlinespattern(repo, rev, pat, msg):
     """Return a file name from `pat` pattern suitable for usage in followlines
     logic.
     """
     if not matchmod.patkind(pat):
         return pathutil.canonpath(repo.root, repo.getcwd(), pat)
     else:
         ctx = repo[rev]
         m = matchmod.match(repo.root, repo.getcwd(), [pat], ctx=ctx)
         files = [f for f in ctx if m(f)]
         if len(files) != 1:
             raise error.ParseError(msg)
         return files[0]
 
 
 def getorigvfs(ui, repo):
     """return a vfs suitable to save 'orig' file
 
     return None if no special directory is configured"""
     origbackuppath = ui.config(b'ui', b'origbackuppath')
     if not origbackuppath:
         return None
     return vfs.vfs(repo.wvfs.join(origbackuppath))
 
 
 def backuppath(ui, repo, filepath):
     """customize where working copy backup files (.orig files) are created
 
     Fetch user defined path from config file: [ui] origbackuppath = <path>
     Fall back to default (filepath with .orig suffix) if not specified
 
     filepath is repo-relative
 
     Returns an absolute path
     """
     origvfs = getorigvfs(ui, repo)
     if origvfs is None:
         return repo.wjoin(filepath + b".orig")
 
     origbackupdir = origvfs.dirname(filepath)
     if not origvfs.isdir(origbackupdir) or origvfs.islink(origbackupdir):
         ui.note(_(b'creating directory: %s\n') % origvfs.join(origbackupdir))
 
         # Remove any files that conflict with the backup file's path
         for f in reversed(list(pathutil.finddirs(filepath))):
             if origvfs.isfileorlink(f):
                 ui.note(_(b'removing conflicting file: %s\n') % origvfs.join(f))
                 origvfs.unlink(f)
                 break
 
         origvfs.makedirs(origbackupdir)
 
     if origvfs.isdir(filepath) and not origvfs.islink(filepath):
         ui.note(
             _(b'removing conflicting directory: %s\n') % origvfs.join(filepath)
         )
         origvfs.rmtree(filepath, forcibly=True)
 
     return origvfs.join(filepath)
 
 
 class _containsnode(object):
     """proxy __contains__(node) to container.__contains__ which accepts revs"""
 
     def __init__(self, repo, revcontainer):
         self._torev = repo.changelog.rev
         self._revcontains = revcontainer.__contains__
 
     def __contains__(self, node):
         return self._revcontains(self._torev(node))
 
 
 def cleanupnodes(
     repo,
     replacements,
     operation,
     moves=None,
     metadata=None,
     fixphase=False,
     targetphase=None,
     backup=True,
 ):
     """do common cleanups when old nodes are replaced by new nodes
 
     That includes writing obsmarkers or stripping nodes, and moving bookmarks.
     (we might also want to move working directory parent in the future)
 
     By default, bookmark moves are calculated automatically from 'replacements',
     but 'moves' can be used to override that. Also, 'moves' may include
     additional bookmark moves that should not have associated obsmarkers.
 
     replacements is {oldnode: [newnode]} or a iterable of nodes if they do not
     have replacements. operation is a string, like "rebase".
 
     metadata is dictionary containing metadata to be stored in obsmarker if
     obsolescence is enabled.
     """
     assert fixphase or targetphase is None
     if not replacements and not moves:
         return
 
     # translate mapping's other forms
     if not util.safehasattr(replacements, b'items'):
         replacements = {(n,): () for n in replacements}
     else:
         # upgrading non tuple "source" to tuple ones for BC
         repls = {}
         for key, value in replacements.items():
             if not isinstance(key, tuple):
                 key = (key,)
             repls[key] = value
         replacements = repls
 
     # Unfiltered repo is needed since nodes in replacements might be hidden.
     unfi = repo.unfiltered()
 
     # Calculate bookmark movements
     if moves is None:
         moves = {}
         for oldnodes, newnodes in replacements.items():
             for oldnode in oldnodes:
                 if oldnode in moves:
                     continue
                 if len(newnodes) > 1:
                     # usually a split, take the one with biggest rev number
                     newnode = next(unfi.set(b'max(%ln)', newnodes)).node()
                 elif len(newnodes) == 0:
                     # move bookmark backwards
                     allreplaced = []
                     for rep in replacements:
                         allreplaced.extend(rep)
                     roots = list(
                         unfi.set(b'max((::%n) - %ln)', oldnode, allreplaced)
                     )
                     if roots:
                         newnode = roots[0].node()
                     else:
                         newnode = repo.nullid
                 else:
                     newnode = newnodes[0]
                 moves[oldnode] = newnode
 
