branching: merge stable into default

mercurial/dispatch.py

@@ -1,1372 +1,1372 b''
 # dispatch.py - command dispatching 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.
 
 
 import errno
 import getopt
 import io
 import os
 import pdb
 import re
 import signal
 import sys
 import traceback
 
 
 from .i18n import _
 from .pycompat import getattr
 
 from hgdemandimport import tracing
 
 from . import (
     cmdutil,
     color,
     commands,
     demandimport,
     encoding,
     error,
     extensions,
     fancyopts,
     help,
     hg,
     hook,
     localrepo,
     profiling,
     pycompat,
     rcutil,
     registrar,
     requirements as requirementsmod,
     scmutil,
     ui as uimod,
     util,
     vfs,
 )
 
 from .utils import (
     procutil,
     stringutil,
     urlutil,
 )
 
 
 class request:
     def __init__(
         self,
         args,
         ui=None,
         repo=None,
         fin=None,
         fout=None,
         ferr=None,
         fmsg=None,
         prereposetups=None,
     ):
         self.args = args
         self.ui = ui
         self.repo = repo
 
         # input/output/error streams
         self.fin = fin
         self.fout = fout
         self.ferr = ferr
         # separate stream for status/error messages
         self.fmsg = fmsg
 
         # remember options pre-parsed by _earlyparseopts()
         self.earlyoptions = {}
 
         # reposetups which run before extensions, useful for chg to pre-fill
         # low-level repo state (for example, changelog) before extensions.
         self.prereposetups = prereposetups or []
 
         # store the parsed and canonical command
         self.canonical_command = None
 
     def _runexithandlers(self):
         exc = None
         handlers = self.ui._exithandlers
         try:
             while handlers:
                 func, args, kwargs = handlers.pop()
                 try:
                     func(*args, **kwargs)
                 except:  # re-raises below
                     if exc is None:
                         exc = sys.exc_info()[1]
                     self.ui.warnnoi18n(b'error in exit handlers:\n')
                     self.ui.traceback(force=True)
         finally:
             if exc is not None:
                 raise exc
 
 
 def _flushstdio(ui, err):
     status = None
     # In all cases we try to flush stdio streams.
     if util.safehasattr(ui, b'fout'):
         assert ui is not None  # help pytype
         assert ui.fout is not None  # help pytype
         try:
             ui.fout.flush()
         except IOError as e:
             err = e
             status = -1
 
     if util.safehasattr(ui, b'ferr'):
         assert ui is not None  # help pytype
         assert ui.ferr is not None  # help pytype
         try:
             if err is not None and err.errno != errno.EPIPE:
                 ui.ferr.write(
                     b'abort: %s\n' % encoding.strtolocal(err.strerror)
                 )
             ui.ferr.flush()
         # There's not much we can do about an I/O error here. So (possibly)
         # change the status code and move on.
         except IOError:
             status = -1
 
     return status
 
 
 def run():
     """run the command in sys.argv"""
     try:
         initstdio()
         with tracing.log('parse args into request'):
             req = request(pycompat.sysargv[1:])
 
         status = dispatch(req)
         _silencestdio()
     except KeyboardInterrupt:
         # Catch early/late KeyboardInterrupt as last ditch. Here nothing will
         # be printed to console to avoid another IOError/KeyboardInterrupt.
         status = -1
     sys.exit(status & 255)
 
 
 def initstdio():
     # stdio streams on Python 3 are io.TextIOWrapper instances proxying another
     # buffer. These streams will normalize \n to \r\n by default. Mercurial's
     # preferred mechanism for writing output (ui.write()) uses io.BufferedWriter
     # instances, which write to the underlying stdio file descriptor in binary
     # mode. ui.write() uses \n for line endings and no line ending normalization
     # is attempted through this interface. This "just works," even if the system
     # preferred line ending is not \n.
     #
     # But some parts of Mercurial (e.g. hooks) can still send data to sys.stdout
     # and sys.stderr. They will inherit the line ending normalization settings,
     # potentially causing e.g. \r\n to be emitted. Since emitting \n should
     # "just work," here we change the sys.* streams to disable line ending
     # normalization, ensuring compatibility with our ui type.
 
     if sys.stdout is not None:
         # write_through is new in Python 3.7.
         kwargs = {
             "newline": "\n",
             "line_buffering": sys.stdout.line_buffering,
         }
         if util.safehasattr(sys.stdout, "write_through"):
             # pytype: disable=attribute-error
             kwargs["write_through"] = sys.stdout.write_through
             # pytype: enable=attribute-error
         sys.stdout = io.TextIOWrapper(
             sys.stdout.buffer, sys.stdout.encoding, sys.stdout.errors, **kwargs
         )
 
     if sys.stderr is not None:
         kwargs = {
             "newline": "\n",
             "line_buffering": sys.stderr.line_buffering,
         }
         if util.safehasattr(sys.stderr, "write_through"):
             # pytype: disable=attribute-error
             kwargs["write_through"] = sys.stderr.write_through
             # pytype: enable=attribute-error
         sys.stderr = io.TextIOWrapper(
             sys.stderr.buffer, sys.stderr.encoding, sys.stderr.errors, **kwargs
         )
 
     if sys.stdin is not None:
         # No write_through on read-only stream.
         sys.stdin = io.TextIOWrapper(
             sys.stdin.buffer,
             sys.stdin.encoding,
             sys.stdin.errors,
             # None is universal newlines mode.
             newline=None,
             line_buffering=sys.stdin.line_buffering,
         )
 
 
 def _silencestdio():
     for fp in (sys.stdout, sys.stderr):
         if fp is None:
             continue
         # Check if the file is okay
         try:
             fp.flush()
             continue
         except IOError:
             pass
         # Otherwise mark it as closed to silence "Exception ignored in"
         # message emitted by the interpreter finalizer.
         try:
             fp.close()
         except IOError:
             pass
 
 
 def _formatargs(args):
     return b' '.join(procutil.shellquote(a) for a in args)
 
 
 def dispatch(req):
     """run the command specified in req.args; returns an integer status code"""
     err = None
     try:
         status = _rundispatch(req)
     except error.StdioError as e:
         err = e
         status = -1
 
     ret = _flushstdio(req.ui, err)
     if ret and not status:
         status = ret
     return status
 
 
 def _rundispatch(req):
     with tracing.log('dispatch._rundispatch'):
         if req.ferr:
             ferr = req.ferr
         elif req.ui:
             ferr = req.ui.ferr
         else:
             ferr = procutil.stderr
 
         try:
             if not req.ui:
                 req.ui = uimod.ui.load()
             req.earlyoptions.update(_earlyparseopts(req.ui, req.args))
             if req.earlyoptions[b'traceback']:
                 req.ui.setconfig(b'ui', b'traceback', b'on', b'--traceback')
 
             # set ui streams from the request
             if req.fin:
                 req.ui.fin = req.fin
             if req.fout:
                 req.ui.fout = req.fout
             if req.ferr:
                 req.ui.ferr = req.ferr
             if req.fmsg:
                 req.ui.fmsg = req.fmsg
         except error.Abort as inst:
             ferr.write(inst.format())
             return -1
 
-        msg = _formatargs(req.args)
+        formattedargs = _formatargs(req.args)
         starttime = util.timer()
         ret = 1  # default of Python exit code on unhandled exception
         try:
             ret = _runcatch(req) or 0
         except error.ProgrammingError as inst:
             req.ui.error(_(b'** ProgrammingError: %s\n') % inst)
             if inst.hint:
                 req.ui.error(_(b'** (%s)\n') % inst.hint)
             raise
         except KeyboardInterrupt as inst:
             try:
                 if isinstance(inst, error.SignalInterrupt):
                     msg = _(b"killed!\n")
                 else:
                     msg = _(b"interrupted!\n")
                 req.ui.error(msg)
             except error.SignalInterrupt:
                 # maybe pager would quit without consuming all the output, and
                 # SIGPIPE was raised. we cannot print anything in this case.
                 pass
             except IOError as inst:
                 if inst.errno != errno.EPIPE:
                     raise
             ret = -1
         finally:
             duration = util.timer() - starttime
             req.ui.flush()  # record blocked times
             if req.ui.logblockedtimes:
                 req.ui._blockedtimes[b'command_duration'] = duration * 1000
                 req.ui.log(
                     b'uiblocked',
                     b'ui blocked ms\n',
                     **pycompat.strkwargs(req.ui._blockedtimes)
                 )
             return_code = ret & 255
             req.ui.log(
                 b"commandfinish",
                 b"%s exited %d after %0.2f seconds\n",
-                msg,
+                formattedargs,
                 return_code,
                 duration,
                 return_code=return_code,
                 duration=duration,
                 canonical_command=req.canonical_command,
             )
             try:
                 req._runexithandlers()
             except:  # exiting, so no re-raises
                 ret = ret or -1
             # do flush again since ui.log() and exit handlers may write to ui
             req.ui.flush()
         return ret
 
 
 def _runcatch(req):
     with tracing.log('dispatch._runcatch'):
 
         def catchterm(*args):
             raise error.SignalInterrupt
 
         ui = req.ui
         try:
             for name in b'SIGBREAK', b'SIGHUP', b'SIGTERM':
                 num = getattr(signal, name, None)
                 if num:
                     signal.signal(num, catchterm)
         except ValueError:
             pass  # happens if called in a thread
 
         def _runcatchfunc():
             realcmd = None
             try:
                 cmdargs = fancyopts.fancyopts(
                     req.args[:], commands.globalopts, {}
                 )
                 cmd = cmdargs[0]
                 aliases, entry = cmdutil.findcmd(cmd, commands.table, False)
                 realcmd = aliases[0]
             except (
                 error.UnknownCommand,
                 error.AmbiguousCommand,
                 IndexError,
                 getopt.GetoptError,
             ):
                 # Don't handle this here. We know the command is
                 # invalid, but all we're worried about for now is that
                 # it's not a command that server operators expect to
                 # be safe to offer to users in a sandbox.
                 pass
             if realcmd == b'serve' and b'--stdio' in cmdargs:
                 # We want to constrain 'hg serve --stdio' instances pretty
                 # closely, as many shared-ssh access tools want to grant
                 # access to run *only* 'hg -R $repo serve --stdio'. We
                 # restrict to exactly that set of arguments, and prohibit
                 # any repo name that starts with '--' to prevent
                 # shenanigans wherein a user does something like pass
                 # --debugger or --config=ui.debugger=1 as a repo
                 # name. This used to actually run the debugger.
                 if (
                     len(req.args) != 4
                     or req.args[0] != b'-R'
                     or req.args[1].startswith(b'--')
                     or req.args[2] != b'serve'
                     or req.args[3] != b'--stdio'
                 ):
                     raise error.Abort(
                         _(b'potentially unsafe serve --stdio invocation: %s')
                         % (stringutil.pprint(req.args),)
                     )
 
             try:
                 debugger = b'pdb'
                 debugtrace = {b'pdb': pdb.set_trace}
                 debugmortem = {b'pdb': pdb.post_mortem}
 
                 # read --config before doing anything else
                 # (e.g. to change trust settings for reading .hg/hgrc)
                 cfgs = _parseconfig(req.ui, req.earlyoptions[b'config'])
 
                 if req.repo:
                     # copy configs that were passed on the cmdline (--config) to
                     # the repo ui
                     for sec, name, val in cfgs:
                         req.repo.ui.setconfig(
                             sec, name, val, source=b'--config'
                         )
 
                 # developer config: ui.debugger
                 debugger = ui.config(b"ui", b"debugger")
                 debugmod = pdb
                 if not debugger or ui.plain():
                     # if we are in HGPLAIN mode, then disable custom debugging
                     debugger = b'pdb'
                 elif req.earlyoptions[b'debugger']:
                     # This import can be slow for fancy debuggers, so only
                     # do it when absolutely necessary, i.e. when actual
                     # debugging has been requested
                     with demandimport.deactivated():
                         try:
                             debugmod = __import__(debugger)
                         except ImportError:
                             pass  # Leave debugmod = pdb
 
                 debugtrace[debugger] = debugmod.set_trace
                 debugmortem[debugger] = debugmod.post_mortem
 
                 # enter the debugger before command execution
                 if req.earlyoptions[b'debugger']:
                     ui.warn(
                         _(
                             b"entering debugger - "
                             b"type c to continue starting hg or h for help\n"
                         )
                     )
 
                     if (
                         debugger != b'pdb'
                         and debugtrace[debugger] == debugtrace[b'pdb']
                     ):
                         ui.warn(
                             _(
                                 b"%s debugger specified "
                                 b"but its module was not found\n"
                             )
                             % debugger
                         )
                     with demandimport.deactivated():
                         debugtrace[debugger]()
                 try:
                     return _dispatch(req)
                 finally:
                     ui.flush()
             except:  # re-raises
                 # enter the debugger when we hit an exception
                 if req.earlyoptions[b'debugger']:
                     traceback.print_exc()
                     debugmortem[debugger](sys.exc_info()[2])
                 raise
 
         return _callcatch(ui, _runcatchfunc)
 
 
 def _callcatch(ui, func):
     """like scmutil.callcatch but handles more high-level exceptions about
     config parsing and commands. besides, use handlecommandexception to handle
     uncaught exceptions.
     """
     detailed_exit_code = -1
     try:
         return scmutil.callcatch(ui, func)
     except error.AmbiguousCommand as inst:
         detailed_exit_code = 10
         ui.warn(
             _(b"hg: command '%s' is ambiguous:\n    %s\n")
             % (inst.prefix, b" ".join(inst.matches))
         )
     except error.CommandError as inst:
         detailed_exit_code = 10
         if inst.command:
             ui.pager(b'help')
             msgbytes = pycompat.bytestr(inst.message)
             ui.warn(_(b"hg %s: %s\n") % (inst.command, msgbytes))
             commands.help_(ui, inst.command, full=False, command=True)
         else:
             ui.warn(_(b"hg: %s\n") % inst.message)
             ui.warn(_(b"(use 'hg help -v' for a list of global options)\n"))
     except error.UnknownCommand as inst:
         detailed_exit_code = 10
         nocmdmsg = _(b"hg: unknown command '%s'\n") % inst.command
         try:
             # check if the command is in a disabled extension
             # (but don't check for extensions themselves)
             formatted = help.formattedhelp(
                 ui, commands, inst.command, unknowncmd=True
             )
             ui.warn(nocmdmsg)
             ui.write(formatted)
         except (error.UnknownCommand, error.Abort):
             suggested = False
             if inst.all_commands:
                 sim = error.getsimilar(inst.all_commands, inst.command)
                 if sim:
                     ui.warn(nocmdmsg)
                     ui.warn(b"(%s)\n" % error.similarity_hint(sim))
                     suggested = True
             if not suggested:
                 ui.warn(nocmdmsg)
                 ui.warn(_(b"(use 'hg help' for a list of commands)\n"))
     except IOError:
         raise
     except KeyboardInterrupt:
         raise
     except:  # probably re-raises
         if not handlecommandexception(ui):
             raise
 
     if ui.configbool(b'ui', b'detailed-exit-code'):
         return detailed_exit_code
     else:
         return -1
 
 
 def aliasargs(fn, givenargs):
     args = []
     # only care about alias 'args', ignore 'args' set by extensions.wrapfunction
     if not util.safehasattr(fn, b'_origfunc'):
         args = getattr(fn, 'args', args)
     if args:
         cmd = b' '.join(map(procutil.shellquote, args))
 
         nums = []
 
         def replacer(m):
             num = int(m.group(1)) - 1
             nums.append(num)
             if num < len(givenargs):
                 return givenargs[num]
             raise error.InputError(_(b'too few arguments for command alias'))
 
         cmd = re.sub(br'\$(\d+|\$)', replacer, cmd)
         givenargs = [x for i, x in enumerate(givenargs) if i not in nums]
         args = pycompat.shlexsplit(cmd)
     return args + givenargs
 
 
 def aliasinterpolate(name, args, cmd):
     """interpolate args into cmd for shell aliases
 
     This also handles $0, $@ and "$@".
     """
     # util.interpolate can't deal with "$@" (with quotes) because it's only
     # built to match prefix + patterns.
     replacemap = {b'$%d' % (i + 1): arg for i, arg in enumerate(args)}
     replacemap[b'$0'] = name
     replacemap[b'$$'] = b'$'
     replacemap[b'$@'] = b' '.join(args)
     # Typical Unix shells interpolate "$@" (with quotes) as all the positional
     # parameters, separated out into words. Emulate the same behavior here by
     # quoting the arguments individually. POSIX shells will then typically
     # tokenize each argument into exactly one word.
     replacemap[b'"$@"'] = b' '.join(procutil.shellquote(arg) for arg in args)
     # escape '\$' for regex
     regex = b'|'.join(replacemap.keys()).replace(b'$', br'\$')
     r = re.compile(regex)
     return r.sub(lambda x: replacemap[x.group()], cmd)
 
 
 class cmdalias:
     def __init__(self, ui, name, definition, cmdtable, source):
         self.name = self.cmd = name
         self.cmdname = b''
         self.definition = definition
         self.fn = None
         self.givenargs = []
         self.opts = []
         self.help = b''
         self.badalias = None
         self.unknowncmd = False
         self.source = source
 
         try:
             aliases, entry = cmdutil.findcmd(self.name, cmdtable)
             for alias, e in cmdtable.items():
                 if e is entry:
                     self.cmd = alias
                     break
             self.shadows = True
         except error.UnknownCommand:
             self.shadows = False
 
         if not self.definition:
             self.badalias = _(b"no definition for alias '%s'") % self.name
             return
 
         if self.definition.startswith(b'!'):
             shdef = self.definition[1:]
             self.shell = True
 
             def fn(ui, *args):
                 env = {b'HG_ARGS': b' '.join((self.name,) + args)}
 
                 def _checkvar(m):
                     if m.groups()[0] == b'$':
                         return m.group()
                     elif int(m.groups()[0]) <= len(args):
                         return m.group()
                     else:
                         ui.debug(
                             b"No argument found for substitution "
                             b"of %i variable in alias '%s' definition.\n"
                             % (int(m.groups()[0]), self.name)
                         )
                         return b''
 
                 cmd = re.sub(br'\$(\d+|\$)', _checkvar, shdef)
                 cmd = aliasinterpolate(self.name, args, cmd)
                 return ui.system(
                     cmd, environ=env, blockedtag=b'alias_%s' % self.name
                 )
 
             self.fn = fn
             self.alias = True
             self._populatehelp(ui, name, shdef, self.fn)
             return
 
         try:
             args = pycompat.shlexsplit(self.definition)
         except ValueError as inst:
             self.badalias = _(b"error in definition for alias '%s': %s") % (
                 self.name,
                 stringutil.forcebytestr(inst),
             )
             return
         earlyopts, args = _earlysplitopts(args)
         if earlyopts:
             self.badalias = _(
                 b"error in definition for alias '%s': %s may "
                 b"only be given on the command line"
             ) % (self.name, b'/'.join(pycompat.ziplist(*earlyopts)[0]))
             return
         self.cmdname = cmd = args.pop(0)
         self.givenargs = args
 
         try:
             tableentry = cmdutil.findcmd(cmd, cmdtable, False)[1]
             if len(tableentry) > 2:
                 self.fn, self.opts, cmdhelp = tableentry
             else:
                 self.fn, self.opts = tableentry
                 cmdhelp = None
 
             self.alias = True
             self._populatehelp(ui, name, cmd, self.fn, cmdhelp)
 
         except error.UnknownCommand:
             self.badalias = _(
                 b"alias '%s' resolves to unknown command '%s'"
             ) % (
                 self.name,
                 cmd,
             )
             self.unknowncmd = True
         except error.AmbiguousCommand:
             self.badalias = _(
                 b"alias '%s' resolves to ambiguous command '%s'"
             ) % (
                 self.name,
                 cmd,
             )
 
     def _populatehelp(self, ui, name, cmd, fn, defaulthelp=None):
         # confine strings to be passed to i18n.gettext()
         cfg = {}
         for k in (b'doc', b'help', b'category'):
             v = ui.config(b'alias', b'%s:%s' % (name, k), None)
             if v is None:
                 continue
             if not encoding.isasciistr(v):
                 self.badalias = _(
                     b"non-ASCII character in alias definition '%s:%s'"
                 ) % (name, k)
                 return
             cfg[k] = v
 
         self.help = cfg.get(b'help', defaulthelp or b'')
         if self.help and self.help.startswith(b"hg " + cmd):
             # drop prefix in old-style help lines so hg shows the alias
             self.help = self.help[4 + len(cmd) :]
 
         self.owndoc = b'doc' in cfg
         doc = cfg.get(b'doc', pycompat.getdoc(fn))
         if doc is not None:
             doc = pycompat.sysstr(doc)
         self.__doc__ = doc
 
         self.helpcategory = cfg.get(
             b'category', registrar.command.CATEGORY_NONE
         )
 
     @property
     def args(self):
         args = pycompat.maplist(util.expandpath, self.givenargs)
         return aliasargs(self.fn, args)
 
     def __getattr__(self, name):
         adefaults = {
             'norepo': True,
             'intents': set(),
             'optionalrepo': False,
             'inferrepo': False,
         }
         if name not in adefaults:
             raise AttributeError(name)
         if self.badalias or util.safehasattr(self, b'shell'):
             return adefaults[name]
         return getattr(self.fn, name)
 
     def __call__(self, ui, *args, **opts):
         if self.badalias:
             hint = None
             if self.unknowncmd:
                 try:
                     # check if the command is in a disabled extension
                     cmd, ext = extensions.disabledcmd(ui, self.cmdname)[:2]
                     hint = _(b"'%s' is provided by '%s' extension") % (cmd, ext)
                 except error.UnknownCommand:
                     pass
             raise error.ConfigError(self.badalias, hint=hint)
         if self.shadows:
             ui.debug(
                 b"alias '%s' shadows command '%s'\n" % (self.name, self.cmdname)
             )
 
         ui.log(
             b'commandalias',
             b"alias '%s' expands to '%s'\n",
             self.name,
             self.definition,
         )
         if util.safehasattr(self, b'shell'):
             return self.fn(ui, *args, **opts)
         else:
             try:
                 return util.checksignature(self.fn)(ui, *args, **opts)
             except error.SignatureError:
                 args = b' '.join([self.cmdname] + self.args)
                 ui.debug(b"alias '%s' expands to '%s'\n" % (self.name, args))
                 raise
 
 
 class lazyaliasentry:
     """like a typical command entry (func, opts, help), but is lazy"""
 
     def __init__(self, ui, name, definition, cmdtable, source):
         self.ui = ui
         self.name = name
         self.definition = definition
         self.cmdtable = cmdtable.copy()
         self.source = source
         self.alias = True
 
     @util.propertycache
     def _aliasdef(self):
         return cmdalias(
             self.ui, self.name, self.definition, self.cmdtable, self.source
         )
 
     def __getitem__(self, n):
         aliasdef = self._aliasdef
         if n == 0:
             return aliasdef
         elif n == 1:
             return aliasdef.opts
         elif n == 2:
             return aliasdef.help
         else:
             raise IndexError
 
     def __iter__(self):
         for i in range(3):
             yield self[i]
 
     def __len__(self):
         return 3
 
 
 def addaliases(ui, cmdtable):
     # aliases are processed after extensions have been loaded, so they
     # may use extension commands. Aliases can also use other alias definitions,
     # but only if they have been defined prior to the current definition.
     for alias, definition in ui.configitems(b'alias', ignoresub=True):
         try:
             if cmdtable[alias].definition == definition:
                 continue
         except (KeyError, AttributeError):
             # definition might not exist or it might not be a cmdalias
             pass
 
         source = ui.configsource(b'alias', alias)
         entry = lazyaliasentry(ui, alias, definition, cmdtable, source)
         cmdtable[alias] = entry
 
 
 def _parse(ui, args):
     options = {}
     cmdoptions = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError as inst:
         raise error.CommandError(None, stringutil.forcebytestr(inst))
 
     if args:
         cmd, args = args[0], args[1:]
         aliases, entry = cmdutil.findcmd(
             cmd, commands.table, ui.configbool(b"ui", b"strict")
         )
         cmd = aliases[0]
         args = aliasargs(entry[0], args)
         defaults = ui.config(b"defaults", cmd)
         if defaults:
             args = (
                 pycompat.maplist(util.expandpath, pycompat.shlexsplit(defaults))
                 + args
             )
         c = list(entry[1])
     else:
         cmd = None
         c = []
 
     # combine global options into local
     for o in commands.globalopts:
         c.append((o[0], o[1], options[o[1]], o[3]))
 
     try:
         args = fancyopts.fancyopts(args, c, cmdoptions, gnu=True)
     except getopt.GetoptError as inst:
         raise error.CommandError(cmd, stringutil.forcebytestr(inst))
 
     # separate global options back out
     for o in commands.globalopts:
         n = o[1]
         options[n] = cmdoptions[n]
         del cmdoptions[n]
 
     return (cmd, cmd and entry[0] or None, args, options, cmdoptions)
 
 
 def _parseconfig(ui, config):
     """parse the --config options from the command line"""
     configs = []
 
     for cfg in config:
         try:
             name, value = [cfgelem.strip() for cfgelem in cfg.split(b'=', 1)]
             section, name = name.split(b'.', 1)
             if not section or not name:
                 raise IndexError
             ui.setconfig(section, name, value, b'--config')
             configs.append((section, name, value))
         except (IndexError, ValueError):
             raise error.InputError(
                 _(
                     b'malformed --config option: %r '
                     b'(use --config section.name=value)'
                 )
                 % pycompat.bytestr(cfg)
             )
 
     return configs
 
 
 def _earlyparseopts(ui, args):
     options = {}
     fancyopts.fancyopts(
         args,
         commands.globalopts,
         options,
         gnu=not ui.plain(b'strictflags'),
         early=True,
         optaliases={b'repository': [b'repo']},
     )
     return options
 
 
 def _earlysplitopts(args):
     """Split args into a list of possible early options and remainder args"""
     shortoptions = b'R:'
     # TODO: perhaps 'debugger' should be included
     longoptions = [b'cwd=', b'repository=', b'repo=', b'config=']
     return fancyopts.earlygetopt(
         args, shortoptions, longoptions, gnu=True, keepsep=True
     )
 
 
 def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
     # run pre-hook, and abort if it fails
     hook.hook(
         lui,
         repo,
         b"pre-%s" % cmd,
         True,
         args=b" ".join(fullargs),
         pats=cmdpats,
         opts=cmdoptions,
     )
     try:
         ret = _runcommand(ui, options, cmd, d)
         # run post-hook, passing command result
         hook.hook(
             lui,
             repo,
             b"post-%s" % cmd,
             False,
             args=b" ".join(fullargs),
             result=ret,
             pats=cmdpats,
             opts=cmdoptions,
         )
     except Exception:
         # run failure hook and re-raise
         hook.hook(
             lui,
             repo,
             b"fail-%s" % cmd,
             False,
             args=b" ".join(fullargs),
             pats=cmdpats,
             opts=cmdoptions,
         )
         raise
     return ret
 
 
 def _readsharedsourceconfig(ui, path):
     """if the current repository is shared one, this tries to read
     .hg/hgrc of shared source if we are in share-safe mode
 
     Config read is loaded into the ui object passed
 
     This should be called before reading .hg/hgrc or the main repo
     as that overrides config set in shared source"""
     try:
         with open(os.path.join(path, b".hg", b"requires"), "rb") as fp:
             requirements = set(fp.read().splitlines())
             if not (
                 requirementsmod.SHARESAFE_REQUIREMENT in requirements
                 and requirementsmod.SHARED_REQUIREMENT in requirements
             ):
                 return
             hgvfs = vfs.vfs(os.path.join(path, b".hg"))
             sharedvfs = localrepo._getsharedvfs(hgvfs, requirements)
             root = sharedvfs.base
             ui.readconfig(sharedvfs.join(b"hgrc"), root)
     except IOError:
         pass
 
 
 def _getlocal(ui, rpath, wd=None):
     """Return (path, local ui object) for the given target path.
 
