copytrace: add a a new config to limit the number of drafts in heuristics

The heuristics options tries to the default full copytracing algorithm if both
the source and destination branches contains of non-public changesets only. But
this can be slow in cases when we have a lot of drafts.

This patch adds a new config option experimental.copytrace.sourcecommitlimit
which defaults to 100. This value will be the limit of number of drafts from c1
to base. Incase there are more changesets even though they are draft, the
heuristics algorithm will be used.

Differential Revision: https://phab.mercurial-scm.org/D763

mercurial/configitems.py

@@ -1,665 +1,668 b''
 # configitems.py - centralized declaration of configuration option
 #
 #  Copyright 2017 Pierre-Yves David <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import functools
 
 from . import (
     encoding,
     error,
 )
 
 def loadconfigtable(ui, extname, configtable):
     """update config item known to the ui with the extension ones"""
     for section, items in configtable.items():
         knownitems = ui._knownconfig.setdefault(section, {})
         knownkeys = set(knownitems)
         newkeys = set(items)
         for key in sorted(knownkeys & newkeys):
             msg = "extension '%s' overwrite config item '%s.%s'"
             msg %= (extname, section, key)
             ui.develwarn(msg, config='warn-config')
 
         knownitems.update(items)
 
 class configitem(object):
     """represent a known config item
 
     :section: the official config section where to find this item,
        :name: the official name within the section,
     :default: default value for this item,
     :alias: optional list of tuples as alternatives.
     """
 
     def __init__(self, section, name, default=None, alias=()):
         self.section = section
         self.name = name
         self.default = default
         self.alias = list(alias)
 
 coreitems = {}
 
 def _register(configtable, *args, **kwargs):
     item = configitem(*args, **kwargs)
     section = configtable.setdefault(item.section, {})
     if item.name in section:
         msg = "duplicated config item registration for '%s.%s'"
         raise error.ProgrammingError(msg % (item.section, item.name))
     section[item.name] = item
 
 # special value for case where the default is derived from other values
 dynamicdefault = object()
 
 # Registering actual config items
 
 def getitemregister(configtable):
     return functools.partial(_register, configtable)
 
 coreconfigitem = getitemregister(coreitems)
 