     allnewnodes = [n for ns in replacements.values() for n in ns]
     toretract = {}
     toadvance = {}
     if fixphase:
         precursors = {}
         for oldnodes, newnodes in replacements.items():
             for oldnode in oldnodes:
                 for newnode in newnodes:
                     precursors.setdefault(newnode, []).append(oldnode)
 
         allnewnodes.sort(key=lambda n: unfi[n].rev())
         newphases = {}
 
         def phase(ctx):
             return newphases.get(ctx.node(), ctx.phase())
 
         for newnode in allnewnodes:
             ctx = unfi[newnode]
             parentphase = max(phase(p) for p in ctx.parents())
             if targetphase is None:
                 oldphase = max(
                     unfi[oldnode].phase() for oldnode in precursors[newnode]
                 )
                 newphase = max(oldphase, parentphase)
             else:
                 newphase = max(targetphase, parentphase)
             newphases[newnode] = newphase
             if newphase > ctx.phase():
                 toretract.setdefault(newphase, []).append(newnode)
             elif newphase < ctx.phase():
                 toadvance.setdefault(newphase, []).append(newnode)
 
     with repo.transaction(b'cleanup') as tr:
         # Move bookmarks
         bmarks = repo._bookmarks
         bmarkchanges = []
         for oldnode, newnode in moves.items():
             oldbmarks = repo.nodebookmarks(oldnode)
             if not oldbmarks:
                 continue
             from . import bookmarks  # avoid import cycle
 
             repo.ui.debug(
                 b'moving bookmarks %r from %s to %s\n'
                 % (
                     pycompat.rapply(pycompat.maybebytestr, oldbmarks),
                     hex(oldnode),
                     hex(newnode),
                 )
             )
             # Delete divergent bookmarks being parents of related newnodes
             deleterevs = repo.revs(
                 b'parents(roots(%ln & (::%n))) - parents(%n)',
                 allnewnodes,
                 newnode,
                 oldnode,
             )
             deletenodes = _containsnode(repo, deleterevs)
             for name in oldbmarks:
                 bmarkchanges.append((name, newnode))
                 for b in bookmarks.divergent2delete(repo, deletenodes, name):
                     bmarkchanges.append((b, None))
 
         if bmarkchanges:
             bmarks.applychanges(repo, tr, bmarkchanges)
 
         for phase, nodes in toretract.items():
             phases.retractboundary(repo, tr, phase, nodes)
         for phase, nodes in toadvance.items():
             phases.advanceboundary(repo, tr, phase, nodes)
 
         mayusearchived = repo.ui.config(b'experimental', b'cleanup-as-archived')
         # Obsolete or strip nodes
         if obsolete.isenabled(repo, obsolete.createmarkersopt):
             # If a node is already obsoleted, and we want to obsolete it
             # without a successor, skip that obssolete request since it's
             # unnecessary. That's the "if s or not isobs(n)" check below.
             # Also sort the node in topology order, that might be useful for
             # some obsstore logic.
             # NOTE: the sorting might belong to createmarkers.
             torev = unfi.changelog.rev
             sortfunc = lambda ns: torev(ns[0][0])
             rels = []
             for ns, s in sorted(replacements.items(), key=sortfunc):
                 rel = (tuple(unfi[n] for n in ns), tuple(unfi[m] for m in s))
                 rels.append(rel)
             if rels:
                 obsolete.createmarkers(
                     repo, rels, operation=operation, metadata=metadata
                 )
         elif phases.supportinternal(repo) and mayusearchived:
             # this assume we do not have "unstable" nodes above the cleaned ones
             allreplaced = set()
             for ns in replacements.keys():
                 allreplaced.update(ns)
             if backup:
                 from . import repair  # avoid import cycle
 
                 node = min(allreplaced, key=repo.changelog.rev)
                 repair.backupbundle(
                     repo, allreplaced, allreplaced, node, operation
                 )
             phases.retractboundary(repo, tr, phases.archived, allreplaced)
         else:
             from . import repair  # avoid import cycle
 
             tostrip = list(n for ns in replacements for n in ns)
             if tostrip:
                 repair.delayedstrip(
                     repo.ui, repo, tostrip, operation, backup=backup
                 )
 
 
 def addremove(repo, matcher, prefix, uipathfn, opts=None):
     if opts is None:
         opts = {}
     m = matcher
     dry_run = opts.get(b'dry_run')
     try:
         similarity = float(opts.get(b'similarity') or 0)
     except ValueError:
         raise error.Abort(_(b'similarity must be a number'))
     if similarity < 0 or similarity > 100:
         raise error.Abort(_(b'similarity must be between 0 and 100'))
     similarity /= 100.0
 