     Takes paths in [cwd]/.hg/hgrc into account."
     """
     if wd is None:
         try:
             wd = encoding.getcwd()
         except OSError as e:
             raise error.Abort(
                 _(b"error getting current working directory: %s")
                 % encoding.strtolocal(e.strerror)
             )
 
     path = cmdutil.findrepo(wd) or b""
     if not path:
         lui = ui
     else:
         lui = ui.copy()
         if rcutil.use_repo_hgrc():
             _readsharedsourceconfig(lui, path)
             lui.readconfig(os.path.join(path, b".hg", b"hgrc"), path)
             lui.readconfig(os.path.join(path, b".hg", b"hgrc-not-shared"), path)
 
     if rpath:
         path = urlutil.get_clone_path(lui, rpath)[0]
         lui = ui.copy()
         if rcutil.use_repo_hgrc():
             _readsharedsourceconfig(lui, path)
             lui.readconfig(os.path.join(path, b".hg", b"hgrc"), path)
             lui.readconfig(os.path.join(path, b".hg", b"hgrc-not-shared"), path)
 
     return path, lui
 
 
 def _checkshellalias(lui, ui, args):
     """Return the function to run the shell alias, if it is required"""
     options = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except getopt.GetoptError:
         return
 
     if not args:
         return
 
     cmdtable = commands.table
 
     cmd = args[0]
     try:
         strict = ui.configbool(b"ui", b"strict")
         aliases, entry = cmdutil.findcmd(cmd, cmdtable, strict)
     except (error.AmbiguousCommand, error.UnknownCommand):
         return
 
     cmd = aliases[0]
     fn = entry[0]
 
     if cmd and util.safehasattr(fn, b'shell'):
         # shell alias shouldn't receive early options which are consumed by hg
         _earlyopts, args = _earlysplitopts(args)
         d = lambda: fn(ui, *args[1:])
         return lambda: runcommand(
             lui, None, cmd, args[:1], ui, options, d, [], {}
         )
 
 
 def _dispatch(req):
     args = req.args
     ui = req.ui
 
     # check for cwd
     cwd = req.earlyoptions[b'cwd']
     if cwd:
         os.chdir(cwd)
 
     rpath = req.earlyoptions[b'repository']
     path, lui = _getlocal(ui, rpath)
 
     uis = {ui, lui}
 
     if req.repo:
         uis.add(req.repo.ui)
 
     if (
         req.earlyoptions[b'verbose']
         or req.earlyoptions[b'debug']
         or req.earlyoptions[b'quiet']
     ):
         for opt in (b'verbose', b'debug', b'quiet'):
             val = pycompat.bytestr(bool(req.earlyoptions[opt]))
             for ui_ in uis:
                 ui_.setconfig(b'ui', opt, val, b'--' + opt)
 
     if req.earlyoptions[b'profile']:
         for ui_ in uis:
             ui_.setconfig(b'profiling', b'enabled', b'true', b'--profile')
     elif req.earlyoptions[b'profile'] is False:
         # Check for it being set already, so that we don't pollute the config
         # with this when using chg in the very common case that it's not
         # enabled.
         if lui.configbool(b'profiling', b'enabled'):
             # Only do this on lui so that `chg foo` with a user config setting
             # profiling.enabled=1 still shows profiling information (chg will
             # specify `--no-profile` when `hg serve` is starting up, we don't
             # want that to propagate to every later invocation).
             lui.setconfig(b'profiling', b'enabled', b'false', b'--no-profile')
 
     profile = lui.configbool(b'profiling', b'enabled')
     with profiling.profile(lui, enabled=profile) as profiler:
         # Configure extensions in phases: uisetup, extsetup, cmdtable, and
         # reposetup
         extensions.loadall(lui)
         # Propagate any changes to lui.__class__ by extensions
         ui.__class__ = lui.__class__
 
         # (uisetup and extsetup are handled in extensions.loadall)
 
         # (reposetup is handled in hg.repository)
 
         addaliases(lui, commands.table)
 
         # All aliases and commands are completely defined, now.
         # Check abbreviation/ambiguity of shell alias.
         shellaliasfn = _checkshellalias(lui, ui, args)
         if shellaliasfn:
             # no additional configs will be set, set up the ui instances
             for ui_ in uis:
                 extensions.populateui(ui_)
             return shellaliasfn()
 
         # check for fallback encoding
         fallback = lui.config(b'ui', b'fallbackencoding')
         if fallback:
             encoding.fallbackencoding = fallback
 
         fullargs = args
         cmd, func, args, options, cmdoptions = _parse(lui, args)
 
         # store the canonical command name in request object for later access
         req.canonical_command = cmd
 
         if options[b"config"] != req.earlyoptions[b"config"]:
             raise error.InputError(_(b"option --config may not be abbreviated"))
         if options[b"cwd"] != req.earlyoptions[b"cwd"]:
             raise error.InputError(_(b"option --cwd may not be abbreviated"))
         if options[b"repository"] != req.earlyoptions[b"repository"]:
             raise error.InputError(
                 _(
                     b"option -R has to be separated from other options (e.g. not "
                     b"-qR) and --repository may only be abbreviated as --repo"
                 )
             )
         if options[b"debugger"] != req.earlyoptions[b"debugger"]:
             raise error.InputError(
                 _(b"option --debugger may not be abbreviated")
             )
         # don't validate --profile/--traceback, which can be enabled from now
 
         if options[b"encoding"]:
             encoding.encoding = options[b"encoding"]
         if options[b"encodingmode"]:
             encoding.encodingmode = options[b"encodingmode"]
         if options[b"time"]:
 
             def get_times():
                 t = os.times()
                 if t[4] == 0.0:
                     # Windows leaves this as zero, so use time.perf_counter()
                     t = (t[0], t[1], t[2], t[3], util.timer())
                 return t
 
             s = get_times()
 
             def print_time():
                 t = get_times()
                 ui.warn(
                     _(b"time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n")
                     % (
                         t[4] - s[4],
                         t[0] - s[0],
                         t[2] - s[2],
                         t[1] - s[1],
                         t[3] - s[3],
                     )
                 )
 
             ui.atexit(print_time)
         if options[b"profile"]:
             profiler.start()
 
         # if abbreviated version of this were used, take them in account, now
         if options[b'verbose'] or options[b'debug'] or options[b'quiet']:
             for opt in (b'verbose', b'debug', b'quiet'):
                 if options[opt] == req.earlyoptions[opt]:
                     continue
                 val = pycompat.bytestr(bool(options[opt]))
                 for ui_ in uis:
                     ui_.setconfig(b'ui', opt, val, b'--' + opt)
 
         if options[b'traceback']:
             for ui_ in uis:
                 ui_.setconfig(b'ui', b'traceback', b'on', b'--traceback')
 
         if options[b'noninteractive']:
             for ui_ in uis:
                 ui_.setconfig(b'ui', b'interactive', b'off', b'-y')
 
         if cmdoptions.get(b'insecure', False):
             for ui_ in uis:
                 ui_.insecureconnections = True
 
         # setup color handling before pager, because setting up pager
         # might cause incorrect console information
         coloropt = options[b'color']
         for ui_ in uis:
             if coloropt:
                 ui_.setconfig(b'ui', b'color', coloropt, b'--color')
             color.setup(ui_)
 
         if stringutil.parsebool(options[b'pager']):
             # ui.pager() expects 'internal-always-' prefix in this case
             ui.pager(b'internal-always-' + cmd)
         elif options[b'pager'] != b'auto':
             for ui_ in uis:
                 ui_.disablepager()
 
         # configs are fully loaded, set up the ui instances
         for ui_ in uis:
             extensions.populateui(ui_)
 
         if options[b'version']:
             return commands.version_(ui)
         if options[b'help']:
             return commands.help_(ui, cmd, command=cmd is not None)
         elif not cmd:
             return commands.help_(ui, b'shortlist')
 
         repo = None
         cmdpats = args[:]
         assert func is not None  # help out pytype
         if not func.norepo:
             # use the repo from the request only if we don't have -R
             if not rpath and not cwd:
                 repo = req.repo
 
             if repo:
                 # set the descriptors of the repo ui to those of ui
                 repo.ui.fin = ui.fin
                 repo.ui.fout = ui.fout
                 repo.ui.ferr = ui.ferr
                 repo.ui.fmsg = ui.fmsg
             else:
                 try:
                     repo = hg.repository(
                         ui,
                         path=path,
                         presetupfuncs=req.prereposetups,
                         intents=func.intents,
                     )
                     if not repo.local():
                         raise error.InputError(
                             _(b"repository '%s' is not local") % path
                         )
                     repo.ui.setconfig(
                         b"bundle", b"mainreporoot", repo.root, b'repo'
                     )
                 except error.RequirementError:
                     raise
                 except error.RepoError:
                     if rpath:  # invalid -R path
                         raise
                     if not func.optionalrepo:
                         if func.inferrepo and args and not path:
                             # try to infer -R from command args
                             repos = pycompat.maplist(cmdutil.findrepo, args)
                             guess = repos[0]
                             if guess and repos.count(guess) == len(repos):
                                 req.args = [b'--repository', guess] + fullargs
                                 req.earlyoptions[b'repository'] = guess
                                 return _dispatch(req)
                         if not path:
                             raise error.InputError(
                                 _(
                                     b"no repository found in"
                                     b" '%s' (.hg not found)"
                                 )
                                 % encoding.getcwd()
                             )
                         raise
             if repo:
                 ui = repo.ui
                 if options[b'hidden']:
                     repo = repo.unfiltered()
             args.insert(0, repo)
         elif rpath:
             ui.warn(_(b"warning: --repository ignored\n"))
 
         msg = _formatargs(fullargs)
         ui.log(b"command", b'%s\n', msg)
         strcmdopt = pycompat.strkwargs(cmdoptions)
         d = lambda: util.checksignature(func)(ui, *args, **strcmdopt)
         try:
             return runcommand(
                 lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions
             )
         finally:
             if repo and repo != req.repo:
                 repo.close()
 
 
 def _runcommand(ui, options, cmd, cmdfunc):
     """Run a command function, possibly with profiling enabled."""
     try:
         with tracing.log("Running %s command" % cmd):
             return cmdfunc()
     except error.SignatureError:
         raise error.CommandError(cmd, _(b'invalid arguments'))
 
 
 def _exceptionwarning(ui):
     """Produce a warning message for the current active exception"""
 
     # For compatibility checking, we discard the portion of the hg
     # version after the + on the assumption that if a "normal
     # user" is running a build with a + in it the packager
     # probably built from fairly close to a tag and anyone with a
     # 'make local' copy of hg (where the version number can be out
     # of date) will be clueful enough to notice the implausible
     # version number and try updating.
     ct = util.versiontuple(n=2)
     worst = None, ct, b'', b''
     if ui.config(b'ui', b'supportcontact') is None:
         for name, mod in extensions.extensions():
             # 'testedwith' should be bytes, but not all extensions are ported
             # to py3 and we don't want UnicodeException because of that.
             testedwith = stringutil.forcebytestr(
                 getattr(mod, 'testedwith', b'')
             )
             version = extensions.moduleversion(mod)
             report = getattr(mod, 'buglink', _(b'the extension author.'))
             if not testedwith.strip():
                 # We found an untested extension. It's likely the culprit.
                 worst = name, b'unknown', report, version
                 break
 
             # Never blame on extensions bundled with Mercurial.
             if extensions.ismoduleinternal(mod):
                 continue
 
             tested = [util.versiontuple(t, 2) for t in testedwith.split()]
             if ct in tested:
                 continue
 
             lower = [t for t in tested if t < ct]
             nearest = max(lower or tested)
             if worst[0] is None or nearest < worst[1]:
                 worst = name, nearest, report, version
     if worst[0] is not None:
         name, testedwith, report, version = worst
         if not isinstance(testedwith, (bytes, str)):
             testedwith = b'.'.join(
                 [stringutil.forcebytestr(c) for c in testedwith]
             )
         extver = version or _(b"(version N/A)")
         warning = _(
             b'** Unknown exception encountered with '
             b'possibly-broken third-party extension "%s" %s\n'
             b'** which supports versions %s of Mercurial.\n'
             b'** Please disable "%s" and try your action again.\n'
             b'** If that fixes the bug please report it to %s\n'
         ) % (name, extver, testedwith, name, stringutil.forcebytestr(report))
     else:
         bugtracker = ui.config(b'ui', b'supportcontact')
         if bugtracker is None:
             bugtracker = _(b"https://mercurial-scm.org/wiki/BugTracker")
         warning = (
             _(
                 b"** unknown exception encountered, "
                 b"please report by visiting\n** "
             )
             + bugtracker
             + b'\n'
         )
     sysversion = pycompat.sysbytes(sys.version).replace(b'\n', b'')
 
     def ext_with_ver(x):
         ext = x[0]
         ver = extensions.moduleversion(x[1])
         if ver:
             ext += b' ' + ver
         return ext
 
     warning += (
         (_(b"** Python %s\n") % sysversion)
         + (_(b"** Mercurial Distributed SCM (version %s)\n") % util.version())
         + (
             _(b"** Extensions loaded: %s\n")
             % b", ".join(
                 [ext_with_ver(x) for x in sorted(extensions.extensions())]
             )
         )
     )
     return warning
 
 
 def handlecommandexception(ui):
     """Produce a warning message for broken commands
 
     Called when handling an exception; the exception is reraised if
     this function returns False, ignored otherwise.
     """
     warning = _exceptionwarning(ui)
     ui.log(
         b"commandexception",
         b"%s\n%s\n",
         warning,
         pycompat.sysbytes(traceback.format_exc()),
     )
     ui.warn(warning)
     return False  # re-raise the exception

rust/Cargo.lock

@@ -1,1204 +1,1264 b''
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
 version = 3
 
 [[package]]
+name = "Inflector"
+version = "0.11.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fe438c63458706e03479442743baae6c88256498e6431708f6dfc520a26515d3"
+
+[[package]]
 name = "adler"
 version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ee2a4ec343196209d6594e19543ae87a39f96d5534d7174822a3ad825dd6ed7e"
 
 [[package]]
 name = "ahash"
 version = "0.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "739f4a8db6605981345c5654f3a85b056ce52f37a39d34da03f25bf2151ea16e"
 
 [[package]]
 name = "aho-corasick"
 version = "0.7.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e37cfd5e7657ada45f742d6e99ca5788580b5c529dc78faf11ece6dc702656f"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
+name = "aliasable"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "250f629c0161ad8107cf89319e990051fae62832fd343083bea452d93e2205fd"
+
+[[package]]
 name = "ansi_term"
 version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d52a9bb7ec0cf484c551830a7ce27bd20d67eac647e1befb56b0be4ee39a55d2"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "atty"
 version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
 dependencies = [
  "hermit-abi",
  "libc",
  "winapi",
 ]
 
 [[package]]
 name = "autocfg"
 version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cdb031dd78e28731d87d56cc8ffef4a8f36ca26c38fe2de700543e627f8a464a"
 
 [[package]]
 name = "bitflags"
 version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "bitmaps"
 version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "031043d04099746d8db04daf1fa424b2bc8bd69d92b25962dcde24da39ab64a2"
 dependencies = [
  "typenum",
 ]
 
 [[package]]
 name = "block-buffer"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4152116fd6e9dadb291ae18fc1ec3575ed6d84c29642d97890f4b4a3417297e4"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "block-buffer"
 version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0bf7fe51849ea569fd452f37822f606a5cabb684dc918707a0193fd4664ff324"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "byteorder"
 version = "1.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "bytes-cast"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0d434f9a4ecbe987e7ccfda7274b6f82ea52c9b63742565a65cb5e8ba0f2c452"
 dependencies = [
  "bytes-cast-derive",
 ]
 
 [[package]]
 name = "bytes-cast-derive"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cb936af9de38476664d6b58e529aff30d482e4ce1c5e150293d00730b0d81fdb"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "cc"
 version = "1.0.66"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4c0496836a84f8d0495758516b8621a622beb77c0fed418570e50764093ced48"
 dependencies = [
  "jobserver",
 ]
 
 [[package]]
 name = "cfg-if"
 version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822"
 
 [[package]]
 name = "cfg-if"
 version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "chrono"
 version = "0.4.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "670ad68c9088c2a963aaa298cb369688cf3f9465ce5e2d4ca10e6e0098a1ce73"
 dependencies = [
  "libc",
  "num-integer",
  "num-traits",
  "time",
  "winapi",
 ]
 
 [[package]]
 name = "clap"
 version = "2.34.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a0610544180c38b88101fecf2dd634b174a62eef6946f84dfc6a7127512b381c"
 dependencies = [
  "ansi_term",
  "atty",
  "bitflags",
  "strsim",
  "textwrap",
  "unicode-width",
  "vec_map",
 ]
 
 [[package]]
 name = "const_fn"
 version = "0.4.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cd51eab21ab4fd6a3bf889e2d0958c0a6e3a61ad04260325e919e652a2a62826"
 
 [[package]]
 name = "convert_case"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
 
 [[package]]
 name = "cpufeatures"
 version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed00c67cb5d0a7d64a44f6ad2668db7e7530311dd53ea79bcd4fb022c64911c8"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "cpufeatures"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "95059428f66df56b63431fdb4e1947ed2190586af5c5a8a8b71122bdf5a7f469"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "cpython"
 version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b7d46ba8ace7f3a1d204ac5060a706d0a68de6b42eafb6a586cc08bebcffe664"
 dependencies = [
  "libc",
  "num-traits",
  "paste",
  "python3-sys",
 ]
 
 [[package]]
 name = "crc32fast"
 version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "81156fece84ab6a9f2afdb109ce3ae577e42b1228441eded99bd77f627953b1a"
 dependencies = [
  "cfg-if 1.0.0",
 ]
 
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e54ea8bc3fb1ee042f5aace6e3c6e025d3874866da222930f70ce62aceba0bfa"
 dependencies = [
  "cfg-if 1.0.0",
  "crossbeam-utils",
 ]
 
 [[package]]
 name = "crossbeam-deque"
 version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94af6efb46fef72616855b036a624cf27ba656ffc9be1b9a3c931cfc7749a9a9"
 dependencies = [
  "cfg-if 1.0.0",
  "crossbeam-epoch",
  "crossbeam-utils",
 ]
 
 [[package]]
 name = "crossbeam-epoch"
 version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1aaa739f95311c2c7887a76863f500026092fb1dce0161dab577e559ef3569d"
 dependencies = [
  "cfg-if 1.0.0",
  "const_fn",
  "crossbeam-utils",
  "lazy_static",
  "memoffset",
  "scopeguard",
 ]
 
 [[package]]
 name = "crossbeam-utils"
 version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "02d96d1e189ef58269ebe5b97953da3274d83a93af647c2ddd6f9dab28cedb8d"
 dependencies = [
  "autocfg",
  "cfg-if 1.0.0",
  "lazy_static",
 ]
 
 [[package]]
 name = "crypto-common"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a4600d695eb3f6ce1cd44e6e291adceb2cc3ab12f20a33777ecd0bf6eba34e06"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "ctor"
 version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7fbaabec2c953050352311293be5c6aba8e141ba19d6811862b232d6fd020484"
 dependencies = [
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "derive_more"
 version = "0.99.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321"
 dependencies = [
  "convert_case",
  "proc-macro2",
  "quote",
  "rustc_version",
  "syn",
 ]
 
 [[package]]
 name = "diff"
 version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0e25ea47919b1560c4e3b7fe0aaab9becf5b84a10325ddf7db0f0ba5e1026499"
 
 [[package]]
 name = "digest"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3dd60d1080a57a05ab032377049e0591415d2b31afd7028356dbf3cc6dcb066"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "digest"
 version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8cb780dce4f9a8f5c087362b3a4595936b2019e7c8b30f2c3e9a7e94e6ae9837"
 dependencies = [
  "block-buffer 0.10.2",
  "crypto-common",
 ]
 
 [[package]]
 name = "either"
 version = "1.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e78d4f1cc4ae33bbfc157ed5d5a5ef3bc29227303d595861deb238fcec4e9457"
 
 [[package]]
 name = "env_logger"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b2cf0344971ee6c64c31be0d530793fba457d322dfec2810c453d0ef228f9c3"
 dependencies = [
  "atty",
  "humantime",
  "log",
  "regex",
  "termcolor",
 ]
 
 [[package]]
 name = "fastrand"
 version = "1.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c3fcf0cee53519c866c09b5de1f6c56ff9d647101f81c1964fa632e148896cdf"
 dependencies = [
  "instant",
 ]
 
 [[package]]
 name = "flate2"
 version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e6988e897c1c9c485f43b47a529cef42fde0547f9d8d41a7062518f1d8fc53f"
 dependencies = [
  "cfg-if 1.0.0",
  "crc32fast",
  "libc",
  "libz-sys",
  "miniz_oxide",
 ]
 
 [[package]]
 name = "format-bytes"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "48942366ef93975da38e175ac9e10068c6fc08ca9e85930d4f098f4d5b14c2fd"
 dependencies = [
  "format-bytes-macros",
 ]
 
 [[package]]
 name = "format-bytes-macros"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "203aadebefcc73d12038296c228eabf830f99cba991b0032adf20e9fa6ce7e4f"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "generic-array"
 version = "0.14.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "501466ecc8a30d1d3b7fc9229b122b2ce8ed6e9d9223f1138d4babb253e51817"
 dependencies = [
  "typenum",
  "version_check",
 ]
 
 [[package]]
 name = "getrandom"
 version = "0.1.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc587bc0ec293155d5bfa6b9891ec18a1e330c234f896ea47fbada4cadbe47e6"
 dependencies = [
  "cfg-if 0.1.10",
  "libc",
  "wasi 0.9.0+wasi-snapshot-preview1",
 ]
 
 [[package]]
 name = "getrandom"
 version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "418d37c8b1d42553c93648be529cb70f920d3baf8ef469b74b9638df426e0b4c"
 dependencies = [
  "cfg-if 1.0.0",
  "libc",
  "wasi 0.10.0+wasi-snapshot-preview1",
 ]
 
 [[package]]
 name = "glob"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
 
 [[package]]
 name = "hashbrown"
 version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d7afe4a420e3fe79967a00898cc1f4db7c8a49a9333a29f8a4bd76a253d5cd04"
 dependencies = [
  "ahash",
  "rayon",
 ]
 
 [[package]]
 name = "hermit-abi"
 version = "0.1.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5aca5565f760fb5b220e499d72710ed156fdb74e631659e99377d9ebfbd13ae8"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "hex"
 version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "hg-core"
 version = "0.1.0"
 dependencies = [
  "bitflags",
  "byteorder",
  "bytes-cast",
  "clap",
  "crossbeam-channel",
  "derive_more",
  "flate2",
  "format-bytes",
  "hashbrown",
  "home",
  "im-rc",
  "itertools 0.10.3",
  "lazy_static",
  "libc",
  "log",
  "memmap2",
  "micro-timer",
+ "ouroboros",
  "pretty_assertions",
  "rand 0.8.5",
  "rand_distr",
  "rand_pcg",
  "rayon",
  "regex",
  "same-file",
  "sha-1 0.10.0",
- "stable_deref_trait",
  "tempfile",
  "twox-hash",
  "zstd",
 ]
 
 [[package]]
 name = "hg-cpython"
 version = "0.1.0"
 dependencies = [
  "cpython",
  "crossbeam-channel",
  "env_logger",
  "hg-core",
  "libc",
  "log",
  "stable_deref_trait",
  "vcsgraph",
 ]
 
 [[package]]
 name = "home"
 version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2456aef2e6b6a9784192ae780c0f15bc57df0e918585282325e8c8ac27737654"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "humantime"
 version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4"
 
 [[package]]
 name = "im-rc"
 version = "15.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3ca8957e71f04a205cb162508f9326aea04676c8dfd0711220190d6b83664f3f"
 dependencies = [
  "bitmaps",
  "rand_core 0.5.1",
  "rand_xoshiro",
  "sized-chunks",
  "typenum",
  "version_check",
 ]
 
 [[package]]
 name = "instant"
 version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
 dependencies = [
  "cfg-if 1.0.0",
 ]
 
 [[package]]
 name = "itertools"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b"
 dependencies = [
  "either",
 ]
 
 [[package]]
 name = "itertools"
 version = "0.10.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a9a9d19fa1e79b6215ff29b9d6880b706147f16e9b1dbb1e4e5947b5b02bc5e3"
 dependencies = [
  "either",
 ]
 
 [[package]]
 name = "jobserver"
 version = "0.1.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5c71313ebb9439f74b00d9d2dcec36440beaf57a6aa0623068441dd7cd81a7f2"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
 version = "0.2.119"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1bf2e165bb3457c8e098ea76f3e3bc9db55f87aa90d52d0e6be741470916aaa4"
 
 [[package]]
 name = "libm"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c7d73b3f436185384286bd8098d17ec07c9a7d2388a6599f824d8502b529702a"
 
 [[package]]
 name = "libz-sys"
 version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "602113192b08db8f38796c4e85c39e960c145965140e918018bcde1952429655"
 dependencies = [
  "cc",
  "pkg-config",
  "vcpkg",
 ]
 
 [[package]]
 name = "log"
 version = "0.4.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "51b9bbe6c47d51fc3e1a9b945965946b4c44142ab8792c50835a980d362c2710"
 dependencies = [
  "cfg-if 1.0.0",
 ]
 
 [[package]]
 name = "memchr"
 version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "308cc39be01b73d0d18f82a0e7b2a3df85245f84af96fdddc5d202d27e47b86a"
 
 [[package]]
 name = "memmap2"
 version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "057a3db23999c867821a7a59feb06a578fcb03685e983dff90daf9e7d24ac08f"
 dependencies = [
  "libc",
  "stable_deref_trait",
 ]
 
 [[package]]
 name = "memoffset"
 version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "157b4208e3059a8f9e78d559edc658e13df41410cb3ae03979c83130067fdd87"
 dependencies = [
  "autocfg",
 ]
 
 [[package]]
 name = "micro-timer"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5de32cb59a062672560d6f0842c4aa7714727457b9fe2daf8987d995a176a405"
 dependencies = [
  "micro-timer-macros",
  "scopeguard",
 ]
 
 [[package]]
 name = "micro-timer-macros"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cee948b94700125b52dfb68dd17c19f6326696c1df57f92c05ee857463c93ba1"
 dependencies = [
  "proc-macro2",
  "quote",
  "scopeguard",
  "syn",
 ]
 
 [[package]]
 name = "miniz_oxide"
 version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0f2d26ec3309788e423cfbf68ad1800f061638098d76a83681af979dc4eda19d"
 dependencies = [
  "adler",
  "autocfg",
 ]
 
 [[package]]
 name = "num-integer"
 version = "0.1.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d2cc698a63b549a70bc047073d2949cce27cd1c7b0a4a862d08a8031bc2801db"
 dependencies = [
  "autocfg",
  "num-traits",
 ]
 
 [[package]]
 name = "num-traits"
 version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9a64b1ec5cda2586e284722486d802acf1f7dbdc623e2bfc57e65ca1cd099290"
 dependencies = [
  "autocfg",
  "libm",
 ]
 