 coreconfigitem('auth', 'cookiefile',
     default=None,
 )
 # bookmarks.pushing: internal hack for discovery
 coreconfigitem('bookmarks', 'pushing',
     default=list,
 )
 # bundle.mainreporoot: internal hack for bundlerepo
 coreconfigitem('bundle', 'mainreporoot',
     default='',
 )
 # bundle.reorder: experimental config
 coreconfigitem('bundle', 'reorder',
     default='auto',
 )
 coreconfigitem('censor', 'policy',
     default='abort',
 )
 coreconfigitem('chgserver', 'idletimeout',
     default=3600,
 )
 coreconfigitem('chgserver', 'skiphash',
     default=False,
 )
 coreconfigitem('cmdserver', 'log',
     default=None,
 )
 coreconfigitem('color', 'mode',
     default='auto',
 )
 coreconfigitem('color', 'pagermode',
     default=dynamicdefault,
 )
 coreconfigitem('commands', 'status.relative',
     default=False,
 )
 coreconfigitem('commands', 'status.skipstates',
     default=[],
 )
 coreconfigitem('commands', 'status.verbose',
     default=False,
 )
 coreconfigitem('commands', 'update.requiredest',
     default=False,
 )
 coreconfigitem('devel', 'all-warnings',
     default=False,
 )
 coreconfigitem('devel', 'bundle2.debug',
     default=False,
 )
 coreconfigitem('devel', 'check-locks',
     default=False,
 )
 coreconfigitem('devel', 'check-relroot',
     default=False,
 )
 coreconfigitem('devel', 'default-date',
     default=None,
 )
 coreconfigitem('devel', 'deprec-warn',
     default=False,
 )
 coreconfigitem('devel', 'disableloaddefaultcerts',
     default=False,
 )
 coreconfigitem('devel', 'legacy.exchange',
     default=list,
 )
 coreconfigitem('devel', 'servercafile',
     default='',
 )
 coreconfigitem('devel', 'serverexactprotocol',
     default='',
 )
 coreconfigitem('devel', 'serverrequirecert',
     default=False,
 )
 coreconfigitem('devel', 'strip-obsmarkers',
     default=True,
 )
 coreconfigitem('email', 'charsets',
     default=list,
 )
 coreconfigitem('email', 'method',
     default='smtp',
 )
 coreconfigitem('experimental', 'bundle-phases',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2-advertise',
     default=True,
 )
 coreconfigitem('experimental', 'bundle2-output-capture',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2.pushback',
     default=False,
 )
 coreconfigitem('experimental', 'bundle2lazylocking',
     default=False,
 )
 coreconfigitem('experimental', 'bundlecomplevel',
     default=None,
 )
 coreconfigitem('experimental', 'changegroup3',
     default=False,
 )
 coreconfigitem('experimental', 'clientcompressionengines',
     default=list,
 )
 coreconfigitem('experimental', 'copytrace',
     default='on',
 )
+coreconfigitem('experimental', 'copytrace.sourcecommitlimit',
+    default=100,
+)
 coreconfigitem('experimental', 'crecordtest',
     default=None,
 )
 coreconfigitem('experimental', 'editortmpinhg',
     default=False,
 )
 coreconfigitem('experimental', 'stabilization',
     default=list,
     alias=[('experimental', 'evolution')],
 )
 coreconfigitem('experimental', 'stabilization.bundle-obsmarker',
     default=False,
     alias=[('experimental', 'evolution.bundle-obsmarker')],
 )
 coreconfigitem('experimental', 'stabilization.track-operation',
     default=True,
     alias=[('experimental', 'evolution.track-operation')]
 )
 coreconfigitem('experimental', 'exportableenviron',
     default=list,
 )
 coreconfigitem('experimental', 'extendedheader.index',
     default=None,
 )
 coreconfigitem('experimental', 'extendedheader.similarity',
     default=False,
 )
 coreconfigitem('experimental', 'format.compression',
     default='zlib',
 )
 coreconfigitem('experimental', 'graphshorten',
     default=False,
 )
 coreconfigitem('experimental', 'hook-track-tags',
     default=False,
 )
 coreconfigitem('experimental', 'httppostargs',
     default=False,
 )
 coreconfigitem('experimental', 'manifestv2',
     default=False,
 )
 coreconfigitem('experimental', 'mergedriver',
     default=None,
 )
 coreconfigitem('experimental', 'obsmarkers-exchange-debug',
     default=False,
 )
 coreconfigitem('experimental', 'rebase.multidest',
     default=False,
 )
 coreconfigitem('experimental', 'revertalternateinteractivemode',
     default=True,
 )
 coreconfigitem('experimental', 'revlogv2',
     default=None,
 )
 coreconfigitem('experimental', 'spacemovesdown',
     default=False,
 )
 coreconfigitem('experimental', 'treemanifest',
     default=False,
 )
 coreconfigitem('experimental', 'updatecheck',
     default=None,
 )
 coreconfigitem('format', 'aggressivemergedeltas',
     default=False,
 )
 coreconfigitem('format', 'chunkcachesize',
     default=None,
 )
 coreconfigitem('format', 'dotencode',
     default=True,
 )
 coreconfigitem('format', 'generaldelta',
     default=False,
 )
 coreconfigitem('format', 'manifestcachesize',
     default=None,
 )
 coreconfigitem('format', 'maxchainlen',
     default=None,
 )
 coreconfigitem('format', 'obsstore-version',
     default=None,
 )
 coreconfigitem('format', 'usefncache',
     default=True,
 )
 coreconfigitem('format', 'usegeneraldelta',
     default=True,
 )
 coreconfigitem('format', 'usestore',
     default=True,
 )
 coreconfigitem('hostsecurity', 'ciphers',
     default=None,
 )
 coreconfigitem('hostsecurity', 'disabletls10warning',
     default=False,
 )
 coreconfigitem('http_proxy', 'always',
     default=False,
 )
 coreconfigitem('http_proxy', 'host',
     default=None,
 )
 coreconfigitem('http_proxy', 'no',
     default=list,
 )
 coreconfigitem('http_proxy', 'passwd',
     default=None,
 )
 coreconfigitem('http_proxy', 'user',
     default=None,
 )
 coreconfigitem('merge', 'followcopies',
     default=True,
 )
 coreconfigitem('pager', 'ignore',
     default=list,
 )
 coreconfigitem('patch', 'eol',
     default='strict',
 )
 coreconfigitem('patch', 'fuzz',
     default=2,
 )
 coreconfigitem('paths', 'default',
     default=None,
 )
 coreconfigitem('paths', 'default-push',
     default=None,
 )
 coreconfigitem('phases', 'checksubrepos',
     default='follow',
 )
 coreconfigitem('phases', 'publish',
     default=True,
 )
 coreconfigitem('profiling', 'enabled',
     default=False,
 )
 coreconfigitem('profiling', 'format',
     default='text',
 )
 coreconfigitem('profiling', 'freq',
     default=1000,
 )
 coreconfigitem('profiling', 'limit',
     default=30,
 )
 coreconfigitem('profiling', 'nested',
     default=0,
 )
 coreconfigitem('profiling', 'sort',
     default='inlinetime',
 )
 coreconfigitem('profiling', 'statformat',
     default='hotpath',
 )
 coreconfigitem('progress', 'assume-tty',
     default=False,
 )
 coreconfigitem('progress', 'changedelay',
     default=1,
 )
 coreconfigitem('progress', 'clear-complete',
     default=True,
 )
 coreconfigitem('progress', 'debug',
     default=False,
 )
 coreconfigitem('progress', 'delay',
     default=3,
 )
 coreconfigitem('progress', 'disable',
     default=False,
 )
 coreconfigitem('progress', 'estimate',
     default=2,
 )
 coreconfigitem('progress', 'refresh',
     default=0.1,
 )
 coreconfigitem('progress', 'width',
     default=dynamicdefault,
 )
 coreconfigitem('push', 'pushvars.server',
     default=False,
 )
 coreconfigitem('server', 'bundle1',
     default=True,
 )
 coreconfigitem('server', 'bundle1gd',
     default=None,
 )
 coreconfigitem('server', 'compressionengines',
     default=list,
 )
 coreconfigitem('server', 'concurrent-push-mode',
     default='strict',
 )
 coreconfigitem('server', 'disablefullbundle',
     default=False,
 )
 coreconfigitem('server', 'maxhttpheaderlen',
     default=1024,
 )
 coreconfigitem('server', 'preferuncompressed',
     default=False,
 )
 coreconfigitem('server', 'uncompressed',
     default=True,
 )
 coreconfigitem('server', 'uncompressedallowsecret',
     default=False,
 )
 coreconfigitem('server', 'validate',
     default=False,
 )
 coreconfigitem('server', 'zliblevel',
     default=-1,
 )
 coreconfigitem('smtp', 'host',
     default=None,
 )
 coreconfigitem('smtp', 'local_hostname',
     default=None,
 )
 coreconfigitem('smtp', 'password',
     default=None,
 )
 coreconfigitem('smtp', 'tls',
     default='none',
 )
 coreconfigitem('smtp', 'username',
     default=None,
 )
 coreconfigitem('sparse', 'missingwarning',
     default=True,
 )
 coreconfigitem('trusted', 'groups',
     default=list,
 )
 coreconfigitem('trusted', 'users',
     default=list,
 )
 coreconfigitem('ui', '_usedassubrepo',
     default=False,
 )
 coreconfigitem('ui', 'allowemptycommit',
     default=False,
 )
 coreconfigitem('ui', 'archivemeta',
     default=True,
 )
 coreconfigitem('ui', 'askusername',
     default=False,
 )
 coreconfigitem('ui', 'clonebundlefallback',
     default=False,
 )
 coreconfigitem('ui', 'clonebundleprefers',
     default=list,
 )
 coreconfigitem('ui', 'clonebundles',
     default=True,
 )
 coreconfigitem('ui', 'color',
     default='auto',
 )
 coreconfigitem('ui', 'commitsubrepos',
     default=False,
 )
 coreconfigitem('ui', 'debug',
     default=False,
 )
 coreconfigitem('ui', 'debugger',
     default=None,
 )
 coreconfigitem('ui', 'fallbackencoding',
     default=None,
 )
 coreconfigitem('ui', 'forcecwd',
     default=None,
 )
 coreconfigitem('ui', 'forcemerge',
     default=None,
 )
 coreconfigitem('ui', 'formatdebug',
     default=False,
 )
 coreconfigitem('ui', 'formatjson',
     default=False,
 )
 coreconfigitem('ui', 'formatted',
     default=None,
 )
 coreconfigitem('ui', 'graphnodetemplate',
     default=None,
 )
 coreconfigitem('ui', 'http2debuglevel',
     default=None,
 )
 coreconfigitem('ui', 'interactive',
     default=None,
 )
 coreconfigitem('ui', 'interface',
     default=None,
 )
 coreconfigitem('ui', 'logblockedtimes',
     default=False,
 )
 coreconfigitem('ui', 'logtemplate',
     default=None,
 )
 coreconfigitem('ui', 'merge',
     default=None,
 )
 coreconfigitem('ui', 'mergemarkers',
     default='basic',
 )
 coreconfigitem('ui', 'mergemarkertemplate',
     default=('{node|short} '
             '{ifeq(tags, "tip", "", '
             'ifeq(tags, "", "", "{tags} "))}'
             '{if(bookmarks, "{bookmarks} ")}'
             '{ifeq(branch, "default", "", "{branch} ")}'
             '- {author|user}: {desc|firstline}')
 )
 coreconfigitem('ui', 'nontty',
     default=False,
 )
 coreconfigitem('ui', 'origbackuppath',
     default=None,
 )
 coreconfigitem('ui', 'paginate',
     default=True,
 )
 coreconfigitem('ui', 'patch',
     default=None,
 )
 coreconfigitem('ui', 'portablefilenames',
     default='warn',
 )
 coreconfigitem('ui', 'promptecho',
     default=False,
 )
 coreconfigitem('ui', 'quiet',
     default=False,
 )
 coreconfigitem('ui', 'quietbookmarkmove',
     default=False,
 )
 coreconfigitem('ui', 'remotecmd',
     default='hg',
 )
 coreconfigitem('ui', 'report_untrusted',
     default=True,
 )
 coreconfigitem('ui', 'rollback',
     default=True,
 )
 coreconfigitem('ui', 'slash',
     default=False,
 )
 coreconfigitem('ui', 'ssh',
     default='ssh',
 )
 coreconfigitem('ui', 'statuscopies',
     default=False,
 )
 coreconfigitem('ui', 'strict',
     default=False,
 )
 coreconfigitem('ui', 'style',
     default='',
 )
 coreconfigitem('ui', 'supportcontact',
     default=None,
 )
 coreconfigitem('ui', 'textwidth',
     default=78,
 )
 coreconfigitem('ui', 'timeout',
     default='600',
 )
 coreconfigitem('ui', 'traceback',
     default=False,
 )
 coreconfigitem('ui', 'tweakdefaults',
     default=False,
 )
 coreconfigitem('ui', 'usehttp2',
     default=False,
 )
 coreconfigitem('ui', 'username',
     alias=[('ui', 'user')]
 )
 coreconfigitem('ui', 'verbose',
     default=False,
 )
 coreconfigitem('verify', 'skipflags',
     default=None,
 )
 coreconfigitem('web', 'accesslog',
     default='-',
 )
 coreconfigitem('web', 'address',
     default='',
 )
 coreconfigitem('web', 'allow_archive',
     default=list,
 )
 coreconfigitem('web', 'allow_read',
     default=list,
 )
 coreconfigitem('web', 'baseurl',
     default=None,
 )
 coreconfigitem('web', 'cacerts',
     default=None,
 )
 coreconfigitem('web', 'certificate',
     default=None,
 )
 coreconfigitem('web', 'collapse',
     default=False,
 )
 coreconfigitem('web', 'csp',
     default=None,
 )
 coreconfigitem('web', 'deny_read',
     default=list,
 )
 coreconfigitem('web', 'descend',
     default=True,
 )
 coreconfigitem('web', 'description',
     default="",
 )
 coreconfigitem('web', 'encoding',
     default=lambda: encoding.encoding,
 )
 coreconfigitem('web', 'errorlog',
     default='-',
 )
 coreconfigitem('web', 'ipv6',
     default=False,
 )
 coreconfigitem('web', 'port',
     default=8000,
 )
 coreconfigitem('web', 'prefix',
     default='',
 )
 coreconfigitem('web', 'refreshinterval',
     default=20,
 )
 coreconfigitem('web', 'stripes',
     default=1,
 )
 coreconfigitem('web', 'style',
     default='paper',
 )
 coreconfigitem('web', 'templates',
     default=None,
 )
 coreconfigitem('worker', 'backgroundclose',
     default=dynamicdefault,
 )
 # Windows defaults to a limit of 512 open files. A buffer of 128
 # should give us enough headway.
 coreconfigitem('worker', 'backgroundclosemaxqueue',
     default=384,
 )
 coreconfigitem('worker', 'backgroundcloseminfilecount',
     default=2048,
 )
 coreconfigitem('worker', 'backgroundclosethreadcount',
     default=4,
 )
 coreconfigitem('worker', 'numcpus',
     default=None,
 )

