copies: add an devel option to trace all files

Filelog based copy tracing only trace copy for file that have been added. This
is a trade off between skipping some rare copy case in exchange for avoiding
atrocious-to-the-point-of-unusable performance.

The changeset centric copy tracing does not need this trade off and naturally
trace all copy, include the one involving non-new files.

In order to ease the comparison from both algorithm, we add a small devel option
to trace copy for all files in the target revisions.

Differential Revision: https://phab.mercurial-scm.org/D9796

mercurial/configitems.py

@@ -1,2599 +1,2605
 # 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 = b"extension '%s' overwrite config item '%s.%s'"
             msg %= (extname, section, key)
             ui.develwarn(msg, config=b'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,
         experimental=False,
     ):
         self.section = section
         self.name = name
         self.default = default
         self.alias = list(alias)
         self.generic = generic
         self.priority = priority
         self.experimental = experimental
         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 = b"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)
 
 
 def _registerdiffopts(section, configprefix=b''):
     coreconfigitem(
         section,
         configprefix + b'nodates',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'showfunc',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'unified',
         default=None,
     )
     coreconfigitem(
         section,
         configprefix + b'git',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'ignorews',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'ignorewsamount',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'ignoreblanklines',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'ignorewseol',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'nobinary',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'noprefix',
         default=False,
     )
     coreconfigitem(
         section,
         configprefix + b'word-diff',
         default=False,
     )
 
 
 coreconfigitem(
     b'alias',
     b'.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'auth',
     b'cookiefile',
     default=None,
 )
 _registerdiffopts(section=b'annotate')
 # bookmarks.pushing: internal hack for discovery
 coreconfigitem(
     b'bookmarks',
     b'pushing',
     default=list,
 )
 # bundle.mainreporoot: internal hack for bundlerepo
 coreconfigitem(
     b'bundle',
     b'mainreporoot',
     default=b'',
 )
 coreconfigitem(
     b'censor',
     b'policy',
     default=b'abort',
     experimental=True,
 )
 coreconfigitem(
     b'chgserver',
     b'idletimeout',
     default=3600,
 )
 coreconfigitem(
     b'chgserver',
     b'skiphash',
     default=False,
 )
 coreconfigitem(
     b'cmdserver',
     b'log',
     default=None,
 )
 coreconfigitem(
     b'cmdserver',
     b'max-log-files',
     default=7,
 )
 coreconfigitem(
     b'cmdserver',
     b'max-log-size',
     default=b'1 MB',
 )
 coreconfigitem(
     b'cmdserver',
     b'max-repo-cache',
     default=0,
     experimental=True,
 )
 coreconfigitem(
     b'cmdserver',
     b'message-encodings',
     default=list,
 )
 coreconfigitem(
     b'cmdserver',
     b'track-log',
     default=lambda: [b'chgserver', b'cmdserver', b'repocache'],
 )
 coreconfigitem(
     b'cmdserver',
     b'shutdown-on-interrupt',
     default=True,
 )
 coreconfigitem(
     b'color',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'color',
     b'mode',
     default=b'auto',
 )
 coreconfigitem(
     b'color',
     b'pagermode',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'command-templates',
     b'graphnode',
     default=None,
     alias=[(b'ui', b'graphnodetemplate')],
 )
 coreconfigitem(
     b'command-templates',
     b'log',
     default=None,
     alias=[(b'ui', b'logtemplate')],
 )
 coreconfigitem(
     b'command-templates',
     b'mergemarker',
     default=(
         b'{node|short} '
         b'{ifeq(tags, "tip", "", '
         b'ifeq(tags, "", "", "{tags} "))}'
         b'{if(bookmarks, "{bookmarks} ")}'
         b'{ifeq(branch, "default", "", "{branch} ")}'
         b'- {author|user}: {desc|firstline}'
     ),
     alias=[(b'ui', b'mergemarkertemplate')],
 )
 coreconfigitem(
     b'command-templates',
     b'pre-merge-tool-output',
     default=None,
     alias=[(b'ui', b'pre-merge-tool-output-template')],
 )
 coreconfigitem(
     b'command-templates',
     b'oneline-summary',
     default=None,
 )
 coreconfigitem(
     b'command-templates',
     b'oneline-summary.*',
     default=dynamicdefault,
     generic=True,
 )
 _registerdiffopts(section=b'commands', configprefix=b'commit.interactive.')
 coreconfigitem(
     b'commands',
     b'commit.post-status',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'grep.all-files',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'commands',
     b'merge.require-rev',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'push.require-revs',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'resolve.confirm',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'resolve.explicit-re-merge',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'resolve.mark-check',
     default=b'none',
 )
 _registerdiffopts(section=b'commands', configprefix=b'revert.interactive.')
 coreconfigitem(
     b'commands',
     b'show.aliasprefix',
     default=list,
 )
 coreconfigitem(
     b'commands',
     b'status.relative',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'status.skipstates',
     default=[],
     experimental=True,
 )
 coreconfigitem(
     b'commands',
     b'status.terse',
     default=b'',
 )
 coreconfigitem(
     b'commands',
     b'status.verbose',
     default=False,
 )
 coreconfigitem(
     b'commands',
     b'update.check',
     default=None,
 )
 coreconfigitem(
     b'commands',
     b'update.requiredest',
     default=False,
 )
 coreconfigitem(
     b'committemplate',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'convert',
     b'bzr.saverev',
     default=True,
 )
 coreconfigitem(
     b'convert',
     b'cvsps.cache',
     default=True,
 )
 coreconfigitem(
     b'convert',
     b'cvsps.fuzz',
     default=60,
 )
 coreconfigitem(
     b'convert',
     b'cvsps.logencoding',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'cvsps.mergefrom',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'cvsps.mergeto',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'git.committeractions',
     default=lambda: [b'messagedifferent'],
 )
 coreconfigitem(
     b'convert',
     b'git.extrakeys',
     default=list,
 )
 coreconfigitem(
     b'convert',
     b'git.findcopiesharder',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'git.remoteprefix',
     default=b'remote',
 )
 coreconfigitem(
     b'convert',
     b'git.renamelimit',
     default=400,
 )
 coreconfigitem(
     b'convert',
     b'git.saverev',
     default=True,
 )
 coreconfigitem(
     b'convert',
     b'git.similarity',
     default=50,
 )
 coreconfigitem(
     b'convert',
     b'git.skipsubmodules',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'hg.clonebranches',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'hg.ignoreerrors',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'hg.preserve-hash',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'hg.revs',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'hg.saverev',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'hg.sourcename',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'hg.startrev',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'hg.tagsbranch',
     default=b'default',
 )
 coreconfigitem(
     b'convert',
     b'hg.usebranchnames',
     default=True,
 )
 coreconfigitem(
     b'convert',
     b'ignoreancestorcheck',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'convert',
     b'localtimezone',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'p4.encoding',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'convert',
     b'p4.startrev',
     default=0,
 )
 coreconfigitem(
     b'convert',
     b'skiptags',
     default=False,
 )
 coreconfigitem(
     b'convert',
     b'svn.debugsvnlog',
     default=True,
 )
 coreconfigitem(
     b'convert',
     b'svn.trunk',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'svn.tags',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'svn.branches',
     default=None,
 )
 coreconfigitem(
     b'convert',
     b'svn.startrev',
     default=0,
 )
 coreconfigitem(
     b'convert',
     b'svn.dangerous-set-commit-dates',
     default=False,
 )
 coreconfigitem(
     b'debug',
     b'dirstate.delaywrite',
     default=0,
 )
 coreconfigitem(
     b'defaults',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'devel',
     b'all-warnings',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'bundle2.debug',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'bundle.delta',
     default=b'',
 )
 coreconfigitem(
     b'devel',
     b'cache-vfs',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'check-locks',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'check-relroot',
     default=False,
 )
+# Track copy information for all file, not just "added" one (very slow)
+coreconfigitem(
+    b'devel',
+    b'copy-tracing.trace-all-files',
+    default=False,
+)
 coreconfigitem(
     b'devel',
     b'default-date',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'deprec-warn',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'disableloaddefaultcerts',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'warn-empty-changegroup',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'legacy.exchange',
     default=list,
 )
 # When True, revlogs use a special reference version of the nodemap, that is not
 # performant but is "known" to behave properly.
 coreconfigitem(
     b'devel',
     b'persistent-nodemap',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'servercafile',
     default=b'',
 )
 coreconfigitem(
     b'devel',
     b'serverexactprotocol',
     default=b'',
 )
 coreconfigitem(
     b'devel',
     b'serverrequirecert',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'strip-obsmarkers',
     default=True,
 )
 coreconfigitem(
     b'devel',
     b'warn-config',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'warn-config-default',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'user.obsmarker',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'warn-config-unknown',
     default=None,
 )
 coreconfigitem(
     b'devel',
     b'debug.copies',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'debug.extensions',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'debug.repo-filters',
     default=False,
 )
 coreconfigitem(
     b'devel',
     b'debug.peer-request',
     default=False,
 )
 # If discovery.exchange-heads is False, the discovery will not start with
 # remote head fetching and local head querying.
 coreconfigitem(
     b'devel',
     b'discovery.exchange-heads',
     default=True,
 )
 # If discovery.grow-sample is False, the sample size used in set discovery will
 # not be increased through the process
 coreconfigitem(
     b'devel',
     b'discovery.grow-sample',
     default=True,
 )
 # discovery.grow-sample.rate control the rate at which the sample grow
 coreconfigitem(
     b'devel',
     b'discovery.grow-sample.rate',
     default=1.05,
 )
 # If discovery.randomize is False, random sampling during discovery are
 # deterministic. It is meant for integration tests.
 coreconfigitem(
     b'devel',
     b'discovery.randomize',
     default=True,
 )
 # Control the initial size of the discovery sample
 coreconfigitem(
     b'devel',
     b'discovery.sample-size',
     default=200,
 )
 # Control the initial size of the discovery for initial change
 coreconfigitem(
     b'devel',
     b'discovery.sample-size.initial',
     default=100,
 )
 _registerdiffopts(section=b'diff')
 coreconfigitem(
     b'email',
     b'bcc',
     default=None,
 )
 coreconfigitem(
     b'email',
     b'cc',
     default=None,
 )
 coreconfigitem(
     b'email',
     b'charsets',
     default=list,
 )
 coreconfigitem(
     b'email',
     b'from',
     default=None,
 )
 coreconfigitem(
     b'email',
     b'method',
     default=b'smtp',
 )
 coreconfigitem(
     b'email',
     b'reply-to',
     default=None,
 )
 coreconfigitem(
     b'email',
     b'to',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'archivemetatemplate',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'experimental',
     b'auto-publish',
     default=b'publish',
 )
 coreconfigitem(
     b'experimental',
     b'bundle-phases',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'bundle2-advertise',
     default=True,
 )
 coreconfigitem(
     b'experimental',
     b'bundle2-output-capture',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'bundle2.pushback',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'bundle2lazylocking',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'bundlecomplevel',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'bundlecomplevel.bzip2',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'bundlecomplevel.gzip',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'bundlecomplevel.none',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'bundlecomplevel.zstd',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'changegroup3',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'cleanup-as-archived',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'clientcompressionengines',
     default=list,
 )
 coreconfigitem(
     b'experimental',
     b'copytrace',
     default=b'on',
 )
 coreconfigitem(
     b'experimental',
     b'copytrace.movecandidateslimit',
     default=100,
 )
 coreconfigitem(
     b'experimental',
     b'copytrace.sourcecommitlimit',
     default=100,
 )
 coreconfigitem(
     b'experimental',
     b'copies.read-from',
     default=b"filelog-only",
 )
 coreconfigitem(
     b'experimental',
     b'copies.write-to',
     default=b'filelog-only',
 )
 coreconfigitem(
     b'experimental',
     b'crecordtest',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'directaccess',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'directaccess.revnums',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'editortmpinhg',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'evolution',
     default=list,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.allowdivergence',
     default=False,
     alias=[(b'experimental', b'allowdivergence')],
 )
 coreconfigitem(
     b'experimental',
     b'evolution.allowunstable',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.createmarkers',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.effect-flags',
     default=True,
     alias=[(b'experimental', b'effect-flags')],
 )
 coreconfigitem(
     b'experimental',
     b'evolution.exchange',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.bundle-obsmarker',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.bundle-obsmarker:mandatory',
     default=True,
 )
 coreconfigitem(
     b'experimental',
     b'log.topo',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.report-instabilities',
     default=True,
 )
 coreconfigitem(
     b'experimental',
     b'evolution.track-operation',
     default=True,
 )
 # repo-level config to exclude a revset visibility
 #
 # The target use case is to use `share` to expose different subset of the same
 # repository, especially server side. See also `server.view`.
 coreconfigitem(
     b'experimental',
     b'extra-filter-revs',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'maxdeltachainspan',
     default=-1,
 )
 # tracks files which were undeleted (merge might delete them but we explicitly
 # kept/undeleted them) and creates new filenodes for them
 coreconfigitem(
     b'experimental',
     b'merge-track-salvaged',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'mergetempdirprefix',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'mmapindexthreshold',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'narrow',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'nonnormalparanoidcheck',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'exportableenviron',
     default=list,
 )
 coreconfigitem(
     b'experimental',
     b'extendedheader.index',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'extendedheader.similarity',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'graphshorten',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'graphstyle.parent',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'experimental',
     b'graphstyle.missing',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'experimental',
     b'graphstyle.grandparent',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'experimental',
     b'hook-track-tags',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'httppeer.advertise-v2',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'httppeer.v2-encoder-order',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'httppostargs',
     default=False,
 )
 coreconfigitem(b'experimental', b'nointerrupt', default=False)
 coreconfigitem(b'experimental', b'nointerrupt-interactiveonly', default=True)
 