 [[package]]
 name = "num_cpus"
 version = "1.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "05499f3756671c15885fee9034446956fff3f243d6077b91e5767df161f766b3"
 dependencies = [
  "hermit-abi",
  "libc",
 ]
 
 [[package]]
 name = "opaque-debug"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
 
 [[package]]
+name = "ouroboros"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f31a3b678685b150cba82b702dcdc5e155893f63610cf388d30cd988d4ca2bf"
+dependencies = [
+ "aliasable",
+ "ouroboros_macro",
+ "stable_deref_trait",
+]
+
+[[package]]
+name = "ouroboros_macro"
+version = "0.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "084fd65d5dd8b3772edccb5ffd1e4b7eba43897ecd0f9401e330e8c542959408"
+dependencies = [
+ "Inflector",
+ "proc-macro-error",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
 name = "output_vt100"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "53cdc5b785b7a58c5aad8216b3dfa114df64b0b06ae6e1501cef91df2fbdf8f9"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "paste"
 version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "acbf547ad0c65e31259204bd90935776d1c693cec2f4ff7abb7a1bbbd40dfe58"
 
 [[package]]
 name = "pkg-config"
 version = "0.3.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3831453b3449ceb48b6d9c7ad7c96d5ea673e9b470a1dc578c2ce6521230884c"
 
 [[package]]
 name = "ppv-lite86"
 version = "0.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac74c624d6b2d21f425f752262f42188365d7b8ff1aff74c82e45136510a4857"
 
 [[package]]
 name = "pretty_assertions"
 version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76d5b548b725018ab5496482b45cb8bef21e9fed1858a6d674e3a8a0f0bb5d50"
 dependencies = [
  "ansi_term",
  "ctor",
  "diff",
  "output_vt100",
 ]
 
 [[package]]
+name = "proc-macro-error"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c"
+dependencies = [
+ "proc-macro-error-attr",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "version_check",
+]
+
+[[package]]
+name = "proc-macro-error-attr"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "version_check",
+]
+
+[[package]]
 name = "proc-macro2"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71"
 dependencies = [
  "unicode-xid",
 ]
 
 [[package]]
 name = "python3-sys"
 version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b18b32e64c103d5045f44644d7ddddd65336f7a0521f6fde673240a9ecceb77e"
 dependencies = [
  "libc",
  "regex",
 ]
 
 [[package]]
 name = "quote"
 version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aa563d17ecb180e500da1cfd2b028310ac758de548efdd203e18f283af693f37"
 dependencies = [
  "proc-macro2",
 ]
 
 [[package]]
 name = "rand"
 version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
 dependencies = [
  "getrandom 0.1.15",
  "libc",
  "rand_chacha 0.2.2",
  "rand_core 0.5.1",
  "rand_hc",
 ]
 
 [[package]]
 name = "rand"
 version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
 dependencies = [
  "libc",
  "rand_chacha 0.3.1",
  "rand_core 0.6.3",
 ]
 
 [[package]]
 name = "rand_chacha"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402"
 dependencies = [
  "ppv-lite86",
  "rand_core 0.5.1",
 ]
 
 [[package]]
 name = "rand_chacha"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
 dependencies = [
  "ppv-lite86",
  "rand_core 0.6.3",
 ]
 
 [[package]]
 name = "rand_core"
 version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
 dependencies = [
  "getrandom 0.1.15",
 ]
 
 [[package]]
 name = "rand_core"
 version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
 dependencies = [
  "getrandom 0.2.4",
 ]
 
 [[package]]
 name = "rand_distr"
 version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32cb0b9bc82b0a0876c2dd994a7e7a2683d3e7390ca40e6886785ef0c7e3ee31"
 dependencies = [
  "num-traits",
  "rand 0.8.5",
 ]
 
 [[package]]
 name = "rand_hc"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c"
 dependencies = [
  "rand_core 0.5.1",
 ]
 
 [[package]]
 name = "rand_pcg"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "59cad018caf63deb318e5a4586d99a24424a364f40f1e5778c29aca23f4fc73e"
 dependencies = [
  "rand_core 0.6.3",
 ]
 
 [[package]]
 name = "rand_xoshiro"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a9fcdd2e881d02f1d9390ae47ad8e5696a9e4be7b547a1da2afbc61973217004"
 dependencies = [
  "rand_core 0.5.1",
 ]
 
 [[package]]
 name = "rayon"
 version = "1.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c06aca804d41dbc8ba42dfd964f0d01334eceb64314b9ecf7c5fad5188a06d90"
 dependencies = [
  "autocfg",
  "crossbeam-deque",
  "either",
  "rayon-core",
 ]
 
 [[package]]
 name = "rayon-core"
 version = "1.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d78120e2c850279833f1dd3582f730c4ab53ed95aeaaaa862a2a5c71b1656d8e"
 dependencies = [
  "crossbeam-channel",
  "crossbeam-deque",
  "crossbeam-utils",
  "lazy_static",
  "num_cpus",
 ]
 
 [[package]]
 name = "redox_syscall"
 version = "0.2.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8380fe0152551244f0747b1bf41737e0f8a74f97a14ccefd1148187271634f3c"
 dependencies = [
  "bitflags",
 ]
 
 [[package]]
 name = "regex"
 version = "1.5.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1a11647b6b25ff05a515cb92c365cec08801e83423a235b51e231e1808747286"
 dependencies = [
  "aho-corasick",
  "memchr",
  "regex-syntax",
 ]
 
 [[package]]
 name = "regex-syntax"
 version = "0.6.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f497285884f3fcff424ffc933e56d7cbca511def0c9831a7f9b5f6153e3cc89b"
 
 [[package]]
 name = "remove_dir_all"
 version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3acd125665422973a33ac9d3dd2df85edad0f4ae9b00dafb1a05e43a9f5ef8e7"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "rhg"
 version = "0.1.0"
 dependencies = [
  "atty",
  "chrono",
  "clap",
  "derive_more",
  "env_logger",
  "format-bytes",
  "hg-core",
  "home",
  "lazy_static",
  "log",
  "micro-timer",
  "regex",
  "users",
 ]
 
 [[package]]
 name = "rustc_version"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
 dependencies = [
  "semver",
 ]
 
 [[package]]
 name = "same-file"
 version = "1.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
 dependencies = [
  "winapi-util",
 ]
 
 [[package]]
 name = "scopeguard"
 version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
 
 [[package]]
 name = "semver"
 version = "1.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a4a3381e03edd24287172047536f20cabde766e2cd3e65e6b00fb3af51c4f38d"
 
 [[package]]
 name = "sha-1"
 version = "0.9.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8c4cfa741c5832d0ef7fab46cabed29c2aae926db0b11bb2069edd8db5e64e16"
 dependencies = [
  "block-buffer 0.9.0",
  "cfg-if 1.0.0",
  "cpufeatures 0.1.4",
  "digest 0.9.0",
  "opaque-debug",
 ]
 
 [[package]]
 name = "sha-1"
 version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "028f48d513f9678cda28f6e4064755b3fbb2af6acd672f2c209b62323f7aea0f"
 dependencies = [
  "cfg-if 1.0.0",
  "cpufeatures 0.2.1",
  "digest 0.10.2",
 ]
 
 [[package]]
 name = "sized-chunks"
 version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1ec31ceca5644fa6d444cc77548b88b67f46db6f7c71683b0f9336e671830d2f"
 dependencies = [
  "bitmaps",
  "typenum",
 ]
 
 [[package]]
 name = "stable_deref_trait"
 version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
 
 [[package]]
 name = "static_assertions"
 version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
 [[package]]
 name = "strsim"
 version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
 version = "1.0.54"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9a2af957a63d6bd42255c359c93d9bfdb97076bd3b820897ce55ffbfbf107f44"
 dependencies = [
  "proc-macro2",
  "quote",
  "unicode-xid",
 ]
 
 [[package]]
 name = "tempfile"
 version = "3.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5cdb1ef4eaeeaddc8fbd371e5017057064af0911902ef36b39801f67cc6d79e4"
 dependencies = [
  "cfg-if 1.0.0",
  "fastrand",
  "libc",
  "redox_syscall",
  "remove_dir_all",
  "winapi",
 ]
 
 [[package]]
 name = "termcolor"
 version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2dfed899f0eb03f32ee8c6a0aabdb8a7949659e3466561fc0adf54e26d88c5f4"
 dependencies = [
  "winapi-util",
 ]
 
 [[package]]
 name = "textwrap"
 version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
 dependencies = [
  "unicode-width",
 ]
 
 [[package]]
 name = "time"
 version = "0.1.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6db9e6914ab8b1ae1c260a4ae7a49b6c5611b40328a735b21862567685e73255"
 dependencies = [
  "libc",
  "wasi 0.10.0+wasi-snapshot-preview1",
  "winapi",
 ]
 
 [[package]]
 name = "twox-hash"
 version = "1.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4ee73e6e4924fe940354b8d4d98cad5231175d615cd855b758adc658c0aac6a0"
 dependencies = [
  "cfg-if 1.0.0",
  "rand 0.8.5",
  "static_assertions",
 ]
 
 [[package]]
 name = "typenum"
 version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "373c8a200f9e67a0c95e62a4f52fbf80c23b4381c05a17845531982fa99e6b33"
 
 [[package]]
 name = "unicode-width"
 version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3ed742d4ea2bd1176e236172c8429aaf54486e7ac098db29ffe6529e0ce50973"
 
 [[package]]
 name = "unicode-xid"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564"
 
 [[package]]
 name = "users"
 version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24cc0f6d6f267b73e5a2cadf007ba8f9bc39c6a6f9666f8cf25ea809a153b032"
 dependencies = [
  "libc",
  "log",
 ]
 
 [[package]]
 name = "vcpkg"
 version = "0.2.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b00bca6106a5e23f3eee943593759b7fcddb00554332e856d990c893966879fb"
 
 [[package]]
 name = "vcsgraph"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4cb68c231e2575f7503a7c19213875f9d4ec2e84e963a56ce3de4b6bee351ef7"
 dependencies = [
  "hex",
  "rand 0.7.3",
  "sha-1 0.9.6",
 ]
 
 [[package]]
 name = "vec_map"
 version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f1bddf1187be692e79c5ffeab891132dfb0f236ed36a43c7ed39f1165ee20191"
 
 [[package]]
 name = "version_check"
 version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b5a972e5669d67ba988ce3dc826706fb0a8b01471c088cb0b6110b805cc36aed"
 
 [[package]]
 name = "wasi"
 version = "0.9.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
 
 [[package]]
 name = "wasi"
 version = "0.10.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
 
 [[package]]
 name = "winapi"
 version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
 dependencies = [
  "winapi-i686-pc-windows-gnu",
  "winapi-x86_64-pc-windows-gnu",
 ]
 
 [[package]]
 name = "winapi-i686-pc-windows-gnu"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
 
 [[package]]
 name = "winapi-util"
 version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "winapi-x86_64-pc-windows-gnu"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
 name = "zstd"
 version = "0.5.4+zstd.1.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "69996ebdb1ba8b1517f61387a883857818a66c8a295f487b1ffd8fd9d2c82910"
 dependencies = [
  "zstd-safe",
 ]
 
 [[package]]
 name = "zstd-safe"
 version = "2.0.6+zstd.1.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "98aa931fb69ecee256d44589d19754e61851ae4769bf963b385119b1cc37a49e"
 dependencies = [
  "libc",
  "zstd-sys",
 ]
 
 [[package]]
 name = "zstd-sys"
 version = "1.4.18+zstd.1.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1e6e8778706838f43f771d80d37787cb2fe06dafe89dd3aebaf6721b9eaec81"
 dependencies = [
  "cc",
  "glob",
  "itertools 0.9.0",
  "libc",
 ]

rust/hg-core/Cargo.toml

@@ -1,48 +1,48 b''
 [package]
 name = "hg-core"
 version = "0.1.0"
 authors = ["Georges Racinet <[e-mail]>"]
 description = "Mercurial pure Rust core library, with no assumption on Python bindings (FFI)"
 edition = "2018"
 
 [lib]
 name = "hg"
 
 [dependencies]
 bitflags = "1.3.2"
 bytes-cast = "0.2.0"
 byteorder = "1.4.3"
 derive_more = "0.99.17"
 hashbrown = { version = "0.9.1", features = ["rayon"] }
 home = "0.5.3"
 im-rc = "15.0.0"
 itertools = "0.10.3"
 lazy_static = "1.4.0"
 libc = "0.2.119"
+ouroboros = "0.15.0"
 rand = "0.8.5"
 rand_pcg = "0.3.1"
 rand_distr = "0.4.3"
 rayon = "1.5.1"
 regex = "1.5.5"
 sha-1 = "0.10.0"
 twox-hash = "1.6.2"
 same-file = "1.0.6"
-stable_deref_trait = "1.2.0"
 tempfile = "3.3.0"
 crossbeam-channel = "0.5.2"
 micro-timer = "0.4.0"
 log = "0.4.14"
 memmap2 = { version = "0.5.3", features = ["stable_deref_trait"] }
 zstd = "0.5.3"
 format-bytes = "0.3.0"
 
 # We don't use the `miniz-oxide` backend to not change rhg benchmarks and until
 # we have a clearer view of which backend is the fastest.
 [dependencies.flate2]
 version = "1.0.22"
 features = ["zlib"]
 default-features = false
 
 [dev-dependencies]
 clap = "2.34.0"
 pretty_assertions = "1.1.0"

rust/hg-core/src/dirstate/status.rs

@@ -1,151 +1,149 b''
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[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.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
 use crate::dirstate::entry::TruncatedTimestamp;
 use crate::dirstate_tree::on_disk::DirstateV2ParseError;
 use crate::{
     utils::hg_path::{HgPath, HgPathError},
     PatternError,
 };
 
 use std::{borrow::Cow, fmt};
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug, Copy, Clone)]
 pub enum BadType {
     CharacterDevice,
     BlockDevice,
     FIFO,
     Socket,
     Directory,
     Unknown,
 }
 
 impl fmt::Display for BadType {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         f.write_str(match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         })
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait + 'static>`, so add
 /// an explicit lifetime here to not fight `'static` bounds "out of nowhere".
 pub type IgnoreFnType<'a> =
     Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>;
 
 /// We have a good mix of owned (from directory traversal) and borrowed (from
 /// the dirstate/explicit) paths, this comes up a lot.
 pub type HgPathCow<'a> = Cow<'a, HgPath>;
 
 #[derive(Debug, Copy, Clone)]
 pub struct StatusOptions {
     /// Whether we are on a filesystem with UNIX-like exec flags
     pub check_exec: bool,
     pub list_clean: bool,
     pub list_unknown: bool,
     pub list_ignored: bool,
     /// Whether to populate `StatusPath::copy_source`
     pub list_copies: bool,
     /// Whether to collect traversed dirs for applying a callback later.
     /// Used by `hg purge` for example.
     pub collect_traversed_dirs: bool,
 }
 
 #[derive(Default)]
 pub struct DirstateStatus<'a> {
     /// The current time at the start of the `status()` algorithm, as measured
     /// and possibly truncated by the filesystem.
     pub filesystem_time_at_status_start: Option<TruncatedTimestamp>,
 
     /// Tracked files whose contents have changed since the parent revision
     pub modified: Vec<StatusPath<'a>>,
 
     /// Newly-tracked files that were not present in the parent
     pub added: Vec<StatusPath<'a>>,
 
     /// Previously-tracked files that have been (re)moved with an hg command
     pub removed: Vec<StatusPath<'a>>,
 
     /// (Still) tracked files that are missing, (re)moved with an non-hg
     /// command
     pub deleted: Vec<StatusPath<'a>>,
 
     /// Tracked files that are up to date with the parent.
     /// Only pupulated if `StatusOptions::list_clean` is true.
     pub clean: Vec<StatusPath<'a>>,
 
     /// Files in the working directory that are ignored with `.hgignore`.
     /// Only pupulated if `StatusOptions::list_ignored` is true.
     pub ignored: Vec<StatusPath<'a>>,
 
     /// Files in the working directory that are neither tracked nor ignored.
     /// Only pupulated if `StatusOptions::list_unknown` is true.
     pub unknown: Vec<StatusPath<'a>>,
 
     /// Was explicitly matched but cannot be found/accessed
     pub bad: Vec<(HgPathCow<'a>, BadMatch)>,
 
     /// Either clean or modified, but we can’t tell from filesystem metadata
     /// alone. The file contents need to be read and compared with that in
     /// the parent.
     pub unsure: Vec<StatusPath<'a>>,
 
     /// Only filled if `collect_traversed_dirs` is `true`
     pub traversed: Vec<HgPathCow<'a>>,
 
     /// Whether `status()` made changed to the `DirstateMap` that should be
     /// written back to disk
     pub dirty: bool,
 }
 
 #[derive(Clone, PartialEq, Eq, PartialOrd, Ord)]
 pub struct StatusPath<'a> {
     pub path: HgPathCow<'a>,
     pub copy_source: Option<HgPathCow<'a>>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum StatusError {
     /// An invalid path that cannot be represented in Mercurial was found
     Path(HgPathError),
     /// An invalid "ignore" pattern was found
     Pattern(PatternError),
     /// Corrupted dirstate
     DirstateV2ParseError(DirstateV2ParseError),
 }
 
-pub type StatusResult<T> = Result<T, StatusError>;
-
 impl fmt::Display for StatusError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             StatusError::Path(error) => error.fmt(f),
             StatusError::Pattern(error) => error.fmt(f),
             StatusError::DirstateV2ParseError(_) => {
                 f.write_str("dirstate-v2 parse error")
             }
         }
     }
 }

rust/hg-core/src/dirstate_tree/dirstate_map.rs

@@ -1,1156 +1,1195 b''
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::path::PathBuf;
 
 use super::on_disk;
 use super::on_disk::DirstateV2ParseError;
 use super::owning::OwningDirstateMap;
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::CopyMapIter;
 use crate::dirstate::StateMapIter;
 use crate::dirstate::TruncatedTimestamp;
 use crate::dirstate::SIZE_FROM_OTHER_PARENT;
 use crate::dirstate::SIZE_NON_NORMAL;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::FastHashbrownMap as FastHashMap;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
 
 /// Append to an existing data file if the amount of unreachable data (not used
 /// anymore) is less than this fraction of the total amount of existing data.
 const ACCEPTABLE_UNREACHABLE_BYTES_RATIO: f32 = 0.5;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     pub(super) on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     pub(super) nodes_with_entry_count: u32,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     pub(super) nodes_with_copy_source_count: u32,
 
     /// See on_disk::Header
     pub(super) ignore_patterns_hash: on_disk::IgnorePatternsHash,
 
     /// How many bytes of `on_disk` are not used anymore
     pub(super) unreachable_bytes: u32,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `HashMap` would waste time always re-hashing the same
 /// string prefix.
 pub(super) type NodeKey<'on_disk> = WithBasename<Cow<'on_disk, HgPath>>;
 
 /// Similar to `&'tree Cow<'on_disk, HgPath>`, but can also be returned
 /// for on-disk nodes that don’t actually have a `Cow` to borrow.
 pub(super) enum BorrowedPath<'tree, 'on_disk> {
     InMemory(&'tree HgPathBuf),
     OnDisk(&'on_disk HgPath),
 }
 
 pub(super) enum ChildNodes<'on_disk> {
     InMemory(FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum ChildNodesRef<'tree, 'on_disk> {
     InMemory(&'tree FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum NodeRef<'tree, 'on_disk> {
     InMemory(&'tree NodeKey<'on_disk>, &'tree Node<'on_disk>),
     OnDisk(&'on_disk on_disk::Node),
 }
 
 impl<'tree, 'on_disk> BorrowedPath<'tree, 'on_disk> {
     pub fn detach_from_tree(&self) -> Cow<'on_disk, HgPath> {
         match *self {
             BorrowedPath::InMemory(in_memory) => Cow::Owned(in_memory.clone()),
             BorrowedPath::OnDisk(on_disk) => Cow::Borrowed(on_disk),
         }
     }
 }
 
 impl<'tree, 'on_disk> std::ops::Deref for BorrowedPath<'tree, 'on_disk> {
     type Target = HgPath;
 
     fn deref(&self) -> &HgPath {
         match *self {
             BorrowedPath::InMemory(in_memory) => in_memory,
             BorrowedPath::OnDisk(on_disk) => on_disk,
         }
     }
 }
 
 impl Default for ChildNodes<'_> {
     fn default() -> Self {
         ChildNodes::InMemory(Default::default())
     }
 }
 
 impl<'on_disk> ChildNodes<'on_disk> {
     pub(super) fn as_ref<'tree>(
         &'tree self,
     ) -> ChildNodesRef<'tree, 'on_disk> {
         match self {
             ChildNodes::InMemory(nodes) => ChildNodesRef::InMemory(nodes),
             ChildNodes::OnDisk(nodes) => ChildNodesRef::OnDisk(nodes),
         }
     }
 
     pub(super) fn is_empty(&self) -> bool {
         match self {
             ChildNodes::InMemory(nodes) => nodes.is_empty(),
             ChildNodes::OnDisk(nodes) => nodes.is_empty(),
         }
     }
 
     fn make_mut(
         &mut self,
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
     ) -> Result<
         &mut FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>,
         DirstateV2ParseError,
     > {
         match self {
             ChildNodes::InMemory(nodes) => Ok(nodes),
             ChildNodes::OnDisk(nodes) => {
                 *unreachable_bytes +=
                     std::mem::size_of_val::<[on_disk::Node]>(nodes) as u32;
                 let nodes = nodes
                     .iter()
                     .map(|node| {
                         Ok((
                             node.path(on_disk)?,
                             node.to_in_memory_node(on_disk)?,
                         ))
                     })
                     .collect::<Result<_, _>>()?;
                 *self = ChildNodes::InMemory(nodes);
                 match self {
                     ChildNodes::InMemory(nodes) => Ok(nodes),
                     ChildNodes::OnDisk(_) => unreachable!(),
                 }
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> ChildNodesRef<'tree, 'on_disk> {
     pub(super) fn get(
         &self,
         base_name: &HgPath,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         match self {
             ChildNodesRef::InMemory(nodes) => Ok(nodes
                 .get_key_value(base_name)
                 .map(|(k, v)| NodeRef::InMemory(k, v))),
             ChildNodesRef::OnDisk(nodes) => {
                 let mut parse_result = Ok(());
                 let search_result = nodes.binary_search_by(|node| {
                     match node.base_name(on_disk) {
                         Ok(node_base_name) => node_base_name.cmp(base_name),
                         Err(e) => {
                             parse_result = Err(e);
                             // Dummy comparison result, `search_result` won’t
                             // be used since `parse_result` is an error
                             std::cmp::Ordering::Equal
                         }
                     }
                 });
                 parse_result.map(|()| {
                     search_result.ok().map(|i| NodeRef::OnDisk(&nodes[i]))
                 })
             }
         }
     }
 
     /// Iterate in undefined order
     pub(super) fn iter(
         &self,
     ) -> impl Iterator<Item = NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => itertools::Either::Left(
                 nodes.iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => {
                 itertools::Either::Right(nodes.iter().map(NodeRef::OnDisk))
             }
         }
     }
 
     /// Iterate in parallel in undefined order
     pub(super) fn par_iter(
         &self,
     ) -> impl rayon::iter::ParallelIterator<Item = NodeRef<'tree, 'on_disk>>
     {
         use rayon::prelude::*;
         match self {
             ChildNodesRef::InMemory(nodes) => rayon::iter::Either::Left(
                 nodes.par_iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => rayon::iter::Either::Right(
                 nodes.par_iter().map(NodeRef::OnDisk),
             ),
         }
     }
 
     pub(super) fn sorted(&self) -> Vec<NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => {
                 let mut vec: Vec<_> = nodes
                     .iter()
                     .map(|(k, v)| NodeRef::InMemory(k, v))
                     .collect();
                 fn sort_key<'a>(node: &'a NodeRef) -> &'a HgPath {
                     match node {
                         NodeRef::InMemory(path, _node) => path.base_name(),
                         NodeRef::OnDisk(_) => unreachable!(),
                     }
                 }
                 // `sort_unstable_by_key` doesn’t allow keys borrowing from the
                 // value: https://github.com/rust-lang/rust/issues/34162
                 vec.sort_unstable_by(|a, b| sort_key(a).cmp(sort_key(b)));
                 vec
             }
             ChildNodesRef::OnDisk(nodes) => {
                 // Nodes on disk are already sorted
                 nodes.iter().map(NodeRef::OnDisk).collect()
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> NodeRef<'tree, 'on_disk> {
     pub(super) fn full_path(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.full_path()),
             NodeRef::OnDisk(node) => node.full_path(on_disk),
         }
     }
 
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn full_path_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<BorrowedPath<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => match path.full_path() {
                 Cow::Borrowed(on_disk) => Ok(BorrowedPath::OnDisk(on_disk)),
                 Cow::Owned(in_memory) => Ok(BorrowedPath::InMemory(in_memory)),
             },
             NodeRef::OnDisk(node) => {
                 Ok(BorrowedPath::OnDisk(node.full_path(on_disk)?))
             }
         }
     }
 
     pub(super) fn base_name(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.base_name()),
             NodeRef::OnDisk(node) => node.base_name(on_disk),
         }
     }
 
     pub(super) fn children(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<ChildNodesRef<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(node.children.as_ref()),
             NodeRef::OnDisk(node) => {
                 Ok(ChildNodesRef::OnDisk(node.children(on_disk)?))
             }
         }
     }
 
     pub(super) fn has_copy_source(&self) -> bool {
         match self {
             NodeRef::InMemory(_path, node) => node.copy_source.is_some(),
             NodeRef::OnDisk(node) => node.has_copy_source(),
         }
     }
 
     pub(super) fn copy_source(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<&'tree HgPath>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.copy_source.as_ref().map(|s| &**s))
             }
             NodeRef::OnDisk(node) => node.copy_source(on_disk),
         }
     }
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn copy_source_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<BorrowedPath<'tree, 'on_disk>>, DirstateV2ParseError>
     {
         Ok(match self {
             NodeRef::InMemory(_path, node) => {
                 node.copy_source.as_ref().map(|source| match source {
                     Cow::Borrowed(on_disk) => BorrowedPath::OnDisk(on_disk),
                     Cow::Owned(in_memory) => BorrowedPath::InMemory(in_memory),
                 })
             }
             NodeRef::OnDisk(node) => node
                 .copy_source(on_disk)?
                 .map(|source| BorrowedPath::OnDisk(source)),
         })
     }
 
     pub(super) fn entry(
         &self,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().copied())
             }
             NodeRef::OnDisk(node) => node.entry(),
         }
     }
 
     pub(super) fn state(
         &self,
     ) -> Result<Option<EntryState>, DirstateV2ParseError> {
         Ok(self.entry()?.map(|e| e.state()))
     }
 
     pub(super) fn cached_directory_mtime(
         &self,
     ) -> Result<Option<TruncatedTimestamp>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(match node.data {
                 NodeData::CachedDirectory { mtime } => Some(mtime),
                 _ => None,
             }),
             NodeRef::OnDisk(node) => node.cached_directory_mtime(),
         }
     }
 
     pub(super) fn descendants_with_entry_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => {
                 node.descendants_with_entry_count
             }
             NodeRef::OnDisk(node) => node.descendants_with_entry_count.get(),
         }
     }
 
     pub(super) fn tracked_descendants_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => node.tracked_descendants_count,
             NodeRef::OnDisk(node) => node.tracked_descendants_count.get(),
         }
     }
 }
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     pub(super) data: NodeData,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node have an entry.
     pub(super) descendants_with_entry_count: u32,
 