     ret = 0
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         if opts.get(b'subrepos') or m.exact(subpath) or any(submatch.files()):
             sub = wctx.sub(subpath)
             subprefix = repo.wvfs.reljoin(prefix, subpath)
             subuipathfn = subdiruipathfn(subpath, uipathfn)
             try:
                 if sub.addremove(submatch, subprefix, subuipathfn, opts):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(
                     _(b"skipping missing subrepository: %s\n")
                     % uipathfn(subpath)
                 )
 
     rejected = []
 
     def badfn(f, msg):
         if f in m.files():
             m.bad(f, msg)
         rejected.append(f)
 
     badmatch = matchmod.badmatch(m, badfn)
     added, unknown, deleted, removed, forgotten = _interestingfiles(
         repo, badmatch
     )
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _(b'adding %s\n') % uipathfn(abs)
                 label = b'ui.addremove.added'
             else:
                 status = _(b'removing %s\n') % uipathfn(abs)
                 label = b'ui.addremove.removed'
             repo.ui.status(status, label=label)
 
     renames = _findrenames(
         repo, m, added + unknown, removed + deleted, similarity, uipathfn
     )
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 
 def marktouched(repo, files, similarity=0.0):
     """Assert that files have somehow been operated upon. files are relative to
     the repo root."""
     m = matchfiles(repo, files, badfn=lambda x, y: rejected.append(x))
     rejected = []
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _(b'adding %s\n') % abs
             else:
                 status = _(b'removing %s\n') % abs
             repo.ui.status(status)
 
     # TODO: We should probably have the caller pass in uipathfn and apply it to
     # the messages above too. legacyrelativevalue=True is consistent with how
     # it used to work.
     uipathfn = getuipathfn(repo, legacyrelativevalue=True)
     renames = _findrenames(
         repo, m, added + unknown, removed + deleted, similarity, uipathfn
     )
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 
 def _interestingfiles(repo, matcher):
     """Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean."""
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root, cached=True)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     matcher = repo.narrowmatch(matcher, includeexact=True)
     walkresults = dirstate.walk(
         matcher,
         subrepos=sorted(ctx.substate),
         unknown=True,
         ignored=False,
         full=False,
     )
     for abs, st in pycompat.iteritems(walkresults):
         dstate = dirstate[abs]
         if dstate == b'?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != b'r' and not st:
             deleted.append(abs)
         elif dstate == b'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == b'r' and not st:
             removed.append(abs)
         elif dstate == b'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 
 def _findrenames(repo, matcher, added, removed, similarity, uipathfn):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(
             repo, added, removed, similarity
         ):
             if (
                 repo.ui.verbose
                 or not matcher.exact(old)
                 or not matcher.exact(new)
             ):
                 repo.ui.status(
                     _(
                         b'recording removal of %s as rename to %s '
                         b'(%d%% similar)\n'
                     )
                     % (uipathfn(old), uipathfn(new), score * 100)
                 )
             renames[new] = old
     return renames
 
 
 def _markchanges(repo, unknown, deleted, renames):
     """Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied."""
     wctx = repo[None]
     with repo.wlock():
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in pycompat.iteritems(renames):
             wctx.copy(old, new)
 
 
 def getrenamedfn(repo, endrev=None):
     if copiesmod.usechangesetcentricalgo(repo):
 
         def getrenamed(fn, rev):
             ctx = repo[rev]
             p1copies = ctx.p1copies()
             if fn in p1copies:
                 return p1copies[fn]
             p2copies = ctx.p2copies()
             if fn in p2copies:
                 return p2copies[fn]
             return None
 
         return getrenamed
 
     rcache = {}
     if endrev is None:
         endrev = len(repo)
 
     def getrenamed(fn, rev):
         """looks up all renames for a file (up to endrev) the first
         time the file is given. It indexes on the changerev and only
         parses the manifest if linkrev != changerev.
         Returns rename info for fn at changerev rev."""
         if fn not in rcache:
             rcache[fn] = {}
             fl = repo.file(fn)
             for i in fl:
                 lr = fl.linkrev(i)
                 renamed = fl.renamed(fl.node(i))
                 rcache[fn][lr] = renamed and renamed[0]
                 if lr >= endrev:
                     break
         if rev in rcache[fn]:
             return rcache[fn][rev]
 
         # If linkrev != rev (i.e. rev not found in rcache) fallback to
         # filectx logic.
         try:
             return repo[rev][fn].copysource()
         except error.LookupError:
             return None
 
     return getrenamed
 
 
 def getcopiesfn(repo, endrev=None):
     if copiesmod.usechangesetcentricalgo(repo):
 
         def copiesfn(ctx):
             if ctx.p2copies():
                 allcopies = ctx.p1copies().copy()
                 # There should be no overlap
                 allcopies.update(ctx.p2copies())
                 return sorted(allcopies.items())
             else:
                 return sorted(ctx.p1copies().items())
 
     else:
         getrenamed = getrenamedfn(repo, endrev)
 
         def copiesfn(ctx):
             copies = []
             for fn in ctx.files():
                 rename = getrenamed(fn, ctx.rev())
                 if rename:
                     copies.append((fn, rename))
             return copies
 
     return copiesfn
 
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc:  # copying back a copy?
         if repo.dirstate[dst] not in b'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == b'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(
                     _(
                         b"%s has not been committed yet, so no copy "
                         b"data will be stored for %s.\n"
                     )
                     % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd))
                 )
             if repo.dirstate[dst] in b'?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 
 def movedirstate(repo, newctx, match=None):
     """Move the dirstate to newctx and adjust it as necessary.
 
