match: delete unused root and cwd arguments to constructors (API)

Most matchers no longer need the root and cwd
arguments. patternmatcher and includematcher still need the root
argument for subincludes.

Differential Revision: https://phab.mercurial-scm.org/D5929

hgext/sparse.py

@@ -1,347 +1,347 b''
 # sparse.py - allow sparse checkouts of the working directory
 #
 # Copyright 2014 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """allow sparse checkouts of the working directory (EXPERIMENTAL)
 
 (This extension is not yet protected by backwards compatibility
 guarantees. Any aspect may break in future releases until this
 notice is removed.)
 
 This extension allows the working directory to only consist of a
 subset of files for the revision. This allows specific files or
 directories to be explicitly included or excluded. Many repository
 operations have performance proportional to the number of files in
 the working directory. So only realizing a subset of files in the
 working directory can improve performance.
 
 Sparse Config Files
 -------------------
 
 The set of files that are part of a sparse checkout are defined by
 a sparse config file. The file defines 3 things: includes (files to
 include in the sparse checkout), excludes (files to exclude from the
 sparse checkout), and profiles (links to other config files).
 
 The file format is newline delimited. Empty lines and lines beginning
 with ``#`` are ignored.
 
 Lines beginning with ``%include `` denote another sparse config file
 to include. e.g. ``%include tests.sparse``. The filename is relative
 to the repository root.
 
 The special lines ``[include]`` and ``[exclude]`` denote the section
 for includes and excludes that follow, respectively. It is illegal to
 have ``[include]`` after ``[exclude]``.
 
 Non-special lines resemble file patterns to be added to either includes
 or excludes. The syntax of these lines is documented by :hg:`help patterns`.
 Patterns are interpreted as ``glob:`` by default and match against the
 root of the repository.
 
 Exclusion patterns take precedence over inclusion patterns. So even
 if a file is explicitly included, an ``[exclude]`` entry can remove it.
 
 For example, say you have a repository with 3 directories, ``frontend/``,
 ``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond
 to different projects and it is uncommon for someone working on one
 to need the files for the other. But ``tools/`` contains files shared
 between both projects. Your sparse config files may resemble::
 
   # frontend.sparse
   frontend/**
   tools/**
 
   # backend.sparse
   backend/**
   tools/**
 
 Say the backend grows in size. Or there's a directory with thousands
 of files you wish to exclude. You can modify the profile to exclude
 certain files::
 
   [include]
   backend/**
   tools/**
 
   [exclude]
   tools/tests/**
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     commands,
     dirstate,
     error,
     extensions,
     hg,
     logcmdutil,
     match as matchmod,
     pycompat,
     registrar,
     sparse,
     util,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 def extsetup(ui):
     sparse.enabled = True
 
     _setupclone(ui)
     _setuplog(ui)
     _setupadd(ui)
     _setupdirstate(ui)
 
 def replacefilecache(cls, propname, replacement):
     """Replace a filecache property with a new class. This allows changing the
     cache invalidation condition."""
     origcls = cls
     assert callable(replacement)
     while cls is not object:
         if propname in cls.__dict__:
             orig = cls.__dict__[propname]
             setattr(cls, propname, replacement(orig))
             break
         cls = cls.__bases__[0]
 
     if cls is object:
         raise AttributeError(_("type '%s' has no property '%s'") % (origcls,
                              propname))
 
 def _setuplog(ui):
     entry = commands.table['log|history']
     entry[1].append(('', 'sparse', None,
         "limit to changesets affecting the sparse checkout"))
 
     def _initialrevs(orig, repo, opts):
         revs = orig(repo, opts)
         if opts.get('sparse'):
             sparsematch = sparse.matcher(repo)
             def ctxmatch(rev):
                 ctx = repo[rev]
                 return any(f for f in ctx.files() if sparsematch(f))
             revs = revs.filter(ctxmatch)
         return revs
     extensions.wrapfunction(logcmdutil, '_initialrevs', _initialrevs)
 
 def _clonesparsecmd(orig, ui, repo, *args, **opts):
     include_pat = opts.get(r'include')
     exclude_pat = opts.get(r'exclude')
     enableprofile_pat = opts.get(r'enable_profile')
     narrow_pat = opts.get(r'narrow')
     include = exclude = enableprofile = False
     if include_pat:
         pat = include_pat
         include = True
     if exclude_pat:
         pat = exclude_pat
         exclude = True
     if enableprofile_pat:
         pat = enableprofile_pat
         enableprofile = True
     if sum([include, exclude, enableprofile]) > 1:
         raise error.Abort(_("too many flags specified."))
     # if --narrow is passed, it means they are includes and excludes for narrow
     # clone
     if not narrow_pat and (include or exclude or enableprofile):
         def clonesparse(orig, self, node, overwrite, *args, **kwargs):
             sparse.updateconfig(self.unfiltered(), pat, {}, include=include,
                                 exclude=exclude, enableprofile=enableprofile,
                                 usereporootpaths=True)
             return orig(self, node, overwrite, *args, **kwargs)
         extensions.wrapfunction(hg, 'updaterepo', clonesparse)
     return orig(ui, repo, *args, **opts)
 
 def _setupclone(ui):
     entry = commands.table['clone']
     entry[1].append(('', 'enable-profile', [],
                     'enable a sparse profile'))
     entry[1].append(('', 'include', [],
                     'include sparse pattern'))
     entry[1].append(('', 'exclude', [],
                     'exclude sparse pattern'))
     extensions.wrapcommand(commands.table, 'clone', _clonesparsecmd)
 
 def _setupadd(ui):
     entry = commands.table['add']
     entry[1].append(('s', 'sparse', None,
                     'also include directories of added files in sparse config'))
 
     def _add(orig, ui, repo, *pats, **opts):
         if opts.get(r'sparse'):
             dirs = set()
             for pat in pats:
                 dirname, basename = util.split(pat)
                 dirs.add(dirname)
             sparse.updateconfig(repo, list(dirs), opts, include=True)
         return orig(ui, repo, *pats, **opts)
 
     extensions.wrapcommand(commands.table, 'add', _add)
 
 def _setupdirstate(ui):
     """Modify the dirstate to prevent stat'ing excluded files,
     and to prevent modifications to files outside the checkout.
     """
 
     def walk(orig, self, match, subrepos, unknown, ignored, full=True):
         # hack to not exclude explicitly-specified paths so that they can
         # be warned later on e.g. dirstate.add()
-        em = matchmod.exact(match._root, match._cwd, match.files())
+        em = matchmod.exact(None, None, match.files())
         sm = matchmod.unionmatcher([self._sparsematcher, em])
         match = matchmod.intersectmatchers(match, sm)
         return orig(self, match, subrepos, unknown, ignored, full)
 
     extensions.wrapfunction(dirstate.dirstate, 'walk', walk)
 
     # dirstate.rebuild should not add non-matching files
     def _rebuild(orig, self, parent, allfiles, changedfiles=None):
         matcher = self._sparsematcher
         if not matcher.always():
             allfiles = [f for f in allfiles if matcher(f)]
             if changedfiles:
                 changedfiles = [f for f in changedfiles if matcher(f)]
 
             if changedfiles is not None:
                 # In _rebuild, these files will be deleted from the dirstate
                 # when they are not found to be in allfiles
                 dirstatefilestoremove = set(f for f in self if not matcher(f))
                 changedfiles = dirstatefilestoremove.union(changedfiles)
 
         return orig(self, parent, allfiles, changedfiles)
     extensions.wrapfunction(dirstate.dirstate, 'rebuild', _rebuild)
 
     # Prevent adding files that are outside the sparse checkout
     editfuncs = ['normal', 'add', 'normallookup', 'copy', 'remove', 'merge']
     hint = _('include file with `hg debugsparse --include <pattern>` or use ' +
              '`hg add -s <file>` to include file directory while adding')
     for func in editfuncs:
         def _wrapper(orig, self, *args):
             sparsematch = self._sparsematcher
             if not sparsematch.always():
                 for f in args:
                     if (f is not None and not sparsematch(f) and
                         f not in self):
                         raise error.Abort(_("cannot add '%s' - it is outside "
                                             "the sparse checkout") % f,
                                           hint=hint)
             return orig(self, *args)
         extensions.wrapfunction(dirstate.dirstate, func, _wrapper)
 
 @command('debugsparse', [
     ('I', 'include', False, _('include files in the sparse checkout')),
     ('X', 'exclude', False, _('exclude files in the sparse checkout')),
     ('d', 'delete', False, _('delete an include/exclude rule')),
     ('f', 'force', False, _('allow changing rules even with pending changes')),
     ('', 'enable-profile', False, _('enables the specified profile')),
     ('', 'disable-profile', False, _('disables the specified profile')),
     ('', 'import-rules', False, _('imports rules from a file')),
     ('', 'clear-rules', False, _('clears local include/exclude rules')),
     ('', 'refresh', False, _('updates the working after sparseness changes')),
     ('', 'reset', False, _('makes the repo full again')),
     ] + commands.templateopts,
     _('[--OPTION] PATTERN...'),
     helpbasic=True)
 def debugsparse(ui, repo, *pats, **opts):
     """make the current checkout sparse, or edit the existing checkout
 
     The sparse command is used to make the current checkout sparse.
     This means files that don't meet the sparse condition will not be
     written to disk, or show up in any working copy operations. It does
     not affect files in history in any way.
 
     Passing no arguments prints the currently applied sparse rules.
 
     --include and --exclude are used to add and remove files from the sparse
     checkout. The effects of adding an include or exclude rule are applied
     immediately. If applying the new rule would cause a file with pending
     changes to be added or removed, the command will fail. Pass --force to
     force a rule change even with pending changes (the changes on disk will
     be preserved).
 
     --delete removes an existing include/exclude rule. The effects are
     immediate.
 
     --refresh refreshes the files on disk based on the sparse rules. This is
     only necessary if .hg/sparse was changed by hand.
 
     --enable-profile and --disable-profile accept a path to a .hgsparse file.
     This allows defining sparse checkouts and tracking them inside the
     repository. This is useful for defining commonly used sparse checkouts for
     many people to use. As the profile definition changes over time, the sparse
     checkout will automatically be updated appropriately, depending on which
     changeset is checked out. Changes to .hgsparse are not applied until they
     have been committed.
 
     --import-rules accepts a path to a file containing rules in the .hgsparse
     format, allowing you to add --include, --exclude and --enable-profile rules
     in bulk. Like the --include, --exclude and --enable-profile switches, the
     changes are applied immediately.
 
     --clear-rules removes all local include and exclude rules, while leaving
     any enabled profiles in place.
 
     Returns 0 if editing the sparse checkout succeeds.
     """
     opts = pycompat.byteskwargs(opts)
     include = opts.get('include')
     exclude = opts.get('exclude')
     force = opts.get('force')
     enableprofile = opts.get('enable_profile')
     disableprofile = opts.get('disable_profile')
     importrules = opts.get('import_rules')
     clearrules = opts.get('clear_rules')
     delete = opts.get('delete')
     refresh = opts.get('refresh')
     reset = opts.get('reset')
     count = sum([include, exclude, enableprofile, disableprofile, delete,
                  importrules, refresh, clearrules, reset])
     if count > 1:
         raise error.Abort(_("too many flags specified"))
 
     if count == 0:
         if repo.vfs.exists('sparse'):
             ui.status(repo.vfs.read("sparse") + "\n")
             temporaryincludes = sparse.readtemporaryincludes(repo)
             if temporaryincludes:
                 ui.status(_("Temporarily Included Files (for merge/rebase):\n"))
                 ui.status(("\n".join(temporaryincludes) + "\n"))
         else:
             ui.status(_('repo is not sparse\n'))
         return
 
     if include or exclude or delete or reset or enableprofile or disableprofile:
         sparse.updateconfig(repo, pats, opts, include=include, exclude=exclude,
                             reset=reset, delete=delete,
                             enableprofile=enableprofile,
                             disableprofile=disableprofile, force=force)
 
     if importrules:
         sparse.importfromfiles(repo, opts, pats, force=force)
 
     if clearrules:
         sparse.clearrules(repo, force=force)
 
     if refresh:
         try:
             wlock = repo.wlock()
             fcounts = map(
                 len,
                 sparse.refreshwdir(repo, repo.status(), sparse.matcher(repo),
                                    force=force))
             sparse.printchanges(ui, opts, added=fcounts[0], dropped=fcounts[1],
                                 conflicting=fcounts[2])
         finally:
             wlock.release()

mercurial/fileset.py

@@ -1,561 +1,560 b''
 # fileset.py - file set queries for mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import re
 
 from .i18n import _
 from . import (
     error,
     filesetlang,
     match as matchmod,
     merge,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 # common weight constants
 _WEIGHT_CHECK_FILENAME = filesetlang.WEIGHT_CHECK_FILENAME
 _WEIGHT_READ_CONTENTS = filesetlang.WEIGHT_READ_CONTENTS
 _WEIGHT_STATUS = filesetlang.WEIGHT_STATUS
 _WEIGHT_STATUS_THOROUGH = filesetlang.WEIGHT_STATUS_THOROUGH
 
 # helpers for processing parsed tree
 getsymbol = filesetlang.getsymbol
 getstring = filesetlang.getstring
 _getkindpat = filesetlang.getkindpat
 getpattern = filesetlang.getpattern
 getargs = filesetlang.getargs
 
 def getmatch(mctx, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     return methods[x[0]](mctx, *x[1:])
 
 def getmatchwithstatus(mctx, x, hint):
     keys = set(getstring(hint, 'status hint must be a string').split())
     return getmatch(mctx.withstatus(keys), x)
 
 def stringmatch(mctx, x):
     return mctx.matcher([x])
 
 def kindpatmatch(mctx, x, y):
     return stringmatch(mctx, _getkindpat(x, y, matchmod.allpatternkinds,
                                          _("pattern must be a string")))
 
 def patternsmatch(mctx, *xs):
     allkinds = matchmod.allpatternkinds
     patterns = [getpattern(x, allkinds, _("pattern must be a string"))
                 for x in xs]
     return mctx.matcher(patterns)
 
 def andmatch(mctx, x, y):
     xm = getmatch(mctx, x)
     ym = getmatch(mctx.narrowed(xm), y)
     return matchmod.intersectmatchers(xm, ym)
 
 def ormatch(mctx, *xs):
     ms = [getmatch(mctx, x) for x in xs]
     return matchmod.unionmatcher(ms)
 
 def notmatch(mctx, x):
     m = getmatch(mctx, x)
     return mctx.predicate(lambda f: not m(f), predrepr=('<not %r>', m))
 
 def minusmatch(mctx, x, y):
     xm = getmatch(mctx, x)
     ym = getmatch(mctx.narrowed(xm), y)
     return matchmod.differencematcher(xm, ym)
 
 def listmatch(mctx, *xs):
     raise error.ParseError(_("can't use a list in this context"),
                            hint=_('see \'hg help "filesets.x or y"\''))
 
 def func(mctx, a, b):
     funcname = getsymbol(a)
     if funcname in symbols:
         return symbols[funcname](mctx, b)
 
     keep = lambda fn: getattr(fn, '__doc__', None) is not None
 
     syms = [s for (s, fn) in symbols.items() if keep(fn)]
     raise error.UnknownIdentifier(funcname, syms)
 
 # symbols are callable like:
 #  fun(mctx, x)
 # with:
 #  mctx - current matchctx instance
 #  x - argument in tree form
 symbols = filesetlang.symbols
 
 predicate = registrar.filesetpredicate(symbols)
 
 @predicate('modified()', callstatus=True, weight=_WEIGHT_STATUS)
 def modified(mctx, x):
     """File that is modified according to :hg:`status`.
     """
     # i18n: "modified" is a keyword
     getargs(x, 0, 0, _("modified takes no arguments"))
     s = set(mctx.status().modified)
     return mctx.predicate(s.__contains__, predrepr='modified')
 
 @predicate('added()', callstatus=True, weight=_WEIGHT_STATUS)
 def added(mctx, x):
     """File that is added according to :hg:`status`.
     """
     # i18n: "added" is a keyword
     getargs(x, 0, 0, _("added takes no arguments"))
     s = set(mctx.status().added)
     return mctx.predicate(s.__contains__, predrepr='added')
 
 @predicate('removed()', callstatus=True, weight=_WEIGHT_STATUS)
 def removed(mctx, x):
     """File that is removed according to :hg:`status`.
     """
     # i18n: "removed" is a keyword
     getargs(x, 0, 0, _("removed takes no arguments"))
     s = set(mctx.status().removed)
     return mctx.predicate(s.__contains__, predrepr='removed')
 
 @predicate('deleted()', callstatus=True, weight=_WEIGHT_STATUS)
 def deleted(mctx, x):
     """Alias for ``missing()``.
     """
     # i18n: "deleted" is a keyword
     getargs(x, 0, 0, _("deleted takes no arguments"))
     s = set(mctx.status().deleted)
     return mctx.predicate(s.__contains__, predrepr='deleted')
 
 @predicate('missing()', callstatus=True, weight=_WEIGHT_STATUS)
 def missing(mctx, x):
     """File that is missing according to :hg:`status`.
     """
     # i18n: "missing" is a keyword
     getargs(x, 0, 0, _("missing takes no arguments"))
     s = set(mctx.status().deleted)
     return mctx.predicate(s.__contains__, predrepr='deleted')
 
 @predicate('unknown()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
 def unknown(mctx, x):
     """File that is unknown according to :hg:`status`."""
     # i18n: "unknown" is a keyword
     getargs(x, 0, 0, _("unknown takes no arguments"))
     s = set(mctx.status().unknown)
     return mctx.predicate(s.__contains__, predrepr='unknown')
 
 @predicate('ignored()', callstatus=True, weight=_WEIGHT_STATUS_THOROUGH)
 def ignored(mctx, x):
     """File that is ignored according to :hg:`status`."""
     # i18n: "ignored" is a keyword
     getargs(x, 0, 0, _("ignored takes no arguments"))
     s = set(mctx.status().ignored)
     return mctx.predicate(s.__contains__, predrepr='ignored')
 
 @predicate('clean()', callstatus=True, weight=_WEIGHT_STATUS)
 def clean(mctx, x):
     """File that is clean according to :hg:`status`.
     """
     # i18n: "clean" is a keyword
     getargs(x, 0, 0, _("clean takes no arguments"))
     s = set(mctx.status().clean)
     return mctx.predicate(s.__contains__, predrepr='clean')
 
 @predicate('tracked()')
 def tracked(mctx, x):
     """File that is under Mercurial control."""
     # i18n: "tracked" is a keyword
     getargs(x, 0, 0, _("tracked takes no arguments"))
     return mctx.predicate(mctx.ctx.__contains__, predrepr='tracked')
 
 @predicate('binary()', weight=_WEIGHT_READ_CONTENTS)
 def binary(mctx, x):
     """File that appears to be binary (contains NUL bytes).
     """
     # i18n: "binary" is a keyword
     getargs(x, 0, 0, _("binary takes no arguments"))
     return mctx.fpredicate(lambda fctx: fctx.isbinary(),
                            predrepr='binary', cache=True)
 
 @predicate('exec()')
 def exec_(mctx, x):
     """File that is marked as executable.
     """
     # i18n: "exec" is a keyword
     getargs(x, 0, 0, _("exec takes no arguments"))
     ctx = mctx.ctx
     return mctx.predicate(lambda f: ctx.flags(f) == 'x', predrepr='exec')
 
 @predicate('symlink()')
 def symlink(mctx, x):
     """File that is marked as a symlink.
     """
     # i18n: "symlink" is a keyword
     getargs(x, 0, 0, _("symlink takes no arguments"))
     ctx = mctx.ctx
     return mctx.predicate(lambda f: ctx.flags(f) == 'l', predrepr='symlink')
 
 @predicate('resolved()', weight=_WEIGHT_STATUS)
 def resolved(mctx, x):
     """File that is marked resolved according to :hg:`resolve -l`.
     """
     # i18n: "resolved" is a keyword
     getargs(x, 0, 0, _("resolved takes no arguments"))
     if mctx.ctx.rev() is not None:
         return mctx.never()
     ms = merge.mergestate.read(mctx.ctx.repo())
     return mctx.predicate(lambda f: f in ms and ms[f] == 'r',
                           predrepr='resolved')
 
 @predicate('unresolved()', weight=_WEIGHT_STATUS)
 def unresolved(mctx, x):
     """File that is marked unresolved according to :hg:`resolve -l`.
     """
     # i18n: "unresolved" is a keyword
     getargs(x, 0, 0, _("unresolved takes no arguments"))
     if mctx.ctx.rev() is not None:
         return mctx.never()
     ms = merge.mergestate.read(mctx.ctx.repo())
     return mctx.predicate(lambda f: f in ms and ms[f] == 'u',
                           predrepr='unresolved')
 
 @predicate('hgignore()', weight=_WEIGHT_STATUS)
 def hgignore(mctx, x):
     """File that matches the active .hgignore pattern.
     """
     # i18n: "hgignore" is a keyword
     getargs(x, 0, 0, _("hgignore takes no arguments"))
     return mctx.ctx.repo().dirstate._ignore
 
 @predicate('portable()', weight=_WEIGHT_CHECK_FILENAME)
 def portable(mctx, x):
     """File that has a portable name. (This doesn't include filenames with case
     collisions.)
     """
     # i18n: "portable" is a keyword
     getargs(x, 0, 0, _("portable takes no arguments"))
     return mctx.predicate(lambda f: util.checkwinfilename(f) is None,
                           predrepr='portable')
 
 @predicate('grep(regex)', weight=_WEIGHT_READ_CONTENTS)
 def grep(mctx, x):
     """File contains the given regular expression.
     """
     try:
         # i18n: "grep" is a keyword
         r = re.compile(getstring(x, _("grep requires a pattern")))
     except re.error as e:
         raise error.ParseError(_('invalid match pattern: %s') %
                                stringutil.forcebytestr(e))
     return mctx.fpredicate(lambda fctx: r.search(fctx.data()),
                            predrepr=('grep(%r)', r.pattern), cache=True)
 
 def _sizetomax(s):
     try:
         s = s.strip().lower()
         for k, v in util._sizeunits:
             if s.endswith(k):
                 # max(4k) = 5k - 1, max(4.5k) = 4.6k - 1
                 n = s[:-len(k)]
                 inc = 1.0
                 if "." in n:
                     inc /= 10 ** len(n.split(".")[1])
                 return int((float(n) + inc) * v) - 1
         # no extension, this is a precise value
         return int(s)
     except ValueError:
         raise error.ParseError(_("couldn't parse size: %s") % s)
 
 def sizematcher(expr):
     """Return a function(size) -> bool from the ``size()`` expression"""
     expr = expr.strip()
     if '-' in expr: # do we have a range?
         a, b = expr.split('-', 1)
         a = util.sizetoint(a)
         b = util.sizetoint(b)
         return lambda x: x >= a and x <= b
     elif expr.startswith("<="):
         a = util.sizetoint(expr[2:])
         return lambda x: x <= a
     elif expr.startswith("<"):
         a = util.sizetoint(expr[1:])
         return lambda x: x < a
     elif expr.startswith(">="):
         a = util.sizetoint(expr[2:])
         return lambda x: x >= a
     elif expr.startswith(">"):
         a = util.sizetoint(expr[1:])
         return lambda x: x > a
     else:
         a = util.sizetoint(expr)
         b = _sizetomax(expr)
         return lambda x: x >= a and x <= b
 
 @predicate('size(expression)', weight=_WEIGHT_STATUS)
 def size(mctx, x):
     """File size matches the given expression. Examples:
 
     - size('1k') - files from 1024 to 2047 bytes
     - size('< 20k') - files less than 20480 bytes
     - size('>= .5MB') - files at least 524288 bytes
     - size('4k - 1MB') - files from 4096 bytes to 1048576 bytes
     """
     # i18n: "size" is a keyword
     expr = getstring(x, _("size requires an expression"))
     m = sizematcher(expr)
     return mctx.fpredicate(lambda fctx: m(fctx.size()),
                            predrepr=('size(%r)', expr), cache=True)
 
 @predicate('encoding(name)', weight=_WEIGHT_READ_CONTENTS)
 def encoding(mctx, x):
     """File can be successfully decoded with the given character
     encoding. May not be useful for encodings other than ASCII and
     UTF-8.
     """
 
     # i18n: "encoding" is a keyword
     enc = getstring(x, _("encoding requires an encoding name"))
 
     def encp(fctx):
         d = fctx.data()
         try:
             d.decode(pycompat.sysstr(enc))
             return True
         except LookupError:
             raise error.Abort(_("unknown encoding '%s'") % enc)
         except UnicodeDecodeError:
             return False
 
     return mctx.fpredicate(encp, predrepr=('encoding(%r)', enc), cache=True)
 
 @predicate('eol(style)', weight=_WEIGHT_READ_CONTENTS)
 def eol(mctx, x):
     """File contains newlines of the given style (dos, unix, mac). Binary
     files are excluded, files with mixed line endings match multiple
     styles.
     """
 
     # i18n: "eol" is a keyword
     enc = getstring(x, _("eol requires a style name"))
 
     def eolp(fctx):
         if fctx.isbinary():
             return False
         d = fctx.data()
         if (enc == 'dos' or enc == 'win') and '\r\n' in d:
             return True
         elif enc == 'unix' and re.search('(?<!\r)\n', d):
             return True
         elif enc == 'mac' and re.search('\r(?!\n)', d):
             return True
         return False
     return mctx.fpredicate(eolp, predrepr=('eol(%r)', enc), cache=True)
 
 @predicate('copied()')
 def copied(mctx, x):
     """File that is recorded as being copied.
     """
     # i18n: "copied" is a keyword
     getargs(x, 0, 0, _("copied takes no arguments"))
     def copiedp(fctx):
         p = fctx.parents()
         return p and p[0].path() != fctx.path()
     return mctx.fpredicate(copiedp, predrepr='copied', cache=True)
 
 @predicate('revs(revs, pattern)', weight=_WEIGHT_STATUS)
 def revs(mctx, x):
     """Evaluate set in the specified revisions. If the revset match multiple
     revs, this will return file matching pattern in any of the revision.
     """
     # i18n: "revs" is a keyword
     r, x = getargs(x, 2, 2, _("revs takes two arguments"))
     # i18n: "revs" is a keyword
     revspec = getstring(r, _("first argument to revs must be a revision"))
     repo = mctx.ctx.repo()
     revs = scmutil.revrange(repo, [revspec])
 
     matchers = []
     for r in revs:
         ctx = repo[r]
         mc = mctx.switch(ctx.p1(), ctx)
         matchers.append(getmatch(mc, x))
     if not matchers:
         return mctx.never()
     if len(matchers) == 1:
         return matchers[0]
     return matchmod.unionmatcher(matchers)
 
 @predicate('status(base, rev, pattern)', weight=_WEIGHT_STATUS)
 def status(mctx, x):
     """Evaluate predicate using status change between ``base`` and
     ``rev``. Examples:
 
     - ``status(3, 7, added())`` - matches files added from "3" to "7"
     """
     repo = mctx.ctx.repo()
     # i18n: "status" is a keyword
     b, r, x = getargs(x, 3, 3, _("status takes three arguments"))
     # i18n: "status" is a keyword
     baseerr = _("first argument to status must be a revision")
     baserevspec = getstring(b, baseerr)
     if not baserevspec:
         raise error.ParseError(baseerr)
     reverr = _("second argument to status must be a revision")
     revspec = getstring(r, reverr)
     if not revspec:
         raise error.ParseError(reverr)
     basectx, ctx = scmutil.revpair(repo, [baserevspec, revspec])
     mc = mctx.switch(basectx, ctx)
     return getmatch(mc, x)
 
 @predicate('subrepo([pattern])')
 def subrepo(mctx, x):
     """Subrepositories whose paths match the given pattern.
     """
     # i18n: "subrepo" is a keyword
     getargs(x, 0, 1, _("subrepo takes at most one argument"))
     ctx = mctx.ctx
     sstate = ctx.substate
     if x:
         pat = getpattern(x, matchmod.allpatternkinds,
                          # i18n: "subrepo" is a keyword
                          _("subrepo requires a pattern or no arguments"))
         fast = not matchmod.patkind(pat)
         if fast:
             def m(s):
                 return (s == pat)
         else:
             m = matchmod.match(ctx.repo().root, '', [pat], ctx=ctx)
         return mctx.predicate(lambda f: f in sstate and m(f),
                               predrepr=('subrepo(%r)', pat))
     else:
         return mctx.predicate(sstate.__contains__, predrepr='subrepo')
 
 methods = {
     'withstatus': getmatchwithstatus,
     'string': stringmatch,
     'symbol': stringmatch,
     'kindpat': kindpatmatch,
     'patterns': patternsmatch,
     'and': andmatch,
     'or': ormatch,
     'minus': minusmatch,
     'list': listmatch,
     'not': notmatch,
     'func': func,
 }
 
 class matchctx(object):
     def __init__(self, basectx, ctx, badfn=None):
         self._basectx = basectx
         self.ctx = ctx
         self._badfn = badfn
         self._match = None
         self._status = None
 
     def narrowed(self, match):
         """Create matchctx for a sub-tree narrowed by the given matcher"""
         mctx = matchctx(self._basectx, self.ctx, self._badfn)
         mctx._match = match
         # leave wider status which we don't have to care
         mctx._status = self._status
         return mctx
 
     def switch(self, basectx, ctx):
         mctx = matchctx(basectx, ctx, self._badfn)
         mctx._match = self._match
         return mctx
 
     def withstatus(self, keys):
         """Create matchctx which has precomputed status specified by the keys"""
         mctx = matchctx(self._basectx, self.ctx, self._badfn)
         mctx._match = self._match
         mctx._buildstatus(keys)
         return mctx
 
     def _buildstatus(self, keys):
         self._status = self._basectx.status(self.ctx, self._match,
                                             listignored='ignored' in keys,
                                             listclean='clean' in keys,
                                             listunknown='unknown' in keys)
 
     def status(self):
         return self._status
 
     def matcher(self, patterns):
         return self.ctx.match(patterns, badfn=self._badfn)
 
     def predicate(self, predfn, predrepr=None, cache=False):
         """Create a matcher to select files by predfn(filename)"""
         if cache:
             predfn = util.cachefunc(predfn)
-        repo = self.ctx.repo()
-        return matchmod.predicatematcher(repo.root, repo.getcwd(), predfn,
-                                         predrepr=predrepr, badfn=self._badfn)
+        return matchmod.predicatematcher(predfn, predrepr=predrepr,
+                                         badfn=self._badfn)
 
     def fpredicate(self, predfn, predrepr=None, cache=False):
         """Create a matcher to select files by predfn(fctx) at the current
         revision
 