     /// How many (non-inclusive) descendants of this node have an entry whose
     /// state is "tracked".
     pub(super) tracked_descendants_count: u32,
 }
 
 pub(super) enum NodeData {
     Entry(DirstateEntry),
     CachedDirectory { mtime: TruncatedTimestamp },
     None,
 }
 
 impl Default for NodeData {
     fn default() -> Self {
         NodeData::None
     }
 }
 
 impl NodeData {
     fn has_entry(&self) -> bool {
         match self {
             NodeData::Entry(_) => true,
             _ => false,
         }
     }
 
     fn as_entry(&self) -> Option<&DirstateEntry> {
         match self {
             NodeData::Entry(entry) => Some(entry),
             _ => None,
         }
     }
 }
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub(super) fn empty(on_disk: &'on_disk [u8]) -> Self {
         Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
             ignore_patterns_hash: [0; on_disk::IGNORE_PATTERNS_HASH_LEN],
             unreachable_bytes: 0,
         }
     }
 
     #[timed]
     pub fn new_v2(
         on_disk: &'on_disk [u8],
         data_size: usize,
         metadata: &[u8],
     ) -> Result<Self, DirstateError> {
         if let Some(data) = on_disk.get(..data_size) {
             Ok(on_disk::read(data, metadata)?)
         } else {
             Err(DirstateV2ParseError.into())
         }
     }
 
     #[timed]
     pub fn new_v1(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self::empty(on_disk);
         if map.on_disk.is_empty() {
             return Ok((map, None));
         }
 
         let parents = parse_dirstate_entries(
             map.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state().is_tracked();
                 let node = Self::get_or_insert_node(
                     map.on_disk,
                     &mut map.unreachable_bytes,
                     &mut map.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                         ancestor.descendants_with_entry_count += 1
                     },
                 )?;
                 assert!(
                     !node.data.has_entry(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.data = NodeData::Entry(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 map.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     map.nodes_with_copy_source_count += 1
                 }
                 Ok(())
             },
         )?;
         let parents = Some(parents.clone());
 
         Ok((map, parents))
     }
 
     /// Assuming dirstate-v2 format, returns whether the next write should
     /// append to the existing data file that contains `self.on_disk` (true),
     /// or create a new data file from scratch (false).
     pub(super) fn write_should_append(&self) -> bool {
         let ratio = self.unreachable_bytes as f32 / self.on_disk.len() as f32;
         ratio < ACCEPTABLE_UNREACHABLE_BYTES_RATIO
     }
 
     fn get_node<'tree>(
         &'tree self,
         path: &HgPath,
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         let mut children = self.root.as_ref();
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children.get(component, self.on_disk)? {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = child.children(self.on_disk)?;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Result<Option<&'tree mut Node<'on_disk>>, DirstateV2ParseError> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children
                 .make_mut(on_disk, unreachable_bytes)?
                 .get_mut(component)
             {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = &mut child.children;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     pub(super) fn get_or_insert<'tree, 'path>(
         &'tree mut self,
         path: &HgPath,
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |_| {},
         )
     }
 
     fn get_or_insert_node<'tree, 'path>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
             let (_, child_node) = child_nodes
                 .make_mut(on_disk, unreachable_bytes)?
                 .raw_entry_mut()
                 .from_key(ancestor_path.base_name())
                 .or_insert_with(|| (to_cow(ancestor_path), Node::default()));
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return Ok(child_node);
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
         old_state: Option<EntryState>,
         new_entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
         let had_entry = old_state.is_some();
         let was_tracked = old_state.map_or(false, |s| s.is_tracked());
         let tracked_count_increment =
             match (was_tracked, new_entry.state().is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 if !had_entry {
                     ancestor.descendants_with_entry_count += 1;
                 }
 
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         )?;
         if !had_entry {
             self.nodes_with_entry_count += 1
         }
         node.data = NodeData::Entry(new_entry);
         Ok(())
     }
 
     fn iter_nodes<'tree>(
         &'tree self,
     ) -> impl Iterator<
         Item = Result<NodeRef<'tree, 'on_disk>, DirstateV2ParseError>,
     > + 'tree {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.as_ref().iter();
         std::iter::from_fn(move || {
             while let Some(child_node) = iter.next() {
                 let children = match child_node.children(self.on_disk) {
                     Ok(children) => children,
                     Err(error) => return Some(Err(error)),
                 };
                 // Pseudo-recursion
                 let new_iter = children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(Ok(child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     fn count_dropped_path(unreachable_bytes: &mut u32, path: &Cow<HgPath>) {
         if let Cow::Borrowed(path) = path {
             *unreachable_bytes += path.len() as u32
         }
     }
 }
 
 /// Like `Iterator::filter_map`, but over a fallible iterator of `Result`s.
 ///
 /// The callback is only called for incoming `Ok` values. Errors are passed
 /// through as-is. In order to let it use the `?` operator the callback is
 /// expected to return a `Result` of `Option`, instead of an `Option` of
 /// `Result`.
 fn filter_map_results<'a, I, F, A, B, E>(
     iter: I,
     f: F,
 ) -> impl Iterator<Item = Result<B, E>> + 'a
 where
     I: Iterator<Item = Result<A, E>> + 'a,
     F: Fn(A) -> Result<Option<B>, E> + 'a,
 {
     iter.filter_map(move |result| match result {
         Ok(node) => f(node).transpose(),
         Err(e) => Some(Err(e)),
     })
 }
 
 impl OwningDirstateMap {
     pub fn clear(&mut self) {
-        let map = self.get_map_mut();
-        map.root = Default::default();
-        map.nodes_with_entry_count = 0;
-        map.nodes_with_copy_source_count = 0;
+        self.with_dmap_mut(|map| {
+            map.root = Default::default();
+            map.nodes_with_entry_count = 0;
+            map.nodes_with_copy_source_count = 0;
+        });
     }
 
     pub fn set_entry(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        map.get_or_insert(&filename)?.data = NodeData::Entry(entry);
-        Ok(())
+        self.with_dmap_mut(|map| {
+            map.get_or_insert(&filename)?.data = NodeData::Entry(entry);
+            Ok(())
+        })
     }
 
     pub fn add_file(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
     ) -> Result<(), DirstateError> {
         let old_state = self.get(filename)?.map(|e| e.state());
-        let map = self.get_map_mut();
-        Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        self.with_dmap_mut(|map| {
+            Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        })
     }
 
     pub fn remove_file(
         &mut self,
         filename: &HgPath,
         in_merge: bool,
     ) -> Result<(), DirstateError> {
         let old_entry_opt = self.get(filename)?;
         let old_state = old_entry_opt.map(|e| e.state());
         let mut size = 0;
         if in_merge {
             // XXX we should not be able to have 'm' state and 'FROM_P2' if not
             // during a merge. So I (marmoute) am not sure we need the
             // conditionnal at all. Adding double checking this with assert
             // would be nice.
             if let Some(old_entry) = old_entry_opt {
                 // backup the previous state
                 if old_entry.state() == EntryState::Merged {
                     size = SIZE_NON_NORMAL;
                 } else if old_entry.state() == EntryState::Normal
                     && old_entry.size() == SIZE_FROM_OTHER_PARENT
                 {
                     // other parent
                     size = SIZE_FROM_OTHER_PARENT;
                 }
             }
         }
         if size == 0 {
             self.copy_map_remove(filename)?;
         }
-        let map = self.get_map_mut();
-        let entry = DirstateEntry::new_removed(size);
-        Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        self.with_dmap_mut(|map| {
+            let entry = DirstateEntry::new_removed(size);
+            Ok(map.add_or_remove_file(filename, old_state, entry)?)
+        })
     }
 
     pub fn drop_entry_and_copy_source(
         &mut self,
         filename: &HgPath,
     ) -> Result<(), DirstateError> {
         let was_tracked = self
             .get(filename)?
             .map_or(false, |e| e.state().is_tracked());
-        let map = self.get_map_mut();
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
             had_copy_source: bool,
         }
 
         /// If this returns `Ok(Some((dropped, removed)))`, then
         ///
         /// * `dropped` is about the leaf node that was at `filename`
         /// * `removed` is whether this particular level of recursion just
         ///   removed a node in `nodes`.
         fn recur<'on_disk>(
             on_disk: &'on_disk [u8],
             unreachable_bytes: &mut u32,
             nodes: &mut ChildNodes<'on_disk>,
             path: &HgPath,
         ) -> Result<Option<(Dropped, bool)>, DirstateV2ParseError> {
             let (first_path_component, rest_of_path) =
                 path.split_first_component();
             let nodes = nodes.make_mut(on_disk, unreachable_bytes)?;
             let node = if let Some(node) = nodes.get_mut(first_path_component)
             {
                 node
             } else {
                 return Ok(None);
             };
             let dropped;
             if let Some(rest) = rest_of_path {
                 if let Some((d, removed)) = recur(
                     on_disk,
                     unreachable_bytes,
                     &mut node.children,
                     rest,
                 )? {
                     dropped = d;
                     if dropped.had_entry {
-                        node.descendants_with_entry_count -= 1;
+                        node.descendants_with_entry_count = node
+                            .descendants_with_entry_count
+                            .checked_sub(1)
+                            .expect(
+                                "descendants_with_entry_count should be >= 0",
+                            );
                     }
                     if dropped.was_tracked {
-                        node.tracked_descendants_count -= 1;
+                        node.tracked_descendants_count = node
+                            .tracked_descendants_count
+                            .checked_sub(1)
+                            .expect(
+                                "tracked_descendants_count should be >= 0",
+                            );
                     }
 
                     // Directory caches must be invalidated when removing a
                     // child node
                     if removed {
                         if let NodeData::CachedDirectory { .. } = &node.data {
                             node.data = NodeData::None
                         }
                     }
                 } else {
                     return Ok(None);
                 }
             } else {
-                let had_entry = node.data.has_entry();
+                let entry = node.data.as_entry();
+                let was_tracked = entry.map_or(false, |entry| entry.tracked());
+                let had_entry = entry.is_some();
                 if had_entry {
                     node.data = NodeData::None
                 }
+                let mut had_copy_source = false;
                 if let Some(source) = &node.copy_source {
                     DirstateMap::count_dropped_path(unreachable_bytes, source);
+                    had_copy_source = true;
                     node.copy_source = None
                 }
                 dropped = Dropped {
-                    was_tracked: node
-                        .data
-                        .as_entry()
-                        .map_or(false, |entry| entry.state().is_tracked()),
+                    was_tracked,
                     had_entry,
-                    had_copy_source: node.copy_source.take().is_some(),
+                    had_copy_source,
                 };
             }
             // After recursion, for both leaf (rest_of_path is None) nodes and
             // parent nodes, remove a node if it just became empty.
             let remove = !node.data.has_entry()
                 && node.copy_source.is_none()
                 && node.children.is_empty();
             if remove {
                 let (key, _) =
                     nodes.remove_entry(first_path_component).unwrap();
                 DirstateMap::count_dropped_path(
                     unreachable_bytes,
                     key.full_path(),
                 )
             }
             Ok(Some((dropped, remove)))
         }
 
-        if let Some((dropped, _removed)) = recur(
-            map.on_disk,
-            &mut map.unreachable_bytes,
-            &mut map.root,
-            filename,
-        )? {
-            if dropped.had_entry {
-                map.nodes_with_entry_count -= 1
+        self.with_dmap_mut(|map| {
+            if let Some((dropped, _removed)) = recur(
+                map.on_disk,
+                &mut map.unreachable_bytes,
+                &mut map.root,
+                filename,
+            )? {
+                if dropped.had_entry {
+                    map.nodes_with_entry_count = map
+                        .nodes_with_entry_count
+                        .checked_sub(1)
+                        .expect("nodes_with_entry_count should be >= 0");
+                }
+                if dropped.had_copy_source {
+                    map.nodes_with_copy_source_count = map
+                        .nodes_with_copy_source_count
+                        .checked_sub(1)
+                        .expect("nodes_with_copy_source_count should be >= 0");
+                }
+            } else {
+                debug_assert!(!was_tracked);
             }
-            if dropped.had_copy_source {
-                map.nodes_with_copy_source_count -= 1
-            }
-        } else {
-            debug_assert!(!was_tracked);
-        }
-        Ok(())
+            Ok(())
+        })
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
-        let map = self.get_map_mut();
-        if let Some(node) = map.get_node(directory)? {
-            // A node without a `DirstateEntry` was created to hold child
-            // nodes, and is therefore a directory.
-            let state = node.state()?;
-            Ok(state.is_none() && node.tracked_descendants_count() > 0)
-        } else {
-            Ok(false)
-        }
+        self.with_dmap_mut(|map| {
+            if let Some(node) = map.get_node(directory)? {
+                // A node without a `DirstateEntry` was created to hold child
+                // nodes, and is therefore a directory.
+                let state = node.state()?;
+                Ok(state.is_none() && node.tracked_descendants_count() > 0)
+            } else {
+                Ok(false)
+            }
+        })
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
-        let map = self.get_map_mut();
-        if let Some(node) = map.get_node(directory)? {
-            // A node without a `DirstateEntry` was created to hold child
-            // nodes, and is therefore a directory.
-            let state = node.state()?;
-            Ok(state.is_none() && node.descendants_with_entry_count() > 0)
-        } else {
-            Ok(false)
-        }
+        self.with_dmap_mut(|map| {
+            if let Some(node) = map.get_node(directory)? {
+                // A node without a `DirstateEntry` was created to hold child
+                // nodes, and is therefore a directory.
+                let state = node.state()?;
+                Ok(state.is_none() && node.descendants_with_entry_count() > 0)
+            } else {
+                Ok(false)
+            }
+        })
     }
 
     #[timed]
     pub fn pack_v1(
         &self,
         parents: DirstateParents,
     ) -> Result<Vec<u8>, DirstateError> {
         let map = self.get_map();
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for node in map.iter_nodes() {
             let node = node?;
             if node.entry()?.is_some() {
                 size += packed_entry_size(
                     node.full_path(map.on_disk)?,
                     node.copy_source(map.on_disk)?,
                 );
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         for node in map.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 pack_entry(
                     node.full_path(map.on_disk)?,
                     &entry,
                     node.copy_source(map.on_disk)?,
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     /// Returns new data and metadata together with whether that data should be
     /// appended to the existing data file whose content is at
     /// `map.on_disk` (true), instead of written to a new data file
     /// (false).
     #[timed]
     pub fn pack_v2(
         &self,
         can_append: bool,
     ) -> Result<(Vec<u8>, on_disk::TreeMetadata, bool), DirstateError> {
         let map = self.get_map();
         on_disk::write(map, can_append)
     }
 
-    pub fn status<'a>(
-        &'a mut self,
-        matcher: &'a (dyn Matcher + Sync),
+    /// `callback` allows the caller to process and do something with the
+    /// results of the status. This is needed to do so efficiently (i.e.
+    /// without cloning the `DirstateStatus` object with its paths) because
+    /// we need to borrow from `Self`.
+    pub fn with_status<R>(
+        &mut self,
+        matcher: &(dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
-    ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
-    {
-        let map = self.get_map_mut();
-        super::status::status(map, matcher, root_dir, ignore_files, options)
+        callback: impl for<'r> FnOnce(
+            Result<(DirstateStatus<'r>, Vec<PatternFileWarning>), StatusError>,
+        ) -> R,
+    ) -> R {
+        self.with_dmap_mut(|map| {
+            callback(super::status::status(
+                map,
+                matcher,
+                root_dir,
+                ignore_files,
+                options,
+            ))
+        })
     }
 
     pub fn copy_map_len(&self) -> usize {
         let map = self.get_map();
         map.nodes_with_copy_source_count as usize
     }
 
     pub fn copy_map_iter(&self) -> CopyMapIter<'_> {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             Ok(if let Some(source) = node.copy_source(map.on_disk)? {
                 Some((node.full_path(map.on_disk)?, source))
             } else {
                 None
             })
         }))
     }
 
     pub fn copy_map_contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         let map = self.get_map();
         Ok(if let Some(node) = map.get_node(key)? {
             node.has_copy_source()
         } else {
             false
         })
     }
 
     pub fn copy_map_get(
         &self,
         key: &HgPath,
     ) -> Result<Option<&HgPath>, DirstateV2ParseError> {
         let map = self.get_map();
         if let Some(node) = map.get_node(key)? {
             if let Some(source) = node.copy_source(map.on_disk)? {
                 return Ok(Some(source));
             }
         }
         Ok(None)
     }
 
     pub fn copy_map_remove(
         &mut self,
         key: &HgPath,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        let count = &mut map.nodes_with_copy_source_count;
-        let unreachable_bytes = &mut map.unreachable_bytes;
-        Ok(DirstateMap::get_node_mut(
-            map.on_disk,
-            unreachable_bytes,
-            &mut map.root,
-            key,
-        )?
-        .and_then(|node| {
-            if let Some(source) = &node.copy_source {
-                *count -= 1;
-                DirstateMap::count_dropped_path(unreachable_bytes, source);
-            }
-            node.copy_source.take().map(Cow::into_owned)
-        }))
+        self.with_dmap_mut(|map| {
+            let count = &mut map.nodes_with_copy_source_count;
+            let unreachable_bytes = &mut map.unreachable_bytes;
+            Ok(DirstateMap::get_node_mut(
+                map.on_disk,
+                unreachable_bytes,
+                &mut map.root,
+                key,
+            )?
+            .and_then(|node| {
+                if let Some(source) = &node.copy_source {
+                    *count -= 1;
+                    DirstateMap::count_dropped_path(unreachable_bytes, source);
+                }
+                node.copy_source.take().map(Cow::into_owned)
+            }))
+        })
     }
 
     pub fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
-        let map = self.get_map_mut();
-        let node = DirstateMap::get_or_insert_node(
-            map.on_disk,
-            &mut map.unreachable_bytes,
-            &mut map.root,
-            &key,
-            WithBasename::to_cow_owned,
-            |_ancestor| {},
-        )?;
-        if node.copy_source.is_none() {
-            map.nodes_with_copy_source_count += 1
-        }
-        Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
+        self.with_dmap_mut(|map| {
+            let node = DirstateMap::get_or_insert_node(
+                map.on_disk,
+                &mut map.unreachable_bytes,
+                &mut map.root,
+                &key,
+                WithBasename::to_cow_owned,
+                |_ancestor| {},
+            )?;
+            if node.copy_source.is_none() {
+                map.nodes_with_copy_source_count += 1
+            }
+            Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
+        })
     }
 
     pub fn len(&self) -> usize {
         let map = self.get_map();
         map.nodes_with_entry_count as usize
     }
 
     pub fn contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(self.get(key)?.is_some())
     }
 
     pub fn get(
         &self,
         key: &HgPath,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         let map = self.get_map();
         Ok(if let Some(node) = map.get_node(key)? {
             node.entry()?
         } else {
             None
         })
     }
 
     pub fn iter(&self) -> StateMapIter<'_> {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             Ok(if let Some(entry) = node.entry()? {
                 Some((node.full_path(map.on_disk)?, entry))
             } else {
                 None
             })
         }))
     }
 
     pub fn iter_tracked_dirs(
         &mut self,
     ) -> Result<
         Box<
             dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>>
                 + Send
                 + '_,
         >,
         DirstateError,
     > {
-        let map = self.get_map_mut();
+        let map = self.get_map();
         let on_disk = map.on_disk;
         Ok(Box::new(filter_map_results(
             map.iter_nodes(),
             move |node| {
                 Ok(if node.tracked_descendants_count() > 0 {
                     Some(node.full_path(on_disk)?)
                 } else {
                     None
                 })
             },
         )))
     }
 
     pub fn debug_iter(
         &self,
         all: bool,
     ) -> Box<
         dyn Iterator<
                 Item = Result<
                     (&HgPath, (u8, i32, i32, i32)),
                     DirstateV2ParseError,
                 >,
             > + Send
             + '_,
     > {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             let debug_tuple = if let Some(entry) = node.entry()? {
                 entry.debug_tuple()
             } else if !all {
                 return Ok(None);
             } else if let Some(mtime) = node.cached_directory_mtime()? {
                 (b' ', 0, -1, mtime.truncated_seconds() as i32)
             } else {
                 (b' ', 0, -1, -1)
             };
             Ok(Some((node.full_path(map.on_disk)?, debug_tuple)))
         }))
     }
 }

rust/hg-core/src/dirstate_tree/owning.rs

@@ -1,105 +1,89 b''
+use crate::{DirstateError, DirstateParents};
+
 use super::dirstate_map::DirstateMap;
-use stable_deref_trait::StableDeref;
 use std::ops::Deref;
 
+use ouroboros::self_referencing;
+
 /// Keep a `DirstateMap<'on_disk>` next to the `on_disk` buffer that it
 /// borrows.
-///
-/// This is similar to [`OwningRef`] which is more limited because it
-/// represents exactly one `&T` reference next to the value it borrows, as
-/// opposed to a struct that may contain an arbitrary number of references in
-/// arbitrarily-nested data structures.
-///
-/// [`OwningRef`]: https://docs.rs/owning_ref/0.4.1/owning_ref/struct.OwningRef.html
+#[self_referencing]
 pub struct OwningDirstateMap {
-    /// Owned handle to a bytes buffer with a stable address.
-    ///
-    /// See <https://docs.rs/owning_ref/0.4.1/owning_ref/trait.StableAddress.html>.
     on_disk: Box<dyn Deref<Target = [u8]> + Send>,
-
-    /// Pointer for `Box<DirstateMap<'on_disk>>`, typed-erased because the
-    /// language cannot represent a lifetime referencing a sibling field.
-    /// This is not quite a self-referencial struct (moving this struct is not
-    /// a problem as it doesn’t change the address of the bytes buffer owned
-    /// by `on_disk`) but touches similar borrow-checker limitations.
-    ptr: *mut (),
+    #[borrows(on_disk)]
+    #[covariant]
+    map: DirstateMap<'this>,
 }
 
 impl OwningDirstateMap {
     pub fn new_empty<OnDisk>(on_disk: OnDisk) -> Self
     where
-        OnDisk: Deref<Target = [u8]> + StableDeref + Send + 'static,
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
     {
         let on_disk = Box::new(on_disk);
-        let bytes: &'_ [u8] = &on_disk;
-        let map = DirstateMap::empty(bytes);
 
-        // Like in `bytes` above, this `'_` lifetime parameter borrows from
-        // the bytes buffer owned by `on_disk`.
-        let ptr: *mut DirstateMap<'_> = Box::into_raw(Box::new(map));
-
-        // Erase the pointed type entirely in order to erase the lifetime.
-        let ptr: *mut () = ptr.cast();
-
-        Self { on_disk, ptr }
+        OwningDirstateMapBuilder {
+            on_disk,
+            map_builder: |bytes| DirstateMap::empty(&bytes),
+        }
+        .build()
     }
 
-    pub fn get_pair_mut<'a>(
-        &'a mut self,
-    ) -> (&'a [u8], &'a mut DirstateMap<'a>) {
-        // SAFETY: We cast the type-erased pointer back to the same type it had
-        // in `new`, except with a different lifetime parameter. This time we
-        // connect the lifetime to that of `self`. This cast is valid because
-        // `self` owns the same `on_disk` whose buffer `DirstateMap`
-        // references. That buffer has a stable memory address because our
-        // `Self::new_empty` counstructor requires `StableDeref`.
-        let ptr: *mut DirstateMap<'a> = self.ptr.cast();
-        // SAFETY: we dereference that pointer, connecting the lifetime of the
-        // new `&mut` to that of `self`. This is valid because the
-        // raw pointer is to a boxed value, and `self` owns that box.
-        (&self.on_disk, unsafe { &mut *ptr })
-    }
+    pub fn new_v1<OnDisk>(
+        on_disk: OnDisk,
+    ) -> Result<(Self, DirstateParents), DirstateError>
+    where
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
+    {
+        let on_disk = Box::new(on_disk);
+        let mut parents = DirstateParents::NULL;
 
-    pub fn get_map_mut<'a>(&'a mut self) -> &'a mut DirstateMap<'a> {
-        self.get_pair_mut().1
+        Ok((
+            OwningDirstateMapTryBuilder {
+                on_disk,
+                map_builder: |bytes| {
+                    DirstateMap::new_v1(&bytes).map(|(dmap, p)| {
+                        parents = p.unwrap_or(DirstateParents::NULL);
+                        dmap
+                    })
+                },
+            }
+            .try_build()?,
+            parents,
+        ))
     }
 
-    pub fn get_map<'a>(&'a self) -> &'a DirstateMap<'a> {
-        // SAFETY: same reasoning as in `get_pair_mut` above.
-        let ptr: *mut DirstateMap<'a> = self.ptr.cast();
-        unsafe { &*ptr }
+    pub fn new_v2<OnDisk>(
+        on_disk: OnDisk,
+        data_size: usize,
+        metadata: &[u8],
+    ) -> Result<Self, DirstateError>
+    where
+        OnDisk: Deref<Target = [u8]> + Send + 'static,
+    {
+        let on_disk = Box::new(on_disk);
+
+        OwningDirstateMapTryBuilder {
+            on_disk,
+            map_builder: |bytes| {
+                DirstateMap::new_v2(&bytes, data_size, metadata)
+            },
+        }
+        .try_build()
     }
 
-    pub fn on_disk<'a>(&'a self) -> &'a [u8] {
-        &self.on_disk
+    pub fn with_dmap_mut<R>(
+        &mut self,
+        f: impl FnOnce(&mut DirstateMap) -> R,
+    ) -> R {
+        self.with_map_mut(f)
+    }
+
+    pub fn get_map(&self) -> &DirstateMap {
+        self.borrow_map()
+    }
+
+    pub fn on_disk(&self) -> &[u8] {
+        self.borrow_on_disk()
     }
 }
-
-impl Drop for OwningDirstateMap {
-    fn drop(&mut self) {
-        // Silence a "field is never read" warning, and demonstrate that this
-        // value is still alive.
-        let _: &Box<dyn Deref<Target = [u8]> + Send> = &self.on_disk;
-        // SAFETY: this cast is the same as in `get_mut`, and is valid for the
-        // same reason. `self.on_disk` still exists at this point, drop glue
-        // will drop it implicitly after this `drop` method returns.
-        let ptr: *mut DirstateMap<'_> = self.ptr.cast();
-        // SAFETY: `Box::from_raw` takes ownership of the box away from `self`.
-        // This is fine because drop glue does nothing for `*mut ()` and we’re
-        // in `drop`, so `get` and `get_mut` cannot be called again.
-        unsafe { drop(Box::from_raw(ptr)) }
-    }
-}
-
-fn _static_assert_is_send<T: Send>() {}
-
-fn _static_assert_fields_are_send() {
-    _static_assert_is_send::<Box<DirstateMap<'_>>>();
-}
-
-// SAFETY: we don’t get this impl implicitly because `*mut (): !Send` because
-// thread-safety of raw pointers is unknown in the general case. However this
-// particular raw pointer represents a `Box<DirstateMap<'on_disk>>` that we
-// own. Since that `Box` is `Send` as shown in above, it is sound to mark
-// this struct as `Send` too.
-unsafe impl Send for OwningDirstateMap {}

rust/hg-core/src/dirstate_tree/status.rs

@@ -1,848 +1,849 b''
 use crate::dirstate::entry::TruncatedTimestamp;
 use crate::dirstate::status::IgnoreFnType;
 use crate::dirstate::status::StatusPath;
 use crate::dirstate_tree::dirstate_map::BorrowedPath;
 use crate::dirstate_tree::dirstate_map::ChildNodesRef;
 use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::dirstate_map::NodeData;
 use crate::dirstate_tree::dirstate_map::NodeRef;
 use crate::dirstate_tree::on_disk::DirstateV2ParseError;
 use crate::matchers::get_ignore_function;
 use crate::matchers::Matcher;
 use crate::utils::files::get_bytes_from_os_string;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::BadMatch;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::HgPathBuf;
 use crate::HgPathCow;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
 use micro_timer::timed;
 use rayon::prelude::*;
 use sha1::{Digest, Sha1};
 use std::borrow::Cow;
 use std::io;
 use std::path::Path;
 use std::path::PathBuf;
 use std::sync::Mutex;
 use std::time::SystemTime;
 
 /// Returns the status of the working directory compared to its parent
 /// changeset.
 ///
 /// This algorithm is based on traversing the filesystem tree (`fs` in function
 /// and variable names) and dirstate tree at the same time. The core of this
 /// traversal is the recursive `traverse_fs_directory_and_dirstate` function
 /// and its use of `itertools::merge_join_by`. When reaching a path that only
 /// exists in one of the two trees, depending on information requested by
 /// `options` we may need to traverse the remaining subtree.
 #[timed]
-pub fn status<'tree, 'on_disk: 'tree>(
-    dmap: &'tree mut DirstateMap<'on_disk>,
+pub fn status<'dirstate>(
+    dmap: &'dirstate mut DirstateMap,
     matcher: &(dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
-) -> Result<(DirstateStatus<'on_disk>, Vec<PatternFileWarning>), StatusError> {
+) -> Result<(DirstateStatus<'dirstate>, Vec<PatternFileWarning>), StatusError>
+{
     // Force the global rayon threadpool to not exceed 16 concurrent threads.
     // This is a stop-gap measure until we figure out why using more than 16
     // threads makes `status` slower for each additional thread.
     // We use `ok()` in case the global threadpool has already been
     // instantiated in `rhg` or some other caller.
     // TODO find the underlying cause and fix it, then remove this.
     rayon::ThreadPoolBuilder::new()
         .num_threads(16)
         .build_global()
         .ok();
 
     let (ignore_fn, warnings, patterns_changed): (IgnoreFnType, _, _) =
         if options.list_ignored || options.list_unknown {
             let mut hasher = Sha1::new();
             let (ignore_fn, warnings) = get_ignore_function(
                 ignore_files,
                 &root_dir,
                 &mut |pattern_bytes| hasher.update(pattern_bytes),
             )?;
             let new_hash = *hasher.finalize().as_ref();
             let changed = new_hash != dmap.ignore_patterns_hash;
             dmap.ignore_patterns_hash = new_hash;
             (ignore_fn, warnings, Some(changed))
         } else {
             (Box::new(|&_| true), vec![], None)
         };
 
     let filesystem_time_at_status_start =
         filesystem_now(&root_dir).ok().map(TruncatedTimestamp::from);
 
     // If the repository is under the current directory, prefer using a
     // relative path, so the kernel needs to traverse fewer directory in every
     // call to `read_dir` or `symlink_metadata`.
     // This is effective in the common case where the current directory is the
     // repository root.
 