 coreconfigitem(
     b'experimental',
     b'obsmarkers-exchange-debug',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'remotenames',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'removeemptydirs',
     default=True,
 )
 coreconfigitem(
     b'experimental',
     b'revert.interactive.select-to-keep',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'revisions.prefixhexnode',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'revlogv2',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'revisions.disambiguatewithin',
     default=None,
 )
 coreconfigitem(
     b'experimental',
     b'rust.index',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'server.filesdata.recommended-batch-size',
     default=50000,
 )
 coreconfigitem(
     b'experimental',
     b'server.manifestdata.recommended-batch-size',
     default=100000,
 )
 coreconfigitem(
     b'experimental',
     b'server.stream-narrow-clones',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'single-head-per-branch',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'single-head-per-branch:account-closed-heads',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'single-head-per-branch:public-changes-only',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'sshserver.support-v2',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'sparse-read',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'sparse-read.density-threshold',
     default=0.50,
 )
 coreconfigitem(
     b'experimental',
     b'sparse-read.min-gap-size',
     default=b'65K',
 )
 coreconfigitem(
     b'experimental',
     b'treemanifest',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'update.atomic-file',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'sshpeer.advertise-v2',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'web.apiserver',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'web.api.http-v2',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'web.api.debugreflect',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'worker.wdir-get-thread-safe',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'worker.repository-upgrade',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'xdiff',
     default=False,
 )
 coreconfigitem(
     b'extensions',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'extdata',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'format',
     b'bookmarks-in-store',
     default=False,
 )
 coreconfigitem(
     b'format',
     b'chunkcachesize',
     default=None,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'dotencode',
     default=True,
 )
 coreconfigitem(
     b'format',
     b'generaldelta',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'manifestcachesize',
     default=None,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'maxchainlen',
     default=dynamicdefault,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'obsstore-version',
     default=None,
 )
 coreconfigitem(
     b'format',
     b'sparse-revlog',
     default=True,
 )
 coreconfigitem(
     b'format',
     b'revlog-compression',
     default=lambda: [b'zlib'],
     alias=[(b'experimental', b'format.compression')],
 )
 coreconfigitem(
     b'format',
     b'usefncache',
     default=True,
 )
 coreconfigitem(
     b'format',
     b'usegeneraldelta',
     default=True,
 )
 coreconfigitem(
     b'format',
     b'usestore',
     default=True,
 )
 coreconfigitem(
     b'format',
     b'use-persistent-nodemap',
     default=False,
 )
 coreconfigitem(
     b'format',
     b'exp-use-copies-side-data-changeset',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'exp-use-side-data',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'format',
     b'use-share-safe',
     default=False,
 )
 coreconfigitem(
     b'format',
     b'internal-phase',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'fsmonitor',
     b'warn_when_unused',
     default=True,
 )
 coreconfigitem(
     b'fsmonitor',
     b'warn_update_file_count',
     default=50000,
 )
 coreconfigitem(
     b'fsmonitor',
     b'warn_update_file_count_rust',
     default=400000,
 )
 coreconfigitem(
     b'help',
     br'hidden-command\..*',
     default=False,
     generic=True,
 )
 coreconfigitem(
     b'help',
     br'hidden-topic\..*',
     default=False,
     generic=True,
 )
 coreconfigitem(
     b'hooks',
     b'.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'hgweb-paths',
     b'.*',
     default=list,
     generic=True,
 )
 coreconfigitem(
     b'hostfingerprints',
     b'.*',
     default=list,
     generic=True,
 )
 coreconfigitem(
     b'hostsecurity',
     b'ciphers',
     default=None,
 )
 coreconfigitem(
     b'hostsecurity',
     b'minimumprotocol',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'hostsecurity',
     b'.*:minimumprotocol$',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'hostsecurity',
     b'.*:ciphers$',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'hostsecurity',
     b'.*:fingerprints$',
     default=list,
     generic=True,
 )
 coreconfigitem(
     b'hostsecurity',
     b'.*:verifycertsfile$',
     default=None,
     generic=True,
 )
 
 coreconfigitem(
     b'http_proxy',
     b'always',
     default=False,
 )
 coreconfigitem(
     b'http_proxy',
     b'host',
     default=None,
 )
 coreconfigitem(
     b'http_proxy',
     b'no',
     default=list,
 )
 coreconfigitem(
     b'http_proxy',
     b'passwd',
     default=None,
 )
 coreconfigitem(
     b'http_proxy',
     b'user',
     default=None,
 )
 
 coreconfigitem(
     b'http',
     b'timeout',
     default=None,
 )
 
 coreconfigitem(
     b'logtoprocess',
     b'commandexception',
     default=None,
 )
 coreconfigitem(
     b'logtoprocess',
     b'commandfinish',
     default=None,
 )
 coreconfigitem(
     b'logtoprocess',
     b'command',
     default=None,
 )
 coreconfigitem(
     b'logtoprocess',
     b'develwarn',
     default=None,
 )
 coreconfigitem(
     b'logtoprocess',
     b'uiblocked',
     default=None,
 )
 coreconfigitem(
     b'merge',
     b'checkunknown',
     default=b'abort',
 )
 coreconfigitem(
     b'merge',
     b'checkignored',
     default=b'abort',
 )
 coreconfigitem(
     b'experimental',
     b'merge.checkpathconflicts',
     default=False,
 )
 coreconfigitem(
     b'merge',
     b'followcopies',
     default=True,
 )
 coreconfigitem(
     b'merge',
     b'on-failure',
     default=b'continue',
 )
 coreconfigitem(
     b'merge',
     b'preferancestor',
     default=lambda: [b'*'],
     experimental=True,
 )
 coreconfigitem(
     b'merge',
     b'strict-capability-check',
     default=False,
 )
 coreconfigitem(
     b'merge-tools',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.args$',
     default=b"$local $base $other",
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.binary$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.check$',
     default=list,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.checkchanged$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.executable$',
     default=dynamicdefault,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.fixeol$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.gui$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.mergemarkers$',
     default=b'basic',
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.mergemarkertemplate$',
     default=dynamicdefault,  # take from command-templates.mergemarker
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.priority$',
     default=0,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.premerge$',
     default=dynamicdefault,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'merge-tools',
     br'.*\.symlink$',
     default=False,
     generic=True,
     priority=-1,
 )
 coreconfigitem(
     b'pager',
     b'attend-.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'pager',
     b'ignore',
     default=list,
 )
 coreconfigitem(
     b'pager',
     b'pager',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'patch',
     b'eol',
     default=b'strict',
 )
 coreconfigitem(
     b'patch',
     b'fuzz',
     default=2,
 )
 coreconfigitem(
     b'paths',
     b'default',
     default=None,
 )
 coreconfigitem(
     b'paths',
     b'default-push',
     default=None,
 )
 coreconfigitem(
     b'paths',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'phases',
     b'checksubrepos',
     default=b'follow',
 )
 coreconfigitem(
     b'phases',
     b'new-commit',
     default=b'draft',
 )
 coreconfigitem(
     b'phases',
     b'publish',
     default=True,
 )
 coreconfigitem(
     b'profiling',
     b'enabled',
     default=False,
 )
 coreconfigitem(
     b'profiling',
     b'format',
     default=b'text',
 )
 coreconfigitem(
     b'profiling',
     b'freq',
     default=1000,
 )
 coreconfigitem(
     b'profiling',
     b'limit',
     default=30,
 )
 coreconfigitem(
     b'profiling',
     b'nested',
     default=0,
 )
 coreconfigitem(
     b'profiling',
     b'output',
     default=None,
 )
 coreconfigitem(
     b'profiling',
     b'showmax',
     default=0.999,
 )
 coreconfigitem(
     b'profiling',
     b'showmin',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'profiling',
     b'showtime',
     default=True,
 )
 coreconfigitem(
     b'profiling',
     b'sort',
     default=b'inlinetime',
 )
 coreconfigitem(
     b'profiling',
     b'statformat',
     default=b'hotpath',
 )
 coreconfigitem(
     b'profiling',
     b'time-track',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'profiling',
     b'type',
     default=b'stat',
 )
 coreconfigitem(
     b'progress',
     b'assume-tty',
     default=False,
 )
 coreconfigitem(
     b'progress',
     b'changedelay',
     default=1,
 )
 coreconfigitem(
     b'progress',
     b'clear-complete',
     default=True,
 )
 coreconfigitem(
     b'progress',
     b'debug',
     default=False,
 )
 coreconfigitem(
     b'progress',
     b'delay',
     default=3,
 )
 coreconfigitem(
     b'progress',
     b'disable',
     default=False,
 )
 coreconfigitem(
     b'progress',
     b'estimateinterval',
     default=60.0,
 )
 coreconfigitem(
     b'progress',
     b'format',
     default=lambda: [b'topic', b'bar', b'number', b'estimate'],
 )
 coreconfigitem(
     b'progress',
     b'refresh',
     default=0.1,
 )
 coreconfigitem(
     b'progress',
     b'width',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'pull',
     b'confirm',
     default=False,
 )
 coreconfigitem(
     b'push',
     b'pushvars.server',
     default=False,
 )
 coreconfigitem(
     b'rewrite',
     b'backup-bundle',
     default=True,
     alias=[(b'ui', b'history-editing-backup')],
 )
 coreconfigitem(
     b'rewrite',
     b'update-timestamp',
     default=False,
 )
 coreconfigitem(
     b'rewrite',
     b'empty-successor',
     default=b'skip',
     experimental=True,
 )
 coreconfigitem(
     b'storage',
     b'new-repo-backend',
     default=b'revlogv1',
     experimental=True,
 )
 coreconfigitem(
     b'storage',
     b'revlog.optimize-delta-parent-choice',
     default=True,
     alias=[(b'format', b'aggressivemergedeltas')],
 )
 # experimental as long as rust is experimental (or a C version is implemented)
 coreconfigitem(
     b'storage',
     b'revlog.persistent-nodemap.mmap',
     default=True,
 )
 # experimental as long as format.use-persistent-nodemap is.
 coreconfigitem(
     b'storage',
     b'revlog.persistent-nodemap.slow-path',
     default=b"abort",
 )
 