         Missing files are ignored.
         """
         ctx = self.ctx
         if ctx.rev() is None:
             def fctxpredfn(f):
                 try:
                     fctx = ctx[f]
                 except error.LookupError:
                     return False
                 try:
                     fctx.audit()
                 except error.Abort:
                     return False
                 try:
                     return predfn(fctx)
                 except (IOError, OSError) as e:
                     # open()-ing a directory fails with EACCES on Windows
                     if e.errno in (errno.ENOENT, errno.EACCES, errno.ENOTDIR,
                                    errno.EISDIR):
                         return False
                     raise
         else:
             def fctxpredfn(f):
                 try:
                     fctx = ctx[f]
                 except error.LookupError:
                     return False
                 return predfn(fctx)
         return self.predicate(fctxpredfn, predrepr=predrepr, cache=cache)
 
     def never(self):
         """Create a matcher to select nothing"""
         repo = self.ctx.repo()
         return matchmod.never(repo.root, repo.getcwd(), badfn=self._badfn)
 
 def match(ctx, expr, badfn=None):
     """Create a matcher for a single fileset expression"""
     tree = filesetlang.parse(expr)
     tree = filesetlang.analyze(tree)
     tree = filesetlang.optimize(tree)
     mctx = matchctx(ctx.p1(), ctx, badfn=badfn)
     return getmatch(mctx, tree)
 
 
 def loadpredicate(ui, extname, registrarobj):
     """Load fileset predicates from specified registrarobj
     """
     for name, func in registrarobj._table.iteritems():
         symbols[name] = func
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = symbols.values()

mercurial/localrepo.py

@@ -1,3072 +1,3072 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import os
 import random
 import sys
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     changegroup,
     changelog,
     color,
     context,
     dirstate,
     dirstateguard,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     manifest,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     namespaces,
     narrowspec,
     obsolete,
     pathutil,
     phases,
     pushkey,
     pycompat,
     repository,
     repoview,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store as storemod,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     interfaceutil,
     procutil,
     stringutil,
 )
 
 from .revlogutils import (
     constants as revlogconst,
 )
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 # set of (path, vfs-location) tuples. vfs-location is:
 # - 'plain for vfs relative paths
 # - '' for svfs relative paths
 _cachedfiles = set()
 
 class _basefilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         # proxy to unfiltered __dict__ since filtered repo has no entry
         unfi = repo.unfiltered()
         try:
             return unfi.__dict__[self.sname]
         except KeyError:
             pass
         return super(_basefilecache, self).__get__(unfi, type)
 
     def set(self, repo, value):
         return super(_basefilecache, self).set(repo.unfiltered(), value)
 
 class repofilecache(_basefilecache):
     """filecache for files in .hg but outside of .hg/store"""
     def __init__(self, *paths):
         super(repofilecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, 'plain'))
 
     def join(self, obj, fname):
         return obj.vfs.join(fname)
 
 class storecache(_basefilecache):
     """filecache for files in the store"""
     def __init__(self, *paths):
         super(storecache, self).__init__(*paths)
         for path in paths:
             _cachedfiles.add((path, ''))
 
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 def isfilecached(repo, name):
     """check if a repo has already cached "name" filecache-ed property
 
     This returns (cachedobj-or-None, iscached) tuple.
     """
     cacheentry = repo.unfiltered()._filecache.get(name, None)
     if not cacheentry:
         return None, False
     return cacheentry.obj, True
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 moderncaps = {'lookup', 'branchmap', 'pushkey', 'known', 'getbundle',
               'unbundle'}
 legacycaps = moderncaps.union({'changegroupsubset'})
 
 @interfaceutil.implementer(repository.ipeercommandexecutor)
 class localcommandexecutor(object):
     def __init__(self, peer):
         self._peer = peer
         self._sent = False
         self._closed = False
 
     def __enter__(self):
         return self
 
     def __exit__(self, exctype, excvalue, exctb):
         self.close()
 
     def callcommand(self, command, args):
         if self._sent:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'sendcommands()')
 
         if self._closed:
             raise error.ProgrammingError('callcommand() cannot be used after '
                                          'close()')
 
         # We don't need to support anything fancy. Just call the named
         # method on the peer and return a resolved future.
         fn = getattr(self._peer, pycompat.sysstr(command))
 
         f = pycompat.futures.Future()
 
         try:
             result = fn(**pycompat.strkwargs(args))
         except Exception:
             pycompat.future_set_exception_info(f, sys.exc_info()[1:])
         else:
             f.set_result(result)
 
         return f
 
     def sendcommands(self):
         self._sent = True
 
     def close(self):
         self._closed = True
 
 @interfaceutil.implementer(repository.ipeercommands)
 class localpeer(repository.peer):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=None):
         super(localpeer, self).__init__()
 
         if caps is None:
             caps = moderncaps.copy()
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
 
     # Begin of _basepeer interface.
 
     def url(self):
         return self._repo.url()
 
     def local(self):
         return self._repo
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         self._repo.close()
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def capabilities(self):
         return self._caps
 
     def clonebundles(self):
         return self._repo.tryread('clonebundles.manifest')
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         """Used to test argument passing over the wire"""
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None,
                   **kwargs):
         chunks = exchange.getbundlechunks(self._repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps,
                                           **kwargs)[1]
         cb = util.chunkbuffer(chunks)
 
         if exchange.bundle2requested(bundlecaps):
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler('01', cb, None)
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def stream_out(self):
         raise error.Abort(_('cannot perform stream clone against local '
                             'peer'))
 
     def unbundle(self, bundle, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 bundle = exchange.readbundle(self.ui, bundle, None)
                 ret = exchange.unbundle(self._repo, bundle, heads, 'push', url)
                 if util.safehasattr(ret, 'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(_('push failed:'),
                                       stringutil.forcebytestr(exc))
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def commandexecutor(self):
         return localcommandexecutor(self)
 
     # End of peer interface.
 
 @interfaceutil.implementer(repository.ipeerlegacycommands)
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         super(locallegacypeer, self).__init__(repo, caps=legacycaps)
 
     # Begin of baselegacywirecommands interface.
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def changegroup(self, nodes, source):
         outgoing = discovery.outgoing(self._repo, missingroots=nodes,
                                       missingheads=self._repo.heads())
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     def changegroupsubset(self, bases, heads, source):
         outgoing = discovery.outgoing(self._repo, missingroots=bases,
                                       missingheads=heads)
         return changegroup.makechangegroup(self._repo, outgoing, '01', source)
 
     # End of baselegacywirecommands interface.
 
 # Increment the sub-version when the revlog v2 format changes to lock out old
 # clients.
 REVLOGV2_REQUIREMENT = 'exp-revlogv2.1'
 
 # A repository with the sparserevlog feature will have delta chains that
 # can spread over a larger span. Sparse reading cuts these large spans into
 # pieces, so that each piece isn't too big.
 # Without the sparserevlog capability, reading from the repository could use
 # huge amounts of memory, because the whole span would be read at once,
 # including all the intermediate revisions that aren't pertinent for the chain.
 # This is why once a repository has enabled sparse-read, it becomes required.
 SPARSEREVLOG_REQUIREMENT = 'sparserevlog'
 
 # Functions receiving (ui, features) that extensions can register to impact
 # the ability to load repositories with custom requirements. Only
 # functions defined in loaded extensions are called.
 #
 # The function receives a set of requirement strings that the repository
 # is capable of opening. Functions will typically add elements to the
 # set to reflect that the extension knows how to handle that requirements.
 featuresetupfuncs = set()
 
 def makelocalrepository(baseui, path, intents=None):
     """Create a local repository object.
 
     Given arguments needed to construct a local repository, this function
     performs various early repository loading functionality (such as
     reading the ``.hg/requires`` and ``.hg/hgrc`` files), validates that
     the repository can be opened, derives a type suitable for representing
     that repository, and returns an instance of it.
 
     The returned object conforms to the ``repository.completelocalrepository``
     interface.
 
     The repository type is derived by calling a series of factory functions
     for each aspect/interface of the final repository. These are defined by
     ``REPO_INTERFACES``.
 
     Each factory function is called to produce a type implementing a specific
     interface. The cumulative list of returned types will be combined into a
     new type and that type will be instantiated to represent the local
     repository.
 
     The factory functions each receive various state that may be consulted
     as part of deriving a type.
 
     Extensions should wrap these factory functions to customize repository type
     creation. Note that an extension's wrapped function may be called even if
     that extension is not loaded for the repo being constructed. Extensions
     should check if their ``__name__`` appears in the
     ``extensionmodulenames`` set passed to the factory function and no-op if
     not.
     """
     ui = baseui.copy()
     # Prevent copying repo configuration.
     ui.copy = baseui.copy
 
     # Working directory VFS rooted at repository root.
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     # Main VFS for .hg/ directory.
     hgpath = wdirvfs.join(b'.hg')
     hgvfs = vfsmod.vfs(hgpath, cacheaudited=True)
 
     # The .hg/ path should exist and should be a directory. All other
     # cases are errors.
     if not hgvfs.isdir():
         try:
             hgvfs.stat()
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
         raise error.RepoError(_(b'repository %s not found') % path)
 
     # .hg/requires file contains a newline-delimited list of
     # features/capabilities the opener (us) must have in order to use
     # the repository. This file was introduced in Mercurial 0.9.2,
     # which means very old repositories may not have one. We assume
     # a missing file translates to no requirements.
     try:
         requirements = set(hgvfs.read(b'requires').splitlines())
     except IOError as e:
         if e.errno != errno.ENOENT:
             raise
         requirements = set()
 
     # The .hg/hgrc file may load extensions or contain config options
     # that influence repository construction. Attempt to load it and
     # process any new extensions that it may have pulled in.
     if loadhgrc(ui, wdirvfs, hgvfs, requirements):
         afterhgrcload(ui, wdirvfs, hgvfs, requirements)
         extensions.loadall(ui)
         extensions.populateui(ui)
 
     # Set of module names of extensions loaded for this repository.
     extensionmodulenames = {m.__name__ for n, m in extensions.extensions(ui)}
 
     supportedrequirements = gathersupportedrequirements(ui)
 
     # We first validate the requirements are known.
     ensurerequirementsrecognized(requirements, supportedrequirements)
 
     # Then we validate that the known set is reasonable to use together.
     ensurerequirementscompatible(ui, requirements)
 
     # TODO there are unhandled edge cases related to opening repositories with
     # shared storage. If storage is shared, we should also test for requirements
     # compatibility in the pointed-to repo. This entails loading the .hg/hgrc in
     # that repo, as that repo may load extensions needed to open it. This is a
     # bit complicated because we don't want the other hgrc to overwrite settings
     # in this hgrc.
     #
     # This bug is somewhat mitigated by the fact that we copy the .hg/requires
     # file when sharing repos. But if a requirement is added after the share is
     # performed, thereby introducing a new requirement for the opener, we may
     # will not see that and could encounter a run-time error interacting with
     # that shared store since it has an unknown-to-us requirement.
 
     # At this point, we know we should be capable of opening the repository.
     # Now get on with doing that.
 
     features = set()
 
     # The "store" part of the repository holds versioned data. How it is
     # accessed is determined by various requirements. The ``shared`` or
     # ``relshared`` requirements indicate the store lives in the path contained
     # in the ``.hg/sharedpath`` file. This is an absolute path for
     # ``shared`` and relative to ``.hg/`` for ``relshared``.
     if b'shared' in requirements or b'relshared' in requirements:
         sharedpath = hgvfs.read(b'sharedpath').rstrip(b'\n')
         if b'relshared' in requirements:
             sharedpath = hgvfs.join(sharedpath)
 
         sharedvfs = vfsmod.vfs(sharedpath, realpath=True)
 
         if not sharedvfs.exists():
             raise error.RepoError(_(b'.hg/sharedpath points to nonexistent '
                                     b'directory %s') % sharedvfs.base)
 
         features.add(repository.REPO_FEATURE_SHARED_STORAGE)
 
         storebasepath = sharedvfs.base
         cachepath = sharedvfs.join(b'cache')
     else:
         storebasepath = hgvfs.base
         cachepath = hgvfs.join(b'cache')
     wcachepath = hgvfs.join(b'wcache')
 
 
     # The store has changed over time and the exact layout is dictated by
     # requirements. The store interface abstracts differences across all
     # of them.
     store = makestore(requirements, storebasepath,
                       lambda base: vfsmod.vfs(base, cacheaudited=True))
     hgvfs.createmode = store.createmode
 
     storevfs = store.vfs
     storevfs.options = resolvestorevfsoptions(ui, requirements, features)
 
     # The cache vfs is used to manage cache files.
     cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
     cachevfs.createmode = store.createmode
     # The cache vfs is used to manage cache files related to the working copy
     wcachevfs = vfsmod.vfs(wcachepath, cacheaudited=True)
     wcachevfs.createmode = store.createmode
 
     # Now resolve the type for the repository object. We do this by repeatedly
     # calling a factory function to produces types for specific aspects of the
     # repo's operation. The aggregate returned types are used as base classes
     # for a dynamically-derived type, which will represent our new repository.
 
     bases = []
     extrastate = {}
 
     for iface, fn in REPO_INTERFACES:
         # We pass all potentially useful state to give extensions tons of
         # flexibility.
         typ = fn()(ui=ui,
                  intents=intents,
                  requirements=requirements,
                  features=features,
                  wdirvfs=wdirvfs,
                  hgvfs=hgvfs,
                  store=store,
                  storevfs=storevfs,
                  storeoptions=storevfs.options,
                  cachevfs=cachevfs,
                  wcachevfs=wcachevfs,
                  extensionmodulenames=extensionmodulenames,
                  extrastate=extrastate,
                  baseclasses=bases)
 
         if not isinstance(typ, type):
             raise error.ProgrammingError('unable to construct type for %s' %
                                          iface)
 
         bases.append(typ)
 
     # type() allows you to use characters in type names that wouldn't be
     # recognized as Python symbols in source code. We abuse that to add
     # rich information about our constructed repo.
     name = pycompat.sysstr(b'derivedrepo:%s<%s>' % (
         wdirvfs.base,
         b','.join(sorted(requirements))))
 
     cls = type(name, tuple(bases), {})
 
     return cls(
         baseui=baseui,
         ui=ui,
         origroot=path,
         wdirvfs=wdirvfs,
         hgvfs=hgvfs,
         requirements=requirements,
         supportedrequirements=supportedrequirements,
         sharedpath=storebasepath,
         store=store,
         cachevfs=cachevfs,
         wcachevfs=wcachevfs,
         features=features,
         intents=intents)
 
 def loadhgrc(ui, wdirvfs, hgvfs, requirements):
     """Load hgrc files/content into a ui instance.
 
     This is called during repository opening to load any additional
     config files or settings relevant to the current repository.
 
     Returns a bool indicating whether any additional configs were loaded.
 
     Extensions should monkeypatch this function to modify how per-repo
     configs are loaded. For example, an extension may wish to pull in
     configs from alternate files or sources.
     """
     try:
         ui.readconfig(hgvfs.join(b'hgrc'), root=wdirvfs.base)
         return True
     except IOError:
         return False
 
 def afterhgrcload(ui, wdirvfs, hgvfs, requirements):
     """Perform additional actions after .hg/hgrc is loaded.
 
     This function is called during repository loading immediately after
     the .hg/hgrc file is loaded and before per-repo extensions are loaded.
 
     The function can be used to validate configs, automatically add
     options (including extensions) based on requirements, etc.
     """
 
     # Map of requirements to list of extensions to load automatically when
     # requirement is present.
     autoextensions = {
         b'largefiles': [b'largefiles'],
         b'lfs': [b'lfs'],
     }
 
     for requirement, names in sorted(autoextensions.items()):
         if requirement not in requirements:
             continue
 
         for name in names:
             if not ui.hasconfig(b'extensions', name):
                 ui.setconfig(b'extensions', name, b'', source='autoload')
 
 def gathersupportedrequirements(ui):
     """Determine the complete set of recognized requirements."""
     # Start with all requirements supported by this file.
     supported = set(localrepository._basesupported)
 
     # Execute ``featuresetupfuncs`` entries if they belong to an extension
     # relevant to this ui instance.
     modules = {m.__name__ for n, m in extensions.extensions(ui)}
 
     for fn in featuresetupfuncs:
         if fn.__module__ in modules:
             fn(ui, supported)
 
     # Add derived requirements from registered compression engines.
     for name in util.compengines:
         engine = util.compengines[name]
         if engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
 
     return supported
 
 def ensurerequirementsrecognized(requirements, supported):
     """Validate that a set of local requirements is recognized.
 
     Receives a set of requirements. Raises an ``error.RepoError`` if there
     exists any requirement in that set that currently loaded code doesn't
     recognize.
 
     Returns a set of supported requirements.
     """
     missing = set()
 
     for requirement in requirements:
         if requirement in supported:
             continue
 
         if not requirement or not requirement[0:1].isalnum():
             raise error.RequirementError(_(b'.hg/requires file is corrupt'))
 
         missing.add(requirement)
 
     if missing:
         raise error.RequirementError(
             _(b'repository requires features unknown to this Mercurial: %s') %
             b' '.join(sorted(missing)),
             hint=_(b'see https://mercurial-scm.org/wiki/MissingRequirement '
                    b'for more information'))
 
 def ensurerequirementscompatible(ui, requirements):
     """Validates that a set of recognized requirements is mutually compatible.
 
     Some requirements may not be compatible with others or require
     config options that aren't enabled. This function is called during
     repository opening to ensure that the set of requirements needed
     to open a repository is sane and compatible with config options.
 
     Extensions can monkeypatch this function to perform additional
     checking.
 
     ``error.RepoError`` should be raised on failure.
     """
     if b'exp-sparse' in requirements and not sparse.enabled:
         raise error.RepoError(_(b'repository is using sparse feature but '
                                 b'sparse is not enabled; enable the '
                                 b'"sparse" extensions to access'))
 
 def makestore(requirements, path, vfstype):
     """Construct a storage object for a repository."""
     if b'store' in requirements:
         if b'fncache' in requirements:
             return storemod.fncachestore(path, vfstype,
                                          b'dotencode' in requirements)
 
         return storemod.encodedstore(path, vfstype)
 
     return storemod.basicstore(path, vfstype)
 
 def resolvestorevfsoptions(ui, requirements, features):
     """Resolve the options to pass to the store vfs opener.
 
     The returned dict is used to influence behavior of the storage layer.
     """
     options = {}
 
     if b'treemanifest' in requirements:
         options[b'treemanifest'] = True
 
     # experimental config: format.manifestcachesize
     manifestcachesize = ui.configint(b'format', b'manifestcachesize')
     if manifestcachesize is not None:
         options[b'manifestcachesize'] = manifestcachesize
 
     # In the absence of another requirement superseding a revlog-related
     # requirement, we have to assume the repo is using revlog version 0.
     # This revlog format is super old and we don't bother trying to parse
     # opener options for it because those options wouldn't do anything
     # meaningful on such old repos.
     if b'revlogv1' in requirements or REVLOGV2_REQUIREMENT in requirements:
         options.update(resolverevlogstorevfsoptions(ui, requirements, features))
 
     return options
 
 def resolverevlogstorevfsoptions(ui, requirements, features):
     """Resolve opener options specific to revlogs."""
 
     options = {}
     options[b'flagprocessors'] = {}
 
     if b'revlogv1' in requirements:
         options[b'revlogv1'] = True
     if REVLOGV2_REQUIREMENT in requirements:
         options[b'revlogv2'] = True
 
     if b'generaldelta' in requirements:
         options[b'generaldelta'] = True
 
     # experimental config: format.chunkcachesize
     chunkcachesize = ui.configint(b'format', b'chunkcachesize')
     if chunkcachesize is not None:
         options[b'chunkcachesize'] = chunkcachesize
 
     deltabothparents = ui.configbool(b'storage',
                                      b'revlog.optimize-delta-parent-choice')
     options[b'deltabothparents'] = deltabothparents
 
     options[b'lazydeltabase'] = not scmutil.gddeltaconfig(ui)
 
     chainspan = ui.configbytes(b'experimental', b'maxdeltachainspan')
     if 0 <= chainspan:
         options[b'maxdeltachainspan'] = chainspan
 
     mmapindexthreshold = ui.configbytes(b'experimental',
                                         b'mmapindexthreshold')
     if mmapindexthreshold is not None:
         options[b'mmapindexthreshold'] = mmapindexthreshold
 
     withsparseread = ui.configbool(b'experimental', b'sparse-read')
     srdensitythres = float(ui.config(b'experimental',
                                      b'sparse-read.density-threshold'))
     srmingapsize = ui.configbytes(b'experimental',
                                   b'sparse-read.min-gap-size')
     options[b'with-sparse-read'] = withsparseread
     options[b'sparse-read-density-threshold'] = srdensitythres
     options[b'sparse-read-min-gap-size'] = srmingapsize
 
     sparserevlog = SPARSEREVLOG_REQUIREMENT in requirements
     options[b'sparse-revlog'] = sparserevlog
     if sparserevlog:
         options[b'generaldelta'] = True
 
     maxchainlen = None
     if sparserevlog:
         maxchainlen = revlogconst.SPARSE_REVLOG_MAX_CHAIN_LENGTH
     # experimental config: format.maxchainlen
     maxchainlen = ui.configint(b'format', b'maxchainlen', maxchainlen)
     if maxchainlen is not None:
         options[b'maxchainlen'] = maxchainlen
 
     for r in requirements:
         if r.startswith(b'exp-compression-'):
             options[b'compengine'] = r[len(b'exp-compression-'):]
 
     if repository.NARROW_REQUIREMENT in requirements:
         options[b'enableellipsis'] = True
 
     return options
 
 def makemain(**kwargs):
     """Produce a type conforming to ``ilocalrepositorymain``."""
     return localrepository
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlogfilestorage(object):
     """File storage when using revlogs."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.filelog(self.svfs, path)
 
 @interfaceutil.implementer(repository.ilocalrepositoryfilestorage)
 class revlognarrowfilestorage(object):
     """File storage when using revlogs and narrow files."""
 
     def file(self, path):
         if path[0] == b'/':
             path = path[1:]
 
         return filelog.narrowfilelog(self.svfs, path, self._storenarrowmatch)
 
 def makefilestorage(requirements, features, **kwargs):
     """Produce a type conforming to ``ilocalrepositoryfilestorage``."""
     features.add(repository.REPO_FEATURE_REVLOG_FILE_STORAGE)
     features.add(repository.REPO_FEATURE_STREAM_CLONE)
 
     if repository.NARROW_REQUIREMENT in requirements:
         return revlognarrowfilestorage
     else:
         return revlogfilestorage
 
 # List of repository interfaces and factory functions for them. Each
 # will be called in order during ``makelocalrepository()`` to iteratively
 # derive the final type for a local repository instance. We capture the
 # function as a lambda so we don't hold a reference and the module-level
 # functions can be wrapped.
 REPO_INTERFACES = [
     (repository.ilocalrepositorymain, lambda: makemain),
     (repository.ilocalrepositoryfilestorage, lambda: makefilestorage),
 ]
 
 @interfaceutil.implementer(repository.ilocalrepositorymain)
 class localrepository(object):
     """Main class for representing local repositories.
 
     All local repositories are instances of this class.
 
     Constructed on its own, instances of this class are not usable as
     repository objects. To obtain a usable repository object, call
     ``hg.repository()``, ``localrepo.instance()``, or
     ``localrepo.makelocalrepository()``. The latter is the lowest-level.
     ``instance()`` adds support for creating new repositories.
     ``hg.repository()`` adds more extension integration, including calling
     ``reposetup()``. Generally speaking, ``hg.repository()`` should be
     used.
     """
 
     # obsolete experimental requirements:
     #  - manifestv2: An experimental new manifest format that allowed
     #    for stem compression of long paths. Experiment ended up not
     #    being successful (repository sizes went up due to worse delta
     #    chains), and the code was deleted in 4.6.
     supportedformats = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
         REVLOGV2_REQUIREMENT,
         SPARSEREVLOG_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         'store',
         'fncache',
         'shared',
         'relshared',
         'dotencode',
         'exp-sparse',
         'internal-phase'
     }
 
     # list of prefix for file which can be written without 'wlock'
     # Extensions should extend this list when needed
     _wlockfreeprefix = {
         # We migh consider requiring 'wlock' for the next
         # two, but pretty much all the existing code assume
         # wlock is not needed so we keep them excluded for
         # now.
         'hgrc',
         'requires',
         # XXX cache is a complicatged business someone
         # should investigate this in depth at some point
         'cache/',
         # XXX shouldn't be dirstate covered by the wlock?
         'dirstate',
         # XXX bisect was still a bit too messy at the time
         # this changeset was introduced. Someone should fix
         # the remainig bit and drop this line
         'bisect.state',
     }
 
     def __init__(self, baseui, ui, origroot, wdirvfs, hgvfs, requirements,
                  supportedrequirements, sharedpath, store, cachevfs, wcachevfs,
                  features, intents=None):
         """Create a new local repository instance.
 
         Most callers should use ``hg.repository()``, ``localrepo.instance()``,
         or ``localrepo.makelocalrepository()`` for obtaining a new repository
         object.
 
         Arguments:
 
         baseui
            ``ui.ui`` instance that ``ui`` argument was based off of.
 
         ui
            ``ui.ui`` instance for use by the repository.
 
         origroot
            ``bytes`` path to working directory root of this repository.
 
         wdirvfs
            ``vfs.vfs`` rooted at the working directory.
 
         hgvfs
            ``vfs.vfs`` rooted at .hg/
 
         requirements
            ``set`` of bytestrings representing repository opening requirements.
 
         supportedrequirements
            ``set`` of bytestrings representing repository requirements that we
            know how to open. May be a supetset of ``requirements``.
 
         sharedpath
            ``bytes`` Defining path to storage base directory. Points to a
            ``.hg/`` directory somewhere.
 
         store
            ``store.basicstore`` (or derived) instance providing access to
            versioned storage.
 
         cachevfs
            ``vfs.vfs`` used for cache files.
 
         wcachevfs
            ``vfs.vfs`` used for cache files related to the working copy.
 
         features
            ``set`` of bytestrings defining features/capabilities of this
            instance.
 
         intents
            ``set`` of system strings indicating what this repo will be used
            for.
         """
         self.baseui = baseui
         self.ui = ui
         self.origroot = origroot
         # vfs rooted at working directory.
         self.wvfs = wdirvfs
         self.root = wdirvfs.base
         # vfs rooted at .hg/. Used to access most non-store paths.
         self.vfs = hgvfs
         self.path = hgvfs.base
         self.requirements = requirements
         self.supported = supportedrequirements
         self.sharedpath = sharedpath
         self.store = store
         self.cachevfs = cachevfs
         self.wcachevfs = wcachevfs
         self.features = features
 
         self.filtername = None
 
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             self.vfs.audit = self._getvfsward(self.vfs.audit)
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
 
         color.setup(self.ui)
 
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         if (self.ui.configbool('devel', 'all-warnings') or
             self.ui.configbool('devel', 'check-locks')):
             if util.safehasattr(self.svfs, 'vfs'): # this is filtervfs
                 self.svfs.vfs.audit = self._getsvfsward(self.svfs.vfs.audit)
             else: # standard vfs
                 self.svfs.audit = self._getsvfsward(self.svfs.audit)
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = branchmap.BranchMapCache()
         self._revbranchcache = None
         self._filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # post-dirstate-status hooks
         self._postdsstatus = []
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
         # Key to signature value.
         self._sparsesignaturecache = {}
         # Signature to cached matcher instance.
         self._sparsematchercache = {}
 
     def _getvfsward(self, origfunc):
         """build a ward for self.vfs"""
         rref = weakref.ref(self)
         def checkvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if (repo is None
                 or not util.safehasattr(repo, '_wlockref')
                 or not util.safehasattr(repo, '_lockref')):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.path):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.path) + 1:]
             if path.startswith('cache/'):
                 msg = 'accessing cache with vfs instead of cachevfs: "%s"'
                 repo.ui.develwarn(msg % path, stacklevel=3, config="cache-vfs")
             if path.startswith('journal.') or path.startswith('undo.'):
                 # journal is covered by 'lock'
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn('write with no lock: "%s"' % path,
                                       stacklevel=3, config='check-locks')
             elif repo._currentlock(repo._wlockref) is None:
                 # rest of vfs files are covered by 'wlock'
                 #
                 # exclude special files
                 for prefix in self._wlockfreeprefix:
                     if path.startswith(prefix):
                         return
                 repo.ui.develwarn('write with no wlock: "%s"' % path,
                                   stacklevel=3, config='check-locks')
             return ret
         return checkvfs
 
     def _getsvfsward(self, origfunc):
         """build a ward for self.svfs"""
         rref = weakref.ref(self)
         def checksvfs(path, mode=None):
             ret = origfunc(path, mode=mode)
             repo = rref()
             if repo is None or not util.safehasattr(repo, '_lockref'):
                 return
             if mode in (None, 'r', 'rb'):
                 return
             if path.startswith(repo.sharedpath):
                 # truncate name relative to the repository (.hg)
                 path = path[len(repo.sharedpath) + 1:]
             if repo._currentlock(repo._lockref) is None:
                 repo.ui.develwarn('write with no lock: "%s"' % path,
                                   stacklevel=4)
             return ret
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool('experimental', 'bundle2-advertise'):
             caps = set(caps)
             capsblob = bundle2.encodecaps(bundle2.getrepocaps(self,
                                                               role='client'))
             caps.add('bundle2=' + urlreq.quote(capsblob))
         return caps
 
     def _writerequirements(self):
         scmutil.writerequires(self.vfs, self.requirements)
 
     # Don't cache auditor/nofsauditor, or you'll end up with reference cycle:
     # self -> auditor -> self._checknested -> self
 
     @property
     def auditor(self):
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested)
 
     @property
     def nofsauditor(self):
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         return pathutil.pathauditor(self.root, callback=self._checknested,
                                     realfs=False, cached=True)
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name, visibilityexceptions=None):
         """Return a filtered version of a repository"""
         cls = repoview.newtype(self.unfiltered().__class__)
         return cls(self, name, visibilityexceptions)
 
     @repofilecache('bookmarks', 'bookmarks.current')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     # _phasesets depend on changelog. what we need is to call
     # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache('phaseroots', '00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         return obsolete.makestore(self.ui, self)
 
     @storecache('00changelog.i')
     def changelog(self):
         return changelog.changelog(self.svfs,
                                    trypending=txnutil.mayhavepending(self.root))
 
     @storecache('00manifest.i')
     def manifestlog(self):
         rootstore = manifest.manifestrevlog(self.svfs)
         return manifest.manifestlog(self.svfs, self, rootstore,
                                     self._storenarrowmatch)
 
     @repofilecache('dirstate')
     def dirstate(self):
         return self._makedirstate()
 
     def _makedirstate(self):
         """Extension point for wrapping the dirstate per-repo."""
         sparsematchfn = lambda: sparse.matcher(self)
 
         return dirstate.dirstate(self.vfs, self.ui, self.root,
                                  self._dirstatevalidate, sparsematchfn)
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(_("warning: ignoring unknown"
                                " working parent %s!\n") % short(node))
             return nullid
 
     @storecache(narrowspec.FILENAME)
     def narrowpats(self):
         """matcher patterns for this repository's narrowspec
 
         A tuple of (includes, excludes).
         """
         return narrowspec.load(self)
 
     @storecache(narrowspec.FILENAME)
     def _storenarrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always(self.root, '')
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(self):
         if repository.NARROW_REQUIREMENT not in self.requirements:
             return matchmod.always(self.root, '')
         narrowspec.checkworkingcopynarrowspec(self)
         include, exclude = self.narrowpats
         return narrowspec.match(self.root, include=include, exclude=exclude)
 
     def narrowmatch(self, match=None, includeexact=False):
         """matcher corresponding the the repo's narrowspec
 
         If `match` is given, then that will be intersected with the narrow
         matcher.
 
