localrepo: move repo creation logic out of localrepository.__init__ (API)

It has long bothered me that local repository creation is handled as
part of localrepository.__init__. Upcoming changes I want to make
around how repositories are initialized and instantiated will make
the continued existence of repository creation code in
localrepository.__init__ even more awkward.

localrepository instances are almost never constructed directly:
instead, callers are supposed to go through hg.repository() to obtain
a handle on a repository. And hg.repository() calls
localrepo.instance() to return a new repo instance.

This commit teaches localrepo.instance() to handle the create=True
logic. Most of the code for repo construction has been moved to a
standalone function. This allows extensions to monkeypatch the function
to further customize freshly-created repositories.

A few calls to localrepo.localrepository.__init__ that were passing
create=True were converted to call localrepo.instance().

.. api:: local repo creation moved out of constructor

   ``localrepo.localrepository.__init__`` no longer accepts a
   ``create`` argument to create a new repository. New repository
   creation is now performed as part of ``localrepo.instance()``
   and the bulk of the work is performed by
   ``localrepo.createrepository()``.

Differential Revision: https://phab.mercurial-scm.org/D4534

hgext/keyword.py

@@ -1,815 +1,815 b''
 # keyword.py - $Keyword$ expansion for Mercurial
 #
 # Copyright 2007-2015 Christian Ebert <[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.
 #
 # $Id$
 #
 # Keyword expansion hack against the grain of a Distributed SCM
 #
 # There are many good reasons why this is not needed in a distributed
 # SCM, still it may be useful in very small projects based on single
 # files (like LaTeX packages), that are mostly addressed to an
 # audience not running a version control system.
 #
 # For in-depth discussion refer to
 # <https://mercurial-scm.org/wiki/KeywordPlan>.
 #
 # Keyword expansion is based on Mercurial's changeset template mappings.
 #
 # Binary files are not touched.
 #
 # Files to act upon/ignore are specified in the [keyword] section.
 # Customized keyword template mappings in the [keywordmaps] section.
 #
 # Run 'hg help keyword' and 'hg kwdemo' to get info on configuration.
 
 '''expand keywords in tracked files
 
 This extension expands RCS/CVS-like or self-customized $Keywords$ in
 tracked text files selected by your configuration.
 
 Keywords are only expanded in local repositories and not stored in the
 change history. The mechanism can be regarded as a convenience for the
 current user or for archive distribution.
 
 Keywords expand to the changeset data pertaining to the latest change
 relative to the working directory parent of each file.
 
 Configuration is done in the [keyword], [keywordset] and [keywordmaps]
 sections of hgrc files.
 
 Example::
 
     [keyword]
     # expand keywords in every python file except those matching "x*"
     **.py =
     x*    = ignore
 
     [keywordset]
     # prefer svn- over cvs-like default keywordmaps
     svn = True
 
 .. note::
 
    The more specific you are in your filename patterns the less you
    lose speed in huge repositories.
 
 For [keywordmaps] template mapping and expansion demonstration and
 control run :hg:`kwdemo`. See :hg:`help templates` for a list of
 available templates and filters.
 
 Three additional date template filters are provided:
 
 :``utcdate``:    "2006/09/18 15:13:13"
 :``svnutcdate``: "2006-09-18 15:13:13Z"
 :``svnisodate``: "2006-09-18 08:13:13 -700 (Mon, 18 Sep 2006)"
 
 The default template mappings (view with :hg:`kwdemo -d`) can be
 replaced with customized keywords and templates. Again, run
 :hg:`kwdemo` to control the results of your configuration changes.
 
 Before changing/disabling active keywords, you must run :hg:`kwshrink`
 to avoid storing expanded keywords in the change history.
 
 To force expansion after enabling it, or a configuration change, run
 :hg:`kwexpand`.
 
 Expansions spanning more than one line and incremental expansions,
 like CVS' $Log$, are not supported. A keyword template map "Log =
 {desc}" expands to the first line of the changeset description.
 '''
 
 
 from __future__ import absolute_import
 
 import os
 import re
 import weakref
 
 from mercurial.i18n import _
 from mercurial.hgweb import webcommands
 
 from mercurial import (
     cmdutil,
     context,
     dispatch,
     error,
     extensions,
     filelog,
     localrepo,
     logcmdutil,
     match,
     patch,
     pathutil,
     pycompat,
     registrar,
     scmutil,
     templatefilters,
     templateutil,
     util,
 )
 from mercurial.utils import (
     dateutil,
     stringutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # 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'
 
 # hg commands that do not act on keywords
 nokwcommands = ('add addremove annotate bundle export grep incoming init log'
                 ' outgoing push tip verify convert email glog')
 
 # webcommands that do not act on keywords
 nokwwebcommands = ('annotate changeset rev filediff diff comparison')
 
 # hg commands that trigger expansion only when writing to working dir,
 # not when reading filelog, and unexpand when reading from working dir
 restricted = ('merge kwexpand kwshrink record qrecord resolve transplant'
               ' unshelve rebase graft backout histedit fetch')
 