     A matcher can be provided as an optimization. It is probably a bug to pass
     a matcher that doesn't match all the differences between the parent of the
     working copy and newctx.
     """
     oldctx = repo[b'.']
     ds = repo.dirstate
     copies = dict(ds.copies())
     ds.setparents(newctx.node(), repo.nullid)
     s = newctx.status(oldctx, match=match)
+
     for f in s.modified:
-        if ds[f] == b'r':
-            # modified + removed -> removed
-            continue
-        ds.normallookup(f)
+        ds.update_file_reference(f, p1_tracked=True)
 
     for f in s.added:
-        if ds[f] == b'r':
-            # added + removed -> unknown
-            ds.drop(f)
-        elif ds[f] != b'a':
-            ds.add(f)
+        ds.update_file_reference(f, p1_tracked=False)
 
     for f in s.removed:
-        if ds[f] == b'a':
-            # removed + added -> normal
-            ds.normallookup(f)
-        elif ds[f] != b'r':
-            ds.remove(f)
+        ds.update_file_reference(f, p1_tracked=True)
 
     # Merge old parent and old working dir copies
     oldcopies = copiesmod.pathcopies(newctx, oldctx, match)
     oldcopies.update(copies)
     copies = {
         dst: oldcopies.get(src, src)
         for dst, src in pycompat.iteritems(oldcopies)
     }
     # Adjust the dirstate copies
     for dst, src in pycompat.iteritems(copies):
         if src not in newctx or dst in newctx or ds[dst] != b'a':
             src = None
         ds.copy(src, dst)
     repo._quick_access_changeid_invalidate()
 
 
 def filterrequirements(requirements):
     """filters the requirements into two sets:
 
     wcreq: requirements which should be written in .hg/requires
     storereq: which should be written in .hg/store/requires
 
     Returns (wcreq, storereq)
     """
     if requirementsmod.SHARESAFE_REQUIREMENT in requirements:
         wc, store = set(), set()
         for r in requirements:
             if r in requirementsmod.WORKING_DIR_REQUIREMENTS:
                 wc.add(r)
             else:
                 store.add(r)
         return wc, store
     return requirements, None
 
 
 def istreemanifest(repo):
     """returns whether the repository is using treemanifest or not"""
     return requirementsmod.TREEMANIFEST_REQUIREMENT in repo.requirements
 
 
 def writereporequirements(repo, requirements=None):
     """writes requirements for the repo
 
     Requirements are written to .hg/requires and .hg/store/requires based
     on whether share-safe mode is enabled and which requirements are wdir
     requirements and which are store requirements
     """
     if requirements:
         repo.requirements = requirements
     wcreq, storereq = filterrequirements(repo.requirements)
     if wcreq is not None:
         writerequires(repo.vfs, wcreq)
     if storereq is not None:
         writerequires(repo.svfs, storereq)
     elif repo.ui.configbool(b'format', b'usestore'):
         # only remove store requires if we are using store
         repo.svfs.tryunlink(b'requires')
 
 
 def writerequires(opener, requirements):
     with opener(b'requires', b'w', atomictemp=True) as fp:
         for r in sorted(requirements):
             fp.write(b"%s\n" % r)
 
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 
 class filecache(object):
     """A property like decorator that tracks files under .hg/ for updates.
 
     On first access, the files defined as arguments are stat()ed and the
     results cached. The decorated function is called. The results are stashed
     away in a ``_filecache`` dict on the object whose method is decorated.
 
     On subsequent access, the cached result is used as it is set to the
     instance dictionary.
 
     On external property set/delete operations, the caller must update the
     corresponding _filecache entry appropriately. Use __class__.<attr>.set()
     instead of directly setting <attr>.
 
     When using the property API, the cached data is always used if available.
     No stat() is performed to check if the file has changed.
 