         If `includeexact` is True, then any exact matches from `match` will
         be included even if they're outside the narrowspec.
         """
         if match:
             if includeexact and not self._narrowmatch.always():
                 # do not exclude explicitly-specified paths so that they can
                 # be warned later on
-                em = matchmod.exact(match._root, match._cwd, match.files())
+                em = matchmod.exact(None, None, match.files())
                 nm = matchmod.unionmatcher([self._narrowmatch, em])
                 return matchmod.intersectmatchers(match, nm)
             return matchmod.intersectmatchers(match, self._narrowmatch)
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         narrowspec.save(self, newincludes, newexcludes)
         self.invalidate(clearfilecache=True)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, context.basectx):
             return changeid
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [self[i]
                     for i in pycompat.xrange(*changeid.indices(len(self)))
                     if i not in self.changelog.filteredrevs]
         try:
             if isinstance(changeid, int):
                 node = self.changelog.node(changeid)
                 rev = changeid
             elif changeid == 'null':
                 node = nullid
                 rev = nullrev
             elif changeid == 'tip':
                 node = self.changelog.tip()
                 rev = self.changelog.rev(node)
             elif changeid == '.':
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 node = self.dirstate.p1()
                 rev = self.unfiltered().changelog.rev(node)
             elif len(changeid) == 20:
                 try:
                     node = changeid
                     rev = self.changelog.rev(changeid)
                 except error.FilteredLookupError:
                     changeid = hex(changeid) # for the error message
                     raise
                 except LookupError:
                     # check if it might have come from damaged dirstate
                     #
                     # XXX we could avoid the unfiltered if we had a recognizable
                     # exception for filtered changeset access
                     if (self.local()
                         and changeid in self.unfiltered().dirstate.parents()):
                         msg = _("working directory has unknown parent '%s'!")
                         raise error.Abort(msg % short(changeid))
                     changeid = hex(changeid) # for the error message
                     raise
 
             elif len(changeid) == 40:
                 node = bin(changeid)
                 rev = self.changelog.rev(node)
             else:
                 raise error.ProgrammingError(
                         "unsupported changeid '%s' of type %s" %
                         (changeid, type(changeid)))
 
             return context.changectx(self, rev, node)
 
         except (error.FilteredIndexError, error.FilteredLookupError):
             raise error.FilteredRepoLookupError(_("filtered revision '%s'")
                                                 % pycompat.bytestr(changeid))
         except (IndexError, LookupError):
             raise error.RepoLookupError(
                 _("unknown revision '%s'") % pycompat.bytestr(changeid))
         except error.WdirUnsupported:
             return context.workingctx(self)
 
     def __contains__(self, changeid):
         """True if the given changeid exists
 
         error.AmbiguousPrefixLookupError is raised if an ambiguous node
         specified.
         """
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         # no need to pay the cost of repoview.changelog
         unfi = self.unfiltered()
         return len(unfi.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revsetlang.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()`` or
         ``repo.anyrevs([expr], user=True)``.
 
         Returns a revset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         '''
         tree = revsetlang.spectree(expr, *args)
         return revset.makematcher(tree)(self)
 
     def set(self, expr, *args):
         '''Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def anyrevs(self, specs, user=False, localalias=None):
         '''Find revisions matching one of the given revsets.
 
         Revset aliases from the configuration are not expanded by default. To
         expand user aliases, specify ``user=True``. To provide some local
         definitions overriding user aliases, set ``localalias`` to
         ``{name: definitionstring}``.
         '''
         if user:
             m = revset.matchany(self.ui, specs,
                                 lookup=revset.lookupfn(self),
                                 localalias=localalias)
         else:
             m = revset.matchany(None, specs, localalias=localalias)
         return m(self)
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         rev = self.changelog.rev
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
 
         # map tag name to (node, hist)
         alltags = tagsmod.findglobaltags(self.ui, self)
         # map tag name to tag type
         tagtypes = dict((tag, 'global') for tag in alltags)
 
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         return self._bookmarks.names(node)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         return self._branchcaches[self]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def branchtip(self, branch, ignoremissing=False):
         '''return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         '''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_("unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         return scmutil.revsymbol(self, key).node()
 
     def lookupbranch(self, key):
         if key in self.branchmap():
             return key
 
         return scmutil.revsymbol(self, key).branch()
 
     def known(self, nodes):
         cl = self.changelog
         nm = cl.nodemap
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool('phases', 'publish', untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered('visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return 'store'
         return None
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def setparents(self, p1, p2=nullid):
         with self.dirstate.parentchange():
             copies = self.dirstate.setparents(p1, p2)
             pctx = self[p1]
             if copies:
                 # Adjust copy records, the dirstate cannot do it, it
                 # requires access to parents manifests. Preserve them
                 # only for entries added to first parent.
                 for f in copies:
                     if f not in pctx and copies[f] in pctx:
                         self.dirstate.copy(copies[f], f)
             if p2 == nullid:
                 for f, s in sorted(self.dirstate.copies().items()):
                     if f not in pctx and s not in pctx:
                         self.dirstate.copy(None, f)
 
     def filectx(self, path, changeid=None, fileid=None, changectx=None):
         """changeid must be a changeset revision, if specified.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid,
                                changectx=changectx)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def _loadfilter(self, filter):
         if filter not in self._filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: procutil.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not pycompat.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self._filterpats[filter] = l
         return self._filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self.wvfs.islink(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False, **kwargs):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(filename, data, backgroundclose=backgroundclose,
                             **kwargs)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
             else:
                 self.wvfs.setflags(filename, False, False)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if (self.ui.configbool('devel', 'all-warnings')
                 or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError('transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest(name=desc)
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found"),
                 hint=_("run 'hg recover' to clean up transaction"))
 
         idbase = "%.40f#%f" % (random.random(), time.time())
         ha = hex(hashlib.sha1(idbase).digest())
         txnid = 'TXN:' + ha
         self.hook('pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {'plain': self.vfs, 'store': self.svfs} # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         # Code to track tag movement
         #
         # Since tags are all handled as file content, it is actually quite hard
         # to track these movement from a code perspective. So we fallback to a
         # tracking at the repository level. One could envision to track changes
         # to the '.hgtags' file through changegroup apply but that fails to
         # cope with case where transaction expose new heads without changegroup
         # being involved (eg: phase movement).
         #
         # For now, We gate the feature behind a flag since this likely comes
         # with performance impacts. The current code run more often than needed
         # and do not use caches as much as it could.  The current focus is on
         # the behavior of the feature so we disable it by default. The flag
         # will be removed when we are happy with the performance impact.
         #
         # Once this feature is no longer experimental move the following
         # documentation to the appropriate help section:
         #
         # The ``HG_TAG_MOVED`` variable will be set if the transaction touched
         # tags (new or changed or deleted tags). In addition the details of
         # these changes are made available in a file at:
         #     ``REPOROOT/.hg/changes/tags.changes``.
         # Make sure you check for HG_TAG_MOVED before reading that file as it
         # might exist from a previous transaction even if no tag were touched
         # in this one. Changes are recorded in a line base format::
         #
         #     <action> <hex-node> <tag-name>\n
         #
         # Actions are defined as follow:
         #   "-R": tag is removed,
         #   "+A": tag is added,
         #   "-M": tag is moved (old value),
         #   "+M": tag is moved (new value),
         tracktags = lambda x: None
         # experimental config: experimental.hook-track-tags
         shouldtracktags = self.ui.configbool('experimental', 'hook-track-tags')
         if desc != 'strip' and shouldtracktags:
             oldheads = self.changelog.headrevs()
             def tracktags(tr2):
                 repo = reporef()
                 oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads)
                 newheads = repo.changelog.headrevs()
                 newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads)
                 # notes: we compare lists here.
                 # As we do it only once buiding set would not be cheaper
                 changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes)
                 if changes:
                     tr2.hookargs['tag_moved'] = '1'
                     with repo.vfs('changes/tags.changes', 'w',
                                   atomictemp=True) as changesfile:
                         # note: we do not register the file to the transaction
                         # because we needs it to still exist on the transaction
                         # is close (for txnclose hooks)
                         tagsmod.writediff(changesfile, changes)
         def validate(tr2):
             """will run pre-closing hooks"""
             # XXX the transaction API is a bit lacking here so we take a hacky
             # path for now
             #
             # We cannot add this as a "pending" hooks since the 'tr.hookargs'
             # dict is copied before these run. In addition we needs the data
             # available to in memory hooks too.
             #
             # Moreover, we also need to make sure this runs before txnclose
             # hooks and there is no "pending" mechanism that would execute
             # logic only if hooks are about to run.
             #
             # Fixing this limitation of the transaction is also needed to track
             # other families of changes (bookmarks, phases, obsolescence).
             #
             # This will have to be fixed before we remove the experimental
             # gating.
             tracktags(tr2)
             repo = reporef()
             if repo.ui.configbool('experimental', 'single-head-per-branch'):
                 scmutil.enforcesinglehead(repo, tr2, desc)
             if hook.hashook(repo.ui, 'pretxnclose-bookmark'):
                 for name, (old, new) in sorted(tr.changes['bookmarks'].items()):
                     args = tr.hookargs.copy()
                     args.update(bookmarks.preparehookargs(name, old, new))
                     repo.hook('pretxnclose-bookmark', throw=True,
                               txnname=desc,
                               **pycompat.strkwargs(args))
             if hook.hashook(repo.ui, 'pretxnclose-phase'):
                 cl = repo.unfiltered().changelog
                 for rev, (old, new) in tr.changes['phases'].items():
                     args = tr.hookargs.copy()
                     node = hex(cl.node(rev))
                     args.update(phases.preparehookargs(node, old, new))
                     repo.hook('pretxnclose-phase', throw=True, txnname=desc,
                               **pycompat.strkwargs(args))
 
             repo.hook('pretxnclose', throw=True,
                       txnname=desc, **pycompat.strkwargs(tr.hookargs))
         def releasefn(tr, success):
             repo = reporef()
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 narrowspec.restorebackup(self, 'journal.narrowspec')
                 narrowspec.restorewcbackup(self, 'journal.narrowspec.dirstate')
                 repo.dirstate.restorebackup(None, 'journal.dirstate')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(rp, self.svfs, vfsmap,
                                      "journal",
                                      "undo",
                                      aftertrans(renames),
                                      self.store.createmode,
                                      validator=validate,
                                      releasefn=releasefn,
                                      checkambigfiles=_cachedfiles,
                                      name=desc)
         tr.changes['origrepolen'] = len(self)
         tr.changes['obsmarkers'] = set()
         tr.changes['phases'] = {}
         tr.changes['bookmarks'] = {}
 
         tr.hookargs['txnid'] = txnid
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize('flush-fncache', self.store.write)
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run
             """
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hookfunc():
                 repo = reporef()
                 if hook.hashook(repo.ui, 'txnclose-bookmark'):
                     bmchanges = sorted(tr.changes['bookmarks'].items())
                     for name, (old, new) in bmchanges:
                         args = tr.hookargs.copy()
                         args.update(bookmarks.preparehookargs(name, old, new))
                         repo.hook('txnclose-bookmark', throw=False,
                                   txnname=desc, **pycompat.strkwargs(args))
 
                 if hook.hashook(repo.ui, 'txnclose-phase'):
                     cl = repo.unfiltered().changelog
                     phasemv = sorted(tr.changes['phases'].items())
                     for rev, (old, new) in phasemv:
                         args = tr.hookargs.copy()
                         node = hex(cl.node(rev))
                         args.update(phases.preparehookargs(node, old, new))
                         repo.hook('txnclose-phase', throw=False, txnname=desc,
                                   **pycompat.strkwargs(args))
 
                 repo.hook('txnclose', throw=False, txnname=desc,
                           **pycompat.strkwargs(hookargs))
             reporef()._afterlock(hookfunc)
         tr.addfinalize('txnclose-hook', txnclosehook)
         # Include a leading "-" to make it happen before the transaction summary
         # reports registered via scmutil.registersummarycallback() whose names
         # are 00-txnreport etc. That way, the caches will be warm when the
         # callbacks run.
         tr.addpostclose('-warm-cache', self._buildcacheupdater(tr))
         def txnaborthook(tr2):
             """To be run if transaction is aborted
             """
             reporef().hook('txnabort', throw=False, txnname=desc,
                            **pycompat.strkwargs(tr2.hookargs))
         tr.addabort('txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose('refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         scmutil.registersummarycallback(self, tr, desc)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.svfs, 'journal.narrowspec'),
                 (self.vfs, 'journal.narrowspec.dirstate'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     @unfilteredmethod
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, 'journal.dirstate')
         narrowspec.savewcbackup(self, 'journal.narrowspec.dirstate')
         narrowspec.savebackup(self, 'journal.narrowspec')
         self.vfs.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.vfs.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.vfs.write("journal.bookmarks",
                           self.vfs.tryread("bookmarks"))
         self.svfs.write("journal.phaseroots",
                            self.svfs.tryread("phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 vfsmap = {'': self.svfs,
                           'plain': self.vfs,}
                 transaction.rollback(self.svfs, vfsmap, "journal",
                                      self.ui.warn,
                                      checkambigfiles=_cachedfiles)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 dsguard = dirstateguard.dirstateguard(self, 'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %d'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise error.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {'plain': self.vfs, '': self.svfs}
         transaction.rollback(self.svfs, vfsmap, 'undo', ui.warn,
                              checkambigfiles=_cachedfiles)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks', checkambig=True)
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots', checkambig=True)
         self.invalidate()
 
         parentgone = any(p not in self.changelog.nodemap for p in parents)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, 'undo.narrowspec')
             narrowspec.restorewcbackup(self, 'undo.narrowspec.dirstate')
             self.dirstate.restorebackup(None, 'undo.dirstate')
             try:
                 branch = self.vfs.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
             mergemod.mergestate.clean(self, self['.'].node())
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def _buildcacheupdater(self, newtransaction):
         """called during transaction to build the callback updating cache
 
         Lives on the repository to help extension who might want to augment
         this logic. For this purpose, the created transaction is passed to the
         method.
         """
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         def updater(tr):
             repo = reporef()
             repo.updatecaches(tr)
         return updater
 
     @unfilteredmethod
     def updatecaches(self, tr=None, full=False):
         """warm appropriate caches
 
         If this function is called after a transaction closed. The transaction
         will be available in the 'tr' argument. This can be used to selectively
         update caches relevant to the changes in that transaction.
 
         If 'full' is set, make sure all caches the function knows about have
         up-to-date data. Even the ones usually loaded more lazily.
         """
         if tr is not None and tr.hookargs.get('source') == 'strip':
             # During strip, many caches are invalid but
             # later call to `destroyed` will refresh them.
             return
 
         if tr is None or tr.changes['origrepolen'] < len(self):
             # accessing the 'ser ved' branchmap should refresh all the others,
             self.ui.debug('updating the branch cache\n')
             self.filtered('served').branchmap()
 
         if full:
             rbc = self.revbranchcache()
             for r in self.changelog:
                 rbc.branchinfo(r)
             rbc.write()
 
             # ensure the working copy parents are in the manifestfulltextcache
             for ctx in self['.'].parents():
                 ctx.manifest()  # accessing the manifest is enough
 
     def invalidatecaches(self):
 
         if r'_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__[r'_tagscache']
 
         self._branchcaches.clear()
         self.invalidatevolatilesets()
         self._sparsesignaturecache.clear()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, r'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), r'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
             if (k == 'changelog' and
                 self.currenttransaction() and
                 self.changelog._delayed):
                 # The changelog object may store unwritten revisions. We don't
                 # want to lose them.
                 # TODO: Solve the problem instead of working around it.
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             k = pycompat.sysstr(k)
             if k == r'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(self, vfs, lockname, wait, releasefn, acquirefn, desc,
               inheritchecker=None, parentenvvar=None):
         parentlock = None
         # the contents of parentenvvar are used by the underlying lock to
         # determine whether it can be inherited
         if parentenvvar is not None:
             parentlock = encoding.environ.get(parentenvvar)
 
         timeout = 0
         warntimeout = 0
         if wait:
             timeout = self.ui.configint("ui", "timeout")
             warntimeout = self.ui.configint("ui", "timeout.warn")
         # internal config: ui.signal-safe-lock
         signalsafe = self.ui.configbool('ui', 'signal-safe-lock')
 
         l = lockmod.trylock(self.ui, vfs, lockname, timeout, warntimeout,
                             releasefn=releasefn,
                             acquirefn=acquirefn, desc=desc,
                             inheritchecker=inheritchecker,
                             parentlock=parentlock,
                             signalsafe=signalsafe)
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else: # no lock have been found.
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(self.svfs, "lock", wait, None,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def _wlockchecktransaction(self):
         if self.currenttransaction() is not None:
             raise error.LockInheritanceContractViolation(
                 'wlock cannot be inherited in the middle of a transaction')
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (self.ui.configbool('devel', 'all-warnings')
                      or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn('"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.vfs, "wlock", wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot,
                        inheritchecker=self._wlockchecktransaction,
                        parentenvvar='HG_WLOCK_LOCKER')
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = manifest2.get(fname, nullid)
         if isinstance(fctx, context.filectx):
             node = fctx.filenode()
             if node in [fparent1, fparent2]:
                 self.ui.debug('reusing %s filelog entry\n' % fname)
                 if manifest1.flags(fname) != fctx.flags():
                     changelist.append(fname)
                 return node
 
         flog = self.file(fname)
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # Here, we used to search backwards through history to try to find
             # where the file copy came from if the source of a copy was not in
             # the parent directory. However, this doesn't actually make sense to
             # do (what does a copy from something not in your working copy even
             # mean?) and it causes bugs (eg, issue4476). Instead, we will warn
             # the user that copy information was dropped, so if they didn't
             # expect this outcome it can be fixed, but this is the correct
             # behavior in this circumstance.
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         text = fctx.data()
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
         # are just the flags changed during merge?
         elif fname in manifest1 and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def checkcommitpatterns(self, wctx, vdirs, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == '.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _('file not found!'))
                 if f in vdirs: # visited directory
                     d = f + '/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _("no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _("file not tracked!"))
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra=None):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         # lock() for recent changelog (see issue4368)
         with self.wlock(), self.lock():
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and not match.always():
                 raise error.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(status.clean) # mq may commit clean files
 
             # check subrepos
             subs, commitsubs, newstate = subrepoutil.precommit(
                 self.ui, wctx, status, match, force=force)
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, vdirs, match, status, fail)
 
             cctx = context.workingcommitctx(self, status,
                                             text, user, date, extra)
 
             # internal config: ui.allowemptycommit
             allowemptycommit = (wctx.branch() != wctx.p1().branch()
                                 or extra.get('close') or merge or cctx.files()
                                 or self.ui.configbool('ui', 'allowemptycommit'))
             if not allowemptycommit:
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                                    subrepoutil.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepoutil.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 with self.transaction('commit'):
                     ret = self.commitctx(cctx, True)
                     # update bookmarks, dirstate and mergestate
                     bookmarks.update(self, [p1, p2], ret)
                     cctx.markcommitted(ret)
                     ms.reset()
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook("commit", node=node, parent1=parent1,
                           parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
 
         ctx.files() should list all files involved in this commit, i.e.
         modified/added/removed files. On merge, it may be wider than the
         ctx.files() to be committed, since any file nodes derived directly
         from p1 or p2 are excluded from the committed ctx.files().
         """
 
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         with self.lock(), self.transaction("commit") as tr:
             trp = weakref.proxy(tr)
 
             if ctx.manifestnode():
                 # reuse an existing manifest revision
                 self.ui.debug('reusing known manifest\n')
                 mn = ctx.manifestnode()
                 files = ctx.files()
             elif ctx.files():
                 m1ctx = p1.manifestctx()
                 m2ctx = p2.manifestctx()
                 mctx = m1ctx.copy()
 
                 m = mctx.read()
                 m1 = m1ctx.read()
                 m2 = m2ctx.read()
 
                 # check in files
                 added = []
                 changed = []
                 removed = list(ctx.removed())
                 linkrev = len(self)
                 self.ui.note(_("committing files:\n"))
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         if fctx is None:
                             removed.append(f)
                         else:
                             added.append(f)
                             m[f] = self._filecommit(fctx, m1, m2, linkrev,
                                                     trp, changed)
                             m.setflag(f, fctx.flags())
                     except OSError:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError as inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
 
                 # update manifest
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m]
                 for f in drop:
                     del m[f]
                 files = changed + removed
                 md = None
                 if not files:
                     # if no "files" actually changed in terms of the changelog,
                     # try hard to detect unmodified manifest entry so that the
                     # exact same commit can be reproduced later on convert.
                     md = m1.diff(m, scmutil.matchfiles(self, ctx.files()))
                 if not files and md:
                     self.ui.debug('not reusing manifest (no file change in '
                                   'changelog, but manifest differs)\n')
                 if files or md:
                     self.ui.note(_("committing manifest\n"))
                     # we're using narrowmatch here since it's already applied at
                     # other stages (such as dirstate.walk), so we're already
                     # ignoring things outside of narrowspec in most cases. The
                     # one case where we might have files outside the narrowspec
                     # at this point is merges, and we already error out in the
                     # case where the merge has files outside of the narrowspec,
                     # so this is safe.
                     mn = mctx.write(trp, linkrev,
                                     p1.manifestnode(), p2.manifestnode(),
                                     added, drop, match=self.narrowmatch())
                 else:
                     self.ui.debug('reusing manifest form p1 (listed files '
                                   'actually unchanged)\n')
                     mn = p1.manifestnode()
             else:
                 self.ui.debug('reusing manifest from p1 (no file change)\n')
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.ui.note(_("committing changelog\n"))
             self.changelog.delayupdate(tr)
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             # set the new commit is proper phase
             targetphase = subrepoutil.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.registernew(self, tr, targetphase, [n])
             return n
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # refresh all repository caches
         self.updatecaches()
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(node2, match, ignored, clean, unknown,
                                   listsubrepos)
 
     def addpostdsstatus(self, ps):
         """Add a callback to run within the wlock, at the point at which status
         fixups happen.
 
         On status completion, callback(wctx, status) will be called with the
         wlock held, unless the dirstate has changed from underneath or the wlock
         couldn't be grabbed.
 
         Callbacks should not capture and use a cached copy of the dirstate --
         it might change in the meanwhile. Instead, they should access the
         dirstate via wctx.repo().dirstate.
 
         This list is emptied out after each status run -- extensions should
         make sure it adds to this list each time dirstate.status is called.
         Extensions should also make sure they don't call this for statuses
         that don't involve the dirstate.
         """
 
         # The list is located here for uniqueness reasons -- it is actually
         # managed by the workingctx, but that isn't unique per-repo.
         self._postdsstatus.append(ps)
 
     def postdsstatus(self):
         """Used by workingctx to get the list of post-dirstate-status hooks."""
         return self._postdsstatus
 
     def clearpostdsstatus(self):
         """Used by workingctx to clear post-dirstate-status hooks."""
         del self._postdsstatus[:]
 
     def heads(self, start=None):
         if start is None:
             cl = self.changelog
             headrevs = reversed(cl.headrevs())
             return [cl.node(rev) for rev in headrevs]
 
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs = pycompat.strkwargs(hookargs)
             hookargs[r'namespace'] = namespace
             hookargs[r'key'] = key
             hookargs[r'old'] = old
             hookargs[r'new'] = new
             self.hook('prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_("pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_("(%s)\n") % exc.hint)
             return False
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         def runhook():
             self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                       ret=ret)
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, pycompat.bytestr(three),
                                    pycompat.bytestr(four),
                                    pycompat.bytestr(five))
 
     def savecommitmessage(self, text):
         fp = self.vfs('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             # if src and dest refer to a same file, vfs.rename is a no-op,
             # leaving both src and dest on disk. delete dest to make sure
             # the rename couldn't be such a no-op.
             vfs.tryunlink(dest)
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create, intents=None, createopts=None):
     localpath = util.urllocalpath(path)
     if create:
         createrepository(ui, localpath, createopts=createopts)
 
     return makelocalrepository(ui, localpath, intents=intents)
 
 def islocal(path):
     return True
 
 def defaultcreateopts(ui, createopts=None):
     """Populate the default creation options for a repository.
 
     A dictionary of explicitly requested creation options can be passed
     in. Missing keys will be populated.
     """
     createopts = dict(createopts or {})
 
     if 'backend' not in createopts:
         # experimental config: storage.new-repo-backend
         createopts['backend'] = ui.config('storage', 'new-repo-backend')
 
     return createopts
 
 def newreporequirements(ui, createopts):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     # If the repo is being created from a shared repository, we copy
     # its requirements.
     if 'sharedrepo' in createopts:
         requirements = set(createopts['sharedrepo'].requirements)
         if createopts.get('sharedrelative'):
             requirements.add('relshared')
         else:
             requirements.add('shared')
 
         return requirements
 
     if 'backend' not in createopts:
         raise error.ProgrammingError('backend key not present in createopts; '
                                      'was defaultcreateopts() called?')
 
     if createopts['backend'] != 'revlogv1':
         raise error.Abort(_('unable to determine repository requirements for '
                             'storage backend: %s') % createopts['backend'])
 
     requirements = {'revlogv1'}
     if ui.configbool('format', 'usestore'):
         requirements.add('store')
         if ui.configbool('format', 'usefncache'):
             requirements.add('fncache')
             if ui.configbool('format', 'dotencode'):
                 requirements.add('dotencode')
 
     compengine = ui.config('experimental', 'format.compression')
     if compengine not in util.compengines:
         raise error.Abort(_('compression engine %s defined by '
                             'experimental.format.compression not available') %
                           compengine,
                           hint=_('run "hg debuginstall" to list available '
                                  'compression engines'))
 
     # zlib is the historical default and doesn't need an explicit requirement.
     if compengine != 'zlib':
         requirements.add('exp-compression-%s' % compengine)
 
     if scmutil.gdinitconfig(ui):
         requirements.add('generaldelta')
         if ui.configbool('format', 'sparse-revlog'):
             requirements.add(SPARSEREVLOG_REQUIREMENT)
     if ui.configbool('experimental', 'treemanifest'):
         requirements.add('treemanifest')
 
     revlogv2 = ui.config('experimental', 'revlogv2')
     if revlogv2 == 'enable-unstable-format-and-corrupt-my-data':
         requirements.remove('revlogv1')
         # generaldelta is implied by revlogv2.
         requirements.discard('generaldelta')
         requirements.add(REVLOGV2_REQUIREMENT)
     # experimental config: format.internal-phase
     if ui.configbool('format', 'internal-phase'):
         requirements.add('internal-phase')
 
     if createopts.get('narrowfiles'):
         requirements.add(repository.NARROW_REQUIREMENT)
 
     if createopts.get('lfs'):
         requirements.add('lfs')
 
     return requirements
 
 def filterknowncreateopts(ui, createopts):
     """Filters a dict of repo creation options against options that are known.
 
     Receives a dict of repo creation options and returns a dict of those
     options that we don't know how to handle.
 
     This function is called as part of repository creation. If the
     returned dict contains any items, repository creation will not
     be allowed, as it means there was a request to create a repository
     with options not recognized by loaded code.
 
     Extensions can wrap this function to filter out creation options
     they know how to handle.
     """
     known = {
         'backend',
         'lfs',
         'narrowfiles',
         'sharedrepo',
         'sharedrelative',
         'shareditems',
         'shallowfilestore',
     }
 
     return {k: v for k, v in createopts.items() if k not in known}
 
 def createrepository(ui, path, createopts=None):
     """Create a new repository in a vfs.
 
     ``path`` path to the new repo's working directory.
     ``createopts`` options for the new repository.
 