 coreconfigitem(
     b'storage',
     b'revlog.reuse-external-delta',
     default=True,
 )
 coreconfigitem(
     b'storage',
     b'revlog.reuse-external-delta-parent',
     default=None,
 )
 coreconfigitem(
     b'storage',
     b'revlog.zlib.level',
     default=None,
 )
 coreconfigitem(
     b'storage',
     b'revlog.zstd.level',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bookmarks-pushkey-compat',
     default=True,
 )
 coreconfigitem(
     b'server',
     b'bundle1',
     default=True,
 )
 coreconfigitem(
     b'server',
     b'bundle1gd',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bundle1.pull',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bundle1gd.pull',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bundle1.push',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bundle1gd.push',
     default=None,
 )
 coreconfigitem(
     b'server',
     b'bundle2.stream',
     default=True,
     alias=[(b'experimental', b'bundle2.stream')],
 )
 coreconfigitem(
     b'server',
     b'compressionengines',
     default=list,
 )
 coreconfigitem(
     b'server',
     b'concurrent-push-mode',
     default=b'check-related',
 )
 coreconfigitem(
     b'server',
     b'disablefullbundle',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'maxhttpheaderlen',
     default=1024,
 )
 coreconfigitem(
     b'server',
     b'pullbundle',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'preferuncompressed',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'streamunbundle',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'uncompressed',
     default=True,
 )
 coreconfigitem(
     b'server',
     b'uncompressedallowsecret',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'view',
     default=b'served',
 )
 coreconfigitem(
     b'server',
     b'validate',
     default=False,
 )
 coreconfigitem(
     b'server',
     b'zliblevel',
     default=-1,
 )
 coreconfigitem(
     b'server',
     b'zstdlevel',
     default=3,
 )
 coreconfigitem(
     b'share',
     b'pool',
     default=None,
 )
 coreconfigitem(
     b'share',
     b'poolnaming',
     default=b'identity',
 )
 coreconfigitem(
     b'share',
     b'safe-mismatch.source-not-safe',
     default=b'abort',
 )
 coreconfigitem(
     b'share',
     b'safe-mismatch.source-safe',
     default=b'abort',
 )
 coreconfigitem(
     b'share',
     b'safe-mismatch.source-not-safe.warn',
     default=True,
 )
 coreconfigitem(
     b'share',
     b'safe-mismatch.source-safe.warn',
     default=True,
 )
 coreconfigitem(
     b'shelve',
     b'maxbackups',
     default=10,
 )
 coreconfigitem(
     b'smtp',
     b'host',
     default=None,
 )
 coreconfigitem(
     b'smtp',
     b'local_hostname',
     default=None,
 )
 coreconfigitem(
     b'smtp',
     b'password',
     default=None,
 )
 coreconfigitem(
     b'smtp',
     b'port',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'smtp',
     b'tls',
     default=b'none',
 )
 coreconfigitem(
     b'smtp',
     b'username',
     default=None,
 )
 coreconfigitem(
     b'sparse',
     b'missingwarning',
     default=True,
     experimental=True,
 )
 coreconfigitem(
     b'subrepos',
     b'allowed',
     default=dynamicdefault,  # to make backporting simpler
 )
 coreconfigitem(
     b'subrepos',
     b'hg:allowed',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'subrepos',
     b'git:allowed',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'subrepos',
     b'svn:allowed',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'templates',
     b'.*',
     default=None,
     generic=True,
 )
 coreconfigitem(
     b'templateconfig',
     b'.*',
     default=dynamicdefault,
     generic=True,
 )
 coreconfigitem(
     b'trusted',
     b'groups',
     default=list,
 )
 coreconfigitem(
     b'trusted',
     b'users',
     default=list,
 )
 coreconfigitem(
     b'ui',
     b'_usedassubrepo',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'allowemptycommit',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'archivemeta',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'askusername',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'available-memory',
     default=None,
 )
 
 coreconfigitem(
     b'ui',
     b'clonebundlefallback',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'clonebundleprefers',
     default=list,
 )
 coreconfigitem(
     b'ui',
     b'clonebundles',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'color',
     default=b'auto',
 )
 coreconfigitem(
     b'ui',
     b'commitsubrepos',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'debug',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'debugger',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'editor',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'ui',
     b'detailed-exit-code',
     default=False,
     experimental=True,
 )
 coreconfigitem(
     b'ui',
     b'fallbackencoding',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'forcecwd',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'forcemerge',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'formatdebug',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'formatjson',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'formatted',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'interactive',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'interface',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'interface.chunkselector',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'large-file-limit',
     default=10000000,
 )
 coreconfigitem(
     b'ui',
     b'logblockedtimes',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'merge',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'mergemarkers',
     default=b'basic',
 )
 coreconfigitem(
     b'ui',
     b'message-output',
     default=b'stdio',
 )
 coreconfigitem(
     b'ui',
     b'nontty',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'origbackuppath',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'paginate',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'patch',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'portablefilenames',
     default=b'warn',
 )
 coreconfigitem(
     b'ui',
     b'promptecho',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'quiet',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'quietbookmarkmove',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'relative-paths',
     default=b'legacy',
 )
 coreconfigitem(
     b'ui',
     b'remotecmd',
     default=b'hg',
 )
 coreconfigitem(
     b'ui',
     b'report_untrusted',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'rollback',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'signal-safe-lock',
     default=True,
 )
 coreconfigitem(
     b'ui',
     b'slash',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'ssh',
     default=b'ssh',
 )
 coreconfigitem(
     b'ui',
     b'ssherrorhint',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'statuscopies',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'strict',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'style',
     default=b'',
 )
 coreconfigitem(
     b'ui',
     b'supportcontact',
     default=None,
 )
 coreconfigitem(
     b'ui',
     b'textwidth',
     default=78,
 )
 coreconfigitem(
     b'ui',
     b'timeout',
     default=b'600',
 )
 coreconfigitem(
     b'ui',
     b'timeout.warn',
     default=0,
 )
 coreconfigitem(
     b'ui',
     b'timestamp-output',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'traceback',
     default=False,
 )
 coreconfigitem(
     b'ui',
     b'tweakdefaults',
     default=False,
 )
 coreconfigitem(b'ui', b'username', alias=[(b'ui', b'user')])
 coreconfigitem(
     b'ui',
     b'verbose',
     default=False,
 )
 coreconfigitem(
     b'verify',
     b'skipflags',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'allowbz2',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'allowgz',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'allow-pull',
     alias=[(b'web', b'allowpull')],
     default=True,
 )
 coreconfigitem(
     b'web',
     b'allow-push',
     alias=[(b'web', b'allow_push')],
     default=list,
 )
 coreconfigitem(
     b'web',
     b'allowzip',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'archivesubrepos',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'cache',
     default=True,
 )
 coreconfigitem(
     b'web',
     b'comparisoncontext',
     default=5,
 )
 coreconfigitem(
     b'web',
     b'contact',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'deny_push',
     default=list,
 )
 coreconfigitem(
     b'web',
     b'guessmime',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'hidden',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'labels',
     default=list,
 )
 coreconfigitem(
     b'web',
     b'logoimg',
     default=b'hglogo.png',
 )
 coreconfigitem(
     b'web',
     b'logourl',
     default=b'https://mercurial-scm.org/',
 )
 coreconfigitem(
     b'web',
     b'accesslog',
     default=b'-',
 )
 coreconfigitem(
     b'web',
     b'address',
     default=b'',
 )
 coreconfigitem(
     b'web',
     b'allow-archive',
     alias=[(b'web', b'allow_archive')],
     default=list,
 )
 coreconfigitem(
     b'web',
     b'allow_read',
     default=list,
 )
 coreconfigitem(
     b'web',
     b'baseurl',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'cacerts',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'certificate',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'collapse',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'csp',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'deny_read',
     default=list,
 )
 coreconfigitem(
     b'web',
     b'descend',
     default=True,
 )
 coreconfigitem(
     b'web',
     b'description',
     default=b"",
 )
 coreconfigitem(
     b'web',
     b'encoding',
     default=lambda: encoding.encoding,
 )
 coreconfigitem(
     b'web',
     b'errorlog',
     default=b'-',
 )
 coreconfigitem(
     b'web',
     b'ipv6',
     default=False,
 )
 coreconfigitem(
     b'web',
     b'maxchanges',
     default=10,
 )
 coreconfigitem(
     b'web',
     b'maxfiles',
     default=10,
 )
 coreconfigitem(
     b'web',
     b'maxshortchanges',
     default=60,
 )
 coreconfigitem(
     b'web',
     b'motd',
     default=b'',
 )
 coreconfigitem(
     b'web',
     b'name',
     default=dynamicdefault,
 )
 coreconfigitem(
     b'web',
     b'port',
     default=8000,
 )
 coreconfigitem(
     b'web',
     b'prefix',
     default=b'',
 )
 coreconfigitem(
     b'web',
     b'push_ssl',
     default=True,
 )
 coreconfigitem(
     b'web',
     b'refreshinterval',
     default=20,
 )
 coreconfigitem(
     b'web',
     b'server-header',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'static',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'staticurl',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'stripes',
     default=1,
 )
 coreconfigitem(
     b'web',
     b'style',
     default=b'paper',
 )
 coreconfigitem(
     b'web',
     b'templates',
     default=None,
 )
 coreconfigitem(
     b'web',
     b'view',
     default=b'served',
     experimental=True,
 )
 coreconfigitem(
     b'worker',
     b'backgroundclose',
     default=dynamicdefault,
 )
 # Windows defaults to a limit of 512 open files. A buffer of 128
 # should give us enough headway.
 coreconfigitem(
     b'worker',
     b'backgroundclosemaxqueue',
     default=384,
 )
 coreconfigitem(
     b'worker',
     b'backgroundcloseminfilecount',
     default=2048,
 )
 coreconfigitem(
     b'worker',
     b'backgroundclosethreadcount',
     default=4,
 )
 coreconfigitem(
     b'worker',
     b'enabled',
     default=True,
 )
 coreconfigitem(
     b'worker',
     b'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(
     b'commands',
     b'rebase.requiredest',
     default=False,
 )
 coreconfigitem(
     b'experimental',
     b'rebaseskipobsolete',
     default=True,
 )
 coreconfigitem(
     b'rebase',
     b'singletransaction',
     default=False,
 )
 coreconfigitem(
     b'rebase',
     b'experimental.inmemory',
     default=False,
 )

mercurial/copies.py

@@ -1,1230 +1,1238
 # coding: utf8
 # copies.py - copy detection for Mercurial
 #
 # Copyright 2008 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 collections
 import os
 
 from .i18n import _
 from .node import (
     nullid,
     nullrev,
 )
 
 from . import (
     match as matchmod,
     pathutil,
     policy,
     pycompat,
     util,
 )
 
 
 from .utils import stringutil
 
 from .revlogutils import (
     flagutil,
     sidedata as sidedatamod,
 )
 
 rustmod = policy.importrust("copy_tracing")
 
 
 def _filter(src, dst, t):
     """filters out invalid copies after chaining"""
 
     # When _chain()'ing copies in 'a' (from 'src' via some other commit 'mid')
     # with copies in 'b' (from 'mid' to 'dst'), we can get the different cases
     # in the following table (not including trivial cases). For example, case 6
     # is where a file existed in 'src' and remained under that name in 'mid' and
     # then was renamed between 'mid' and 'dst'.
     #
     # case src mid dst result
     #   1   x   y   -    -
     #   2   x   y   y   x->y
     #   3   x   y   x    -
     #   4   x   y   z   x->z
     #   5   -   x   y    -
     #   6   x   x   y   x->y
     #
     # _chain() takes care of chaining the copies in 'a' and 'b', but it
     # cannot tell the difference between cases 1 and 2, between 3 and 4, or
     # between 5 and 6, so it includes all cases in its result.
     # Cases 1, 3, and 5 are then removed by _filter().
 
     for k, v in list(t.items()):
         if k == v:  # case 3
             del t[k]
         elif v not in src:  # case 5
             # remove copies from files that didn't exist
             del t[k]
         elif k not in dst:  # case 1
             # remove copies to files that were then removed
             del t[k]
 
 
 def _chain(prefix, suffix):
     """chain two sets of copies 'prefix' and 'suffix'"""
     result = prefix.copy()
     for key, value in pycompat.iteritems(suffix):
         result[key] = prefix.get(value, value)
     return result
 
 
 def _tracefile(fctx, am, basemf):
     """return file context that is the ancestor of fctx present in ancestor
     manifest am
 
     Note: we used to try and stop after a given limit, however checking if that
     limit is reached turned out to be very expensive. we are better off
     disabling that feature."""
 
     for f in fctx.ancestors():
         path = f.path()
         if am.get(path, None) == f.filenode():
             return path
         if basemf and basemf.get(path, None) == f.filenode():
             return path
 
 
 def _dirstatecopies(repo, match=None):
     ds = repo.dirstate
     c = ds.copies().copy()
     for k in list(c):
         if ds[k] not in b'anm' or (match and not match(k)):
             del c[k]
     return c
 
 
 def _computeforwardmissing(a, b, match=None):
     """Computes which files are in b but not a.
     This is its own function so extensions can easily wrap this call to see what
     files _forwardcopies is about to process.
     """
     ma = a.manifest()
     mb = b.manifest()
     return mb.filesnotin(ma, match=match)
 
 
 def usechangesetcentricalgo(repo):
     """Checks if we should use changeset-centric copy algorithms"""
     if repo.filecopiesmode == b'changeset-sidedata':
         return True
     readfrom = repo.ui.config(b'experimental', b'copies.read-from')
     changesetsource = (b'changeset-only', b'compatibility')
     return readfrom in changesetsource
 
 
 def _committedforwardcopies(a, b, base, match):
     """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""
     # files might have to be traced back to the fctx parent of the last
     # one-side-only changeset, but not further back than that
     repo = a._repo
 
     if usechangesetcentricalgo(repo):
         return _changesetforwardcopies(a, b, match)
 