     // TODO: Better yet would be to use libc functions like `openat` and
     // `fstatat` to remove such repeated traversals entirely, but the standard
     // library does not provide APIs based on those.
     // Maybe with a crate like https://crates.io/crates/openat instead?
     let root_dir = if let Some(relative) = std::env::current_dir()
         .ok()
         .and_then(|cwd| root_dir.strip_prefix(cwd).ok())
     {
         relative
     } else {
         &root_dir
     };
 
     let outcome = DirstateStatus {
         filesystem_time_at_status_start,
         ..Default::default()
     };
     let common = StatusCommon {
         dmap,
         options,
         matcher,
         ignore_fn,
         outcome: Mutex::new(outcome),
         ignore_patterns_have_changed: patterns_changed,
         new_cachable_directories: Default::default(),
         outated_cached_directories: Default::default(),
         filesystem_time_at_status_start,
     };
     let is_at_repo_root = true;
     let hg_path = &BorrowedPath::OnDisk(HgPath::new(""));
     let has_ignored_ancestor = false;
     let root_cached_mtime = None;
     let root_dir_metadata = None;
     // If the path we have for the repository root is a symlink, do follow it.
     // (As opposed to symlinks within the working directory which are not
     // followed, using `std::fs::symlink_metadata`.)
     common.traverse_fs_directory_and_dirstate(
         has_ignored_ancestor,
         dmap.root.as_ref(),
         hg_path,
         &root_dir,
         root_dir_metadata,
         root_cached_mtime,
         is_at_repo_root,
     )?;
     let mut outcome = common.outcome.into_inner().unwrap();
     let new_cachable = common.new_cachable_directories.into_inner().unwrap();
     let outdated = common.outated_cached_directories.into_inner().unwrap();
 
     outcome.dirty = common.ignore_patterns_have_changed == Some(true)
         || !outdated.is_empty()
         || !new_cachable.is_empty();
 
     // Remove outdated mtimes before adding new mtimes, in case a given
     // directory is both
     for path in &outdated {
         let node = dmap.get_or_insert(path)?;
         if let NodeData::CachedDirectory { .. } = &node.data {
             node.data = NodeData::None
         }
     }
     for (path, mtime) in &new_cachable {
         let node = dmap.get_or_insert(path)?;
         match &node.data {
             NodeData::Entry(_) => {} // Don’t overwrite an entry
             NodeData::CachedDirectory { .. } | NodeData::None => {
                 node.data = NodeData::CachedDirectory { mtime: *mtime }
             }
         }
     }
 
     Ok((outcome, warnings))
 }
 
 /// Bag of random things needed by various parts of the algorithm. Reduces the
 /// number of parameters passed to functions.
 struct StatusCommon<'a, 'tree, 'on_disk: 'tree> {
     dmap: &'tree DirstateMap<'on_disk>,
     options: StatusOptions,
     matcher: &'a (dyn Matcher + Sync),
     ignore_fn: IgnoreFnType<'a>,
     outcome: Mutex<DirstateStatus<'on_disk>>,
     new_cachable_directories:
         Mutex<Vec<(Cow<'on_disk, HgPath>, TruncatedTimestamp)>>,
     outated_cached_directories: Mutex<Vec<Cow<'on_disk, HgPath>>>,
 
     /// Whether ignore files like `.hgignore` have changed since the previous
     /// time a `status()` call wrote their hash to the dirstate. `None` means
     /// we don’t know as this run doesn’t list either ignored or uknown files
     /// and therefore isn’t reading `.hgignore`.
     ignore_patterns_have_changed: Option<bool>,
 
     /// The current time at the start of the `status()` algorithm, as measured
     /// and possibly truncated by the filesystem.
     filesystem_time_at_status_start: Option<TruncatedTimestamp>,
 }
 
 enum Outcome {
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Ignored,
     Unknown,
     Unsure,
 }
 
 impl<'a, 'tree, 'on_disk> StatusCommon<'a, 'tree, 'on_disk> {
     fn push_outcome(
         &self,
         which: Outcome,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         let path = dirstate_node
             .full_path_borrowed(self.dmap.on_disk)?
             .detach_from_tree();
         let copy_source = if self.options.list_copies {
             dirstate_node
                 .copy_source_borrowed(self.dmap.on_disk)?
                 .map(|source| source.detach_from_tree())
         } else {
             None
         };
         self.push_outcome_common(which, path, copy_source);
         Ok(())
     }
 
     fn push_outcome_without_copy_source(
         &self,
         which: Outcome,
         path: &BorrowedPath<'_, 'on_disk>,
     ) {
         self.push_outcome_common(which, path.detach_from_tree(), None)
     }
 
     fn push_outcome_common(
         &self,
         which: Outcome,
         path: HgPathCow<'on_disk>,
         copy_source: Option<HgPathCow<'on_disk>>,
     ) {
         let mut outcome = self.outcome.lock().unwrap();
         let vec = match which {
             Outcome::Modified => &mut outcome.modified,
             Outcome::Added => &mut outcome.added,
             Outcome::Removed => &mut outcome.removed,
             Outcome::Deleted => &mut outcome.deleted,
             Outcome::Clean => &mut outcome.clean,
             Outcome::Ignored => &mut outcome.ignored,
             Outcome::Unknown => &mut outcome.unknown,
             Outcome::Unsure => &mut outcome.unsure,
         };
         vec.push(StatusPath { path, copy_source });
     }
 
     fn read_dir(
         &self,
         hg_path: &HgPath,
         fs_path: &Path,
         is_at_repo_root: bool,
     ) -> Result<Vec<DirEntry>, ()> {
         DirEntry::read_dir(fs_path, is_at_repo_root)
             .map_err(|error| self.io_error(error, hg_path))
     }
 
     fn io_error(&self, error: std::io::Error, hg_path: &HgPath) {
         let errno = error.raw_os_error().expect("expected real OS error");
         self.outcome
             .lock()
             .unwrap()
             .bad
             .push((hg_path.to_owned().into(), BadMatch::OsError(errno)))
     }
 
     fn check_for_outdated_directory_cache(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if self.ignore_patterns_have_changed == Some(true)
             && dirstate_node.cached_directory_mtime()?.is_some()
         {
             self.outated_cached_directories.lock().unwrap().push(
                 dirstate_node
                     .full_path_borrowed(self.dmap.on_disk)?
                     .detach_from_tree(),
             )
         }
         Ok(())
     }
 
     /// If this returns true, we can get accurate results by only using
     /// `symlink_metadata` for child nodes that exist in the dirstate and don’t
     /// need to call `read_dir`.
     fn can_skip_fs_readdir(
         &self,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<TruncatedTimestamp>,
     ) -> bool {
         if !self.options.list_unknown && !self.options.list_ignored {
             // All states that we care about listing have corresponding
             // dirstate entries.
             // This happens for example with `hg status -mard`.
             return true;
         }
         if !self.options.list_ignored
             && self.ignore_patterns_have_changed == Some(false)
         {
             if let Some(cached_mtime) = cached_directory_mtime {
                 // The dirstate contains a cached mtime for this directory, set
                 // by a previous run of the `status` algorithm which found this
                 // directory eligible for `read_dir` caching.
                 if let Some(meta) = directory_metadata {
                     if cached_mtime
                         .likely_equal_to_mtime_of(meta)
                         .unwrap_or(false)
                     {
                         // The mtime of that directory has not changed
                         // since then, which means that the results of
                         // `read_dir` should also be unchanged.
                         return true;
                     }
                 }
             }
         }
         false
     }
 
     /// Returns whether all child entries of the filesystem directory have a
     /// corresponding dirstate node or are ignored.
     fn traverse_fs_directory_and_dirstate(
         &self,
         has_ignored_ancestor: bool,
         dirstate_nodes: ChildNodesRef<'tree, 'on_disk>,
         directory_hg_path: &BorrowedPath<'tree, 'on_disk>,
         directory_fs_path: &Path,
         directory_metadata: Option<&std::fs::Metadata>,
         cached_directory_mtime: Option<TruncatedTimestamp>,
         is_at_repo_root: bool,
     ) -> Result<bool, DirstateV2ParseError> {
         if self.can_skip_fs_readdir(directory_metadata, cached_directory_mtime)
         {
             dirstate_nodes
                 .par_iter()
                 .map(|dirstate_node| {
                     let fs_path = directory_fs_path.join(get_path_from_bytes(
                         dirstate_node.base_name(self.dmap.on_disk)?.as_bytes(),
                     ));
                     match std::fs::symlink_metadata(&fs_path) {
                         Ok(fs_metadata) => self.traverse_fs_and_dirstate(
                             &fs_path,
                             &fs_metadata,
                             dirstate_node,
                             has_ignored_ancestor,
                         ),
                         Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
                             self.traverse_dirstate_only(dirstate_node)
                         }
                         Err(error) => {
                             let hg_path =
                                 dirstate_node.full_path(self.dmap.on_disk)?;
                             Ok(self.io_error(error, hg_path))
                         }
                     }
                 })
                 .collect::<Result<_, _>>()?;
 
             // We don’t know, so conservatively say this isn’t the case
             let children_all_have_dirstate_node_or_are_ignored = false;
 
             return Ok(children_all_have_dirstate_node_or_are_ignored);
         }
 
         let mut fs_entries = if let Ok(entries) = self.read_dir(
             directory_hg_path,
             directory_fs_path,
             is_at_repo_root,
         ) {
             entries
         } else {
             // Treat an unreadable directory (typically because of insufficient
             // permissions) like an empty directory. `self.read_dir` has
             // already called `self.io_error` so a warning will be emitted.
             Vec::new()
         };
 
         // `merge_join_by` requires both its input iterators to be sorted:
 
         let dirstate_nodes = dirstate_nodes.sorted();
         // `sort_unstable_by_key` doesn’t allow keys borrowing from the value:
         // https://github.com/rust-lang/rust/issues/34162
         fs_entries.sort_unstable_by(|e1, e2| e1.base_name.cmp(&e2.base_name));
 
         // Propagate here any error that would happen inside the comparison
         // callback below
         for dirstate_node in &dirstate_nodes {
             dirstate_node.base_name(self.dmap.on_disk)?;
         }
         itertools::merge_join_by(
             dirstate_nodes,
             &fs_entries,
             |dirstate_node, fs_entry| {
                 // This `unwrap` never panics because we already propagated
                 // those errors above
                 dirstate_node
                     .base_name(self.dmap.on_disk)
                     .unwrap()
                     .cmp(&fs_entry.base_name)
             },
         )
         .par_bridge()
         .map(|pair| {
             use itertools::EitherOrBoth::*;
             let has_dirstate_node_or_is_ignored;
             match pair {
                 Both(dirstate_node, fs_entry) => {
                     self.traverse_fs_and_dirstate(
                         &fs_entry.full_path,
                         &fs_entry.metadata,
                         dirstate_node,
                         has_ignored_ancestor,
                     )?;
                     has_dirstate_node_or_is_ignored = true
                 }
                 Left(dirstate_node) => {
                     self.traverse_dirstate_only(dirstate_node)?;
                     has_dirstate_node_or_is_ignored = true;
                 }
                 Right(fs_entry) => {
                     has_dirstate_node_or_is_ignored = self.traverse_fs_only(
                         has_ignored_ancestor,
                         directory_hg_path,
                         fs_entry,
                     )
                 }
             }
             Ok(has_dirstate_node_or_is_ignored)
         })
         .try_reduce(|| true, |a, b| Ok(a && b))
     }
 
     fn traverse_fs_and_dirstate(
         &self,
         fs_path: &Path,
         fs_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
         has_ignored_ancestor: bool,
     ) -> Result<(), DirstateV2ParseError> {
         self.check_for_outdated_directory_cache(&dirstate_node)?;
         let hg_path = &dirstate_node.full_path_borrowed(self.dmap.on_disk)?;
         let file_type = fs_metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if !file_or_symlink {
             // If we previously had a file here, it was removed (with
             // `hg rm` or similar) or deleted before it could be
             // replaced by a directory or something else.
             self.mark_removed_or_deleted_if_file(&dirstate_node)?;
         }
         if file_type.is_dir() {
             if self.options.collect_traversed_dirs {
                 self.outcome
                     .lock()
                     .unwrap()
                     .traversed
                     .push(hg_path.detach_from_tree())
             }
             let is_ignored = has_ignored_ancestor || (self.ignore_fn)(hg_path);
             let is_at_repo_root = false;
             let children_all_have_dirstate_node_or_are_ignored = self
                 .traverse_fs_directory_and_dirstate(
                     is_ignored,
                     dirstate_node.children(self.dmap.on_disk)?,
                     hg_path,
                     fs_path,
                     Some(fs_metadata),
                     dirstate_node.cached_directory_mtime()?,
                     is_at_repo_root,
                 )?;
             self.maybe_save_directory_mtime(
                 children_all_have_dirstate_node_or_are_ignored,
                 fs_metadata,
                 dirstate_node,
             )?
         } else {
             if file_or_symlink && self.matcher.matches(hg_path) {
                 if let Some(state) = dirstate_node.state()? {
                     match state {
                         EntryState::Added => {
                             self.push_outcome(Outcome::Added, &dirstate_node)?
                         }
                         EntryState::Removed => self
                             .push_outcome(Outcome::Removed, &dirstate_node)?,
                         EntryState::Merged => self
                             .push_outcome(Outcome::Modified, &dirstate_node)?,
                         EntryState::Normal => self
                             .handle_normal_file(&dirstate_node, fs_metadata)?,
                     }
                 } else {
                     // `node.entry.is_none()` indicates a "directory"
                     // node, but the filesystem has a file
                     self.mark_unknown_or_ignored(
                         has_ignored_ancestor,
                         hg_path,
                     );
                 }
             }
 
             for child_node in dirstate_node.children(self.dmap.on_disk)?.iter()
             {
                 self.traverse_dirstate_only(child_node)?
             }
         }
         Ok(())
     }
 
     fn maybe_save_directory_mtime(
         &self,
         children_all_have_dirstate_node_or_are_ignored: bool,
         directory_metadata: &std::fs::Metadata,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if !children_all_have_dirstate_node_or_are_ignored {
             return Ok(());
         }
         // All filesystem directory entries from `read_dir` have a
         // corresponding node in the dirstate, so we can reconstitute the
         // names of those entries without calling `read_dir` again.
 
         // TODO: use let-else here and below when available:
         // https://github.com/rust-lang/rust/issues/87335
         let status_start = if let Some(status_start) =
             &self.filesystem_time_at_status_start
         {
             status_start
         } else {
             return Ok(());
         };
 
         // Although the Rust standard library’s `SystemTime` type
         // has nanosecond precision, the times reported for a
         // directory’s (or file’s) modified time may have lower
         // resolution based on the filesystem (for example ext3
         // only stores integer seconds), kernel (see
         // https://stackoverflow.com/a/14393315/1162888), etc.
         let directory_mtime = if let Ok(option) =
             TruncatedTimestamp::for_reliable_mtime_of(
                 directory_metadata,
                 status_start,
             ) {
             if let Some(directory_mtime) = option {
                 directory_mtime
             } else {
                 // The directory was modified too recently,
                 // don’t cache its `read_dir` results.
                 //
                 // 1. A change to this directory (direct child was
                 //    added or removed) cause its mtime to be set
                 //    (possibly truncated) to `directory_mtime`
                 // 2. This `status` algorithm calls `read_dir`
                 // 3. An other change is made to the same directory is
                 //    made so that calling `read_dir` agin would give
                 //    different results, but soon enough after 1. that
                 //    the mtime stays the same
                 //
                 // On a system where the time resolution poor, this
                 // scenario is not unlikely if all three steps are caused
                 // by the same script.
                 return Ok(());
             }
         } else {
             // OS/libc does not support mtime?
             return Ok(());
         };
         // We’ve observed (through `status_start`) that time has
         // “progressed” since `directory_mtime`, so any further
         // change to this directory is extremely likely to cause a
         // different mtime.
         //
         // Having the same mtime again is not entirely impossible
         // since the system clock is not monotonous. It could jump
         // backward to some point before `directory_mtime`, then a
         // directory change could potentially happen during exactly
         // the wrong tick.
         //
         // We deem this scenario (unlike the previous one) to be
         // unlikely enough in practice.
 
         let is_up_to_date =
             if let Some(cached) = dirstate_node.cached_directory_mtime()? {
                 cached.likely_equal(directory_mtime)
             } else {
                 false
             };
         if !is_up_to_date {
             let hg_path = dirstate_node
                 .full_path_borrowed(self.dmap.on_disk)?
                 .detach_from_tree();
             self.new_cachable_directories
                 .lock()
                 .unwrap()
                 .push((hg_path, directory_mtime))
         }
         Ok(())
     }
 
     /// A file with `EntryState::Normal` in the dirstate was found in the
     /// filesystem
     fn handle_normal_file(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
         fs_metadata: &std::fs::Metadata,
     ) -> Result<(), DirstateV2ParseError> {
         // Keep the low 31 bits
         fn truncate_u64(value: u64) -> i32 {
             (value & 0x7FFF_FFFF) as i32
         }
 
         let entry = dirstate_node
             .entry()?
             .expect("handle_normal_file called with entry-less node");
         let mode_changed =
             || self.options.check_exec && entry.mode_changed(fs_metadata);
         let size = entry.size();
         let size_changed = size != truncate_u64(fs_metadata.len());
         if size >= 0 && size_changed && fs_metadata.file_type().is_symlink() {
             // issue6456: Size returned may be longer due to encryption
             // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
             self.push_outcome(Outcome::Unsure, dirstate_node)?
         } else if dirstate_node.has_copy_source()
             || entry.is_from_other_parent()
             || (size >= 0 && (size_changed || mode_changed()))
         {
             self.push_outcome(Outcome::Modified, dirstate_node)?
         } else {
             let mtime_looks_clean;
             if let Some(dirstate_mtime) = entry.truncated_mtime() {
                 let fs_mtime = TruncatedTimestamp::for_mtime_of(fs_metadata)
                     .expect("OS/libc does not support mtime?");
                 // There might be a change in the future if for example the
                 // internal clock become off while process run, but this is a
                 // case where the issues the user would face
                 // would be a lot worse and there is nothing we
                 // can really do.
                 mtime_looks_clean = fs_mtime.likely_equal(dirstate_mtime)
             } else {
                 // No mtime in the dirstate entry
                 mtime_looks_clean = false
             };
             if !mtime_looks_clean {
                 self.push_outcome(Outcome::Unsure, dirstate_node)?
             } else if self.options.list_clean {
                 self.push_outcome(Outcome::Clean, dirstate_node)?
             }
         }
         Ok(())
     }
 
     /// A node in the dirstate tree has no corresponding filesystem entry
     fn traverse_dirstate_only(
         &self,
         dirstate_node: NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         self.check_for_outdated_directory_cache(&dirstate_node)?;
         self.mark_removed_or_deleted_if_file(&dirstate_node)?;
         dirstate_node
             .children(self.dmap.on_disk)?
             .par_iter()
             .map(|child_node| self.traverse_dirstate_only(child_node))
             .collect()
     }
 
     /// A node in the dirstate tree has no corresponding *file* on the
     /// filesystem
     ///
     /// Does nothing on a "directory" node
     fn mark_removed_or_deleted_if_file(
         &self,
         dirstate_node: &NodeRef<'tree, 'on_disk>,
     ) -> Result<(), DirstateV2ParseError> {
         if let Some(state) = dirstate_node.state()? {
             let path = dirstate_node.full_path(self.dmap.on_disk)?;
             if self.matcher.matches(path) {
                 if let EntryState::Removed = state {
                     self.push_outcome(Outcome::Removed, dirstate_node)?
                 } else {
                     self.push_outcome(Outcome::Deleted, &dirstate_node)?
                 }
             }
         }
         Ok(())
     }
 
     /// Something in the filesystem has no corresponding dirstate node
     ///
     /// Returns whether that path is ignored
     fn traverse_fs_only(
         &self,
         has_ignored_ancestor: bool,
         directory_hg_path: &HgPath,
         fs_entry: &DirEntry,
     ) -> bool {
         let hg_path = directory_hg_path.join(&fs_entry.base_name);
         let file_type = fs_entry.metadata.file_type();
         let file_or_symlink = file_type.is_file() || file_type.is_symlink();
         if file_type.is_dir() {
             let is_ignored =
                 has_ignored_ancestor || (self.ignore_fn)(&hg_path);
             let traverse_children = if is_ignored {
                 // Descendants of an ignored directory are all ignored
                 self.options.list_ignored
             } else {
                 // Descendants of an unknown directory may be either unknown or
                 // ignored
                 self.options.list_unknown || self.options.list_ignored
             };
             if traverse_children {
                 let is_at_repo_root = false;
                 if let Ok(children_fs_entries) = self.read_dir(
                     &hg_path,
                     &fs_entry.full_path,
                     is_at_repo_root,
                 ) {
                     children_fs_entries.par_iter().for_each(|child_fs_entry| {
                         self.traverse_fs_only(
                             is_ignored,
                             &hg_path,
                             child_fs_entry,
                         );
                     })
                 }
             }
             if self.options.collect_traversed_dirs {
                 self.outcome.lock().unwrap().traversed.push(hg_path.into())
             }
             is_ignored
         } else {
             if file_or_symlink {
                 if self.matcher.matches(&hg_path) {
                     self.mark_unknown_or_ignored(
                         has_ignored_ancestor,
                         &BorrowedPath::InMemory(&hg_path),
                     )
                 } else {
                     // We haven’t computed whether this path is ignored. It
                     // might not be, and a future run of status might have a
                     // different matcher that matches it. So treat it as not
                     // ignored. That is, inhibit readdir caching of the parent
                     // directory.
                     false
                 }
             } else {
                 // This is neither a directory, a plain file, or a symlink.
                 // Treat it like an ignored file.
                 true
             }
         }
     }
 
     /// Returns whether that path is ignored
     fn mark_unknown_or_ignored(
         &self,
         has_ignored_ancestor: bool,
         hg_path: &BorrowedPath<'_, 'on_disk>,
     ) -> bool {
         let is_ignored = has_ignored_ancestor || (self.ignore_fn)(&hg_path);
         if is_ignored {
             if self.options.list_ignored {
                 self.push_outcome_without_copy_source(
                     Outcome::Ignored,
                     hg_path,
                 )
             }
         } else {
             if self.options.list_unknown {
                 self.push_outcome_without_copy_source(
                     Outcome::Unknown,
                     hg_path,
                 )
             }
         }
         is_ignored
     }
 }
 
 struct DirEntry {
     base_name: HgPathBuf,
     full_path: PathBuf,
     metadata: std::fs::Metadata,
 }
 
 impl DirEntry {
     /// Returns **unsorted** entries in the given directory, with name and
     /// metadata.
     ///
     /// If a `.hg` sub-directory is encountered:
     ///
     /// * At the repository root, ignore that sub-directory
     /// * Elsewhere, we’re listing the content of a sub-repo. Return an empty
     ///   list instead.
     fn read_dir(path: &Path, is_at_repo_root: bool) -> io::Result<Vec<Self>> {
         // `read_dir` returns a "not found" error for the empty path
         let at_cwd = path == Path::new("");
         let read_dir_path = if at_cwd { Path::new(".") } else { path };
         let mut results = Vec::new();
         for entry in read_dir_path.read_dir()? {
             let entry = entry?;
             let metadata = match entry.metadata() {
                 Ok(v) => v,
                 Err(e) => {
                     // race with file deletion?
                     if e.kind() == std::io::ErrorKind::NotFound {
                         continue;
                     } else {
                         return Err(e);
                     }
                 }
             };
             let file_name = entry.file_name();
             // FIXME don't do this when cached
             if file_name == ".hg" {
                 if is_at_repo_root {
                     // Skip the repo’s own .hg (might be a symlink)
                     continue;
                 } else if metadata.is_dir() {
                     // A .hg sub-directory at another location means a subrepo,
                     // skip it entirely.
                     return Ok(Vec::new());
                 }
             }
             let full_path = if at_cwd {
                 file_name.clone().into()
             } else {
                 entry.path()
             };
             let base_name = get_bytes_from_os_string(file_name).into();
             results.push(DirEntry {
                 base_name,
                 full_path,
                 metadata,
             })
         }
         Ok(results)
     }
 }
 