     The following keys for ``createopts`` are recognized:
 
     backend
        The storage backend to use.
     lfs
        Repository will be created with ``lfs`` requirement. The lfs extension
        will automatically be loaded when the repository is accessed.
     narrowfiles
        Set up repository to support narrow file storage.
     sharedrepo
        Repository object from which storage should be shared.
     sharedrelative
        Boolean indicating if the path to the shared repo should be
        stored as relative. By default, the pointer to the "parent" repo
        is stored as an absolute path.
     shareditems
        Set of items to share to the new repository (in addition to storage).
     shallowfilestore
        Indicates that storage for files should be shallow (not all ancestor
        revisions are known).
     """
     createopts = defaultcreateopts(ui, createopts=createopts)
 
     unknownopts = filterknowncreateopts(ui, createopts)
 
     if not isinstance(unknownopts, dict):
         raise error.ProgrammingError('filterknowncreateopts() did not return '
                                      'a dict')
 
     if unknownopts:
         raise error.Abort(_('unable to create repository because of unknown '
                             'creation option: %s') %
                           ', '.join(sorted(unknownopts)),
                           hint=_('is a required extension not loaded?'))
 
     requirements = newreporequirements(ui, createopts=createopts)
 
     wdirvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
 
     hgvfs = vfsmod.vfs(wdirvfs.join(b'.hg'))
     if hgvfs.exists():
         raise error.RepoError(_('repository %s already exists') % path)
 
     if 'sharedrepo' in createopts:
         sharedpath = createopts['sharedrepo'].sharedpath
 
         if createopts.get('sharedrelative'):
             try:
                 sharedpath = os.path.relpath(sharedpath, hgvfs.base)
             except (IOError, ValueError) as e:
                 # ValueError is raised on Windows if the drive letters differ
                 # on each path.
                 raise error.Abort(_('cannot calculate relative path'),
                                   hint=stringutil.forcebytestr(e))
 
     if not wdirvfs.exists():
         wdirvfs.makedirs()
 
     hgvfs.makedir(notindexed=True)
     if 'sharedrepo' not in createopts:
         hgvfs.mkdir(b'cache')
     hgvfs.mkdir(b'wcache')
 
     if b'store' in requirements and 'sharedrepo' not in createopts:
         hgvfs.mkdir(b'store')
 
         # We create an invalid changelog outside the store so very old
         # Mercurial versions (which didn't know about the requirements
         # file) encounter an error on reading the changelog. This
         # effectively locks out old clients and prevents them from
         # mucking with a repo in an unknown format.
         #
         # The revlog header has version 2, which won't be recognized by
         # such old clients.
         hgvfs.append(b'00changelog.i',
                      b'\0\0\0\2 dummy changelog to prevent using the old repo '
                      b'layout')
 
     scmutil.writerequires(hgvfs, requirements)
 
     # Write out file telling readers where to find the shared store.
     if 'sharedrepo' in createopts:
         hgvfs.write(b'sharedpath', sharedpath)
 
     if createopts.get('shareditems'):
         shared = b'\n'.join(sorted(createopts['shareditems'])) + b'\n'
         hgvfs.write(b'shared', shared)
 
 def poisonrepository(repo):
     """Poison a repository instance so it can no longer be used."""
     # Perform any cleanup on the instance.
     repo.close()
 
     # Our strategy is to replace the type of the object with one that
     # has all attribute lookups result in error.
     #
     # But we have to allow the close() method because some constructors
     # of repos call close() on repo references.
     class poisonedrepository(object):
         def __getattribute__(self, item):
             if item == r'close':
                 return object.__getattribute__(self, item)
 
             raise error.ProgrammingError('repo instances should not be used '
                                          'after unshare')
 
         def close(self):
             pass
 
     # We may have a repoview, which intercepts __setattr__. So be sure
     # we operate at the lowest level possible.
     object.__setattr__(repo, r'__class__', poisonedrepository)

mercurial/match.py

@@ -1,1374 +1,1371 b''
 # match.py - filename matching
 #
 #  Copyright 2008, 2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import copy
 import itertools
 import os
 import re
 
 from .i18n import _
 from . import (
     encoding,
     error,
     pathutil,
     pycompat,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 allpatternkinds = ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                    'rootglob',
                    'listfile', 'listfile0', 'set', 'include', 'subinclude',
                    'rootfilesin')
 cwdrelativepatternkinds = ('relpath', 'glob')
 
 propertycache = util.propertycache
 
 def _rematcher(regex):
     '''compile the regexp with the best available regexp engine and return a
     matcher function'''
     m = util.re.compile(regex)
     try:
         # slightly faster, provided by facebook's re2 bindings
         return m.test_match
     except AttributeError:
         return m.match
 
-def _expandsets(root, cwd, kindpats, ctx, listsubrepos, badfn):
+def _expandsets(kindpats, ctx, listsubrepos, badfn):
     '''Returns the kindpats list with the 'set' patterns expanded to matchers'''
     matchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'set':
             if ctx is None:
                 raise error.ProgrammingError("fileset expression with no "
                                              "context")
             matchers.append(ctx.matchfileset(pat, badfn=badfn))
 
             if listsubrepos:
                 for subpath in ctx.substate:
                     sm = ctx.sub(subpath).matchfileset(pat, badfn=badfn)
-                    pm = prefixdirmatcher(root, cwd, subpath, sm, badfn=badfn)
+                    pm = prefixdirmatcher(subpath, sm, badfn=badfn)
                     matchers.append(pm)
 
             continue
         other.append((kind, pat, source))
     return matchers, other
 
 def _expandsubinclude(kindpats, root):
     '''Returns the list of subinclude matcher args and the kindpats without the
     subincludes in it.'''
     relmatchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'subinclude':
             sourceroot = pathutil.dirname(util.normpath(source))
             pat = util.pconvert(pat)
             path = pathutil.join(sourceroot, pat)
 
             newroot = pathutil.dirname(path)
             matcherargs = (newroot, '', [], ['include:%s' % path])
 
             prefix = pathutil.canonpath(root, root, newroot)
             if prefix:
                 prefix += '/'
             relmatchers.append((prefix, matcherargs))
         else:
             other.append((kind, pat, source))
 
     return relmatchers, other
 
 def _kindpatsalwaysmatch(kindpats):
     """"Checks whether the kindspats match everything, as e.g.
     'relpath:.' does.
     """
     for kind, pat, source in kindpats:
         if pat != '' or kind not in ['relpath', 'glob']:
             return False
     return True
 
-def _buildkindpatsmatcher(matchercls, root, cwd, kindpats, ctx=None,
+def _buildkindpatsmatcher(matchercls, root, kindpats, ctx=None,
                           listsubrepos=False, badfn=None):
     matchers = []
-    fms, kindpats = _expandsets(root, cwd, kindpats, ctx=ctx,
+    fms, kindpats = _expandsets(kindpats, ctx=ctx,
                                 listsubrepos=listsubrepos, badfn=badfn)
     if kindpats:
-        m = matchercls(root, cwd, kindpats, badfn=badfn)
+        m = matchercls(root, kindpats, badfn=badfn)
         matchers.append(m)
     if fms:
         matchers.extend(fms)
     if not matchers:
-        return nevermatcher(root, cwd, badfn=badfn)
+        return nevermatcher(badfn=badfn)
     if len(matchers) == 1:
         return matchers[0]
     return unionmatcher(matchers)
 
 def match(root, cwd, patterns=None, include=None, exclude=None, default='glob',
           auditor=None, ctx=None, listsubrepos=False, warn=None,
           badfn=None, icasefs=False):
     """build an object to match a set of file patterns
 
     arguments:
     root - the canonical root of the tree you're matching against
     cwd - the current working directory, if relevant
     patterns - patterns to find
     include - patterns to include (unless they are excluded)
     exclude - patterns to exclude (even if they are included)
     default - if a pattern in patterns has no explicit type, assume this one
     warn - optional function used for printing warnings
     badfn - optional bad() callback for this matcher instead of the default
     icasefs - make a matcher for wdir on case insensitive filesystems, which
         normalizes the given patterns to the case in the filesystem
 
     a pattern is one of:
     'glob:<glob>' - a glob relative to cwd
     're:<regexp>' - a regular expression
     'path:<path>' - a path relative to repository root, which is matched
                     recursively
     'rootfilesin:<path>' - a path relative to repository root, which is
                     matched non-recursively (will not match subdirectories)
     'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
     'relpath:<path>' - a path relative to cwd
     'relre:<regexp>' - a regexp that needn't match the start of a name
     'set:<fileset>' - a fileset expression
     'include:<path>' - a file of patterns to read and include
     'subinclude:<path>' - a file of patterns to match against files under
                           the same directory
     '<something>' - a pattern of the specified default type
     """
     normalize = _donormalize
     if icasefs:
         dirstate = ctx.repo().dirstate
         dsnormalize = dirstate.normalize
 
         def normalize(patterns, default, root, cwd, auditor, warn):
             kp = _donormalize(patterns, default, root, cwd, auditor, warn)
             kindpats = []
             for kind, pats, source in kp:
                 if kind not in ('re', 'relre'):  # regex can't be normalized
                     p = pats
                     pats = dsnormalize(pats)
 
                     # Preserve the original to handle a case only rename.
                     if p != pats and p in dirstate:
                         kindpats.append((kind, p, source))
 
                 kindpats.append((kind, pats, source))
             return kindpats
 
     if patterns:
         kindpats = normalize(patterns, default, root, cwd, auditor, warn)
         if _kindpatsalwaysmatch(kindpats):
-            m = alwaysmatcher(root, cwd, badfn)
+            m = alwaysmatcher(badfn)
         else:
-            m = _buildkindpatsmatcher(patternmatcher, root, cwd, kindpats,
-                                      ctx=ctx, listsubrepos=listsubrepos,
-                                      badfn=badfn)
+            m = _buildkindpatsmatcher(patternmatcher, root, kindpats, ctx=ctx,
+                                      listsubrepos=listsubrepos, badfn=badfn)
     else:
         # It's a little strange that no patterns means to match everything.
         # Consider changing this to match nothing (probably using nevermatcher).
-        m = alwaysmatcher(root, cwd, badfn)
+        m = alwaysmatcher(badfn)
 
     if include:
         kindpats = normalize(include, 'glob', root, cwd, auditor, warn)
-        im = _buildkindpatsmatcher(includematcher, root, cwd, kindpats, ctx=ctx,
+        im = _buildkindpatsmatcher(includematcher, root, kindpats, ctx=ctx,
                                    listsubrepos=listsubrepos, badfn=None)
         m = intersectmatchers(m, im)
     if exclude:
         kindpats = normalize(exclude, 'glob', root, cwd, auditor, warn)
-        em = _buildkindpatsmatcher(includematcher, root, cwd, kindpats, ctx=ctx,
+        em = _buildkindpatsmatcher(includematcher, root, kindpats, ctx=ctx,
                                    listsubrepos=listsubrepos, badfn=None)
         m = differencematcher(m, em)
     return m
 
 def exact(root, cwd, files, badfn=None):
-    return exactmatcher(root, cwd, files, badfn=badfn)
+    return exactmatcher(files, badfn=badfn)
 
 def always(root, cwd, badfn=None):
-    return alwaysmatcher(root, cwd, badfn=badfn)
+    return alwaysmatcher(badfn=badfn)
 
 def never(root, cwd, badfn=None):
-    return nevermatcher(root, cwd, badfn=badfn)
+    return nevermatcher(badfn=badfn)
 
 def badmatch(match, badfn):
     """Make a copy of the given matcher, replacing its bad method with the given
     one.
     """
     m = copy.copy(match)
     m.bad = badfn
     return m
 
 def _donormalize(patterns, default, root, cwd, auditor, warn):
     '''Convert 'kind:pat' from the patterns list to tuples with kind and
     normalized and rooted patterns and with listfiles expanded.'''
     kindpats = []
     for kind, pat in [_patsplit(p, default) for p in patterns]:
         if kind in cwdrelativepatternkinds:
             pat = pathutil.canonpath(root, cwd, pat, auditor)
         elif kind in ('relglob', 'path', 'rootfilesin', 'rootglob'):
             pat = util.normpath(pat)
         elif kind in ('listfile', 'listfile0'):
             try:
                 files = util.readfile(pat)
                 if kind == 'listfile0':
                     files = files.split('\0')
                 else:
                     files = files.splitlines()
                 files = [f for f in files if f]
             except EnvironmentError:
                 raise error.Abort(_("unable to read file list (%s)") % pat)
             for k, p, source in _donormalize(files, default, root, cwd,
                                              auditor, warn):
                 kindpats.append((k, p, pat))
             continue
         elif kind == 'include':
             try:
                 fullpath = os.path.join(root, util.localpath(pat))
                 includepats = readpatternfile(fullpath, warn)
                 for k, p, source in _donormalize(includepats, default,
                                                  root, cwd, auditor, warn):
                     kindpats.append((k, p, source or pat))
             except error.Abort as inst:
                 raise error.Abort('%s: %s' % (pat, inst[0]))
             except IOError as inst:
                 if warn:
                     warn(_("skipping unreadable pattern file '%s': %s\n") %
                          (pat, stringutil.forcebytestr(inst.strerror)))
             continue
         # else: re or relre - which cannot be normalized
         kindpats.append((kind, pat, ''))
     return kindpats
 
 class basematcher(object):
 
-    def __init__(self, root, cwd, badfn=None):
-        self._root = root
-        self._cwd = cwd
+    def __init__(self, badfn=None):
         if badfn is not None:
             self.bad = badfn
 
     def __call__(self, fn):
         return self.matchfn(fn)
     def __iter__(self):
         for f in self._files:
             yield f
     # Callbacks related to how the matcher is used by dirstate.walk.
     # Subscribers to these events must monkeypatch the matcher object.
     def bad(self, f, msg):
         '''Callback from dirstate.walk for each explicit file that can't be
         found/accessed, with an error message.'''
 
     # If an explicitdir is set, it will be called when an explicitly listed
     # directory is visited.
     explicitdir = None
 
     # If an traversedir is set, it will be called when a directory discovered
     # by recursive traversal is visited.
     traversedir = None
 
     @propertycache
     def _files(self):
         return []
 
     def files(self):
         '''Explicitly listed files or patterns or roots:
         if no patterns or .always(): empty list,
         if exact: list exact files,
         if not .anypats(): list all files and dirs,
         else: optimal roots'''
         return self._files
 
     @propertycache
     def _fileset(self):
         return set(self._files)
 
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fileset
 
     def matchfn(self, f):
         return False
 
     def visitdir(self, dir):
         '''Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories. This is
         based on the match's primary, included, and excluded patterns.
 
         Returns the string 'all' if the given directory and all subdirectories
         should be visited. Otherwise returns True or False indicating whether
         the given directory should be visited.
         '''
         return True
 
     def visitchildrenset(self, dir):
         '''Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories, and
         potentially lists which subdirectories of that directory should be
         visited. This is based on the match's primary, included, and excluded
         patterns.
 
         This function is very similar to 'visitdir', and the following mapping
         can be applied:
 
              visitdir | visitchildrenlist
             ----------+-------------------
              False    | set()
              'all'    | 'all'
              True     | 'this' OR non-empty set of subdirs -or files- to visit
 
         Example:
           Assume matchers ['path:foo/bar', 'rootfilesin:qux'], we would return
           the following values (assuming the implementation of visitchildrenset
           is capable of recognizing this; some implementations are not).
 
           '.' -> {'foo', 'qux'}
           'baz' -> set()
           'foo' -> {'bar'}
           # Ideally this would be 'all', but since the prefix nature of matchers
           # is applied to the entire matcher, we have to downgrade this to
           # 'this' due to the non-prefix 'rootfilesin'-kind matcher being mixed
           # in.
           'foo/bar' -> 'this'
           'qux' -> 'this'
 
         Important:
           Most matchers do not know if they're representing files or
           directories. They see ['path:dir/f'] and don't know whether 'f' is a
           file or a directory, so visitchildrenset('dir') for most matchers will
           return {'f'}, but if the matcher knows it's a file (like exactmatcher
           does), it may return 'this'. Do not rely on the return being a set
           indicating that there are no files in this dir to investigate (or
           equivalently that if there are files to investigate in 'dir' that it
           will always return 'this').
         '''
         return 'this'
 
     def always(self):
         '''Matcher will match everything and .files() will be empty --
         optimization might be possible.'''
         return False
 
     def isexact(self):
         '''Matcher will match exactly the list of files in .files() --
         optimization might be possible.'''
         return False
 
     def prefix(self):
         '''Matcher will match the paths in .files() recursively --
         optimization might be possible.'''
         return False
 
     def anypats(self):
         '''None of .always(), .isexact(), and .prefix() is true --
         optimizations will be difficult.'''
         return not self.always() and not self.isexact() and not self.prefix()
 
 class alwaysmatcher(basematcher):
     '''Matches everything.'''
 
-    def __init__(self, root, cwd, badfn=None):
-        super(alwaysmatcher, self).__init__(root, cwd, badfn)
+    def __init__(self, badfn=None):
+        super(alwaysmatcher, self).__init__(badfn)
 
     def always(self):
         return True
 
     def matchfn(self, f):
         return True
 
     def visitdir(self, dir):
         return 'all'
 
     def visitchildrenset(self, dir):
         return 'all'
 
     def __repr__(self):
         return r'<alwaysmatcher>'
 
 class nevermatcher(basematcher):
     '''Matches nothing.'''
 
-    def __init__(self, root, cwd, badfn=None):
-        super(nevermatcher, self).__init__(root, cwd, badfn)
+    def __init__(self, badfn=None):
+        super(nevermatcher, self).__init__(badfn)
 
     # It's a little weird to say that the nevermatcher is an exact matcher
     # or a prefix matcher, but it seems to make sense to let callers take
     # fast paths based on either. There will be no exact matches, nor any
     # prefixes (files() returns []), so fast paths iterating over them should
     # be efficient (and correct).
     def isexact(self):
         return True
 
     def prefix(self):
         return True
 
     def visitdir(self, dir):
         return False
 
     def visitchildrenset(self, dir):
         return set()
 
     def __repr__(self):
         return r'<nevermatcher>'
 
 class predicatematcher(basematcher):
     """A matcher adapter for a simple boolean function"""
 
-    def __init__(self, root, cwd, predfn, predrepr=None, badfn=None):
-        super(predicatematcher, self).__init__(root, cwd, badfn)
+    def __init__(self, predfn, predrepr=None, badfn=None):
+        super(predicatematcher, self).__init__(badfn)
         self.matchfn = predfn
         self._predrepr = predrepr
 
     @encoding.strmethod
     def __repr__(self):
         s = (stringutil.buildrepr(self._predrepr)
              or pycompat.byterepr(self.matchfn))
         return '<predicatenmatcher pred=%s>' % s
 
 class patternmatcher(basematcher):
 
-    def __init__(self, root, cwd, kindpats, badfn=None):
-        super(patternmatcher, self).__init__(root, cwd, badfn)
+    def __init__(self, root, kindpats, badfn=None):
+        super(patternmatcher, self).__init__(badfn)
 
         self._files = _explicitfiles(kindpats)
         self._prefix = _prefix(kindpats)
         self._pats, self.matchfn = _buildmatch(kindpats, '$', root)
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileset)) | {'.'}
 
     def visitdir(self, dir):
         if self._prefix and dir in self._fileset:
             return 'all'
         return ('.' in self._fileset or
                 dir in self._fileset or
                 dir in self._dirs or
                 any(parentdir in self._fileset
                     for parentdir in util.finddirs(dir)))
 
     def visitchildrenset(self, dir):
         ret = self.visitdir(dir)
         if ret is True:
             return 'this'
         elif not ret:
             return set()
         assert ret == 'all'
         return 'all'
 
     def prefix(self):
         return self._prefix
 
     @encoding.strmethod
     def __repr__(self):
         return ('<patternmatcher patterns=%r>' % pycompat.bytestr(self._pats))
 
 # This is basically a reimplementation of util.dirs that stores the children
 # instead of just a count of them, plus a small optional optimization to avoid
 # some directories we don't need.
 class _dirchildren(object):
     def __init__(self, paths, onlyinclude=None):
         self._dirs = {}
         self._onlyinclude = onlyinclude or []
         addpath = self.addpath
         for f in paths:
             addpath(f)
 
     def addpath(self, path):
         if path == '.':
             return
         dirs = self._dirs
         findsplitdirs = _dirchildren._findsplitdirs
         for d, b in findsplitdirs(path):
             if d not in self._onlyinclude:
                 continue
             dirs.setdefault(d, set()).add(b)
 
     @staticmethod
     def _findsplitdirs(path):
         # yields (dirname, basename) tuples, walking back to the root.  This is
         # very similar to util.finddirs, except:
         #  - produces a (dirname, basename) tuple, not just 'dirname'
         #  - includes root dir
         # Unlike manifest._splittopdir, this does not suffix `dirname` with a
         # slash, and produces '.' for the root instead of ''.
         oldpos = len(path)
         pos = path.rfind('/')
         while pos != -1:
             yield path[:pos], path[pos + 1:oldpos]
             oldpos = pos
             pos = path.rfind('/', 0, pos)
         yield '.', path[:oldpos]
 
     def get(self, path):
         return self._dirs.get(path, set())
 
 class includematcher(basematcher):
 
-    def __init__(self, root, cwd, kindpats, badfn=None):
-        super(includematcher, self).__init__(root, cwd, badfn)
+    def __init__(self, root, kindpats, badfn=None):
+        super(includematcher, self).__init__(badfn)
 
         self._pats, self.matchfn = _buildmatch(kindpats, '(?:/|$)', root)
         self._prefix = _prefix(kindpats)
         roots, dirs, parents = _rootsdirsandparents(kindpats)
         # roots are directories which are recursively included.
         self._roots = set(roots)
         # dirs are directories which are non-recursively included.
         self._dirs = set(dirs)
         # parents are directories which are non-recursively included because
         # they are needed to get to items in _dirs or _roots.
         self._parents = set(parents)
 
     def visitdir(self, dir):
         if self._prefix and dir in self._roots:
             return 'all'
         return ('.' in self._roots or
                 dir in self._roots or
                 dir in self._dirs or
                 dir in self._parents or
                 any(parentdir in self._roots
                     for parentdir in util.finddirs(dir)))
 
     @propertycache
     def _allparentschildren(self):
         # It may seem odd that we add dirs, roots, and parents, and then
         # restrict to only parents. This is to catch the case of:
         #   dirs = ['foo/bar']
         #   parents = ['foo']
         # if we asked for the children of 'foo', but had only added
         # self._parents, we wouldn't be able to respond ['bar'].
         return _dirchildren(
                 itertools.chain(self._dirs, self._roots, self._parents),
                 onlyinclude=self._parents)
 
     def visitchildrenset(self, dir):
         if self._prefix and dir in self._roots:
             return 'all'
         # Note: this does *not* include the 'dir in self._parents' case from
         # visitdir, that's handled below.
         if ('.' in self._roots or
             dir in self._roots or
             dir in self._dirs or
             any(parentdir in self._roots
                 for parentdir in util.finddirs(dir))):
             return 'this'
 
         if dir in self._parents:
             return self._allparentschildren.get(dir) or set()
         return set()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<includematcher includes=%r>' % pycompat.bytestr(self._pats))
 
 class exactmatcher(basematcher):
     '''Matches the input files exactly. They are interpreted as paths, not
     patterns (so no kind-prefixes).
     '''
 
-    def __init__(self, root, cwd, files, badfn=None):
-        super(exactmatcher, self).__init__(root, cwd, badfn)
+    def __init__(self, files, badfn=None):
+        super(exactmatcher, self).__init__(badfn)
 
         if isinstance(files, list):
             self._files = files
         else:
             self._files = list(files)
 
     matchfn = basematcher.exact
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileset)) | {'.'}
 
     def visitdir(self, dir):
         return dir in self._dirs
 
     def visitchildrenset(self, dir):
         if not self._fileset or dir not in self._dirs:
             return set()
 
         candidates = self._fileset | self._dirs - {'.'}
         if dir != '.':
             d = dir + '/'
             candidates = set(c[len(d):] for c in candidates if
                              c.startswith(d))
         # self._dirs includes all of the directories, recursively, so if
         # we're attempting to match foo/bar/baz.txt, it'll have '.', 'foo',
         # 'foo/bar' in it. Thus we can safely ignore a candidate that has a
         # '/' in it, indicating a it's for a subdir-of-a-subdir; the
         # immediate subdir will be in there without a slash.
         ret = {c for c in candidates if '/' not in c}
         # We really do not expect ret to be empty, since that would imply that
         # there's something in _dirs that didn't have a file in _fileset.
         assert ret
         return ret
 
     def isexact(self):
         return True
 
     @encoding.strmethod
     def __repr__(self):
         return ('<exactmatcher files=%r>' % self._files)
 
 class differencematcher(basematcher):
     '''Composes two matchers by matching if the first matches and the second
     does not.
 
-    The second matcher's non-matching-attributes (root, cwd, bad, explicitdir,
+    The second matcher's non-matching-attributes (bad, explicitdir,
     traversedir) are ignored.
     '''
     def __init__(self, m1, m2):
-        super(differencematcher, self).__init__(m1._root, m1._cwd)
+        super(differencematcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
 
     def matchfn(self, f):
         return self._m1(f) and not self._m2(f)
 
     @propertycache
     def _files(self):
         if self.isexact():
             return [f for f in self._m1.files() if self(f)]
         # If m1 is not an exact matcher, we can't easily figure out the set of
         # files, because its files() are not always files. For example, if
         # m1 is "path:dir" and m2 is "rootfileins:.", we don't
         # want to remove "dir" from the set even though it would match m2,
         # because the "dir" in m1 may not be a file.
         return self._m1.files()
 
     def visitdir(self, dir):
         if self._m2.visitdir(dir) == 'all':
             return False
         elif not self._m2.visitdir(dir):
             # m2 does not match dir, we can return 'all' here if possible
             return self._m1.visitdir(dir)
         return bool(self._m1.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m2_set = self._m2.visitchildrenset(dir)
         if m2_set == 'all':
             return set()
         m1_set = self._m1.visitchildrenset(dir)
         # Possible values for m1: 'all', 'this', set(...), set()
         # Possible values for m2:        'this', set(...), set()
         # If m2 has nothing under here that we care about, return m1, even if
         # it's 'all'. This is a change in behavior from visitdir, which would
         # return True, not 'all', for some reason.
         if not m2_set:
             return m1_set
         if m1_set in ['all', 'this']:
             # Never return 'all' here if m2_set is any kind of non-empty (either
             # 'this' or set(foo)), since m2 might return set() for a
             # subdirectory.
             return 'this'
         # Possible values for m1:         set(...), set()
         # Possible values for m2: 'this', set(...)
         # We ignore m2's set results. They're possibly incorrect:
         #  m1 = path:dir/subdir, m2=rootfilesin:dir, visitchildrenset('.'):
         #    m1 returns {'dir'}, m2 returns {'dir'}, if we subtracted we'd
         #    return set(), which is *not* correct, we still need to visit 'dir'!
         return m1_set
 
     def isexact(self):
         return self._m1.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<differencematcher m1=%r, m2=%r>' % (self._m1, self._m2))
 
 def intersectmatchers(m1, m2):
     '''Composes two matchers by matching if both of them match.
 
-    The second matcher's non-matching-attributes (root, cwd, bad, explicitdir,
+    The second matcher's non-matching-attributes (bad, explicitdir,
     traversedir) are ignored.
     '''
     if m1 is None or m2 is None:
         return m1 or m2
     if m1.always():
         m = copy.copy(m2)
         # TODO: Consider encapsulating these things in a class so there's only
         # one thing to copy from m1.
         m.bad = m1.bad
         m.explicitdir = m1.explicitdir
         m.traversedir = m1.traversedir
         return m
     if m2.always():
         m = copy.copy(m1)
         return m
     return intersectionmatcher(m1, m2)
 
 class intersectionmatcher(basematcher):
     def __init__(self, m1, m2):
-        super(intersectionmatcher, self).__init__(m1._root, m1._cwd)
+        super(intersectionmatcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
 
     @propertycache
     def _files(self):
         if self.isexact():
             m1, m2 = self._m1, self._m2
             if not m1.isexact():
                 m1, m2 = m2, m1
             return [f for f in m1.files() if m2(f)]
         # It neither m1 nor m2 is an exact matcher, we can't easily intersect
         # the set of files, because their files() are not always files. For
         # example, if intersecting a matcher "-I glob:foo.txt" with matcher of
         # "path:dir2", we don't want to remove "dir2" from the set.
         return self._m1.files() + self._m2.files()
 
     def matchfn(self, f):
         return self._m1(f) and self._m2(f)
 
     def visitdir(self, dir):
         visit1 = self._m1.visitdir(dir)
         if visit1 == 'all':
             return self._m2.visitdir(dir)
         # bool() because visit1=True + visit2='all' should not be 'all'
         return bool(visit1 and self._m2.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m1_set = self._m1.visitchildrenset(dir)
         if not m1_set:
             return set()
         m2_set = self._m2.visitchildrenset(dir)
         if not m2_set:
             return set()
 
         if m1_set == 'all':
             return m2_set
         elif m2_set == 'all':
             return m1_set
 
         if m1_set == 'this' or m2_set == 'this':
             return 'this'
 
         assert isinstance(m1_set, set) and isinstance(m2_set, set)
         return m1_set.intersection(m2_set)
 
     def always(self):
         return self._m1.always() and self._m2.always()
 
     def isexact(self):
         return self._m1.isexact() or self._m2.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<intersectionmatcher m1=%r, m2=%r>' % (self._m1, self._m2))
 
 class subdirmatcher(basematcher):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> from . import pycompat
     >>> m1 = match(b'root', b'', [b'a.txt', b'sub/b.txt'])
     >>> m2 = subdirmatcher(b'sub', m1)
     >>> bool(m2(b'a.txt'))
     False
     >>> bool(m2(b'b.txt'))
     True
     >>> bool(m2.matchfn(b'a.txt'))
     False
     >>> bool(m2.matchfn(b'b.txt'))
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact(b'b.txt')
     True
     >>> def bad(f, msg):
     ...     print(pycompat.sysstr(b"%s: %s" % (f, msg)))
     >>> m1.bad = bad
     >>> m2.bad(b'x.txt', b'No such file')
     sub/x.txt: No such file
     """
 
     def __init__(self, path, matcher):
-        super(subdirmatcher, self).__init__(matcher._root, matcher._cwd)
+        super(subdirmatcher, self).__init__()
         self._path = path
         self._matcher = matcher
         self._always = matcher.always()
 
         self._files = [f[len(path) + 1:] for f in matcher._files
                        if f.startswith(path + "/")]
 
         # If the parent repo had a path to this subrepo and the matcher is
         # a prefix matcher, this submatcher always matches.
         if matcher.prefix():
             self._always = any(f == path for f in matcher._files)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + "/" + f, msg)
 
     def matchfn(self, f):
         # Some information is lost in the superclass's constructor, so we
         # can not accurately create the matching function for the subdirectory
         # from the inputs. Instead, we override matchfn() and visitdir() to
         # call the original matcher with the subdirectory path prepended.
         return self._matcher.matchfn(self._path + "/" + f)
 
     def visitdir(self, dir):
         if dir == '.':
             dir = self._path
         else:
             dir = self._path + "/" + dir
         return self._matcher.visitdir(dir)
 
     def visitchildrenset(self, dir):
         if dir == '.':
             dir = self._path
         else:
             dir = self._path + "/" + dir
         return self._matcher.visitchildrenset(dir)
 
     def always(self):
         return self._always
 
     def prefix(self):
         return self._matcher.prefix() and not self._always
 
     @encoding.strmethod
     def __repr__(self):
         return ('<subdirmatcher path=%r, matcher=%r>' %
                 (self._path, self._matcher))
 
 class prefixdirmatcher(basematcher):
     """Adapt a matcher to work on a parent directory.
 
-    The matcher's non-matching-attributes (root, cwd, bad, explicitdir,
-    traversedir) are ignored.
+    The matcher's non-matching-attributes (bad, explicitdir, traversedir) are
+    ignored.
 
     The prefix path should usually be the relative path from the root of
     this matcher to the root of the wrapped matcher.
 
     >>> m1 = match(util.localpath(b'root/d/e'), b'f', [b'../a.txt', b'b.txt'])
-    >>> m2 = prefixdirmatcher(b'root', b'd/e/f', b'd/e', m1)
+    >>> m2 = prefixdirmatcher(b'd/e', m1)
     >>> bool(m2(b'a.txt'),)
     False
     >>> bool(m2(b'd/e/a.txt'))
     True
     >>> bool(m2(b'd/e/b.txt'))
     False
     >>> m2.files()
     ['d/e/a.txt', 'd/e/f/b.txt']
     >>> m2.exact(b'd/e/a.txt')
     True
     >>> m2.visitdir(b'd')
     True
     >>> m2.visitdir(b'd/e')
     True
     >>> m2.visitdir(b'd/e/f')
     True
     >>> m2.visitdir(b'd/e/g')
     False
     >>> m2.visitdir(b'd/ef')
     False
     """
 
-    def __init__(self, root, cwd, path, matcher, badfn=None):
-        super(prefixdirmatcher, self).__init__(root, cwd, badfn)
+    def __init__(self, path, matcher, badfn=None):
+        super(prefixdirmatcher, self).__init__(badfn)
         if not path:
             raise error.ProgrammingError('prefix path must not be empty')
         self._path = path
         self._pathprefix = path + '/'
         self._matcher = matcher
 
     @propertycache
     def _files(self):
         return [self._pathprefix + f for f in self._matcher._files]
 
     def matchfn(self, f):
         if not f.startswith(self._pathprefix):
             return False
         return self._matcher.matchfn(f[len(self._pathprefix):])
 
     @propertycache
     def _pathdirs(self):
         return set(util.finddirs(self._path)) | {'.'}
 
     def visitdir(self, dir):
         if dir == self._path:
             return self._matcher.visitdir('.')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitdir(dir[len(self._pathprefix):])
         return dir in self._pathdirs
 
     def visitchildrenset(self, dir):
         if dir == self._path:
             return self._matcher.visitchildrenset('.')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitchildrenset(dir[len(self._pathprefix):])
         if dir in self._pathdirs:
             return 'this'
         return set()
 
     def isexact(self):
         return self._matcher.isexact()
 
     def prefix(self):
         return self._matcher.prefix()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<prefixdirmatcher path=%r, matcher=%r>'
                 % (pycompat.bytestr(self._path), self._matcher))
 
 class unionmatcher(basematcher):
     """A matcher that is the union of several matchers.
 