 # names of extensions using dorecord
 recordextensions = 'record'
 
 colortable = {
     'kwfiles.enabled': 'green bold',
     'kwfiles.deleted': 'cyan bold underline',
     'kwfiles.enabledunknown': 'green',
     'kwfiles.ignored': 'bold',
     'kwfiles.ignoredunknown': 'none'
 }
 
 templatefilter = registrar.templatefilter()
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('keywordset', 'svn',
     default=False,
 )
 # date like in cvs' $Date
 @templatefilter('utcdate', intype=templateutil.date)
 def utcdate(date):
     '''Date. Returns a UTC-date in this format: "2009/08/18 11:00:13".
     '''
     dateformat = '%Y/%m/%d %H:%M:%S'
     return dateutil.datestr((date[0], 0), dateformat)
 # date like in svn's $Date
 @templatefilter('svnisodate', intype=templateutil.date)
 def svnisodate(date):
     '''Date. Returns a date in this format: "2009-08-18 13:00:13
     +0200 (Tue, 18 Aug 2009)".
     '''
     return dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)')
 # date like in svn's $Id
 @templatefilter('svnutcdate', intype=templateutil.date)
 def svnutcdate(date):
     '''Date. Returns a UTC-date in this format: "2009-08-18
     11:00:13Z".
     '''
     dateformat = '%Y-%m-%d %H:%M:%SZ'
     return dateutil.datestr((date[0], 0), dateformat)
 
 # make keyword tools accessible
 kwtools = {'hgcmd': ''}
 
 def _defaultkwmaps(ui):
     '''Returns default keywordmaps according to keywordset configuration.'''
     templates = {
         'Revision': '{node|short}',
         'Author': '{author|user}',
     }
     kwsets = ({
         'Date': '{date|utcdate}',
         'RCSfile': '{file|basename},v',
         'RCSFile': '{file|basename},v', # kept for backwards compatibility
                                         # with hg-keyword
         'Source': '{root}/{file},v',
         'Id': '{file|basename},v {node|short} {date|utcdate} {author|user}',
         'Header': '{root}/{file},v {node|short} {date|utcdate} {author|user}',
     }, {
         'Date': '{date|svnisodate}',
         'Id': '{file|basename},v {node|short} {date|svnutcdate} {author|user}',
         'LastChangedRevision': '{node|short}',
         'LastChangedBy': '{author|user}',
         'LastChangedDate': '{date|svnisodate}',
     })
     templates.update(kwsets[ui.configbool('keywordset', 'svn')])
     return templates
 
 def _shrinktext(text, subfunc):
     '''Helper for keyword expansion removal in text.
     Depending on subfunc also returns number of substitutions.'''
     return subfunc(br'$\1$', text)
 
 def _preselect(wstatus, changed):
     '''Retrieves modified and added files from a working directory state
     and returns the subset of each contained in given changed files
     retrieved from a change context.'''
     modified = [f for f in wstatus.modified if f in changed]
     added = [f for f in wstatus.added if f in changed]
     return modified, added
 
 
 class kwtemplater(object):
     '''
     Sets up keyword templates, corresponding keyword regex, and
     provides keyword substitution functions.
     '''
 
     def __init__(self, ui, repo, inc, exc):
         self.ui = ui
         self._repo = weakref.ref(repo)
         self.match = match.match(repo.root, '', [], inc, exc)
         self.restrict = kwtools['hgcmd'] in restricted.split()
         self.postcommit = False
 
         kwmaps = self.ui.configitems('keywordmaps')
         if kwmaps: # override default templates
             self.templates = dict(kwmaps)
         else:
             self.templates = _defaultkwmaps(self.ui)
 
     @property
     def repo(self):
         return self._repo()
 
     @util.propertycache
     def escape(self):
         '''Returns bar-separated and escaped keywords.'''
         return '|'.join(map(stringutil.reescape, self.templates.keys()))
 
     @util.propertycache
     def rekw(self):
         '''Returns regex for unexpanded keywords.'''
         return re.compile(br'\$(%s)\$' % self.escape)
 
     @util.propertycache
     def rekwexp(self):
         '''Returns regex for expanded keywords.'''
         return re.compile(br'\$(%s): [^$\n\r]*? \$' % self.escape)
 
     def substitute(self, data, path, ctx, subfunc):
         '''Replaces keywords in data with expanded template.'''
         def kwsub(mobj):
             kw = mobj.group(1)
             ct = logcmdutil.maketemplater(self.ui, self.repo,
                                           self.templates[kw])
             self.ui.pushbuffer()
             ct.show(ctx, root=self.repo.root, file=path)
             ekw = templatefilters.firstline(self.ui.popbuffer())
             return '$%s: %s $' % (kw, ekw)
         return subfunc(kwsub, data)
 
     def linkctx(self, path, fileid):
         '''Similar to filelog.linkrev, but returns a changectx.'''
         return self.repo.filectx(path, fileid=fileid).changectx()
 
     def expand(self, path, node, data):
         '''Returns data with keywords expanded.'''
         if (not self.restrict and self.match(path)
             and not stringutil.binary(data)):
             ctx = self.linkctx(path, node)
             return self.substitute(data, path, ctx, self.rekw.sub)
         return data
 
     def iskwfile(self, cand, ctx):
         '''Returns subset of candidates which are configured for keyword
         expansion but are not symbolic links.'''
         return [f for f in cand if self.match(f) and 'l' not in ctx.flags(f)]
 