 /// Return the `mtime` of a temporary file newly-created in the `.hg` directory
 /// of the give repository.
 ///
 /// This is similar to `SystemTime::now()`, with the result truncated to the
 /// same time resolution as other files’ modification times. Using `.hg`
 /// instead of the system’s default temporary directory (such as `/tmp`) makes
 /// it more likely the temporary file is in the same disk partition as contents
 /// of the working directory, which can matter since different filesystems may
 /// store timestamps with different resolutions.
 ///
 /// This may fail, typically if we lack write permissions. In that case we
 /// should continue the `status()` algoritm anyway and consider the current
 /// date/time to be unknown.
 fn filesystem_now(repo_root: &Path) -> Result<SystemTime, io::Error> {
     tempfile::tempfile_in(repo_root.join(".hg"))?
         .metadata()?
         .modified()
 }

rust/hg-core/src/repo.rs

@@ -1,516 +1,509 b''
 use crate::changelog::Changelog;
 use crate::config::{Config, ConfigError, ConfigParseError};
 use crate::dirstate::DirstateParents;
-use crate::dirstate_tree::dirstate_map::DirstateMap;
 use crate::dirstate_tree::on_disk::Docket as DirstateDocket;
 use crate::dirstate_tree::owning::OwningDirstateMap;
 use crate::errors::HgResultExt;
 use crate::errors::{HgError, IoResultExt};
 use crate::lock::{try_with_lock_no_wait, LockError};
 use crate::manifest::{Manifest, Manifestlog};
 use crate::revlog::filelog::Filelog;
 use crate::revlog::revlog::RevlogError;
 use crate::utils::files::get_path_from_bytes;
 use crate::utils::hg_path::HgPath;
 use crate::utils::SliceExt;
 use crate::vfs::{is_dir, is_file, Vfs};
 use crate::{requirements, NodePrefix};
 use crate::{DirstateError, Revision};
 use std::cell::{Ref, RefCell, RefMut};
 use std::collections::HashSet;
 use std::io::Seek;
 use std::io::SeekFrom;
 use std::io::Write as IoWrite;
 use std::path::{Path, PathBuf};
 
 /// A repository on disk
 pub struct Repo {
     working_directory: PathBuf,
     dot_hg: PathBuf,
     store: PathBuf,
     requirements: HashSet<String>,
     config: Config,
     dirstate_parents: LazyCell<DirstateParents, HgError>,
     dirstate_data_file_uuid: LazyCell<Option<Vec<u8>>, HgError>,
     dirstate_map: LazyCell<OwningDirstateMap, DirstateError>,
     changelog: LazyCell<Changelog, HgError>,
     manifestlog: LazyCell<Manifestlog, HgError>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum RepoError {
     NotFound {
         at: PathBuf,
     },
     #[from]
     ConfigParseError(ConfigParseError),
     #[from]
     Other(HgError),
 }
 
 impl From<ConfigError> for RepoError {
     fn from(error: ConfigError) -> Self {
         match error {
             ConfigError::Parse(error) => error.into(),
             ConfigError::Other(error) => error.into(),
         }
     }
 }
 
 impl Repo {
     /// tries to find nearest repository root in current working directory or
     /// its ancestors
     pub fn find_repo_root() -> Result<PathBuf, RepoError> {
         let current_directory = crate::utils::current_dir()?;
         // ancestors() is inclusive: it first yields `current_directory`
         // as-is.
         for ancestor in current_directory.ancestors() {
             if is_dir(ancestor.join(".hg"))? {
                 return Ok(ancestor.to_path_buf());
             }
         }
         return Err(RepoError::NotFound {
             at: current_directory,
         });
     }
 
     /// Find a repository, either at the given path (which must contain a `.hg`
     /// sub-directory) or by searching the current directory and its
     /// ancestors.
     ///
     /// A method with two very different "modes" like this usually a code smell
     /// to make two methods instead, but in this case an `Option` is what rhg
     /// sub-commands get from Clap for the `-R` / `--repository` CLI argument.
     /// Having two methods would just move that `if` to almost all callers.
     pub fn find(
         config: &Config,
         explicit_path: Option<PathBuf>,
     ) -> Result<Self, RepoError> {
         if let Some(root) = explicit_path {
             if is_dir(root.join(".hg"))? {
                 Self::new_at_path(root.to_owned(), config)
             } else if is_file(&root)? {
                 Err(HgError::unsupported("bundle repository").into())
             } else {
                 Err(RepoError::NotFound {
                     at: root.to_owned(),
                 })
             }
         } else {
             let root = Self::find_repo_root()?;
             Self::new_at_path(root, config)
         }
     }
 
     /// To be called after checking that `.hg` is a sub-directory
     fn new_at_path(
         working_directory: PathBuf,
         config: &Config,
     ) -> Result<Self, RepoError> {
         let dot_hg = working_directory.join(".hg");
 
         let mut repo_config_files = Vec::new();
         repo_config_files.push(dot_hg.join("hgrc"));
         repo_config_files.push(dot_hg.join("hgrc-not-shared"));
 
         let hg_vfs = Vfs { base: &dot_hg };
         let mut reqs = requirements::load_if_exists(hg_vfs)?;
         let relative =
             reqs.contains(requirements::RELATIVE_SHARED_REQUIREMENT);
         let shared =
             reqs.contains(requirements::SHARED_REQUIREMENT) || relative;
 
         // From `mercurial/localrepo.py`:
         //
         // if .hg/requires contains the sharesafe requirement, it means
         // there exists a `.hg/store/requires` too and we should read it
         // NOTE: presence of SHARESAFE_REQUIREMENT imply that store requirement
         // is present. We never write SHARESAFE_REQUIREMENT for a repo if store
         // is not present, refer checkrequirementscompat() for that
         //
         // However, if SHARESAFE_REQUIREMENT is not present, it means that the
         // repository was shared the old way. We check the share source
         // .hg/requires for SHARESAFE_REQUIREMENT to detect whether the
         // current repository needs to be reshared
         let share_safe = reqs.contains(requirements::SHARESAFE_REQUIREMENT);
 
         let store_path;
         if !shared {
             store_path = dot_hg.join("store");
         } else {
             let bytes = hg_vfs.read("sharedpath")?;
             let mut shared_path =
                 get_path_from_bytes(bytes.trim_end_matches(|b| b == b'\n'))
                     .to_owned();
             if relative {
                 shared_path = dot_hg.join(shared_path)
             }
             if !is_dir(&shared_path)? {
                 return Err(HgError::corrupted(format!(
                     ".hg/sharedpath points to nonexistent directory {}",
                     shared_path.display()
                 ))
                 .into());
             }
 
             store_path = shared_path.join("store");
 
             let source_is_share_safe =
                 requirements::load(Vfs { base: &shared_path })?
                     .contains(requirements::SHARESAFE_REQUIREMENT);
 
             if share_safe != source_is_share_safe {
                 return Err(HgError::unsupported("share-safe mismatch").into());
             }
 
             if share_safe {
                 repo_config_files.insert(0, shared_path.join("hgrc"))
             }
         }
         if share_safe {
             reqs.extend(requirements::load(Vfs { base: &store_path })?);
         }
 
         let repo_config = if std::env::var_os("HGRCSKIPREPO").is_none() {
             config.combine_with_repo(&repo_config_files)?
         } else {
             config.clone()
         };
 
         let repo = Self {
             requirements: reqs,
             working_directory,
             store: store_path,
             dot_hg,
             config: repo_config,
             dirstate_parents: LazyCell::new(Self::read_dirstate_parents),
             dirstate_data_file_uuid: LazyCell::new(
                 Self::read_dirstate_data_file_uuid,
             ),
             dirstate_map: LazyCell::new(Self::new_dirstate_map),
             changelog: LazyCell::new(Changelog::open),
             manifestlog: LazyCell::new(Manifestlog::open),
         };
 
         requirements::check(&repo)?;
 
         Ok(repo)
     }
 
     pub fn working_directory_path(&self) -> &Path {
         &self.working_directory
     }
 
     pub fn requirements(&self) -> &HashSet<String> {
         &self.requirements
     }
 
     pub fn config(&self) -> &Config {
         &self.config
     }
 
     /// For accessing repository files (in `.hg`), except for the store
     /// (`.hg/store`).
     pub fn hg_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.dot_hg }
     }
 
     /// For accessing repository store files (in `.hg/store`)
     pub fn store_vfs(&self) -> Vfs<'_> {
         Vfs { base: &self.store }
     }
 
     /// For accessing the working copy
     pub fn working_directory_vfs(&self) -> Vfs<'_> {
         Vfs {
             base: &self.working_directory,
         }
     }
 
     pub fn try_with_wlock_no_wait<R>(
         &self,
         f: impl FnOnce() -> R,
     ) -> Result<R, LockError> {
         try_with_lock_no_wait(self.hg_vfs(), "wlock", f)
     }
 
     pub fn has_dirstate_v2(&self) -> bool {
         self.requirements
             .contains(requirements::DIRSTATE_V2_REQUIREMENT)
     }
 
     pub fn has_sparse(&self) -> bool {
         self.requirements.contains(requirements::SPARSE_REQUIREMENT)
     }
 
     pub fn has_narrow(&self) -> bool {
         self.requirements.contains(requirements::NARROW_REQUIREMENT)
     }
 
     fn dirstate_file_contents(&self) -> Result<Vec<u8>, HgError> {
         Ok(self
             .hg_vfs()
             .read("dirstate")
             .io_not_found_as_none()?
             .unwrap_or(Vec::new()))
     }
 
     pub fn dirstate_parents(&self) -> Result<DirstateParents, HgError> {
         Ok(*self.dirstate_parents.get_or_init(self)?)
     }
 
     fn read_dirstate_parents(&self) -> Result<DirstateParents, HgError> {
         let dirstate = self.dirstate_file_contents()?;
         let parents = if dirstate.is_empty() {
             if self.has_dirstate_v2() {
                 self.dirstate_data_file_uuid.set(None);
             }
             DirstateParents::NULL
         } else if self.has_dirstate_v2() {
             let docket =
                 crate::dirstate_tree::on_disk::read_docket(&dirstate)?;
             self.dirstate_data_file_uuid
                 .set(Some(docket.uuid.to_owned()));
             docket.parents()
         } else {
             crate::dirstate::parsers::parse_dirstate_parents(&dirstate)?
                 .clone()
         };
         self.dirstate_parents.set(parents);
         Ok(parents)
     }
 
     fn read_dirstate_data_file_uuid(
         &self,
     ) -> Result<Option<Vec<u8>>, HgError> {
         assert!(
             self.has_dirstate_v2(),
             "accessing dirstate data file ID without dirstate-v2"
         );
         let dirstate = self.dirstate_file_contents()?;
         if dirstate.is_empty() {
             self.dirstate_parents.set(DirstateParents::NULL);
             Ok(None)
         } else {
             let docket =
                 crate::dirstate_tree::on_disk::read_docket(&dirstate)?;
             self.dirstate_parents.set(docket.parents());
             Ok(Some(docket.uuid.to_owned()))
         }
     }
 
     fn new_dirstate_map(&self) -> Result<OwningDirstateMap, DirstateError> {
         let dirstate_file_contents = self.dirstate_file_contents()?;
         if dirstate_file_contents.is_empty() {
             self.dirstate_parents.set(DirstateParents::NULL);
             if self.has_dirstate_v2() {
                 self.dirstate_data_file_uuid.set(None);
             }
             Ok(OwningDirstateMap::new_empty(Vec::new()))
         } else if self.has_dirstate_v2() {
             let docket = crate::dirstate_tree::on_disk::read_docket(
                 &dirstate_file_contents,
             )?;
             self.dirstate_parents.set(docket.parents());
             self.dirstate_data_file_uuid
                 .set(Some(docket.uuid.to_owned()));
             let data_size = docket.data_size();
             let metadata = docket.tree_metadata();
-            let mut map = if let Some(data_mmap) = self
+            if let Some(data_mmap) = self
                 .hg_vfs()
                 .mmap_open(docket.data_filename())
                 .io_not_found_as_none()?
             {
-                OwningDirstateMap::new_empty(data_mmap)
+                OwningDirstateMap::new_v2(data_mmap, data_size, metadata)
             } else {
-                OwningDirstateMap::new_empty(Vec::new())
-            };
-            let (on_disk, placeholder) = map.get_pair_mut();
-            *placeholder = DirstateMap::new_v2(on_disk, data_size, metadata)?;
-            Ok(map)
+                OwningDirstateMap::new_v2(Vec::new(), data_size, metadata)
+            }
         } else {
-            let mut map = OwningDirstateMap::new_empty(dirstate_file_contents);
-            let (on_disk, placeholder) = map.get_pair_mut();
-            let (inner, parents) = DirstateMap::new_v1(on_disk)?;
-            self.dirstate_parents
-                .set(parents.unwrap_or(DirstateParents::NULL));
-            *placeholder = inner;
+            let (map, parents) =
+                OwningDirstateMap::new_v1(dirstate_file_contents)?;
+            self.dirstate_parents.set(parents);
             Ok(map)
         }
     }
 
     pub fn dirstate_map(
         &self,
     ) -> Result<Ref<OwningDirstateMap>, DirstateError> {
         self.dirstate_map.get_or_init(self)
     }
 
     pub fn dirstate_map_mut(
         &self,
     ) -> Result<RefMut<OwningDirstateMap>, DirstateError> {
         self.dirstate_map.get_mut_or_init(self)
     }
 
     pub fn changelog(&self) -> Result<Ref<Changelog>, HgError> {
         self.changelog.get_or_init(self)
     }
 
     pub fn changelog_mut(&self) -> Result<RefMut<Changelog>, HgError> {
         self.changelog.get_mut_or_init(self)
     }
 
     pub fn manifestlog(&self) -> Result<Ref<Manifestlog>, HgError> {
         self.manifestlog.get_or_init(self)
     }
 
     pub fn manifestlog_mut(&self) -> Result<RefMut<Manifestlog>, HgError> {
         self.manifestlog.get_mut_or_init(self)
     }
 
     /// Returns the manifest of the *changeset* with the given node ID
     pub fn manifest_for_node(
         &self,
         node: impl Into<NodePrefix>,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_node(node.into())?
                 .manifest_node()?
                 .into(),
         )
     }
 
     /// Returns the manifest of the *changeset* with the given revision number
     pub fn manifest_for_rev(
         &self,
         revision: Revision,
     ) -> Result<Manifest, RevlogError> {
         self.manifestlog()?.data_for_node(
             self.changelog()?
                 .data_for_rev(revision)?
                 .manifest_node()?
                 .into(),
         )
     }
 
     pub fn has_subrepos(&self) -> Result<bool, DirstateError> {
         if let Some(entry) = self.dirstate_map()?.get(HgPath::new(".hgsub"))? {
             Ok(entry.state().is_tracked())
         } else {
             Ok(false)
         }
     }
 
     pub fn filelog(&self, path: &HgPath) -> Result<Filelog, HgError> {
         Filelog::open(self, path)
     }
 
     /// Write to disk any updates that were made through `dirstate_map_mut`.
     ///
     /// The "wlock" must be held while calling this.
     /// See for example `try_with_wlock_no_wait`.
     ///
     /// TODO: have a `WritableRepo` type only accessible while holding the
     /// lock?
     pub fn write_dirstate(&self) -> Result<(), DirstateError> {
         let map = self.dirstate_map()?;
         // TODO: Maintain a `DirstateMap::dirty` flag, and return early here if
         // it’s unset
         let parents = self.dirstate_parents()?;
         let packed_dirstate = if self.has_dirstate_v2() {
             let uuid = self.dirstate_data_file_uuid.get_or_init(self)?;
             let mut uuid = uuid.as_ref();
             let can_append = uuid.is_some();
             let (data, tree_metadata, append) = map.pack_v2(can_append)?;
             if !append {
                 uuid = None
             }
             let uuid = if let Some(uuid) = uuid {
                 std::str::from_utf8(uuid)
                     .map_err(|_| {
                         HgError::corrupted("non-UTF-8 dirstate data file ID")
                     })?
                     .to_owned()
             } else {
                 DirstateDocket::new_uid()
             };
             let data_filename = format!("dirstate.{}", uuid);
             let data_filename = self.hg_vfs().join(data_filename);
             let mut options = std::fs::OpenOptions::new();
             if append {
                 options.append(true);
             } else {
                 options.write(true).create_new(true);
             }
             let data_size = (|| {
                 // TODO: loop and try another random ID if !append and this
                 // returns `ErrorKind::AlreadyExists`? Collision chance of two
                 // random IDs is one in 2**32
                 let mut file = options.open(&data_filename)?;
                 file.write_all(&data)?;
                 file.flush()?;
                 // TODO: use https://doc.rust-lang.org/std/io/trait.Seek.html#method.stream_position when we require Rust 1.51+
                 file.seek(SeekFrom::Current(0))
             })()
             .when_writing_file(&data_filename)?;
             DirstateDocket::serialize(
                 parents,
                 tree_metadata,
                 data_size,
                 uuid.as_bytes(),
             )
             .map_err(|_: std::num::TryFromIntError| {
                 HgError::corrupted("overflow in dirstate docket serialization")
             })?
         } else {
             map.pack_v1(parents)?
         };
         self.hg_vfs().atomic_write("dirstate", &packed_dirstate)?;
         Ok(())
     }
 }
 
 /// Lazily-initialized component of `Repo` with interior mutability
 ///
 /// This differs from `OnceCell` in that the value can still be "deinitialized"
 /// later by setting its inner `Option` to `None`.
 struct LazyCell<T, E> {
     value: RefCell<Option<T>>,
     // `Fn`s that don’t capture environment are zero-size, so this box does
     // not allocate:
     init: Box<dyn Fn(&Repo) -> Result<T, E>>,
 }
 
 impl<T, E> LazyCell<T, E> {
     fn new(init: impl Fn(&Repo) -> Result<T, E> + 'static) -> Self {
         Self {
             value: RefCell::new(None),
             init: Box::new(init),
         }
     }
 
     fn set(&self, value: T) {
         *self.value.borrow_mut() = Some(value)
     }
 
     fn get_or_init(&self, repo: &Repo) -> Result<Ref<T>, E> {
         let mut borrowed = self.value.borrow();
         if borrowed.is_none() {
             drop(borrowed);
             // Only use `borrow_mut` if it is really needed to avoid panic in
             // case there is another outstanding borrow but mutation is not
             // needed.
             *self.value.borrow_mut() = Some((self.init)(repo)?);
             borrowed = self.value.borrow()
         }
         Ok(Ref::map(borrowed, |option| option.as_ref().unwrap()))
     }
 
     fn get_mut_or_init(&self, repo: &Repo) -> Result<RefMut<T>, E> {
         let mut borrowed = self.value.borrow_mut();
         if borrowed.is_none() {
             *borrowed = Some((self.init)(repo)?);
         }
         Ok(RefMut::map(borrowed, |option| option.as_mut().unwrap()))
     }
 }

rust/hg-core/src/utils/hg_path.rs

@@ -1,820 +1,813 b''
 // hg_path.rs
 //
 // Copyright 2019 Raphaël Gomès <[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.
 
 use crate::utils::SliceExt;
 use std::borrow::Borrow;
 use std::borrow::Cow;
 use std::convert::TryFrom;
 use std::ffi::{OsStr, OsString};
 use std::fmt;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 #[derive(Debug, Eq, PartialEq)]
 pub enum HgPathError {
     /// Bytes from the invalid `HgPath`
     LeadingSlash(Vec<u8>),
     ConsecutiveSlashes {
         bytes: Vec<u8>,
         second_slash_index: usize,
     },
     ContainsNullByte {
         bytes: Vec<u8>,
         null_byte_index: usize,
     },
     /// Bytes
     DecodeError(Vec<u8>),
     /// The rest come from audit errors
     EndsWithSlash(HgPathBuf),
     ContainsIllegalComponent(HgPathBuf),
     /// Path is inside the `.hg` folder
     InsideDotHg(HgPathBuf),
     IsInsideNestedRepo {
         path: HgPathBuf,
         nested_repo: HgPathBuf,
     },
     TraversesSymbolicLink {
         path: HgPathBuf,
         symlink: HgPathBuf,
     },
     NotFsCompliant(HgPathBuf),
     /// `path` is the smallest invalid path
     NotUnderRoot {
         path: PathBuf,
         root: PathBuf,
     },
 }
 
 impl fmt::Display for HgPathError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             HgPathError::LeadingSlash(bytes) => {
                 write!(f, "Invalid HgPath '{:?}': has a leading slash.", bytes)
             }
             HgPathError::ConsecutiveSlashes {
                 bytes,
                 second_slash_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': consecutive slashes at pos {}.",
                 bytes, pos
             ),
             HgPathError::ContainsNullByte {
                 bytes,
                 null_byte_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': contains null byte at pos {}.",
                 bytes, pos
             ),
             HgPathError::DecodeError(bytes) => write!(
                 f,
                 "Invalid HgPath '{:?}': could not be decoded.",
                 bytes
             ),
             HgPathError::EndsWithSlash(path) => {
                 write!(f, "Audit failed for '{}': ends with a slash.", path)
             }
             HgPathError::ContainsIllegalComponent(path) => write!(
                 f,
                 "Audit failed for '{}': contains an illegal component.",
                 path
             ),
             HgPathError::InsideDotHg(path) => write!(
                 f,
                 "Audit failed for '{}': is inside the '.hg' folder.",
                 path
             ),
             HgPathError::IsInsideNestedRepo {
                 path,
                 nested_repo: nested,
             } => {
                 write!(f,
                 "Audit failed for '{}': is inside a nested repository '{}'.",
                 path, nested
             )
             }
             HgPathError::TraversesSymbolicLink { path, symlink } => write!(
                 f,
                 "Audit failed for '{}': traverses symbolic link '{}'.",
                 path, symlink
             ),
             HgPathError::NotFsCompliant(path) => write!(
                 f,
                 "Audit failed for '{}': cannot be turned into a \
                  filesystem path.",
                 path
             ),
             HgPathError::NotUnderRoot { path, root } => write!(
                 f,
                 "Audit failed for '{}': not under root {}.",
                 path.display(),
                 root.display()
             ),
         }
     }
 }
 
 impl From<HgPathError> for std::io::Error {
     fn from(e: HgPathError) -> Self {
         std::io::Error::new(std::io::ErrorKind::InvalidData, e.to_string())
     }
 }
 
 /// This is a repository-relative path (or canonical path):
 ///     - no null characters
 ///     - `/` separates directories
 ///     - no consecutive slashes
 ///     - no leading slash,
 ///     - no `.` nor `..` of special meaning
 ///     - stored in repository and shared across platforms
 ///
 /// Note: there is no guarantee of any `HgPath` being well-formed at any point
 /// in its lifetime for performance reasons and to ease ergonomics. It is
 /// however checked using the `check_state` method before any file-system
 /// operation.
 ///
 /// This allows us to be encoding-transparent as much as possible, until really
 /// needed; `HgPath` can be transformed into a platform-specific path (`OsStr`
 /// or `Path`) whenever more complex operations are needed:
 /// On Unix, it's just byte-to-byte conversion. On Windows, it has to be
 /// decoded from MBCS to WTF-8. If WindowsUTF8Plan is implemented, the source
 /// character encoding will be determined on a per-repository basis.
-//
-// FIXME: (adapted from a comment in the stdlib)
-// `HgPath::new()` current implementation relies on `Slice` being
-// layout-compatible with `[u8]`.
-// When attribute privacy is implemented, `Slice` should be annotated as
-// `#[repr(transparent)]`.
-// Anyway, `Slice` representation and layout are considered implementation
-// detail, are not documented and must not be relied upon.
 #[derive(Eq, Ord, PartialEq, PartialOrd, Hash)]
+#[repr(transparent)]
 pub struct HgPath {
     inner: [u8],
 }
 
 impl HgPath {
     pub fn new<S: AsRef<[u8]> + ?Sized>(s: &S) -> &Self {
         unsafe { &*(s.as_ref() as *const [u8] as *const Self) }
     }
     pub fn is_empty(&self) -> bool {
         self.inner.is_empty()
     }
     pub fn len(&self) -> usize {
         self.inner.len()
     }
     fn to_hg_path_buf(&self) -> HgPathBuf {
         HgPathBuf {
             inner: self.inner.to_owned(),
         }
     }
     pub fn bytes(&self) -> std::slice::Iter<u8> {
         self.inner.iter()
     }
     pub fn to_ascii_uppercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_uppercase())
     }
     pub fn to_ascii_lowercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_lowercase())
     }
     pub fn as_bytes(&self) -> &[u8] {
         &self.inner
     }
     pub fn contains(&self, other: u8) -> bool {
         self.inner.contains(&other)
     }
     pub fn starts_with(&self, needle: impl AsRef<Self>) -> bool {
         self.inner.starts_with(needle.as_ref().as_bytes())
     }
     pub fn trim_trailing_slash(&self) -> &Self {
         Self::new(if self.inner.last() == Some(&b'/') {
             &self.inner[..self.inner.len() - 1]
         } else {
             &self.inner[..]
         })
     }
     /// Returns a tuple of slices `(base, filename)` resulting from the split
     /// at the rightmost `/`, if any.
     ///
     /// # Examples:
     ///
     /// ```
     /// use hg::utils::hg_path::HgPath;
     ///
     /// let path = HgPath::new(b"cool/hg/path").split_filename();
     /// assert_eq!(path, (HgPath::new(b"cool/hg"), HgPath::new(b"path")));
     ///
     /// let path = HgPath::new(b"pathwithoutsep").split_filename();
     /// assert_eq!(path, (HgPath::new(b""), HgPath::new(b"pathwithoutsep")));
     /// ```
     pub fn split_filename(&self) -> (&Self, &Self) {
         match &self.inner.iter().rposition(|c| *c == b'/') {
             None => (HgPath::new(""), &self),
             Some(size) => (
                 HgPath::new(&self.inner[..*size]),
                 HgPath::new(&self.inner[*size + 1..]),
             ),
         }
     }
 
     pub fn join(&self, path: &HgPath) -> HgPathBuf {
         let mut buf = self.to_owned();
         buf.push(path);
         buf
     }
 
     pub fn components(&self) -> impl Iterator<Item = &HgPath> {
         self.inner.split(|&byte| byte == b'/').map(HgPath::new)
     }
 
     /// Returns the first (that is "root-most") slash-separated component of
     /// the path, and the rest after the first slash if there is one.
     pub fn split_first_component(&self) -> (&HgPath, Option<&HgPath>) {
         match self.inner.split_2(b'/') {
             Some((a, b)) => (HgPath::new(a), Some(HgPath::new(b))),
             None => (self, None),
         }
     }
 
     pub fn parent(&self) -> &Self {
         let inner = self.as_bytes();
         HgPath::new(match inner.iter().rposition(|b| *b == b'/') {
             Some(pos) => &inner[..pos],
             None => &[],
         })
     }
     /// Given a base directory, returns the slice of `self` relative to the
     /// base directory. If `base` is not a directory (does not end with a
     /// `b'/'`), returns `None`.
     pub fn relative_to(&self, base: impl AsRef<Self>) -> Option<&Self> {
         let base = base.as_ref();
         if base.is_empty() {
             return Some(self);
         }
         let is_dir = base.as_bytes().ends_with(b"/");
         if is_dir && self.starts_with(base) {
             Some(Self::new(&self.inner[base.len()..]))
         } else {
             None
         }
     }
 