-    The non-matching-attributes (root, cwd, bad, explicitdir, traversedir) are
-    taken from the first matcher.
+    The non-matching-attributes (bad, explicitdir, traversedir) are taken from
+    the first matcher.
     """
 
     def __init__(self, matchers):
         m1 = matchers[0]
-        super(unionmatcher, self).__init__(m1._root, m1._cwd)
+        super(unionmatcher, self).__init__()
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
         self._matchers = matchers
 
     def matchfn(self, f):
         for match in self._matchers:
             if match(f):
                 return True
         return False
 
     def visitdir(self, dir):
         r = False
         for m in self._matchers:
             v = m.visitdir(dir)
             if v == 'all':
                 return v
             r |= v
         return r
 
     def visitchildrenset(self, dir):
         r = set()
         this = False
         for m in self._matchers:
             v = m.visitchildrenset(dir)
             if not v:
                 continue
             if v == 'all':
                 return v
             if this or v == 'this':
                 this = True
                 # don't break, we might have an 'all' in here.
                 continue
             assert isinstance(v, set)
             r = r.union(v)
         if this:
             return 'this'
         return r
 
     @encoding.strmethod
     def __repr__(self):
         return ('<unionmatcher matchers=%r>' % self._matchers)
 
 def patkind(pattern, default=None):
     '''If pattern is 'kind:pat' with a known kind, return kind.'''
     return _patsplit(pattern, default)[0]
 
 def _patsplit(pattern, default):
     """Split a string into the optional pattern kind prefix and the actual
     pattern."""
     if ':' in pattern:
         kind, pat = pattern.split(':', 1)
         if kind in allpatternkinds:
             return kind, pat
     return default, pattern
 
 def _globre(pat):
     r'''Convert an extended glob string to a regexp string.
 
     >>> from . import pycompat
     >>> def bprint(s):
     ...     print(pycompat.sysstr(s))
     >>> bprint(_globre(br'?'))
     .
     >>> bprint(_globre(br'*'))
     [^/]*
     >>> bprint(_globre(br'**'))
     .*
     >>> bprint(_globre(br'**/a'))
     (?:.*/)?a
     >>> bprint(_globre(br'a/**/b'))
     a/(?:.*/)?b
     >>> bprint(_globre(br'[a*?!^][^b][!c]'))
     [a*?!^][\^b][^c]
     >>> bprint(_globre(br'{a,b}'))
     (?:a|b)
     >>> bprint(_globre(br'.\*\?'))
     \.\*\?
     '''
     i, n = 0, len(pat)
     res = ''
     group = 0
     escape = util.stringutil.regexbytesescapemap.get
     def peek():
         return i < n and pat[i:i + 1]
     while i < n:
         c = pat[i:i + 1]
         i += 1
         if c not in '*?[{},\\':
             res += escape(c, c)
         elif c == '*':
             if peek() == '*':
                 i += 1
                 if peek() == '/':
                     i += 1
                     res += '(?:.*/)?'
                 else:
                     res += '.*'
             else:
                 res += '[^/]*'
         elif c == '?':
             res += '.'
         elif c == '[':
             j = i
             if j < n and pat[j:j + 1] in '!]':
                 j += 1
             while j < n and pat[j:j + 1] != ']':
                 j += 1
             if j >= n:
                 res += '\\['
             else:
                 stuff = pat[i:j].replace('\\','\\\\')
                 i = j + 1
                 if stuff[0:1] == '!':
                     stuff = '^' + stuff[1:]
                 elif stuff[0:1] == '^':
                     stuff = '\\' + stuff
                 res = '%s[%s]' % (res, stuff)
         elif c == '{':
             group += 1
             res += '(?:'
         elif c == '}' and group:
             res += ')'
             group -= 1
         elif c == ',' and group:
             res += '|'
         elif c == '\\':
             p = peek()
             if p:
                 i += 1
                 res += escape(p, p)
             else:
                 res += escape(c, c)
         else:
             res += escape(c, c)
     return res
 
 def _regex(kind, pat, globsuffix):
     '''Convert a (normalized) pattern of any kind into a regular expression.
     globsuffix is appended to the regexp of globs.'''
     if not pat:
         return ''
     if kind == 're':
         return pat
     if kind in ('path', 'relpath'):
         if pat == '.':
             return ''
         return util.stringutil.reescape(pat) + '(?:/|$)'
     if kind == 'rootfilesin':
         if pat == '.':
             escaped = ''
         else:
             # Pattern is a directory name.
             escaped = util.stringutil.reescape(pat) + '/'
         # Anything after the pattern must be a non-directory.
         return escaped + '[^/]+$'
     if kind == 'relglob':
         return '(?:|.*/)' + _globre(pat) + globsuffix
     if kind == 'relre':
         if pat.startswith('^'):
             return pat
         return '.*' + pat
     if kind in ('glob', 'rootglob'):
         return _globre(pat) + globsuffix
     raise error.ProgrammingError('not a regex pattern: %s:%s' % (kind, pat))
 
 def _buildmatch(kindpats, globsuffix, root):
     '''Return regexp string and a matcher function for kindpats.
     globsuffix is appended to the regexp of globs.'''
     matchfuncs = []
 
     subincludes, kindpats = _expandsubinclude(kindpats, root)
     if subincludes:
         submatchers = {}
         def matchsubinclude(f):
             for prefix, matcherargs in subincludes:
                 if f.startswith(prefix):
                     mf = submatchers.get(prefix)
                     if mf is None:
                         mf = match(*matcherargs)
                         submatchers[prefix] = mf
 
                     if mf(f[len(prefix):]):
                         return True
             return False
         matchfuncs.append(matchsubinclude)
 
     regex = ''
     if kindpats:
         if all(k == 'rootfilesin' for k, p, s in kindpats):
             dirs = {p for k, p, s in kindpats}
             def mf(f):
                 i = f.rfind('/')
                 if i >= 0:
                     dir = f[:i]
                 else:
                     dir = '.'
                 return dir in dirs
             regex = b'rootfilesin: %s' % stringutil.pprint(list(sorted(dirs)))
             matchfuncs.append(mf)
         else:
             regex, mf = _buildregexmatch(kindpats, globsuffix)
             matchfuncs.append(mf)
 
     if len(matchfuncs) == 1:
         return regex, matchfuncs[0]
     else:
         return regex, lambda f: any(mf(f) for mf in matchfuncs)
 
 MAX_RE_SIZE = 20000
 
 def _joinregexes(regexps):
     """gather multiple regular expressions into a single one"""
     return '|'.join(regexps)
 
 def _buildregexmatch(kindpats, globsuffix):
     """Build a match function from a list of kinds and kindpats,
     return regexp string and a matcher function.
 
     Test too large input
     >>> _buildregexmatch([
     ...     (b'relglob', b'?' * MAX_RE_SIZE, b'')
     ... ], b'$')
     Traceback (most recent call last):
     ...
     Abort: matcher pattern is too long (20009 bytes)
     """
     try:
         allgroups = []
         regexps = [_regex(k, p, globsuffix) for (k, p, s) in kindpats]
         fullregexp = _joinregexes(regexps)
 
         startidx = 0
         groupsize = 0
         for idx, r in enumerate(regexps):
             piecesize = len(r)
             if piecesize > MAX_RE_SIZE:
                 msg = _("matcher pattern is too long (%d bytes)") % piecesize
                 raise error.Abort(msg)
             elif (groupsize + piecesize) > MAX_RE_SIZE:
                 group = regexps[startidx:idx]
                 allgroups.append(_joinregexes(group))
                 startidx = idx
                 groupsize = 0
             groupsize += piecesize + 1
 
         if startidx == 0:
             func = _rematcher(fullregexp)
         else:
             group = regexps[startidx:]
             allgroups.append(_joinregexes(group))
             allmatchers = [_rematcher(g) for g in allgroups]
             func = lambda s: any(m(s) for m in allmatchers)
         return fullregexp, func
     except re.error:
         for k, p, s in kindpats:
             try:
                 _rematcher(_regex(k, p, globsuffix))
             except re.error:
                 if s:
                     raise error.Abort(_("%s: invalid pattern (%s): %s") %
                                       (s, k, p))
                 else:
                     raise error.Abort(_("invalid pattern (%s): %s") % (k, p))
         raise error.Abort(_("invalid pattern"))
 
 def _patternrootsanddirs(kindpats):
     '''Returns roots and directories corresponding to each pattern.
 
     This calculates the roots and directories exactly matching the patterns and
     returns a tuple of (roots, dirs) for each. It does not return other
     directories which may also need to be considered, like the parent
     directories.
     '''
     r = []
     d = []
     for kind, pat, source in kindpats:
         if kind in ('glob', 'rootglob'): # find the non-glob prefix
             root = []
             for p in pat.split('/'):
                 if '[' in p or '{' in p or '*' in p or '?' in p:
                     break
                 root.append(p)
             r.append('/'.join(root) or '.')
         elif kind in ('relpath', 'path'):
             r.append(pat or '.')
         elif kind in ('rootfilesin',):
             d.append(pat or '.')
         else: # relglob, re, relre
             r.append('.')
     return r, d
 
 def _roots(kindpats):
     '''Returns root directories to match recursively from the given patterns.'''
     roots, dirs = _patternrootsanddirs(kindpats)
     return roots
 
 def _rootsdirsandparents(kindpats):
     '''Returns roots and exact directories from patterns.
 
     `roots` are directories to match recursively, `dirs` should
     be matched non-recursively, and `parents` are the implicitly required
     directories to walk to items in either roots or dirs.
 
     Returns a tuple of (roots, dirs, parents).
 
     >>> _rootsdirsandparents(
     ...     [(b'glob', b'g/h/*', b''), (b'glob', b'g/h', b''),
     ...      (b'glob', b'g*', b'')])
     (['g/h', 'g/h', '.'], [], ['g', '.'])
     >>> _rootsdirsandparents(
     ...     [(b'rootfilesin', b'g/h', b''), (b'rootfilesin', b'', b'')])
     ([], ['g/h', '.'], ['g', '.'])
     >>> _rootsdirsandparents(
     ...     [(b'relpath', b'r', b''), (b'path', b'p/p', b''),
     ...      (b'path', b'', b'')])
     (['r', 'p/p', '.'], [], ['p', '.'])
     >>> _rootsdirsandparents(
     ...     [(b'relglob', b'rg*', b''), (b're', b're/', b''),
     ...      (b'relre', b'rr', b'')])
     (['.', '.', '.'], [], ['.'])
     '''
     r, d = _patternrootsanddirs(kindpats)
 
     p = []
     # Append the parents as non-recursive/exact directories, since they must be
     # scanned to get to either the roots or the other exact directories.
     p.extend(util.dirs(d))
     p.extend(util.dirs(r))
     # util.dirs() does not include the root directory, so add it manually
     p.append('.')
 
     # FIXME: all uses of this function convert these to sets, do so before
     # returning.
     # FIXME: all uses of this function do not need anything in 'roots' and
     # 'dirs' to also be in 'parents', consider removing them before returning.
     return r, d, p
 
 def _explicitfiles(kindpats):
     '''Returns the potential explicit filenames from the patterns.
 
     >>> _explicitfiles([(b'path', b'foo/bar', b'')])
     ['foo/bar']
     >>> _explicitfiles([(b'rootfilesin', b'foo/bar', b'')])
     []
     '''
     # Keep only the pattern kinds where one can specify filenames (vs only
     # directory names).
     filable = [kp for kp in kindpats if kp[0] not in ('rootfilesin',)]
     return _roots(filable)
 
 def _prefix(kindpats):
     '''Whether all the patterns match a prefix (i.e. recursively)'''
     for kind, pat, source in kindpats:
         if kind not in ('path', 'relpath'):
             return False
     return True
 
 _commentre = None
 
 def readpatternfile(filepath, warn, sourceinfo=False):
     '''parse a pattern file, returning a list of
     patterns. These patterns should be given to compile()
     to be validated and converted into a match function.
 
     trailing white space is dropped.
     the escape character is backslash.
     comments start with #.
     empty lines are skipped.
 
     lines can be of the following formats:
 
     syntax: regexp # defaults following lines to non-rooted regexps
     syntax: glob   # defaults following lines to non-rooted globs
     re:pattern     # non-rooted regular expression
     glob:pattern   # non-rooted glob
     rootglob:pat   # rooted glob (same root as ^ in regexps)
     pattern        # pattern of the current default type
 
     if sourceinfo is set, returns a list of tuples:
     (pattern, lineno, originalline). This is useful to debug ignore patterns.
     '''
 
     syntaxes = {
         're': 'relre:',
         'regexp': 'relre:',
         'glob': 'relglob:',
         'rootglob': 'rootglob:',
         'include': 'include',
         'subinclude': 'subinclude',
     }
     syntax = 'relre:'
     patterns = []
 
     fp = open(filepath, 'rb')
     for lineno, line in enumerate(util.iterfile(fp), start=1):
         if "#" in line:
             global _commentre
             if not _commentre:
                 _commentre = util.re.compile(br'((?:^|[^\\])(?:\\\\)*)#.*')
             # remove comments prefixed by an even number of escapes
             m = _commentre.search(line)
             if m:
                 line = line[:m.end(1)]
             # fixup properly escaped comments that survived the above
             line = line.replace("\\#", "#")
         line = line.rstrip()
         if not line:
             continue
 
         if line.startswith('syntax:'):
             s = line[7:].strip()
             try:
                 syntax = syntaxes[s]
             except KeyError:
                 if warn:
                     warn(_("%s: ignoring invalid syntax '%s'\n") %
                          (filepath, s))
             continue
 
         linesyntax = syntax
         for s, rels in syntaxes.iteritems():
             if line.startswith(rels):
                 linesyntax = rels
                 line = line[len(rels):]
                 break
             elif line.startswith(s+':'):
                 linesyntax = rels
                 line = line[len(s) + 1:]
                 break
         if sourceinfo:
             patterns.append((linesyntax + line, lineno, line))
         else:
             patterns.append(linesyntax + line)
     fp.close()
     return patterns

mercurial/sparse.py

@@ -1,700 +1,700 b''
 # sparse.py - functionality for sparse checkouts
 #
 # Copyright 2014 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 import os
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
 )
 from . import (
     error,
     match as matchmod,
     merge as mergemod,
     pathutil,
     pycompat,
     scmutil,
     util,
 )
 
 # Whether sparse features are enabled. This variable is intended to be
 # temporary to facilitate porting sparse to core. It should eventually be
 # a per-repo option, possibly a repo requirement.
 enabled = False
 
 def parseconfig(ui, raw, action):
     """Parse sparse config file content.
 
     action is the command which is trigerring this read, can be narrow, sparse
 
     Returns a tuple of includes, excludes, and profiles.
     """
     includes = set()
     excludes = set()
     profiles = set()
     current = None
     havesection = False
 
     for line in raw.split('\n'):
         line = line.strip()
         if not line or line.startswith('#'):
             # empty or comment line, skip
             continue
         elif line.startswith('%include '):
             line = line[9:].strip()
             if line:
                 profiles.add(line)
         elif line == '[include]':
             if havesection and current != includes:
                 # TODO pass filename into this API so we can report it.
                 raise error.Abort(_('%(action)s config cannot have includes '
                                     'after excludes') % {'action': action})
             havesection = True
             current = includes
             continue
         elif line == '[exclude]':
             havesection = True
             current = excludes
         elif line:
             if current is None:
                 raise error.Abort(_('%(action)s config entry outside of '
                                     'section: %(line)s')
                                   % {'action': action, 'line': line},
                                   hint=_('add an [include] or [exclude] line '
                                          'to declare the entry type'))
 
             if line.strip().startswith('/'):
                 ui.warn(_('warning: %(action)s profile cannot use'
                           ' paths starting with /, ignoring %(line)s\n')
                         % {'action': action, 'line': line})
                 continue
             current.add(line)
 
     return includes, excludes, profiles
 
 # Exists as separate function to facilitate monkeypatching.
 def readprofile(repo, profile, changeid):
     """Resolve the raw content of a sparse profile file."""
     # TODO add some kind of cache here because this incurs a manifest
     # resolve and can be slow.
     return repo.filectx(profile, changeid=changeid).data()
 
 def patternsforrev(repo, rev):
     """Obtain sparse checkout patterns for the given rev.
 
     Returns a tuple of iterables representing includes, excludes, and
     patterns.
     """
     # Feature isn't enabled. No-op.
     if not enabled:
         return set(), set(), set()
 
     raw = repo.vfs.tryread('sparse')
     if not raw:
         return set(), set(), set()
 
     if rev is None:
         raise error.Abort(_('cannot parse sparse patterns from working '
                             'directory'))
 
     includes, excludes, profiles = parseconfig(repo.ui, raw, 'sparse')
     ctx = repo[rev]
 
     if profiles:
         visited = set()
         while profiles:
             profile = profiles.pop()
             if profile in visited:
                 continue
 
             visited.add(profile)
 
             try:
                 raw = readprofile(repo, profile, rev)
             except error.ManifestLookupError:
                 msg = (
                     "warning: sparse profile '%s' not found "
                     "in rev %s - ignoring it\n" % (profile, ctx))
                 # experimental config: sparse.missingwarning
                 if repo.ui.configbool(
                         'sparse', 'missingwarning'):
                     repo.ui.warn(msg)
                 else:
                     repo.ui.debug(msg)
                 continue
 
             pincludes, pexcludes, subprofs = parseconfig(repo.ui, raw, 'sparse')
             includes.update(pincludes)
             excludes.update(pexcludes)
             profiles.update(subprofs)
 
         profiles = visited
 
     if includes:
         includes.add('.hg*')
 
     return includes, excludes, profiles
 
 def activeconfig(repo):
     """Determine the active sparse config rules.
 
     Rules are constructed by reading the current sparse config and bringing in
     referenced profiles from parents of the working directory.
     """
     revs = [repo.changelog.rev(node) for node in
             repo.dirstate.parents() if node != nullid]
 
     allincludes = set()
     allexcludes = set()
     allprofiles = set()
 
     for rev in revs:
         includes, excludes, profiles = patternsforrev(repo, rev)
         allincludes |= includes
         allexcludes |= excludes
         allprofiles |= profiles
 
     return allincludes, allexcludes, allprofiles
 
 def configsignature(repo, includetemp=True):
     """Obtain the signature string for the current sparse configuration.
 
     This is used to construct a cache key for matchers.
     """
     cache = repo._sparsesignaturecache
 
     signature = cache.get('signature')
 
     if includetemp:
         tempsignature = cache.get('tempsignature')
     else:
         tempsignature = '0'
 
     if signature is None or (includetemp and tempsignature is None):
         signature = hex(hashlib.sha1(repo.vfs.tryread('sparse')).digest())
         cache['signature'] = signature
 
         if includetemp:
             raw = repo.vfs.tryread('tempsparse')
             tempsignature = hex(hashlib.sha1(raw).digest())
             cache['tempsignature'] = tempsignature
 
     return '%s %s' % (signature, tempsignature)
 
 def writeconfig(repo, includes, excludes, profiles):
     """Write the sparse config file given a sparse configuration."""
     with repo.vfs('sparse', 'wb') as fh:
         for p in sorted(profiles):
             fh.write('%%include %s\n' % p)
 
         if includes:
             fh.write('[include]\n')
             for i in sorted(includes):
                 fh.write(i)
                 fh.write('\n')
 
         if excludes:
             fh.write('[exclude]\n')
             for e in sorted(excludes):
                 fh.write(e)
                 fh.write('\n')
 
     repo._sparsesignaturecache.clear()
 
 def readtemporaryincludes(repo):
     raw = repo.vfs.tryread('tempsparse')
     if not raw:
         return set()
 
     return set(raw.split('\n'))
 
 def writetemporaryincludes(repo, includes):
     repo.vfs.write('tempsparse', '\n'.join(sorted(includes)))
     repo._sparsesignaturecache.clear()
 
 def addtemporaryincludes(repo, additional):
     includes = readtemporaryincludes(repo)
     for i in additional:
         includes.add(i)
     writetemporaryincludes(repo, includes)
 
 def prunetemporaryincludes(repo):
     if not enabled or not repo.vfs.exists('tempsparse'):
         return
 
     s = repo.status()
     if s.modified or s.added or s.removed or s.deleted:
         # Still have pending changes. Don't bother trying to prune.
         return
 
     sparsematch = matcher(repo, includetemp=False)
     dirstate = repo.dirstate
     actions = []
     dropped = []
     tempincludes = readtemporaryincludes(repo)
     for file in tempincludes:
         if file in dirstate and not sparsematch(file):
             message = _('dropping temporarily included sparse files')
             actions.append((file, None, message))
             dropped.append(file)
 
     typeactions = mergemod.emptyactions()
     typeactions['r'] = actions
     mergemod.applyupdates(repo, typeactions, repo[None], repo['.'], False)
 
     # Fix dirstate
     for file in dropped:
         dirstate.drop(file)
 
     repo.vfs.unlink('tempsparse')
     repo._sparsesignaturecache.clear()
     msg = _('cleaned up %d temporarily added file(s) from the '
             'sparse checkout\n')
     repo.ui.status(msg % len(tempincludes))
 
 def forceincludematcher(matcher, includes):
     """Returns a matcher that returns true for any of the forced includes
     before testing against the actual matcher."""
     kindpats = [('path', include, '') for include in includes]
-    includematcher = matchmod.includematcher('', '', kindpats)
+    includematcher = matchmod.includematcher('', kindpats)
     return matchmod.unionmatcher([includematcher, matcher])
 
 def matcher(repo, revs=None, includetemp=True):
     """Obtain a matcher for sparse working directories for the given revs.
 
     If multiple revisions are specified, the matcher is the union of all
     revs.
 
     ``includetemp`` indicates whether to use the temporary sparse profile.
     """
     # If sparse isn't enabled, sparse matcher matches everything.
     if not enabled:
         return matchmod.always(repo.root, '')
 
     if not revs or revs == [None]:
         revs = [repo.changelog.rev(node)
                 for node in repo.dirstate.parents() if node != nullid]
 
     signature = configsignature(repo, includetemp=includetemp)
 
     key = '%s %s' % (signature, ' '.join(map(pycompat.bytestr, revs)))
 
     result = repo._sparsematchercache.get(key)
     if result:
         return result
 
     matchers = []
     for rev in revs:
         try:
             includes, excludes, profiles = patternsforrev(repo, rev)
 
             if includes or excludes:
                 matcher = matchmod.match(repo.root, '', [],
                                          include=includes, exclude=excludes,
                                          default='relpath')
                 matchers.append(matcher)
         except IOError:
             pass
 
     if not matchers:
         result = matchmod.always(repo.root, '')
     elif len(matchers) == 1:
         result = matchers[0]
     else:
         result = matchmod.unionmatcher(matchers)
 
     if includetemp:
         tempincludes = readtemporaryincludes(repo)
         result = forceincludematcher(result, tempincludes)
 
     repo._sparsematchercache[key] = result
 
     return result
 
 def filterupdatesactions(repo, wctx, mctx, branchmerge, actions):
     """Filter updates to only lay out files that match the sparse rules."""
     if not enabled:
         return actions
 
     oldrevs = [pctx.rev() for pctx in wctx.parents()]
     oldsparsematch = matcher(repo, oldrevs)
 
     if oldsparsematch.always():
         return actions
 
     files = set()
     prunedactions = {}
 
     if branchmerge:
         # If we're merging, use the wctx filter, since we're merging into
         # the wctx.
         sparsematch = matcher(repo, [wctx.p1().rev()])
     else:
         # If we're updating, use the target context's filter, since we're
         # moving to the target context.
         sparsematch = matcher(repo, [mctx.rev()])
 
     temporaryfiles = []
     for file, action in actions.iteritems():
         type, args, msg = action
         files.add(file)
         if sparsematch(file):
             prunedactions[file] = action
         elif type == 'm':
             temporaryfiles.append(file)
             prunedactions[file] = action
         elif branchmerge:
             if type != 'k':
                 temporaryfiles.append(file)
                 prunedactions[file] = action
         elif type == 'f':
             prunedactions[file] = action
         elif file in wctx:
             prunedactions[file] = ('r', args, msg)
 
         if branchmerge and type == mergemod.ACTION_MERGE:
             f1, f2, fa, move, anc = args
             if not sparsematch(f1):
                 temporaryfiles.append(f1)
 
     if len(temporaryfiles) > 0:
         repo.ui.status(_('temporarily included %d file(s) in the sparse '
                          'checkout for merging\n') % len(temporaryfiles))
         addtemporaryincludes(repo, temporaryfiles)
 
         # Add the new files to the working copy so they can be merged, etc
         actions = []
         message = 'temporarily adding to sparse checkout'
         wctxmanifest = repo[None].manifest()
         for file in temporaryfiles:
             if file in wctxmanifest:
                 fctx = repo[None][file]
                 actions.append((file, (fctx.flags(), False), message))
 
         typeactions = mergemod.emptyactions()
         typeactions['g'] = actions
         mergemod.applyupdates(repo, typeactions, repo[None], repo['.'],
                               False)
 
         dirstate = repo.dirstate
         for file, flags, msg in actions:
             dirstate.normal(file)
 
     profiles = activeconfig(repo)[2]
     changedprofiles = profiles & files
     # If an active profile changed during the update, refresh the checkout.
     # Don't do this during a branch merge, since all incoming changes should
     # have been handled by the temporary includes above.
     if changedprofiles and not branchmerge:
         mf = mctx.manifest()
         for file in mf:
             old = oldsparsematch(file)
             new = sparsematch(file)
             if not old and new:
                 flags = mf.flags(file)
                 prunedactions[file] = ('g', (flags, False), '')
             elif old and not new:
                 prunedactions[file] = ('r', [], '')
 
     return prunedactions
 
 def refreshwdir(repo, origstatus, origsparsematch, force=False):
     """Refreshes working directory by taking sparse config into account.
 
     The old status and sparse matcher is compared against the current sparse
     matcher.
 
     Will abort if a file with pending changes is being excluded or included
     unless ``force`` is True.
     """
     # Verify there are no pending changes
     pending = set()
     pending.update(origstatus.modified)
     pending.update(origstatus.added)
     pending.update(origstatus.removed)
     sparsematch = matcher(repo)
     abort = False
 
     for f in pending:
         if not sparsematch(f):
             repo.ui.warn(_("pending changes to '%s'\n") % f)
             abort = not force
 
     if abort:
         raise error.Abort(_('could not update sparseness due to pending '
                             'changes'))
 
     # Calculate actions
     dirstate = repo.dirstate
     ctx = repo['.']
     added = []
     lookup = []
     dropped = []
     mf = ctx.manifest()
     files = set(mf)
 
     actions = {}
 
     for file in files:
         old = origsparsematch(file)
         new = sparsematch(file)
         # Add files that are newly included, or that don't exist in
         # the dirstate yet.
         if (new and not old) or (old and new and not file in dirstate):
             fl = mf.flags(file)
             if repo.wvfs.exists(file):
                 actions[file] = ('e', (fl,), '')
                 lookup.append(file)
             else:
                 actions[file] = ('g', (fl, False), '')
                 added.append(file)
         # Drop files that are newly excluded, or that still exist in
         # the dirstate.
         elif (old and not new) or (not old and not new and file in dirstate):
             dropped.append(file)
             if file not in pending:
                 actions[file] = ('r', [], '')
 
     # Verify there are no pending changes in newly included files
     abort = False
     for file in lookup:
         repo.ui.warn(_("pending changes to '%s'\n") % file)
         abort = not force
     if abort:
         raise error.Abort(_('cannot change sparseness due to pending '
                             'changes (delete the files or use '
                             '--force to bring them back dirty)'))
 
     # Check for files that were only in the dirstate.
     for file, state in dirstate.iteritems():
         if not file in files:
             old = origsparsematch(file)
             new = sparsematch(file)
             if old and not new:
                 dropped.append(file)
 
     # Apply changes to disk
     typeactions = mergemod.emptyactions()
     for f, (m, args, msg) in actions.iteritems():
         typeactions[m].append((f, args, msg))
 
     mergemod.applyupdates(repo, typeactions, repo[None], repo['.'], False)
 
     # Fix dirstate
     for file in added:
         dirstate.normal(file)
 
     for file in dropped:
         dirstate.drop(file)
 
     for file in lookup:
         # File exists on disk, and we're bringing it back in an unknown state.
         dirstate.normallookup(file)
 
     return added, dropped, lookup
 
 def aftercommit(repo, node):
     """Perform actions after a working directory commit."""
     # This function is called unconditionally, even if sparse isn't
     # enabled.
     ctx = repo[node]
 
     profiles = patternsforrev(repo, ctx.rev())[2]
 
     # profiles will only have data if sparse is enabled.
     if profiles & set(ctx.files()):
         origstatus = repo.status()
         origsparsematch = matcher(repo)
         refreshwdir(repo, origstatus, origsparsematch, force=True)
 
     prunetemporaryincludes(repo)
 
 def _updateconfigandrefreshwdir(repo, includes, excludes, profiles,
                                 force=False, removing=False):
     """Update the sparse config and working directory state."""
     raw = repo.vfs.tryread('sparse')
     oldincludes, oldexcludes, oldprofiles = parseconfig(repo.ui, raw, 'sparse')
 
     oldstatus = repo.status()
     oldmatch = matcher(repo)
     oldrequires = set(repo.requirements)
 
     # TODO remove this try..except once the matcher integrates better
     # with dirstate. We currently have to write the updated config
     # because that will invalidate the matcher cache and force a
     # re-read. We ideally want to update the cached matcher on the
     # repo instance then flush the new config to disk once wdir is
     # updated. But this requires massive rework to matcher() and its
     # consumers.
 
     if 'exp-sparse' in oldrequires and removing:
         repo.requirements.discard('exp-sparse')
         scmutil.writerequires(repo.vfs, repo.requirements)
     elif 'exp-sparse' not in oldrequires:
         repo.requirements.add('exp-sparse')
         scmutil.writerequires(repo.vfs, repo.requirements)
 
     try:
         writeconfig(repo, includes, excludes, profiles)
         return refreshwdir(repo, oldstatus, oldmatch, force=force)
     except Exception:
         if repo.requirements != oldrequires:
             repo.requirements.clear()
             repo.requirements |= oldrequires
             scmutil.writerequires(repo.vfs, repo.requirements)
         writeconfig(repo, oldincludes, oldexcludes, oldprofiles)
         raise
 
 def clearrules(repo, force=False):
     """Clears include/exclude rules from the sparse config.
 