mercurial/copies.py

@@ -1,862 +1,867 b''
 # 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 heapq
 import os
 
 from . import (
     match as matchmod,
     node,
     pathutil,
     phases,
     scmutil,
     util,
 )
 
 def _findlimit(repo, a, b):
     """
     Find the last revision that needs to be checked to ensure that a full
     transitive closure for file copies can be properly calculated.
     Generally, this means finding the earliest revision number that's an
     ancestor of a or b but not both, except when a or b is a direct descendent
     of the other, in which case we can return the minimum revnum of a and b.
     None if no such revision exists.
     """
 
     # basic idea:
     # - mark a and b with different sides
     # - if a parent's children are all on the same side, the parent is
     #   on that side, otherwise it is on no side
     # - walk the graph in topological order with the help of a heap;
     #   - add unseen parents to side map
     #   - clear side of any parent that has children on different sides
     #   - track number of interesting revs that might still be on a side
     #   - track the lowest interesting rev seen
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
     working = len(cl) # pseudo rev for the working directory
     if a is None:
         a = working
     if b is None:
         b = working
 
     side = {a: -1, b: 1}
     visit = [-a, -b]
     heapq.heapify(visit)
     interesting = len(visit)
     hascommonancestor = False
     limit = working
 
     while interesting:
         r = -heapq.heappop(visit)
         if r == working:
             parents = [cl.rev(p) for p in repo.dirstate.parents()]
         else:
             parents = cl.parentrevs(r)
         for p in parents:
             if p < 0:
                 continue
             if p not in side:
                 # first time we see p; add it to visit
                 side[p] = side[r]
                 if side[p]:
                     interesting += 1
                 heapq.heappush(visit, -p)
             elif side[p] and side[p] != side[r]:
                 # p was interesting but now we know better
                 side[p] = 0
                 interesting -= 1
                 hascommonancestor = True
         if side[r]:
             limit = r # lowest rev visited
             interesting -= 1
 
