cleanup: say goodbye to manifestv2 format

This experiment was a bust: we'd hoped for smaller repository sizes,
but things got larger. Google ended up rolling out tree manifests in a
format that's compatible with the original manifest format, and I
believe Facebook is doing the same. This code was never implemented as
native speedups, so I'm pretty comfortable saying nobody is using the
experimental feature. Let's rip it out.

I noticed this code still kicking around because I was investigating a
repo corruption issue for timeless.

.. bc::

   Support for the experimental manifestv2 format has been removed, as
   it was never completed and failed to meet expectations.

Differential Revision: https://phab.mercurial-scm.org/D2393

mercurial/configitems.py

@@ -1,1311 +1,1308 b''
 # configitems.py - centralized declaration of configuration option
 #
 #  Copyright 2017 Pierre-Yves David <[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 functools
 import re
 
 from . import (
     encoding,
     error,
 )
 
 def loadconfigtable(ui, extname, configtable):
     """update config item known to the ui with the extension ones"""
     for section, items in sorted(configtable.items()):
         knownitems = ui._knownconfig.setdefault(section, itemregister())
         knownkeys = set(knownitems)
         newkeys = set(items)
         for key in sorted(knownkeys & newkeys):
             msg = "extension '%s' overwrite config item '%s.%s'"
             msg %= (extname, section, key)
             ui.develwarn(msg, config='warn-config')
 
         knownitems.update(items)
 
 class configitem(object):
     """represent a known config item
 
     :section: the official config section where to find this item,
        :name: the official name within the section,
     :default: default value for this item,
     :alias: optional list of tuples as alternatives,
     :generic: this is a generic definition, match name using regular expression.
     """
 
     def __init__(self, section, name, default=None, alias=(),
                  generic=False, priority=0):
         self.section = section
         self.name = name
         self.default = default
         self.alias = list(alias)
         self.generic = generic
         self.priority = priority
         self._re = None
         if generic:
             self._re = re.compile(self.name)
 
 class itemregister(dict):
     """A specialized dictionary that can handle wild-card selection"""
 
     def __init__(self):
         super(itemregister, self).__init__()
         self._generics = set()
 
     def update(self, other):
         super(itemregister, self).update(other)
         self._generics.update(other._generics)
 
     def __setitem__(self, key, item):
         super(itemregister, self).__setitem__(key, item)
         if item.generic:
             self._generics.add(item)
 
     def get(self, key):
         baseitem = super(itemregister, self).get(key)
         if baseitem is not None and not baseitem.generic:
             return baseitem
 
         # search for a matching generic item
         generics = sorted(self._generics, key=(lambda x: (x.priority, x.name)))
         for item in generics:
             # we use 'match' instead of 'search' to make the matching simpler
             # for people unfamiliar with regular expression. Having the match
             # rooted to the start of the string will produce less surprising
             # result for user writing simple regex for sub-attribute.
             #
             # For example using "color\..*" match produces an unsurprising
             # result, while using search could suddenly match apparently
             # unrelated configuration that happens to contains "color."
             # anywhere. This is a tradeoff where we favor requiring ".*" on
             # some match to avoid the need to prefix most pattern with "^".
             # The "^" seems more error prone.
             if item._re.match(key):
                 return item
 
         return None
 
 coreitems = {}
 
 def _register(configtable, *args, **kwargs):
     item = configitem(*args, **kwargs)
     section = configtable.setdefault(item.section, itemregister())
     if item.name in section:
         msg = "duplicated config item registration for '%s.%s'"
         raise error.ProgrammingError(msg % (item.section, item.name))
     section[item.name] = item
 
 # special value for case where the default is derived from other values
 dynamicdefault = object()
 
 # Registering actual config items
 
 def getitemregister(configtable):
     f = functools.partial(_register, configtable)
     # export pseudo enum as configitem.*
     f.dynamicdefault = dynamicdefault
     return f
 
 coreconfigitem = getitemregister(coreitems)
 
 coreconfigitem('alias', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('annotate', 'nodates',
     default=False,
 )
 coreconfigitem('annotate', 'showfunc',
     default=False,
 )
 coreconfigitem('annotate', 'unified',
     default=None,
 )
 coreconfigitem('annotate', 'git',
     default=False,
 )
 coreconfigitem('annotate', 'ignorews',
     default=False,
 )
 coreconfigitem('annotate', 'ignorewsamount',
     default=False,
 )
 coreconfigitem('annotate', 'ignoreblanklines',
     default=False,
 )
 coreconfigitem('annotate', 'ignorewseol',
     default=False,
 )
 coreconfigitem('annotate', 'nobinary',
     default=False,
 )
 coreconfigitem('annotate', 'noprefix',
     default=False,
 )
 coreconfigitem('auth', 'cookiefile',
     default=None,
 )
 # bookmarks.pushing: internal hack for discovery
 coreconfigitem('bookmarks', 'pushing',
     default=list,
 )
 # bundle.mainreporoot: internal hack for bundlerepo
 coreconfigitem('bundle', 'mainreporoot',
     default='',
 )
 # bundle.reorder: experimental config
 coreconfigitem('bundle', 'reorder',
     default='auto',
 )
 coreconfigitem('censor', 'policy',
     default='abort',
 )
 coreconfigitem('chgserver', 'idletimeout',
     default=3600,
 )
 coreconfigitem('chgserver', 'skiphash',
     default=False,
 )
 coreconfigitem('cmdserver', 'log',
     default=None,
 )
 coreconfigitem('color', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('color', 'mode',
     default='auto',
 )
 coreconfigitem('color', 'pagermode',
     default=dynamicdefault,
 )
 coreconfigitem('commands', 'show.aliasprefix',
     default=list,
 )
 coreconfigitem('commands', 'status.relative',
     default=False,
 )
 coreconfigitem('commands', 'status.skipstates',
     default=[],
 )
 coreconfigitem('commands', 'status.verbose',
     default=False,
 )
 coreconfigitem('commands', 'update.check',
     default=None,
     # Deprecated, remove after 4.4 release
     alias=[('experimental', 'updatecheck')]
 )
 coreconfigitem('commands', 'update.requiredest',
     default=False,
 )
 coreconfigitem('committemplate', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('convert', 'cvsps.cache',
     default=True,
 )
 coreconfigitem('convert', 'cvsps.fuzz',
     default=60,
 )
 coreconfigitem('convert', 'cvsps.logencoding',
     default=None,
 )
 coreconfigitem('convert', 'cvsps.mergefrom',
     default=None,
 )
 coreconfigitem('convert', 'cvsps.mergeto',
     default=None,
 )
 coreconfigitem('convert', 'git.committeractions',
     default=lambda: ['messagedifferent'],
 )
 coreconfigitem('convert', 'git.extrakeys',
     default=list,
 )
 coreconfigitem('convert', 'git.findcopiesharder',
     default=False,
 )
 coreconfigitem('convert', 'git.remoteprefix',
     default='remote',
 )
 coreconfigitem('convert', 'git.renamelimit',
     default=400,
 )
 coreconfigitem('convert', 'git.saverev',
     default=True,
 )
 coreconfigitem('convert', 'git.similarity',
     default=50,
 )
 coreconfigitem('convert', 'git.skipsubmodules',
     default=False,
 )
 coreconfigitem('convert', 'hg.clonebranches',
     default=False,
 )
 coreconfigitem('convert', 'hg.ignoreerrors',
     default=False,
 )
 coreconfigitem('convert', 'hg.revs',
     default=None,
 )
 coreconfigitem('convert', 'hg.saverev',
     default=False,
 )
 coreconfigitem('convert', 'hg.sourcename',
     default=None,
 )
 coreconfigitem('convert', 'hg.startrev',
     default=None,
 )
 coreconfigitem('convert', 'hg.tagsbranch',
     default='default',
 )
 coreconfigitem('convert', 'hg.usebranchnames',
     default=True,
 )
 coreconfigitem('convert', 'ignoreancestorcheck',
     default=False,
 )
 coreconfigitem('convert', 'localtimezone',
     default=False,
 )
 coreconfigitem('convert', 'p4.encoding',
     default=dynamicdefault,
 )
 coreconfigitem('convert', 'p4.startrev',
     default=0,
 )
 coreconfigitem('convert', 'skiptags',
     default=False,
 )
 coreconfigitem('convert', 'svn.debugsvnlog',
     default=True,
 )
 coreconfigitem('convert', 'svn.trunk',
     default=None,
 )
 coreconfigitem('convert', 'svn.tags',
     default=None,
 )
 coreconfigitem('convert', 'svn.branches',
     default=None,
 )
 coreconfigitem('convert', 'svn.startrev',
     default=0,
 )
 coreconfigitem('debug', 'dirstate.delaywrite',
     default=0,
 )
 coreconfigitem('defaults', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('devel', 'all-warnings',
     default=False,
 )
 coreconfigitem('devel', 'bundle2.debug',
     default=False,
 )
 coreconfigitem('devel', 'cache-vfs',
     default=None,
 )
 coreconfigitem('devel', 'check-locks',
     default=False,
 )
 coreconfigitem('devel', 'check-relroot',
     default=False,
 )
 coreconfigitem('devel', 'default-date',
     default=None,
 )
 coreconfigitem('devel', 'deprec-warn',
     default=False,
 )
 coreconfigitem('devel', 'disableloaddefaultcerts',
     default=False,
 )
 coreconfigitem('devel', 'warn-empty-changegroup',
     default=False,
 )
 coreconfigitem('devel', 'legacy.exchange',
     default=list,
 )
 coreconfigitem('devel', 'servercafile',
     default='',
 )
 coreconfigitem('devel', 'serverexactprotocol',
     default='',
 )
 coreconfigitem('devel', 'serverrequirecert',
     default=False,
 )
 coreconfigitem('devel', 'strip-obsmarkers',
     default=True,
 )
 coreconfigitem('devel', 'warn-config',
     default=None,
 )
 coreconfigitem('devel', 'warn-config-default',
     default=None,
 )
 coreconfigitem('devel', 'user.obsmarker',
     default=None,
 )
 coreconfigitem('devel', 'warn-config-unknown',
     default=None,
 )
 coreconfigitem('devel', 'debug.peer-request',
     default=False,
 )
 coreconfigitem('diff', 'nodates',
     default=False,
 )
 coreconfigitem('diff', 'showfunc',
     default=False,
 )
 coreconfigitem('diff', 'unified',
     default=None,
 )
 coreconfigitem('diff', 'git',
     default=False,
 )
 coreconfigitem('diff', 'ignorews',
     default=False,
 )
 coreconfigitem('diff', 'ignorewsamount',
     default=False,
 )
 coreconfigitem('diff', 'ignoreblanklines',
     default=False,
 )
 coreconfigitem('diff', 'ignorewseol',
     default=False,
 )
 coreconfigitem('diff', 'nobinary',
     default=False,
 )
 coreconfigitem('diff', 'noprefix',
     default=False,
 )
 coreconfigitem('email', 'bcc',
     default=None,
 )
 coreconfigitem('email', 'cc',
     default=None,
 )
 coreconfigitem('email', 'charsets',
     default=list,
 )
 coreconfigitem('email', 'from',
     default=None,
 )
 coreconfigitem('email', 'method',
     default='smtp',
 )
 coreconfigitem('email', 'reply-to',
     default=None,
 )
 coreconfigitem('email', 'to',
     default=None,
 )
 coreconfigitem('experimental', 'archivemetatemplate',
     default=dynamicdefault,
 )
 coreconfigitem('experimental', 'bundle-phases',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2-advertise',
     default=True,
 )
 coreconfigitem('experimental', 'bundle2-output-capture',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2.pushback',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2.stream',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2lazylocking',
     default=False,
 )
 coreconfigitem('experimental', 'bundlecomplevel',
     default=None,
 )
 coreconfigitem('experimental', 'changegroup3',
     default=False,
 )
 coreconfigitem('experimental', 'clientcompressionengines',
     default=list,
 )
 coreconfigitem('experimental', 'copytrace',
     default='on',
 )
 coreconfigitem('experimental', 'copytrace.movecandidateslimit',
     default=100,
 )
 coreconfigitem('experimental', 'copytrace.sourcecommitlimit',
     default=100,
 )
 coreconfigitem('experimental', 'crecordtest',
     default=None,
 )
 coreconfigitem('experimental', 'directaccess',
     default=False,
 )
 coreconfigitem('experimental', 'directaccess.revnums',
     default=False,
 )
 coreconfigitem('experimental', 'editortmpinhg',
     default=False,
 )
 coreconfigitem('experimental', 'evolution',
     default=list,
 )
 coreconfigitem('experimental', 'evolution.allowdivergence',
     default=False,
     alias=[('experimental', 'allowdivergence')]
 )
 coreconfigitem('experimental', 'evolution.allowunstable',
     default=None,
 )
 coreconfigitem('experimental', 'evolution.createmarkers',
     default=None,
 )
 coreconfigitem('experimental', 'evolution.effect-flags',
     default=True,
     alias=[('experimental', 'effect-flags')]
 )
 coreconfigitem('experimental', 'evolution.exchange',
     default=None,
 )
 coreconfigitem('experimental', 'evolution.bundle-obsmarker',
     default=False,
 )
 coreconfigitem('experimental', 'evolution.report-instabilities',
     default=True,
 )
 coreconfigitem('experimental', 'evolution.track-operation',
     default=True,
 )
 coreconfigitem('experimental', 'worddiff',
     default=False,
 )
 coreconfigitem('experimental', 'maxdeltachainspan',
     default=-1,
 )
 coreconfigitem('experimental', 'mmapindexthreshold',
     default=None,
 )
 coreconfigitem('experimental', 'nonnormalparanoidcheck',
     default=False,
 )
 coreconfigitem('experimental', 'exportableenviron',
     default=list,
 )
 coreconfigitem('experimental', 'extendedheader.index',
     default=None,
 )
 coreconfigitem('experimental', 'extendedheader.similarity',
     default=False,
 )
 coreconfigitem('experimental', 'format.compression',
     default='zlib',
 )
 coreconfigitem('experimental', 'graphshorten',
     default=False,
 )
 coreconfigitem('experimental', 'graphstyle.parent',
     default=dynamicdefault,
 )
 coreconfigitem('experimental', 'graphstyle.missing',
     default=dynamicdefault,
 )
 coreconfigitem('experimental', 'graphstyle.grandparent',
     default=dynamicdefault,
 )
 coreconfigitem('experimental', 'hook-track-tags',
     default=False,
 )
 coreconfigitem('experimental', 'httppostargs',
     default=False,
 )
-coreconfigitem('experimental', 'manifestv2',
-    default=False,
-)
 coreconfigitem('experimental', 'mergedriver',
     default=None,
 )
 coreconfigitem('experimental', 'obsmarkers-exchange-debug',
     default=False,
 )
 coreconfigitem('experimental', 'remotenames',
     default=False,
 )
 coreconfigitem('experimental', 'revlogv2',
     default=None,
 )
 coreconfigitem('experimental', 'single-head-per-branch',
     default=False,
 )
 coreconfigitem('experimental', 'sshserver.support-v2',
     default=False,
 )
 coreconfigitem('experimental', 'spacemovesdown',
     default=False,
 )
 coreconfigitem('experimental', 'sparse-read',
     default=False,
 )
 coreconfigitem('experimental', 'sparse-read.density-threshold',
     default=0.25,
 )
 coreconfigitem('experimental', 'sparse-read.min-gap-size',
     default='256K',
 )
 coreconfigitem('experimental', 'treemanifest',
     default=False,
 )
 coreconfigitem('experimental', 'update.atomic-file',
     default=False,
 )
 coreconfigitem('experimental', 'sshpeer.advertise-v2',
     default=False,
 )
 coreconfigitem('extensions', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('extdata', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('format', 'aggressivemergedeltas',
     default=False,
 )
 coreconfigitem('format', 'chunkcachesize',
     default=None,
 )
 coreconfigitem('format', 'dotencode',
     default=True,
 )
 coreconfigitem('format', 'generaldelta',
     default=False,
 )
 coreconfigitem('format', 'manifestcachesize',
     default=None,
 )
 coreconfigitem('format', 'maxchainlen',
     default=None,
 )
 coreconfigitem('format', 'obsstore-version',
     default=None,
 )
 coreconfigitem('format', 'usefncache',
     default=True,
 )
 coreconfigitem('format', 'usegeneraldelta',
     default=True,
 )
 coreconfigitem('format', 'usestore',
     default=True,
 )
 coreconfigitem('fsmonitor', 'warn_when_unused',
     default=True,
 )
 coreconfigitem('fsmonitor', 'warn_update_file_count',
     default=50000,
 )
 coreconfigitem('hooks', '.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem('hgweb-paths', '.*',
     default=list,
     generic=True,
 )
 coreconfigitem('hostfingerprints', '.*',
     default=list,
     generic=True,
 )
 coreconfigitem('hostsecurity', 'ciphers',
     default=None,
 )
 coreconfigitem('hostsecurity', 'disabletls10warning',
     default=False,
 )
 coreconfigitem('hostsecurity', 'minimumprotocol',
     default=dynamicdefault,
 )
 coreconfigitem('hostsecurity', '.*:minimumprotocol$',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem('hostsecurity', '.*:ciphers$',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem('hostsecurity', '.*:fingerprints$',
     default=list,
     generic=True,
 )
 coreconfigitem('hostsecurity', '.*:verifycertsfile$',
     default=None,
     generic=True,
 )
 