     #[cfg(windows)]
     /// Copied from the Python stdlib's `os.path.splitdrive` implementation.
     ///
     /// Split a pathname into drive/UNC sharepoint and relative path
     /// specifiers. Returns a 2-tuple (drive_or_unc, path); either part may
     /// be empty.
     ///
     /// If you assign
     ///  result = split_drive(p)
     /// It is always true that:
     ///  result[0] + result[1] == p
     ///
     /// If the path contained a drive letter, drive_or_unc will contain
     /// everything up to and including the colon.
     /// e.g. split_drive("c:/dir") returns ("c:", "/dir")
     ///
     /// If the path contained a UNC path, the drive_or_unc will contain the
     /// host name and share up to but not including the fourth directory
     /// separator character.
     /// e.g. split_drive("//host/computer/dir") returns ("//host/computer",
     /// "/dir")
     ///
     /// Paths cannot contain both a drive letter and a UNC path.
     pub fn split_drive<'a>(&self) -> (&HgPath, &HgPath) {
         let bytes = self.as_bytes();
         let is_sep = |b| std::path::is_separator(b as char);
 
         if self.len() < 2 {
             (HgPath::new(b""), &self)
         } else if is_sep(bytes[0])
             && is_sep(bytes[1])
             && (self.len() == 2 || !is_sep(bytes[2]))
         {
             // Is a UNC path:
             // vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
             // \\machine\mountpoint\directory\etc\...
             //           directory ^^^^^^^^^^^^^^^
 
             let machine_end_index = bytes[2..].iter().position(|b| is_sep(*b));
             let mountpoint_start_index = if let Some(i) = machine_end_index {
                 i + 2
             } else {
                 return (HgPath::new(b""), &self);
             };
 
             match bytes[mountpoint_start_index + 1..]
                 .iter()
                 .position(|b| is_sep(*b))
             {
                 // A UNC path can't have two slashes in a row
                 // (after the initial two)
                 Some(0) => (HgPath::new(b""), &self),
                 Some(i) => {
                     let (a, b) =
                         bytes.split_at(mountpoint_start_index + 1 + i);
                     (HgPath::new(a), HgPath::new(b))
                 }
                 None => (&self, HgPath::new(b"")),
             }
         } else if bytes[1] == b':' {
             // Drive path c:\directory
             let (a, b) = bytes.split_at(2);
             (HgPath::new(a), HgPath::new(b))
         } else {
             (HgPath::new(b""), &self)
         }
     }
 
     #[cfg(unix)]
     /// Split a pathname into drive and path. On Posix, drive is always empty.
     pub fn split_drive(&self) -> (&HgPath, &HgPath) {
         (HgPath::new(b""), &self)
     }
 
     /// Checks for errors in the path, short-circuiting at the first one.
     /// This generates fine-grained errors useful for debugging.
     /// To simply check if the path is valid during tests, use `is_valid`.
     pub fn check_state(&self) -> Result<(), HgPathError> {
         if self.is_empty() {
             return Ok(());
         }
         let bytes = self.as_bytes();
         let mut previous_byte = None;
 
         if bytes[0] == b'/' {
             return Err(HgPathError::LeadingSlash(bytes.to_vec()));
         }
         for (index, byte) in bytes.iter().enumerate() {
             match byte {
                 0 => {
                     return Err(HgPathError::ContainsNullByte {
                         bytes: bytes.to_vec(),
                         null_byte_index: index,
                     })
                 }
                 b'/' => {
                     if previous_byte.is_some() && previous_byte == Some(b'/') {
                         return Err(HgPathError::ConsecutiveSlashes {
                             bytes: bytes.to_vec(),
                             second_slash_index: index,
                         });
                     }
                 }
                 _ => (),
             };
             previous_byte = Some(*byte);
         }
         Ok(())
     }
 
     #[cfg(test)]
     /// Only usable during tests to force developers to handle invalid states
     fn is_valid(&self) -> bool {
         self.check_state().is_ok()
     }
 }
 
 impl fmt::Debug for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPath({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 #[derive(
     Default, Eq, Ord, Clone, PartialEq, PartialOrd, Hash, derive_more::From,
 )]
 pub struct HgPathBuf {
     inner: Vec<u8>,
 }
 
 impl HgPathBuf {
     pub fn new() -> Self {
         Default::default()
     }
 
     pub fn push<T: ?Sized + AsRef<HgPath>>(&mut self, other: &T) -> () {
         if !self.inner.is_empty() && self.inner.last() != Some(&b'/') {
             self.inner.push(b'/');
         }
         self.inner.extend(other.as_ref().bytes())
     }
 
     pub fn push_byte(&mut self, byte: u8) {
         self.inner.push(byte);
     }
     pub fn from_bytes(s: &[u8]) -> HgPathBuf {
         HgPath::new(s).to_owned()
     }
     pub fn into_vec(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl fmt::Debug for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPathBuf({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl Deref for HgPathBuf {
     type Target = HgPath;
 
     #[inline]
     fn deref(&self) -> &HgPath {
         &HgPath::new(&self.inner)
     }
 }
 
 impl<T: ?Sized + AsRef<HgPath>> From<&T> for HgPathBuf {
     fn from(s: &T) -> HgPathBuf {
         s.as_ref().to_owned()
     }
 }
 
 impl Into<Vec<u8>> for HgPathBuf {
     fn into(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl Borrow<HgPath> for HgPathBuf {
     fn borrow(&self) -> &HgPath {
         &HgPath::new(self.as_bytes())
     }
 }
 
 impl ToOwned for HgPath {
     type Owned = HgPathBuf;
 
     fn to_owned(&self) -> HgPathBuf {
         self.to_hg_path_buf()
     }
 }
 
 impl AsRef<HgPath> for HgPath {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl AsRef<HgPath> for HgPathBuf {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl Extend<u8> for HgPathBuf {
     fn extend<T: IntoIterator<Item = u8>>(&mut self, iter: T) {
         self.inner.extend(iter);
     }
 }
 
 /// TODO: Once https://www.mercurial-scm.org/wiki/WindowsUTF8Plan is
 /// implemented, these conversion utils will have to work differently depending
 /// on the repository encoding: either `UTF-8` or `MBCS`.
 
 pub fn hg_path_to_os_string<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<OsString, HgPathError> {
     hg_path.as_ref().check_state()?;
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(&hg_path.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     Ok(os_str.to_os_string())
 }
 
 pub fn hg_path_to_path_buf<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<PathBuf, HgPathError> {
     Ok(Path::new(&hg_path_to_os_string(hg_path)?).to_path_buf())
 }
 
 pub fn os_string_to_hg_path_buf<S: AsRef<OsStr>>(
     os_string: S,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_string.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 pub fn path_to_hg_path_buf<P: AsRef<Path>>(
     path: P,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     let os_str = path.as_ref().as_os_str();
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_str.as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 impl TryFrom<PathBuf> for HgPathBuf {
     type Error = HgPathError;
     fn try_from(path: PathBuf) -> Result<Self, Self::Error> {
         path_to_hg_path_buf(path)
     }
 }
 
 impl From<HgPathBuf> for Cow<'_, HgPath> {
     fn from(path: HgPathBuf) -> Self {
         Cow::Owned(path)
     }
 }
 
 impl<'a> From<&'a HgPath> for Cow<'a, HgPath> {
     fn from(path: &'a HgPath) -> Self {
         Cow::Borrowed(path)
     }
 }
 
 impl<'a> From<&'a HgPathBuf> for Cow<'a, HgPath> {
     fn from(path: &'a HgPathBuf) -> Self {
         Cow::Borrowed(&**path)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn test_path_states() {
         assert_eq!(
             Err(HgPathError::LeadingSlash(b"/".to_vec())),
             HgPath::new(b"/").check_state()
         );
         assert_eq!(
             Err(HgPathError::ConsecutiveSlashes {
                 bytes: b"a/b//c".to_vec(),
                 second_slash_index: 4
             }),
             HgPath::new(b"a/b//c").check_state()
         );
         assert_eq!(
             Err(HgPathError::ContainsNullByte {
                 bytes: b"a/b/\0c".to_vec(),
                 null_byte_index: 4
             }),
             HgPath::new(b"a/b/\0c").check_state()
         );
         // TODO test HgPathError::DecodeError for the Windows implementation.
         assert_eq!(true, HgPath::new(b"").is_valid());
         assert_eq!(true, HgPath::new(b"a/b/c").is_valid());
         // Backslashes in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(br"a\b/c").is_valid());
         // Dots in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(b"a/b/../c/").is_valid());
         assert_eq!(true, HgPath::new(b"./a/b/../c/").is_valid());
     }
 
     #[test]
     fn test_iter() {
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'c'), iter.next_back());
         assert_eq!(Some(&b'b'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'b'), iter.next());
         assert_eq!(Some(&b'c'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let iter = path.bytes();
         let mut vec = Vec::new();
         vec.extend(iter);
         assert_eq!(vec![b'a', b'b', b'c'], vec);
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(2), iter.rposition(|c| *c == b'c'));
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(None, iter.rposition(|c| *c == b'd'));
     }
 
     #[test]
     fn test_join() {
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"b"));
         assert_eq!(b"a/b", path.as_bytes());
 
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"b/c"));
         assert_eq!(b"a/b/c", path.as_bytes());
 
         // No leading slash if empty before join
         let path = HgPathBuf::new().join(HgPath::new(b"b/c"));
         assert_eq!(b"b/c", path.as_bytes());
 
         // The leading slash is an invalid representation of an `HgPath`, but
         // it can happen. This creates another invalid representation of
         // consecutive bytes.
         // TODO What should be done in this case? Should we silently remove
         // the extra slash? Should we change the signature to a problematic
         // `Result<HgPathBuf, HgPathError>`, or should we just keep it so and
         // let the error happen upon filesystem interaction?
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
     }
 
     #[test]
     fn test_relative_to() {
         let path = HgPath::new(b"");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"path");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"a");
         let base = HgPath::new(b"b");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a/");
         assert_eq!(Some(HgPath::new(b"b")), path.relative_to(base));
 
         let path = HgPath::new(b"nested/path/to/b");
         let base = HgPath::new(b"nested/path/");
         assert_eq!(Some(HgPath::new(b"to/b")), path.relative_to(base));
 
         let path = HgPath::new(b"ends/with/dir/");
         let base = HgPath::new(b"ends/");
         assert_eq!(Some(HgPath::new(b"with/dir/")), path.relative_to(base));
     }
 
     #[test]
     #[cfg(unix)]
     fn test_split_drive() {
         // Taken from the Python stdlib's tests
         assert_eq!(
             HgPath::new(br"/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"foo:bar"))
         );
         assert_eq!(
             HgPath::new(br":foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br":foo:bar"))
         );
         // Also try NT paths; should not split them
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(b""),
                 HgPath::new(br"\\conky\mountpoint\foo\bar")
             )
         );
     }
 
     #[test]
     #[cfg(windows)]
     fn test_split_drive() {
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br"\\conky\mountpoint"),
                 HgPath::new(br"\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br"//conky/mountpoint"),
                 HgPath::new(br"/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\\conky\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"///conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"///conky/mountpoint/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\conky\\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\conky\\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky//mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"//conky//mountpoint/foo/bar")
             )
         );
         // UNC part containing U+0130
         assert_eq!(
             HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT/foo/bar").split_drive(),
             (
                 HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT"),
                 HgPath::new(br"/foo/bar")
             )
         );
     }
 
     #[test]
     fn test_parent() {
         let path = HgPath::new(b"");
         assert_eq!(path.parent(), path);
 
         let path = HgPath::new(b"a");
         assert_eq!(path.parent(), HgPath::new(b""));
 
         let path = HgPath::new(b"a/b");
         assert_eq!(path.parent(), HgPath::new(b"a"));
 
         let path = HgPath::new(b"a/other/b");
         assert_eq!(path.parent(), HgPath::new(b"a/other"));
     }
 }

rust/hg-cpython/src/dirstate/dirstate_map.rs

@@ -1,499 +1,490 b''
 // dirstate_map.rs
 //
 // Copyright 2019 Raphaël Gomès <[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.
 
 //! Bindings for the `hg::dirstate::dirstate_map` file provided by the
 //! `hg-core` package.
 
 use std::cell::{RefCell, RefMut};
 use std::convert::TryInto;
 
 use cpython::{
     exc, PyBool, PyBytes, PyClone, PyDict, PyErr, PyList, PyNone, PyObject,
     PyResult, Python, PythonObject, ToPyObject, UnsafePyLeaked,
 };
 
 use crate::{
     dirstate::copymap::{CopyMap, CopyMapItemsIterator, CopyMapKeysIterator},
     dirstate::item::DirstateItem,
     pybytes_deref::PyBytesDeref,
 };
 use hg::{
     dirstate::StateMapIter,
-    dirstate_tree::dirstate_map::DirstateMap as TreeDirstateMap,
     dirstate_tree::on_disk::DirstateV2ParseError,
     dirstate_tree::owning::OwningDirstateMap,
     revlog::Node,
     utils::files::normalize_case,
     utils::hg_path::{HgPath, HgPathBuf},
     DirstateEntry, DirstateError, DirstateParents, EntryState,
 };
 
 // TODO
 //     This object needs to share references to multiple members of its Rust
 //     inner struct, namely `copy_map`, `dirs` and `all_dirs`.
 //     Right now `CopyMap` is done, but it needs to have an explicit reference
 //     to `RustDirstateMap` which itself needs to have an encapsulation for
 //     every method in `CopyMap` (copymapcopy, etc.).
 //     This is ugly and hard to maintain.
 //     The same logic applies to `dirs` and `all_dirs`, however the `Dirs`
 //     `py_class!` is already implemented and does not mention
 //     `RustDirstateMap`, rightfully so.
 //     All attributes also have to have a separate refcount data attribute for
 //     leaks, with all methods that go along for reference sharing.
 py_class!(pub class DirstateMap |py| {
     @shared data inner: OwningDirstateMap;
 
     /// Returns a `(dirstate_map, parents)` tuple
     @staticmethod
     def new_v1(
         on_disk: PyBytes,
     ) -> PyResult<PyObject> {
         let on_disk = PyBytesDeref::new(py, on_disk);
-        let mut map = OwningDirstateMap::new_empty(on_disk);
-        let (on_disk, map_placeholder) = map.get_pair_mut();
-
-        let (actual_map, parents) = TreeDirstateMap::new_v1(on_disk)
+        let (map, parents) = OwningDirstateMap::new_v1(on_disk)
             .map_err(|e| dirstate_error(py, e))?;
-        *map_placeholder = actual_map;
         let map = Self::create_instance(py, map)?;
-        let parents = parents.map(|p| {
-            let p1 = PyBytes::new(py, p.p1.as_bytes());
-            let p2 = PyBytes::new(py, p.p2.as_bytes());
-            (p1, p2)
-        });
+        let p1 = PyBytes::new(py, parents.p1.as_bytes());
+        let p2 = PyBytes::new(py, parents.p2.as_bytes());
+        let parents = (p1, p2);
         Ok((map, parents).to_py_object(py).into_object())
     }
 
     /// Returns a DirstateMap
     @staticmethod
     def new_v2(
         on_disk: PyBytes,
         data_size: usize,
         tree_metadata: PyBytes,
     ) -> PyResult<PyObject> {
         let dirstate_error = |e: DirstateError| {
             PyErr::new::<exc::OSError, _>(py, format!("Dirstate error: {:?}", e))
         };
         let on_disk = PyBytesDeref::new(py, on_disk);
-        let mut map = OwningDirstateMap::new_empty(on_disk);
-        let (on_disk, map_placeholder) = map.get_pair_mut();
-        *map_placeholder = TreeDirstateMap::new_v2(
+        let map = OwningDirstateMap::new_v2(
             on_disk, data_size, tree_metadata.data(py),
         ).map_err(dirstate_error)?;
         let map = Self::create_instance(py, map)?;
         Ok(map.into_object())
     }
 
     def clear(&self) -> PyResult<PyObject> {
         self.inner(py).borrow_mut().clear();
         Ok(py.None())
     }
 
     def get(
         &self,
         key: PyObject,
         default: Option<PyObject> = None
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow()
             .get(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))?
         {
             Some(entry) => {
                 Ok(Some(DirstateItem::new_as_pyobject(py, entry)?))
             },
             None => Ok(default)
         }
     }
 
     def set_dirstate_item(
         &self,
         path: PyObject,
         item: DirstateItem
     ) -> PyResult<PyObject> {
         let f = path.extract::<PyBytes>(py)?;
         let filename = HgPath::new(f.data(py));
         self.inner(py)
             .borrow_mut()
             .set_entry(filename, item.get_entry(py))
             .map_err(|e| v2_error(py, e))?;
         Ok(py.None())
     }
 
     def addfile(
         &self,
         f: PyBytes,
         item: DirstateItem,
     ) -> PyResult<PyNone> {
         let filename = HgPath::new(f.data(py));
         let entry = item.get_entry(py);
         self.inner(py)
             .borrow_mut()
             .add_file(filename, entry)
             .map_err(|e |dirstate_error(py, e))?;
         Ok(PyNone)
     }
 
     def removefile(
         &self,
         f: PyObject,
         in_merge: PyObject
     ) -> PyResult<PyObject> {
         self.inner(py).borrow_mut()
             .remove_file(
                 HgPath::new(f.extract::<PyBytes>(py)?.data(py)),
                 in_merge.extract::<PyBool>(py)?.is_true(),
             )
             .or_else(|_| {
                 Err(PyErr::new::<exc::OSError, _>(
                     py,
                     "Dirstate error".to_string(),
                 ))
             })?;
         Ok(py.None())
     }
 
     def drop_item_and_copy_source(
         &self,
         f: PyBytes,
     ) -> PyResult<PyNone> {
         self.inner(py)
             .borrow_mut()
             .drop_entry_and_copy_source(HgPath::new(f.data(py)))
             .map_err(|e |dirstate_error(py, e))?;
         Ok(PyNone)
     }
 
     def hastrackeddir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_tracked_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def hasdir(&self, d: PyObject) -> PyResult<PyBool> {
         let d = d.extract::<PyBytes>(py)?;
         Ok(self.inner(py).borrow_mut()
             .has_dir(HgPath::new(d.data(py)))
             .map_err(|e| {
                 PyErr::new::<exc::ValueError, _>(py, e.to_string())
             })?
             .to_py_object(py))
     }
 
     def write_v1(
         &self,
         p1: PyObject,
         p2: PyObject,
     ) -> PyResult<PyBytes> {
         let inner = self.inner(py).borrow();
         let parents = DirstateParents {
             p1: extract_node_id(py, &p1)?,
             p2: extract_node_id(py, &p2)?,
         };
         let result = inner.pack_v1(parents);
         match result {
             Ok(packed) => Ok(PyBytes::new(py, &packed)),
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
 
     /// Returns new data together with whether that data should be appended to
     /// the existing data file whose content is at `self.on_disk` (True),
     /// instead of written to a new data file (False).
     def write_v2(
         &self,
         can_append: bool,
     ) -> PyResult<PyObject> {
         let inner = self.inner(py).borrow();
         let result = inner.pack_v2(can_append);
         match result {
             Ok((packed, tree_metadata, append)) => {
                 let packed = PyBytes::new(py, &packed);
                 let tree_metadata = PyBytes::new(py, tree_metadata.as_bytes());
                 let tuple = (packed, tree_metadata, append);
                 Ok(tuple.to_py_object(py).into_object())
             },
             Err(_) => Err(PyErr::new::<exc::OSError, _>(
                 py,
                 "Dirstate error".to_string(),
             )),
         }
     }
 
     def filefoldmapasdict(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for item in self.inner(py).borrow_mut().iter() {
             let (path, entry) = item.map_err(|e| v2_error(py, e))?;
             if entry.state() != EntryState::Removed {
                 let key = normalize_case(path);
                 let value = path;
                 dict.set_item(
                     py,
                     PyBytes::new(py, key.as_bytes()).into_object(),
                     PyBytes::new(py, value.as_bytes()).into_object(),
                 )?;
             }
         }
         Ok(dict)
     }
 
     def __len__(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().len())
     }
 
     def __contains__(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         self.inner(py)
             .borrow()
             .contains_key(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))
     }
 
     def __getitem__(&self, key: PyObject) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let key = HgPath::new(key.data(py));
         match self
             .inner(py)
             .borrow()
             .get(key)
             .map_err(|e| v2_error(py, e))?
         {
             Some(entry) => {
                 Ok(DirstateItem::new_as_pyobject(py, entry)?)
             },
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.as_bytes()),
             )),
         }
     }
 
     def keys(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def items(&self) -> PyResult<DirstateMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     def __iter__(&self) -> PyResult<DirstateMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         DirstateMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.iter()) },
         )
     }
 
     // TODO all copymap* methods, see docstring above
     def copymapcopy(&self) -> PyResult<PyDict> {
         let dict = PyDict::new(py);
         for item in self.inner(py).borrow().copy_map_iter() {
             let (key, value) = item.map_err(|e| v2_error(py, e))?;
             dict.set_item(
                 py,
                 PyBytes::new(py, key.as_bytes()),
                 PyBytes::new(py, value.as_bytes()),
             )?;
         }
         Ok(dict)
     }
 
     def copymapgetitem(&self, key: PyObject) -> PyResult<PyBytes> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow()
             .copy_map_get(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))?
         {
             Some(copy) => Ok(PyBytes::new(py, copy.as_bytes())),
             None => Err(PyErr::new::<exc::KeyError, _>(
                 py,
                 String::from_utf8_lossy(key.data(py)),
             )),
         }
     }
     def copymap(&self) -> PyResult<CopyMap> {
         CopyMap::from_inner(py, self.clone_ref(py))
     }
 
     def copymaplen(&self) -> PyResult<usize> {
         Ok(self.inner(py).borrow().copy_map_len())
     }
     def copymapcontains(&self, key: PyObject) -> PyResult<bool> {
         let key = key.extract::<PyBytes>(py)?;
         self.inner(py)
             .borrow()
             .copy_map_contains_key(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))
     }
     def copymapget(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow()
             .copy_map_get(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))?
         {
             Some(copy) => Ok(Some(
                 PyBytes::new(py, copy.as_bytes()).into_object(),
             )),
             None => Ok(default),
         }
     }
     def copymapsetitem(
         &self,
         key: PyObject,
         value: PyObject
     ) -> PyResult<PyObject> {
         let key = key.extract::<PyBytes>(py)?;
         let value = value.extract::<PyBytes>(py)?;
         self.inner(py)
             .borrow_mut()
             .copy_map_insert(
                 HgPathBuf::from_bytes(key.data(py)),
                 HgPathBuf::from_bytes(value.data(py)),
             )
             .map_err(|e| v2_error(py, e))?;
         Ok(py.None())
     }
     def copymappop(
         &self,
         key: PyObject,
         default: Option<PyObject>
     ) -> PyResult<Option<PyObject>> {
         let key = key.extract::<PyBytes>(py)?;
         match self
             .inner(py)
             .borrow_mut()
             .copy_map_remove(HgPath::new(key.data(py)))
             .map_err(|e| v2_error(py, e))?
         {
             Some(copy) => Ok(Some(
                 PyBytes::new(py, copy.as_bytes()).into_object(),
             )),
             None => Ok(default),
         }
     }
 
     def copymapiter(&self) -> PyResult<CopyMapKeysIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapKeysIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map_iter()) },
         )
     }
 
     def copymapitemsiter(&self) -> PyResult<CopyMapItemsIterator> {
         let leaked_ref = self.inner(py).leak_immutable();
         CopyMapItemsIterator::from_inner(
             py,
             unsafe { leaked_ref.map(py, |o| o.copy_map_iter()) },
         )
     }
 
     def tracked_dirs(&self) -> PyResult<PyList> {
         let dirs = PyList::new(py, &[]);
         for path in self.inner(py).borrow_mut().iter_tracked_dirs()
             .map_err(|e |dirstate_error(py, e))?
         {
             let path = path.map_err(|e| v2_error(py, e))?;
             let path = PyBytes::new(py, path.as_bytes());
             dirs.append(py, path.into_object())
         }
         Ok(dirs)
     }
 
     def debug_iter(&self, all: bool) -> PyResult<PyList> {
         let dirs = PyList::new(py, &[]);
         for item in self.inner(py).borrow().debug_iter(all) {
             let (path, (state, mode, size, mtime)) =
                 item.map_err(|e| v2_error(py, e))?;
             let path = PyBytes::new(py, path.as_bytes());
             let item = (path, state, mode, size, mtime);
             dirs.append(py, item.to_py_object(py).into_object())
         }
         Ok(dirs)
     }
 });
 
 impl DirstateMap {
     pub fn get_inner_mut<'a>(
         &'a self,
         py: Python<'a>,
     ) -> RefMut<'a, OwningDirstateMap> {
         self.inner(py).borrow_mut()
     }
     fn translate_key(
         py: Python,
         res: Result<(&HgPath, DirstateEntry), DirstateV2ParseError>,
     ) -> PyResult<Option<PyBytes>> {
         let (f, _entry) = res.map_err(|e| v2_error(py, e))?;
         Ok(Some(PyBytes::new(py, f.as_bytes())))
     }
     fn translate_key_value(
         py: Python,
         res: Result<(&HgPath, DirstateEntry), DirstateV2ParseError>,
     ) -> PyResult<Option<(PyBytes, PyObject)>> {
         let (f, entry) = res.map_err(|e| v2_error(py, e))?;
         Ok(Some((
             PyBytes::new(py, f.as_bytes()),
             DirstateItem::new_as_pyobject(py, entry)?,
         )))
     }
 }
 
 py_shared_iterator!(
     DirstateMapKeysIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key,
     Option<PyBytes>
 );
 
 py_shared_iterator!(
     DirstateMapItemsIterator,
     UnsafePyLeaked<StateMapIter<'static>>,
     DirstateMap::translate_key_value,
     Option<(PyBytes, PyObject)>
 );
 
 fn extract_node_id(py: Python, obj: &PyObject) -> PyResult<Node> {
     let bytes = obj.extract::<PyBytes>(py)?;
     match bytes.data(py).try_into() {
         Ok(s) => Ok(s),
         Err(e) => Err(PyErr::new::<exc::ValueError, _>(py, e.to_string())),
     }
 }
 
 pub(super) fn v2_error(py: Python<'_>, _: DirstateV2ParseError) -> PyErr {
     PyErr::new::<exc::ValueError, _>(py, "corrupted dirstate-v2")
 }
 
 fn dirstate_error(py: Python<'_>, e: DirstateError) -> PyErr {
     PyErr::new::<exc::OSError, _>(py, format!("Dirstate error: {:?}", e))
 }

rust/hg-cpython/src/dirstate/status.rs

@@ -1,303 +1,302 b''
 // status.rs
 //
 // Copyright 2019, Raphaël Gomès <[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.
 