     if not hascommonancestor:
         return None
 
     # Consider the following flow (see test-commit-amend.t under issue4405):
     # 1/ File 'a0' committed
     # 2/ File renamed from 'a0' to 'a1' in a new commit (call it 'a1')
     # 3/ Move back to first commit
     # 4/ Create a new commit via revert to contents of 'a1' (call it 'a1-amend')
     # 5/ Rename file from 'a1' to 'a2' and commit --amend 'a1-msg'
     #
     # During the amend in step five, we will be in this state:
     #
     # @  3 temporary amend commit for a1-amend
     # |
     # o  2 a1-amend
     # |
     # | o  1 a1
     # |/
     # o  0 a0
     #
     # When _findlimit is called, a and b are revs 3 and 0, so limit will be 2,
     # yet the filelog has the copy information in rev 1 and we will not look
     # back far enough unless we also look at the a and b as candidates.
     # This only occurs when a is a descendent of b or visa-versa.
     return min(limit, a, b)
 
 def _chain(src, dst, a, b):
     '''chain two sets of copies a->b'''
     t = a.copy()
     for k, v in b.iteritems():
         if v in t:
             # found a chain
             if t[v] != k:
                 # file wasn't renamed back to itself
                 t[k] = t[v]
             if v not in dst:
                 # chain was a rename, not a copy
                 del t[v]
         if v in src:
             # file is a copy of an existing file
             t[k] = v
 
     # remove criss-crossed copies
     for k, v in t.items():
         if k in src and v in dst:
             del t[k]
 
     return t
 
 def _tracefile(fctx, am, limit=-1):
     '''return file context that is the ancestor of fctx present in ancestor
     manifest am, stopping after the first ancestor lower than limit'''
 
     for f in fctx.ancestors():
         if am.get(f.path(), None) == f.filenode():
             return f
         if limit >= 0 and f.linkrev() < limit and f.rev() < limit:
             return None
 
 def _dirstatecopies(d):
     ds = d._repo.dirstate
     c = ds.copies().copy()
     for k in c.keys():
         if ds[k] not in 'anm':
             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 _forwardcopies(a, b, match=None):
     '''find {dst@b: src@a} copy mapping where a is an ancestor of b'''
 
     # check for working copy
     w = None
     if b.rev() is None:
         w = b
         b = w.p1()
         if a == b:
             # short-circuit to avoid issues with merge states
             return _dirstatecopies(w)
 
     # files might have to be traced back to the fctx parent of the last
     # one-side-only changeset, but not further back than that
     limit = _findlimit(a._repo, a.rev(), b.rev())
     if limit is None:
         limit = -1
     am = a.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() == node.nullid:
         filesmatcher = scmutil.matchfiles(a._repo, b.files())
         forwardmissingmatch = matchmod.intersectmatchers(match, filesmatcher)
     missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
     for f in missing:
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
         ofctx = _tracefile(fctx, am, limit)
         if ofctx:
             cm[f] = ofctx.path()
 
     # combine copies from dirstate if necessary
     if w is not None:
         cm = _chain(a, w, cm, _dirstatecopies(w))
 
     return cm
 
 def _backwardrenames(a, b):
     if a._repo.ui.config('experimental', 'copytrace') == '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.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(f.iteritems()):
         # 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'''
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
         return _forwardcopies(x, y, match=match)
     if a == y:
         return _backwardrenames(x, y)
     return _chain(x, y, _backwardrenames(x, a),
                   _forwardcopies(a, y, match=match))
 
 def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2, baselabel=''):
     """Computes, based on addedinm1 and addedinm2, the files exclusive to c1
     and c2. This is its own function so extensions can easily wrap this call
     to see what files mergecopies is about to process.
 
     Even though c1 and c2 are not used in this function, they are useful in
     other extensions for being able to read the file nodes of the changed files.
 
     "baselabel" can be passed to help distinguish the multiple computations
     done in the graft case.
     """
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
     header = "  unmatched files in %s"
     if baselabel:
         header += ' (from %s)' % baselabel
     if u1:
         repo.ui.debug("%s:\n   %s\n" % (header % 'local', "\n   ".join(u1)))
     if u2:
         repo.ui.debug("%s:\n   %s\n" % (header % 'other', "\n   ".join(u2)))
     return u1, u2
 
 def _makegetfctx(ctx):
     """return a 'getfctx' function suitable for _checkcopies usage
 
     We have to re-setup the function building 'filectx' for each
     '_checkcopies' to ensure the linkrev adjustment is properly setup for
     each. Linkrev adjustment is important to avoid bug in rename
     detection. Moreover, having a proper '_ancestrycontext' setup ensures
     the performance impact of this adjustment is kept limited. Without it,
     each file could do a full dag traversal making the time complexity of
     the operation explode (see issue4537).
 
     This function exists here mostly to limit the impact on stable. Feel
     free to refactor on default.
     """
     rev = ctx.rev()
     repo = ctx._repo
     ac = getattr(ctx, '_ancestrycontext', None)
     if ac is None:
         revs = [rev]
         if rev is None:
             revs = [p.rev() for p in ctx.parents()]
         ac = repo.changelog.ancestors(revs, inclusive=True)
         ctx._ancestrycontext = ac
     def makectx(f, n):
         if n in node.wdirnodes:  # in a working context?
             if ctx.rev() is None:
                 return ctx.filectx(f)
             return repo[None][f]
         fctx = repo.filectx(f, fileid=n)
         # setup only needed for filectx not create from a changectx
         fctx._ancestrycontext = ac
         fctx._descendantrev = rev
         return fctx
     return util.lrucachefunc(makectx)
 
 def _combinecopies(copyfrom, copyto, finalcopy, diverge, incompletediverge):
     """combine partial copy paths"""
     remainder = {}
     for f in copyfrom:
         if f in copyto:
             finalcopy[copyto[f]] = copyfrom[f]
             del copyto[f]
     for f in incompletediverge:
         assert f not in diverge
         ic = incompletediverge[f]
         if ic[0] in copyto:
             diverge[f] = [copyto[ic[0]], ic[1]]
         else:
             remainder[f] = ic
     return remainder
 
 def mergecopies(repo, c1, c2, base):
     """
     The function calling different copytracing algorithms on the basis of config
     which find 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 five dicts: "copy", "movewithdir", "diverge", "renamedelete" and
     "dirmove".
 