 coreconfigitem('http_proxy', 'always',
     default=False,
 )
 coreconfigitem('http_proxy', 'host',
     default=None,
 )
 coreconfigitem('http_proxy', 'no',
     default=list,
 )
 coreconfigitem('http_proxy', 'passwd',
     default=None,
 )
 coreconfigitem('http_proxy', 'user',
     default=None,
 )
 coreconfigitem('logtoprocess', 'commandexception',
     default=None,
 )
 coreconfigitem('logtoprocess', 'commandfinish',
     default=None,
 )
 coreconfigitem('logtoprocess', 'command',
     default=None,
 )
 coreconfigitem('logtoprocess', 'develwarn',
     default=None,
 )
 coreconfigitem('logtoprocess', 'uiblocked',
     default=None,
 )
 coreconfigitem('merge', 'checkunknown',
     default='abort',
 )
 coreconfigitem('merge', 'checkignored',
     default='abort',
 )
 coreconfigitem('experimental', 'merge.checkpathconflicts',
     default=False,
 )
 coreconfigitem('merge', 'followcopies',
     default=True,
 )
 coreconfigitem('merge', 'on-failure',
     default='continue',
 )
 coreconfigitem('merge', 'preferancestor',
         default=lambda: ['*'],
 )
 coreconfigitem('merge-tools', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('merge-tools', br'.*\.args$',
     default="$local $base $other",
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.binary$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.check$',
     default=list,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.checkchanged$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.executable$',
     default=dynamicdefault,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.fixeol$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.gui$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.mergemarkers$',
     default='basic',
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.mergemarkertemplate$',
     default=dynamicdefault,  # take from ui.mergemarkertemplate
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.priority$',
     default=0,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.premerge$',
     default=dynamicdefault,
     generic=True,
     priority=-1,
 )
 coreconfigitem('merge-tools', br'.*\.symlink$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem('pager', 'attend-.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem('pager', 'ignore',
     default=list,
 )
 coreconfigitem('pager', 'pager',
     default=dynamicdefault,
 )
 coreconfigitem('patch', 'eol',
     default='strict',
 )
 coreconfigitem('patch', 'fuzz',
     default=2,
 )
 coreconfigitem('paths', 'default',
     default=None,
 )
 coreconfigitem('paths', 'default-push',
     default=None,
 )
 coreconfigitem('paths', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('phases', 'checksubrepos',
     default='follow',
 )
 coreconfigitem('phases', 'new-commit',
     default='draft',
 )
 coreconfigitem('phases', 'publish',
     default=True,
 )
 coreconfigitem('profiling', 'enabled',
     default=False,
 )
 coreconfigitem('profiling', 'format',
     default='text',
 )
 coreconfigitem('profiling', 'freq',
     default=1000,
 )
 coreconfigitem('profiling', 'limit',
     default=30,
 )
 coreconfigitem('profiling', 'nested',
     default=0,
 )
 coreconfigitem('profiling', 'output',
     default=None,
 )
 coreconfigitem('profiling', 'showmax',
     default=0.999,
 )
 coreconfigitem('profiling', 'showmin',
     default=dynamicdefault,
 )
 coreconfigitem('profiling', 'sort',
     default='inlinetime',
 )
 coreconfigitem('profiling', 'statformat',
     default='hotpath',
 )
 coreconfigitem('profiling', 'type',
     default='stat',
 )
 coreconfigitem('progress', 'assume-tty',
     default=False,
 )
 coreconfigitem('progress', 'changedelay',
     default=1,
 )
 coreconfigitem('progress', 'clear-complete',
     default=True,
 )
 coreconfigitem('progress', 'debug',
     default=False,
 )
 coreconfigitem('progress', 'delay',
     default=3,
 )
 coreconfigitem('progress', 'disable',
     default=False,
 )
 coreconfigitem('progress', 'estimateinterval',
     default=60.0,
 )
 coreconfigitem('progress', 'format',
     default=lambda: ['topic', 'bar', 'number', 'estimate'],
 )
 coreconfigitem('progress', 'refresh',
     default=0.1,
 )
 coreconfigitem('progress', 'width',
     default=dynamicdefault,
 )
 coreconfigitem('push', 'pushvars.server',
     default=False,
 )
 coreconfigitem('server', 'bookmarks-pushkey-compat',
     default=True,
 )
 coreconfigitem('server', 'bundle1',
     default=True,
 )
 coreconfigitem('server', 'bundle1gd',
     default=None,
 )
 coreconfigitem('server', 'bundle1.pull',
     default=None,
 )
 coreconfigitem('server', 'bundle1gd.pull',
     default=None,
 )
 coreconfigitem('server', 'bundle1.push',
     default=None,
 )
 coreconfigitem('server', 'bundle1gd.push',
     default=None,
 )
 coreconfigitem('server', 'compressionengines',
     default=list,
 )
 coreconfigitem('server', 'concurrent-push-mode',
     default='strict',
 )
 coreconfigitem('server', 'disablefullbundle',
     default=False,
 )
 coreconfigitem('server', 'maxhttpheaderlen',
     default=1024,
 )
 coreconfigitem('server', 'preferuncompressed',
     default=False,
 )
 coreconfigitem('server', 'uncompressed',
     default=True,
 )
 coreconfigitem('server', 'uncompressedallowsecret',
     default=False,
 )
 coreconfigitem('server', 'validate',
     default=False,
 )
 coreconfigitem('server', 'zliblevel',
     default=-1,
 )
 coreconfigitem('share', 'pool',
     default=None,
 )
 coreconfigitem('share', 'poolnaming',
     default='identity',
 )
 coreconfigitem('smtp', 'host',
     default=None,
 )
 coreconfigitem('smtp', 'local_hostname',
     default=None,
 )
 coreconfigitem('smtp', 'password',
     default=None,
 )
 coreconfigitem('smtp', 'port',
     default=dynamicdefault,
 )
 coreconfigitem('smtp', 'tls',
     default='none',
 )
 coreconfigitem('smtp', 'username',
     default=None,
 )
 coreconfigitem('sparse', 'missingwarning',
     default=True,
 )
 coreconfigitem('subrepos', 'allowed',
     default=dynamicdefault,  # to make backporting simpler
 )
 coreconfigitem('subrepos', 'hg:allowed',
     default=dynamicdefault,
 )
 coreconfigitem('subrepos', 'git:allowed',
     default=dynamicdefault,
 )
 coreconfigitem('subrepos', 'svn:allowed',
     default=dynamicdefault,
 )
 coreconfigitem('templates', '.*',
     default=None,
     generic=True,
 )
 coreconfigitem('trusted', 'groups',
     default=list,
 )
 coreconfigitem('trusted', 'users',
     default=list,
 )
 coreconfigitem('ui', '_usedassubrepo',
     default=False,
 )
 coreconfigitem('ui', 'allowemptycommit',
     default=False,
 )
 coreconfigitem('ui', 'archivemeta',
     default=True,
 )
 coreconfigitem('ui', 'askusername',
     default=False,
 )
 coreconfigitem('ui', 'clonebundlefallback',
     default=False,
 )
 coreconfigitem('ui', 'clonebundleprefers',
     default=list,
 )
 coreconfigitem('ui', 'clonebundles',
     default=True,
 )
 coreconfigitem('ui', 'color',
     default='auto',
 )
 coreconfigitem('ui', 'commitsubrepos',
     default=False,
 )
 coreconfigitem('ui', 'debug',
     default=False,
 )
 coreconfigitem('ui', 'debugger',
     default=None,
 )
 coreconfigitem('ui', 'editor',
     default=dynamicdefault,
 )
 coreconfigitem('ui', 'fallbackencoding',
     default=None,
 )
 coreconfigitem('ui', 'forcecwd',
     default=None,
 )
 coreconfigitem('ui', 'forcemerge',
     default=None,
 )
 coreconfigitem('ui', 'formatdebug',
     default=False,
 )
 coreconfigitem('ui', 'formatjson',
     default=False,
 )
 coreconfigitem('ui', 'formatted',
     default=None,
 )
 coreconfigitem('ui', 'graphnodetemplate',
     default=None,
 )
 coreconfigitem('ui', 'http2debuglevel',
     default=None,
 )
 coreconfigitem('ui', 'interactive',
     default=None,
 )
 coreconfigitem('ui', 'interface',
     default=None,
 )
 coreconfigitem('ui', 'interface.chunkselector',
     default=None,
 )
 coreconfigitem('ui', 'logblockedtimes',
     default=False,
 )
 coreconfigitem('ui', 'logtemplate',
     default=None,
 )
 coreconfigitem('ui', 'merge',
     default=None,
 )
 coreconfigitem('ui', 'mergemarkers',
     default='basic',
 )
 coreconfigitem('ui', 'mergemarkertemplate',
     default=('{node|short} '
             '{ifeq(tags, "tip", "", '
             'ifeq(tags, "", "", "{tags} "))}'
             '{if(bookmarks, "{bookmarks} ")}'
             '{ifeq(branch, "default", "", "{branch} ")}'
             '- {author|user}: {desc|firstline}')
 )
 coreconfigitem('ui', 'nontty',
     default=False,
 )
 coreconfigitem('ui', 'origbackuppath',
     default=None,
 )
 coreconfigitem('ui', 'paginate',
     default=True,
 )
 coreconfigitem('ui', 'patch',
     default=None,
 )
 coreconfigitem('ui', 'portablefilenames',
     default='warn',
 )
 coreconfigitem('ui', 'promptecho',
     default=False,
 )
 coreconfigitem('ui', 'quiet',
     default=False,
 )
 coreconfigitem('ui', 'quietbookmarkmove',
     default=False,
 )
 coreconfigitem('ui', 'remotecmd',
     default='hg',
 )
 coreconfigitem('ui', 'report_untrusted',
     default=True,
 )
 coreconfigitem('ui', 'rollback',
     default=True,
 )
 coreconfigitem('ui', 'slash',
     default=False,
 )
 coreconfigitem('ui', 'ssh',
     default='ssh',
 )
 coreconfigitem('ui', 'ssherrorhint',
     default=None,
 )
 coreconfigitem('ui', 'statuscopies',
     default=False,
 )
 coreconfigitem('ui', 'strict',
     default=False,
 )
 coreconfigitem('ui', 'style',
     default='',
 )
 coreconfigitem('ui', 'supportcontact',
     default=None,
 )
 coreconfigitem('ui', 'textwidth',
     default=78,
 )
 coreconfigitem('ui', 'timeout',
     default='600',
 )
 coreconfigitem('ui', 'timeout.warn',
     default=0,
 )
 coreconfigitem('ui', 'traceback',
     default=False,
 )
 coreconfigitem('ui', 'tweakdefaults',
     default=False,
 )
 coreconfigitem('ui', 'usehttp2',
     default=False,
 )
 coreconfigitem('ui', 'username',
     alias=[('ui', 'user')]
 )
 coreconfigitem('ui', 'verbose',
     default=False,
 )
 coreconfigitem('verify', 'skipflags',
     default=None,
 )
 coreconfigitem('web', 'allowbz2',
     default=False,
 )
 coreconfigitem('web', 'allowgz',
     default=False,
 )
 coreconfigitem('web', 'allow-pull',
     alias=[('web', 'allowpull')],
     default=True,
 )
 coreconfigitem('web', 'allow-push',
     alias=[('web', 'allow_push')],
     default=list,
 )
 coreconfigitem('web', 'allowzip',
     default=False,
 )
 coreconfigitem('web', 'archivesubrepos',
     default=False,
 )
 coreconfigitem('web', 'cache',
     default=True,
 )
 coreconfigitem('web', 'contact',
     default=None,
 )
 coreconfigitem('web', 'deny_push',
     default=list,
 )
 coreconfigitem('web', 'guessmime',
     default=False,
 )
 coreconfigitem('web', 'hidden',
     default=False,
 )
 coreconfigitem('web', 'labels',
     default=list,
 )
 coreconfigitem('web', 'logoimg',
     default='hglogo.png',
 )
 coreconfigitem('web', 'logourl',
     default='https://mercurial-scm.org/',
 )
 coreconfigitem('web', 'accesslog',
     default='-',
 )
 coreconfigitem('web', 'address',
     default='',
 )
 coreconfigitem('web', 'allow_archive',
     default=list,
 )
 coreconfigitem('web', 'allow_read',
     default=list,
 )
 coreconfigitem('web', 'baseurl',
     default=None,
 )
 coreconfigitem('web', 'cacerts',
     default=None,
 )
 coreconfigitem('web', 'certificate',
     default=None,
 )
 coreconfigitem('web', 'collapse',
     default=False,
 )
 coreconfigitem('web', 'csp',
     default=None,
 )
 coreconfigitem('web', 'deny_read',
     default=list,
 )
 coreconfigitem('web', 'descend',
     default=True,
 )
 coreconfigitem('web', 'description',
     default="",
 )
 coreconfigitem('web', 'encoding',
     default=lambda: encoding.encoding,
 )
 coreconfigitem('web', 'errorlog',
     default='-',
 )
 coreconfigitem('web', 'ipv6',
     default=False,
 )
 coreconfigitem('web', 'maxchanges',
     default=10,
 )
 coreconfigitem('web', 'maxfiles',
     default=10,
 )
 coreconfigitem('web', 'maxshortchanges',
     default=60,
 )
 coreconfigitem('web', 'motd',
     default='',
 )
 coreconfigitem('web', 'name',
     default=dynamicdefault,
 )
 coreconfigitem('web', 'port',
     default=8000,
 )
 coreconfigitem('web', 'prefix',
     default='',
 )
 coreconfigitem('web', 'push_ssl',
     default=True,
 )
 coreconfigitem('web', 'refreshinterval',
     default=20,
 )
 coreconfigitem('web', 'staticurl',
     default=None,
 )
 coreconfigitem('web', 'stripes',
     default=1,
 )
 coreconfigitem('web', 'style',
     default='paper',
 )
 coreconfigitem('web', 'templates',
     default=None,
 )
 coreconfigitem('web', 'view',
     default='served',
 )
 coreconfigitem('worker', 'backgroundclose',
     default=dynamicdefault,
 )
 # Windows defaults to a limit of 512 open files. A buffer of 128
 # should give us enough headway.
 coreconfigitem('worker', 'backgroundclosemaxqueue',
     default=384,
 )
 coreconfigitem('worker', 'backgroundcloseminfilecount',
     default=2048,
 )
 coreconfigitem('worker', 'backgroundclosethreadcount',
     default=4,
 )
 coreconfigitem('worker', 'enabled',
     default=True,
 )
 coreconfigitem('worker', 'numcpus',
     default=None,
 )
 
 # Rebase related configuration moved to core because other extension are doing
 # strange things. For example, shelve import the extensions to reuse some bit
 # without formally loading it.
 coreconfigitem('commands', 'rebase.requiredest',
             default=False,
 )
 coreconfigitem('experimental', 'rebaseskipobsolete',
     default=True,
 )
 coreconfigitem('rebase', 'singletransaction',
     default=False,
 )
 coreconfigitem('rebase', 'experimental.inmemory',
     default=False,
 )

mercurial/help/internals/requirements.txt

@@ -1,130 +1,131 b''
-
 Repositories contain a file (``.hg/requires``) containing a list of
 features/capabilities that are *required* for clients to interface
 with the repository. This file has been present in Mercurial since
 version 0.9.2 (released December 2006).
 