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     dbg = repo.ui.debug
     if debug:
         dbg(b'debug.copies:    looking into rename from %s to %s\n' % (a, b))
     am = a.manifest()
     basemf = None if base is None else base.manifest()
 
     # find where new files came from
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
 
     # Computing the forward missing is quite expensive on large manifests, since
     # it compares the entire manifests. We can optimize it in the common use
     # case of computing what copies are in a commit versus its parent (like
     # during a rebase or histedit). Note, we exclude merge commits from this
     # optimization, since the ctx.files() for a merge commit is not correct for
     # this comparison.
     forwardmissingmatch = match
     if b.p1() == a and b.p2().node() == nullid:
         filesmatcher = matchmod.exact(b.files())
         forwardmissingmatch = matchmod.intersectmatchers(match, filesmatcher)
-    missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
+    if repo.ui.configbool(b'devel', b'copy-tracing.trace-all-files'):
+        missing = list(b.walk(match))
+        # _computeforwardmissing(a, b, match=forwardmissingmatch)
+        if debug:
+            dbg(b'debug.copies:      searching all files: %d\n' % len(missing))
+    else:
+        missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
+        if debug:
+            dbg(
+                b'debug.copies:      missing files to search: %d\n'
+                % len(missing)
+            )
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
 
-    if debug:
-        dbg(b'debug.copies:      missing files to search: %d\n' % len(missing))
-
     for f in sorted(missing):
         if debug:
             dbg(b'debug.copies:        tracing file: %s\n' % f)
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
 
         if debug:
             start = util.timer()
         opath = _tracefile(fctx, am, basemf)
         if opath:
             if debug:
                 dbg(b'debug.copies:          rename of: %s\n' % opath)
             cm[f] = opath
         if debug:
             dbg(
                 b'debug.copies:          time: %f seconds\n'
                 % (util.timer() - start)
             )
     return cm
 
 
 def _revinfo_getter(repo, match):
     """returns a function that returns the following data given a <rev>"
 
     * p1: revision number of first parent
     * p2: revision number of first parent
     * changes: a ChangingFiles object
     """
     cl = repo.changelog
     parents = cl.parentrevs
     flags = cl.flags
 
     HASCOPIESINFO = flagutil.REVIDX_HASCOPIESINFO
 
     changelogrevision = cl.changelogrevision
 
     if rustmod is not None:
 
         def revinfo(rev):
             p1, p2 = parents(rev)
             if flags(rev) & HASCOPIESINFO:
                 raw = changelogrevision(rev)._sidedata.get(sidedatamod.SD_FILES)
             else:
                 raw = None
             return (p1, p2, raw)
 
     else:
 
         def revinfo(rev):
             p1, p2 = parents(rev)
             if flags(rev) & HASCOPIESINFO:
                 changes = changelogrevision(rev).changes
             else:
                 changes = None
             return (p1, p2, changes)
 
     return revinfo
 
 
 def cached_is_ancestor(is_ancestor):
     """return a cached version of is_ancestor"""
     cache = {}
 
     def _is_ancestor(anc, desc):
         if anc > desc:
             return False
         elif anc == desc:
             return True
         key = (anc, desc)
         ret = cache.get(key)
         if ret is None:
             ret = cache[key] = is_ancestor(anc, desc)
         return ret
 
     return _is_ancestor
 
 
 def _changesetforwardcopies(a, b, match):
     if a.rev() in (nullrev, b.rev()):
         return {}
 
     repo = a.repo().unfiltered()
     children = {}
 
     cl = repo.changelog
     isancestor = cl.isancestorrev
 
     # To track rename from "A" to B, we need to gather all parent → children
     # edges that are contains in `::B` but not in `::A`.
     #
     #
     # To do so, we need to gather all revisions exclusive¹ to "B" (ie¹: `::b -
     # ::a`) and also all the "roots point", ie the parents of the exclusive set
     # that belong to ::a. These are exactly all the revisions needed to express
     # the parent → children we need to combine.
     #
     # [1] actually, we need to gather all the edges within `(::a)::b`, ie:
     # excluding paths that leads to roots that are not ancestors of `a`. We
     # keep this out of the explanation because it is hard enough without this special case..
 
     parents = cl._uncheckedparentrevs
     graph_roots = (nullrev, nullrev)
 
     ancestors = cl.ancestors([a.rev()], inclusive=True)
     revs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()])
     roots = set()
     has_graph_roots = False
 
     # iterate over `only(B, A)`
     for r in revs:
         ps = parents(r)
         if ps == graph_roots:
             has_graph_roots = True
         else:
             p1, p2 = ps
 
             # find all the "root points" (see larger comment above)
             if p1 != nullrev and p1 in ancestors:
                 roots.add(p1)
             if p2 != nullrev and p2 in ancestors:
                 roots.add(p2)
     if not roots:
         # no common revision to track copies from
         return {}
     if has_graph_roots:
         # this deal with the special case mentionned in the [1] footnotes. We
         # must filter out revisions that leads to non-common graphroots.
         roots = list(roots)
         m = min(roots)
         h = [b.rev()]
         roots_to_head = cl.reachableroots(m, h, roots, includepath=True)
         roots_to_head = set(roots_to_head)
         revs = [r for r in revs if r in roots_to_head]
 
     if repo.filecopiesmode == b'changeset-sidedata':
         # When using side-data, we will process the edges "from" the children.
         # We iterate over the childre, gathering previous collected data for
         # the parents. Do know when the parents data is no longer necessary, we
         # keep a counter of how many children each revision has.
         #
         # An interresting property of `children_count` is that it only contains
         # revision that will be relevant for a edge of the graph. So if a
         # children has parent not in `children_count`, that edges should not be
         # processed.
         children_count = dict((r, 0) for r in roots)
         for r in revs:
             for p in cl.parentrevs(r):
                 if p == nullrev:
                     continue
                 children_count[r] = 0
                 if p in children_count:
                     children_count[p] += 1
         revinfo = _revinfo_getter(repo, match)
         return _combine_changeset_copies(
             revs, children_count, b.rev(), revinfo, match, isancestor
         )
     else:
         # When not using side-data, we will process the edges "from" the parent.
         # so we need a full mapping of the parent -> children relation.
         children = dict((r, []) for r in roots)
         for r in revs:
             for p in cl.parentrevs(r):
                 if p == nullrev:
                     continue
                 children[r] = []
                 if p in children:
                     children[p].append(r)
         x = revs.pop()
         assert x == b.rev()
         revs.extend(roots)
         revs.sort()
 
         revinfo = _revinfo_getter_extra(repo)
         return _combine_changeset_copies_extra(
             revs, children, b.rev(), revinfo, match, isancestor
         )
 
 
 def _combine_changeset_copies(
     revs, children_count, targetrev, revinfo, match, isancestor
 ):
     """combine the copies information for each item of iterrevs
 
     revs: sorted iterable of revision to visit
     children_count: a {parent: <number-of-relevant-children>} mapping.
     targetrev: the final copies destination revision (not in iterrevs)
     revinfo(rev): a function that return (p1, p2, p1copies, p2copies, removed)
     match: a matcher
 
     It returns the aggregated copies information for `targetrev`.
     """
 
     alwaysmatch = match.always()
 
     if rustmod is not None:
         final_copies = rustmod.combine_changeset_copies(
             list(revs), children_count, targetrev, revinfo, isancestor
         )
     else:
         isancestor = cached_is_ancestor(isancestor)
 
         all_copies = {}
         # iterate over all the "children" side of copy tracing "edge"
         for current_rev in revs:
             p1, p2, changes = revinfo(current_rev)
             current_copies = None
             # iterate over all parents to chain the existing data with the
             # data from the parent → child edge.
             for parent, parent_rev in ((1, p1), (2, p2)):
                 if parent_rev == nullrev:
                     continue
                 remaining_children = children_count.get(parent_rev)
                 if remaining_children is None:
                     continue
                 remaining_children -= 1
                 children_count[parent_rev] = remaining_children
                 if remaining_children:
                     copies = all_copies.get(parent_rev, None)
                 else:
                     copies = all_copies.pop(parent_rev, None)
 
                 if copies is None:
                     # this is a root
                     newcopies = copies = {}
                 elif remaining_children:
                     newcopies = copies.copy()
                 else:
                     newcopies = copies
                 # chain the data in the edge with the existing data
                 if changes is not None:
                     childcopies = {}
                     if parent == 1:
                         childcopies = changes.copied_from_p1
                     elif parent == 2:
                         childcopies = changes.copied_from_p2
 
                     if childcopies:
                         newcopies = copies.copy()
                         for dest, source in pycompat.iteritems(childcopies):
                             prev = copies.get(source)
                             if prev is not None and prev[1] is not None:
                                 source = prev[1]
                             newcopies[dest] = (current_rev, source)
                         assert newcopies is not copies
                     if changes.removed:
                         for f in changes.removed:
                             if f in newcopies:
                                 if newcopies is copies:
                                     # copy on write to avoid affecting potential other
                                     # branches.  when there are no other branches, this
                                     # could be avoided.
                                     newcopies = copies.copy()
                                 newcopies[f] = (current_rev, None)
                 # check potential need to combine the data from another parent (for
                 # that child). See comment below for details.
                 if current_copies is None:
                     current_copies = newcopies
                 else:
                     # we are the second parent to work on c, we need to merge our
                     # work with the other.
                     #
                     # In case of conflict, parent 1 take precedence over parent 2.
                     # This is an arbitrary choice made anew when implementing
                     # changeset based copies. It was made without regards with
                     # potential filelog related behavior.
                     assert parent == 2
                     current_copies = _merge_copies_dict(
                         newcopies, current_copies, isancestor, changes
                     )
             all_copies[current_rev] = current_copies
 
         # filter out internal details and return a {dest: source mapping}
         final_copies = {}
         for dest, (tt, source) in all_copies[targetrev].items():
             if source is not None:
                 final_copies[dest] = source
     if not alwaysmatch:
         for filename in list(final_copies.keys()):
             if not match(filename):
                 del final_copies[filename]
     return final_copies
 
 
 # constant to decide which side to pick with _merge_copies_dict
 PICK_MINOR = 0
 PICK_MAJOR = 1
 PICK_EITHER = 2
 
 
 def _merge_copies_dict(minor, major, isancestor, changes):
     """merge two copies-mapping together, minor and major
 
     In case of conflict, value from "major" will be picked.
 
     - `isancestors(low_rev, high_rev)`: callable return True if `low_rev` is an
                                         ancestors of `high_rev`,
 
     - `ismerged(path)`: callable return True if `path` have been merged in the
                         current revision,
 
     return the resulting dict (in practice, the "minor" object, updated)
     """
     for dest, value in major.items():
         other = minor.get(dest)
         if other is None:
             minor[dest] = value
         else:
             pick = _compare_values(changes, isancestor, dest, other, value)
             if pick == PICK_MAJOR:
                 minor[dest] = value
     return minor
 
 
 def _compare_values(changes, isancestor, dest, minor, major):
     """compare two value within a _merge_copies_dict loop iteration"""
     major_tt, major_value = major
     minor_tt, minor_value = minor
 
     # evacuate some simple case first:
     if major_tt == minor_tt:
         # if it comes from the same revision it must be the same value
         assert major_value == minor_value
         return PICK_EITHER
     elif major[1] == minor[1]:
         return PICK_EITHER
 
     # actual merging needed: content from "major" wins, unless it is older than
     # the branch point or there is a merge
     elif changes is not None and major[1] is None and dest in changes.salvaged:
         return PICK_MINOR
     elif changes is not None and minor[1] is None and dest in changes.salvaged:
         return PICK_MAJOR
     elif changes is not None and dest in changes.merged:
         return PICK_MAJOR
     elif not isancestor(major_tt, minor_tt):
         if major[1] is not None:
             return PICK_MAJOR
         elif isancestor(minor_tt, major_tt):
             return PICK_MAJOR
     return PICK_MINOR
 
 
 def _revinfo_getter_extra(repo):
     """return a function that return multiple data given a <rev>"i
 