     def overwrite(self, ctx, candidates, lookup, expand, rekw=False):
         '''Overwrites selected files expanding/shrinking keywords.'''
         if self.restrict or lookup or self.postcommit: # exclude kw_copy
             candidates = self.iskwfile(candidates, ctx)
         if not candidates:
             return
         kwcmd = self.restrict and lookup # kwexpand/kwshrink
         if self.restrict or expand and lookup:
             mf = ctx.manifest()
         if self.restrict or rekw:
             re_kw = self.rekw
         else:
             re_kw = self.rekwexp
         if expand:
             msg = _('overwriting %s expanding keywords\n')
         else:
             msg = _('overwriting %s shrinking keywords\n')
         for f in candidates:
             if self.restrict:
                 data = self.repo.file(f).read(mf[f])
             else:
                 data = self.repo.wread(f)
             if stringutil.binary(data):
                 continue
             if expand:
                 parents = ctx.parents()
                 if lookup:
                     ctx = self.linkctx(f, mf[f])
                 elif self.restrict and len(parents) > 1:
                     # merge commit
                     # in case of conflict f is in modified state during
                     # merge, even if f does not differ from f in parent
                     for p in parents:
                         if f in p and not p[f].cmp(ctx[f]):
                             ctx = p[f].changectx()
                             break
                 data, found = self.substitute(data, f, ctx, re_kw.subn)
             elif self.restrict:
                 found = re_kw.search(data)
             else:
                 data, found = _shrinktext(data, re_kw.subn)
             if found:
                 self.ui.note(msg % f)
                 fp = self.repo.wvfs(f, "wb", atomictemp=True)
                 fp.write(data)
                 fp.close()
                 if kwcmd:
                     self.repo.dirstate.normal(f)
                 elif self.postcommit:
                     self.repo.dirstate.normallookup(f)
 
     def shrink(self, fname, text):
         '''Returns text with all keyword substitutions removed.'''
         if self.match(fname) and not stringutil.binary(text):
             return _shrinktext(text, self.rekwexp.sub)
         return text
 
     def shrinklines(self, fname, lines):
         '''Returns lines with keyword substitutions removed.'''
         if self.match(fname):
             text = ''.join(lines)
             if not stringutil.binary(text):
                 return _shrinktext(text, self.rekwexp.sub).splitlines(True)
         return lines
 
     def wread(self, fname, data):
         '''If in restricted mode returns data read from wdir with
         keyword substitutions removed.'''
         if self.restrict:
             return self.shrink(fname, data)
         return data
 
 class kwfilelog(filelog.filelog):
     '''
     Subclass of filelog to hook into its read, add, cmp methods.
     Keywords are "stored" unexpanded, and processed on reading.
     '''
     def __init__(self, opener, kwt, path):
         super(kwfilelog, self).__init__(opener, path)
         self.kwt = kwt
         self.path = path
 
     def read(self, node):
         '''Expands keywords when reading filelog.'''
         data = super(kwfilelog, self).read(node)
         if self.renamed(node):
             return data
         return self.kwt.expand(self.path, node, data)
 
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).add(text, meta, tr, link, p1, p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).cmp(node, text)
 
 def _status(ui, repo, wctx, kwt, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if kwt:
         opts = pycompat.byteskwargs(opts)
         return repo.status(match=scmutil.match(wctx, pats, opts), clean=True,
                            unknown=opts.get('unknown') or opts.get('all'))
     if ui.configitems('keyword'):
         raise error.Abort(_('[keyword] patterns cannot match'))
     raise error.Abort(_('no [keyword] patterns configured'))
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to kwtemplater.overwrite.'''
     wctx = repo[None]
     if len(wctx.parents()) > 1:
         raise error.Abort(_('outstanding uncommitted merge'))
     kwt = getattr(repo, '_keywordkwt', None)
     with repo.wlock():
         status = _status(ui, repo, wctx, kwt, *pats, **opts)
         if status.modified or status.added or status.removed or status.deleted:
             raise error.Abort(_('outstanding uncommitted changes'))
         kwt.overwrite(wctx, status.clean, True, expand)
 
 @command('kwdemo',
          [('d', 'default', None, _('show default keyword template maps')),
           ('f', 'rcfile', '',
            _('read maps from rcfile'), _('FILE'))],
          _('hg kwdemo [-d] [-f RCFILE] [TEMPLATEMAP]...'),
          optionalrepo=True)
 def demo(ui, repo, *args, **opts):
     '''print [keywordmaps] configuration and an expansion example
 
     Show current, custom, or default keyword template maps and their
     expansions.
 
     Extend the current configuration by specifying maps as arguments
     and using -f/--rcfile to source an external hgrc file.
 
     Use -d/--default to disable current configuration.
 