 One of the first things clients do when opening a repository is read
 ``.hg/requires`` and verify that all listed requirements are supported,
 aborting if not. Requirements are therefore a strong mechanism to
 prevent incompatible clients from reading from unknown repository
 formats or even corrupting them by writing to them.
 
 Extensions may add requirements. When they do this, clients not running
 an extension will be unable to read from repositories.
 
 The following sections describe the requirements defined by the
 Mercurial core distribution.
 
 revlogv1
 ========
 
 When present, revlogs are version 1 (RevlogNG). RevlogNG was introduced
 in 2006. The ``revlogv1`` requirement has been enabled by default
 since the ``requires`` file was introduced in Mercurial 0.9.2.
 
 If this requirement is not present, version 0 revlogs are assumed.
 
 store
 =====
 
 The *store* repository layout should be used.
 
 This requirement has been enabled by default since the ``requires`` file
 was introduced in Mercurial 0.9.2.
 
 fncache
 =======
 
 The *fncache* repository layout should be used.
 
 The *fncache* layout hash encodes filenames with long paths and
 encodes reserved filenames.
 
 This requirement is enabled by default when the *store* requirement is
 enabled (which is the default behavior). It was introduced in Mercurial
 1.1 (released December 2008).
 
 shared
 ======
 
 Denotes that the store for a repository is shared from another location
 (defined by the ``.hg/sharedpath`` file).
 
 This requirement is set when a repository is created via :hg:`share`.
 
 The requirement was added in Mercurial 1.3 (released July 2009).
 
 relshared
 =========
 
 Derivative of ``shared``; the location of the store is relative to the
 store of this repository.
 
 This requirement is set when a repository is created via :hg:`share`
 using the ``--relative`` option.
 
 The requirement was added in Mercurial 4.2 (released May 2017).
 
 dotencode
 =========
 
 The *dotencode* repository layout should be used.
 
 The *dotencode* layout encodes the first period or space in filenames
 to prevent issues on OS X and Windows.
 
 This requirement is enabled by default when the *store* requirement
 is enabled (which is the default behavior). It was introduced in
 Mercurial 1.7 (released November 2010).
 
 parentdelta
 ===========
 
 Denotes a revlog delta encoding format that was experimental and
 replaced by *generaldelta*. It should not be seen in the wild because
 it was never enabled by default.
 
 This requirement was added in Mercurial 1.7 and removed in Mercurial
 1.9.
 
 generaldelta
 ============
 
 Revlogs should be created with the *generaldelta* flag enabled. The
 generaldelta flag will cause deltas to be encoded against a parent
 revision instead of the previous revision in the revlog.
 
 Support for this requirement was added in Mercurial 1.9 (released
 July 2011). The requirement was disabled on new repositories by
 default until Mercurial 3.7 (released February 2016).
 
 manifestv2
 ==========
 
 Denotes that version 2 of manifests are being used.
 
 Support for this requirement was added in Mercurial 3.4 (released
-May 2015). The requirement is currently experimental and is disabled
-by default.
+May 2015). The new format failed to meet expectations and support
+for the format and requirement were removed in Mercurial 4.6
+(released May 2018) since the feature never graduated frome experiment
+status.
 
 treemanifest
 ============
 
 Denotes that tree manifests are being used. Tree manifests are
 one manifest per directory (as opposed to a single flat manifest).
 
 Support for this requirement was added in Mercurial 3.4 (released
 August 2015). The requirement is currently experimental and is
 disabled by default.
 
 exp-sparse
 ==========
 
 The working directory is sparse (only contains a subset of files).
 
 Support for this requirement was added in Mercurial 4.3 (released
 August 2017). This requirement and feature are experimental and may
 disappear in a future Mercurial release. The requirement will only
 be present on repositories that have opted in to a sparse working
 directory.

mercurial/localrepo.py

@@ -1,2274 +1,2275 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 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,
     obsolete,
     pathutil,
     peer,
     phases,
     pushkey,
     pycompat,
     repository,
     repoview,
     revset,
     revsetlang,
     scmutil,
     sparse,
     store,
     subrepoutil,
     tags as tagsmod,
     transaction,
     txnutil,
     util,
     vfs as vfsmod,
 )
 
 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'})
 
 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.
 
     @util.propertycache
     def ui(self):
         return self._ui
 
     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 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, three, four, 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, cg, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 cg = exchange.readbundle(self.ui, cg, None)
                 ret = exchange.unbundle(self._repo, cg, 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:'), str(exc))
 
     # End of _basewirecommands interface.
 
     # Begin of peer interface.
 
     def iterbatch(self):
         return peer.localiterbatcher(self)
 
     # End of peer interface.
 
 class locallegacypeer(repository.legacypeer, 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, basenodes, source):
         outgoing = discovery.outgoing(self._repo, missingroots=basenodes,
                                       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'
 
 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',
-        'manifestv2',
         REVLOGV2_REQUIREMENT,
     }
     _basesupported = supportedformats | {
         'store',
         'fncache',
         'shared',
         'relshared',
         'dotencode',
         'exp-sparse',
     }
     openerreqs = {
         'revlogv1',
         'generaldelta',
         'treemanifest',
-        'manifestv2',
     }
 
     # a list of (ui, featureset) functions.
     # only functions defined in module of enabled extensions are invoked
     featuresetupfuncs = set()
 
     # 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):
         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
         # This is only used by context.workingctx.match in order to
         # detect files in subrepos.
         self.auditor = pathutil.pathauditor(
             self.root, callback=self._checknested)
         # This is only used by context.basectx.match in order to detect
         # files in subrepos.
         self.nofsauditor = pathutil.pathauditor(
             self.root, callback=self._checknested, realfs=False, cached=True)
         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 self.featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in self.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)
 
                 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:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % 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.maxchainlen
         maxchainlen = self.ui.configint('format', 'maxchainlen')
         if maxchainlen is not None:
             self.svfs.options['maxchainlen'] = maxchainlen
         # experimental config: format.manifestcachesize
         manifestcachesize = self.ui.configint('format', 'manifestcachesize')
         if manifestcachesize is not None:
             self.svfs.options['manifestcachesize'] = manifestcachesize
         # experimental config: format.aggressivemergedeltas
         aggressivemergedeltas = self.ui.configbool('format',
                                                    'aggressivemergedeltas')
         self.svfs.options['aggressivemergedeltas'] = aggressivemergedeltas
         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
 
         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)
 
     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):
         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
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         if isinstance(changeid, slice):
             # wdirrev isn't contiguous so the slice shouldn't include it
             return [context.changectx(self, i)
                     for i in 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.LookupError 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, repo=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"""
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     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 self[key].node()
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[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 changectx(self, changeid):
         return self[changeid]
 
     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):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     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: util.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()
 
         # 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
                 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)
         tr.changes['revs'] = xrange(0, 0)
         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')
         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()
 
             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):
         """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 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['revs']:
             # updating the unfiltered branchmap should refresh all the others,
             self.ui.debug('updating the branch cache\n')
             branchmap.updatecache(self.filtered('served'))
 
     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")
 
         l = lockmod.trylock(self.ui, vfs, lockname, timeout, warntimeout,
                             releasefn=releasefn,
                             acquirefn=acquirefn, desc=desc,
                             inheritchecker=inheritchecker,
                             parentlock=parentlock)
         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.
         """
 
         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
                 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
                 self.ui.note(_("committing manifest\n"))
                 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]
                 mn = mctx.write(trp, linkrev,
                                 p1.manifestnode(), p2.manifestnode(),
                                 added, drop)
                 files = changed + removed
             else:
                 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['namespace'] = namespace
             hookargs['key'] = key
             hookargs['old'] = old
             hookargs['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, three, four, 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):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True
 
 def newreporequirements(repo):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     ui = repo.ui
     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')
-    if ui.configbool('experimental', 'manifestv2'):
-        requirements.add('manifestv2')
 
     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)
 
     return requirements

mercurial/manifest.py

@@ -1,1649 +1,1573 b''
 # manifest.py - manifest revision 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 heapq
 import itertools
-import os
 import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
 )
 from . import (
     error,
     mdiff,
     policy,
     revlog,
     util,
 )
 
 parsers = policy.importmod(r'parsers')
 propertycache = util.propertycache
 
-def _parsev1(data):
+def _parse(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1:] != '\n':
         raise ValueError('Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError('Manifest lines not in sorted order.')
         prev = l
         f, n = l.split('\0')
         if len(n) > 40:
             yield f, bin(n[:40]), n[40:]
         else:
             yield f, bin(n), ''
 
-def _parsev2(data):
-    metadataend = data.find('\n')
-    # Just ignore metadata for now
-    pos = metadataend + 1
-    prevf = ''
-    while pos < len(data):
-        end = data.find('\n', pos + 1) # +1 to skip stem length byte
-        if end == -1:
-            raise ValueError('Manifest ended with incomplete file entry.')
-        stemlen = ord(data[pos:pos + 1])
-        items = data[pos + 1:end].split('\0')
-        f = prevf[:stemlen] + items[0]
-        if prevf > f:
-            raise ValueError('Manifest entries not in sorted order.')
-        fl = items[1]
-        # Just ignore metadata (items[2:] for now)
-        n = data[end + 1:end + 21]
-        yield f, n, fl
-        pos = end + 22
-        prevf = f
-
-def _parse(data):
-    """Generates (path, node, flags) tuples from a manifest text"""
-    if data.startswith('\0'):
-        return iter(_parsev2(data))
-    else:
-        return iter(_parsev1(data))
-
-def _text(it, usemanifestv2):
-    """Given an iterator over (path, node, flags) tuples, returns a manifest
-    text"""
-    if usemanifestv2:
-        return _textv2(it)
-    else:
-        return _textv1(it)
-
-def _textv1(it):
+def _text(it):
     files = []
     lines = []
     _hex = revlog.hex
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append("%s\0%s%s\n" % (f, _hex(n), fl))
 
     _checkforbidden(files)
     return ''.join(lines)
 
-def _textv2(it):
-    files = []
-    lines = ['\0\n']
-    prevf = ''
-    for f, n, fl in it:
-        files.append(f)
-        stem = os.path.commonprefix([prevf, f])
-        stemlen = min(len(stem), 255)
-        lines.append("%c%s\0%s\n%s\n" % (stemlen, f[stemlen:], fl, n))
-        prevf = f
-    _checkforbidden(files)
-    return ''.join(lines)
-
 class lazymanifestiter(object):
     def __init__(self, lm):
         self.pos = 0
         self.lm = lm
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data[0]
         self.pos += 1
         zeropos = data.find('\x00', pos)
         return data[pos:zeropos]
 
     __next__ = next
 
 class lazymanifestiterentries(object):
     def __init__(self, lm):
         self.lm = lm
         self.pos = 0
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data
         zeropos = data.find('\x00', pos)
         hashval = unhexlify(data, self.lm.extrainfo[self.pos],
                             zeropos + 1, 40)
         flags = self.lm._getflags(data, self.pos, zeropos)
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
     __next__ = next
 
 def unhexlify(data, extra, pos, length):
     s = bin(data[pos:pos + length])
     if extra:
         s += chr(extra & 0xff)
     return s
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 class _lazymanifest(object):
     def __init__(self, data, positions=None, extrainfo=None, extradata=None):
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
 
     def findlines(self, data):
         if not data:
             return []
         pos = data.find("\n")
         if pos == -1 or data[-1:] != '\n':
             raise ValueError("Manifest did not end in a newline.")
         positions = [0]
         prev = data[:data.find('\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1:data.find('\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError("Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find("\n", pos + 1)
         return positions
 
     def _get(self, index):
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos):
         if pos >= 0:
             return self.data[pos:self.data.find('\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key):
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key):
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last)//2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key):
         return self.bsearch(key) != -1
 
     def _getflags(self, data, needle, pos):
         start = pos + 41
         end = data.find("\n", start)
         if end == -1:
             end = len(data) - 1
         if start == end:
             return ''
         return self.data[start:end]
 
     def __getitem__(self, key):
         if not isinstance(key, bytes):
             raise TypeError("getitem: manifest keys must be a bytes.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             return (data[1], data[2])
         zeropos = data.find('\x00', pos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, 40)
         flags = self._getflags(data, needle, zeropos)
         return (hashval, flags)
 
     def __delitem__(self, key):
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1:]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
         if cur >= 0:
             self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]
 
     def __setitem__(self, key, value):
         if not isinstance(key, bytes):
             raise TypeError("setitem: manifest keys must be a byte string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError("Manifest values must be a tuple of (node, flags).")
         hashval = value[0]
         if not isinstance(hashval, bytes) or not 20 <= len(hashval) <= 22:
             raise TypeError("node must be a 20-byte byte string")
         flags = value[1]
         if len(hashval) == 22:
             hashval = hashval[:-1]
         if not isinstance(flags, bytes) or len(flags) > 1:
             raise TypeError("flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (self.positions[:needle] + [-len(self.extradata)]
                               + self.positions[needle:])
             self.extrainfo = (self.extrainfo[:needle] + [0] +
                               self.extrainfo[needle:])
 
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(self.data, self.positions, self.extrainfo,
             self.extradata)
 
     def _compact(self):
         # hopefully not called TOO often
         if len(self.extradata) == 0:
             return
         l = []
         last_cut = 0
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find('\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     if len(t[1]) > 20:
                         self.extrainfo[i] = ord(t[1][21])
                     offset += len(l[-1])
                     i += 1
         self.data = ''.join(l)
         self.extradata = []
 
     def _pack(self, d):
         return d[0] + '\x00' + hex(d[1][:20]) + d[2] + '\n'
 
     def text(self):
         self._compact()
         return self.data
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, '')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, ''), (e2, flags)
 
         return diff
 
     def iterentries(self):
         return lazymanifestiterentries(self)
 
     def iterkeys(self):
         return lazymanifestiter(self)
 
     def __iter__(self):
         return lazymanifestiter(self)
 
     def __len__(self):
         return len(self.positions)
 
     def filtercopy(self, filterfn):
         # XXX should be optimized
         c = _lazymanifest('')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 class manifestdict(object):
     def __init__(self, data=''):
-        if data.startswith('\0'):
-            #_lazymanifest can not parse v2
-            self._lm = _lazymanifest('')
-            for f, n, fl in _parsev2(data):
-                self._lm[f] = n, fl
-        else:
-            self._lm = _lazymanifest(data)
+        self._lm = _lazymanifest(data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __nonzero__(self):
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     __bool__ = __nonzero__
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key, '')
 
     def __contains__(self, key):
         if key is None:
             return False
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
         diff = self.diff(m2)
         files = set(filepath
                     for filepath, hashflags in diff.iteritems()
                     if hashflags[1][0] is None)
         return files
 
     @propertycache
     def _dirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         '''Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files.'''
         files = match.files()
         return (len(files) < 100 and (match.isexact() or
             (match.prefix() and all(fn in self for fn in files))))
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict()
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict()
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key, default=''):
         try:
             return self._lm[key][1]
         except KeyError:
             return default
 
     def copy(self):
         c = manifestdict()
         c._lm = self._lm.copy()
         return c
 
     def items(self):
         return (x[:2] for x in self._lm.iterentries())
 
     iteritems = items
 
     def iterentries(self):
         return self._lm.iterentries()
 