     "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.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     "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.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return {}, {}, {}, {}, {}
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return repo.dirstate.copies(), {}, {}, {}, {}
 
     copytracing = repo.ui.config('experimental', 'copytrace')
 
     # 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 == 'off':
         return {}, {}, {}, {}, {}
     elif copytracing == 'heuristics':
         # Do full copytracing if only drafts are involved as that will be fast
         # enough and will also cover the copies which can be missed by
         # heuristics
-        if _isfullcopytraceable(c1, base):
+        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(c1, base):
+def _isfullcopytraceable(repo, c1, base):
     """ Checks that if base, source and destination are all draft branches, if
     yes let's use the full copytrace algorithm for increased capabilities since
     it will be fast enough.
     """
+    if c1.rev() is None:
+        c1 = c1.p1()
 
     nonpublicphases = set([phases.draft, phases.secret])
 
     if (c1.phase() in nonpublicphases) and (base.phase() in nonpublicphases):
-        return True
+        sourcecommitlimit = repo.ui.configint('experimental',
+                                              'copytrace.sourcecommitlimit')
+        commits = len(repo.revs('%d::%d', base.rev(), c1.rev()))
+        return commits < sourcecommitlimit
     return False
 
 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.
     """
     # In certain scenarios (e.g. graft, update or rebase), base can be
     # overridden We still need to know a real common ancestor in this case We
     # can't just compute _c1.ancestor(_c2) and compare it to ca, because there
     # can be multiple common ancestors, e.g. in case of bidmerge.  Because our
     # caller may not know if the revision passed in lieu of the CA is a genuine
     # common ancestor or not without explicitly checking it, it's better to
     # determine that here.
     #
     # base.descendant(wc) and base.descendant(base) are False, work around that
     _c1 = c1.p1() if c1.rev() is None else c1
     _c2 = c2.p1() if c2.rev() is None else c2
     # an endpoint is "dirty" if it isn't a descendant of the merge base
     # if we have a dirty endpoint, we need to trigger graft logic, and also
     # keep track of which endpoint is dirty
     dirtyc1 = not (base == _c1 or base.descendant(_c1))
     dirtyc2 = not (base == _c2 or base.descendant(_c2))
     graft = dirtyc1 or dirtyc2
     tca = base
     if graft:
         tca = _c1.ancestor(_c2)
 
     limit = _findlimit(repo, c1.rev(), c2.rev())
     if limit is None:
         # no common ancestor, no copies
         return {}, {}, {}, {}, {}
     repo.ui.debug("  searching for copies back to rev %d\n" % limit)
 
     m1 = c1.manifest()
     m2 = c2.manifest()
     mb = base.manifest()
 
     # gather data from _checkcopies:
     # - diverge = record all diverges in this dict
     # - copy = record all non-divergent copies in this dict
     # - fullcopy = record all copies in this dict
     # - incomplete = record non-divergent partial copies here
     # - incompletediverge = record divergent partial copies here
     diverge = {} # divergence data is shared
     incompletediverge  = {}
     data1 = {'copy': {},
              'fullcopy': {},
              'incomplete': {},
              'diverge': diverge,
              'incompletediverge': incompletediverge,
             }
     data2 = {'copy': {},
              'fullcopy': {},
              'incomplete': {},
              'diverge': diverge,
              'incompletediverge': incompletediverge,
             }
 
     # find interesting file sets from manifests
     addedinm1 = m1.filesnotin(mb)
     addedinm2 = m2.filesnotin(mb)
     bothnew = sorted(addedinm1 & addedinm2)
     if tca == base:
         # unmatched file from base
         u1r, u2r = _computenonoverlap(repo, c1, c2, addedinm1, addedinm2)
         u1u, u2u = u1r, u2r
     else:
         # unmatched file from base (DAG rotation in the graft case)
         u1r, u2r = _computenonoverlap(repo, c1, c2, addedinm1, addedinm2,
                                       baselabel='base')
         # unmatched file from topological common ancestors (no DAG rotation)
         # need to recompute this for directory move handling when grafting
         mta = tca.manifest()
         u1u, u2u = _computenonoverlap(repo, c1, c2, m1.filesnotin(mta),
                                                     m2.filesnotin(mta),
                                       baselabel='topological common ancestor')
 
     for f in u1u:
         _checkcopies(c1, c2, f, base, tca, dirtyc1, limit, data1)
 
     for f in u2u:
         _checkcopies(c2, c1, f, base, tca, dirtyc2, limit, data2)
 
     copy = dict(data1['copy'])
     copy.update(data2['copy'])
     fullcopy = dict(data1['fullcopy'])
     fullcopy.update(data2['fullcopy'])
 
     if dirtyc1:
         _combinecopies(data2['incomplete'], data1['incomplete'], copy, diverge,
                        incompletediverge)
     else:
         _combinecopies(data1['incomplete'], data2['incomplete'], copy, diverge,
                        incompletediverge)
 
     renamedelete = {}
     renamedeleteset = set()
     divergeset = set()
     for of, fl in diverge.items():
         if len(fl) == 1 or of in c1 or of in c2:
             del diverge[of] # not actually divergent, or not a rename
             if of not in c1 and of not in c2:
                 # renamed on one side, deleted on the other side, but filter
                 # out files that have been renamed and then deleted
                 renamedelete[of] = [f for f in fl if f in c1 or f in c2]
                 renamedeleteset.update(fl) # reverse map for below
         else:
             divergeset.update(fl) # reverse map for below
 