     The remaining sparse config only has profiles, if defined. The working
     directory is refreshed, as needed.
     """
     with repo.wlock():
         raw = repo.vfs.tryread('sparse')
         includes, excludes, profiles = parseconfig(repo.ui, raw, 'sparse')
 
         if not includes and not excludes:
             return
 
         _updateconfigandrefreshwdir(repo, set(), set(), profiles, force=force)
 
 def importfromfiles(repo, opts, paths, force=False):
     """Import sparse config rules from files.
 
     The updated sparse config is written out and the working directory
     is refreshed, as needed.
     """
     with repo.wlock():
         # read current configuration
         raw = repo.vfs.tryread('sparse')
         includes, excludes, profiles = parseconfig(repo.ui, raw, 'sparse')
         aincludes, aexcludes, aprofiles = activeconfig(repo)
 
         # Import rules on top; only take in rules that are not yet
         # part of the active rules.
         changed = False
         for p in paths:
             with util.posixfile(util.expandpath(p), mode='rb') as fh:
                 raw = fh.read()
 
             iincludes, iexcludes, iprofiles = parseconfig(repo.ui, raw,
                                                           'sparse')
             oldsize = len(includes) + len(excludes) + len(profiles)
             includes.update(iincludes - aincludes)
             excludes.update(iexcludes - aexcludes)
             profiles.update(iprofiles - aprofiles)
             if len(includes) + len(excludes) + len(profiles) > oldsize:
                 changed = True
 
         profilecount = includecount = excludecount = 0
         fcounts = (0, 0, 0)
 
         if changed:
             profilecount = len(profiles - aprofiles)
             includecount = len(includes - aincludes)
             excludecount = len(excludes - aexcludes)
 
             fcounts = map(len, _updateconfigandrefreshwdir(
                 repo, includes, excludes, profiles, force=force))
 
         printchanges(repo.ui, opts, profilecount, includecount, excludecount,
                      *fcounts)
 
 def updateconfig(repo, pats, opts, include=False, exclude=False, reset=False,
                  delete=False, enableprofile=False, disableprofile=False,
                  force=False, usereporootpaths=False):
     """Perform a sparse config update.
 
     Only one of the actions may be performed.
 
     The new config is written out and a working directory refresh is performed.
     """
     with repo.wlock():
         raw = repo.vfs.tryread('sparse')
         oldinclude, oldexclude, oldprofiles = parseconfig(repo.ui, raw,
                                                           'sparse')
 
         if reset:
             newinclude = set()
             newexclude = set()
             newprofiles = set()
         else:
             newinclude = set(oldinclude)
             newexclude = set(oldexclude)
             newprofiles = set(oldprofiles)
 
         if any(os.path.isabs(pat) for pat in pats):
             raise error.Abort(_('paths cannot be absolute'))
 
         if not usereporootpaths:
             # let's treat paths as relative to cwd
             root, cwd = repo.root, repo.getcwd()
             abspats = []
             for kindpat in pats:
                 kind, pat = matchmod._patsplit(kindpat, None)
                 if kind in matchmod.cwdrelativepatternkinds or kind is None:
                     ap = (kind + ':' if kind else '') +\
                             pathutil.canonpath(root, cwd, pat)
                     abspats.append(ap)
                 else:
                     abspats.append(kindpat)
             pats = abspats
 
         if include:
             newinclude.update(pats)
         elif exclude:
             newexclude.update(pats)
         elif enableprofile:
             newprofiles.update(pats)
         elif disableprofile:
             newprofiles.difference_update(pats)
         elif delete:
             newinclude.difference_update(pats)
             newexclude.difference_update(pats)
 
         profilecount = (len(newprofiles - oldprofiles) -
                         len(oldprofiles - newprofiles))
         includecount = (len(newinclude - oldinclude) -
                         len(oldinclude - newinclude))
         excludecount = (len(newexclude - oldexclude) -
                         len(oldexclude - newexclude))
 
         fcounts = map(len, _updateconfigandrefreshwdir(
             repo, newinclude, newexclude, newprofiles, force=force,
             removing=reset))
 
         printchanges(repo.ui, opts, profilecount, includecount,
                      excludecount, *fcounts)
 
 def printchanges(ui, opts, profilecount=0, includecount=0, excludecount=0,
                  added=0, dropped=0, conflicting=0):
     """Print output summarizing sparse config changes."""
     with ui.formatter('sparse', opts) as fm:
         fm.startitem()
         fm.condwrite(ui.verbose, 'profiles_added', _('Profiles changed: %d\n'),
                      profilecount)
         fm.condwrite(ui.verbose, 'include_rules_added',
                      _('Include rules changed: %d\n'), includecount)
         fm.condwrite(ui.verbose, 'exclude_rules_added',
                      _('Exclude rules changed: %d\n'), excludecount)
 
         # In 'plain' verbose mode, mergemod.applyupdates already outputs what
         # files are added or removed outside of the templating formatter
         # framework. No point in repeating ourselves in that case.
         if not fm.isplain():
             fm.condwrite(ui.verbose, 'files_added', _('Files added: %d\n'),
                          added)
             fm.condwrite(ui.verbose, 'files_dropped', _('Files dropped: %d\n'),
                          dropped)
             fm.condwrite(ui.verbose, 'files_conflicting',
                          _('Files conflicting: %d\n'), conflicting)

mercurial/subrepo.py

@@ -1,1840 +1,1839 b''
 # subrepo.py - sub-repository classes and factory
 #
 # Copyright 2009-2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import copy
 import errno
 import hashlib
 import os
 import re
 import stat
 import subprocess
 import sys
 import tarfile
 import xml.dom.minidom
 
 from .i18n import _
 from . import (
     cmdutil,
     encoding,
     error,
     exchange,
     logcmdutil,
     match as matchmod,
     node,
     pathutil,
     phases,
     pycompat,
     scmutil,
     subrepoutil,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     dateutil,
     procutil,
     stringutil,
 )
 
 hg = None
 reporelpath = subrepoutil.reporelpath
 subrelpath = subrepoutil.subrelpath
 _abssource = subrepoutil._abssource
 propertycache = util.propertycache
 
 def _expandedabspath(path):
     '''
     get a path or url and if it is a path expand it and return an absolute path
     '''
     expandedpath = util.urllocalpath(util.expandpath(path))
     u = util.url(expandedpath)
     if not u.scheme:
         path = util.normpath(os.path.abspath(u.path))
     return path
 
 def _getstorehashcachename(remotepath):
     '''get a unique filename for the store hash cache of a remote repository'''
     return node.hex(hashlib.sha1(_expandedabspath(remotepath)).digest())[0:12]
 
 class SubrepoAbort(error.Abort):
     """Exception class used to avoid handling a subrepo error more than once"""
     def __init__(self, *args, **kw):
         self.subrepo = kw.pop(r'subrepo', None)
         self.cause = kw.pop(r'cause', None)
         error.Abort.__init__(self, *args, **kw)
 
 def annotatesubrepoerror(func):
     def decoratedmethod(self, *args, **kargs):
         try:
             res = func(self, *args, **kargs)
         except SubrepoAbort as ex:
             # This exception has already been handled
             raise ex
         except error.Abort as ex:
             subrepo = subrelpath(self)
             errormsg = (stringutil.forcebytestr(ex) + ' '
                         + _('(in subrepository "%s")') % subrepo)
             # avoid handling this exception by raising a SubrepoAbort exception
             raise SubrepoAbort(errormsg, hint=ex.hint, subrepo=subrepo,
                                cause=sys.exc_info())
         return res
     return decoratedmethod
 
 def _updateprompt(ui, sub, dirty, local, remote):
     if dirty:
         msg = (_(' subrepository sources for %s differ\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     else:
         msg = (_(' subrepository sources for %s differ (in checked out '
                  'version)\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?'
                  '$$ &Local $$ &Remote')
                % (subrelpath(sub), local, remote))
     return ui.promptchoice(msg, 0)
 
 def _sanitize(ui, vfs, ignore):
     for dirname, dirs, names in vfs.walk():
         for i, d in enumerate(dirs):
             if d.lower() == ignore:
                 del dirs[i]
                 break
         if vfs.basename(dirname).lower() != '.hg':
             continue
         for f in names:
             if f.lower() == 'hgrc':
                 ui.warn(_("warning: removing potentially hostile 'hgrc' "
                           "in '%s'\n") % vfs.join(dirname))
                 vfs.unlink(vfs.reljoin(dirname, f))
 
 def _auditsubrepopath(repo, path):
     # sanity check for potentially unsafe paths such as '~' and '$FOO'
     if path.startswith('~') or '$' in path or util.expandpath(path) != path:
         raise error.Abort(_('subrepo path contains illegal component: %s')
                           % path)
     # auditor doesn't check if the path itself is a symlink
     pathutil.pathauditor(repo.root)(path)
     if repo.wvfs.islink(path):
         raise error.Abort(_("subrepo '%s' traverses symbolic link") % path)
 
 SUBREPO_ALLOWED_DEFAULTS = {
     'hg': True,
     'git': False,
     'svn': False,
 }
 
 def _checktype(ui, kind):
     # subrepos.allowed is a master kill switch. If disabled, subrepos are
     # disabled period.
     if not ui.configbool('subrepos', 'allowed', True):
         raise error.Abort(_('subrepos not enabled'),
                           hint=_("see 'hg help config.subrepos' for details"))
 
     default = SUBREPO_ALLOWED_DEFAULTS.get(kind, False)
     if not ui.configbool('subrepos', '%s:allowed' % kind, default):
         raise error.Abort(_('%s subrepos not allowed') % kind,
                           hint=_("see 'hg help config.subrepos' for details"))
 
     if kind not in types:
         raise error.Abort(_('unknown subrepo type %s') % kind)
 
 def subrepo(ctx, path, allowwdir=False, allowcreate=True):
     """return instance of the right subrepo class for subrepo in path"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     from . import hg as h
     hg = h
 
     repo = ctx.repo()
     _auditsubrepopath(repo, path)
     state = ctx.substate[path]
     _checktype(repo.ui, state[2])
     if allowwdir:
         state = (state[0], ctx.subrev(path), state[2])
     return types[state[2]](ctx, path, state[:2], allowcreate)
 
 def nullsubrepo(ctx, path, pctx):
     """return an empty subrepo in pctx for the extant subrepo in ctx"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     from . import hg as h
     hg = h
 
     repo = ctx.repo()
     _auditsubrepopath(repo, path)
     state = ctx.substate[path]
     _checktype(repo.ui, state[2])
     subrev = ''
     if state[2] == 'hg':
         subrev = "0" * 40
     return types[state[2]](pctx, path, (state[0], subrev), True)
 
 # subrepo classes need to implement the following abstract class:
 
 class abstractsubrepo(object):
 
     def __init__(self, ctx, path):
         """Initialize abstractsubrepo part
 
         ``ctx`` is the context referring this subrepository in the
         parent repository.
 
         ``path`` is the path to this subrepository as seen from
         innermost repository.
         """
         self.ui = ctx.repo().ui
         self._ctx = ctx
         self._path = path
 
     def addwebdirpath(self, serverpath, webconf):
         """Add the hgwebdir entries for this subrepo, and any of its subrepos.
 
         ``serverpath`` is the path component of the URL for this repo.
 
         ``webconf`` is the dictionary of hgwebdir entries.
         """
         pass
 
     def storeclean(self, path):
         """
         returns true if the repository has not changed since it was last
         cloned from or pushed to a given repository.
         """
         return False
 
     def dirty(self, ignoreupdate=False, missing=False):
         """returns true if the dirstate of the subrepo is dirty or does not
         match current stored state. If ignoreupdate is true, only check
         whether the subrepo has uncommitted changes in its dirstate.  If missing
         is true, check for deleted files.
         """
         raise NotImplementedError
 
     def dirtyreason(self, ignoreupdate=False, missing=False):
         """return reason string if it is ``dirty()``
 
         Returned string should have enough information for the message
         of exception.
 
         This returns None, otherwise.
         """
         if self.dirty(ignoreupdate=ignoreupdate, missing=missing):
             return _('uncommitted changes in subrepository "%s"'
                      ) % subrelpath(self)
 
     def bailifchanged(self, ignoreupdate=False, hint=None):
         """raise Abort if subrepository is ``dirty()``
         """
         dirtyreason = self.dirtyreason(ignoreupdate=ignoreupdate,
                                        missing=True)
         if dirtyreason:
             raise error.Abort(dirtyreason, hint=hint)
 
     def basestate(self):
         """current working directory base state, disregarding .hgsubstate
         state and working directory modifications"""
         raise NotImplementedError
 
     def checknested(self, path):
         """check if path is a subrepository within this repository"""
         return False
 
     def commit(self, text, user, date):
         """commit the current changes to the subrepo with the given
         log message. Use given user and date if possible. Return the
         new state of the subrepo.
         """
         raise NotImplementedError
 
     def phase(self, state):
         """returns phase of specified state in the subrepository.
         """
         return phases.public
 
     def remove(self):
         """remove the subrepo
 
         (should verify the dirstate is not dirty first)
         """
         raise NotImplementedError
 
     def get(self, state, overwrite=False):
         """run whatever commands are needed to put the subrepo into
         this state
         """
         raise NotImplementedError
 
     def merge(self, state):
         """merge currently-saved state with the new state."""
         raise NotImplementedError
 
     def push(self, opts):
         """perform whatever action is analogous to 'hg push'
 
         This may be a no-op on some systems.
         """
         raise NotImplementedError
 
     def add(self, ui, match, prefix, uipathfn, explicitonly, **opts):
         return []
 
     def addremove(self, matcher, prefix, uipathfn, opts):
         self.ui.warn("%s: %s" % (prefix, _("addremove is not supported")))
         return 1
 
     def cat(self, match, fm, fntemplate, prefix, **opts):
         return 1
 
     def status(self, rev2, **opts):
         return scmutil.status([], [], [], [], [], [], [])
 
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         pass
 
     def outgoing(self, ui, dest, opts):
         return 1
 
     def incoming(self, ui, source, opts):
         return 1
 
     def files(self):
         """return filename iterator"""
         raise NotImplementedError
 
     def filedata(self, name, decode):
         """return file data, optionally passed through repo decoders"""
         raise NotImplementedError
 
     def fileflags(self, name):
         """return file flags"""
         return ''
 
     def matchfileset(self, expr, badfn=None):
         """Resolve the fileset expression for this repo"""
         return matchmod.never(self.wvfs.base, '', badfn=badfn)
 
     def printfiles(self, ui, m, fm, fmt, subrepos):
         """handle the files command for this subrepo"""
         return 1
 
     def archive(self, archiver, prefix, match=None, decode=True):
         if match is not None:
             files = [f for f in self.files() if match(f)]
         else:
             files = self.files()
         total = len(files)
         relpath = subrelpath(self)
         progress = self.ui.makeprogress(_('archiving (%s)') % relpath,
                                         unit=_('files'), total=total)
         progress.update(0)
         for name in files:
             flags = self.fileflags(name)
             mode = 'x' in flags and 0o755 or 0o644
             symlink = 'l' in flags
             archiver.addfile(prefix + name, mode, symlink,
                              self.filedata(name, decode))
             progress.increment()
         progress.complete()
         return total
 
     def walk(self, match):
         '''
         walk recursively through the directory tree, finding all files
         matched by the match function
         '''
 
     def forget(self, match, prefix, uipathfn, dryrun, interactive):
         return ([], [])
 
     def removefiles(self, matcher, prefix, uipathfn, after, force, subrepos,
                     dryrun, warnings):
         """remove the matched files from the subrepository and the filesystem,
         possibly by force and/or after the file has been removed from the
         filesystem.  Return 0 on success, 1 on any warning.
         """
         warnings.append(_("warning: removefiles not implemented (%s)")
                         % self._path)
         return 1
 
     def revert(self, substate, *pats, **opts):
         self.ui.warn(_('%s: reverting %s subrepos is unsupported\n') \
             % (substate[0], substate[2]))
         return []
 
     def shortid(self, revid):
         return revid
 
     def unshare(self):
         '''
         convert this repository from shared to normal storage.
         '''
 
     def verify(self):
         '''verify the integrity of the repository.  Return 0 on success or
         warning, 1 on any error.
         '''
         return 0
 
     @propertycache
     def wvfs(self):
         """return vfs to access the working directory of this subrepository
         """
         return vfsmod.vfs(self._ctx.repo().wvfs.join(self._path))
 
     @propertycache
     def _relpath(self):
         """return path to this subrepository as seen from outermost repository
         """
         return self.wvfs.reljoin(reporelpath(self._ctx.repo()), self._path)
 
 class hgsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state, allowcreate):
         super(hgsubrepo, self).__init__(ctx, path)
         self._state = state
         r = ctx.repo()
         root = r.wjoin(path)
         create = allowcreate and not r.wvfs.exists('%s/.hg' % path)
         # repository constructor does expand variables in path, which is
         # unsafe since subrepo path might come from untrusted source.
         if os.path.realpath(util.expandpath(root)) != root:
             raise error.Abort(_('subrepo path contains illegal component: %s')
                               % path)
         self._repo = hg.repository(r.baseui, root, create=create)
         if self._repo.root != root:
             raise error.ProgrammingError('failed to reject unsafe subrepo '
                                          'path: %s (expanded to %s)'
                                          % (root, self._repo.root))
 
         # Propagate the parent's --hidden option
         if r is r.unfiltered():
             self._repo = self._repo.unfiltered()
 
         self.ui = self._repo.ui
         for s, k in [('ui', 'commitsubrepos')]:
             v = r.ui.config(s, k)
             if v:
                 self.ui.setconfig(s, k, v, 'subrepo')
         # internal config: ui._usedassubrepo
         self.ui.setconfig('ui', '_usedassubrepo', 'True', 'subrepo')
         self._initrepo(r, state[0], create)
 
     @annotatesubrepoerror
     def addwebdirpath(self, serverpath, webconf):
         cmdutil.addwebdirpath(self._repo, subrelpath(self), webconf)
 
     def storeclean(self, path):
         with self._repo.lock():
             return self._storeclean(path)
 
     def _storeclean(self, path):
         clean = True
         itercache = self._calcstorehash(path)
         for filehash in self._readstorehashcache(path):
             if filehash != next(itercache, None):
                 clean = False
                 break
         if clean:
             # if not empty:
             # the cached and current pull states have a different size
             clean = next(itercache, None) is None
         return clean
 
     def _calcstorehash(self, remotepath):
         '''calculate a unique "store hash"
 
         This method is used to to detect when there are changes that may
         require a push to a given remote path.'''
         # sort the files that will be hashed in increasing (likely) file size
         filelist = ('bookmarks', 'store/phaseroots', 'store/00changelog.i')
         yield '# %s\n' % _expandedabspath(remotepath)
         vfs = self._repo.vfs
         for relname in filelist:
             filehash = node.hex(hashlib.sha1(vfs.tryread(relname)).digest())
             yield '%s = %s\n' % (relname, filehash)
 
     @propertycache
     def _cachestorehashvfs(self):
         return vfsmod.vfs(self._repo.vfs.join('cache/storehash'))
 
     def _readstorehashcache(self, remotepath):
         '''read the store hash cache for a given remote repository'''
         cachefile = _getstorehashcachename(remotepath)
         return self._cachestorehashvfs.tryreadlines(cachefile, 'r')
 
     def _cachestorehash(self, remotepath):
         '''cache the current store hash
 
         Each remote repo requires its own store hash cache, because a subrepo
         store may be "clean" versus a given remote repo, but not versus another
         '''
         cachefile = _getstorehashcachename(remotepath)
         with self._repo.lock():
             storehash = list(self._calcstorehash(remotepath))
             vfs = self._cachestorehashvfs
             vfs.writelines(cachefile, storehash, mode='wb', notindexed=True)
 
     def _getctx(self):
         '''fetch the context for this subrepo revision, possibly a workingctx
         '''
         if self._ctx.rev() is None:
             return self._repo[None]  # workingctx if parent is workingctx
         else:
             rev = self._state[1]
             return self._repo[rev]
 
     @annotatesubrepoerror
     def _initrepo(self, parentrepo, source, create):
         self._repo._subparent = parentrepo
         self._repo._subsource = source
 
         if create:
             lines = ['[paths]\n']
 
             def addpathconfig(key, value):
                 if value:
                     lines.append('%s = %s\n' % (key, value))
                     self.ui.setconfig('paths', key, value, 'subrepo')
 
             defpath = _abssource(self._repo, abort=False)
             defpushpath = _abssource(self._repo, True, abort=False)
             addpathconfig('default', defpath)
             if defpath != defpushpath:
                 addpathconfig('default-push', defpushpath)
 
             self._repo.vfs.write('hgrc', util.tonativeeol(''.join(lines)))
 
     @annotatesubrepoerror
     def add(self, ui, match, prefix, uipathfn, explicitonly, **opts):
         return cmdutil.add(ui, self._repo, match, prefix, uipathfn,
                            explicitonly, **opts)
 
     @annotatesubrepoerror
     def addremove(self, m, prefix, uipathfn, opts):
         # In the same way as sub directories are processed, once in a subrepo,
         # always entry any of its subrepos.  Don't corrupt the options that will
         # be used to process sibling subrepos however.
         opts = copy.copy(opts)
         opts['subrepos'] = True
         return scmutil.addremove(self._repo, m, prefix, uipathfn, opts)
 
     @annotatesubrepoerror
     def cat(self, match, fm, fntemplate, prefix, **opts):
         rev = self._state[1]
         ctx = self._repo[rev]
         return cmdutil.cat(self.ui, self._repo, ctx, match, fm, fntemplate,
                            prefix, **opts)
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         try:
             rev1 = self._state[1]
             ctx1 = self._repo[rev1]
             ctx2 = self._repo[rev2]
             return self._repo.status(ctx1, ctx2, **opts)
         except error.RepoLookupError as inst:
             self.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                          % (inst, subrelpath(self)))
             return scmutil.status([], [], [], [], [], [], [])
 
     @annotatesubrepoerror
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         try:
             node1 = node.bin(self._state[1])
             # We currently expect node2 to come from substate and be
             # in hex format
             if node2 is not None:
                 node2 = node.bin(node2)
             logcmdutil.diffordiffstat(ui, self._repo, diffopts, node1, node2,
                                       match, prefix=prefix, listsubrepos=True,
                                       **opts)
         except error.RepoLookupError as inst:
             self.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                           % (inst, subrelpath(self)))
 
     @annotatesubrepoerror
     def archive(self, archiver, prefix, match=None, decode=True):
         self._get(self._state + ('hg',))
         files = self.files()
         if match:
             files = [f for f in files if match(f)]
         rev = self._state[1]
         ctx = self._repo[rev]
         scmutil.prefetchfiles(self._repo, [ctx.rev()],
                               scmutil.matchfiles(self._repo, files))
         total = abstractsubrepo.archive(self, archiver, prefix, match)
         for subpath in ctx.substate:
             s = subrepo(ctx, subpath, True)
             submatch = matchmod.subdirmatcher(subpath, match)
             subprefix = prefix + subpath + '/'
             total += s.archive(archiver, subprefix, submatch,
                                decode)
         return total
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False, missing=False):
         r = self._state[1]
         if r == '' and not ignoreupdate: # no state recorded
             return True
         w = self._repo[None]
         if r != w.p1().hex() and not ignoreupdate:
             # different version checked out
             return True
         return w.dirty(missing=missing) # working directory changed
 
     def basestate(self):
         return self._repo['.'].hex()
 
     def checknested(self, path):
         return self._repo._checknested(self._repo.wjoin(path))
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # don't bother committing in the subrepo if it's only been
         # updated
         if not self.dirty(True):
             return self._repo['.'].hex()
         self.ui.debug("committing subrepo %s\n" % subrelpath(self))
         n = self._repo.commit(text, user, date)
         if not n:
             return self._repo['.'].hex() # different version checked out
         return node.hex(n)
 
     @annotatesubrepoerror
     def phase(self, state):
         return self._repo[state or '.'].phase()
 
     @annotatesubrepoerror
     def remove(self):
         # we can't fully delete the repository as it may contain
         # local-only history
         self.ui.note(_('removing subrepo %s\n') % subrelpath(self))
         hg.clean(self._repo, node.nullid, False)
 
     def _get(self, state):
         source, revision, kind = state
         parentrepo = self._repo._subparent
 
         if revision in self._repo.unfiltered():
             # Allow shared subrepos tracked at null to setup the sharedpath
             if len(self._repo) != 0 or not parentrepo.shared():
                 return True
         self._repo._subsource = source
         srcurl = _abssource(self._repo)
 
         # Defer creating the peer until after the status message is logged, in
         # case there are network problems.
         getpeer = lambda: hg.peer(self._repo, {}, srcurl)
 
         if len(self._repo) == 0:
             # use self._repo.vfs instead of self.wvfs to remove .hg only
             self._repo.vfs.rmtree()
 
             # A remote subrepo could be shared if there is a local copy
             # relative to the parent's share source.  But clone pooling doesn't
             # assemble the repos in a tree, so that can't be consistently done.
             # A simpler option is for the user to configure clone pooling, and
             # work with that.
             if parentrepo.shared() and hg.islocal(srcurl):
                 self.ui.status(_('sharing subrepo %s from %s\n')
                                % (subrelpath(self), srcurl))
                 shared = hg.share(self._repo._subparent.baseui,
                                   getpeer(), self._repo.root,
                                   update=False, bookmarks=False)
                 self._repo = shared.local()
             else:
                 # TODO: find a common place for this and this code in the
                 # share.py wrap of the clone command.
                 if parentrepo.shared():
                     pool = self.ui.config('share', 'pool')
                     if pool:
                         pool = util.expandpath(pool)
 
                     shareopts = {
                         'pool': pool,
                         'mode': self.ui.config('share', 'poolnaming'),
                     }
                 else:
                     shareopts = {}
 
                 self.ui.status(_('cloning subrepo %s from %s\n')
                                % (subrelpath(self), util.hidepassword(srcurl)))
                 other, cloned = hg.clone(self._repo._subparent.baseui, {},
                                          getpeer(), self._repo.root,
                                          update=False, shareopts=shareopts)
                 self._repo = cloned.local()
             self._initrepo(parentrepo, source, create=True)
             self._cachestorehash(srcurl)
         else:
             self.ui.status(_('pulling subrepo %s from %s\n')
                            % (subrelpath(self), util.hidepassword(srcurl)))
             cleansub = self.storeclean(srcurl)
             exchange.pull(self._repo, getpeer())
             if cleansub:
                 # keep the repo clean after pull
                 self._cachestorehash(srcurl)
         return False
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         inrepo = self._get(state)
         source, revision, kind = state
         repo = self._repo
         repo.ui.debug("getting subrepo %s\n" % self._path)
         if inrepo:
             urepo = repo.unfiltered()
             ctx = urepo[revision]
             if ctx.hidden():
                 urepo.ui.warn(
                     _('revision %s in subrepository "%s" is hidden\n') \
                     % (revision[0:12], self._path))
                 repo = urepo
         hg.updaterepo(repo, revision, overwrite)
 
     @annotatesubrepoerror
     def merge(self, state):
         self._get(state)
         cur = self._repo['.']
         dst = self._repo[state[1]]
         anc = dst.ancestor(cur)
 
         def mergefunc():
             if anc == cur and dst.branch() == cur.branch():
                 self.ui.debug('updating subrepository "%s"\n'
                               % subrelpath(self))
                 hg.update(self._repo, state[1])
             elif anc == dst:
                 self.ui.debug('skipping subrepository "%s"\n'
                               % subrelpath(self))
             else:
                 self.ui.debug('merging subrepository "%s"\n' % subrelpath(self))
                 hg.merge(self._repo, state[1], remind=False)
 
         wctx = self._repo[None]
         if self.dirty():
             if anc != dst:
                 if _updateprompt(self.ui, self, wctx.dirty(), cur, dst):
                     mergefunc()
             else:
                 mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
         newbranch = opts.get('new_branch')
         ssh = opts.get('ssh')
 
         # push subrepos depth-first for coherent ordering
         c = self._repo['.']
         subs = c.substate # only repos that are committed
         for s in sorted(subs):
             if c.sub(s).push(opts) == 0:
                 return False
 
         dsturl = _abssource(self._repo, True)
         if not force:
             if self.storeclean(dsturl):
                 self.ui.status(
                     _('no changes made to subrepo %s since last push to %s\n')
                     % (subrelpath(self), util.hidepassword(dsturl)))
                 return None
         self.ui.status(_('pushing subrepo %s to %s\n') %
             (subrelpath(self), util.hidepassword(dsturl)))
         other = hg.peer(self._repo, {'ssh': ssh}, dsturl)
         res = exchange.push(self._repo, other, force, newbranch=newbranch)
 
         # the repo is now clean
         self._cachestorehash(dsturl)
         return res.cgresult
 
     @annotatesubrepoerror
     def outgoing(self, ui, dest, opts):
         if 'rev' in opts or 'branch' in opts:
             opts = copy.copy(opts)
             opts.pop('rev', None)
             opts.pop('branch', None)
         return hg.outgoing(ui, self._repo, _abssource(self._repo, True), opts)
 
     @annotatesubrepoerror
     def incoming(self, ui, source, opts):
         if 'rev' in opts or 'branch' in opts:
             opts = copy.copy(opts)
             opts.pop('rev', None)
             opts.pop('branch', None)
         return hg.incoming(ui, self._repo, _abssource(self._repo, False), opts)
 
     @annotatesubrepoerror
     def files(self):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.manifest().keys()
 
     def filedata(self, name, decode):
         rev = self._state[1]
         data = self._repo[rev][name].data()
         if decode:
             data = self._repo.wwritedata(name, data)
         return data
 
     def fileflags(self, name):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.flags(name)
 
     @annotatesubrepoerror
     def printfiles(self, ui, m, fm, fmt, subrepos):
         # If the parent context is a workingctx, use the workingctx here for
         # consistency.
         if self._ctx.rev() is None:
             ctx = self._repo[None]
         else:
             rev = self._state[1]
             ctx = self._repo[rev]
         return cmdutil.files(ui, ctx, m, fm, fmt, subrepos)
 
     @annotatesubrepoerror
     def matchfileset(self, expr, badfn=None):
         repo = self._repo
         if self._ctx.rev() is None:
             ctx = repo[None]
         else:
             rev = self._state[1]
             ctx = repo[rev]
 
         matchers = [ctx.matchfileset(expr, badfn=badfn)]
 
         for subpath in ctx.substate:
             sub = ctx.sub(subpath)
 
             try:
                 sm = sub.matchfileset(expr, badfn=badfn)
-                pm = matchmod.prefixdirmatcher(repo.root, repo.getcwd(),
-                                               subpath, sm, badfn=badfn)
+                pm = matchmod.prefixdirmatcher(subpath, sm, badfn=badfn)
                 matchers.append(pm)
             except error.LookupError:
                 self.ui.status(_("skipping missing subrepository: %s\n")
                                % self.wvfs.reljoin(reporelpath(self), subpath))
         if len(matchers) == 1:
             return matchers[0]
         return matchmod.unionmatcher(matchers)
 
     def walk(self, match):
         ctx = self._repo[None]
         return ctx.walk(match)
 