-    def text(self, usemanifestv2=False):
-        if usemanifestv2:
-            return _textv2(self._lm.iterentries())
-        else:
-            # use (probably) native version for v1
-            return self._lm.text()
+    def text(self):
+        # most likely uses native version
+        return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as a bytearray and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < 1000:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = "%s\0%s%s\n" % (f, revlog.hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                                 _("failed to remove %s from manifest") % f)
                     l = ""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, "".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, "".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = bytearray(self.text())
             deltatext = mdiff.textdiff(
                 util.buffer(base), util.buffer(arraytext))
 
         return arraytext, deltatext
 
 def _msearch(m, s, lo=0, hi=None):
     '''return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer, a memoryview or a byte string.
     s is a byte string'''
     def advance(i, c):
         while i < lenm and m[i:i + 1] != c:
             i += 1
         return i
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1:start] != '\n':
             start -= 1
         end = advance(start, '\0')
         if bytes(m[start:end]) < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, '\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, '\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, '\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if '\n' in f or '\r' in f:
             raise error.RevlogError(
                 _("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = "".join(struct.pack(">lll", start, end, len(content))
                    + content for start, end, content in x)
     return deltatext, newaddlist
 
 def _splittopdir(f):
     if '/' in f:
         dir, subpath = f.split('/', 1)
         return dir + '/', subpath
     else:
         return '', f
 
 _noop = lambda s: None
 
 class treemanifest(object):
     def __init__(self, dir='', text=''):
         self._dir = dir
         self._node = revlog.nullid
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
             def readsubtree(subdir, subm):
                 raise AssertionError('treemanifest constructor only accepts '
                                      'flat manifests')
             self.parse(text, readsubtree)
             self._dirty = True # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def __len__(self):
         self._load()
         size = len(self._files)
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def __nonzero__(self):
         # Faster than "__len() != 0" since it avoids loading sub-manifests
         return not self._isempty()
 
     __bool__ = __nonzero__
 
     def _isempty(self):
         self._load() # for consistency; already loaded by all callers
         return (not self._files and (not self._dirs or
                 all(m._isempty() for m in self._dirs.values())))
 
     def __repr__(self):
         return ('<treemanifest dir=%s, node=%s, loaded=%s, dirty=%s at 0x%x>' %
                 (self._dir, revlog.hex(self._node),
                  bool(self._loadfunc is _noop),
                  self._dirty, id(self)))
 
     def dir(self):
         '''The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory.'''
         return self._dir
 
     def node(self):
         '''This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         '''
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         for p, n in sorted(itertools.chain(self._dirs.items(),
                                            self._files.items())):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, '')
             else:
                 for x in n.iterentries():
                     yield x
 
     def items(self):
         self._load()
         for p, n in sorted(itertools.chain(self._dirs.items(),
                                            self._files.items())):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in n.iteritems():
                     yield f, sn
 
     iteritems = items
 
     def iterkeys(self):
         self._load()
         for p in sorted(itertools.chain(self._dirs, self._files)):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p]:
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return False
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 return ''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._dirs:
                 return ''
             return self._flags.get(f, '')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, '')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].__setitem__(subpath, n)
         else:
             self._files[f] = n[:21] # to match manifestdict's behavior
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(self._subpath(dir))
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
             def _copyfunc(s):
                 self._load()
                 for d in self._dirs:
                     s._dirs[d] = self._dirs[d].copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.filesnotin(m2)
 
         files = set()
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files:
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return util.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         return (dir + '/') in self._dirs
 
     def walk(self, match):
         '''Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         '''
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         if not match.visitdir(self._dir[:-1] or '.'):
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         for p in sorted(list(self._dirs) + list(self._files)):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 for f in self._dirs[p]._walk(match):
                     yield f
 
     def matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         return self._matches(match)
 
     def _matches(self, match):
         '''recursively generate a new manifest filtered by the match argument.
         '''
 
         visit = match.visitdir(self._dir[:-1] or '.')
         if visit == 'all':
             return self.copy()
         ret = treemanifest(self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             fullp = self._subpath(fn)
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         for dir, subm in self._dirs.iteritems():
             m = subm._matches(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def diff(self, m2, match=None, clean=False):
         '''Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         '''
         if match:
             m1 = self.matches(match)
             m2 = m2.matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest()
         def _diff(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             for d, m1 in t1._dirs.iteritems():
                 m2 = t2._dirs.get(d, emptytree)
                 _diff(m1, m2)
 
             for d, m2 in t2._dirs.iteritems():
                 if d not in t1._dirs:
                     _diff(emptytree, m2)
 
             for fn, n1 in t1._files.iteritems():
                 fl1 = t1._flags.get(fn, '')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, '')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in t2._files.iteritems():
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, '')
                     result[t2._subpath(fn)] = ((None, ''), (n2, fl2))
 
         _diff(self, m2)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         for f, n, fl in _parse(text):
             if fl == 't':
                 f = f + '/'
                 self._dirs[f] = readsubtree(self._subpath(f), n)
             elif '/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
-    def text(self, usemanifestv2=False):
+    def text(self):
         """Get the full data of this manifest as a bytestring."""
         self._load()
-        return _text(self.iterentries(), usemanifestv2)
+        return _text(self.iterentries())
 
-    def dirtext(self, usemanifestv2=False):
+    def dirtext(self):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         dirs = [(d[:-1], self._dirs[d]._node, 't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
-        return _text(sorted(dirs + files), usemanifestv2)
+        return _text(sorted(dirs + files))
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree):
         self._load() # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest()
         for d, subm in self._dirs.iteritems():
             subp1 = m1._dirs.get(d, emptytree)._node
             subp2 = m2._dirs.get(d, emptytree)._node
             if subp1 == revlog.nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2)
 
     def walksubtrees(self, matcher=None):
         """Returns an iterator of the subtrees of this manifest, including this
         manifest itself.
 
         If `matcher` is provided, it only returns subtrees that match.
         """
         if matcher and not matcher.visitdir(self._dir[:-1] or '.'):
             return
         if not matcher or matcher(self._dir[:-1]):
             yield self
 
         self._load()
         for d, subm in self._dirs.iteritems():
             for subtree in subm.walksubtrees(matcher=matcher):
                 yield subtree
 
 class manifestrevlog(revlog.revlog):
     '''A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     '''
     def __init__(self, opener, dir='', dirlogcache=None, indexfile=None,
                  treemanifest=False):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
 
         `treemanifest` - used to indicate this is a tree manifest revlog. Opener
         options can also be used to make this a tree manifest revlog. The opener
         option takes precedence, so if it is set to True, we ignore whatever
         value is passed in to the constructor.
         """
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         optiontreemanifest = False
-        usemanifestv2 = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get('manifestcachesize', cachesize)
             optiontreemanifest = opts.get('treemanifest', False)
-            usemanifestv2 = opts.get('manifestv2', usemanifestv2)
 
         self._treeondisk = optiontreemanifest or treemanifest
-        self._usemanifestv2 = usemanifestv2
 
         self._fulltextcache = util.lrucachedict(cachesize)
 
         if dir:
             assert self._treeondisk, 'opts is %r' % opts
             if not dir.endswith('/'):
                 dir = dir + '/'
 
         if indexfile is None:
             indexfile = '00manifest.i'
             if dir:
                 indexfile = "meta/" + dir + indexfile
 
         self._dir = dir
         # The dirlogcache is kept on the root manifest log
         if dir:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {'': self}
 
         super(manifestrevlog, self).__init__(opener, indexfile,
                                              # only root indexfile is cached
                                              checkambig=not bool(dir),
                                              mmaplargeindex=True)
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self):
         super(manifestrevlog, self).clearcaches()
         self._fulltextcache.clear()
         self._dirlogcache = {'': self}
 
     def dirlog(self, d):
         if d:
             assert self._treeondisk
         if d not in self._dirlogcache:
             mfrevlog = manifestrevlog(self.opener, d,
                                       self._dirlogcache,
                                       treemanifest=self._treeondisk)
             self._dirlogcache[d] = mfrevlog
         return self._dirlogcache[d]
 
     def add(self, m, transaction, link, p1, p2, added, removed, readtree=None):
-        if (p1 in self.fulltextcache and util.safehasattr(m, 'fastdelta')
-            and not self._usemanifestv2):
+        if p1 in self.fulltextcache and util.safehasattr(m, 'fastdelta'):
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge([(x, False) for x in added],
                                [(x, True) for x in removed])
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self.rev(p1), deltatext
             text = util.buffer(arraytext)
             n = self.addrevision(text, transaction, link, p1, p2, cachedelta)
         else:
             # The first parent manifest isn't already loaded, so we'll
             # just encode a fulltext of the manifest and pass that
             # through to the revlog layer, and let it handle the delta
             # process.
             if self._treeondisk:
                 assert readtree, "readtree must be set for treemanifest writes"
                 m1 = readtree(self._dir, p1)
                 m2 = readtree(self._dir, p2)
                 n = self._addtree(m, transaction, link, m1, m2, readtree)
                 arraytext = None
             else:
-                text = m.text(self._usemanifestv2)
+                text = m.text()
                 n = self.addrevision(text, transaction, link, p1, p2)
                 arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self._dir != '' and (m.unmodifiedsince(m1) or m.unmodifiedsince(m2)):
             return m.node()
         def writesubtree(subm, subp1, subp2):
             sublog = self.dirlog(subm.dir())
             sublog.add(subm, transaction, link, subp1, subp2, None, None,
                        readtree=readtree)
         m.writesubtrees(m1, m2, writesubtree)
-        text = m.dirtext(self._usemanifestv2)
+        text = m.dirtext()
         n = None
         if self._dir != '':
             # Double-check whether contents are unchanged to one parent
-            if text == m1.dirtext(self._usemanifestv2):
+            if text == m1.dirtext():
                 n = m1.node()
-            elif text == m2.dirtext(self._usemanifestv2):
+            elif text == m2.dirtext():
                 n = m2.node()
 
         if not n:
             n = self.addrevision(text, transaction, link, m1.node(), m2.node())
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
 class manifestlog(object):
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
     def __init__(self, opener, repo):
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get('treemanifest', usetreemanifest)
             cachesize = opts.get('manifestcachesize', cachesize)
         self._treeinmem = usetreemanifest
 
         self._revlog = repo._constructmanifest()
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[''] = util.lrucachedict(cachesize)
 
         self.cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get('', node)
 
     def get(self, dir, node, verify=True):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(dir, ()):
             return self._dirmancache[dir][node]
 
         if dir:
             if self._revlog._treeondisk:
                 if verify:
                     dirlog = self._revlog.dirlog(dir)
                     if node not in dirlog.nodemap:
                         raise LookupError(node, dirlog.indexfile,
                                           _('no node'))
                 m = treemanifestctx(self, dir, node)
             else:
                 raise error.Abort(
                         _("cannot ask for manifest directory '%s' in a flat "
                           "manifest") % dir)
         else:
             if verify:
                 if node not in self._revlog.nodemap:
                     raise LookupError(node, self._revlog.indexfile,
                                       _('no node'))
             if self._treeinmem:
                 m = treemanifestctx(self, '', node)
             else:
                 m = manifestctx(self, node)
 
         if node != revlog.nullid:
             mancache = self._dirmancache.get(dir)
             if not mancache:
                 mancache = util.lrucachedict(self.cachesize)
                 self._dirmancache[dir] = mancache
             mancache[node] = m
         return m
 
     def clearcaches(self):
         self._dirmancache.clear()
         self._revlog.clearcaches()
 
 class memmanifestctx(object):
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict()
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self):
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed):
         return self._revlog().add(self._manifestdict, transaction, link, p1, p2,
                                   added, removed)
 
 class manifestctx(object):
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         #self.p1, self.p2 = revlog.parents(node)
         #rev = revlog.rev(node)
         #self.linkrev = revlog.linkrev(rev)
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def node(self):
         return self._node
 
     def new(self):
         return memmanifestctx(self._manifestlog)
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._revlog().parents(self._node)
 
     def read(self):
         if self._data is None:
             if self._node == revlog.nullid:
                 self._data = manifestdict()
             else:
                 rl = self._revlog()
                 text = rl.revision(self._node)
                 arraytext = bytearray(text)
                 rl._fulltextcache[self._node] = arraytext
                 self._data = manifestdict(text)
         return self._data
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         '''
         rl = self._revlog()
         r = rl.rev(self._node)
         deltaparent = rl.deltaparent(r)
         if deltaparent != revlog.nullrev and deltaparent in rl.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         '''
         revlog = self._revlog()
-        if revlog._usemanifestv2:
-            # Need to perform a slow delta
-            r0 = revlog.deltaparent(revlog.rev(self._node))
-            m0 = self._manifestlog[revlog.node(r0)].read()
-            m1 = self.read()
-            md = manifestdict()
-            for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
-                if n1:
-                    md[f] = n1
-                    if fl1:
-                        md.setflag(f, fl1)
-            return md
-
         r = revlog.rev(self._node)
         d = mdiff.patchtext(revlog.revdiff(revlog.deltaparent(r), r))
         return manifestdict(d)
 
     def find(self, key):
         return self.read().find(key)
 
 class memtreemanifestctx(object):
     def __init__(self, manifestlog, dir=''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest()
 
     def _revlog(self):
         return self._manifestlog._revlog
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self):
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
         return self._revlog().add(self._treemanifest, transaction, link, p1, p2,
                                   added, removed, readtree=readtree)
 
 class treemanifestctx(object):
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         #self.p1, self.p2 = revlog.parents(node)
         #rev = revlog.rev(node)
         #self.linkrev = revlog.linkrev(rev)
 
     def _revlog(self):
         return self._manifestlog._revlog.dirlog(self._dir)
 
     def read(self):
         if self._data is None:
             rl = self._revlog()
             if self._node == revlog.nullid:
                 self._data = treemanifest()
             elif rl._treeondisk:
                 m = treemanifest(dir=self._dir)
                 def gettext():
                     return rl.revision(self._node)
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 text = rl.revision(self._node)
                 arraytext = bytearray(text)
                 rl.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(dir=self._dir, text=text)
 
         return self._data
 
     def node(self):
         return self._node
 
     def new(self, dir=''):
         return memtreemanifestctx(self._manifestlog, dir=dir)
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._revlog().parents(self._node)
 
     def readdelta(self, shallow=False):
         '''Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         If `shallow` is True, this will read the delta for this directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifest, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.
         '''
         revlog = self._revlog()
-        if shallow and not revlog._usemanifestv2:
+        if shallow:
             r = revlog.rev(self._node)
             d = mdiff.patchtext(revlog.revdiff(revlog.deltaparent(r), r))
             return manifestdict(d)
         else:
             # Need to perform a slow delta
             r0 = revlog.deltaparent(revlog.rev(self._node))
             m0 = self._manifestlog.get(self._dir, revlog.node(r0)).read()
             m1 = self.read()
             md = treemanifest(dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def readfast(self, shallow=False):
         '''Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         '''
         rl = self._revlog()
         r = rl.rev(self._node)
         deltaparent = rl.deltaparent(r)
         if (deltaparent != revlog.nullrev and
             deltaparent in rl.parentrevs(r)):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(rl.revision(self._node))
         else:
             return self.read()
 
     def find(self, key):
         return self.read().find(key)

mercurial/upgrade.py

@@ -1,867 +1,866 b''
 # upgrade.py - functions for in place upgrade of Mercurial repository
 #
 # Copyright (c) 2016-present, Gregory Szorc
 #
 # 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 stat
 import tempfile
 
 from .i18n import _
 from . import (
     changelog,
     error,
     filelog,
     hg,
     localrepo,
     manifest,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
 )
 
 def requiredsourcerequirements(repo):
     """Obtain requirements required to be present to upgrade a repo.
 
     An upgrade will not be allowed if the repository doesn't have the
     requirements returned by this function.
     """
     return {
         # Introduced in Mercurial 0.9.2.
         'revlogv1',
         # Introduced in Mercurial 0.9.2.
         'store',
     }
 
 def blocksourcerequirements(repo):
     """Obtain requirements that will prevent an upgrade from occurring.
 
     An upgrade cannot be performed if the source repository contains a
     requirements in the returned set.
     """
     return {
         # The upgrade code does not yet support these experimental features.
         # This is an artificial limitation.
-        'manifestv2',
         'treemanifest',
         # This was a precursor to generaldelta and was never enabled by default.
         # It should (hopefully) not exist in the wild.
         'parentdelta',
         # Upgrade should operate on the actual store, not the shared link.
         'shared',
     }
 
 def supportremovedrequirements(repo):
     """Obtain requirements that can be removed during an upgrade.
 