     See :hg:`help templates` for information on templates and filters.
     '''
     def demoitems(section, items):
         ui.write('[%s]\n' % section)
         for k, v in sorted(items):
             ui.write('%s = %s\n' % (k, v))
 
     fn = 'demo.txt'
     tmpdir = pycompat.mkdtemp('', 'kwdemo.')
     ui.note(_('creating temporary repository at %s\n') % tmpdir)
     if repo is None:
         baseui = ui
     else:
         baseui = repo.baseui
-    repo = localrepo.localrepository(baseui, tmpdir, True)
+    repo = localrepo.instance(baseui, tmpdir, create=True)
     ui.setconfig('keyword', fn, '', 'keyword')
     svn = ui.configbool('keywordset', 'svn')
     # explicitly set keywordset for demo output
     ui.setconfig('keywordset', 'svn', svn, 'keyword')
 
     uikwmaps = ui.configitems('keywordmaps')
     if args or opts.get(r'rcfile'):
         ui.status(_('\n\tconfiguration using custom keyword template maps\n'))
         if uikwmaps:
             ui.status(_('\textending current template maps\n'))
         if opts.get(r'default') or not uikwmaps:
             if svn:
                 ui.status(_('\toverriding default svn keywordset\n'))
             else:
                 ui.status(_('\toverriding default cvs keywordset\n'))
         if opts.get(r'rcfile'):
             ui.readconfig(opts.get('rcfile'))
         if args:
             # simulate hgrc parsing
             rcmaps = '[keywordmaps]\n%s\n' % '\n'.join(args)
             repo.vfs.write('hgrc', rcmaps)
             ui.readconfig(repo.vfs.join('hgrc'))
         kwmaps = dict(ui.configitems('keywordmaps'))
     elif opts.get(r'default'):
         if svn:
             ui.status(_('\n\tconfiguration using default svn keywordset\n'))
         else:
             ui.status(_('\n\tconfiguration using default cvs keywordset\n'))
         kwmaps = _defaultkwmaps(ui)
         if uikwmaps:
             ui.status(_('\tdisabling current template maps\n'))
             for k, v in kwmaps.iteritems():
                 ui.setconfig('keywordmaps', k, v, 'keyword')
     else:
         ui.status(_('\n\tconfiguration using current keyword template maps\n'))
         if uikwmaps:
             kwmaps = dict(uikwmaps)
         else:
             kwmaps = _defaultkwmaps(ui)
 
     uisetup(ui)
     reposetup(ui, repo)
     ui.write(('[extensions]\nkeyword =\n'))
     demoitems('keyword', ui.configitems('keyword'))
     demoitems('keywordset', ui.configitems('keywordset'))
     demoitems('keywordmaps', kwmaps.iteritems())
     keywords = '$' + '$\n$'.join(sorted(kwmaps.keys())) + '$\n'
     repo.wvfs.write(fn, keywords)
     repo[None].add([fn])
     ui.note(_('\nkeywords written to %s:\n') % fn)
     ui.note(keywords)
     with repo.wlock():
         repo.dirstate.setbranch('demobranch')
     for name, cmd in ui.configitems('hooks'):
         if name.split('.', 1)[0].find('commit') > -1:
             repo.ui.setconfig('hooks', name, '', 'keyword')
     msg = _('hg keyword configuration and expansion example')
     ui.note(("hg ci -m '%s'\n" % msg))
     repo.commit(text=msg)
     ui.status(_('\n\tkeywords expanded\n'))
     ui.write(repo.wread(fn))
     repo.wvfs.rmtree(repo.root)
 
 @command('kwexpand',
     cmdutil.walkopts,
     _('hg kwexpand [OPTION]... [FILE]...'),
     inferrepo=True)
 def expand(ui, repo, *pats, **opts):
     '''expand keywords in the working directory
 
     Run after (re)enabling keyword expansion.
 
     kwexpand refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to True
     _kwfwrite(ui, repo, True, *pats, **opts)
 
 @command('kwfiles',
          [('A', 'all', None, _('show keyword status flags of all files')),
           ('i', 'ignore', None, _('show files excluded from expansion')),
           ('u', 'unknown', None, _('only show unknown (not tracked) files')),
          ] + cmdutil.walkopts,
          _('hg kwfiles [OPTION]... [FILE]...'),
          inferrepo=True)
 def files(ui, repo, *pats, **opts):
     '''show files configured for keyword expansion
 
     List which files in the working directory are matched by the
     [keyword] configuration patterns.
 
     Useful to prevent inadvertent keyword expansion and to speed up
     execution by including only files that are actual candidates for
     expansion.
 
     See :hg:`help keyword` on how to construct patterns both for
     inclusion and exclusion of files.
 
     With -A/--all and -v/--verbose the codes used to show the status
     of files are::
 
       K = keyword expansion candidate
       k = keyword expansion candidate (not tracked)
       I = ignored
       i = ignored (not tracked)
     '''
     kwt = getattr(repo, '_keywordkwt', None)
     wctx = repo[None]
     status = _status(ui, repo, wctx, kwt, *pats, **opts)
     if pats:
         cwd = repo.getcwd()
     else:
         cwd = ''
     files = []
     opts = pycompat.byteskwargs(opts)
     if not opts.get('unknown') or opts.get('all'):
         files = sorted(status.modified + status.added + status.clean)
     kwfiles = kwt.iskwfile(files, wctx)
     kwdeleted = kwt.iskwfile(status.deleted, wctx)
     kwunknown = kwt.iskwfile(status.unknown, wctx)
     if not opts.get('ignore') or opts.get('all'):
         showfiles = kwfiles, kwdeleted, kwunknown
     else:
         showfiles = [], [], []
     if opts.get('all') or opts.get('ignore'):
         showfiles += ([f for f in files if f not in kwfiles],
                       [f for f in status.unknown if f not in kwunknown])
     kwlabels = 'enabled deleted enabledunknown ignored ignoredunknown'.split()
     kwstates = zip(kwlabels, pycompat.bytestr('K!kIi'), showfiles)
     fm = ui.formatter('kwfiles', opts)
     fmt = '%.0s%s\n'
     if opts.get('all') or ui.verbose:
         fmt = '%s %s\n'
     for kwstate, char, filenames in kwstates:
         label = 'kwfiles.' + kwstate
         for f in filenames:
             fm.startitem()
             fm.data(kwstatus=char, path=f)
             fm.plain(fmt % (char, repo.pathto(f, cwd)), label=label)
     fm.end()
 