     * p1: revision number of first parent
     * p2: revision number of first parent
     * p1copies: mapping of copies from p1
     * p2copies: mapping of copies from p2
     * removed: a list of removed files
     * ismerged: a callback to know if file was merged in that revision
     """
     cl = repo.changelog
     parents = cl.parentrevs
 
     def get_ismerged(rev):
         ctx = repo[rev]
 
         def ismerged(path):
             if path not in ctx.files():
                 return False
             fctx = ctx[path]
             parents = fctx._filelog.parents(fctx._filenode)
             nb_parents = 0
             for n in parents:
                 if n != nullid:
                     nb_parents += 1
             return nb_parents >= 2
 
         return ismerged
 
     def revinfo(rev):
         p1, p2 = parents(rev)
         ctx = repo[rev]
         p1copies, p2copies = ctx._copies
         removed = ctx.filesremoved()
         return p1, p2, p1copies, p2copies, removed, get_ismerged(rev)
 
     return revinfo
 
 
 def _combine_changeset_copies_extra(
     revs, children, targetrev, revinfo, match, isancestor
 ):
     """version of `_combine_changeset_copies` that works with the Google
     specific "extra" based storage for copy information"""
     all_copies = {}
     alwaysmatch = match.always()
     for r in revs:
         copies = all_copies.pop(r, None)
         if copies is None:
             # this is a root
             copies = {}
         for i, c in enumerate(children[r]):
             p1, p2, p1copies, p2copies, removed, ismerged = revinfo(c)
             if r == p1:
                 parent = 1
                 childcopies = p1copies
             else:
                 assert r == p2
                 parent = 2
                 childcopies = p2copies
             if not alwaysmatch:
                 childcopies = {
                     dst: src for dst, src in childcopies.items() if match(dst)
                 }
             newcopies = copies
             if childcopies:
                 newcopies = copies.copy()
                 for dest, source in pycompat.iteritems(childcopies):
                     prev = copies.get(source)
                     if prev is not None and prev[1] is not None:
                         source = prev[1]
                     newcopies[dest] = (c, source)
                 assert newcopies is not copies
             for f in removed:
                 if f in newcopies:
                     if newcopies is copies:
                         # copy on write to avoid affecting potential other
                         # branches.  when there are no other branches, this
                         # could be avoided.
                         newcopies = copies.copy()
                     newcopies[f] = (c, None)
             othercopies = all_copies.get(c)
             if othercopies is None:
                 all_copies[c] = newcopies
             else:
                 # we are the second parent to work on c, we need to merge our
                 # work with the other.
                 #
                 # In case of conflict, parent 1 take precedence over parent 2.
                 # This is an arbitrary choice made anew when implementing
                 # changeset based copies. It was made without regards with
                 # potential filelog related behavior.
                 if parent == 1:
                     _merge_copies_dict_extra(
                         othercopies, newcopies, isancestor, ismerged
                     )
                 else:
                     _merge_copies_dict_extra(
                         newcopies, othercopies, isancestor, ismerged
                     )
                     all_copies[c] = newcopies
 
     final_copies = {}
     for dest, (tt, source) in all_copies[targetrev].items():
         if source is not None:
             final_copies[dest] = source
     return final_copies
 
 
 def _merge_copies_dict_extra(minor, major, isancestor, ismerged):
     """version of `_merge_copies_dict` that works with the Google
     specific "extra" based storage for copy information"""
     for dest, value in major.items():
         other = minor.get(dest)
         if other is None:
             minor[dest] = value
         else:
             new_tt = value[0]
             other_tt = other[0]
             if value[1] == other[1]:
                 continue
             # content from "major" wins, unless it is older
             # than the branch point or there is a merge
             if (
                 new_tt == other_tt
                 or not isancestor(new_tt, other_tt)
                 or ismerged(dest)
             ):
                 minor[dest] = value
 
 
 def _forwardcopies(a, b, base=None, match=None):
     """find {dst@b: src@a} copy mapping where a is an ancestor of b"""
 
     if base is None:
         base = a
     match = a.repo().narrowmatch(match)
     # check for working copy
     if b.rev() is None:
         cm = _committedforwardcopies(a, b.p1(), base, match)
         # combine copies from dirstate if necessary
         copies = _chain(cm, _dirstatecopies(b._repo, match))
     else:
         copies = _committedforwardcopies(a, b, base, match)
     return copies
 
 
 def _backwardrenames(a, b, match):
     if a._repo.ui.config(b'experimental', b'copytrace') == b'off':
         return {}
 
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     # We don't want to pass in "match" here, since that would filter
     # the destination by it. Since we're reversing the copies, we want
     # to filter the source instead.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(pycompat.iteritems(f)):
         if match and not match(v):
             continue
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 
 def pathcopies(x, y, match=None):
     """find {dst@y: src@x} copy mapping for directed compare"""
     repo = x._repo
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     if debug:
         repo.ui.debug(
             b'debug.copies: searching copies from %s to %s\n' % (x, y)
         )
     if x == y or not x or not y:
         return {}
     if y.rev() is None and x == y.p1():
         if debug:
             repo.ui.debug(b'debug.copies: search mode: dirstate\n')
         # short-circuit to avoid issues with merge states
         return _dirstatecopies(repo, match)
     a = y.ancestor(x)
     if a == x:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: forward\n')
         copies = _forwardcopies(x, y, match=match)
     elif a == y:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: backward\n')
         copies = _backwardrenames(x, y, match=match)
     else:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: combined\n')
         base = None
         if a.rev() != nullrev:
             base = x
         copies = _chain(
             _backwardrenames(x, a, match=match),
             _forwardcopies(a, y, base, match=match),
         )
     _filter(x, y, copies)
     return copies
 
 
 def mergecopies(repo, c1, c2, base):
     """
     Finds moves and copies between context c1 and c2 that are relevant for
     merging. 'base' will be used as the merge base.
 
     Copytracing is used in commands like rebase, merge, unshelve, etc to merge
     files that were moved/ copied in one merge parent and modified in another.
     For example:
 
     o          ---> 4 another commit
     |
     |   o      ---> 3 commit that modifies a.txt
     |  /
     o /        ---> 2 commit that moves a.txt to b.txt
     |/
     o          ---> 1 merge base
 
     If we try to rebase revision 3 on revision 4, since there is no a.txt in
     revision 4, and if user have copytrace disabled, we prints the following
     message:
 
     ```other changed <file> which local deleted```
 
     Returns a tuple where:
 
     "branch_copies" an instance of branch_copies.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     This function calls different copytracing algorithms based on config.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return branch_copies(), branch_copies(), {}
 
     narrowmatch = c1.repo().narrowmatch()
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return (
             branch_copies(_dirstatecopies(repo, narrowmatch)),
             branch_copies(),
             {},
         )
 
     copytracing = repo.ui.config(b'experimental', b'copytrace')
     if stringutil.parsebool(copytracing) is False:
         # stringutil.parsebool() returns None when it is unable to parse the
         # value, so we should rely on making sure copytracing is on such cases
         return branch_copies(), branch_copies(), {}
 
     if usechangesetcentricalgo(repo):
         # The heuristics don't make sense when we need changeset-centric algos
         return _fullcopytracing(repo, c1, c2, base)
 
     # Copy trace disabling is explicitly below the node == p1 logic above
     # because the logic above is required for a simple copy to be kept across a
     # rebase.
     if copytracing == b'heuristics':
         # Do full copytracing if only non-public revisions are involved as
         # that will be fast enough and will also cover the copies which could
         # be missed by heuristics
         if _isfullcopytraceable(repo, c1, base):
             return _fullcopytracing(repo, c1, c2, base)
         return _heuristicscopytracing(repo, c1, c2, base)
     else:
         return _fullcopytracing(repo, c1, c2, base)
 
 
 def _isfullcopytraceable(repo, c1, base):
     """Checks that if base, source and destination are all no-public branches,
     if yes let's use the full copytrace algorithm for increased capabilities
     since it will be fast enough.
 
     `experimental.copytrace.sourcecommitlimit` can be used to set a limit for
     number of changesets from c1 to base such that if number of changesets are
     more than the limit, full copytracing algorithm won't be used.
     """
     if c1.rev() is None:
         c1 = c1.p1()
     if c1.mutable() and base.mutable():
         sourcecommitlimit = repo.ui.configint(
             b'experimental', b'copytrace.sourcecommitlimit'
         )
         commits = len(repo.revs(b'%d::%d', base.rev(), c1.rev()))
         return commits < sourcecommitlimit
     return False
 
 
 def _checksinglesidecopies(
     src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
 ):
     if src not in m2:
         # deleted on side 2
         if src not in m1:
             # renamed on side 1, deleted on side 2
             renamedelete[src] = dsts1
     elif src not in mb:
         # Work around the "short-circuit to avoid issues with merge states"
         # thing in pathcopies(): pathcopies(x, y) can return a copy where the
         # destination doesn't exist in y.
         pass
     elif mb[src] != m2[src] and not _related(c2[src], base[src]):
         return
     elif mb[src] != m2[src] or mb.flags(src) != m2.flags(src):
         # modified on side 2
         for dst in dsts1:
             copy[dst] = src
 
 
 class branch_copies(object):
     """Information about copies made on one side of a merge/graft.
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
 
     "dirmove" is a mapping of detected source dir -> destination dir renames.
     This is needed for handling changes to new files previously grafted into
     renamed directories.
     """
 
     def __init__(
         self, copy=None, renamedelete=None, dirmove=None, movewithdir=None
     ):
         self.copy = {} if copy is None else copy
         self.renamedelete = {} if renamedelete is None else renamedelete
         self.dirmove = {} if dirmove is None else dirmove
         self.movewithdir = {} if movewithdir is None else movewithdir
 
     def __repr__(self):
         return '<branch_copies\n  copy=%r\n  renamedelete=%r\n  dirmove=%r\n  movewithdir=%r\n>' % (
             self.copy,
             self.renamedelete,
             self.dirmove,
             self.movewithdir,
         )
 
 
 def _fullcopytracing(repo, c1, c2, base):
     """The full copytracing algorithm which finds all the new files that were
     added from merge base up to the top commit and for each file it checks if
     this file was copied from another file.
 
     This is pretty slow when a lot of changesets are involved but will track all
     the copies.
     """
     m1 = c1.manifest()
     m2 = c2.manifest()
     mb = base.manifest()
 
     copies1 = pathcopies(base, c1)
     copies2 = pathcopies(base, c2)
 
     if not (copies1 or copies2):
         return branch_copies(), branch_copies(), {}
 
     inversecopies1 = {}
     inversecopies2 = {}
     for dst, src in copies1.items():
         inversecopies1.setdefault(src, []).append(dst)
     for dst, src in copies2.items():
         inversecopies2.setdefault(src, []).append(dst)
 
     copy1 = {}
     copy2 = {}
     diverge = {}
     renamedelete1 = {}
     renamedelete2 = {}
     allsources = set(inversecopies1) | set(inversecopies2)
     for src in allsources:
         dsts1 = inversecopies1.get(src)
         dsts2 = inversecopies2.get(src)
         if dsts1 and dsts2:
             # copied/renamed on both sides
             if src not in m1 and src not in m2:
                 # renamed on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 # If there's some overlap in the rename destinations, we
                 # consider it not divergent. For example, if side 1 copies 'a'
                 # to 'b' and 'c' and deletes 'a', and side 2 copies 'a' to 'c'
                 # and 'd' and deletes 'a'.
                 if dsts1 & dsts2:
                     for dst in dsts1 & dsts2:
                         copy1[dst] = src
                         copy2[dst] = src
                 else:
                     diverge[src] = sorted(dsts1 | dsts2)
             elif src in m1 and src in m2:
                 # copied on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 for dst in dsts1 & dsts2:
                     copy1[dst] = src
                     copy2[dst] = src
             # TODO: Handle cases where it was renamed on one side and copied
             # on the other side
         elif dsts1:
             # copied/renamed only on side 1
             _checksinglesidecopies(
                 src, dsts1, m1, m2, mb, c2, base, copy1, renamedelete1
             )
         elif dsts2:
             # copied/renamed only on side 2
             _checksinglesidecopies(
                 src, dsts2, m2, m1, mb, c1, base, copy2, renamedelete2
             )
 