     Others can muck about with the state of the ``_filecache`` dict. e.g. they
     can populate an entry before the property's getter is called. In this case,
     entries in ``_filecache`` will be used during property operations,
     if available. If the underlying file changes, it is up to external callers
     to reflect this by e.g. calling ``delattr(obj, attr)`` to remove the cached
     method result as well as possibly calling ``del obj._filecache[attr]`` to
     remove the ``filecacheentry``.
     """
 
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         raise NotImplementedError
 
     def __call__(self, func):
         self.func = func
         self.sname = func.__name__
         self.name = pycompat.sysbytes(self.sname)
         return self
 
     def __get__(self, obj, type=None):
         # if accessed on the class, return the descriptor itself.
         if obj is None:
             return self
 
         assert self.sname not in obj.__dict__
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.sname] = entry.obj
         return entry.obj
 
     # don't implement __set__(), which would make __dict__ lookup as slow as
     # function call.
 
     def set(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value  # update cached copy
         obj.__dict__[self.sname] = value  # update copy returned by obj.x
 
 
 def extdatasource(repo, source):
     """Gather a map of rev -> value dict from the specified source
 
     A source spec is treated as a URL, with a special case shell: type
     for parsing the output from a shell command.
 
     The data is parsed as a series of newline-separated records where
     each record is a revision specifier optionally followed by a space
     and a freeform string value. If the revision is known locally, it
     is converted to a rev, otherwise the record is skipped.
 
     Note that both key and value are treated as UTF-8 and converted to
     the local encoding. This allows uniformity between local and
     remote data sources.
     """
 
     spec = repo.ui.config(b"extdata", source)
     if not spec:
         raise error.Abort(_(b"unknown extdata source '%s'") % source)
 
     data = {}
     src = proc = None
     try:
         if spec.startswith(b"shell:"):
             # external commands should be run relative to the repo root
             cmd = spec[6:]
             proc = subprocess.Popen(
                 procutil.tonativestr(cmd),
                 shell=True,
                 bufsize=-1,
                 close_fds=procutil.closefds,
                 stdout=subprocess.PIPE,
                 cwd=procutil.tonativestr(repo.root),
             )
             src = proc.stdout
         else:
             # treat as a URL or file
             src = url.open(repo.ui, spec)
         for l in src:
             if b" " in l:
                 k, v = l.strip().split(b" ", 1)
             else:
                 k, v = l.strip(), b""
 
             k = encoding.tolocal(k)
             try:
                 data[revsingle(repo, k).rev()] = encoding.tolocal(v)
             except (error.LookupError, error.RepoLookupError, error.InputError):
                 pass  # we ignore data for nodes that don't exist locally
     finally:
         if proc:
             try:
                 proc.communicate()
             except ValueError:
                 # This happens if we started iterating src and then
                 # get a parse error on a line. It should be safe to ignore.
                 pass
         if src:
             src.close()
     if proc and proc.returncode != 0:
         raise error.Abort(
             _(b"extdata command '%s' failed: %s")
             % (cmd, procutil.explainexit(proc.returncode))
         )
 
     return data
 
 
 class progress(object):
     def __init__(self, ui, updatebar, topic, unit=b"", total=None):
         self.ui = ui
         self.pos = 0
         self.topic = topic
         self.unit = unit
         self.total = total
         self.debug = ui.configbool(b'progress', b'debug')
         self._updatebar = updatebar
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         self.complete()
 
     def update(self, pos, item=b"", total=None):
         assert pos is not None
         if total:
             self.total = total
         self.pos = pos
         self._updatebar(self.topic, self.pos, item, self.unit, self.total)
         if self.debug:
             self._printdebug(item)
 
     def increment(self, step=1, item=b"", total=None):
         self.update(self.pos + step, item, total)
 
     def complete(self):
         self.pos = None
         self.unit = b""
         self.total = None
         self._updatebar(self.topic, self.pos, b"", self.unit, self.total)
 
     def _printdebug(self, item):
         unit = b''
         if self.unit:
             unit = b' ' + self.unit
         if item:
             item = b' ' + item
 
         if self.total:
             pct = 100.0 * self.pos / self.total
             self.ui.debug(
                 b'%s:%s %d/%d%s (%4.2f%%)\n'
                 % (self.topic, item, self.pos, self.total, unit, pct)
             )
         else:
             self.ui.debug(b'%s:%s %d%s\n' % (self.topic, item, self.pos, unit))
 
 
 def gdinitconfig(ui):
     """helper function to know if a repo should be created as general delta"""
     # experimental config: format.generaldelta
     return ui.configbool(b'format', b'generaldelta') or ui.configbool(
         b'format', b'usegeneraldelta'
     )
 
 
 def gddeltaconfig(ui):
     """helper function to know if incoming delta should be optimised"""
     # experimental config: format.generaldelta
     return ui.configbool(b'format', b'generaldelta')
 
 
 class simplekeyvaluefile(object):
     """A simple file with key=value lines
 
     Keys must be alphanumerics and start with a letter, values must not
     contain '\n' characters"""
 
     firstlinekey = b'__firstline'
 
     def __init__(self, vfs, path, keys=None):
         self.vfs = vfs
         self.path = path
 
     def read(self, firstlinenonkeyval=False):
         """Read the contents of a simple key-value file
 