 @command('kwshrink',
     cmdutil.walkopts,
     _('hg kwshrink [OPTION]... [FILE]...'),
     inferrepo=True)
 def shrink(ui, repo, *pats, **opts):
     '''revert expanded keywords in the working directory
 
     Must be run before changing/disabling active keywords.
 
     kwshrink refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to False
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 # monkeypatches
 
 def kwpatchfile_init(orig, self, ui, gp, backend, store, eolmode=None):
     '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
     rejects or conflicts due to expanded keywords in working dir.'''
     orig(self, ui, gp, backend, store, eolmode)
     kwt = getattr(getattr(backend, 'repo', None), '_keywordkwt', None)
     if kwt:
         # shrink keywords read from working dir
         self.lines = kwt.shrinklines(self.fname, self.lines)
 
 def kwdiff(orig, repo, *args, **kwargs):
     '''Monkeypatch patch.diff to avoid expansion.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt:
         restrict = kwt.restrict
         kwt.restrict = True
     try:
         for chunk in orig(repo, *args, **kwargs):
             yield chunk
     finally:
         if kwt:
             kwt.restrict = restrict
 
 def kwweb_skip(orig, web):
     '''Wraps webcommands.x turning off keyword expansion.'''
     kwt = getattr(web.repo, '_keywordkwt', None)
     if kwt:
         origmatch = kwt.match
         kwt.match = util.never
     try:
         for chunk in orig(web):
             yield chunk
     finally:
         if kwt:
             kwt.match = origmatch
 
 def kw_amend(orig, ui, repo, old, extra, pats, opts):
     '''Wraps cmdutil.amend expanding keywords after amend.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, old, extra, pats, opts)
     with repo.wlock():
         kwt.postcommit = True
         newid = orig(ui, repo, old, extra, pats, opts)
         if newid != old.node():
             ctx = repo[newid]
             kwt.restrict = True
             kwt.overwrite(ctx, ctx.files(), False, True)
             kwt.restrict = False
         return newid
 
 def kw_copy(orig, ui, repo, pats, opts, rename=False):
     '''Wraps cmdutil.copy so that copy/rename destinations do not
     contain expanded keywords.
     Note that the source of a regular file destination may also be a
     symlink:
     hg cp sym x                -> x is symlink
     cp sym x; hg cp -A sym x   -> x is file (maybe expanded keywords)
     For the latter we have to follow the symlink to find out whether its
     target is configured for expansion and we therefore must unexpand the
     keywords in the destination.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, pats, opts, rename)
     with repo.wlock():
         orig(ui, repo, pats, opts, rename)
         if opts.get('dry_run'):
             return
         wctx = repo[None]
         cwd = repo.getcwd()
 
         def haskwsource(dest):
             '''Returns true if dest is a regular file and configured for
             expansion or a symlink which points to a file configured for
             expansion. '''
             source = repo.dirstate.copied(dest)
             if 'l' in wctx.flags(source):
                 source = pathutil.canonpath(repo.root, cwd,
                                            os.path.realpath(source))
             return kwt.match(source)
 
         candidates = [f for f in repo.dirstate.copies() if
                       'l' not in wctx.flags(f) and haskwsource(f)]
         kwt.overwrite(wctx, candidates, False, False)
 
 def kw_dorecord(orig, ui, repo, commitfunc, *pats, **opts):
     '''Wraps record.dorecord expanding keywords after recording.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, commitfunc, *pats, **opts)
     with repo.wlock():
         # record returns 0 even when nothing has changed
         # therefore compare nodes before and after
         kwt.postcommit = True
         ctx = repo['.']
         wstatus = ctx.status()
         ret = orig(ui, repo, commitfunc, *pats, **opts)
         recctx = repo['.']
         if ctx != recctx:
             modified, added = _preselect(wstatus, recctx.files())
             kwt.restrict = False
             kwt.overwrite(recctx, modified, False, True)
             kwt.overwrite(recctx, added, False, True, True)
             kwt.restrict = True
         return ret
 
 def kwfilectx_cmp(orig, self, fctx):
     if fctx._customcmp:
         return fctx.cmp(self)
     kwt = getattr(self._repo, '_keywordkwt', None)
     if kwt is None:
         return orig(self, fctx)
     # keyword affects data size, comparing wdir and filelog size does
     # not make sense
     if (fctx._filenode is None and
         (self._repo._encodefilterpats or
          kwt.match(fctx.path()) and 'l' not in fctx.flags() or
          self.size() - 4 == fctx.size()) or
         self.size() == fctx.size()):
         return self._filelog.cmp(self._filenode, fctx.data())
     return True
 
 def uisetup(ui):
     ''' Monkeypatches dispatch._parse to retrieve user command.
     Overrides file method to return kwfilelog instead of filelog
     if file matches user configuration.
     Wraps commit to overwrite configured files with updated
     keyword substitutions.
     Monkeypatches patch and webcommands.'''
 