     # find interesting file sets from manifests
     cache = []
 
     def _get_addedfiles(idx):
         if not cache:
             addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
             addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
             u1 = sorted(addedinm1 - addedinm2)
             u2 = sorted(addedinm2 - addedinm1)
             cache.extend((u1, u2))
         return cache[idx]
 
     u1fn = lambda: _get_addedfiles(0)
     u2fn = lambda: _get_addedfiles(1)
     if repo.ui.debugflag:
         u1 = u1fn()
         u2 = u2fn()
 
         header = b"  unmatched files in %s"
         if u1:
             repo.ui.debug(
                 b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1))
             )
         if u2:
             repo.ui.debug(
                 b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2))
             )
 
         renamedeleteset = set()
         divergeset = set()
         for dsts in diverge.values():
             divergeset.update(dsts)
         for dsts in renamedelete1.values():
             renamedeleteset.update(dsts)
         for dsts in renamedelete2.values():
             renamedeleteset.update(dsts)
 
         repo.ui.debug(
             b"  all copies found (* = to merge, ! = divergent, "
             b"% = renamed and deleted):\n"
         )
         for side, copies in ((b"local", copies1), (b"remote", copies2)):
             if not copies:
                 continue
             repo.ui.debug(b"   on %s side:\n" % side)
             for f in sorted(copies):
                 note = b""
                 if f in copy1 or f in copy2:
                     note += b"*"
                 if f in divergeset:
                     note += b"!"
                 if f in renamedeleteset:
                     note += b"%"
                 repo.ui.debug(
                     b"    src: '%s' -> dst: '%s' %s\n" % (copies[f], f, note)
                 )
         del renamedeleteset
         del divergeset
 
     repo.ui.debug(b"  checking for directory renames\n")
 
     dirmove1, movewithdir2 = _dir_renames(repo, c1, copy1, copies1, u2fn)
     dirmove2, movewithdir1 = _dir_renames(repo, c2, copy2, copies2, u1fn)
 
     branch_copies1 = branch_copies(copy1, renamedelete1, dirmove1, movewithdir1)
     branch_copies2 = branch_copies(copy2, renamedelete2, dirmove2, movewithdir2)
 
     return branch_copies1, branch_copies2, diverge
 
 
 def _dir_renames(repo, ctx, copy, fullcopy, addedfilesfn):
     """Finds moved directories and files that should move with them.
 
     ctx: the context for one of the sides
     copy: files copied on the same side (as ctx)
     fullcopy: files copied on the same side (as ctx), including those that
               merge.manifestmerge() won't care about
     addedfilesfn: function returning added files on the other side (compared to
                   ctx)
     """
     # generate a directory move map
     invalid = set()
     dirmove = {}
 
     # examine each file copy for a potential directory move, which is
     # when all the files in a directory are moved to a new directory
     for dst, src in pycompat.iteritems(fullcopy):
         dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif ctx.hasdir(dsrc) and ctx.hasdir(ddst):
             # directory wasn't entirely moved locally
             invalid.add(dsrc)
         elif dsrc in dirmove and dirmove[dsrc] != ddst:
             # files from the same directory moved to two different places
             invalid.add(dsrc)
         else:
             # looks good so far
             dirmove[dsrc] = ddst
 
     for i in invalid:
         if i in dirmove:
             del dirmove[i]
     del invalid
 
     if not dirmove:
         return {}, {}
 
     dirmove = {k + b"/": v + b"/" for k, v in pycompat.iteritems(dirmove)}
 
     for d in dirmove:
         repo.ui.debug(
             b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
         )
 
     movewithdir = {}
     # check unaccounted nonoverlapping files against directory moves
     for f in addedfilesfn():
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
                     # new file added in a directory that was moved, move it
                     df = dirmove[d] + f[len(d) :]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(
                             b"   pending file src: '%s' -> dst: '%s'\n"
                             % (f, df)
                         )
                     break
 
     return dirmove, movewithdir
 
 
 def _heuristicscopytracing(repo, c1, c2, base):
     """Fast copytracing using filename heuristics
 
     Assumes that moves or renames are of following two types:
 
     1) Inside a directory only (same directory name but different filenames)
     2) Move from one directory to another
                     (same filenames but different directory names)
 
     Works only when there are no merge commits in the "source branch".
     Source branch is commits from base up to c2 not including base.
 
     If merge is involved it fallbacks to _fullcopytracing().
 
     Can be used by setting the following config:
 
         [experimental]
         copytrace = heuristics
 
     In some cases the copy/move candidates found by heuristics can be very large
     in number and that will make the algorithm slow. The number of possible
     candidates to check can be limited by using the config
     `experimental.copytrace.movecandidateslimit` which defaults to 100.
     """
 
     if c1.rev() is None:
         c1 = c1.p1()
     if c2.rev() is None:
         c2 = c2.p1()
 
     changedfiles = set()
     m1 = c1.manifest()
     if not repo.revs(b'%d::%d', base.rev(), c2.rev()):
         # If base is not in c2 branch, we switch to fullcopytracing
         repo.ui.debug(
             b"switching to full copytracing as base is not "
             b"an ancestor of c2\n"
         )
         return _fullcopytracing(repo, c1, c2, base)
 
     ctx = c2
     while ctx != base:
         if len(ctx.parents()) == 2:
             # To keep things simple let's not handle merges
             repo.ui.debug(b"switching to full copytracing because of merges\n")
             return _fullcopytracing(repo, c1, c2, base)
         changedfiles.update(ctx.files())
         ctx = ctx.p1()
 
     copies2 = {}
     cp = _forwardcopies(base, c2)
     for dst, src in pycompat.iteritems(cp):
         if src in m1:
             copies2[dst] = src
 
     # file is missing if it isn't present in the destination, but is present in
     # the base and present in the source.
     # Presence in the base is important to exclude added files, presence in the
     # source is important to exclude removed files.
     filt = lambda f: f not in m1 and f in base and f in c2
     missingfiles = [f for f in changedfiles if filt(f)]
 
     copies1 = {}
     if missingfiles:
         basenametofilename = collections.defaultdict(list)
         dirnametofilename = collections.defaultdict(list)
 
         for f in m1.filesnotin(base.manifest()):
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             basenametofilename[basename].append(f)
             dirnametofilename[dirname].append(f)
 
         for f in missingfiles:
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             samebasename = basenametofilename[basename]
             samedirname = dirnametofilename[dirname]
             movecandidates = samebasename + samedirname
             # f is guaranteed to be present in c2, that's why
             # c2.filectx(f) won't fail
             f2 = c2.filectx(f)
             # we can have a lot of candidates which can slow down the heuristics
             # config value to limit the number of candidates moves to check
             maxcandidates = repo.ui.configint(
                 b'experimental', b'copytrace.movecandidateslimit'
             )
 
             if len(movecandidates) > maxcandidates:
                 repo.ui.status(
                     _(
                         b"skipping copytracing for '%s', more "
                         b"candidates than the limit: %d\n"
                     )
                     % (f, len(movecandidates))
                 )
                 continue
 
             for candidate in movecandidates:
                 f1 = c1.filectx(candidate)
                 if _related(f1, f2):
                     # if there are a few related copies then we'll merge
                     # changes into all of them. This matches the behaviour
                     # of upstream copytracing
                     copies1[candidate] = f
 
     return branch_copies(copies1), branch_copies(copies2), {}
 
 
 def _related(f1, f2):
     """return True if f1 and f2 filectx have a common ancestor
 
     Walk back to common ancestor to see if the two files originate
     from the same file. Since workingfilectx's rev() is None it messes
     up the integer comparison logic, hence the pre-step check for
     None (f1 and f2 can only be workingfilectx's initially).
     """
 
     if f1 == f2:
         return True  # a match
 
     g1, g2 = f1.ancestors(), f2.ancestors()
     try:
         f1r, f2r = f1.linkrev(), f2.linkrev()
 
         if f1r is None:
             f1 = next(g1)
         if f2r is None:
             f2 = next(g2)
 
         while True:
             f1r, f2r = f1.linkrev(), f2.linkrev()
             if f1r > f2r:
                 f1 = next(g1)
             elif f2r > f1r:
                 f2 = next(g2)
             else:  # f1 and f2 point to files in the same linkrev
                 return f1 == f2  # true if they point to the same file
     except StopIteration:
         return False
 
 
 def graftcopies(wctx, ctx, base):
     """reproduce copies between base and ctx in the wctx
 
     Unlike mergecopies(), this function will only consider copies between base
     and ctx; it will ignore copies between base and wctx. Also unlike
     mergecopies(), this function will apply copies to the working copy (instead
     of just returning information about the copies). That makes it cheaper
     (especially in the common case of base==ctx.p1()) and useful also when
     experimental.copytrace=off.
 
     merge.update() will have already marked most copies, but it will only
     mark copies if it thinks the source files are related (see
     merge._related()). It will also not mark copies if the file wasn't modified
     on the local side. This function adds the copies that were "missed"
     by merge.update().
     """
     new_copies = pathcopies(base, ctx)
     parent = wctx.p1()
     _filter(parent, wctx, new_copies)
     # extra filtering to drop copy information for files that existed before
     # the graft (otherwise we would create merge filelog for non-merge commit
     for dest, __ in list(new_copies.items()):
         if dest in parent:
             del new_copies[dest]
     for dst, src in pycompat.iteritems(new_copies):
         wctx[dst].markcopied(src)

tests/test-copies.t

@@ -1,721 +1,725
 #testcases filelog compatibility changeset sidedata
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > rebase=
   > [alias]
   > l = log -G -T '{rev} {desc}\n{files}\n'
   > EOF
 
 #if compatibility
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = compatibility
   > EOF
 #endif
 
 #if changeset
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.read-from = changeset-only
   > copies.write-to = changeset-only
   > EOF
 #endif
 
 #if sidedata
   $ cat >> $HGRCPATH << EOF
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
 #endif
 
   $ REPONUM=0
   $ newrepo() {
   >     cd $TESTTMP
   >     REPONUM=`expr $REPONUM + 1`
   >     hg init repo-$REPONUM
   >     cd repo-$REPONUM
   > }
 
 Simple rename case
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'rename x to y'
   $ hg l
   @  1 rename x to y
   |  x y
   o  0 add x
      x
   $ hg debugp1copies -r 1
   x -> y
   $ hg debugpathcopies 0 1
   x -> y
   $ hg debugpathcopies 1 0
   y -> x
 Test filtering copies by path. We do filtering by destination.
   $ hg debugpathcopies 0 1 x
   $ hg debugpathcopies 1 0 x
   y -> x
   $ hg debugpathcopies 0 1 y
   x -> y
   $ hg debugpathcopies 1 0 y
 
 Copies not including commit changes
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugpathcopies . .
   $ hg debugpathcopies . 'wdir()'
   x -> y
   $ hg debugpathcopies 'wdir()' .
   y -> x
 
 Copy a file onto another file
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg cp -f x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'copy x onto y'
   $ hg l
   @  1 copy x onto y
   |  y
   o  0 add x and y
      x y
   $ hg debugp1copies -r 1
   x -> y
   $ hg debugpathcopies 0 1
   x -> y (no-filelog !)
+  $ hg debugpathcopies 0 1  --config devel.copy-tracing.trace-all-files=yes
+  x -> y
 
 Copy a file onto another file with same content. If metadata is stored in changeset, this does not
 produce a new filelog entry. The changeset's "files" entry should still list the file.
   $ newrepo
   $ echo x > x
   $ echo x > x2
   $ hg ci -Aqm 'add x and x2 with same content'
   $ hg cp -f x x2
   $ hg ci -m 'copy x onto x2'
   $ hg l
   @  1 copy x onto x2
   |  x2
   o  0 add x and x2 with same content
      x x2
   $ hg debugp1copies -r 1
   x -> x2
   $ hg debugpathcopies 0 1
   x -> x2 (no-filelog !)
+  $ hg debugpathcopies 0 1  --config devel.copy-tracing.trace-all-files=yes
+  x -> x2
 
 Rename file in a loop: x->y->z->x
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg debugp1copies
   x -> y
   $ hg debugp2copies
   $ hg ci -m 'rename x to y'
   $ hg mv y z
   $ hg ci -m 'rename y to z'
   $ hg mv z x
   $ hg ci -m 'rename z to x'
   $ hg l
   @  3 rename z to x
   |  x z
   o  2 rename y to z
   |  y z
   o  1 rename x to y
   |  x y
   o  0 add x
      x
   $ hg debugpathcopies 0 3
 
 Copy x to z, then remove z, then copy x2 (same content as x) to z. With copy metadata in the
 changeset, the two copies here will have the same filelog entry, so ctx['z'].introrev() might point
 to the first commit that added the file. We should still report the copy as being from x2.
   $ newrepo
   $ echo x > x
   $ echo x > x2
   $ hg ci -Aqm 'add x and x2 with same content'
   $ hg cp x z
   $ hg ci -qm 'copy x to z'
   $ hg rm z
   $ hg ci -m 'remove z'
   $ hg cp x2 z
   $ hg ci -m 'copy x2 to z'
   $ hg l
   @  3 copy x2 to z
   |  z
   o  2 remove z
   |  z
   o  1 copy x to z
   |  z
   o  0 add x and x2 with same content
      x x2
   $ hg debugp1copies -r 3
   x2 -> z
   $ hg debugpathcopies 0 3
   x2 -> z
 