     If an upgrade were to create a repository that dropped a requirement,
     the dropped requirement must appear in the returned set for the upgrade
     to be allowed.
     """
     return set()
 
 def supporteddestrequirements(repo):
     """Obtain requirements that upgrade supports in the destination.
 
     If the result of the upgrade would create requirements not in this set,
     the upgrade is disallowed.
 
     Extensions should monkeypatch this to add their custom requirements.
     """
     return {
         'dotencode',
         'fncache',
         'generaldelta',
         'revlogv1',
         'store',
     }
 
 def allowednewrequirements(repo):
     """Obtain requirements that can be added to a repository during upgrade.
 
     This is used to disallow proposed requirements from being added when
     they weren't present before.
 
     We use a list of allowed requirement additions instead of a list of known
     bad additions because the whitelist approach is safer and will prevent
     future, unknown requirements from accidentally being added.
     """
     return {
         'dotencode',
         'fncache',
         'generaldelta',
     }
 
 def preservedrequirements(repo):
     return set()
 
 deficiency = 'deficiency'
 optimisation = 'optimization'
 
 class improvement(object):
     """Represents an improvement that can be made as part of an upgrade.
 
     The following attributes are defined on each instance:
 
     name
        Machine-readable string uniquely identifying this improvement. It
        will be mapped to an action later in the upgrade process.
 
     type
        Either ``deficiency`` or ``optimisation``. A deficiency is an obvious
        problem. An optimization is an action (sometimes optional) that
        can be taken to further improve the state of the repository.
 
     description
        Message intended for humans explaining the improvement in more detail,
        including the implications of it. For ``deficiency`` types, should be
        worded in the present tense. For ``optimisation`` types, should be
        worded in the future tense.
 
     upgrademessage
        Message intended for humans explaining what an upgrade addressing this
        issue will do. Should be worded in the future tense.
     """
     def __init__(self, name, type, description, upgrademessage):
         self.name = name
         self.type = type
         self.description = description
         self.upgrademessage = upgrademessage
 
     def __eq__(self, other):
         if not isinstance(other, improvement):
             # This is what python tell use to do
             return NotImplemented
         return self.name == other.name
 
     def __ne__(self, other):
         return not self == other
 
     def __hash__(self):
         return hash(self.name)
 
 allformatvariant = []
 
 def registerformatvariant(cls):
     allformatvariant.append(cls)
     return cls
 
 class formatvariant(improvement):
     """an improvement subclass dedicated to repository format"""
     type = deficiency
     ### The following attributes should be defined for each class:
 
     # machine-readable string uniquely identifying this improvement. it will be
     # mapped to an action later in the upgrade process.
     name = None
 
     # message intended for humans explaining the improvement in more detail,
     # including the implications of it ``deficiency`` types, should be worded
     # in the present tense.
     description = None
 
     # message intended for humans explaining what an upgrade addressing this
     # issue will do. should be worded in the future tense.
     upgrademessage = None
 
     # value of current Mercurial default for new repository
     default = None
 
     def __init__(self):
         raise NotImplementedError()
 
     @staticmethod
     def fromrepo(repo):
         """current value of the variant in the repository"""
         raise NotImplementedError()
 
     @staticmethod
     def fromconfig(repo):
         """current value of the variant in the configuration"""
         raise NotImplementedError()
 
 class requirementformatvariant(formatvariant):
     """formatvariant based on a 'requirement' name.
 
     Many format variant are controlled by a 'requirement'. We define a small
     subclass to factor the code.
     """
 
     # the requirement that control this format variant
     _requirement = None
 
     @staticmethod
     def _newreporequirements(repo):
         return localrepo.newreporequirements(repo)
 
     @classmethod
     def fromrepo(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in repo.requirements
 
     @classmethod
     def fromconfig(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in cls._newreporequirements(repo)
 
 @registerformatvariant
 class fncache(requirementformatvariant):
     name = 'fncache'
 
     _requirement = 'fncache'
 
     default = True
 
     description = _('long and reserved filenames may not work correctly; '
                     'repository performance is sub-optimal')
 
     upgrademessage = _('repository will be more resilient to storing '
                        'certain paths and performance of certain '
                        'operations should be improved')
 
 @registerformatvariant
 class dotencode(requirementformatvariant):
     name = 'dotencode'
 
     _requirement = 'dotencode'
 
     default = True
 
     description = _('storage of filenames beginning with a period or '
                     'space may not work correctly')
 
     upgrademessage = _('repository will be better able to store files '
                        'beginning with a space or period')
 
 @registerformatvariant
 class generaldelta(requirementformatvariant):
     name = 'generaldelta'
 
     _requirement = 'generaldelta'
 
     default = True
 
     description = _('deltas within internal storage are unable to '
                     'choose optimal revisions; repository is larger and '
                     'slower than it could be; interaction with other '
                     'repositories may require extra network and CPU '
                     'resources, making "hg push" and "hg pull" slower')
 
     upgrademessage = _('repository storage will be able to create '
                        'optimal deltas; new repository data will be '
                        'smaller and read times should decrease; '
                        'interacting with other repositories using this '
                        'storage model should require less network and '
                        'CPU resources, making "hg push" and "hg pull" '
                        'faster')
 
 @registerformatvariant
 class removecldeltachain(formatvariant):
     name = 'plain-cl-delta'
 
     default = True
 
     description = _('changelog storage is using deltas instead of '
                     'raw entries; changelog reading and any '
                     'operation relying on changelog data are slower '
                     'than they could be')
 
     upgrademessage = _('changelog storage will be reformated to '
                        'store raw entries; changelog reading will be '
                        'faster; changelog size may be reduced')
 
     @staticmethod
     def fromrepo(repo):
         # Mercurial 4.0 changed changelogs to not use delta chains. Search for
         # changelogs with deltas.
         cl = repo.changelog
         chainbase = cl.chainbase
         return all(rev == chainbase(rev) for rev in cl)
 
     @staticmethod
     def fromconfig(repo):
         return True
 
 @registerformatvariant
 class compressionengine(formatvariant):
     name = 'compression'
     default = 'zlib'
 
     description = _('Compresion algorithm used to compress data. '
                     'Some engine are faster than other')
 
     upgrademessage = _('revlog content will be recompressed with the new '
                        'algorithm.')
 
     @classmethod
     def fromrepo(cls, repo):
         for req in repo.requirements:
             if req.startswith('exp-compression-'):
                 return req.split('-', 2)[2]
         return 'zlib'
 
     @classmethod
     def fromconfig(cls, repo):
         return repo.ui.config('experimental', 'format.compression')
 
 def finddeficiencies(repo):
     """returns a list of deficiencies that the repo suffer from"""
     deficiencies = []
 
     # We could detect lack of revlogv1 and store here, but they were added
     # in 0.9.2 and we don't support upgrading repos without these
     # requirements, so let's not bother.
 
     for fv in allformatvariant:
         if not fv.fromrepo(repo):
             deficiencies.append(fv)
 
     return deficiencies
 
 def findoptimizations(repo):
     """Determine optimisation that could be used during upgrade"""
     # These are unconditionally added. There is logic later that figures out
     # which ones to apply.
     optimizations = []
 
     optimizations.append(improvement(
         name='redeltaparent',
         type=optimisation,
         description=_('deltas within internal storage will be recalculated to '
                       'choose an optimal base revision where this was not '
                       'already done; the size of the repository may shrink and '
                       'various operations may become faster; the first time '
                       'this optimization is performed could slow down upgrade '
                       'execution considerably; subsequent invocations should '
                       'not run noticeably slower'),
         upgrademessage=_('deltas within internal storage will choose a new '
                          'base revision if needed')))
 
     optimizations.append(improvement(
         name='redeltamultibase',
         type=optimisation,
         description=_('deltas within internal storage will be recalculated '
                       'against multiple base revision and the smallest '
                       'difference will be used; the size of the repository may '
                       'shrink significantly when there are many merges; this '
                       'optimization will slow down execution in proportion to '
                       'the number of merges in the repository and the amount '
                       'of files in the repository; this slow down should not '
                       'be significant unless there are tens of thousands of '
                       'files and thousands of merges'),
         upgrademessage=_('deltas within internal storage will choose an '
                          'optimal delta by computing deltas against multiple '
                          'parents; may slow down execution time '
                          'significantly')))
 
     optimizations.append(improvement(
         name='redeltaall',
         type=optimisation,
         description=_('deltas within internal storage will always be '
                       'recalculated without reusing prior deltas; this will '
                       'likely make execution run several times slower; this '
                       'optimization is typically not needed'),
         upgrademessage=_('deltas within internal storage will be fully '
                          'recomputed; this will likely drastically slow down '
                          'execution time')))
 
     optimizations.append(improvement(
         name='redeltafulladd',
         type=optimisation,
         description=_('every revision will be re-added as if it was new '
                       'content. It will go through the full storage '
                       'mechanism giving extensions a chance to process it '
                       '(eg. lfs). This is similar to "redeltaall" but even '
                       'slower since more logic is involved.'),
         upgrademessage=_('each revision will be added as new content to the '
                          'internal storage; this will likely drastically slow '
                          'down execution time, but some extensions might need '
                          'it')))
 
     return optimizations
 
 def determineactions(repo, deficiencies, sourcereqs, destreqs):
     """Determine upgrade actions that will be performed.
 
     Given a list of improvements as returned by ``finddeficiencies`` and
     ``findoptimizations``, determine the list of upgrade actions that
     will be performed.
 
     The role of this function is to filter improvements if needed, apply
     recommended optimizations from the improvements list that make sense,
     etc.
 
     Returns a list of action names.
     """
     newactions = []
 
     knownreqs = supporteddestrequirements(repo)
 
     for d in deficiencies:
         name = d.name
 
         # If the action is a requirement that doesn't show up in the
         # destination requirements, prune the action.
         if name in knownreqs and name not in destreqs:
             continue
 
         newactions.append(d)
 
     # FUTURE consider adding some optimizations here for certain transitions.
     # e.g. adding generaldelta could schedule parent redeltas.
 
     return newactions
 
 def _revlogfrompath(repo, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if path == '00changelog.i':
         return changelog.changelog(repo.svfs)
     elif path.endswith('00manifest.i'):
         mandir = path[:-len('00manifest.i')]
         return manifest.manifestrevlog(repo.svfs, dir=mandir)
     else:
         #reverse of "/".join(("data", path + ".i"))
         return filelog.filelog(repo.svfs, path[5:-2])
 
 def _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse, aggressivemergedeltas):
     """Copy revlogs between 2 repos."""
     revcount = 0
     srcsize = 0
     srcrawsize = 0
     dstsize = 0
     fcount = 0
     frevcount = 0
     fsrcsize = 0
     frawsize = 0
     fdstsize = 0
     mcount = 0
     mrevcount = 0
     msrcsize = 0
     mrawsize = 0
     mdstsize = 0
     crevcount = 0
     csrcsize = 0
     crawsize = 0
     cdstsize = 0
 
     # Perform a pass to collect metadata. This validates we can open all
     # source files and allows a unified progress bar to be displayed.
     for unencoded, encoded, size in srcrepo.store.walk():
         if unencoded.endswith('.d'):
             continue
 
         rl = _revlogfrompath(srcrepo, unencoded)
         revcount += len(rl)
 
         datasize = 0
         rawsize = 0
         idx = rl.index
         for rev in rl:
             e = idx[rev]
             datasize += e[1]
             rawsize += e[2]
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if isinstance(rl, changelog.changelog):
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif isinstance(rl, manifest.manifestrevlog):
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif isinstance(rl, revlog.revlog):
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
 
     if not revcount:
         return
 
     ui.write(_('migrating %d total revisions (%d in filelogs, %d in manifests, '
                '%d in changelog)\n') %
              (revcount, frevcount, mrevcount, crevcount))
     ui.write(_('migrating %s in store; %s tracked data\n') % (
              (util.bytecount(srcsize), util.bytecount(srcrawsize))))
 
     # Used to keep track of progress.
     progress = []
     def oncopiedrevision(rl, rev, node):
         progress[1] += 1
         srcrepo.ui.progress(progress[0], progress[1], total=progress[2])
 
     # Do the actual copying.
     # FUTURE this operation can be farmed off to worker processes.
     seen = set()
     for unencoded, encoded, size in srcrepo.store.walk():
         if unencoded.endswith('.d'):
             continue
 
         oldrl = _revlogfrompath(srcrepo, unencoded)
         newrl = _revlogfrompath(dstrepo, unencoded)
 
         if isinstance(oldrl, changelog.changelog) and 'c' not in seen:
             ui.write(_('finished migrating %d manifest revisions across %d '
                        'manifests; change in size: %s\n') %
                      (mrevcount, mcount, util.bytecount(mdstsize - msrcsize)))
 
             ui.write(_('migrating changelog containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (crevcount, util.bytecount(csrcsize),
                       util.bytecount(crawsize)))
             seen.add('c')
             progress[:] = [_('changelog revisions'), 0, crevcount]
         elif isinstance(oldrl, manifest.manifestrevlog) and 'm' not in seen:
             ui.write(_('finished migrating %d filelog revisions across %d '
                        'filelogs; change in size: %s\n') %
                      (frevcount, fcount, util.bytecount(fdstsize - fsrcsize)))
 
             ui.write(_('migrating %d manifests containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (mcount, mrevcount, util.bytecount(msrcsize),
                       util.bytecount(mrawsize)))
             seen.add('m')
             progress[:] = [_('manifest revisions'), 0, mrevcount]
         elif 'f' not in seen:
             ui.write(_('migrating %d filelogs containing %d revisions '
                        '(%s in store; %s tracked data)\n') %
                      (fcount, frevcount, util.bytecount(fsrcsize),
                       util.bytecount(frawsize)))
             seen.add('f')
             progress[:] = [_('file revisions'), 0, frevcount]
 
         ui.progress(progress[0], progress[1], total=progress[2])
 
         ui.note(_('cloning %d revisions from %s\n') % (len(oldrl), unencoded))
         oldrl.clone(tr, newrl, addrevisioncb=oncopiedrevision,
                     deltareuse=deltareuse,
                     aggressivemergedeltas=aggressivemergedeltas)
 
         datasize = 0
         idx = newrl.index
         for rev in newrl:
             datasize += idx[rev][1]
 
         dstsize += datasize
 
         if isinstance(newrl, changelog.changelog):
             cdstsize += datasize
         elif isinstance(newrl, manifest.manifestrevlog):
             mdstsize += datasize
         else:
             fdstsize += datasize
 
     ui.progress(progress[0], None)
 
     ui.write(_('finished migrating %d changelog revisions; change in size: '
                '%s\n') % (crevcount, util.bytecount(cdstsize - csrcsize)))
 
     ui.write(_('finished migrating %d total revisions; total change in store '
                'size: %s\n') % (revcount, util.bytecount(dstsize - srcsize)))
 
 def _filterstorefile(srcrepo, dstrepo, requirements, path, mode, st):
     """Determine whether to copy a store file during upgrade.
 
     This function is called when migrating store files from ``srcrepo`` to
     ``dstrepo`` as part of upgrading a repository.
 