     if bothnew:
         repo.ui.debug("  unmatched files new in both:\n   %s\n"
                       % "\n   ".join(bothnew))
     bothdiverge = {}
     bothincompletediverge = {}
     remainder = {}
     both1 = {'copy': {},
              'fullcopy': {},
              'incomplete': {},
              'diverge': bothdiverge,
              'incompletediverge': bothincompletediverge
             }
     both2 = {'copy': {},
              'fullcopy': {},
              'incomplete': {},
              'diverge': bothdiverge,
              'incompletediverge': bothincompletediverge
             }
     for f in bothnew:
         _checkcopies(c1, c2, f, base, tca, dirtyc1, limit, both1)
         _checkcopies(c2, c1, f, base, tca, dirtyc2, limit, both2)
     if dirtyc1:
         # incomplete copies may only be found on the "dirty" side for bothnew
         assert not both2['incomplete']
         remainder = _combinecopies({}, both1['incomplete'], copy, bothdiverge,
                                    bothincompletediverge)
     elif dirtyc2:
         assert not both1['incomplete']
         remainder = _combinecopies({}, both2['incomplete'], copy, bothdiverge,
                                    bothincompletediverge)
     else:
         # incomplete copies and divergences can't happen outside grafts
         assert not both1['incomplete']
         assert not both2['incomplete']
         assert not bothincompletediverge
     for f in remainder:
         assert f not in bothdiverge
         ic = remainder[f]
         if ic[0] in (m1 if dirtyc1 else m2):
             # backed-out rename on one side, but watch out for deleted files
             bothdiverge[f] = ic
     for of, fl in bothdiverge.items():
         if len(fl) == 2 and fl[0] == fl[1]:
             copy[fl[0]] = of # not actually divergent, just matching renames
 
     if fullcopy and repo.ui.debugflag:
         repo.ui.debug("  all copies found (* = to merge, ! = divergent, "
                       "% = renamed and deleted):\n")
         for f in sorted(fullcopy):
             note = ""
             if f in copy:
                 note += "*"
             if f in divergeset:
                 note += "!"
             if f in renamedeleteset:
                 note += "%"
             repo.ui.debug("   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f,
                                                               note))
     del divergeset
 
     if not fullcopy:
         return copy, {}, diverge, renamedelete, {}
 
     repo.ui.debug("  checking for directory renames\n")
 
     # generate a directory move map
     d1, d2 = c1.dirs(), c2.dirs()
     # Hack for adding '', which is not otherwise added, to d1 and d2
     d1.addpath('/')
     d2.addpath('/')
     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 fullcopy.iteritems():
         dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif dsrc in d1 and ddst in d1:
             # directory wasn't entirely moved locally
             invalid.add(dsrc + "/")
         elif dsrc in d2 and ddst in d2:
             # directory wasn't entirely moved remotely
             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 d1, d2, invalid
 
     if not dirmove:
         return copy, {}, diverge, renamedelete, {}
 
     for d in dirmove:
         repo.ui.debug("   discovered dir src: '%s' -> dst: '%s'\n" %
                       (d, dirmove[d]))
 
     movewithdir = {}
     # check unaccounted nonoverlapping files against directory moves
     for f in u1r + u2r:
         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(("   pending file src: '%s' -> "
                                        "dst: '%s'\n") % (f, df))
                     break
 
     return copy, movewithdir, diverge, renamedelete, dirmove
 
 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
     """
 
     if c1.rev() is None:
         c1 = c1.p1()
     if c2.rev() is None:
         c2 = c2.p1()
 
     copies = {}
 
     changedfiles = set()
     m1 = c1.manifest()
     if not repo.revs('%d::%d', base.rev(), c2.rev()):
         # If base is not in c2 branch, we switch to fullcopytracing
         repo.ui.debug("switching to full copytracing as base is not "
                       "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("switching to full copytracing because of merges\n")
             return _fullcopytracing(repo, c1, c2, base)
         changedfiles.update(ctx.files())
         ctx = ctx.p1()
 
     cp = _forwardcopies(base, c2)
     for dst, src in cp.iteritems():
         if src in m1:
             copies[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.
     missingfiles = filter(lambda f: f not in m1 and f in base and f in c2,
                           changedfiles)
 
     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)
 
         # in case of a rebase/graft, base may not be a common ancestor
         anc = c1.ancestor(c2)
 
         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)
             for candidate in movecandidates:
                 f1 = c1.filectx(candidate)
                 if _related(f1, f2, anc.rev()):
                     # if there are a few related copies then we'll merge
                     # changes into all of them. This matches the behaviour
                     # of upstream copytracing
                     copies[candidate] = f
 
     return copies, {}, {}, {}, {}
 
 def _related(f1, f2, limit):
     """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 f1 # 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)
             elif f1 == f2:
                 return f1 # a match
             elif f1r == f2r or f1r < limit or f2r < limit:
                 return False # copy no longer relevant
     except StopIteration:
         return False
 
 def _checkcopies(srcctx, dstctx, f, base, tca, remotebase, limit, data):
     """
     check possible copies of f from msrc to mdst
 
     srcctx = starting context for f in msrc
     dstctx = destination context for f in mdst
     f = the filename to check (as in msrc)
     base = the changectx used as a merge base
     tca = topological common ancestor for graft-like scenarios
     remotebase = True if base is outside tca::srcctx, False otherwise
     limit = the rev number to not search beyond
     data = dictionary of dictionary to store copy data. (see mergecopies)
 
     note: limit is only an optimization, and provides no guarantee that
     irrelevant revisions will not be visited
     there is no easy way to make this algorithm stop in a guaranteed way
     once it "goes behind a certain revision".
     """
 
     msrc = srcctx.manifest()
     mdst = dstctx.manifest()
     mb = base.manifest()
     mta = tca.manifest()
     # Might be true if this call is about finding backward renames,
     # This happens in the case of grafts because the DAG is then rotated.
     # If the file exists in both the base and the source, we are not looking
     # for a rename on the source side, but on the part of the DAG that is
     # traversed backwards.
     #
     # In the case there is both backward and forward renames (before and after
     # the base) this is more complicated as we must detect a divergence.
     # We use 'backwards = False' in that case.
     backwards = not remotebase and base != tca and f in mb
     getsrcfctx = _makegetfctx(srcctx)
     getdstfctx = _makegetfctx(dstctx)
 
     if msrc[f] == mb.get(f) and not remotebase:
         # Nothing to merge
         return
 
     of = None
     seen = {f}
     for oc in getsrcfctx(f, msrc[f]).ancestors():
         ocr = oc.linkrev()
         of = oc.path()
         if of in seen:
             # check limit late - grab last rename before
             if ocr < limit:
                 break
             continue
         seen.add(of)
 