     def kwdispatch_parse(orig, ui, args):
         '''Monkeypatch dispatch._parse to obtain running hg command.'''
         cmd, func, args, options, cmdoptions = orig(ui, args)
         kwtools['hgcmd'] = cmd
         return cmd, func, args, options, cmdoptions
 
     extensions.wrapfunction(dispatch, '_parse', kwdispatch_parse)
 
     extensions.wrapfunction(context.filectx, 'cmp', kwfilectx_cmp)
     extensions.wrapfunction(patch.patchfile, '__init__', kwpatchfile_init)
     extensions.wrapfunction(patch, 'diff', kwdiff)
     extensions.wrapfunction(cmdutil, 'amend', kw_amend)
     extensions.wrapfunction(cmdutil, 'copy', kw_copy)
     extensions.wrapfunction(cmdutil, 'dorecord', kw_dorecord)
     for c in nokwwebcommands.split():
         extensions.wrapfunction(webcommands, c, kwweb_skip)
 
 def reposetup(ui, repo):
     '''Sets up repo as kwrepo for keyword substitution.'''
 
     try:
         if (not repo.local() or kwtools['hgcmd'] in nokwcommands.split()
             or '.hg' in util.splitpath(repo.root)
             or repo._url.startswith('bundle:')):
             return
     except AttributeError:
         pass
 
     inc, exc = [], ['.hg*']
     for pat, opt in ui.configitems('keyword'):
         if opt != 'ignore':
             inc.append(pat)
         else:
             exc.append(pat)
     if not inc:
         return
 
     kwt = kwtemplater(ui, repo, inc, exc)
 
     class kwrepo(repo.__class__):
         def file(self, f):
             if f[0] == '/':
                 f = f[1:]
             return kwfilelog(self.svfs, kwt, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             return kwt.wread(filename, data)
 
         def commit(self, *args, **opts):
             # use custom commitctx for user commands
             # other extensions can still wrap repo.commitctx directly
             self.commitctx = self.kwcommitctx
             try:
                 return super(kwrepo, self).commit(*args, **opts)
             finally:
                 del self.commitctx
 
         def kwcommitctx(self, ctx, error=False):
             n = super(kwrepo, self).commitctx(ctx, error)
             # no lock needed, only called from repo.commit() which already locks
             if not kwt.postcommit:
                 restrict = kwt.restrict
                 kwt.restrict = True
                 kwt.overwrite(self[n], sorted(ctx.added() + ctx.modified()),
                               False, True)
                 kwt.restrict = restrict
             return n
 
         def rollback(self, dryrun=False, force=False):
             with self.wlock():
                 origrestrict = kwt.restrict
                 try:
                     if not dryrun:
                         changed = self['.'].files()
                     ret = super(kwrepo, self).rollback(dryrun, force)
                     if not dryrun:
                         ctx = self['.']
                         modified, added = _preselect(ctx.status(), changed)
                         kwt.restrict = False
                         kwt.overwrite(ctx, modified, True, True)
                         kwt.overwrite(ctx, added, True, False)
                     return ret
                 finally:
                     kwt.restrict = origrestrict
 
     repo.__class__ = kwrepo
     repo._keywordkwt = kwt

mercurial/localrepo.py

@@ -1,2449 +1,2472 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 (
     hex,
     nullid,
     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,
     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
         return super(_basefilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(_basefilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(_basefilecache, self).__delete__(repo.unfiltered())
 
 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-revlogv2.0'
 
 # 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()
 
 @interfaceutil.implementer(repository.completelocalrepository)
 class localrepository(object):
 
     # 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'
     }
     openerreqs = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
     }
 
     # 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, path, create=False, intents=None):
+    def __init__(self, baseui, path, intents=None):
+        """Create a new local repository instance.
+
+        Most callers should use ``hg.repository()`` or ``localrepo.instance()``
+        for obtaining a new repository object.
+        """
+
         self.requirements = set()
         self.filtername = None
         # wvfs: rooted at the repository root, used to access the working copy
         self.wvfs = vfsmod.vfs(path, expandpath=True, realpath=True)
         # vfs: rooted at .hg, used to access repo files outside of .hg/store
         self.vfs = None
         # svfs: usually rooted at .hg/store, used to access repository history
         # If this is a shared repository, this vfs may point to another
         # repository's .hg/store directory.
         self.svfs = None
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
         self.baseui = baseui
         self.ui = baseui.copy()
         self.ui.copy = baseui.copy # prevent copying repo configuration
         self.vfs = vfsmod.vfs(self.path, cacheaudited=True)
         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 = []
         try:
             self.ui.readconfig(self.vfs.join("hgrc"), self.root)
             self._loadextensions()
         except IOError:
             pass
 
         if featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in featuresetupfuncs:
                 if setupfunc.__module__ in extmods:
                     setupfunc(self.ui, self.supported)
         else:
             self.supported = self._basesupported
         color.setup(self.ui)
 