 //! Bindings for the `hg::status` module provided by the
 //! `hg-core` crate. From Python, this will be seen as
 //! `rustext.dirstate.status`.
 
 use crate::{dirstate::DirstateMap, exceptions::FallbackError};
 use cpython::{
     exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
     PyResult, PyTuple, Python, PythonObject, ToPyObject,
 };
 use hg::dirstate::status::StatusPath;
 use hg::{
     matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
     parse_pattern_syntax,
     utils::{
         files::{get_bytes_from_path, get_path_from_bytes},
         hg_path::{HgPath, HgPathBuf},
     },
     BadMatch, DirstateStatus, IgnorePattern, PatternFileWarning, StatusError,
     StatusOptions,
 };
 use std::borrow::Borrow;
 
 fn collect_status_path_list(py: Python, paths: &[StatusPath<'_>]) -> PyList {
     collect_pybytes_list(py, paths.iter().map(|item| &*item.path))
 }
 
 /// This will be useless once trait impls for collection are added to `PyBytes`
 /// upstream.
 fn collect_pybytes_list(
     py: Python,
     iter: impl Iterator<Item = impl AsRef<HgPath>>,
 ) -> PyList {
     let list = PyList::new(py, &[]);
 
     for path in iter {
         list.append(
             py,
             PyBytes::new(py, path.as_ref().as_bytes()).into_object(),
         )
     }
 
     list
 }
 
 fn collect_bad_matches(
     py: Python,
     collection: &[(impl AsRef<HgPath>, BadMatch)],
 ) -> PyResult<PyList> {
     let list = PyList::new(py, &[]);
 
     let os = py.import("os")?;
     let get_error_message = |code: i32| -> PyResult<_> {
         os.call(
             py,
             "strerror",
             PyTuple::new(py, &[code.to_py_object(py).into_object()]),
             None,
         )
     };
 
     for (path, bad_match) in collection.iter() {
         let message = match bad_match {
             BadMatch::OsError(code) => get_error_message(*code)?,
             BadMatch::BadType(bad_type) => format!(
                 "unsupported file type (type is {})",
                 bad_type.to_string()
             )
             .to_py_object(py)
             .into_object(),
         };
         list.append(
             py,
             (PyBytes::new(py, path.as_ref().as_bytes()), message)
                 .to_py_object(py)
                 .into_object(),
         )
     }
 
     Ok(list)
 }
 
 fn handle_fallback(py: Python, err: StatusError) -> PyErr {
     match err {
         StatusError::Pattern(e) => {
             let as_string = e.to_string();
             log::trace!("Rust status fallback: `{}`", &as_string);
 
             PyErr::new::<FallbackError, _>(py, &as_string)
         }
         e => PyErr::new::<ValueError, _>(py, e.to_string()),
     }
 }
 
 pub fn status_wrapper(
     py: Python,
     dmap: DirstateMap,
     matcher: PyObject,
     root_dir: PyObject,
     ignore_files: PyList,
     check_exec: bool,
     list_clean: bool,
     list_ignored: bool,
     list_unknown: bool,
     collect_traversed_dirs: bool,
 ) -> PyResult<PyTuple> {
     let bytes = root_dir.extract::<PyBytes>(py)?;
     let root_dir = get_path_from_bytes(bytes.data(py));
 
     let dmap: DirstateMap = dmap.to_py_object(py);
     let mut dmap = dmap.get_inner_mut(py);
 
     let ignore_files: PyResult<Vec<_>> = ignore_files
         .iter(py)
         .map(|b| {
             let file = b.extract::<PyBytes>(py)?;
             Ok(get_path_from_bytes(file.data(py)).to_owned())
         })
         .collect();
     let ignore_files = ignore_files?;
     // The caller may call `copymap.items()` separately
     let list_copies = false;
 
+    let after_status = |res: Result<(DirstateStatus<'_>, _), StatusError>| {
+        let (status_res, warnings) =
+            res.map_err(|e| handle_fallback(py, e))?;
+        build_response(py, status_res, warnings)
+    };
+
     match matcher.get_type(py).name(py).borrow() {
         "alwaysmatcher" => {
             let matcher = AlwaysMatcher;
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         "exactmatcher" => {
             let files = matcher.call_method(
                 py,
                 "files",
                 PyTuple::new(py, &[]),
                 None,
             )?;
             let files: PyList = files.cast_into(py)?;
             let files: PyResult<Vec<HgPathBuf>> = files
                 .iter(py)
                 .map(|f| {
                     Ok(HgPathBuf::from_bytes(
                         f.extract::<PyBytes>(py)?.data(py),
                     ))
                 })
                 .collect();
 
             let files = files?;
             let matcher = FileMatcher::new(files.as_ref())
                 .map_err(|e| PyErr::new::<ValueError, _>(py, e.to_string()))?;
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         "includematcher" => {
             // Get the patterns from Python even though most of them are
             // redundant with those we will parse later on, as they include
             // those passed from the command line.
             let ignore_patterns: PyResult<Vec<_>> = matcher
                 .getattr(py, "_kindpats")?
                 .iter(py)?
                 .map(|k| {
                     let k = k?;
                     let syntax = parse_pattern_syntax(
                         &[
                             k.get_item(py, 0)?
                                 .extract::<PyBytes>(py)?
                                 .data(py),
                             &b":"[..],
                         ]
                         .concat(),
                     )
                     .map_err(|e| {
                         handle_fallback(py, StatusError::Pattern(e))
                     })?;
                     let pattern = k.get_item(py, 1)?.extract::<PyBytes>(py)?;
                     let pattern = pattern.data(py);
                     let source = k.get_item(py, 2)?.extract::<PyBytes>(py)?;
                     let source = get_path_from_bytes(source.data(py));
                     let new = IgnorePattern::new(syntax, pattern, source);
                     Ok(new)
                 })
                 .collect();
 
             let ignore_patterns = ignore_patterns?;
 
             let matcher = IncludeMatcher::new(ignore_patterns)
                 .map_err(|e| handle_fallback(py, e.into()))?;
 
-            let (status_res, warnings) = dmap
-                .status(
-                    &matcher,
-                    root_dir.to_path_buf(),
-                    ignore_files,
-                    StatusOptions {
-                        check_exec,
-                        list_clean,
-                        list_ignored,
-                        list_unknown,
-                        list_copies,
-                        collect_traversed_dirs,
-                    },
-                )
-                .map_err(|e| handle_fallback(py, e))?;
-
-            build_response(py, status_res, warnings)
+            dmap.with_status(
+                &matcher,
+                root_dir.to_path_buf(),
+                ignore_files,
+                StatusOptions {
+                    check_exec,
+                    list_clean,
+                    list_ignored,
+                    list_unknown,
+                    list_copies,
+                    collect_traversed_dirs,
+                },
+                after_status,
+            )
         }
         e => Err(PyErr::new::<ValueError, _>(
             py,
             format!("Unsupported matcher {}", e),
         )),
     }
 }
 
 fn build_response(
     py: Python,
     status_res: DirstateStatus,
     warnings: Vec<PatternFileWarning>,
 ) -> PyResult<PyTuple> {
     let modified = collect_status_path_list(py, &status_res.modified);
     let added = collect_status_path_list(py, &status_res.added);
     let removed = collect_status_path_list(py, &status_res.removed);
     let deleted = collect_status_path_list(py, &status_res.deleted);
     let clean = collect_status_path_list(py, &status_res.clean);
     let ignored = collect_status_path_list(py, &status_res.ignored);
     let unknown = collect_status_path_list(py, &status_res.unknown);
     let unsure = collect_status_path_list(py, &status_res.unsure);
     let bad = collect_bad_matches(py, &status_res.bad)?;
     let traversed = collect_pybytes_list(py, status_res.traversed.iter());
     let dirty = status_res.dirty.to_py_object(py);
     let py_warnings = PyList::new(py, &[]);
     for warning in warnings.iter() {
         // We use duck-typing on the Python side for dispatch, good enough for
         // now.
         match warning {
             PatternFileWarning::InvalidSyntax(file, syn) => {
                 py_warnings.append(
                     py,
                     (
                         PyBytes::new(py, &get_bytes_from_path(&file)),
                         PyBytes::new(py, syn),
                     )
                         .to_py_object(py)
                         .into_object(),
                 );
             }
             PatternFileWarning::NoSuchFile(file) => py_warnings.append(
                 py,
                 PyBytes::new(py, &get_bytes_from_path(&file)).into_object(),
             ),
         }
     }
 
     Ok(PyTuple::new(
         py,
         &[
             unsure.into_object(),
             modified.into_object(),
             added.into_object(),
             removed.into_object(),
             deleted.into_object(),
             clean.into_object(),
             ignored.into_object(),
             unknown.into_object(),
             py_warnings.into_object(),
             bad.into_object(),
             traversed.into_object(),
             dirty.into_object(),
         ][..],
     ))
 }

rust/rhg/src/commands/status.rs

@@ -1,531 +1,549 b''
 // status.rs
 //
 // Copyright 2020, Georges Racinet <[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.
 
 use crate::error::CommandError;
 use crate::ui::Ui;
 use crate::utils::path_utils::RelativizePaths;
 use clap::{Arg, SubCommand};
 use format_bytes::format_bytes;
 use hg;
 use hg::config::Config;
 use hg::dirstate::has_exec_bit;
 use hg::dirstate::status::StatusPath;
 use hg::dirstate::TruncatedTimestamp;
 use hg::dirstate::RANGE_MASK_31BIT;
 use hg::errors::{HgError, IoResultExt};
 use hg::lock::LockError;
 use hg::manifest::Manifest;
 use hg::matchers::AlwaysMatcher;
 use hg::repo::Repo;
 use hg::utils::files::get_bytes_from_os_string;
 use hg::utils::files::get_bytes_from_path;
 use hg::utils::files::get_path_from_bytes;
 use hg::utils::hg_path::{hg_path_to_path_buf, HgPath};
+use hg::DirstateStatus;
+use hg::PatternFileWarning;
+use hg::StatusError;
 use hg::StatusOptions;
 use log::info;
 use std::io;
 use std::path::PathBuf;
 
 pub const HELP_TEXT: &str = "
 Show changed files in the working directory
 
 This is a pure Rust version of `hg status`.
 
 Some options might be missing, check the list below.
 ";
 
 pub fn args() -> clap::App<'static, 'static> {
     SubCommand::with_name("status")
         .alias("st")
         .about(HELP_TEXT)
         .arg(
             Arg::with_name("all")
                 .help("show status of all files")
                 .short("-A")
                 .long("--all"),
         )
         .arg(
             Arg::with_name("modified")
                 .help("show only modified files")
                 .short("-m")
                 .long("--modified"),
         )
         .arg(
             Arg::with_name("added")
                 .help("show only added files")
                 .short("-a")
                 .long("--added"),
         )
         .arg(
             Arg::with_name("removed")
                 .help("show only removed files")
                 .short("-r")
                 .long("--removed"),
         )
         .arg(
             Arg::with_name("clean")
                 .help("show only clean files")
                 .short("-c")
                 .long("--clean"),
         )
         .arg(
             Arg::with_name("deleted")
                 .help("show only deleted files")
                 .short("-d")
                 .long("--deleted"),
         )
         .arg(
             Arg::with_name("unknown")
                 .help("show only unknown (not tracked) files")
                 .short("-u")
                 .long("--unknown"),
         )
         .arg(
             Arg::with_name("ignored")
                 .help("show only ignored files")
                 .short("-i")
                 .long("--ignored"),
         )
         .arg(
             Arg::with_name("copies")
                 .help("show source of copied files (DEFAULT: ui.statuscopies)")
                 .short("-C")
                 .long("--copies"),
         )
         .arg(
             Arg::with_name("no-status")
                 .help("hide status prefix")
                 .short("-n")
                 .long("--no-status"),
         )
 }
 
 /// Pure data type allowing the caller to specify file states to display
 #[derive(Copy, Clone, Debug)]
 pub struct DisplayStates {
     pub modified: bool,
     pub added: bool,
     pub removed: bool,
     pub clean: bool,
     pub deleted: bool,
     pub unknown: bool,
     pub ignored: bool,
 }
 
 pub const DEFAULT_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: false,
     deleted: true,
     unknown: true,
     ignored: false,
 };
 
 pub const ALL_DISPLAY_STATES: DisplayStates = DisplayStates {
     modified: true,
     added: true,
     removed: true,
     clean: true,
     deleted: true,
     unknown: true,
     ignored: true,
 };
 
 impl DisplayStates {
     pub fn is_empty(&self) -> bool {
         !(self.modified
             || self.added
             || self.removed
             || self.clean
             || self.deleted
             || self.unknown
             || self.ignored)
     }
 }
 
 pub fn run(invocation: &crate::CliInvocation) -> Result<(), CommandError> {
     // TODO: lift these limitations
     if invocation.config.get_bool(b"ui", b"tweakdefaults")? {
         return Err(CommandError::unsupported(
             "ui.tweakdefaults is not yet supported with rhg status",
         ));
     }
     if invocation.config.get_bool(b"ui", b"statuscopies")? {
         return Err(CommandError::unsupported(
             "ui.statuscopies is not yet supported with rhg status",
         ));
     }
     if invocation
         .config
         .get(b"commands", b"status.terse")
         .is_some()
     {
         return Err(CommandError::unsupported(
             "status.terse is not yet supported with rhg status",
         ));
     }
 
     let ui = invocation.ui;
     let config = invocation.config;
     let args = invocation.subcommand_args;
 
     let verbose = !ui.plain(None)
         && !args.is_present("print0")
         && (config.get_bool(b"ui", b"verbose")?
             || config.get_bool(b"commands", b"status.verbose")?);
     if verbose {
         return Err(CommandError::unsupported(
             "verbose status is not supported yet",
         ));
     }
 
     let all = args.is_present("all");
     let display_states = if all {
         // TODO when implementing `--quiet`: it excludes clean files
         // from `--all`
         ALL_DISPLAY_STATES
     } else {
         let requested = DisplayStates {
             modified: args.is_present("modified"),
             added: args.is_present("added"),
             removed: args.is_present("removed"),
             clean: args.is_present("clean"),
             deleted: args.is_present("deleted"),
             unknown: args.is_present("unknown"),
             ignored: args.is_present("ignored"),
         };
         if requested.is_empty() {
             DEFAULT_DISPLAY_STATES
         } else {
             requested
         }
     };
     let no_status = args.is_present("no-status");
     let list_copies = all
         || args.is_present("copies")
         || config.get_bool(b"ui", b"statuscopies")?;
 
     let repo = invocation.repo?;
 
     if repo.has_sparse() || repo.has_narrow() {
         return Err(CommandError::unsupported(
             "rhg status is not supported for sparse checkouts or narrow clones yet"
         ));
     }
 
     let mut dmap = repo.dirstate_map_mut()?;
 
     let options = StatusOptions {
         // we're currently supporting file systems with exec flags only
         // anyway
         check_exec: true,
         list_clean: display_states.clean,
         list_unknown: display_states.unknown,
         list_ignored: display_states.ignored,
         list_copies,
         collect_traversed_dirs: false,
     };
-    let (mut ds_status, pattern_warnings) = dmap.status(
-        &AlwaysMatcher,
-        repo.working_directory_path().to_owned(),
-        ignore_files(repo, config),
-        options,
-    )?;
-    for warning in pattern_warnings {
-        match warning {
-            hg::PatternFileWarning::InvalidSyntax(path, syntax) => ui
-                .write_stderr(&format_bytes!(
-                    b"{}: ignoring invalid syntax '{}'\n",
-                    get_bytes_from_path(path),
-                    &*syntax
-                ))?,
-            hg::PatternFileWarning::NoSuchFile(path) => {
-                let path = if let Ok(relative) =
-                    path.strip_prefix(repo.working_directory_path())
-                {
-                    relative
-                } else {
-                    &*path
-                };
-                ui.write_stderr(&format_bytes!(
-                    b"skipping unreadable pattern file '{}': \
-                      No such file or directory\n",
-                    get_bytes_from_path(path),
-                ))?
+
+    type StatusResult<'a> =
+        Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>;
+
+    let after_status = |res: StatusResult| -> Result<_, CommandError> {
+        let (mut ds_status, pattern_warnings) = res?;
+        for warning in pattern_warnings {
+            match warning {
+                hg::PatternFileWarning::InvalidSyntax(path, syntax) => ui
+                    .write_stderr(&format_bytes!(
+                        b"{}: ignoring invalid syntax '{}'\n",
+                        get_bytes_from_path(path),
+                        &*syntax
+                    ))?,
+                hg::PatternFileWarning::NoSuchFile(path) => {
+                    let path = if let Ok(relative) =
+                        path.strip_prefix(repo.working_directory_path())
+                    {
+                        relative
+                    } else {
+                        &*path
+                    };
+                    ui.write_stderr(&format_bytes!(
+                        b"skipping unreadable pattern file '{}': \
+                          No such file or directory\n",
+                        get_bytes_from_path(path),
+                    ))?
+                }
             }
         }
-    }
 
-    for (path, error) in ds_status.bad {
-        let error = match error {
-            hg::BadMatch::OsError(code) => {
-                std::io::Error::from_raw_os_error(code).to_string()
-            }
-            hg::BadMatch::BadType(ty) => {
-                format!("unsupported file type (type is {})", ty)
-            }
-        };
-        ui.write_stderr(&format_bytes!(
-            b"{}: {}\n",
-            path.as_bytes(),
-            error.as_bytes()
-        ))?
-    }
-    if !ds_status.unsure.is_empty() {
-        info!(
-            "Files to be rechecked by retrieval from filelog: {:?}",
-            ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
-        );
-    }
-    let mut fixup = Vec::new();
-    if !ds_status.unsure.is_empty()
-        && (display_states.modified || display_states.clean)
-    {
-        let p1 = repo.dirstate_parents()?.p1;
-        let manifest = repo.manifest_for_node(p1).map_err(|e| {
-            CommandError::from((e, &*format!("{:x}", p1.short())))
-        })?;
-        for to_check in ds_status.unsure {
-            if unsure_is_modified(repo, &manifest, &to_check.path)? {
-                if display_states.modified {
-                    ds_status.modified.push(to_check);
+        for (path, error) in ds_status.bad {
+            let error = match error {
+                hg::BadMatch::OsError(code) => {
+                    std::io::Error::from_raw_os_error(code).to_string()
+                }
+                hg::BadMatch::BadType(ty) => {
+                    format!("unsupported file type (type is {})", ty)
                 }
-            } else {
-                if display_states.clean {
-                    ds_status.clean.push(to_check.clone());
+            };
+            ui.write_stderr(&format_bytes!(
+                b"{}: {}\n",
+                path.as_bytes(),
+                error.as_bytes()
+            ))?
+        }
+        if !ds_status.unsure.is_empty() {
+            info!(
+                "Files to be rechecked by retrieval from filelog: {:?}",
+                ds_status.unsure.iter().map(|s| &s.path).collect::<Vec<_>>()
+            );
+        }
+        let mut fixup = Vec::new();
+        if !ds_status.unsure.is_empty()
+            && (display_states.modified || display_states.clean)
+        {
+            let p1 = repo.dirstate_parents()?.p1;
+            let manifest = repo.manifest_for_node(p1).map_err(|e| {
+                CommandError::from((e, &*format!("{:x}", p1.short())))
+            })?;
+            for to_check in ds_status.unsure {
+                if unsure_is_modified(repo, &manifest, &to_check.path)? {
+                    if display_states.modified {
+                        ds_status.modified.push(to_check);
+                    }
+                } else {
+                    if display_states.clean {
+                        ds_status.clean.push(to_check.clone());
+                    }
+                    fixup.push(to_check.path.into_owned())
                 }
-                fixup.push(to_check.path.into_owned())
             }
         }
-    }
-    let relative_paths = (!ui.plain(None))
-        && config
-            .get_option(b"commands", b"status.relative")?
-            .unwrap_or(config.get_bool(b"ui", b"relative-paths")?);
-    let output = DisplayStatusPaths {
-        ui,
-        no_status,
-        relativize: if relative_paths {
-            Some(RelativizePaths::new(repo)?)
-        } else {
-            None
-        },
+        let relative_paths = (!ui.plain(None))
+            && config
+                .get_option(b"commands", b"status.relative")?
+                .unwrap_or(config.get_bool(b"ui", b"relative-paths")?);
+        let output = DisplayStatusPaths {
+            ui,
+            no_status,
+            relativize: if relative_paths {
+                Some(RelativizePaths::new(repo)?)
+            } else {
+                None
+            },
+        };
+        if display_states.modified {
+            output.display(b"M ", "status.modified", ds_status.modified)?;
+        }
+        if display_states.added {
+            output.display(b"A ", "status.added", ds_status.added)?;
+        }
+        if display_states.removed {
+            output.display(b"R ", "status.removed", ds_status.removed)?;
+        }
+        if display_states.deleted {
+            output.display(b"! ", "status.deleted", ds_status.deleted)?;
+        }
+        if display_states.unknown {
+            output.display(b"? ", "status.unknown", ds_status.unknown)?;
+        }
+        if display_states.ignored {
+            output.display(b"I ", "status.ignored", ds_status.ignored)?;
+        }
+        if display_states.clean {
+            output.display(b"C ", "status.clean", ds_status.clean)?;
+        }
+
+        let dirstate_write_needed = ds_status.dirty;
+        let filesystem_time_at_status_start =
+            ds_status.filesystem_time_at_status_start;
+
+        Ok((
+            fixup,
+            dirstate_write_needed,
+            filesystem_time_at_status_start,
+        ))
     };
-    if display_states.modified {
-        output.display(b"M ", "status.modified", ds_status.modified)?;
-    }
-    if display_states.added {
-        output.display(b"A ", "status.added", ds_status.added)?;
-    }
-    if display_states.removed {
-        output.display(b"R ", "status.removed", ds_status.removed)?;
-    }
-    if display_states.deleted {
-        output.display(b"! ", "status.deleted", ds_status.deleted)?;
-    }
-    if display_states.unknown {
-        output.display(b"? ", "status.unknown", ds_status.unknown)?;
-    }
-    if display_states.ignored {
-        output.display(b"I ", "status.ignored", ds_status.ignored)?;
-    }
-    if display_states.clean {
-        output.display(b"C ", "status.clean", ds_status.clean)?;
-    }
-
-    let mut dirstate_write_needed = ds_status.dirty;
-    let filesystem_time_at_status_start =
-        ds_status.filesystem_time_at_status_start;
+    let (fixup, mut dirstate_write_needed, filesystem_time_at_status_start) =
+        dmap.with_status(
+            &AlwaysMatcher,
+            repo.working_directory_path().to_owned(),
+            ignore_files(repo, config),
+            options,
+            after_status,
+        )?;
 
     if (fixup.is_empty() || filesystem_time_at_status_start.is_none())
         && !dirstate_write_needed
     {
         // Nothing to update
         return Ok(());
     }
 
     // Update the dirstate on disk if we can
     let with_lock_result =
         repo.try_with_wlock_no_wait(|| -> Result<(), CommandError> {
             if let Some(mtime_boundary) = filesystem_time_at_status_start {
                 for hg_path in fixup {
                     use std::os::unix::fs::MetadataExt;
                     let fs_path = hg_path_to_path_buf(&hg_path)
                         .expect("HgPath conversion");
                     // Specifically do not reuse `fs_metadata` from
                     // `unsure_is_clean` which was needed before reading
                     // contents. Here we access metadata again after reading
                     // content, in case it changed in the meantime.
                     let fs_metadata = repo
                         .working_directory_vfs()
                         .symlink_metadata(&fs_path)?;
                     if let Some(mtime) =
                         TruncatedTimestamp::for_reliable_mtime_of(
                             &fs_metadata,
                             &mtime_boundary,
                         )
                         .when_reading_file(&fs_path)?
                     {
                         let mode = fs_metadata.mode();
                         let size = fs_metadata.len() as u32 & RANGE_MASK_31BIT;
                         let mut entry = dmap
                             .get(&hg_path)?
                             .expect("ambiguous file not in dirstate");
                         entry.set_clean(mode, size, mtime);
                         dmap.add_file(&hg_path, entry)?;
                         dirstate_write_needed = true
                     }
                 }
             }
             drop(dmap); // Avoid "already mutably borrowed" RefCell panics
             if dirstate_write_needed {
                 repo.write_dirstate()?
             }
             Ok(())
         });
     match with_lock_result {
         Ok(closure_result) => closure_result?,
         Err(LockError::AlreadyHeld) => {
             // Not updating the dirstate is not ideal but not critical:
             // don’t keep our caller waiting until some other Mercurial
             // process releases the lock.
         }
         Err(LockError::Other(HgError::IoError { error, .. }))
             if error.kind() == io::ErrorKind::PermissionDenied =>
         {
             // `hg status` on a read-only repository is fine
         }
         Err(LockError::Other(error)) => {
             // Report other I/O errors
             Err(error)?
         }
     }
     Ok(())
 }
 
 fn ignore_files(repo: &Repo, config: &Config) -> Vec<PathBuf> {
     let mut ignore_files = Vec::new();
     let repo_ignore = repo.working_directory_vfs().join(".hgignore");
     if repo_ignore.exists() {
         ignore_files.push(repo_ignore)
     }
     for (key, value) in config.iter_section(b"ui") {
         if key == b"ignore" || key.starts_with(b"ignore.") {
             let path = get_path_from_bytes(value);
             // TODO: expand "~/" and environment variable here, like Python
             // does with `os.path.expanduser` and `os.path.expandvars`
 
             let joined = repo.working_directory_path().join(path);
             ignore_files.push(joined);
         }
     }
     ignore_files
 }
 
 struct DisplayStatusPaths<'a> {
     ui: &'a Ui,
     no_status: bool,
     relativize: Option<RelativizePaths>,
 }
 
 impl DisplayStatusPaths<'_> {
     // Probably more elegant to use a Deref or Borrow trait rather than
     // harcode HgPathBuf, but probably not really useful at this point
     fn display(
         &self,
         status_prefix: &[u8],
         label: &'static str,
         mut paths: Vec<StatusPath<'_>>,
     ) -> Result<(), CommandError> {
         paths.sort_unstable();
         // TODO: get the stdout lock once for the whole loop
         // instead of in each write
         for StatusPath { path, copy_source } in paths {
             let relative;
             let path = if let Some(relativize) = &self.relativize {
                 relative = relativize.relativize(&path);
                 &*relative
             } else {
                 path.as_bytes()
             };
             // TODO: Add a way to use `write_bytes!` instead of `format_bytes!`
             // in order to stream to stdout instead of allocating an
             // itermediate `Vec<u8>`.
             if !self.no_status {
                 self.ui.write_stdout_labelled(status_prefix, label)?
             }
             self.ui
                 .write_stdout_labelled(&format_bytes!(b"{}\n", path), label)?;
             if let Some(source) = copy_source {
                 let label = "status.copied";
                 self.ui.write_stdout_labelled(
                     &format_bytes!(b"  {}\n", source.as_bytes()),
                     label,
                 )?
             }
         }
         Ok(())
     }
 }
 
 /// Check if a file is modified by comparing actual repo store and file system.
 ///
 /// This meant to be used for those that the dirstate cannot resolve, due
 /// to time resolution limits.
 fn unsure_is_modified(
     repo: &Repo,
     manifest: &Manifest,
     hg_path: &HgPath,
 ) -> Result<bool, HgError> {
     let vfs = repo.working_directory_vfs();
     let fs_path = hg_path_to_path_buf(hg_path).expect("HgPath conversion");
     let fs_metadata = vfs.symlink_metadata(&fs_path)?;
     let is_symlink = fs_metadata.file_type().is_symlink();
     // TODO: Also account for `FALLBACK_SYMLINK` and `FALLBACK_EXEC` from the
     // dirstate
     let fs_flags = if is_symlink {
         Some(b'l')
     } else if has_exec_bit(&fs_metadata) {
         Some(b'x')
     } else {
         None
     };
 
     let entry = manifest
         .find_by_path(hg_path)?
         .expect("ambgious file not in p1");
     if entry.flags != fs_flags {
         return Ok(true);
     }
     let filelog = repo.filelog(hg_path)?;
     let fs_len = fs_metadata.len();
     let filelog_entry =
         filelog.entry_for_node(entry.node_id()?).map_err(|_| {
             HgError::corrupted("filelog missing node from manifest")
         })?;
     if filelog_entry.file_data_len_not_equal_to(fs_len) {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(true);
     }
 
     let p1_filelog_data = filelog_entry.data()?;
     let p1_contents = p1_filelog_data.file_data()?;
     if p1_contents.len() as u64 != fs_len {
         // No need to read file contents:
         // it cannot be equal if it has a different length.
         return Ok(true);
     }
 
     let fs_contents = if is_symlink {
         get_bytes_from_os_string(vfs.read_link(fs_path)?.into_os_string())
     } else {
         vfs.read(fs_path)?
     };
     Ok(p1_contents != &*fs_contents)
 }