 Create x and y, then rename them both to the same name, but on different sides of a fork
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg mv x z
   $ hg ci -qm 'rename x to z'
   $ hg co -q 0
   $ hg mv y z
   $ hg ci -qm 'rename y to z'
   $ hg l
   @  2 rename y to z
   |  y z
   | o  1 rename x to z
   |/   x z
   o  0 add x and y
      x y
   $ hg debugpathcopies 1 2
   z -> x
   y -> z
 
 Fork renames x to y on one side and removes x on the other
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg co -q 0
   $ hg rm x
   $ hg ci -m 'remove x'
   created new head
   $ hg l
   @  2 remove x
   |  x
   | o  1 rename x to y
   |/   x y
   o  0 add x
      x
   $ hg debugpathcopies 1 2
 
 Merge rename from other branch
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg mv x y
   $ hg ci -m 'rename x to y'
   $ hg co -q 0
   $ echo z > z
   $ hg ci -Aqm 'add z'
   $ hg merge -q 1
   $ hg debugp1copies
   $ hg debugp2copies
   $ hg ci -m 'merge rename from p2'
   $ hg l
   @    3 merge rename from p2
   |\
   | o  2 add z
   | |  z
   o |  1 rename x to y
   |/   x y
   o  0 add x
      x
 Perhaps we should indicate the rename here, but `hg status` is documented to be weird during
 merges, so...
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 0 3
   x -> y
   $ hg debugpathcopies 1 2
   y -> x
   $ hg debugpathcopies 1 3
   $ hg debugpathcopies 2 3
   x -> y
 
 Copy file from either side in a merge
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg co -q null
   $ echo y > y
   $ hg ci -Aqm 'add y'
   $ hg merge -q 0
   $ hg cp y z
   $ hg debugp1copies
   y -> z
   $ hg debugp2copies
   $ hg ci -m 'copy file from p1 in merge'
   $ hg co -q 1
   $ hg merge -q 0
   $ hg cp x z
   $ hg debugp1copies
   $ hg debugp2copies
   x -> z
   $ hg ci -qm 'copy file from p2 in merge'
   $ hg l
   @    3 copy file from p2 in merge
   |\   z
   +---o  2 copy file from p1 in merge
   | |/   z
   | o  1 add y
   |    y
   o  0 add x
      x
   $ hg debugp1copies -r 2
   y -> z
   $ hg debugp2copies -r 2
   $ hg debugpathcopies 1 2
   y -> z
   $ hg debugpathcopies 0 2
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   x -> z
   $ hg debugpathcopies 1 3
   $ hg debugpathcopies 0 3
   x -> z
 
 Copy file that exists on both sides of the merge, same content on both sides
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x on branch 1'
   $ hg co -q null
   $ echo x > x
   $ hg ci -Aqm 'add x on branch 2'
   $ hg merge -q 0
   $ hg cp x z
   $ hg debugp1copies
   x -> z
   $ hg debugp2copies
   $ hg ci -qm 'merge'
   $ hg l
   @    2 merge
   |\   z
   | o  1 add x on branch 2
   |    x
   o  0 add x on branch 1
      x
   $ hg debugp1copies -r 2
   x -> z
   $ hg debugp2copies -r 2
 It's a little weird that it shows up on both sides
   $ hg debugpathcopies 1 2
   x -> z
   $ hg debugpathcopies 0 2
   x -> z (filelog !)
 
 Copy file that exists on both sides of the merge, different content
   $ newrepo
   $ echo branch1 > x
   $ hg ci -Aqm 'add x on branch 1'
   $ hg co -q null
   $ echo branch2 > x
   $ hg ci -Aqm 'add x on branch 2'
   $ hg merge -q 0
   warning: conflicts while merging x! (edit, then use 'hg resolve --mark')
   [1]
   $ echo resolved > x
   $ hg resolve -m x
   (no more unresolved files)
   $ hg cp x z
   $ hg debugp1copies
   x -> z
   $ hg debugp2copies
   $ hg ci -qm 'merge'
   $ hg l
   @    2 merge
   |\   x z
   | o  1 add x on branch 2
   |    x
   o  0 add x on branch 1
      x
   $ hg debugp1copies -r 2
   x -> z (changeset !)
   x -> z (sidedata !)
   $ hg debugp2copies -r 2
   x -> z (no-changeset no-sidedata !)
   $ hg debugpathcopies 1 2
   x -> z (changeset !)
   x -> z (sidedata !)
   $ hg debugpathcopies 0 2
   x -> z (no-changeset no-sidedata !)
 
 Copy x->y on one side of merge and copy x->z on the other side. Pathcopies from one parent
 of the merge to the merge should include the copy from the other side.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg cp x y
   $ hg ci -qm 'copy x to y'
   $ hg co -q 0
   $ hg cp x z
   $ hg ci -qm 'copy x to z'
   $ hg merge -q 1
   $ hg ci -m 'merge copy x->y and copy x->z'
   $ hg l
   @    3 merge copy x->y and copy x->z
   |\
   | o  2 copy x to z
   | |  z
   o |  1 copy x to y
   |/   y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 2 3
   x -> y
   $ hg debugpathcopies 1 3
   x -> z
 
 Copy x to y on one side of merge, create y and rename to z on the other side.
   $ newrepo
   $ echo x > x
   $ hg ci -Aqm 'add x'
   $ hg cp x y
   $ hg ci -qm 'copy x to y'
   $ hg co -q 0
   $ echo y > y
   $ hg ci -Aqm 'add y'
   $ hg mv y z
   $ hg ci -m 'rename y to z'
   $ hg merge -q 1
   $ hg ci -m 'merge'
   $ hg l
   @    4 merge
   |\
   | o  3 rename y to z
   | |  y z
   | o  2 add y
   | |  y
   o |  1 copy x to y
   |/   y
   o  0 add x
      x
   $ hg debugp1copies -r 3
   y -> z
   $ hg debugp2copies -r 3
   $ hg debugpathcopies 2 3
   y -> z
   $ hg debugpathcopies 1 3
   y -> z (no-filelog !)
 
 Create x and y, then rename x to z on one side of merge, and rename y to z and
 modify z on the other side. When storing copies in the changeset, we don't
 filter out copies whose target was created on the other side of the merge.
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg mv x z
   $ hg ci -qm 'rename x to z'
   $ hg co -q 0
   $ hg mv y z
   $ hg ci -qm 'rename y to z'
   $ echo z >> z
   $ hg ci -m 'modify z'
   $ hg merge -q 1
   warning: conflicts while merging z! (edit, then use 'hg resolve --mark')
   [1]
   $ echo z > z
   $ hg resolve -qm z
   $ hg ci -m 'merge 1 into 3'
 Try merging the other direction too
   $ hg co -q 1
   $ hg merge -q 3
   warning: conflicts while merging z! (edit, then use 'hg resolve --mark')
   [1]
   $ echo z > z
   $ hg resolve -qm z
   $ hg ci -m 'merge 3 into 1'
   created new head
   $ hg l
   @    5 merge 3 into 1
   |\   z
   +---o  4 merge 1 into 3
   | |/   z
   | o  3 modify z
   | |  z
   | o  2 rename y to z
   | |  y z
   o |  1 rename x to z
   |/   x z
   o  0 add x and y
      x y
   $ hg debugpathcopies 1 4
   y -> z (no-filelog !)
   $ hg debugpathcopies 2 4
   x -> z (no-filelog !)
   $ hg debugpathcopies 0 4
   x -> z (filelog !)
   y -> z (no-filelog !)
   $ hg debugpathcopies 1 5
   y -> z (no-filelog !)
   $ hg debugpathcopies 2 5
   x -> z (no-filelog !)
   $ hg debugpathcopies 0 5
   x -> z
 
 Create x and y, then remove y and rename x to y on one side of merge, and
 modify x on the other side. The modification to x from the second side
 should be propagated to y.
   $ newrepo
   $ echo original > x
   $ hg add x
   $ echo unrelated > y
   $ hg add y
   $ hg commit -m 'add x and y'
   $ hg remove y
   $ hg commit -m 'remove y'
   $ hg rename x y
   $ hg commit -m 'rename x to y'
   $ hg checkout -q 0
   $ echo modified > x
   $ hg commit -m 'modify x'
   created new head
   $ hg l
   @  3 modify x
   |  x
   | o  2 rename x to y
   | |  x y
   | o  1 remove y
   |/   y
   o  0 add x and y
      x y
 #if filelog
   $ hg merge 2
   file 'x' was deleted in other [merge rev] but was modified in local [working copy].
   You can use (c)hanged version, (d)elete, or leave (u)nresolved.
   What do you want to do? u
   1 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   [1]
 This should ideally be "modified", but we will probably not be able to fix
 that in the filelog case.
   $ cat y
   original
 #else
   $ hg merge 2
   merging x and y to y
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ cat y
   modified
 #endif
 Same as above, but in the opposite direction
 #if filelog
   $ hg co -qC 2
   $ hg merge 3
   file 'x' was deleted in local [working copy] but was modified in other [merge rev].
   You can use (c)hanged version, leave (d)eleted, or leave (u)nresolved.
   What do you want to do? u
   0 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg merge --abort' to abandon
   [1]
 BROKEN: should be "modified"
   $ cat y
   original
 #else
   $ hg co -qC 2
   $ hg merge 3
   merging y and x to y
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ cat y
   modified
 #endif
 
 Create x and y, then rename x to z on one side of merge, and rename y to z and
 then delete z on the other side.
   $ newrepo
   $ echo x > x
   $ echo y > y
   $ hg ci -Aqm 'add x and y'
   $ hg mv x z
   $ hg ci -qm 'rename x to z'
   $ hg co -q 0
   $ hg mv y z
   $ hg ci -qm 'rename y to z'
   $ hg rm z
   $ hg ci -m 'delete z'
   $ hg merge -q 1
   $ echo z > z
   $ hg ci -m 'merge 1 into 3'
 Try merging the other direction too
   $ hg co -q 1
   $ hg merge -q 3
   $ echo z > z
   $ hg ci -m 'merge 3 into 1'
   created new head
   $ hg l
   @    5 merge 3 into 1
   |\   z
   +---o  4 merge 1 into 3
   | |/   z
   | o  3 delete z
   | |  z
   | o  2 rename y to z
   | |  y z
   o |  1 rename x to z
   |/   x z
   o  0 add x and y
      x y
   $ hg debugpathcopies 1 4
   $ hg debugpathcopies 2 4
   x -> z (no-filelog !)
   $ hg debugpathcopies 0 4
   x -> z (no-changeset no-compatibility !)
   $ hg debugpathcopies 1 5
   $ hg debugpathcopies 2 5
   x -> z (no-filelog !)
   $ hg debugpathcopies 0 5
   x -> z
 
 
 Test for a case in fullcopytracing algorithm where neither of the merging csets
 is a descendant of the merge base. This test reflects that the algorithm
 correctly finds the copies:
 
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > evolution.createmarkers=True
   > evolution.allowunstable=True
   > EOF
 
   $ newrepo
   $ echo a > a
   $ hg add a
   $ hg ci -m "added a"
   $ echo b > b
   $ hg add b
   $ hg ci -m "added b"
 
   $ hg mv b b1
   $ hg ci -m "rename b to b1"
 
   $ hg up ".^"
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo d > d
   $ hg add d
   $ hg ci -m "added d"
   created new head
 
   $ echo baba >> b
   $ hg ci --amend -m "added d, modified b"
 
   $ hg l --hidden
   @  4 added d, modified b
   |  b d
   | x  3 added d
   |/   d
   | o  2 rename b to b1
   |/   b b1
   o  1 added b
   |  b
   o  0 added a
      a
 
 Grafting revision 4 on top of revision 2, showing that it respect the rename:
 
   $ hg up 2 -q
   $ hg graft -r 4 --base 3 --hidden
   grafting 4:af28412ec03c "added d, modified b" (tip) (no-changeset !)
   grafting 4:6325ca0b7a1c "added d, modified b" (tip) (changeset !)
   merging b1 and b to b1
 
   $ hg l -l1 -p
   @  5 added d, modified b
   |  b1
   ~  diff -r 5a4825cc2926 -r 94a2f1a0e8e2 b1 (no-changeset !)
   ~  diff -r 0a0ed3b3251c -r d544fb655520 b1 (changeset !)
      --- a/b1	Thu Jan 01 00:00:00 1970 +0000
      +++ b/b1	Thu Jan 01 00:00:00 1970 +0000
      @@ -1,1 +1,2 @@
       b
      +baba
   
 Test to make sure that fullcopytracing algorithm doesn't fail when neither of the
 merging csets is a descendant of the base.
 -------------------------------------------------------------------------------------------------
 
   $ newrepo
   $ echo a > a
   $ hg add a
   $ hg ci -m "added a"
   $ echo b > b
   $ hg add b
   $ hg ci -m "added b"
 
   $ echo foobar > willconflict
   $ hg add willconflict
   $ hg ci -m "added willconflict"
   $ echo c > c
   $ hg add c
   $ hg ci -m "added c"
 
   $ hg l
   @  3 added c
   |  c
   o  2 added willconflict
   |  willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
   $ hg up ".^^"
   0 files updated, 0 files merged, 2 files removed, 0 files unresolved
   $ echo d > d
   $ hg add d
   $ hg ci -m "added d"
   created new head
 
   $ echo barfoo > willconflict
   $ hg add willconflict
   $ hg ci --amend -m "added willconflict and d"
 
   $ hg l
   @  5 added willconflict and d
   |  d willconflict
   | o  3 added c
   | |  c
   | o  2 added willconflict
   |/   willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
   $ hg rebase -r . -d 2 -t :other
   rebasing 5:5018b1509e94 tip "added willconflict and d" (no-changeset !)
   rebasing 5:af8d273bf580 tip "added willconflict and d" (changeset !)
 