         'firstlinenonkeyval' indicates whether the first line of file should
         be treated as a key-value pair or reuturned fully under the
         __firstline key."""
         lines = self.vfs.readlines(self.path)
         d = {}
         if firstlinenonkeyval:
             if not lines:
                 e = _(b"empty simplekeyvalue file")
                 raise error.CorruptedState(e)
             # we don't want to include '\n' in the __firstline
             d[self.firstlinekey] = lines[0][:-1]
             del lines[0]
 
         try:
             # the 'if line.strip()' part prevents us from failing on empty
             # lines which only contain '\n' therefore are not skipped
             # by 'if line'
             updatedict = dict(
                 line[:-1].split(b'=', 1) for line in lines if line.strip()
             )
             if self.firstlinekey in updatedict:
                 e = _(b"%r can't be used as a key")
                 raise error.CorruptedState(e % self.firstlinekey)
             d.update(updatedict)
         except ValueError as e:
             raise error.CorruptedState(stringutil.forcebytestr(e))
         return d
 
     def write(self, data, firstline=None):
         """Write key=>value mapping to a file
         data is a dict. Keys must be alphanumerical and start with a letter.
         Values must not contain newline characters.
 
         If 'firstline' is not None, it is written to file before
         everything else, as it is, not in a key=value form"""
         lines = []
         if firstline is not None:
             lines.append(b'%s\n' % firstline)
 
         for k, v in data.items():
             if k == self.firstlinekey:
                 e = b"key name '%s' is reserved" % self.firstlinekey
                 raise error.ProgrammingError(e)
             if not k[0:1].isalpha():
                 e = b"keys must start with a letter in a key-value file"
                 raise error.ProgrammingError(e)
             if not k.isalnum():
                 e = b"invalid key name in a simple key-value file"
                 raise error.ProgrammingError(e)
             if b'\n' in v:
                 e = b"invalid value in a simple key-value file"
                 raise error.ProgrammingError(e)
             lines.append(b"%s=%s\n" % (k, v))
         with self.vfs(self.path, mode=b'wb', atomictemp=True) as fp:
             fp.write(b''.join(lines))
 
 
 _reportobsoletedsource = [
     b'debugobsolete',
     b'pull',
     b'push',
     b'serve',
     b'unbundle',
 ]
 
 _reportnewcssource = [
     b'pull',
     b'unbundle',
 ]
 
 
 def prefetchfiles(repo, revmatches):
     """Invokes the registered file prefetch functions, allowing extensions to
     ensure the corresponding files are available locally, before the command
     uses them.
 
     Args:
       revmatches: a list of (revision, match) tuples to indicate the files to
       fetch at each revision. If any of the match elements is None, it matches
       all files.
     """
 
     def _matcher(m):
         if m:
             assert isinstance(m, matchmod.basematcher)
             # The command itself will complain about files that don't exist, so
             # don't duplicate the message.
             return matchmod.badmatch(m, lambda fn, msg: None)
         else:
             return matchall(repo)
 
     revbadmatches = [(rev, _matcher(match)) for (rev, match) in revmatches]
 
     fileprefetchhooks(repo, revbadmatches)
 
 
 # a list of (repo, revs, match) prefetch functions
 fileprefetchhooks = util.hooks()
 
 # A marker that tells the evolve extension to suppress its own reporting
 _reportstroubledchangesets = True
 
 
 def registersummarycallback(repo, otr, txnname=b'', as_validator=False):
     """register a callback to issue a summary after the transaction is closed
 
     If as_validator is true, then the callbacks are registered as transaction
     validators instead
     """
 
     def txmatch(sources):
         return any(txnname.startswith(source) for source in sources)
 
     categories = []
 
     def reportsummary(func):
         """decorator for report callbacks."""
         # The repoview life cycle is shorter than the one of the actual
         # underlying repository. So the filtered object can die before the
         # weakref is used leading to troubles. We keep a reference to the
         # unfiltered object and restore the filtering when retrieving the
         # repository through the weakref.
         filtername = repo.filtername
         reporef = weakref.ref(repo.unfiltered())
 
         def wrapped(tr):
             repo = reporef()
             if filtername:
                 assert repo is not None  # help pytype
                 repo = repo.filtered(filtername)
             func(repo, tr)
 
         newcat = b'%02i-txnreport' % len(categories)
         if as_validator:
             otr.addvalidator(newcat, wrapped)
         else:
             otr.addpostclose(newcat, wrapped)
         categories.append(newcat)
         return wrapped
 