         # remember for dir rename detection
         if backwards:
             data['fullcopy'][of] = f # grafting backwards through renames
         else:
             data['fullcopy'][f] = of
         if of not in mdst:
             continue # no match, keep looking
         if mdst[of] == mb.get(of):
             return # no merge needed, quit early
         c2 = getdstfctx(of, mdst[of])
         # c2 might be a plain new file on added on destination side that is
         # unrelated to the droids we are looking for.
         cr = _related(oc, c2, tca.rev())
         if cr and (of == f or of == c2.path()): # non-divergent
             if backwards:
                 data['copy'][of] = f
             elif of in mb:
                 data['copy'][f] = of
             elif remotebase: # special case: a <- b <- a -> b "ping-pong" rename
                 data['copy'][of] = f
                 del data['fullcopy'][f]
                 data['fullcopy'][of] = f
             else: # divergence w.r.t. graft CA on one side of topological CA
                 for sf in seen:
                     if sf in mb:
                         assert sf not in data['diverge']
                         data['diverge'][sf] = [f, of]
                         break
             return
 
     if of in mta:
         if backwards or remotebase:
             data['incomplete'][of] = f
         else:
             for sf in seen:
                 if sf in mb:
                     if tca == base:
                         data['diverge'].setdefault(sf, []).append(f)
                     else:
                         data['incompletediverge'][sf] = [of, f]
                     return
 
 def duplicatecopies(repo, rev, fromrev, skiprev=None):
     '''reproduce copies from fromrev to rev in the dirstate
 
     If skiprev is specified, it's a revision that should be used to
     filter copy records. Any copies that occur between fromrev and
     skiprev will not be duplicated, even if they appear in the set of
     copies between fromrev and rev.
     '''
     exclude = {}
     if (skiprev is not None and
         repo.ui.config('experimental', 'copytrace') != 'off'):
         # copytrace='off' skips this line, but not the entire function because
         # the line below is O(size of the repo) during a rebase, while the rest
         # of the function is much faster (and is required for carrying copy
         # metadata across the rebase anyway).
         exclude = pathcopies(repo[fromrev], repo[skiprev])
     for dst, src in pathcopies(repo[fromrev], repo[rev]).iteritems():
         # copies.pathcopies returns backward renames, so dst might not
         # actually be in the dirstate
         if dst in exclude:
             continue
         if repo.dirstate[dst] in "nma":
             repo.dirstate.copy(src, dst)

tests/test-copytrace-heuristics.t

@@ -1,667 +1,714 b''
 Test for the heuristic copytracing algorithm
 ============================================
 
   $ cat >> $TESTTMP/copytrace.sh << '__EOF__'
   > initclient() {
   > cat >> $1/.hg/hgrc <<EOF
   > [experimental]
   > copytrace = heuristics
   > EOF
   > }
   > __EOF__
   $ . "$TESTTMP/copytrace.sh"
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > rebase=
   > shelve=
   > EOF
 
 Check filename heuristics (same dirname and same basename)
   $ hg init server
   $ cd server
   $ echo a > a
   $ mkdir dir
   $ echo a > dir/file.txt
   $ hg addremove
   adding a
   adding dir/file.txt
   $ hg ci -m initial
   $ hg mv a b
   $ hg mv -q dir dir2
   $ hg ci -m 'mv a b, mv dir/ dir2/'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ echo b > a
   $ echo b > dir/file.txt
   $ hg ci -qm 'mod a, mod dir/file.txt'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 557f403c0afd2a3cf15d7e2fb1f1001a8b85e081
   |   desc: mod a, mod dir/file.txt, phase: draft
   | o  changeset: 928d74bc9110681920854d845c06959f6dfc9547
   |/    desc: mv a b, mv dir/ dir2/, phase: public
   o  changeset: 3c482b16e54596fed340d05ffaf155f156cda7ee
       desc: initial, phase: public
 
   $ hg rebase -s . -d 1
   rebasing 2:557f403c0afd "mod a, mod dir/file.txt" (tip)
   merging b and a to b
   merging dir2/file.txt and dir/file.txt to dir2/file.txt
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/557f403c0afd-9926eeff-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Make sure filename heuristics do not when they are not related
   $ hg init server
   $ cd server
   $ echo 'somecontent' > a
   $ hg add a
   $ hg ci -m initial
   $ hg rm a
   $ echo 'completelydifferentcontext' > b
   $ hg add b
   $ hg ci -m 'rm a, add b'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ printf 'somecontent\nmoarcontent' > a
   $ hg ci -qm 'mode a'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: d526312210b9e8f795d576a77dc643796384d86e
   |   desc: mode a, phase: draft
   | o  changeset: 46985f76c7e5e5123433527f5c8526806145650b
   |/    desc: rm a, add b, phase: public
   o  changeset: e5b71fb099c29d9172ef4a23485aaffd497e4cc0
       desc: initial, phase: public
 
   $ hg rebase -s . -d 1
   rebasing 2:d526312210b9 "mode a" (tip)
   other [source] changed a which local [dest] deleted
   use (c)hanged version, leave (d)eleted, or leave (u)nresolved? u
   unresolved conflicts (see hg resolve, then hg rebase --continue)
   [1]
 
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Test when lca didn't modified the file that was moved
   $ hg init server
   $ cd server
   $ echo 'somecontent' > a
   $ hg add a
   $ hg ci -m initial
   $ echo c > c
   $ hg add c
   $ hg ci -m randomcommit
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 1
   $ echo b > a
   $ hg ci -qm 'mod a'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 9d5cf99c3d9f8e8b05ba55421f7f56530cfcf3bc
   |   desc: mod a, phase: draft
   | o  changeset: d760186dd240fc47b91eb9f0b58b0002aaeef95d
   |/    desc: mv a b, phase: public
   o  changeset: 48e1b6ba639d5d7fb313fa7989eebabf99c9eb83
   |   desc: randomcommit, phase: public
   o  changeset: e5b71fb099c29d9172ef4a23485aaffd497e4cc0
       desc: initial, phase: public
 
   $ hg rebase -s . -d 2
   rebasing 3:9d5cf99c3d9f "mod a" (tip)
   merging b and a to b
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/9d5cf99c3d9f-f02358cc-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Rebase "backwards"
   $ hg init server
   $ cd server
   $ echo 'somecontent' > a
   $ hg add a
   $ hg ci -m initial
   $ echo c > c
   $ hg add c
   $ hg ci -m randomcommit
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 2
   $ echo b > b
   $ hg ci -qm 'mod b'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: fbe97126b3969056795c462a67d93faf13e4d298
   |   desc: mod b, phase: draft
   o  changeset: d760186dd240fc47b91eb9f0b58b0002aaeef95d
   |   desc: mv a b, phase: public
   o  changeset: 48e1b6ba639d5d7fb313fa7989eebabf99c9eb83
   |   desc: randomcommit, phase: public
   o  changeset: e5b71fb099c29d9172ef4a23485aaffd497e4cc0
       desc: initial, phase: public
 