     Args:
       srcrepo: repo we are copying from
       dstrepo: repo we are copying to
       requirements: set of requirements for ``dstrepo``
       path: store file being examined
       mode: the ``ST_MODE`` file type of ``path``
       st: ``stat`` data structure for ``path``
 
     Function should return ``True`` if the file is to be copied.
     """
     # Skip revlogs.
     if path.endswith(('.i', '.d')):
         return False
     # Skip transaction related files.
     if path.startswith('undo'):
         return False
     # Only copy regular files.
     if mode != stat.S_IFREG:
         return False
     # Skip other skipped files.
     if path in ('lock', 'fncache'):
         return False
 
     return True
 
 def _finishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 def _upgraderepo(ui, srcrepo, dstrepo, requirements, actions):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
 
     ui.write(_('(it is safe to interrupt this process any time before '
                'data migration completes)\n'))
 
     if 'redeltaall' in actions:
         deltareuse = revlog.revlog.DELTAREUSENEVER
     elif 'redeltaparent' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif 'redeltamultibase' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif 'redeltafulladd' in actions:
         deltareuse = revlog.revlog.DELTAREUSEFULLADD
     else:
         deltareuse = revlog.revlog.DELTAREUSEALWAYS
 
     with dstrepo.transaction('upgrade') as tr:
         _copyrevlogs(ui, srcrepo, dstrepo, tr, deltareuse,
                      'redeltamultibase' in actions)
 
     # Now copy other files in the store directory.
     # The sorted() makes execution deterministic.
     for p, kind, st in sorted(srcrepo.store.vfs.readdir('', stat=True)):
         if not _filterstorefile(srcrepo, dstrepo, requirements,
                                        p, kind, st):
             continue
 
         srcrepo.ui.write(_('copying %s\n') % p)
         src = srcrepo.store.rawvfs.join(p)
         dst = dstrepo.store.rawvfs.join(p)
         util.copyfile(src, dst, copystat=True)
 
     _finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
     ui.write(_('data fully migrated to temporary repository\n'))
 
     backuppath = tempfile.mkdtemp(prefix='upgradebackup.', dir=srcrepo.path)
     backupvfs = vfsmod.vfs(backuppath)
 
     # Make a backup of requires file first, as it is the first to be modified.
     util.copyfile(srcrepo.vfs.join('requires'), backupvfs.join('requires'))
 
     # We install an arbitrary requirement that clients must not support
     # as a mechanism to lock out new clients during the data swap. This is
     # better than allowing a client to continue while the repository is in
     # an inconsistent state.
     ui.write(_('marking source repository as being upgraded; clients will be '
                'unable to read from repository\n'))
     scmutil.writerequires(srcrepo.vfs,
                           srcrepo.requirements | {'upgradeinprogress'})
 
     ui.write(_('starting in-place swap of repository data\n'))
     ui.write(_('replaced files will be backed up at %s\n') %
              backuppath)
 
     # Now swap in the new store directory. Doing it as a rename should make
     # the operation nearly instantaneous and atomic (at least in well-behaved
     # environments).
     ui.write(_('replacing store...\n'))
     tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join('store'))
     util.rename(dstrepo.spath, srcrepo.spath)
     elapsed = util.timer() - tstart
     ui.write(_('store replacement complete; repository was inconsistent for '
                '%0.1fs\n') % elapsed)
 
     # We first write the requirements file. Any new requirements will lock
     # out legacy clients.
     ui.write(_('finalizing requirements file and making repository readable '
                'again\n'))
     scmutil.writerequires(srcrepo.vfs, requirements)
 
     # The lock file from the old store won't be removed because nothing has a
     # reference to its new location. So clean it up manually. Alternatively, we
     # could update srcrepo.svfs and other variables to point to the new
     # location. This is simpler.
     backupvfs.unlink('store/lock')
 
     return backuppath
 
 def upgraderepo(ui, repo, run=False, optimize=None):
     """Upgrade a repository in place."""
     optimize = set(optimize or [])
     repo = repo.unfiltered()
 
     # Ensure the repository can be upgraded.
     missingreqs = requiredsourcerequirements(repo) - repo.requirements
     if missingreqs:
         raise error.Abort(_('cannot upgrade repository; requirement '
                             'missing: %s') % _(', ').join(sorted(missingreqs)))
 
     blockedreqs = blocksourcerequirements(repo) & repo.requirements
     if blockedreqs:
         raise error.Abort(_('cannot upgrade repository; unsupported source '
                             'requirement: %s') %
                           _(', ').join(sorted(blockedreqs)))
 
     # FUTURE there is potentially a need to control the wanted requirements via
     # command arguments or via an extension hook point.
     newreqs = localrepo.newreporequirements(repo)
     newreqs.update(preservedrequirements(repo))
 
     noremovereqs = (repo.requirements - newreqs -
                    supportremovedrequirements(repo))
     if noremovereqs:
         raise error.Abort(_('cannot upgrade repository; requirement would be '
                             'removed: %s') % _(', ').join(sorted(noremovereqs)))
 
     noaddreqs = (newreqs - repo.requirements -
                  allowednewrequirements(repo))
     if noaddreqs:
         raise error.Abort(_('cannot upgrade repository; do not support adding '
                             'requirement: %s') %
                           _(', ').join(sorted(noaddreqs)))
 
     unsupportedreqs = newreqs - supporteddestrequirements(repo)
     if unsupportedreqs:
         raise error.Abort(_('cannot upgrade repository; do not support '
                             'destination requirement: %s') %
                           _(', ').join(sorted(unsupportedreqs)))
 
     # Find and validate all improvements that can be made.
     alloptimizations = findoptimizations(repo)
 
     # Apply and Validate arguments.
     optimizations = []
     for o in alloptimizations:
         if o.name in optimize:
             optimizations.append(o)
             optimize.discard(o.name)
 
     if optimize: # anything left is unknown
         raise error.Abort(_('unknown optimization action requested: %s') %
                           ', '.join(sorted(optimize)),
                           hint=_('run without arguments to see valid '
                                  'optimizations'))
 
     deficiencies = finddeficiencies(repo)
     actions = determineactions(repo, deficiencies, repo.requirements, newreqs)
     actions.extend(o for o in sorted(optimizations)
                    # determineactions could have added optimisation
                    if o not in actions)
 
     def printrequirements():
         ui.write(_('requirements\n'))
         ui.write(_('   preserved: %s\n') %
                  _(', ').join(sorted(newreqs & repo.requirements)))
 
         if repo.requirements - newreqs:
             ui.write(_('   removed: %s\n') %
                      _(', ').join(sorted(repo.requirements - newreqs)))
 
         if newreqs - repo.requirements:
             ui.write(_('   added: %s\n') %
                      _(', ').join(sorted(newreqs - repo.requirements)))
 
         ui.write('\n')
 
     def printupgradeactions():
         for a in actions:
             ui.write('%s\n   %s\n\n' % (a.name, a.upgrademessage))
 
     if not run:
         fromconfig = []
         onlydefault = []
 
         for d in deficiencies:
             if d.fromconfig(repo):
                 fromconfig.append(d)
             elif d.default:
                 onlydefault.append(d)
 
         if fromconfig or onlydefault:
 
             if fromconfig:
                 ui.write(_('repository lacks features recommended by '
                            'current config options:\n\n'))
                 for i in fromconfig:
                     ui.write('%s\n   %s\n\n' % (i.name, i.description))
 
             if onlydefault:
                 ui.write(_('repository lacks features used by the default '
                            'config options:\n\n'))
                 for i in onlydefault:
                     ui.write('%s\n   %s\n\n' % (i.name, i.description))
 
             ui.write('\n')
         else:
             ui.write(_('(no feature deficiencies found in existing '
                        'repository)\n'))
 
         ui.write(_('performing an upgrade with "--run" will make the following '
                    'changes:\n\n'))
 
         printrequirements()
         printupgradeactions()
 
         unusedoptimize = [i for i in alloptimizations if i not in actions]
 
         if unusedoptimize:
             ui.write(_('additional optimizations are available by specifying '
                      '"--optimize <name>":\n\n'))
             for i in unusedoptimize:
                 ui.write(_('%s\n   %s\n\n') % (i.name, i.description))
         return
 
     # Else we're in the run=true case.
     ui.write(_('upgrade will perform the following actions:\n\n'))
     printrequirements()
     printupgradeactions()
 
     upgradeactions = [a.name for a in actions]
 
     ui.write(_('beginning upgrade...\n'))
     with repo.wlock(), repo.lock():
         ui.write(_('repository locked and read-only\n'))
         # Our strategy for upgrading the repository is to create a new,
         # temporary repository, write data to it, then do a swap of the
         # data. There are less heavyweight ways to do this, but it is easier
         # to create a new repo object than to instantiate all the components
         # (like the store) separately.
         tmppath = tempfile.mkdtemp(prefix='upgrade.', dir=repo.path)
         backuppath = None
         try:
             ui.write(_('creating temporary repository to stage migrated '
                        'data: %s\n') % tmppath)
 
             # clone ui without using ui.copy because repo.ui is protected
             repoui = repo.ui.__class__(repo.ui)
             dstrepo = hg.repository(repoui, path=tmppath, create=True)
 
             with dstrepo.wlock(), dstrepo.lock():
                 backuppath = _upgraderepo(ui, repo, dstrepo, newreqs,
                                           upgradeactions)
 
         finally:
             ui.write(_('removing temporary repository %s\n') % tmppath)
             repo.vfs.rmtree(tmppath, forcibly=True)
 
             if backuppath:
                 ui.warn(_('copy of old repository backed up at %s\n') %
                         backuppath)
                 ui.warn(_('the old repository will not be deleted; remove '
                           'it to free up disk space once the upgraded '
                           'repository is verified\n'))

tests/test-manifest.py

@@ -1,489 +1,422 b''
 from __future__ import absolute_import
 
 import binascii
 import itertools
 import silenttestrunner
 import unittest
 
 from mercurial import (
     manifest as manifestmod,
     match as matchmod,
 )
 
 EMTPY_MANIFEST = b''
-EMTPY_MANIFEST_V2 = b'\0\n'
 
 HASH_1 = b'1' * 40
 BIN_HASH_1 = binascii.unhexlify(HASH_1)
 HASH_2 = b'f' * 40
 BIN_HASH_2 = binascii.unhexlify(HASH_2)
 HASH_3 = b'1234567890abcdef0987654321deadbeef0fcafe'
 BIN_HASH_3 = binascii.unhexlify(HASH_3)
 A_SHORT_MANIFEST = (
     b'bar/baz/qux.py\0%(hash2)s%(flag2)s\n'
     b'foo\0%(hash1)s%(flag1)s\n'
     ) % {b'hash1': HASH_1,
          b'flag1': b'',
          b'hash2': HASH_2,
          b'flag2': b'l',
          }
 
-# Same data as A_SHORT_MANIFEST
-A_SHORT_MANIFEST_V2 = (
-    b'\0\n'
-    b'\x00bar/baz/qux.py\0%(flag2)s\n%(hash2)s\n'
-    b'\x00foo\0%(flag1)s\n%(hash1)s\n'
-    ) % {b'hash1': BIN_HASH_1,
-         b'flag1': b'',
-         b'hash2': BIN_HASH_2,
-         b'flag2': b'l',
-         }
-
-# Same data as A_SHORT_MANIFEST
-A_METADATA_MANIFEST = (
-    b'\0foo\0bar\n'
-    b'\x00bar/baz/qux.py\0%(flag2)s\0foo\0bar\n%(hash2)s\n' # flag and metadata
-    b'\x00foo\0%(flag1)s\0foo\n%(hash1)s\n' # no flag, but metadata
-    ) % {b'hash1': BIN_HASH_1,
-         b'flag1': b'',
-         b'hash2': BIN_HASH_2,
-         b'flag2': b'l',
-         }
-
-A_STEM_COMPRESSED_MANIFEST = (
-    b'\0\n'
-    b'\x00bar/baz/qux.py\0%(flag2)s\n%(hash2)s\n'
-    b'\x04qux/foo.py\0%(flag1)s\n%(hash1)s\n' # simple case of 4 stem chars
-    b'\x0az.py\0%(flag1)s\n%(hash1)s\n' # tricky newline = 10 stem characters
-    b'\x00%(verylongdir)sx/x\0\n%(hash1)s\n'
-    b'\xffx/y\0\n%(hash2)s\n' # more than 255 stem chars
-    ) % {b'hash1': BIN_HASH_1,
-         b'flag1': b'',
-         b'hash2': BIN_HASH_2,
-         b'flag2': b'l',
-         b'verylongdir': 255 * b'x',
-         }
-
 A_DEEPER_MANIFEST = (
     b'a/b/c/bar.py\0%(hash3)s%(flag1)s\n'
     b'a/b/c/bar.txt\0%(hash1)s%(flag1)s\n'
     b'a/b/c/foo.py\0%(hash3)s%(flag1)s\n'
     b'a/b/c/foo.txt\0%(hash2)s%(flag2)s\n'
     b'a/b/d/baz.py\0%(hash3)s%(flag1)s\n'
     b'a/b/d/qux.py\0%(hash1)s%(flag2)s\n'
     b'a/b/d/ten.txt\0%(hash3)s%(flag2)s\n'
     b'a/b/dog.py\0%(hash3)s%(flag1)s\n'
     b'a/b/fish.py\0%(hash2)s%(flag1)s\n'
     b'a/c/london.py\0%(hash3)s%(flag2)s\n'
     b'a/c/paper.txt\0%(hash2)s%(flag2)s\n'
     b'a/c/paris.py\0%(hash2)s%(flag1)s\n'
     b'a/d/apple.py\0%(hash3)s%(flag1)s\n'
     b'a/d/pizza.py\0%(hash3)s%(flag2)s\n'
     b'a/green.py\0%(hash1)s%(flag2)s\n'
     b'a/purple.py\0%(hash2)s%(flag1)s\n'
     b'app.py\0%(hash3)s%(flag1)s\n'
     b'readme.txt\0%(hash2)s%(flag1)s\n'
     ) % {b'hash1': HASH_1,
          b'flag1': b'',
          b'hash2': HASH_2,
          b'flag2': b'l',
          b'hash3': HASH_3,
          }
 
 HUGE_MANIFEST_ENTRIES = 200001
 
 izip = getattr(itertools, 'izip', zip)
 if 'xrange' not in globals():
     xrange = range
 
 A_HUGE_MANIFEST = b''.join(sorted(
     b'file%d\0%s%s\n' % (i, h, f) for i, h, f in
     izip(xrange(200001),
          itertools.cycle((HASH_1, HASH_2)),
          itertools.cycle((b'', b'x', b'l')))))
 
 class basemanifesttests(object):
     def parsemanifest(self, text):
         raise NotImplementedError('parsemanifest not implemented by test case')
 
     def testEmptyManifest(self):
         m = self.parsemanifest(EMTPY_MANIFEST)
         self.assertEqual(0, len(m))
         self.assertEqual([], list(m))
 
-    def testEmptyManifestv2(self):
-        m = self.parsemanifest(EMTPY_MANIFEST_V2)
-        self.assertEqual(0, len(m))
-        self.assertEqual([], list(m))
-
     def testManifest(self):
         m = self.parsemanifest(A_SHORT_MANIFEST)
         self.assertEqual([b'bar/baz/qux.py', b'foo'], list(m))
         self.assertEqual(BIN_HASH_2, m[b'bar/baz/qux.py'])
         self.assertEqual(b'l', m.flags(b'bar/baz/qux.py'))
         self.assertEqual(BIN_HASH_1, m[b'foo'])
         self.assertEqual(b'', m.flags(b'foo'))
         with self.assertRaises(KeyError):
             m[b'wat']
 