         # Add compression engines.
         for name in util.compengines:
             engine = util.compengines[name]
             if engine.revlogheader():
                 self.supported.add('exp-compression-%s' % name)
 
         if not self.vfs.isdir():
-            if create:
-                self.requirements = newreporequirements(self.ui)
-
-                if not self.wvfs.exists():
-                    self.wvfs.makedirs()
-                self.vfs.makedir(notindexed=True)
-
-                if 'store' in self.requirements:
-                    self.vfs.mkdir("store")
-
-                    # create an invalid changelog
-                    self.vfs.append(
-                        "00changelog.i",
-                        '\0\0\0\2' # represents revlogv2
-                        ' dummy changelog to prevent using the old repo layout'
-                    )
-            else:
-                try:
-                    self.vfs.stat()
-                except OSError as inst:
-                    if inst.errno != errno.ENOENT:
-                        raise
-                raise error.RepoError(_("repository %s not found") % path)
-        elif create:
-            raise error.RepoError(_("repository %s already exists") % path)
+            try:
+                self.vfs.stat()
+            except OSError as inst:
+                if inst.errno != errno.ENOENT:
+                    raise
+            raise error.RepoError(_("repository %s not found") % path)
         else:
             try:
                 self.requirements = scmutil.readrequires(
                         self.vfs, self.supported)
             except IOError as inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
         cachepath = self.vfs.join('cache')
         self.sharedpath = self.path
         try:
             sharedpath = self.vfs.read("sharedpath").rstrip('\n')
             if 'relshared' in self.requirements:
                 sharedpath = self.vfs.join(sharedpath)
             vfs = vfsmod.vfs(sharedpath, realpath=True)
             cachepath = vfs.join('cache')
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         if 'exp-sparse' in self.requirements and not sparse.enabled:
             raise error.RepoError(_('repository is using sparse feature but '
                                     'sparse is not enabled; enable the '
                                     '"sparse" extensions to access'))
 
         self.store = store.store(
             self.requirements, self.sharedpath,
             lambda base: vfsmod.vfs(base, cacheaudited=True))
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self.cachevfs = vfsmod.vfs(cachepath, cacheaudited=True)
         self.cachevfs.createmode = self.store.createmode
         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._applyopenerreqs()
-        if create:
-            self._writerequirements()
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = {}
         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=2, config="cache-vfs")
             if path.startswith('journal.'):
                 # journal is covered by 'lock'
                 if repo._currentlock(repo._lockref) is None:
                     repo.ui.develwarn('write with no lock: "%s"' % path,
                                       stacklevel=2, 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=2, 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=3)
             return ret
         return checksvfs
 
     def close(self):
         self._writecaches()
 
     def _loadextensions(self):
         extensions.loadall(self.ui)
 
     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 _applyopenerreqs(self):
         self.svfs.options = dict((r, 1) for r in self.requirements
                                            if r in self.openerreqs)
         # experimental config: format.chunkcachesize
         chunkcachesize = self.ui.configint('format', 'chunkcachesize')
         if chunkcachesize is not None:
             self.svfs.options['chunkcachesize'] = chunkcachesize
         # experimental config: format.manifestcachesize
         manifestcachesize = self.ui.configint('format', 'manifestcachesize')
         if manifestcachesize is not None:
             self.svfs.options['manifestcachesize'] = manifestcachesize
         deltabothparents = self.ui.configbool('storage',
             'revlog.optimize-delta-parent-choice')
         self.svfs.options['deltabothparents'] = deltabothparents
         self.svfs.options['lazydeltabase'] = not scmutil.gddeltaconfig(self.ui)
         chainspan = self.ui.configbytes('experimental', 'maxdeltachainspan')
         if 0 <= chainspan:
             self.svfs.options['maxdeltachainspan'] = chainspan
         mmapindexthreshold = self.ui.configbytes('experimental',
                                                  'mmapindexthreshold')
         if mmapindexthreshold is not None:
             self.svfs.options['mmapindexthreshold'] = mmapindexthreshold
         withsparseread = self.ui.configbool('experimental', 'sparse-read')
         srdensitythres = float(self.ui.config('experimental',
                                               'sparse-read.density-threshold'))
         srmingapsize = self.ui.configbytes('experimental',
                                            'sparse-read.min-gap-size')
         self.svfs.options['with-sparse-read'] = withsparseread
         self.svfs.options['sparse-read-density-threshold'] = srdensitythres
         self.svfs.options['sparse-read-min-gap-size'] = srmingapsize
         sparserevlog = SPARSEREVLOG_REQUIREMENT in self.requirements
         self.svfs.options['sparse-revlog'] = sparserevlog
         if sparserevlog:
             self.svfs.options['generaldelta'] = True
         maxchainlen = None
         if sparserevlog:
             maxchainlen = revlogconst.SPARSE_REVLOG_MAX_CHAIN_LENGTH
         # experimental config: format.maxchainlen
         maxchainlen = self.ui.configint('format', 'maxchainlen', maxchainlen)
         if maxchainlen is not None:
             self.svfs.options['maxchainlen'] = maxchainlen
 
         for r in self.requirements:
             if r.startswith('exp-compression-'):
                 self.svfs.options['compengine'] = r[len('exp-compression-'):]
 