   $ hg up 3 -q
   $ hg l --hidden
   o  6 added willconflict and d
   |  d willconflict
   | x  5 added willconflict and d
   | |  d willconflict
   | | x  4 added d
   | |/   d
   +---@  3 added c
   | |    c
   o |  2 added willconflict
   |/   willconflict
   o  1 added b
   |  b
   o  0 added a
      a
 
 Now if we trigger a merge between revision 3 and 6 using base revision 4,
 neither of the merging csets will be a descendant of the base revision:
 
   $ hg graft -r 6 --base 4 --hidden -t :other
   grafting 6:99802e4f1e46 "added willconflict and d" (tip) (no-changeset !)
   grafting 6:b19f0df72728 "added willconflict and d" (tip) (changeset !)

tests/test-copy.t

@@ -1,374 +1,385
   $ mkdir part1
   $ cd part1
 
   $ hg init
   $ echo a > a
   $ hg add a
   $ hg commit -m "1"
   $ hg status
   $ hg copy a b
   $ hg --config ui.portablefilenames=abort copy a con.xml
   abort: filename contains 'con', which is reserved on Windows: con.xml
   [10]
   $ hg status
   A b
   $ hg sum
   parent: 0:c19d34741b0a tip
    1
   branch: default
   commit: 1 copied
   update: (current)
   phases: 1 draft
   $ hg --debug commit -m "2"
   committing files:
   b
    b: copy a:b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   committing manifest
   committing changelog
   updating the branch cache
   committed changeset 1:93580a2c28a50a56f63526fb305067e6fbf739c4
 
 we should see two history entries
 
   $ hg history -v
   changeset:   1:93580a2c28a5
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   files:       b
   description:
   2
   
   
   changeset:   0:c19d34741b0a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   files:       a
   description:
   1
   
   
 
 we should see one log entry for a
 
   $ hg log a
   changeset:   0:c19d34741b0a
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     1
   
 
 this should show a revision linked to changeset 0
 
   $ hg debugindex a
      rev linkrev nodeid       p1           p2
        0       0 b789fdd96dc2 000000000000 000000000000
 
 we should see one log entry for b
 
   $ hg log b
   changeset:   1:93580a2c28a5
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     2
   
 
 this should show a revision linked to changeset 1
 
   $ hg debugindex b
      rev linkrev nodeid       p1           p2
        0       1 37d9b5d994ea 000000000000 000000000000
 
 this should show the rename information in the metadata
 
   $ hg debugdata b 0 | head -3 | tail -2
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
 
 #if reporevlogstore
   $ md5sum.py .hg/store/data/b.i
   44913824c8f5890ae218f9829535922e  .hg/store/data/b.i
 #endif
   $ hg cat b > bsum
   $ md5sum.py bsum
   60b725f10c9c85c70d97880dfe8191b3  bsum
   $ hg cat a > asum
   $ md5sum.py asum
   60b725f10c9c85c70d97880dfe8191b3  asum
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   checked 2 changesets with 2 changes to 2 files
 
   $ cd ..
 
 
   $ mkdir part2
   $ cd part2
 
   $ hg init
   $ echo foo > foo
 should fail - foo is not managed
   $ hg mv foo bar
   foo: not copying - file is not managed
   abort: no files to copy
   [10]
   $ hg st -A
   ? foo
 respects ui.relative-paths
   $ mkdir dir
   $ cd dir
   $ hg mv ../foo ../bar
   ../foo: not copying - file is not managed
   abort: no files to copy
   [10]
   $ hg mv ../foo ../bar --config ui.relative-paths=yes
   ../foo: not copying - file is not managed
   abort: no files to copy
   [10]
   $ hg mv ../foo ../bar --config ui.relative-paths=no
   foo: not copying - file is not managed
   abort: no files to copy
   [10]
   $ cd ..
   $ rmdir dir
   $ hg add foo
 dry-run; print a warning that this is not a real copy; foo is added
   $ hg mv --dry-run foo bar
   foo has not been committed yet, so no copy data will be stored for bar.
   $ hg st -A
   A foo
 should print a warning that this is not a real copy; bar is added
   $ hg mv foo bar
   foo has not been committed yet, so no copy data will be stored for bar.
   $ hg st -A
   A bar
 should print a warning that this is not a real copy; foo is added
   $ hg cp bar foo
   bar has not been committed yet, so no copy data will be stored for foo.
   $ hg rm -f bar
   $ rm bar
   $ hg st -A
   A foo
   $ hg commit -m1
 
 moving a missing file
   $ rm foo
   $ hg mv foo foo3
   foo: deleted in working directory
   foo3 does not exist!
   $ hg up -qC .
 
 copy --after to a nonexistent target filename
   $ hg cp -A foo dummy
   foo: not recording copy - dummy does not exist
   [1]
 
 dry-run; should show that foo is clean
   $ hg copy --dry-run foo bar
   $ hg st -A
   C foo
 should show copy
   $ hg copy foo bar
   $ hg st -C
   A bar
     foo
 
 shouldn't show copy
   $ hg commit -m2
   $ hg st -C
 
 should match
   $ hg debugindex foo
      rev linkrev nodeid       p1           p2
        0       0 2ed2a3912a0b 000000000000 000000000000
   $ hg debugrename bar
   bar renamed from foo:2ed2a3912a0b24502043eae84ee4b279c18b90dd
 
   $ echo bleah > foo
   $ echo quux > bar
   $ hg commit -m3
 
 should not be renamed
   $ hg debugrename bar
   bar not renamed
 
   $ hg copy -f foo bar
 should show copy
   $ hg st -C
   M bar
     foo
 
 XXX: filtering lfilesrepo.status() in 3.3-rc causes the copy source to not be
 displayed.
   $ hg st -C --config extensions.largefiles=
   The fsmonitor extension is incompatible with the largefiles extension and has been disabled. (fsmonitor !)
   M bar
     foo
 
   $ hg commit -m3
 
 should show no parents for tip
   $ hg debugindex bar
      rev linkrev nodeid       p1           p2
        0       1 7711d36246cc 000000000000 000000000000
        1       2 bdf70a2b8d03 7711d36246cc 000000000000
        2       3 b2558327ea8d 000000000000 000000000000
 should match
   $ hg debugindex foo
      rev linkrev nodeid       p1           p2
        0       0 2ed2a3912a0b 000000000000 000000000000
        1       2 dd12c926cf16 2ed2a3912a0b 000000000000
   $ hg debugrename bar
   bar renamed from foo:dd12c926cf165e3eb4cf87b084955cb617221c17
 
 should show no copies
   $ hg st -C
 
+note: since filelog based copy tracing only trace copy for new file, the copy information here is not displayed.
+
+  $ hg status --copies --change .
+  M bar
+
+They are a devel option to walk all file and fine this information anyway.
+
+  $ hg status --copies --change . --config devel.copy-tracing.trace-all-files=yes
+  M bar
+    foo
+
 copy --after on an added file
   $ cp bar baz
   $ hg add baz
   $ hg cp -A bar baz
   $ hg st -C
   A baz
     bar
 
 foo was clean:
   $ hg st -AC foo
   C foo
 Trying to copy on top of an existing file fails,
   $ hg copy -A bar foo
   foo: not overwriting - file already committed
   ('hg copy --after --force' to replace the file by recording a copy)
   [1]
 same error without the --after, so the user doesn't have to go through
 two hints:
   $ hg copy bar foo
   foo: not overwriting - file already committed
   ('hg copy --force' to replace the file by recording a copy)
   [1]
 but it's considered modified after a copy --after --force
   $ hg copy -Af bar foo
   $ hg st -AC foo
   M foo
     bar
 The hint for a file that exists but is not in file history doesn't
 mention --force:
   $ touch xyzzy
   $ hg cp bar xyzzy
   xyzzy: not overwriting - file exists
   ('hg copy --after' to record the copy)
   [1]
   $ hg co -qC .
   $ rm baz xyzzy
 
 
 Test unmarking copy of a single file
 
 # Set up by creating a copy
   $ hg cp bar baz
 # Test uncopying a non-existent file
   $ hg copy --forget non-existent
   non-existent: $ENOENT$
 # Test uncopying an tracked but unrelated file
   $ hg copy --forget foo
   foo: not unmarking as copy - file is not marked as copied
 # Test uncopying a copy source
   $ hg copy --forget bar
   bar: not unmarking as copy - file is not marked as copied
 # baz should still be marked as a copy
   $ hg st -C
   A baz
     bar
 # Test the normal case
   $ hg copy --forget baz
   $ hg st -C
   A baz
 # Test uncopy with matching an non-matching patterns
   $ hg cp bar baz --after
   $ hg copy --forget bar baz
   bar: not unmarking as copy - file is not marked as copied
   $ hg st -C
   A baz
 # Test uncopy with no exact matches
   $ hg cp bar baz --after
   $ hg copy --forget .
   $ hg st -C
   A baz
   $ hg forget baz
   $ rm baz
 
 Test unmarking copy of a directory
 
   $ mkdir dir
   $ echo foo > dir/foo
   $ echo bar > dir/bar
   $ hg add dir
   adding dir/bar
   adding dir/foo
   $ hg ci -m 'add dir/'
   $ hg cp dir dir2
   copying dir/bar to dir2/bar
   copying dir/foo to dir2/foo
   $ touch dir2/untracked
   $ hg copy --forget dir2
   $ hg st -C
   A dir2/bar
   A dir2/foo
   ? dir2/untracked
 # Clean up for next test
   $ hg forget dir2
   removing dir2/bar
   removing dir2/foo
   $ rm -r dir2
 
 Test uncopy on committed copies
 
 # Commit some copies
   $ hg cp bar baz
   $ hg cp bar qux
   $ hg ci -m copies
   $ hg st -C --change .
   A baz
     bar
   A qux
     bar
   $ base=$(hg log -r '.^' -T '{rev}')
   $ hg log -G -T '{rev}:{node|short} {desc}\n' -r $base:
   @  5:a612dc2edfda copies
   |
   o  4:4800b1f1f38e add dir/
   |
   ~
 # Add a dirty change on top to show that it's unaffected
   $ echo dirty >> baz
   $ hg st
   M baz
   $ cat baz
   bleah
   dirty
   $ hg copy --forget --at-rev . baz
   saved backup bundle to $TESTTMP/part2/.hg/strip-backup/a612dc2edfda-e36b4448-uncopy.hg
 # The unwanted copy is no longer recorded, but the unrelated one is
   $ hg st -C --change .
   A baz
   A qux
     bar
 # The old commit is gone and we have updated to the new commit
   $ hg log -G -T '{rev}:{node|short} {desc}\n' -r $base:
   @  5:c45090e5effe copies
   |
   o  4:4800b1f1f38e add dir/
   |
   ~
 # Working copy still has the uncommitted change
   $ hg st
   M baz
   $ cat baz
   bleah
   dirty
 
   $ cd ..