     @annotatesubrepoerror
     def forget(self, match, prefix, uipathfn, dryrun, interactive):
         return cmdutil.forget(self.ui, self._repo, match, prefix, uipathfn,
                               True, dryrun=dryrun, interactive=interactive)
 
     @annotatesubrepoerror
     def removefiles(self, matcher, prefix, uipathfn, after, force, subrepos,
                     dryrun, warnings):
         return cmdutil.remove(self.ui, self._repo, matcher, prefix, uipathfn,
                               after, force, subrepos, dryrun)
 
     @annotatesubrepoerror
     def revert(self, substate, *pats, **opts):
         # reverting a subrepo is a 2 step process:
         # 1. if the no_backup is not set, revert all modified
         #    files inside the subrepo
         # 2. update the subrepo to the revision specified in
         #    the corresponding substate dictionary
         self.ui.status(_('reverting subrepo %s\n') % substate[0])
         if not opts.get(r'no_backup'):
             # Revert all files on the subrepo, creating backups
             # Note that this will not recursively revert subrepos
             # We could do it if there was a set:subrepos() predicate
             opts = opts.copy()
             opts[r'date'] = None
             opts[r'rev'] = substate[1]
 
             self.filerevert(*pats, **opts)
 
         # Update the repo to the revision specified in the given substate
         if not opts.get(r'dry_run'):
             self.get(substate, overwrite=True)
 
     def filerevert(self, *pats, **opts):
         ctx = self._repo[opts[r'rev']]
         parents = self._repo.dirstate.parents()
         if opts.get(r'all'):
             pats = ['set:modified()']
         else:
             pats = []
         cmdutil.revert(self.ui, self._repo, ctx, parents, *pats, **opts)
 
     def shortid(self, revid):
         return revid[:12]
 
     @annotatesubrepoerror
     def unshare(self):
         # subrepo inherently violates our import layering rules
         # because it wants to make repo objects from deep inside the stack
         # so we manually delay the circular imports to not break
         # scripts that don't use our demand-loading
         global hg
         from . import hg as h
         hg = h
 
         # Nothing prevents a user from sharing in a repo, and then making that a
         # subrepo.  Alternately, the previous unshare attempt may have failed
         # part way through.  So recurse whether or not this layer is shared.
         if self._repo.shared():
             self.ui.status(_("unsharing subrepo '%s'\n") % self._relpath)
 
         hg.unshare(self.ui, self._repo)
 
     def verify(self):
         try:
             rev = self._state[1]
             ctx = self._repo.unfiltered()[rev]
             if ctx.hidden():
                 # Since hidden revisions aren't pushed/pulled, it seems worth an
                 # explicit warning.
                 ui = self._repo.ui
                 ui.warn(_("subrepo '%s' is hidden in revision %s\n") %
                         (self._relpath, node.short(self._ctx.node())))
             return 0
         except error.RepoLookupError:
             # A missing subrepo revision may be a case of needing to pull it, so
             # don't treat this as an error.
             self._repo.ui.warn(_("subrepo '%s' not found in revision %s\n") %
                                (self._relpath, node.short(self._ctx.node())))
             return 0
 
     @propertycache
     def wvfs(self):
         """return own wvfs for efficiency and consistency
         """
         return self._repo.wvfs
 
     @propertycache
     def _relpath(self):
         """return path to this subrepository as seen from outermost repository
         """
         # Keep consistent dir separators by avoiding vfs.join(self._path)
         return reporelpath(self._repo)
 
 class svnsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state, allowcreate):
         super(svnsubrepo, self).__init__(ctx, path)
         self._state = state
         self._exe = procutil.findexe('svn')
         if not self._exe:
             raise error.Abort(_("'svn' executable not found for subrepo '%s'")
                              % self._path)
 
     def _svncommand(self, commands, filename='', failok=False):
         cmd = [self._exe]
         extrakw = {}
         if not self.ui.interactive():
             # Making stdin be a pipe should prevent svn from behaving
             # interactively even if we can't pass --non-interactive.
             extrakw[r'stdin'] = subprocess.PIPE
             # Starting in svn 1.5 --non-interactive is a global flag
             # instead of being per-command, but we need to support 1.4 so
             # we have to be intelligent about what commands take
             # --non-interactive.
             if commands[0] in ('update', 'checkout', 'commit'):
                 cmd.append('--non-interactive')
         cmd.extend(commands)
         if filename is not None:
             path = self.wvfs.reljoin(self._ctx.repo().origroot,
                                      self._path, filename)
             cmd.append(path)
         env = dict(encoding.environ)
         # Avoid localized output, preserve current locale for everything else.
         lc_all = env.get('LC_ALL')
         if lc_all:
             env['LANG'] = lc_all
             del env['LC_ALL']
         env['LC_MESSAGES'] = 'C'
         p = subprocess.Popen(pycompat.rapply(procutil.tonativestr, cmd),
                              bufsize=-1, close_fds=procutil.closefds,
                              stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                              env=procutil.tonativeenv(env), **extrakw)
         stdout, stderr = map(util.fromnativeeol, p.communicate())
         stderr = stderr.strip()
         if not failok:
             if p.returncode:
                 raise error.Abort(stderr or 'exited with code %d'
                                   % p.returncode)
             if stderr:
                 self.ui.warn(stderr + '\n')
         return stdout, stderr
 
     @propertycache
     def _svnversion(self):
         output, err = self._svncommand(['--version', '--quiet'], filename=None)
         m = re.search(br'^(\d+)\.(\d+)', output)
         if not m:
             raise error.Abort(_('cannot retrieve svn tool version'))
         return (int(m.group(1)), int(m.group(2)))
 
     def _svnmissing(self):
         return not self.wvfs.exists('.svn')
 
     def _wcrevs(self):
         # Get the working directory revision as well as the last
         # commit revision so we can compare the subrepo state with
         # both. We used to store the working directory one.
         output, err = self._svncommand(['info', '--xml'])
         doc = xml.dom.minidom.parseString(output)
         entries = doc.getElementsByTagName(r'entry')
         lastrev, rev = '0', '0'
         if entries:
             rev = pycompat.bytestr(entries[0].getAttribute(r'revision')) or '0'
             commits = entries[0].getElementsByTagName(r'commit')
             if commits:
                 lastrev = pycompat.bytestr(
                     commits[0].getAttribute(r'revision')) or '0'
         return (lastrev, rev)
 
     def _wcrev(self):
         return self._wcrevs()[0]
 
     def _wcchanged(self):
         """Return (changes, extchanges, missing) where changes is True
         if the working directory was changed, extchanges is
         True if any of these changes concern an external entry and missing
         is True if any change is a missing entry.
         """
         output, err = self._svncommand(['status', '--xml'])
         externals, changes, missing = [], [], []
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName(r'entry'):
             s = e.getElementsByTagName(r'wc-status')
             if not s:
                 continue
             item = s[0].getAttribute(r'item')
             props = s[0].getAttribute(r'props')
             path = e.getAttribute(r'path').encode('utf8')
             if item == r'external':
                 externals.append(path)
             elif item == r'missing':
                 missing.append(path)
             if (item not in (r'', r'normal', r'unversioned', r'external')
                 or props not in (r'', r'none', r'normal')):
                 changes.append(path)
         for path in changes:
             for ext in externals:
                 if path == ext or path.startswith(ext + pycompat.ossep):
                     return True, True, bool(missing)
         return bool(changes), False, bool(missing)
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False, missing=False):
         if self._svnmissing():
             return self._state[1] != ''
         wcchanged = self._wcchanged()
         changed = wcchanged[0] or (missing and wcchanged[2])
         if not changed:
             if self._state[1] in self._wcrevs() or ignoreupdate:
                 return False
         return True
 
     def basestate(self):
         lastrev, rev = self._wcrevs()
         if lastrev != rev:
             # Last committed rev is not the same than rev. We would
             # like to take lastrev but we do not know if the subrepo
             # URL exists at lastrev.  Test it and fallback to rev it
             # is not there.
             try:
                 self._svncommand(['list', '%s@%s' % (self._state[0], lastrev)])
                 return lastrev
             except error.Abort:
                 pass
         return rev
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         # user and date are out of our hands since svn is centralized
         changed, extchanged, missing = self._wcchanged()
         if not changed:
             return self.basestate()
         if extchanged:
             # Do not try to commit externals
             raise error.Abort(_('cannot commit svn externals'))
         if missing:
             # svn can commit with missing entries but aborting like hg
             # seems a better approach.
             raise error.Abort(_('cannot commit missing svn entries'))
         commitinfo, err = self._svncommand(['commit', '-m', text])
         self.ui.status(commitinfo)
         newrev = re.search('Committed revision ([0-9]+).', commitinfo)
         if not newrev:
             if not commitinfo.strip():
                 # Sometimes, our definition of "changed" differs from
                 # svn one. For instance, svn ignores missing files
                 # when committing. If there are only missing files, no
                 # commit is made, no output and no error code.
                 raise error.Abort(_('failed to commit svn changes'))
             raise error.Abort(commitinfo.splitlines()[-1])
         newrev = newrev.groups()[0]
         self.ui.status(self._svncommand(['update', '-r', newrev])[0])
         return newrev
 
     @annotatesubrepoerror
     def remove(self):
         if self.dirty():
             self.ui.warn(_('not removing repo %s because '
                            'it has changes.\n') % self._path)
             return
         self.ui.note(_('removing subrepo %s\n') % self._path)
 
         self.wvfs.rmtree(forcibly=True)
         try:
             pwvfs = self._ctx.repo().wvfs
             pwvfs.removedirs(pwvfs.dirname(self._path))
         except OSError:
             pass
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         if overwrite:
             self._svncommand(['revert', '--recursive'])
         args = ['checkout']
         if self._svnversion >= (1, 5):
             args.append('--force')
         # The revision must be specified at the end of the URL to properly
         # update to a directory which has since been deleted and recreated.
         args.append('%s@%s' % (state[0], state[1]))
 
         # SEC: check that the ssh url is safe
         util.checksafessh(state[0])
 
         status, err = self._svncommand(args, failok=True)
         _sanitize(self.ui, self.wvfs, '.svn')
         if not re.search('Checked out revision [0-9]+.', status):
             if ('is already a working copy for a different URL' in err
                 and (self._wcchanged()[:2] == (False, False))):
                 # obstructed but clean working copy, so just blow it away.
                 self.remove()
                 self.get(state, overwrite=False)
                 return
             raise error.Abort((status or err).splitlines()[-1])
         self.ui.status(status)
 
     @annotatesubrepoerror
     def merge(self, state):
         old = self._state[1]
         new = state[1]
         wcrev = self._wcrev()
         if new != wcrev:
             dirty = old == wcrev or self._wcchanged()[0]
             if _updateprompt(self.ui, self, dirty, wcrev, new):
                 self.get(state, False)
 
     def push(self, opts):
         # push is a no-op for SVN
         return True
 
     @annotatesubrepoerror
     def files(self):
         output = self._svncommand(['list', '--recursive', '--xml'])[0]
         doc = xml.dom.minidom.parseString(output)
         paths = []
         for e in doc.getElementsByTagName(r'entry'):
             kind = pycompat.bytestr(e.getAttribute(r'kind'))
             if kind != 'file':
                 continue
             name = r''.join(c.data for c
                             in e.getElementsByTagName(r'name')[0].childNodes
                             if c.nodeType == c.TEXT_NODE)
             paths.append(name.encode('utf8'))
         return paths
 
     def filedata(self, name, decode):
         return self._svncommand(['cat'], name)[0]
 
 
 class gitsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state, allowcreate):
         super(gitsubrepo, self).__init__(ctx, path)
         self._state = state
         self._abspath = ctx.repo().wjoin(path)
         self._subparent = ctx.repo()
         self._ensuregit()
 
     def _ensuregit(self):
         try:
             self._gitexecutable = 'git'
             out, err = self._gitnodir(['--version'])
         except OSError as e:
             genericerror = _("error executing git for subrepo '%s': %s")
             notfoundhint = _("check git is installed and in your PATH")
             if e.errno != errno.ENOENT:
                 raise error.Abort(genericerror % (
                     self._path, encoding.strtolocal(e.strerror)))
             elif pycompat.iswindows:
                 try:
                     self._gitexecutable = 'git.cmd'
                     out, err = self._gitnodir(['--version'])
                 except OSError as e2:
                     if e2.errno == errno.ENOENT:
                         raise error.Abort(_("couldn't find 'git' or 'git.cmd'"
                             " for subrepo '%s'") % self._path,
                             hint=notfoundhint)
                     else:
                         raise error.Abort(genericerror % (self._path,
                             encoding.strtolocal(e2.strerror)))
             else:
                 raise error.Abort(_("couldn't find git for subrepo '%s'")
                     % self._path, hint=notfoundhint)
         versionstatus = self._checkversion(out)
         if versionstatus == 'unknown':
             self.ui.warn(_('cannot retrieve git version\n'))
         elif versionstatus == 'abort':
             raise error.Abort(_('git subrepo requires at least 1.6.0 or later'))
         elif versionstatus == 'warning':
             self.ui.warn(_('git subrepo requires at least 1.6.0 or later\n'))
 
     @staticmethod
     def _gitversion(out):
         m = re.search(br'^git version (\d+)\.(\d+)\.(\d+)', out)
         if m:
             return (int(m.group(1)), int(m.group(2)), int(m.group(3)))
 
         m = re.search(br'^git version (\d+)\.(\d+)', out)
         if m:
             return (int(m.group(1)), int(m.group(2)), 0)
 
         return -1
 
     @staticmethod
     def _checkversion(out):
         '''ensure git version is new enough
 
         >>> _checkversion = gitsubrepo._checkversion
         >>> _checkversion(b'git version 1.6.0')
         'ok'
         >>> _checkversion(b'git version 1.8.5')
         'ok'
         >>> _checkversion(b'git version 1.4.0')
         'abort'
         >>> _checkversion(b'git version 1.5.0')
         'warning'
         >>> _checkversion(b'git version 1.9-rc0')
         'ok'
         >>> _checkversion(b'git version 1.9.0.265.g81cdec2')
         'ok'
         >>> _checkversion(b'git version 1.9.0.GIT')
         'ok'
         >>> _checkversion(b'git version 12345')
         'unknown'
         >>> _checkversion(b'no')
         'unknown'
         '''
         version = gitsubrepo._gitversion(out)
         # git 1.4.0 can't work at all, but 1.5.X can in at least some cases,
         # despite the docstring comment.  For now, error on 1.4.0, warn on
         # 1.5.0 but attempt to continue.
         if version == -1:
             return 'unknown'
         if version < (1, 5, 0):
             return 'abort'
         elif version < (1, 6, 0):
             return 'warning'
         return 'ok'
 
     def _gitcommand(self, commands, env=None, stream=False):
         return self._gitdir(commands, env=env, stream=stream)[0]
 
     def _gitdir(self, commands, env=None, stream=False):
         return self._gitnodir(commands, env=env, stream=stream,
                               cwd=self._abspath)
 
     def _gitnodir(self, commands, env=None, stream=False, cwd=None):
         """Calls the git command
 
         The methods tries to call the git command. versions prior to 1.6.0
         are not supported and very probably fail.
         """
         self.ui.debug('%s: git %s\n' % (self._relpath, ' '.join(commands)))
         if env is None:
             env = encoding.environ.copy()
         # disable localization for Git output (issue5176)
         env['LC_ALL'] = 'C'
         # fix for Git CVE-2015-7545
         if 'GIT_ALLOW_PROTOCOL' not in env:
             env['GIT_ALLOW_PROTOCOL'] = 'file:git:http:https:ssh'
         # unless ui.quiet is set, print git's stderr,
         # which is mostly progress and useful info
         errpipe = None
         if self.ui.quiet:
             errpipe = open(os.devnull, 'w')
         if self.ui._colormode and len(commands) and commands[0] == "diff":
             # insert the argument in the front,
             # the end of git diff arguments is used for paths
             commands.insert(1, '--color')
         p = subprocess.Popen(pycompat.rapply(procutil.tonativestr,
                                              [self._gitexecutable] + commands),
                              bufsize=-1,
                              cwd=pycompat.rapply(procutil.tonativestr, cwd),
                              env=procutil.tonativeenv(env),
                              close_fds=procutil.closefds,
                              stdout=subprocess.PIPE, stderr=errpipe)
         if stream:
             return p.stdout, None
 
         retdata = p.stdout.read().strip()
         # wait for the child to exit to avoid race condition.
         p.wait()
 
         if p.returncode != 0 and p.returncode != 1:
             # there are certain error codes that are ok
             command = commands[0]
             if command in ('cat-file', 'symbolic-ref'):
                 return retdata, p.returncode
             # for all others, abort
             raise error.Abort(_('git %s error %d in %s') %
                              (command, p.returncode, self._relpath))
 
         return retdata, p.returncode
 
     def _gitmissing(self):
         return not self.wvfs.exists('.git')
 
     def _gitstate(self):
         return self._gitcommand(['rev-parse', 'HEAD'])
 
     def _gitcurrentbranch(self):
         current, err = self._gitdir(['symbolic-ref', 'HEAD', '--quiet'])
         if err:
             current = None
         return current
 
     def _gitremote(self, remote):
         out = self._gitcommand(['remote', 'show', '-n', remote])
         line = out.split('\n')[1]
         i = line.index('URL: ') + len('URL: ')
         return line[i:]
 
     def _githavelocally(self, revision):
         out, code = self._gitdir(['cat-file', '-e', revision])
         return code == 0
 
     def _gitisancestor(self, r1, r2):
         base = self._gitcommand(['merge-base', r1, r2])
         return base == r1
 
     def _gitisbare(self):
         return self._gitcommand(['config', '--bool', 'core.bare']) == 'true'
 
     def _gitupdatestat(self):
         """This must be run before git diff-index.
         diff-index only looks at changes to file stat;
         this command looks at file contents and updates the stat."""
         self._gitcommand(['update-index', '-q', '--refresh'])
 
     def _gitbranchmap(self):
         '''returns 2 things:
         a map from git branch to revision
         a map from revision to branches'''
         branch2rev = {}
         rev2branch = {}
 
         out = self._gitcommand(['for-each-ref', '--format',
                                 '%(objectname) %(refname)'])
         for line in out.split('\n'):
             revision, ref = line.split(' ')
             if (not ref.startswith('refs/heads/') and
                 not ref.startswith('refs/remotes/')):
                 continue
             if ref.startswith('refs/remotes/') and ref.endswith('/HEAD'):
                 continue # ignore remote/HEAD redirects
             branch2rev[ref] = revision
             rev2branch.setdefault(revision, []).append(ref)
         return branch2rev, rev2branch
 
     def _gittracking(self, branches):
         'return map of remote branch to local tracking branch'
         # assumes no more than one local tracking branch for each remote
         tracking = {}
         for b in branches:
             if b.startswith('refs/remotes/'):
                 continue
             bname = b.split('/', 2)[2]
             remote = self._gitcommand(['config', 'branch.%s.remote' % bname])
             if remote:
                 ref = self._gitcommand(['config', 'branch.%s.merge' % bname])
                 tracking['refs/remotes/%s/%s' %
                          (remote, ref.split('/', 2)[2])] = b
         return tracking
 
     def _abssource(self, source):
         if '://' not in source:
             # recognize the scp syntax as an absolute source
             colon = source.find(':')
             if colon != -1 and '/' not in source[:colon]:
                 return source
         self._subsource = source
         return _abssource(self)
 
     def _fetch(self, source, revision):
         if self._gitmissing():
             # SEC: check for safe ssh url
             util.checksafessh(source)
 
             source = self._abssource(source)
             self.ui.status(_('cloning subrepo %s from %s\n') %
                             (self._relpath, source))
             self._gitnodir(['clone', source, self._abspath])
         if self._githavelocally(revision):
             return
         self.ui.status(_('pulling subrepo %s from %s\n') %
                         (self._relpath, self._gitremote('origin')))
         # try only origin: the originally cloned repo
         self._gitcommand(['fetch'])
         if not self._githavelocally(revision):
             raise error.Abort(_('revision %s does not exist in subrepository '
                                 '"%s"\n') % (revision, self._relpath))
 
     @annotatesubrepoerror
     def dirty(self, ignoreupdate=False, missing=False):
         if self._gitmissing():
             return self._state[1] != ''
         if self._gitisbare():
             return True
         if not ignoreupdate and self._state[1] != self._gitstate():
             # different version checked out
             return True
         # check for staged changes or modified files; ignore untracked files
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
         return code == 1
 
     def basestate(self):
         return self._gitstate()
 
     @annotatesubrepoerror
     def get(self, state, overwrite=False):
         source, revision, kind = state
         if not revision:
             self.remove()
             return
         self._fetch(source, revision)
         # if the repo was set to be bare, unbare it
         if self._gitisbare():
             self._gitcommand(['config', 'core.bare', 'false'])
             if self._gitstate() == revision:
                 self._gitcommand(['reset', '--hard', 'HEAD'])
                 return
         elif self._gitstate() == revision:
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # reset --hard will otherwise throw away files added for commit,
                 # not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 self._gitcommand(['reset', '--hard', 'HEAD'])
             return
         branch2rev, rev2branch = self._gitbranchmap()
 
         def checkout(args):
             cmd = ['checkout']
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # the -f option will otherwise throw away files added for
                 # commit, not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 cmd.append('-f')
             self._gitcommand(cmd + args)
             _sanitize(self.ui, self.wvfs, '.git')
 
         def rawcheckout():
             # no branch to checkout, check it out with no branch
             self.ui.warn(_('checking out detached HEAD in '
                            'subrepository "%s"\n') % self._relpath)
             self.ui.warn(_('check out a git branch if you intend '
                             'to make changes\n'))
             checkout(['-q', revision])
 
         if revision not in rev2branch:
             rawcheckout()
             return
         branches = rev2branch[revision]
         firstlocalbranch = None
         for b in branches:
             if b == 'refs/heads/master':
                 # master trumps all other branches
                 checkout(['refs/heads/master'])
                 return
             if not firstlocalbranch and not b.startswith('refs/remotes/'):
                 firstlocalbranch = b
         if firstlocalbranch:
             checkout([firstlocalbranch])
             return
 
         tracking = self._gittracking(branch2rev.keys())
         # choose a remote branch already tracked if possible
         remote = branches[0]
         if remote not in tracking:
             for b in branches:
                 if b in tracking:
                     remote = b
                     break
 
         if remote not in tracking:
             # create a new local tracking branch
             local = remote.split('/', 3)[3]
             checkout(['-b', local, remote])
         elif self._gitisancestor(branch2rev[tracking[remote]], remote):
             # When updating to a tracked remote branch,
             # if the local tracking branch is downstream of it,
             # a normal `git pull` would have performed a "fast-forward merge"
             # which is equivalent to updating the local branch to the remote.
             # Since we are only looking at branching at update, we need to
             # detect this situation and perform this action lazily.
             if tracking[remote] != self._gitcurrentbranch():
                 checkout([tracking[remote]])
             self._gitcommand(['merge', '--ff', remote])
             _sanitize(self.ui, self.wvfs, '.git')
         else:
             # a real merge would be required, just checkout the revision
             rawcheckout()
 
     @annotatesubrepoerror
     def commit(self, text, user, date):
         if self._gitmissing():
             raise error.Abort(_("subrepo %s is missing") % self._relpath)
         cmd = ['commit', '-a', '-m', text]
         env = encoding.environ.copy()
         if user:
             cmd += ['--author', user]
         if date:
             # git's date parser silently ignores when seconds < 1e9
             # convert to ISO8601
             env['GIT_AUTHOR_DATE'] = dateutil.datestr(date,
                                                   '%Y-%m-%dT%H:%M:%S %1%2')
         self._gitcommand(cmd, env=env)
         # make sure commit works otherwise HEAD might not exist under certain
         # circumstances
         return self._gitstate()
 
     @annotatesubrepoerror
     def merge(self, state):
         source, revision, kind = state
         self._fetch(source, revision)
         base = self._gitcommand(['merge-base', revision, self._state[1]])
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
 
         def mergefunc():
             if base == revision:
                 self.get(state) # fast forward merge
             elif base != self._state[1]:
                 self._gitcommand(['merge', '--no-commit', revision])
             _sanitize(self.ui, self.wvfs, '.git')
 
         if self.dirty():
             if self._gitstate() != revision:
                 dirty = self._gitstate() == self._state[1] or code != 0
                 if _updateprompt(self.ui, self, dirty,
                                  self._state[1][:7], revision[:7]):
                     mergefunc()
         else:
             mergefunc()
 
     @annotatesubrepoerror
     def push(self, opts):
         force = opts.get('force')
 
         if not self._state[1]:
             return True
         if self._gitmissing():
             raise error.Abort(_("subrepo %s is missing") % self._relpath)
         # if a branch in origin contains the revision, nothing to do
         branch2rev, rev2branch = self._gitbranchmap()
         if self._state[1] in rev2branch:
             for b in rev2branch[self._state[1]]:
                 if b.startswith('refs/remotes/origin/'):
                     return True
         for b, revision in branch2rev.iteritems():
             if b.startswith('refs/remotes/origin/'):
                 if self._gitisancestor(self._state[1], revision):
                     return True
         # otherwise, try to push the currently checked out branch
         cmd = ['push']
         if force:
             cmd.append('--force')
 
         current = self._gitcurrentbranch()
         if current:
             # determine if the current branch is even useful
             if not self._gitisancestor(self._state[1], current):
                 self.ui.warn(_('unrelated git branch checked out '
                                'in subrepository "%s"\n') % self._relpath)
                 return False
             self.ui.status(_('pushing branch %s of subrepository "%s"\n') %
                            (current.split('/', 2)[2], self._relpath))
             ret = self._gitdir(cmd + ['origin', current])
             return ret[1] == 0
         else:
             self.ui.warn(_('no branch checked out in subrepository "%s"\n'
                            'cannot push revision %s\n') %
                           (self._relpath, self._state[1]))
             return False
 
     @annotatesubrepoerror
     def add(self, ui, match, prefix, uipathfn, explicitonly, **opts):
         if self._gitmissing():
             return []
 
         s = self.status(None, unknown=True, clean=True)
 
         tracked = set()
         # dirstates 'amn' warn, 'r' is added again
         for l in (s.modified, s.added, s.deleted, s.clean):
             tracked.update(l)
 
         # Unknown files not of interest will be rejected by the matcher
         files = s.unknown
         files.extend(match.files())
 
         rejected = []
 
         files = [f for f in sorted(set(files)) if match(f)]
         for f in files:
             exact = match.exact(f)
             command = ["add"]
             if exact:
                 command.append("-f") #should be added, even if ignored
             if ui.verbose or not exact:
                 ui.status(_('adding %s\n') % uipathfn(f))
 
             if f in tracked:  # hg prints 'adding' even if already tracked
                 if exact:
                     rejected.append(f)
                 continue
             if not opts.get(r'dry_run'):
                 self._gitcommand(command + [f])
 
         for f in rejected:
             ui.warn(_("%s already tracked!\n") % uipathfn(f))
 
         return rejected
 
     @annotatesubrepoerror
     def remove(self):
         if self._gitmissing():
             return
         if self.dirty():
             self.ui.warn(_('not removing repo %s because '
                            'it has changes.\n') % self._relpath)
             return
         # we can't fully delete the repository as it may contain
         # local-only history
         self.ui.note(_('removing subrepo %s\n') % self._relpath)
         self._gitcommand(['config', 'core.bare', 'true'])
         for f, kind in self.wvfs.readdir():
             if f == '.git':
                 continue
             if kind == stat.S_IFDIR:
                 self.wvfs.rmtree(f)
             else:
                 self.wvfs.unlink(f)
 
     def archive(self, archiver, prefix, match=None, decode=True):
         total = 0
         source, revision = self._state
         if not revision:
             return total
         self._fetch(source, revision)
 
         # Parse git's native archive command.
         # This should be much faster than manually traversing the trees
         # and objects with many subprocess calls.
         tarstream = self._gitcommand(['archive', revision], stream=True)
         tar = tarfile.open(fileobj=tarstream, mode=r'r|')
         relpath = subrelpath(self)
         progress = self.ui.makeprogress(_('archiving (%s)') % relpath,
                                         unit=_('files'))
         progress.update(0)
         for info in tar:
             if info.isdir():
                 continue
             bname = pycompat.fsencode(info.name)
             if match and not match(bname):
                 continue
             if info.issym():
                 data = info.linkname
             else:
                 data = tar.extractfile(info).read()
             archiver.addfile(prefix + bname, info.mode, info.issym(), data)
             total += 1
             progress.increment()
         progress.complete()
         return total
 
 
     @annotatesubrepoerror
     def cat(self, match, fm, fntemplate, prefix, **opts):
         rev = self._state[1]
         if match.anypats():
             return 1 #No support for include/exclude yet
 
         if not match.files():
             return 1
 
         # TODO: add support for non-plain formatter (see cmdutil.cat())
         for f in match.files():
             output = self._gitcommand(["show", "%s:%s" % (rev, f)])
             fp = cmdutil.makefileobj(self._ctx, fntemplate,
                                      pathname=self.wvfs.reljoin(prefix, f))
             fp.write(output)
             fp.close()
         return 0
 
 
     @annotatesubrepoerror
     def status(self, rev2, **opts):
         rev1 = self._state[1]
         if self._gitmissing() or not rev1:
             # if the repo is missing, return no results
             return scmutil.status([], [], [], [], [], [], [])
         modified, added, removed = [], [], []
         self._gitupdatestat()
         if rev2:
             command = ['diff-tree', '--no-renames', '-r', rev1, rev2]
         else:
             command = ['diff-index', '--no-renames', rev1]
         out = self._gitcommand(command)
         for line in out.split('\n'):
             tab = line.find('\t')
             if tab == -1:
                 continue
             status, f = line[tab - 1:tab], line[tab + 1:]
             if status == 'M':
                 modified.append(f)
             elif status == 'A':
                 added.append(f)
             elif status == 'D':
                 removed.append(f)
 
         deleted, unknown, ignored, clean = [], [], [], []
 
         command = ['status', '--porcelain', '-z']
         if opts.get(r'unknown'):
             command += ['--untracked-files=all']
         if opts.get(r'ignored'):
             command += ['--ignored']
         out = self._gitcommand(command)
 
         changedfiles = set()
         changedfiles.update(modified)
         changedfiles.update(added)
         changedfiles.update(removed)
         for line in out.split('\0'):
             if not line:
                 continue
             st = line[0:2]
             #moves and copies show 2 files on one line
             if line.find('\0') >= 0:
                 filename1, filename2 = line[3:].split('\0')
             else:
                 filename1 = line[3:]
                 filename2 = None
 
             changedfiles.add(filename1)
             if filename2:
                 changedfiles.add(filename2)
 
             if st == '??':
                 unknown.append(filename1)
             elif st == '!!':
                 ignored.append(filename1)
 
         if opts.get(r'clean'):
             out = self._gitcommand(['ls-files'])
             for f in out.split('\n'):
                 if not f in changedfiles:
                     clean.append(f)
 
         return scmutil.status(modified, added, removed, deleted,
                               unknown, ignored, clean)
 