     @reportsummary
     def reportchangegroup(repo, tr):
         cgchangesets = tr.changes.get(b'changegroup-count-changesets', 0)
         cgrevisions = tr.changes.get(b'changegroup-count-revisions', 0)
         cgfiles = tr.changes.get(b'changegroup-count-files', 0)
         cgheads = tr.changes.get(b'changegroup-count-heads', 0)
         if cgchangesets or cgrevisions or cgfiles:
             htext = b""
             if cgheads:
                 htext = _(b" (%+d heads)") % cgheads
             msg = _(b"added %d changesets with %d changes to %d files%s\n")
             if as_validator:
                 msg = _(b"adding %d changesets with %d changes to %d files%s\n")
             assert repo is not None  # help pytype
             repo.ui.status(msg % (cgchangesets, cgrevisions, cgfiles, htext))
 
     if txmatch(_reportobsoletedsource):
 
         @reportsummary
         def reportobsoleted(repo, tr):
             obsoleted = obsutil.getobsoleted(repo, tr)
             newmarkers = len(tr.changes.get(b'obsmarkers', ()))
             if newmarkers:
                 repo.ui.status(_(b'%i new obsolescence markers\n') % newmarkers)
             if obsoleted:
                 msg = _(b'obsoleted %i changesets\n')
                 if as_validator:
                     msg = _(b'obsoleting %i changesets\n')
                 repo.ui.status(msg % len(obsoleted))
 
     if obsolete.isenabled(
         repo, obsolete.createmarkersopt
     ) and repo.ui.configbool(
         b'experimental', b'evolution.report-instabilities'
     ):
         instabilitytypes = [
             (b'orphan', b'orphan'),
             (b'phase-divergent', b'phasedivergent'),
             (b'content-divergent', b'contentdivergent'),
         ]
 
         def getinstabilitycounts(repo):
             filtered = repo.changelog.filteredrevs
             counts = {}
             for instability, revset in instabilitytypes:
                 counts[instability] = len(
                     set(obsolete.getrevs(repo, revset)) - filtered
                 )
             return counts
 
         oldinstabilitycounts = getinstabilitycounts(repo)
 
         @reportsummary
         def reportnewinstabilities(repo, tr):
             newinstabilitycounts = getinstabilitycounts(repo)
             for instability, revset in instabilitytypes:
                 delta = (
                     newinstabilitycounts[instability]
                     - oldinstabilitycounts[instability]
                 )
                 msg = getinstabilitymessage(delta, instability)
                 if msg:
                     repo.ui.warn(msg)
 
     if txmatch(_reportnewcssource):
 
         @reportsummary
         def reportnewcs(repo, tr):
             """Report the range of new revisions pulled/unbundled."""
             origrepolen = tr.changes.get(b'origrepolen', len(repo))
             unfi = repo.unfiltered()
             if origrepolen >= len(unfi):
                 return
 
             # Compute the bounds of new visible revisions' range.
             revs = smartset.spanset(repo, start=origrepolen)
             if revs:
                 minrev, maxrev = repo[revs.min()], repo[revs.max()]
 
                 if minrev == maxrev:
                     revrange = minrev
                 else:
                     revrange = b'%s:%s' % (minrev, maxrev)
                 draft = len(repo.revs(b'%ld and draft()', revs))
                 secret = len(repo.revs(b'%ld and secret()', revs))
                 if not (draft or secret):
                     msg = _(b'new changesets %s\n') % revrange
                 elif draft and secret:
                     msg = _(b'new changesets %s (%d drafts, %d secrets)\n')
                     msg %= (revrange, draft, secret)
                 elif draft:
                     msg = _(b'new changesets %s (%d drafts)\n')
                     msg %= (revrange, draft)
                 elif secret:
                     msg = _(b'new changesets %s (%d secrets)\n')
                     msg %= (revrange, secret)
                 else:
                     errormsg = b'entered unreachable condition'
                     raise error.ProgrammingError(errormsg)
                 repo.ui.status(msg)
 
             # search new changesets directly pulled as obsolete
             duplicates = tr.changes.get(b'revduplicates', ())
             obsadded = unfi.revs(
                 b'(%d: + %ld) and obsolete()', origrepolen, duplicates
             )
             cl = repo.changelog
             extinctadded = [r for r in obsadded if r not in cl]
             if extinctadded:
                 # They are not just obsolete, but obsolete and invisible
                 # we call them "extinct" internally but the terms have not been
                 # exposed to users.
                 msg = b'(%d other changesets obsolete on arrival)\n'
                 repo.ui.status(msg % len(extinctadded))
 