         # TODO move "revlogv2" to openerreqs once finalized.
         if REVLOGV2_REQUIREMENT in self.requirements:
             self.svfs.options['revlogv2'] = True
 
     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))
 
     def _constructmanifest(self):
         # This is a temporary function while we migrate from manifest to
         # manifestlog. It allows bundlerepo and unionrepo to intercept the
         # manifest creation.
         return manifest.manifestrevlog(self.svfs)
 
     @storecache('00manifest.i')
     def manifestlog(self):
         return manifest.manifestlog(self.svfs, self)
 
     @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).
         """
         source = self
         if self.shared():
             from . import hg
             source = hg.sharedreposource(self)
         return narrowspec.load(source)
 
     @storecache(narrowspec.FILENAME)
     def _narrowmatch(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)
 
     # TODO(martinvonz): make this property-like instead?
     def narrowmatch(self):
         return self._narrowmatch
 
     def setnarrowpats(self, newincludes, newexcludes):
         target = self
         if self.shared():
             from . import hg
             target = hg.sharedreposource(self)
         narrowspec.save(target, 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 [context.changectx(self, i)
                     for i in pycompat.xrange(*changeid.indices(len(self)))
                     if i not in self.changelog.filteredrevs]
         try:
             return context.changectx(self, 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.
         '''
         expr = revsetlang.formatspec(expr, *args)
         m = revset.match(None, expr)
         return m(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
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.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'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
     @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 file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.svfs, f)
 
     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 can be a changeset revision, node, or tag.
            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} # 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')
                 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.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.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 = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             narrowspec.restorebackup(self, 'undo.narrowspec')
             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):
             # updating the unfiltered branchmap should refresh all the others,
             self.ui.debug('updating the branch cache\n')
             branchmap.updatecache(self.filtered('served'))
 
         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 '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._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, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in list(self._filecache.keys()):
             # dirstate is invalidated separately in invalidatedirstate()
             if k == '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
 
         wlock = lock = tr = None
         try:
             wlock = self.wlock()
             lock = self.lock() # for recent changelog (see issue4368)
 
             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)
                 tr = self.transaction('commit')
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
             tr.close()
 
         finally:
             lockmod.release(tr, lock, wlock)
 
         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().
         """
 
         tr = None
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             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 as inst:
                         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"))
                     mn = mctx.write(trp, linkrev,
                                     p1.manifestnode(), p2.manifestnode(),
                                     added, drop)
                 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])
             tr.close()
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @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):
-    return localrepository(ui, util.urllocalpath(path), create,
-                           intents=intents)
+    if create:
+        vfs = vfsmod.vfs(path, expandpath=True, realpath=True)
+
+        if vfs.exists('.hg'):
+            raise error.RepoError(_('repository %s already exists') % path)
+
+        createrepository(ui, vfs)
+
+    return localrepository(ui, util.urllocalpath(path), intents=intents)
 
 def islocal(path):
     return True
 
 def newreporequirements(ui):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     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('experimental', 'treemanifest'):
         requirements.add('treemanifest')
     # experimental config: format.sparse-revlog
     if ui.configbool('format', 'sparse-revlog'):
         requirements.add(SPARSEREVLOG_REQUIREMENT)
 
     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')
 
     return requirements
+
+def createrepository(ui, wdirvfs):
+    """Create a new repository in a vfs.
+
+    ``wdirvfs`` is a vfs instance pointing at the working directory.
+    ``requirements`` is a set of requirements for the new repository.
+    """
+    requirements = newreporequirements(ui)
+
+    if not wdirvfs.exists():
+        wdirvfs.makedirs()
+
+    hgvfs = vfsmod.vfs(wdirvfs.join(b'.hg'))
+    hgvfs.makedir(notindexed=True)
+
+    if b'store' in requirements:
+        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)

tests/test-status-inprocess.py

@@ -1,47 +1,47 b''
 #!/usr/bin/env python
 from __future__ import absolute_import, print_function
 
 import sys
 
 from mercurial import (
     commands,
     localrepo,
     ui as uimod,
 )
 
 print_ = print
 def print(*args, **kwargs):
     """print() wrapper that flushes stdout buffers to avoid py3 buffer issues
 
     We could also just write directly to sys.stdout.buffer the way the
     ui object will, but this was easier for porting the test.
     """
     print_(*args, **kwargs)
     sys.stdout.flush()
 
 u = uimod.ui.load()
 
 print('% creating repo')
-repo = localrepo.localrepository(u, b'.', create=True)
+repo = localrepo.instance(u, b'.', create=True)
 
 f = open('test.py', 'w')
 try:
     f.write('foo\n')
 finally:
     f.close
 
 print('% add and commit')
 commands.add(u, repo, b'test.py')
 commands.commit(u, repo, message=b'*')
 commands.status(u, repo, clean=True)
 
 
 print('% change')
 f = open('test.py', 'w')
 try:
     f.write('bar\n')
 finally:
     f.close()
 
 # this would return clean instead of changed before the fix
 commands.status(u, repo, clean=True, modified=True)