     @annotatesubrepoerror
     def diff(self, ui, diffopts, node2, match, prefix, **opts):
         node1 = self._state[1]
         cmd = ['diff', '--no-renames']
         if opts[r'stat']:
             cmd.append('--stat')
         else:
             # for Git, this also implies '-p'
             cmd.append('-U%d' % diffopts.context)
 
         if diffopts.noprefix:
             cmd.extend(['--src-prefix=%s/' % prefix,
                         '--dst-prefix=%s/' % prefix])
         else:
             cmd.extend(['--src-prefix=a/%s/' % prefix,
                         '--dst-prefix=b/%s/' % prefix])
 
         if diffopts.ignorews:
             cmd.append('--ignore-all-space')
         if diffopts.ignorewsamount:
             cmd.append('--ignore-space-change')
         if self._gitversion(self._gitcommand(['--version'])) >= (1, 8, 4) \
                 and diffopts.ignoreblanklines:
             cmd.append('--ignore-blank-lines')
 
         cmd.append(node1)
         if node2:
             cmd.append(node2)
 
         output = ""
         if match.always():
             output += self._gitcommand(cmd) + '\n'
         else:
             st = self.status(node2)[:3]
             files = [f for sublist in st for f in sublist]
             for f in files:
                 if match(f):
                     output += self._gitcommand(cmd + ['--', f]) + '\n'
 
         if output.strip():
             ui.write(output)
 
     @annotatesubrepoerror
     def revert(self, substate, *pats, **opts):
         self.ui.status(_('reverting subrepo %s\n') % substate[0])
         if not opts.get(r'no_backup'):
             status = self.status(None)
             names = status.modified
             for name in names:
                 # backuppath() expects a path relative to the parent repo (the
                 # repo that ui.origbackuppath is relative to)
                 parentname = os.path.join(self._path, name)
                 bakname = scmutil.backuppath(self.ui, self._subparent,
                                              parentname)
                 self.ui.note(_('saving current version of %s as %s\n') %
                         (name, os.path.relpath(bakname)))
                 util.rename(self.wvfs.join(name), bakname)
 
         if not opts.get(r'dry_run'):
             self.get(substate, overwrite=True)
         return []
 
     def shortid(self, revid):
         return revid[:7]
 
 types = {
     'hg': hgsubrepo,
     'svn': svnsubrepo,
     'git': gitsubrepo,
     }

tests/test-match.py

@@ -1,832 +1,832 b''
 from __future__ import absolute_import
 
 import unittest
 
 import silenttestrunner
 
 from mercurial import (
     match as matchmod,
     util,
 )
 
 class BaseMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
-        m = matchmod.basematcher(b'', b'')
+        m = matchmod.basematcher()
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
 
     def testVisitchildrenset(self):
-        m = matchmod.basematcher(b'', b'')
+        m = matchmod.basematcher()
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir'), b'this')
 
 class AlwaysMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
-        m = matchmod.alwaysmatcher(b'', b'')
+        m = matchmod.alwaysmatcher()
         self.assertEqual(m.visitdir(b'.'), b'all')
         self.assertEqual(m.visitdir(b'dir'), b'all')
 
     def testVisitchildrenset(self):
-        m = matchmod.alwaysmatcher(b'', b'')
+        m = matchmod.alwaysmatcher()
         self.assertEqual(m.visitchildrenset(b'.'), b'all')
         self.assertEqual(m.visitchildrenset(b'dir'), b'all')
 
 class NeverMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
-        m = matchmod.nevermatcher(b'', b'')
+        m = matchmod.nevermatcher()
         self.assertFalse(m.visitdir(b'.'))
         self.assertFalse(m.visitdir(b'dir'))
 
     def testVisitchildrenset(self):
-        m = matchmod.nevermatcher(b'', b'')
+        m = matchmod.nevermatcher()
         self.assertEqual(m.visitchildrenset(b'.'), set())
         self.assertEqual(m.visitchildrenset(b'dir'), set())
 
 class PredicateMatcherTests(unittest.TestCase):
     # predicatematcher does not currently define either of these methods, so
     # this is equivalent to BaseMatcherTests.
 
     def testVisitdir(self):
-        m = matchmod.predicatematcher(b'', b'', lambda *a: False)
+        m = matchmod.predicatematcher(lambda *a: False)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
 
     def testVisitchildrenset(self):
-        m = matchmod.predicatematcher(b'', b'', lambda *a: False)
+        m = matchmod.predicatematcher(lambda *a: False)
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir'), b'this')
 
 class PatternMatcherTests(unittest.TestCase):
 
     def testVisitdirPrefix(self):
         m = matchmod.match(b'x', b'', patterns=[b'path:dir/subdir'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertEqual(m.visitdir(b'dir/subdir'), b'all')
         # OPT: This should probably be 'all' if its parent is?
         self.assertTrue(m.visitdir(b'dir/subdir/x'))
         self.assertFalse(m.visitdir(b'folder'))
 
     def testVisitchildrensetPrefix(self):
         m = matchmod.match(b'x', b'', patterns=[b'path:dir/subdir'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), b'all')
         # OPT: This should probably be 'all' if its parent is?
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), b'this')
         self.assertEqual(m.visitchildrenset(b'folder'), set())
 
     def testVisitdirRootfilesin(self):
         m = matchmod.match(b'x', b'', patterns=[b'rootfilesin:dir/subdir'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertFalse(m.visitdir(b'dir/subdir/x'))
         self.assertFalse(m.visitdir(b'folder'))
         # FIXME: These should probably be True.
         self.assertFalse(m.visitdir(b'dir'))
         self.assertFalse(m.visitdir(b'dir/subdir'))
 
     def testVisitchildrensetRootfilesin(self):
         m = matchmod.match(b'x', b'', patterns=[b'rootfilesin:dir/subdir'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), set())
         self.assertEqual(m.visitchildrenset(b'folder'), set())
         # FIXME: These should probably be {'subdir'} and 'this', respectively,
         # or at least 'this' and 'this'.
         self.assertEqual(m.visitchildrenset(b'dir'), set())
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), set())
 
     def testVisitdirGlob(self):
         m = matchmod.match(b'x', b'', patterns=[b'glob:dir/z*'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertFalse(m.visitdir(b'folder'))
         # OPT: these should probably be False.
         self.assertTrue(m.visitdir(b'dir/subdir'))
         self.assertTrue(m.visitdir(b'dir/subdir/x'))
 
     def testVisitchildrensetGlob(self):
         m = matchmod.match(b'x', b'', patterns=[b'glob:dir/z*'])
         assert isinstance(m, matchmod.patternmatcher)
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'folder'), set())
         self.assertEqual(m.visitchildrenset(b'dir'), b'this')
         # OPT: these should probably be set().
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), b'this')
 
 class IncludeMatcherTests(unittest.TestCase):
 
     def testVisitdirPrefix(self):
         m = matchmod.match(b'x', b'', include=[b'path:dir/subdir'])
         assert isinstance(m, matchmod.includematcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertEqual(m.visitdir(b'dir/subdir'), b'all')
         # OPT: This should probably be 'all' if its parent is?
         self.assertTrue(m.visitdir(b'dir/subdir/x'))
         self.assertFalse(m.visitdir(b'folder'))
 
     def testVisitchildrensetPrefix(self):
         m = matchmod.match(b'x', b'', include=[b'path:dir/subdir'])
         assert isinstance(m, matchmod.includematcher)
         self.assertEqual(m.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(m.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), b'all')
         # OPT: This should probably be 'all' if its parent is?
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), b'this')
         self.assertEqual(m.visitchildrenset(b'folder'), set())
 
     def testVisitdirRootfilesin(self):
         m = matchmod.match(b'x', b'', include=[b'rootfilesin:dir/subdir'])
         assert isinstance(m, matchmod.includematcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertTrue(m.visitdir(b'dir/subdir'))
         self.assertFalse(m.visitdir(b'dir/subdir/x'))
         self.assertFalse(m.visitdir(b'folder'))
 
     def testVisitchildrensetRootfilesin(self):
         m = matchmod.match(b'x', b'', include=[b'rootfilesin:dir/subdir'])
         assert isinstance(m, matchmod.includematcher)
         self.assertEqual(m.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(m.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), set())
         self.assertEqual(m.visitchildrenset(b'folder'), set())
 
     def testVisitdirGlob(self):
         m = matchmod.match(b'x', b'', include=[b'glob:dir/z*'])
         assert isinstance(m, matchmod.includematcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertFalse(m.visitdir(b'folder'))
         # OPT: these should probably be False.
         self.assertTrue(m.visitdir(b'dir/subdir'))
         self.assertTrue(m.visitdir(b'dir/subdir/x'))
 
     def testVisitchildrensetGlob(self):
         m = matchmod.match(b'x', b'', include=[b'glob:dir/z*'])
         assert isinstance(m, matchmod.includematcher)
         self.assertEqual(m.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(m.visitchildrenset(b'folder'), set())
         self.assertEqual(m.visitchildrenset(b'dir'), b'this')
         # OPT: these should probably be set().
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), b'this')
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), b'this')
 
 class ExactMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
         m = matchmod.exact(b'x', b'', files=[b'dir/subdir/foo.txt'])
         assert isinstance(m, matchmod.exactmatcher)
         self.assertTrue(m.visitdir(b'.'))
         self.assertTrue(m.visitdir(b'dir'))
         self.assertTrue(m.visitdir(b'dir/subdir'))
         self.assertFalse(m.visitdir(b'dir/subdir/foo.txt'))
         self.assertFalse(m.visitdir(b'dir/foo'))
         self.assertFalse(m.visitdir(b'dir/subdir/x'))
         self.assertFalse(m.visitdir(b'folder'))
 
     def testVisitchildrenset(self):
         m = matchmod.exact(b'x', b'', files=[b'dir/subdir/foo.txt'])
         assert isinstance(m, matchmod.exactmatcher)
         self.assertEqual(m.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(m.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(m.visitchildrenset(b'dir/subdir'), {b'foo.txt'})
         self.assertEqual(m.visitchildrenset(b'dir/subdir/x'), set())
         self.assertEqual(m.visitchildrenset(b'dir/subdir/foo.txt'), set())
         self.assertEqual(m.visitchildrenset(b'folder'), set())
 
     def testVisitchildrensetFilesAndDirs(self):
         m = matchmod.exact(b'x', b'', files=[b'rootfile.txt',
                                              b'a/file1.txt',
                                              b'a/b/file2.txt',
                                              # no file in a/b/c
                                              b'a/b/c/d/file4.txt'])
         assert isinstance(m, matchmod.exactmatcher)
         self.assertEqual(m.visitchildrenset(b'.'), {b'a', b'rootfile.txt'})
         self.assertEqual(m.visitchildrenset(b'a'), {b'b', b'file1.txt'})
         self.assertEqual(m.visitchildrenset(b'a/b'), {b'c', b'file2.txt'})
         self.assertEqual(m.visitchildrenset(b'a/b/c'), {b'd'})
         self.assertEqual(m.visitchildrenset(b'a/b/c/d'), {b'file4.txt'})
         self.assertEqual(m.visitchildrenset(b'a/b/c/d/e'), set())
         self.assertEqual(m.visitchildrenset(b'folder'), set())
 
 class DifferenceMatcherTests(unittest.TestCase):
 
     def testVisitdirM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         dm = matchmod.differencematcher(m1, m2)
         # dm should be equivalent to a nevermatcher.
         self.assertFalse(dm.visitdir(b'.'))
         self.assertFalse(dm.visitdir(b'dir'))
         self.assertFalse(dm.visitdir(b'dir/subdir'))
         self.assertFalse(dm.visitdir(b'dir/subdir/z'))
         self.assertFalse(dm.visitdir(b'dir/foo'))
         self.assertFalse(dm.visitdir(b'dir/subdir/x'))
         self.assertFalse(dm.visitdir(b'folder'))
 
     def testVisitchildrensetM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         dm = matchmod.differencematcher(m1, m2)
         # dm should be equivalent to a nevermatcher.
         self.assertEqual(dm.visitchildrenset(b'.'), set())
         self.assertEqual(dm.visitchildrenset(b'dir'), set())
         self.assertEqual(dm.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/z'), set())
         self.assertEqual(dm.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/x'), set())
         self.assertEqual(dm.visitchildrenset(b'folder'), set())
 
     def testVisitdirM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         dm = matchmod.differencematcher(m1, m2)
         # dm should be equivalent to a alwaysmatcher.
         #
         # We're testing Equal-to-True instead of just 'assertTrue' since
         # assertTrue does NOT verify that it's a bool, just that it's truthy.
         # While we may want to eventually make these return 'all', they should
         # not currently do so.
         self.assertEqual(dm.visitdir(b'.'), b'all')
         self.assertEqual(dm.visitdir(b'dir'), b'all')
         self.assertEqual(dm.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(dm.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(dm.visitdir(b'dir/foo'), b'all')
         self.assertEqual(dm.visitdir(b'dir/subdir/x'), b'all')
         self.assertEqual(dm.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         dm = matchmod.differencematcher(m1, m2)
         # dm should be equivalent to a alwaysmatcher.
         self.assertEqual(dm.visitchildrenset(b'.'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/x'), b'all')
         self.assertEqual(dm.visitchildrenset(b'folder'), b'all')
 
     def testVisitdirM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', patterns=[b'path:dir/subdir'])
         dm = matchmod.differencematcher(m1, m2)
         self.assertEqual(dm.visitdir(b'.'), True)
         self.assertEqual(dm.visitdir(b'dir'), True)
         self.assertFalse(dm.visitdir(b'dir/subdir'))
         # OPT: We should probably return False for these; we don't because
         # patternmatcher.visitdir() (our m2) doesn't return 'all' for subdirs of
         # an 'all' pattern, just True.
         self.assertEqual(dm.visitdir(b'dir/subdir/z'), True)
         self.assertEqual(dm.visitdir(b'dir/subdir/x'), True)
         self.assertEqual(dm.visitdir(b'dir/foo'), b'all')
         self.assertEqual(dm.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', patterns=[b'path:dir/subdir'])
         dm = matchmod.differencematcher(m1, m2)
         self.assertEqual(dm.visitchildrenset(b'.'), b'this')
         self.assertEqual(dm.visitchildrenset(b'dir'), b'this')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(dm.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(dm.visitchildrenset(b'folder'), b'all')
         # OPT: We should probably return set() for these; we don't because
         # patternmatcher.visitdir() (our m2) doesn't return 'all' for subdirs of
         # an 'all' pattern, just 'this'.
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/z'), b'this')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/x'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeIncludfe(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         dm = matchmod.differencematcher(m1, m2)
         self.assertEqual(dm.visitdir(b'.'), True)
         self.assertEqual(dm.visitdir(b'dir'), True)
         self.assertEqual(dm.visitdir(b'dir/subdir'), b'all')
         self.assertFalse(dm.visitdir(b'dir/foo'))
         self.assertFalse(dm.visitdir(b'folder'))
         # OPT: We should probably return False for these; we don't because
         # patternmatcher.visitdir() (our m2) doesn't return 'all' for subdirs of
         # an 'all' pattern, just True.
         self.assertEqual(dm.visitdir(b'dir/subdir/z'), True)
         self.assertEqual(dm.visitdir(b'dir/subdir/x'), True)
 
     def testVisitchildrensetIncludeInclude(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         dm = matchmod.differencematcher(m1, m2)
         self.assertEqual(dm.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(dm.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(dm.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(dm.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(dm.visitchildrenset(b'folder'), set())
         # OPT: We should probably return set() for these; we don't because
         # patternmatcher.visitdir() (our m2) doesn't return 'all' for subdirs of
         # an 'all' pattern, just 'this'.
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/z'), b'this')
         self.assertEqual(dm.visitchildrenset(b'dir/subdir/x'), b'this')
 
 class IntersectionMatcherTests(unittest.TestCase):
 
     def testVisitdirM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         im = matchmod.intersectmatchers(m1, m2)
         # im should be equivalent to a alwaysmatcher.
         self.assertEqual(im.visitdir(b'.'), b'all')
         self.assertEqual(im.visitdir(b'dir'), b'all')
         self.assertEqual(im.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(im.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(im.visitdir(b'dir/foo'), b'all')
         self.assertEqual(im.visitdir(b'dir/subdir/x'), b'all')
         self.assertEqual(im.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         im = matchmod.intersectmatchers(m1, m2)
         # im should be equivalent to a alwaysmatcher.
         self.assertEqual(im.visitchildrenset(b'.'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), b'all')
         self.assertEqual(im.visitchildrenset(b'folder'), b'all')
 
     def testVisitdirM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         im = matchmod.intersectmatchers(m1, m2)
         # im should be equivalent to a nevermatcher.
         self.assertFalse(im.visitdir(b'.'))
         self.assertFalse(im.visitdir(b'dir'))
         self.assertFalse(im.visitdir(b'dir/subdir'))
         self.assertFalse(im.visitdir(b'dir/subdir/z'))
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'dir/subdir/x'))
         self.assertFalse(im.visitdir(b'folder'))
 
     def testVisitchildrensetM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         im = matchmod.intersectmatchers(m1, m2)
         # im should be equivalent to a nevermqtcher.
         self.assertEqual(im.visitchildrenset(b'.'), set())
         self.assertEqual(im.visitchildrenset(b'dir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), set())
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
 
     def testVisitdirM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', patterns=[b'path:dir/subdir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitdir(b'.'), True)
         self.assertEqual(im.visitdir(b'dir'), True)
         self.assertEqual(im.visitdir(b'dir/subdir'), b'all')
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'folder'))
         # OPT: We should probably return 'all' for these; we don't because
         # patternmatcher.visitdir() (our m2) doesn't return 'all' for subdirs of
         # an 'all' pattern, just True.
         self.assertEqual(im.visitdir(b'dir/subdir/z'), True)
         self.assertEqual(im.visitdir(b'dir/subdir/x'), True)
 
     def testVisitchildrensetM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(im.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
         # OPT: We should probably return 'all' for these
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), b'this')
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeIncludfe(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitdir(b'.'), True)
         self.assertEqual(im.visitdir(b'dir'), True)
         self.assertFalse(im.visitdir(b'dir/subdir'))
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'folder'))
         self.assertFalse(im.visitdir(b'dir/subdir/z'))
         self.assertFalse(im.visitdir(b'dir/subdir/x'))
 
     def testVisitchildrensetIncludeInclude(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(im.visitchildrenset(b'dir'), b'this')
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), set())
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude2(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'path:folder'])
         im = matchmod.intersectmatchers(m1, m2)
         # FIXME: is True correct here?
         self.assertEqual(im.visitdir(b'.'), True)
         self.assertFalse(im.visitdir(b'dir'))
         self.assertFalse(im.visitdir(b'dir/subdir'))
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'folder'))
         self.assertFalse(im.visitdir(b'dir/subdir/z'))
         self.assertFalse(im.visitdir(b'dir/subdir/x'))
 
     def testVisitchildrensetIncludeInclude2(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'path:folder'])
         im = matchmod.intersectmatchers(m1, m2)
         # FIXME: is set() correct here?
         self.assertEqual(im.visitchildrenset(b'.'), set())
         self.assertEqual(im.visitchildrenset(b'dir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), set())
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude3(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitdir(b'.'), True)
         self.assertEqual(im.visitdir(b'dir'), True)
         self.assertEqual(im.visitdir(b'dir/subdir'), True)
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'folder'))
         self.assertFalse(im.visitdir(b'dir/subdir/z'))
         # OPT: this should probably be 'all' not True.
         self.assertEqual(im.visitdir(b'dir/subdir/x'), True)
 
     def testVisitchildrensetIncludeInclude3(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         im = matchmod.intersectmatchers(m1, m2)
         self.assertEqual(im.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(im.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), {b'x'})
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), set())
         # OPT: this should probably be 'all' not 'this'.
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude4(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir/z'])
         im = matchmod.intersectmatchers(m1, m2)
         # OPT: these next three could probably be False as well.
         self.assertEqual(im.visitdir(b'.'), True)
         self.assertEqual(im.visitdir(b'dir'), True)
         self.assertEqual(im.visitdir(b'dir/subdir'), True)
         self.assertFalse(im.visitdir(b'dir/foo'))
         self.assertFalse(im.visitdir(b'folder'))
         self.assertFalse(im.visitdir(b'dir/subdir/z'))
         self.assertFalse(im.visitdir(b'dir/subdir/x'))
 
     def testVisitchildrensetIncludeInclude4(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir/z'])
         im = matchmod.intersectmatchers(m1, m2)
         # OPT: these next two could probably be set() as well.
         self.assertEqual(im.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(im.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(im.visitchildrenset(b'dir/subdir'), set())
         self.assertEqual(im.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(im.visitchildrenset(b'folder'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/z'), set())
         self.assertEqual(im.visitchildrenset(b'dir/subdir/x'), set())
 
 class UnionMatcherTests(unittest.TestCase):
 
     def testVisitdirM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitdir(b'.'), b'all')
         self.assertEqual(um.visitdir(b'dir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitdir(b'dir/foo'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM2always(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.alwaysmatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitchildrenset(b'.'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitchildrenset(b'folder'), b'all')
 
     def testVisitdirM1never(self):
-        m1 = matchmod.nevermatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.nevermatcher()
+        m2 = matchmod.alwaysmatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitdir(b'.'), b'all')
         self.assertEqual(um.visitdir(b'dir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitdir(b'dir/foo'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM1never(self):
-        m1 = matchmod.nevermatcher(b'', b'')
-        m2 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.nevermatcher()
+        m2 = matchmod.alwaysmatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitchildrenset(b'.'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitchildrenset(b'folder'), b'all')
 
     def testVisitdirM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitdir(b'.'), b'all')
         self.assertEqual(um.visitdir(b'dir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitdir(b'dir/foo'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitdir(b'folder'), b'all')
 
     def testVisitchildrensetM2never(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
-        m2 = matchmod.nevermatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
+        m2 = matchmod.nevermatcher()
         um = matchmod.unionmatcher([m1, m2])
         # um should be equivalent to a alwaysmatcher.
         self.assertEqual(um.visitchildrenset(b'.'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
         self.assertEqual(um.visitchildrenset(b'folder'), b'all')
 
     def testVisitdirM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', patterns=[b'path:dir/subdir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitdir(b'.'), b'all')
         self.assertEqual(um.visitdir(b'dir'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertEqual(um.visitdir(b'dir/foo'), b'all')
         self.assertEqual(um.visitdir(b'folder'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
 
     def testVisitchildrensetM2SubdirPrefix(self):
-        m1 = matchmod.alwaysmatcher(b'', b'')
+        m1 = matchmod.alwaysmatcher()
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitchildrenset(b'.'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), b'all')
         self.assertEqual(um.visitchildrenset(b'folder'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeIncludfe(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitdir(b'.'), True)
         self.assertEqual(um.visitdir(b'dir'), True)
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertFalse(um.visitdir(b'dir/foo'))
         self.assertFalse(um.visitdir(b'folder'))
         # OPT: These two should probably be 'all' not True.
         self.assertEqual(um.visitdir(b'dir/subdir/z'), True)
         self.assertEqual(um.visitdir(b'dir/subdir/x'), True)
 
     def testVisitchildrensetIncludeInclude(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'rootfilesin:dir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(um.visitchildrenset(b'dir'), b'this')
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(um.visitchildrenset(b'folder'), set())
         # OPT: These next two could be 'all' instead of 'this'.
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'this')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude2(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'path:folder'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitdir(b'.'), True)
         self.assertEqual(um.visitdir(b'dir'), True)
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertFalse(um.visitdir(b'dir/foo'))
         self.assertEqual(um.visitdir(b'folder'), b'all')
         # OPT: These should probably be 'all' not True.
         self.assertEqual(um.visitdir(b'dir/subdir/z'), True)
         self.assertEqual(um.visitdir(b'dir/subdir/x'), True)
 
     def testVisitchildrensetIncludeInclude2(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         m2 = matchmod.match(b'', b'', include=[b'path:folder'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitchildrenset(b'.'), {b'folder', b'dir'})
         self.assertEqual(um.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(um.visitchildrenset(b'folder'), b'all')
         # OPT: These next two could be 'all' instead of 'this'.
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'this')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude3(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitdir(b'.'), True)
         self.assertEqual(um.visitdir(b'dir'), True)
         self.assertEqual(um.visitdir(b'dir/subdir'), b'all')
         self.assertFalse(um.visitdir(b'dir/foo'))
         self.assertFalse(um.visitdir(b'folder'))
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
         # OPT: this should probably be 'all' not True.
         self.assertEqual(um.visitdir(b'dir/subdir/z'), True)
 
     def testVisitchildrensetIncludeInclude3(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(um.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(um.visitchildrenset(b'folder'), set())
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
         # OPT: this should probably be 'all' not 'this'.
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'this')
 
     # We're using includematcher instead of patterns because it behaves slightly
     # better (giving narrower results) than patternmatcher.
     def testVisitdirIncludeInclude4(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir/z'])
         um = matchmod.unionmatcher([m1, m2])
         # OPT: these next three could probably be False as well.
         self.assertEqual(um.visitdir(b'.'), True)
         self.assertEqual(um.visitdir(b'dir'), True)
         self.assertEqual(um.visitdir(b'dir/subdir'), True)
         self.assertFalse(um.visitdir(b'dir/foo'))
         self.assertFalse(um.visitdir(b'folder'))
         self.assertEqual(um.visitdir(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitdir(b'dir/subdir/x'), b'all')
 
     def testVisitchildrensetIncludeInclude4(self):
         m1 = matchmod.match(b'', b'', include=[b'path:dir/subdir/x'])
         m2 = matchmod.match(b'', b'', include=[b'path:dir/subdir/z'])
         um = matchmod.unionmatcher([m1, m2])
         self.assertEqual(um.visitchildrenset(b'.'), {b'dir'})
         self.assertEqual(um.visitchildrenset(b'dir'), {b'subdir'})
         self.assertEqual(um.visitchildrenset(b'dir/subdir'), {b'x', b'z'})
         self.assertEqual(um.visitchildrenset(b'dir/foo'), set())
         self.assertEqual(um.visitchildrenset(b'folder'), set())
         self.assertEqual(um.visitchildrenset(b'dir/subdir/z'), b'all')
         self.assertEqual(um.visitchildrenset(b'dir/subdir/x'), b'all')
 
 class SubdirMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
         m = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         sm = matchmod.subdirmatcher(b'dir', m)
 
         self.assertEqual(sm.visitdir(b'.'), True)
         self.assertEqual(sm.visitdir(b'subdir'), b'all')
         # OPT: These next two should probably be 'all' not True.
         self.assertEqual(sm.visitdir(b'subdir/x'), True)
         self.assertEqual(sm.visitdir(b'subdir/z'), True)
         self.assertFalse(sm.visitdir(b'foo'))
 
     def testVisitchildrenset(self):
         m = matchmod.match(b'', b'', include=[b'path:dir/subdir'])
         sm = matchmod.subdirmatcher(b'dir', m)
 
         self.assertEqual(sm.visitchildrenset(b'.'), {b'subdir'})
         self.assertEqual(sm.visitchildrenset(b'subdir'), b'all')
         # OPT: These next two should probably be 'all' not 'this'.
         self.assertEqual(sm.visitchildrenset(b'subdir/x'), b'this')
         self.assertEqual(sm.visitchildrenset(b'subdir/z'), b'this')
         self.assertEqual(sm.visitchildrenset(b'foo'), set())
 
 class PrefixdirMatcherTests(unittest.TestCase):
 
     def testVisitdir(self):
         m = matchmod.match(util.localpath(b'root/d'), b'e/f',
                 [b'../a.txt', b'b.txt'])
-        pm = matchmod.prefixdirmatcher(b'root', b'd/e/f', b'd', m)
+        pm = matchmod.prefixdirmatcher(b'd', m)
 
         # `m` elides 'd' because it's part of the root, and the rest of the
         # patterns are relative.
         self.assertEqual(bool(m(b'a.txt')), False)
         self.assertEqual(bool(m(b'b.txt')), False)
         self.assertEqual(bool(m(b'e/a.txt')), True)
         self.assertEqual(bool(m(b'e/b.txt')), False)
         self.assertEqual(bool(m(b'e/f/b.txt')), True)
 
         # The prefix matcher re-adds 'd' to the paths, so they need to be
         # specified when using the prefixdirmatcher.
         self.assertEqual(bool(pm(b'a.txt')), False)
         self.assertEqual(bool(pm(b'b.txt')), False)
         self.assertEqual(bool(pm(b'd/e/a.txt')), True)
         self.assertEqual(bool(pm(b'd/e/b.txt')), False)
         self.assertEqual(bool(pm(b'd/e/f/b.txt')), True)
 
         self.assertEqual(m.visitdir(b'.'), True)
         self.assertEqual(m.visitdir(b'e'), True)
         self.assertEqual(m.visitdir(b'e/f'), True)
         self.assertEqual(m.visitdir(b'e/f/g'), False)
 
         self.assertEqual(pm.visitdir(b'.'), True)
         self.assertEqual(pm.visitdir(b'd'), True)
         self.assertEqual(pm.visitdir(b'd/e'), True)
         self.assertEqual(pm.visitdir(b'd/e/f'), True)
         self.assertEqual(pm.visitdir(b'd/e/f/g'), False)
 
     def testVisitchildrenset(self):
         m = matchmod.match(util.localpath(b'root/d'), b'e/f',
                 [b'../a.txt', b'b.txt'])
-        pm = matchmod.prefixdirmatcher(b'root', b'd/e/f', b'd', m)
+        pm = matchmod.prefixdirmatcher(b'd', m)
 
         # OPT: visitchildrenset could possibly return {'e'} and {'f'} for these
         # next two, respectively; patternmatcher does not have this
         # optimization.
         self.assertEqual(m.visitchildrenset(b'.'), b'this')
         self.assertEqual(m.visitchildrenset(b'e'), b'this')
         self.assertEqual(m.visitchildrenset(b'e/f'), b'this')
         self.assertEqual(m.visitchildrenset(b'e/f/g'), set())
 
         # OPT: visitchildrenset could possibly return {'d'}, {'e'}, and {'f'}
         # for these next three, respectively; patternmatcher does not have this
         # optimization.
         self.assertEqual(pm.visitchildrenset(b'.'), b'this')
         self.assertEqual(pm.visitchildrenset(b'd'), b'this')
         self.assertEqual(pm.visitchildrenset(b'd/e'), b'this')
         self.assertEqual(pm.visitchildrenset(b'd/e/f'), b'this')
         self.assertEqual(pm.visitchildrenset(b'd/e/f/g'), set())
 
 if __name__ == '__main__':
     silenttestrunner.main(__name__)