         @reportsummary
         def reportphasechanges(repo, tr):
             """Report statistics of phase changes for changesets pre-existing
             pull/unbundle.
             """
             origrepolen = tr.changes.get(b'origrepolen', len(repo))
             published = []
             for revs, (old, new) in tr.changes.get(b'phases', []):
                 if new != phases.public:
                     continue
                 published.extend(rev for rev in revs if rev < origrepolen)
             if not published:
                 return
             msg = _(b'%d local changesets published\n')
             if as_validator:
                 msg = _(b'%d local changesets will be published\n')
             repo.ui.status(msg % len(published))
 
 
 def getinstabilitymessage(delta, instability):
     """function to return the message to show warning about new instabilities
 
     exists as a separate function so that extension can wrap to show more
     information like how to fix instabilities"""
     if delta > 0:
         return _(b'%i new %s changesets\n') % (delta, instability)
 
 
 def nodesummaries(repo, nodes, maxnumnodes=4):
     if len(nodes) <= maxnumnodes or repo.ui.verbose:
         return b' '.join(short(h) for h in nodes)
     first = b' '.join(short(h) for h in nodes[:maxnumnodes])
     return _(b"%s and %d others") % (first, len(nodes) - maxnumnodes)
 
 
 def enforcesinglehead(repo, tr, desc, accountclosed, filtername):
     """check that no named branch has multiple heads"""
     if desc in (b'strip', b'repair'):
         # skip the logic during strip
         return
     visible = repo.filtered(filtername)
     # possible improvement: we could restrict the check to affected branch
     bm = visible.branchmap()
     for name in bm:
         heads = bm.branchheads(name, closed=accountclosed)
         if len(heads) > 1:
             msg = _(b'rejecting multiple heads on branch "%s"')
             msg %= name
             hint = _(b'%d heads: %s')
             hint %= (len(heads), nodesummaries(repo, heads))
             raise error.Abort(msg, hint=hint)
 
 
 def wrapconvertsink(sink):
     """Allow extensions to wrap the sink returned by convcmd.convertsink()
     before it is used, whether or not the convert extension was formally loaded.
     """
     return sink
 
 
 def unhidehashlikerevs(repo, specs, hiddentype):
     """parse the user specs and unhide changesets whose hash or revision number
     is passed.
 
     hiddentype can be: 1) 'warn': warn while unhiding changesets
                        2) 'nowarn': don't warn while unhiding changesets
 
     returns a repo object with the required changesets unhidden
     """
     if not repo.filtername or not repo.ui.configbool(
         b'experimental', b'directaccess'
     ):
         return repo
 
     if repo.filtername not in (b'visible', b'visible-hidden'):
         return repo
 
     symbols = set()
     for spec in specs:
         try:
             tree = revsetlang.parse(spec)
         except error.ParseError:  # will be reported by scmutil.revrange()
             continue
 
         symbols.update(revsetlang.gethashlikesymbols(tree))
 
     if not symbols:
         return repo
 
     revs = _getrevsfromsymbols(repo, symbols)
 
     if not revs:
         return repo
 
     if hiddentype == b'warn':
         unfi = repo.unfiltered()
         revstr = b", ".join([pycompat.bytestr(unfi[l]) for l in revs])
         repo.ui.warn(
             _(
                 b"warning: accessing hidden changesets for write "
                 b"operation: %s\n"
             )
             % revstr
         )
 
     # we have to use new filtername to separate branch/tags cache until we can
     # disbale these cache when revisions are dynamically pinned.
     return repo.filtered(b'visible-hidden', revs)
 
 
 def _getrevsfromsymbols(repo, symbols):
     """parse the list of symbols and returns a set of revision numbers of hidden
     changesets present in symbols"""
     revs = set()
     unfi = repo.unfiltered()
     unficl = unfi.changelog
     cl = repo.changelog
     tiprev = len(unficl)
     allowrevnums = repo.ui.configbool(b'experimental', b'directaccess.revnums')
     for s in symbols:
         try:
             n = int(s)
             if n <= tiprev:
                 if not allowrevnums:
                     continue
                 else:
                     if n not in cl:
                         revs.add(n)
                     continue
         except ValueError:
             pass
 
         try:
             s = resolvehexnodeidprefix(unfi, s)
         except (error.LookupError, error.WdirUnsupported):
             s = None
 
         if s is not None:
             rev = unficl.rev(s)
             if rev not in cl:
                 revs.add(rev)
 
     return revs
 
 
 def bookmarkrevs(repo, mark):
     """Select revisions reachable by a given bookmark
 
     If the bookmarked revision isn't a head, an empty set will be returned.
     """
     return repo.revs(format_bookmark_revspec(mark))
 
 
 def format_bookmark_revspec(mark):
     """Build a revset expression to select revisions reachable by a given
     bookmark"""
     mark = b'literal:' + mark
     return revsetlang.formatspec(
         b"ancestors(bookmark(%s)) - "
         b"ancestors(head() and not bookmark(%s)) - "
         b"ancestors(bookmark() and not bookmark(%s))",
         mark,
         mark,
         mark,
     )