-    def testParseManifestV2(self):
-        m1 = self.parsemanifest(A_SHORT_MANIFEST)
-        m2 = self.parsemanifest(A_SHORT_MANIFEST_V2)
-        # Should have same content as A_SHORT_MANIFEST
-        self.assertEqual(m1.text(), m2.text())
-
-    def testParseManifestMetadata(self):
-        # Metadata is for future-proofing and should be accepted but ignored
-        m = self.parsemanifest(A_METADATA_MANIFEST)
-        self.assertEqual(A_SHORT_MANIFEST, m.text())
-
-    def testParseManifestStemCompression(self):
-        m = self.parsemanifest(A_STEM_COMPRESSED_MANIFEST)
-        self.assertIn(b'bar/baz/qux.py', m)
-        self.assertIn(b'bar/qux/foo.py', m)
-        self.assertIn(b'bar/qux/foz.py', m)
-        self.assertIn(256 * b'x' + b'/x', m)
-        self.assertIn(256 * b'x' + b'/y', m)
-        self.assertEqual(A_STEM_COMPRESSED_MANIFEST, m.text(usemanifestv2=True))
-
-    def testTextV2(self):
-        m1 = self.parsemanifest(A_SHORT_MANIFEST)
-        v2text = m1.text(usemanifestv2=True)
-        self.assertEqual(A_SHORT_MANIFEST_V2, v2text)
-
     def testSetItem(self):
         want = BIN_HASH_1
 
         m = self.parsemanifest(EMTPY_MANIFEST)
         m[b'a'] = want
         self.assertIn(b'a', m)
         self.assertEqual(want, m[b'a'])
         self.assertEqual(b'a\0' + HASH_1 + b'\n', m.text())
 
         m = self.parsemanifest(A_SHORT_MANIFEST)
         m[b'a'] = want
         self.assertEqual(want, m[b'a'])
         self.assertEqual(b'a\0' + HASH_1 + b'\n' + A_SHORT_MANIFEST,
                          m.text())
 
     def testSetFlag(self):
         want = b'x'
 
         m = self.parsemanifest(EMTPY_MANIFEST)
         # first add a file; a file-less flag makes no sense
         m[b'a'] = BIN_HASH_1
         m.setflag(b'a', want)
         self.assertEqual(want, m.flags(b'a'))
         self.assertEqual(b'a\0' + HASH_1 + want + b'\n', m.text())
 
         m = self.parsemanifest(A_SHORT_MANIFEST)
         # first add a file; a file-less flag makes no sense
         m[b'a'] = BIN_HASH_1
         m.setflag(b'a', want)
         self.assertEqual(want, m.flags(b'a'))
         self.assertEqual(b'a\0' + HASH_1 + want + b'\n' + A_SHORT_MANIFEST,
                          m.text())
 
     def testCopy(self):
         m = self.parsemanifest(A_SHORT_MANIFEST)
         m[b'a'] = BIN_HASH_1
         m2 = m.copy()
         del m
         del m2 # make sure we don't double free() anything
 
     def testCompaction(self):
         unhex = binascii.unhexlify
         h1, h2 = unhex(HASH_1), unhex(HASH_2)
         m = self.parsemanifest(A_SHORT_MANIFEST)
         m[b'alpha'] = h1
         m[b'beta'] = h2
         del m[b'foo']
         want = b'alpha\0%s\nbar/baz/qux.py\0%sl\nbeta\0%s\n' % (
             HASH_1, HASH_2, HASH_2)
         self.assertEqual(want, m.text())
         self.assertEqual(3, len(m))
         self.assertEqual([b'alpha', b'bar/baz/qux.py', b'beta'], list(m))
         self.assertEqual(h1, m[b'alpha'])
         self.assertEqual(h2, m[b'bar/baz/qux.py'])
         self.assertEqual(h2, m[b'beta'])
         self.assertEqual(b'', m.flags(b'alpha'))
         self.assertEqual(b'l', m.flags(b'bar/baz/qux.py'))
         self.assertEqual(b'', m.flags(b'beta'))
         with self.assertRaises(KeyError):
             m[b'foo']
 
     def testSetGetNodeSuffix(self):
         clean = self.parsemanifest(A_SHORT_MANIFEST)
         m = self.parsemanifest(A_SHORT_MANIFEST)
         h = m[b'foo']
         f = m.flags(b'foo')
         want = h + b'a'
         # Merge code wants to set 21-byte fake hashes at times
         m[b'foo'] = want
         self.assertEqual(want, m[b'foo'])
         self.assertEqual([(b'bar/baz/qux.py', BIN_HASH_2),
                           (b'foo', BIN_HASH_1 + b'a')],
                          list(m.items()))
         # Sometimes it even tries a 22-byte fake hash, but we can
         # return 21 and it'll work out
         m[b'foo'] = want + b'+'
         self.assertEqual(want, m[b'foo'])
         # make sure the suffix survives a copy
         match = matchmod.match(b'', b'', [b're:foo'])
         m2 = m.matches(match)
         self.assertEqual(want, m2[b'foo'])
         self.assertEqual(1, len(m2))
         m2 = m.copy()
         self.assertEqual(want, m2[b'foo'])
         # suffix with iteration
         self.assertEqual([(b'bar/baz/qux.py', BIN_HASH_2),
                           (b'foo', want)],
                          list(m.items()))
 
         # shows up in diff
         self.assertEqual({b'foo': ((want, f), (h, b''))}, m.diff(clean))
         self.assertEqual({b'foo': ((h, b''), (want, f))}, clean.diff(m))
 
     def testMatchException(self):
         m = self.parsemanifest(A_SHORT_MANIFEST)
         match = matchmod.match(b'', b'', [b're:.*'])
         def filt(path):
             if path == b'foo':
                 assert False
             return True
         match.matchfn = filt
         with self.assertRaises(AssertionError):
             m.matches(match)
 
     def testRemoveItem(self):
         m = self.parsemanifest(A_SHORT_MANIFEST)
         del m[b'foo']
         with self.assertRaises(KeyError):
             m[b'foo']
         self.assertEqual(1, len(m))
         self.assertEqual(1, len(list(m)))
         # now restore and make sure everything works right
         m[b'foo'] = b'a' * 20
         self.assertEqual(2, len(m))
         self.assertEqual(2, len(list(m)))
 
     def testManifestDiff(self):
         MISSING = (None, b'')
         addl = b'z-only-in-left\0' + HASH_1 + b'\n'
         addr = b'z-only-in-right\0' + HASH_2 + b'x\n'
         left = self.parsemanifest(
             A_SHORT_MANIFEST.replace(HASH_1, HASH_3 + b'x') + addl)
         right = self.parsemanifest(A_SHORT_MANIFEST + addr)
         want = {
             b'foo': ((BIN_HASH_3, b'x'),
                      (BIN_HASH_1, b'')),
             b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
             b'z-only-in-right': (MISSING, (BIN_HASH_2, b'x')),
             }
         self.assertEqual(want, left.diff(right))
 
         want = {
             b'bar/baz/qux.py': (MISSING, (BIN_HASH_2, b'l')),
             b'foo': (MISSING, (BIN_HASH_3, b'x')),
             b'z-only-in-left': (MISSING, (BIN_HASH_1, b'')),
             }
         self.assertEqual(want, self.parsemanifest(EMTPY_MANIFEST).diff(left))
 
         want = {
             b'bar/baz/qux.py': ((BIN_HASH_2, b'l'), MISSING),
             b'foo': ((BIN_HASH_3, b'x'), MISSING),
             b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
             }
         self.assertEqual(want, left.diff(self.parsemanifest(EMTPY_MANIFEST)))
         copy = right.copy()
         del copy[b'z-only-in-right']
         del right[b'foo']
         want = {
             b'foo': (MISSING, (BIN_HASH_1, b'')),
             b'z-only-in-right': ((BIN_HASH_2, b'x'), MISSING),
             }
         self.assertEqual(want, right.diff(copy))
 
         short = self.parsemanifest(A_SHORT_MANIFEST)
         pruned = short.copy()
         del pruned[b'foo']
         want = {
             b'foo': ((BIN_HASH_1, b''), MISSING),
             }
         self.assertEqual(want, short.diff(pruned))
         want = {
             b'foo': (MISSING, (BIN_HASH_1, b'')),
             }
         self.assertEqual(want, pruned.diff(short))
         want = {
             b'bar/baz/qux.py': None,
             b'foo': (MISSING, (BIN_HASH_1, b'')),
             }
         self.assertEqual(want, pruned.diff(short, clean=True))
 
     def testReversedLines(self):
         backwards = b''.join(
             l + b'\n' for l in reversed(A_SHORT_MANIFEST.split(b'\n')) if l)
         try:
             self.parsemanifest(backwards)
             self.fail('Should have raised ValueError')
         except ValueError as v:
             self.assertIn('Manifest lines not in sorted order.', str(v))
 
     def testNoTerminalNewline(self):
         try:
             self.parsemanifest(A_SHORT_MANIFEST + b'wat')
             self.fail('Should have raised ValueError')
         except ValueError as v:
             self.assertIn('Manifest did not end in a newline.', str(v))
 
     def testNoNewLineAtAll(self):
         try:
             self.parsemanifest(b'wat')
             self.fail('Should have raised ValueError')
         except ValueError as v:
             self.assertIn('Manifest did not end in a newline.', str(v))
 
     def testHugeManifest(self):
         m = self.parsemanifest(A_HUGE_MANIFEST)
         self.assertEqual(HUGE_MANIFEST_ENTRIES, len(m))
         self.assertEqual(len(m), len(list(m)))
 
     def testMatchesMetadata(self):
         '''Tests matches() for a few specific files to make sure that both
         the set of files as well as their flags and nodeids are correct in
         the resulting manifest.'''
         m = self.parsemanifest(A_HUGE_MANIFEST)
 
         match = matchmod.match(b'/', b'',
                 [b'file1', b'file200', b'file300'], exact=True)
         m2 = m.matches(match)
 
         w = (b'file1\0%sx\n'
              b'file200\0%sl\n'
              b'file300\0%s\n') % (HASH_2, HASH_1, HASH_1)
         self.assertEqual(w, m2.text())
 
     def testMatchesNonexistentFile(self):
         '''Tests matches() for a small set of specific files, including one
         nonexistent file to make sure in only matches against existing files.
         '''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'',
                 [b'a/b/c/bar.txt', b'a/b/d/qux.py',
                  b'readme.txt', b'nonexistent'],
                 exact=True)
         m2 = m.matches(match)
 
         self.assertEqual(
                 [b'a/b/c/bar.txt', b'a/b/d/qux.py', b'readme.txt'],
                 m2.keys())
 
     def testMatchesNonexistentDirectory(self):
         '''Tests matches() for a relpath match on a directory that doesn't
         actually exist.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'', [b'a/f'], default=b'relpath')
         m2 = m.matches(match)
 
         self.assertEqual([], m2.keys())
 
     def testMatchesExactLarge(self):
         '''Tests matches() for files matching a large list of exact files.
         '''
         m = self.parsemanifest(A_HUGE_MANIFEST)
 
         flist = m.keys()[80:300]
         match = matchmod.match(b'/', b'', flist, exact=True)
         m2 = m.matches(match)
 
         self.assertEqual(flist, m2.keys())
 
     def testMatchesFull(self):
         '''Tests matches() for what should be a full match.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'', [b''])
         m2 = m.matches(match)
 
         self.assertEqual(m.keys(), m2.keys())
 
     def testMatchesDirectory(self):
         '''Tests matches() on a relpath match on a directory, which should
         match against all files within said directory.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'', [b'a/b'], default=b'relpath')
         m2 = m.matches(match)
 
         self.assertEqual([
             b'a/b/c/bar.py', b'a/b/c/bar.txt', b'a/b/c/foo.py',
             b'a/b/c/foo.txt',
             b'a/b/d/baz.py', b'a/b/d/qux.py', b'a/b/d/ten.txt', b'a/b/dog.py',
             b'a/b/fish.py'], m2.keys())
 
     def testMatchesExactPath(self):
         '''Tests matches() on an exact match on a directory, which should
         result in an empty manifest because you can't perform an exact match
         against a directory.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'', [b'a/b'], exact=True)
         m2 = m.matches(match)
 
         self.assertEqual([], m2.keys())
 
     def testMatchesCwd(self):
         '''Tests matches() on a relpath match with the current directory ('.')
         when not in the root directory.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'a/b', [b'.'], default=b'relpath')
         m2 = m.matches(match)
 
         self.assertEqual([
             b'a/b/c/bar.py', b'a/b/c/bar.txt', b'a/b/c/foo.py',
             b'a/b/c/foo.txt', b'a/b/d/baz.py', b'a/b/d/qux.py',
             b'a/b/d/ten.txt', b'a/b/dog.py', b'a/b/fish.py'], m2.keys())
 
     def testMatchesWithPattern(self):
         '''Tests matches() for files matching a pattern that reside
         deeper than the specified directory.'''
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         match = matchmod.match(b'/', b'', [b'a/b/*/*.txt'])
         m2 = m.matches(match)
 
         self.assertEqual(
                 [b'a/b/c/bar.txt', b'a/b/c/foo.txt', b'a/b/d/ten.txt'],
                 m2.keys())
 
 class testmanifestdict(unittest.TestCase, basemanifesttests):
     def parsemanifest(self, text):
         return manifestmod.manifestdict(text)
 
 class testtreemanifest(unittest.TestCase, basemanifesttests):
     def parsemanifest(self, text):
         return manifestmod.treemanifest(b'', text)
 
     def testWalkSubtrees(self):
         m = self.parsemanifest(A_DEEPER_MANIFEST)
 
         dirs = [s._dir for s in m.walksubtrees()]
         self.assertEqual(
             sorted([
                 b'', b'a/', b'a/c/', b'a/d/', b'a/b/', b'a/b/c/', b'a/b/d/']),
             sorted(dirs)
         )
 
         match = matchmod.match(b'/', b'', [b'path:a/b/'])
         dirs = [s._dir for s in m.walksubtrees(matcher=match)]
         self.assertEqual(
             sorted([b'a/b/', b'a/b/c/', b'a/b/d/']),
             sorted(dirs)
         )
 
 if __name__ == '__main__':
     silenttestrunner.main(__name__)

tests/test-upgrade-repo.t

@@ -1,702 +1,697 b''
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > share =
   > EOF
 
 store and revlogv1 are required in source
 
   $ hg --config format.usestore=false init no-store
   $ hg -R no-store debugupgraderepo
   abort: cannot upgrade repository; requirement missing: store
   [255]
 
   $ hg init no-revlogv1
   $ cat > no-revlogv1/.hg/requires << EOF
   > dotencode
   > fncache
   > generaldelta
   > store
   > EOF
 
   $ hg -R no-revlogv1 debugupgraderepo
   abort: cannot upgrade repository; requirement missing: revlogv1
   [255]
 
 Cannot upgrade shared repositories
 
   $ hg init share-parent
   $ hg -q share share-parent share-child
 
   $ hg -R share-child debugupgraderepo
   abort: cannot upgrade repository; unsupported source requirement: shared
   [255]
 
-Do not yet support upgrading manifestv2 and treemanifest repos
-
-  $ hg --config experimental.manifestv2=true init manifestv2
-  $ hg -R manifestv2 debugupgraderepo
-  abort: cannot upgrade repository; unsupported source requirement: manifestv2
-  [255]
+Do not yet support upgrading treemanifest repos
 
   $ hg --config experimental.treemanifest=true init treemanifest
   $ hg -R treemanifest debugupgraderepo
   abort: cannot upgrade repository; unsupported source requirement: treemanifest
   [255]
 
-Cannot add manifestv2 or treemanifest requirement during upgrade
+Cannot add treemanifest requirement during upgrade
 
   $ hg init disallowaddedreq
-  $ hg -R disallowaddedreq --config experimental.manifestv2=true --config experimental.treemanifest=true debugupgraderepo
-  abort: cannot upgrade repository; do not support adding requirement: manifestv2, treemanifest
+  $ hg -R disallowaddedreq --config experimental.treemanifest=true debugupgraderepo
+  abort: cannot upgrade repository; do not support adding requirement: treemanifest
   [255]
 
 An upgrade of a repository created with recommended settings only suggests optimizations
 
   $ hg init empty
   $ cd empty
   $ hg debugformat
   format-variant repo
   fncache:        yes
   dotencode:      yes
   generaldelta:   yes
   plain-cl-delta: yes
   compression:    zlib
   $ hg debugformat --verbose
   format-variant repo config default
   fncache:        yes    yes     yes
   dotencode:      yes    yes     yes
   generaldelta:   yes    yes     yes
   plain-cl-delta: yes    yes     yes
   compression:    zlib   zlib    zlib
   $ hg debugformat --verbose --config format.usegfncache=no
   format-variant repo config default
   fncache:        yes    yes     yes
   dotencode:      yes    yes     yes
   generaldelta:   yes    yes     yes
   plain-cl-delta: yes    yes     yes
   compression:    zlib   zlib    zlib
   $ hg debugformat --verbose --config format.usegfncache=no --color=debug
   format-variant repo config default
   [formatvariant.name.uptodate|fncache:       ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|dotencode:     ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|generaldelta:  ][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|plain-cl-delta:][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|compression:   ][formatvariant.repo.uptodate| zlib][formatvariant.config.default|   zlib][formatvariant.default|    zlib]
   $ hg debugformat -Tjson
   [
    {
     "config": true,
     "default": true,
     "name": "fncache",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "dotencode",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "generaldelta",
     "repo": true
    },
    {
     "config": true,
     "default": true,
     "name": "plain-cl-delta",
     "repo": true
    },
    {
     "config": "zlib",
     "default": "zlib",
     "name": "compression",
     "repo": "zlib"
    }
   ]
   $ hg debugupgraderepo
   (no feature deficiencies found in existing repository)
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   additional optimizations are available by specifying "--optimize <name>":
   
   redeltaparent
      deltas within internal storage will be recalculated to choose an optimal base revision where this was not already done; the size of the repository may shrink and various operations may become faster; the first time this optimization is performed could slow down upgrade execution considerably; subsequent invocations should not run noticeably slower
   
   redeltamultibase
      deltas within internal storage will be recalculated against multiple base revision and the smallest difference will be used; the size of the repository may shrink significantly when there are many merges; this optimization will slow down execution in proportion to the number of merges in the repository and the amount of files in the repository; this slow down should not be significant unless there are tens of thousands of files and thousands of merges
   
   redeltaall
      deltas within internal storage will always be recalculated without reusing prior deltas; this will likely make execution run several times slower; this optimization is typically not needed
   
   redeltafulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "redeltaall" but even slower since more logic is involved.
   
 
 --optimize can be used to add optimizations
 
   $ hg debugupgrade --optimize redeltaparent
   (no feature deficiencies found in existing repository)
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   redeltaparent
      deltas within internal storage will choose a new base revision if needed
   
   additional optimizations are available by specifying "--optimize <name>":
   
   redeltamultibase
      deltas within internal storage will be recalculated against multiple base revision and the smallest difference will be used; the size of the repository may shrink significantly when there are many merges; this optimization will slow down execution in proportion to the number of merges in the repository and the amount of files in the repository; this slow down should not be significant unless there are tens of thousands of files and thousands of merges
   
   redeltaall
      deltas within internal storage will always be recalculated without reusing prior deltas; this will likely make execution run several times slower; this optimization is typically not needed
   
   redeltafulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "redeltaall" but even slower since more logic is involved.
   
 
 Various sub-optimal detections work
 
   $ cat > .hg/requires << EOF
   > revlogv1
   > store
   > EOF
 
   $ hg debugformat
   format-variant repo
   fncache:         no
   dotencode:       no
   generaldelta:    no
   plain-cl-delta: yes
   compression:    zlib
   $ hg debugformat --verbose
   format-variant repo config default
   fncache:         no    yes     yes
   dotencode:       no    yes     yes
   generaldelta:    no    yes     yes
   plain-cl-delta: yes    yes     yes
   compression:    zlib   zlib    zlib
   $ hg debugformat --verbose --config format.usegeneraldelta=no
   format-variant repo config default
   fncache:         no    yes     yes
   dotencode:       no    yes     yes
   generaldelta:    no     no     yes
   plain-cl-delta: yes    yes     yes
   compression:    zlib   zlib    zlib
   $ hg debugformat --verbose --config format.usegeneraldelta=no --color=debug
   format-variant repo config default
   [formatvariant.name.mismatchconfig|fncache:       ][formatvariant.repo.mismatchconfig|  no][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.mismatchconfig|dotencode:     ][formatvariant.repo.mismatchconfig|  no][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.mismatchdefault|generaldelta:  ][formatvariant.repo.mismatchdefault|  no][formatvariant.config.special|     no][formatvariant.default|     yes]
   [formatvariant.name.uptodate|plain-cl-delta:][formatvariant.repo.uptodate| yes][formatvariant.config.default|    yes][formatvariant.default|     yes]
   [formatvariant.name.uptodate|compression:   ][formatvariant.repo.uptodate| zlib][formatvariant.config.default|   zlib][formatvariant.default|    zlib]
   $ hg debugupgraderepo
   repository lacks features recommended by current config options:
   
   fncache
      long and reserved filenames may not work correctly; repository performance is sub-optimal
   
   dotencode
      storage of filenames beginning with a period or space may not work correctly
   
   generaldelta
      deltas within internal storage are unable to choose optimal revisions; repository is larger and slower than it could be; interaction with other repositories may require extra network and CPU resources, making "hg push" and "hg pull" slower
   
   
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: revlogv1, store
      added: dotencode, fncache, generaldelta
   
   fncache
      repository will be more resilient to storing certain paths and performance of certain operations should be improved
   
   dotencode
      repository will be better able to store files beginning with a space or period
   
   generaldelta
      repository storage will be able to create optimal deltas; new repository data will be smaller and read times should decrease; interacting with other repositories using this storage model should require less network and CPU resources, making "hg push" and "hg pull" faster
   
   additional optimizations are available by specifying "--optimize <name>":
   
   redeltaparent
      deltas within internal storage will be recalculated to choose an optimal base revision where this was not already done; the size of the repository may shrink and various operations may become faster; the first time this optimization is performed could slow down upgrade execution considerably; subsequent invocations should not run noticeably slower
   
   redeltamultibase
      deltas within internal storage will be recalculated against multiple base revision and the smallest difference will be used; the size of the repository may shrink significantly when there are many merges; this optimization will slow down execution in proportion to the number of merges in the repository and the amount of files in the repository; this slow down should not be significant unless there are tens of thousands of files and thousands of merges
   
   redeltaall
      deltas within internal storage will always be recalculated without reusing prior deltas; this will likely make execution run several times slower; this optimization is typically not needed
   
   redeltafulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "redeltaall" but even slower since more logic is involved.
   
 
   $ hg --config format.dotencode=false debugupgraderepo
   repository lacks features recommended by current config options:
   
   fncache
      long and reserved filenames may not work correctly; repository performance is sub-optimal
   
   generaldelta
      deltas within internal storage are unable to choose optimal revisions; repository is larger and slower than it could be; interaction with other repositories may require extra network and CPU resources, making "hg push" and "hg pull" slower
   
   repository lacks features used by the default config options:
   
   dotencode
      storage of filenames beginning with a period or space may not work correctly
   
   
   performing an upgrade with "--run" will make the following changes:
   
   requirements
      preserved: revlogv1, store
      added: fncache, generaldelta
   
   fncache
      repository will be more resilient to storing certain paths and performance of certain operations should be improved
   
   generaldelta
      repository storage will be able to create optimal deltas; new repository data will be smaller and read times should decrease; interacting with other repositories using this storage model should require less network and CPU resources, making "hg push" and "hg pull" faster
   
   additional optimizations are available by specifying "--optimize <name>":
   
   redeltaparent
      deltas within internal storage will be recalculated to choose an optimal base revision where this was not already done; the size of the repository may shrink and various operations may become faster; the first time this optimization is performed could slow down upgrade execution considerably; subsequent invocations should not run noticeably slower
   
   redeltamultibase
      deltas within internal storage will be recalculated against multiple base revision and the smallest difference will be used; the size of the repository may shrink significantly when there are many merges; this optimization will slow down execution in proportion to the number of merges in the repository and the amount of files in the repository; this slow down should not be significant unless there are tens of thousands of files and thousands of merges
   
   redeltaall
      deltas within internal storage will always be recalculated without reusing prior deltas; this will likely make execution run several times slower; this optimization is typically not needed
   
   redeltafulladd
      every revision will be re-added as if it was new content. It will go through the full storage mechanism giving extensions a chance to process it (eg. lfs). This is similar to "redeltaall" but even slower since more logic is involved.
   
 
   $ cd ..
 
 Upgrading a repository that is already modern essentially no-ops
 
   $ hg init modern
   $ hg -R modern debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/modern/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/modern/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/modern/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/modern/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
 Upgrading a repository to generaldelta works
 
   $ hg --config format.usegeneraldelta=false init upgradegd
   $ cd upgradegd
   $ touch f0
   $ hg -q commit -A -m initial
   $ touch f1
   $ hg -q commit -A -m 'add f1'
   $ hg -q up -r 0
   $ touch f2
   $ hg -q commit -A -m 'add f2'
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, revlogv1, store
      added: generaldelta
   
   generaldelta
      repository storage will be able to create optimal deltas; new repository data will be smaller and read times should decrease; interacting with other repositories using this storage model should require less network and CPU resources, making "hg push" and "hg pull" faster
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 9 total revisions (3 in filelogs, 3 in manifests, 3 in changelog)
   migrating 341 bytes in store; 401 bytes tracked data
   migrating 3 filelogs containing 3 revisions (0 bytes in store; 0 bytes tracked data)
   finished migrating 3 filelog revisions across 3 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 3 revisions (157 bytes in store; 220 bytes tracked data)
   finished migrating 3 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 3 revisions (184 bytes in store; 181 bytes tracked data)
   finished migrating 3 changelog revisions; change in size: 0 bytes
   finished migrating 9 total revisions; total change in store size: 0 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/upgradegd/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/upgradegd/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
 Original requirements backed up
 
   $ cat .hg/upgradebackup.*/requires
   dotencode
   fncache
   revlogv1
   store
 
 generaldelta added to original requirements files
 
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   revlogv1
   store
 
 store directory has files we expect
 
   $ ls .hg/store
   00changelog.i
   00manifest.i
   data
   fncache
   phaseroots
   undo
   undo.backupfiles
   undo.phaseroots
 
 manifest should be generaldelta
 
   $ hg debugrevlog -m | grep flags
   flags  : inline, generaldelta
 
 verify should be happy
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   3 files, 3 changesets, 3 total revisions
 
 old store should be backed up
 
   $ ls .hg/upgradebackup.*/store
   00changelog.i
   00manifest.i
   data
   fncache
   phaseroots
   undo
   undo.backup.fncache
   undo.backupfiles
   undo.phaseroots
 
   $ cd ..
 
 store files with special filenames aren't encoded during copy
 
   $ hg init store-filenames
   $ cd store-filenames
   $ touch foo
   $ hg -q commit -A -m initial
   $ touch .hg/store/.XX_special_filename
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 109 bytes in store; 107 bytes tracked data
   migrating 1 filelogs containing 1 revisions (0 bytes in store; 0 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (46 bytes in store; 45 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (63 bytes in store; 62 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying .XX_special_filename
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ hg debugupgraderepo --run --optimize redeltafulladd
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   redeltafulladd
      each revision will be added as new content to the internal storage; this will likely drastically slow down execution time, but some extensions might need it
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 109 bytes in store; 107 bytes tracked data
   migrating 1 filelogs containing 1 revisions (0 bytes in store; 0 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (46 bytes in store; 45 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (63 bytes in store; 62 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying .XX_special_filename
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/store-filenames/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/store-filenames/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
   $ cd ..
 
 Check upgrading a large file repository
 ---------------------------------------
 
   $ hg init largefilesrepo
   $ cat << EOF >> largefilesrepo/.hg/hgrc
   > [extensions]
   > largefiles =
   > EOF
 
   $ cd largefilesrepo
   $ touch foo
   $ hg add --large foo
   $ hg -q commit -m initial
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   largefiles
   revlogv1
   store
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, largefiles, revlogv1, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 3 total revisions (1 in filelogs, 1 in manifests, 1 in changelog)
   migrating 163 bytes in store; 160 bytes tracked data
   migrating 1 filelogs containing 1 revisions (42 bytes in store; 41 bytes tracked data)
   finished migrating 1 filelog revisions across 1 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 1 revisions (52 bytes in store; 51 bytes tracked data)
   finished migrating 1 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 1 revisions (69 bytes in store; 68 bytes tracked data)
   finished migrating 1 changelog revisions; change in size: 0 bytes
   finished migrating 3 total revisions; total change in store size: 0 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ cat .hg/requires
   dotencode
   fncache
   generaldelta
   largefiles
   revlogv1
   store
 
   $ cat << EOF >> .hg/hgrc
   > [extensions]
   > lfs =
   > [lfs]
   > threshold = 10
   > EOF
   $ echo '123456789012345' > lfs.bin
   $ hg ci -Am 'lfs.bin'
   adding lfs.bin
   $ grep lfs .hg/requires
   lfs
   $ find .hg/store/lfs -type f
   .hg/store/lfs/objects/d0/beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
 
   $ hg debugupgraderepo --run
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, largefiles, lfs, revlogv1, store
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 6 total revisions (2 in filelogs, 2 in manifests, 2 in changelog)
   migrating 417 bytes in store; 467 bytes tracked data
   migrating 2 filelogs containing 2 revisions (168 bytes in store; 182 bytes tracked data)
   finished migrating 2 filelog revisions across 2 filelogs; change in size: 0 bytes
   migrating 1 manifests containing 2 revisions (113 bytes in store; 151 bytes tracked data)
   finished migrating 2 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 2 revisions (136 bytes in store; 134 bytes tracked data)
   finished migrating 2 changelog revisions; change in size: 0 bytes
   finished migrating 6 total revisions; total change in store size: 0 bytes
   copying phaseroots
   copying lfs blob d0beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/largefilesrepo/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/largefilesrepo/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
 
   $ grep lfs .hg/requires
   lfs
   $ find .hg/store/lfs -type f
   .hg/store/lfs/objects/d0/beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   2 files, 2 changesets, 2 total revisions
   $ hg debugdata lfs.bin 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:d0beab232adff5ba365880366ad30b1edb85c4c5372442b5d2fe27adc96d653f
   size 16
   x-is-binary 0
 
   $ cd ..
 
 repository config is taken in account
 -------------------------------------
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > maxchainlen = 1
   > EOF
 
   $ hg init localconfig
   $ cd localconfig
   $ cat << EOF > file
   > some content
   > with some length
   > to make sure we get a delta
   > after changes
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > very long
   > EOF
   $ hg -q commit -A -m A
   $ echo "new line" >> file
   $ hg -q commit -m B
   $ echo "new line" >> file
   $ hg -q commit -m C
 
   $ cat << EOF >> .hg/hgrc
   > [format]
   > maxchainlen = 9001
   > EOF
   $ hg config format
   format.maxchainlen=9001
   $ hg debugindex file
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      77     -1       0 bcc1d3df78b2 000000000000 000000000000
        1        77      21      0       1 af3e29f7a72e bcc1d3df78b2 000000000000
        2        98      84     -1       2 8daf79c5522b af3e29f7a72e 000000000000
 
   $ hg debugupgraderepo --run --optimize redeltaall
   upgrade will perform the following actions:
   
   requirements
      preserved: dotencode, fncache, generaldelta, revlogv1, store
   
   redeltaall
      deltas within internal storage will be fully recomputed; this will likely drastically slow down execution time
   
   beginning upgrade...
   repository locked and read-only
   creating temporary repository to stage migrated data: $TESTTMP/localconfig/.hg/upgrade.* (glob)
   (it is safe to interrupt this process any time before data migration completes)
   migrating 9 total revisions (3 in filelogs, 3 in manifests, 3 in changelog)
   migrating 497 bytes in store; 882 bytes tracked data
   migrating 1 filelogs containing 3 revisions (182 bytes in store; 573 bytes tracked data)
   finished migrating 3 filelog revisions across 1 filelogs; change in size: -63 bytes
   migrating 1 manifests containing 3 revisions (141 bytes in store; 138 bytes tracked data)
   finished migrating 3 manifest revisions across 1 manifests; change in size: 0 bytes
   migrating changelog containing 3 revisions (174 bytes in store; 171 bytes tracked data)
   finished migrating 3 changelog revisions; change in size: 0 bytes
   finished migrating 9 total revisions; total change in store size: -63 bytes
   copying phaseroots
   data fully migrated to temporary repository
   marking source repository as being upgraded; clients will be unable to read from repository
   starting in-place swap of repository data
   replaced files will be backed up at $TESTTMP/localconfig/.hg/upgradebackup.* (glob)
   replacing store...
   store replacement complete; repository was inconsistent for *s (glob)
   finalizing requirements file and making repository readable again
   removing temporary repository $TESTTMP/localconfig/.hg/upgrade.* (glob)
   copy of old repository backed up at $TESTTMP/localconfig/.hg/upgradebackup.* (glob)
   the old repository will not be deleted; remove it to free up disk space once the upgraded repository is verified
   $ hg debugindex file
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      77     -1       0 bcc1d3df78b2 000000000000 000000000000
        1        77      21      0       1 af3e29f7a72e bcc1d3df78b2 000000000000
        2        98      21      1       2 8daf79c5522b af3e29f7a72e 000000000000
   $ cd ..
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > maxchainlen = 9001
   > EOF