   $ hg rebase -s . -d 0
   rebasing 3:fbe97126b396 "mod b" (tip)
   merging a and b to a
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/fbe97126b396-cf5452a1-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Rebase draft commit on top of draft commit
   $ hg init repo
   $ initclient repo
   $ cd repo
   $ echo 'somecontent' > a
   $ hg add a
   $ hg ci -m initial
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ hg up -q ".^"
   $ echo b > a
   $ hg ci -qm 'mod a'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 5268f05aa1684cfb5741e9eb05eddcc1c5ee7508
   |   desc: mod a, phase: draft
   | o  changeset: 542cb58df733ee48fa74729bd2cdb94c9310d362
   |/    desc: mv a b, phase: draft
   o  changeset: e5b71fb099c29d9172ef4a23485aaffd497e4cc0
       desc: initial, phase: draft
 
   $ hg rebase -s . -d 1
   rebasing 2:5268f05aa168 "mod a" (tip)
   merging b and a to b
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/5268f05aa168-284f6515-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Check a few potential move candidates
   $ hg init server
   $ initclient server
   $ cd server
   $ mkdir dir
   $ echo a > dir/a
   $ hg add dir/a
   $ hg ci -qm initial
   $ hg mv dir/a dir/b
   $ hg ci -qm 'mv dir/a dir/b'
   $ mkdir dir2
   $ echo b > dir2/a
   $ hg add dir2/a
   $ hg ci -qm 'create dir2/a'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ echo b > dir/a
   $ hg ci -qm 'mod dir/a'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 6b2f4cece40fd320f41229f23821256ffc08efea
   |   desc: mod dir/a, phase: draft
   | o  changeset: 4494bf7efd2e0dfdd388e767fb913a8a3731e3fa
   | |   desc: create dir2/a, phase: public
   | o  changeset: b1784dfab6ea6bfafeb11c0ac50a2981b0fe6ade
   |/    desc: mv dir/a dir/b, phase: public
   o  changeset: 36859b8907c513a3a87ae34ba5b1e7eea8c20944
       desc: initial, phase: public
 
   $ hg rebase -s . -d 2
   rebasing 3:6b2f4cece40f "mod dir/a" (tip)
   merging dir/b and dir/a to dir/b
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/6b2f4cece40f-503efe60-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move file in one branch and delete it in another
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ hg up -q ".^"
   $ hg rm a
   $ hg ci -m 'del a'
   created new head
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 7d61ee3b1e48577891a072024968428ba465c47b
   |   desc: del a, phase: draft
   | o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |/    desc: mv a b, phase: draft
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
 
   $ hg rebase -s 1 -d 2
   rebasing 1:472e38d57782 "mv a b"
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/472e38d57782-17d50e29-rebase.hg (glob)
   $ hg up -q c492ed3c7e35dcd1dc938053b8adf56e2cfbd062
   $ ls
   b
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move a directory in draft branch
   $ hg init server
   $ initclient server
   $ cd server
   $ mkdir dir
   $ echo a > dir/a
   $ hg add dir/a
   $ hg ci -qm initial
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ echo b > dir/a
   $ hg ci -qm 'mod dir/a'
   $ hg up -q ".^"
   $ hg mv -q dir/ dir2
   $ hg ci -qm 'mv dir/ dir2/'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: a33d80b6e352591dfd82784e1ad6cdd86b25a239
   |   desc: mv dir/ dir2/, phase: draft
   | o  changeset: 6b2f4cece40fd320f41229f23821256ffc08efea
   |/    desc: mod dir/a, phase: draft
   o  changeset: 36859b8907c513a3a87ae34ba5b1e7eea8c20944
       desc: initial, phase: public
 
   $ hg rebase -s . -d 1
   rebasing 2:a33d80b6e352 "mv dir/ dir2/" (tip)
   merging dir/a and dir2/a to dir2/a
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/a33d80b6e352-fecb9ada-rebase.hg (glob)
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move file twice and rebase mod on top of moves
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ hg mv b c
   $ hg ci -m 'mv b c'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ echo c > a
   $ hg ci -m 'mod a'
   created new head
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: d413169422167a3fa5275fc5d71f7dea9f5775f3
   |   desc: mod a, phase: draft
   | o  changeset: d3efd280421d24f9f229997c19e654761c942a71
   | |   desc: mv b c, phase: public
   | o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |/    desc: mv a b, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
   $ hg rebase -s . -d 2
   rebasing 3:d41316942216 "mod a" (tip)
   merging c and a to c
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/d41316942216-2b5949bc-rebase.hg (glob)
 
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move file twice and rebase moves on top of mods
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ hg mv b c
   $ hg ci -m 'mv b c'
   $ hg up -q 0
   $ echo c > a
   $ hg ci -m 'mod a'
   created new head
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: d413169422167a3fa5275fc5d71f7dea9f5775f3
   |   desc: mod a, phase: draft
   | o  changeset: d3efd280421d24f9f229997c19e654761c942a71
   | |   desc: mv b c, phase: draft
   | o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |/    desc: mv a b, phase: draft
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
   $ hg rebase -s 1 -d .
   rebasing 1:472e38d57782 "mv a b"
   merging a and b to b
   rebasing 2:d3efd280421d "mv b c"
   merging b and c to c
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/472e38d57782-ab8d3c58-rebase.hg (glob)
 
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move one file and add another file in the same folder in one branch, modify file in another branch
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg mv a b
   $ hg ci -m 'mv a b'
   $ echo c > c
   $ hg add c
   $ hg ci -m 'add c'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ echo b > a
   $ hg ci -m 'mod a'
   created new head
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: ef716627c70bf4ca0bdb623cfb0d6fe5b9acc51e
   |   desc: mod a, phase: draft
   | o  changeset: b1a6187e79fbce851bb584eadcb0cc4a80290fd9
   | |   desc: add c, phase: public
   | o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |/    desc: mv a b, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
 
   $ hg rebase -s . -d 2
   rebasing 3:ef716627c70b "mod a" (tip)
   merging b and a to b
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/ef716627c70b-24681561-rebase.hg (glob)
   $ ls
   b
   c
   $ cat b
   b
 
 Merge test
   $ hg init server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ echo b > a
   $ hg ci -m 'modify a'
   $ hg up -q 0
   $ hg mv a b
   $ hg ci -m 'mv a b'
   created new head
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 2
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |   desc: mv a b, phase: public
   | o  changeset: b0357b07f79129a3d08a68621271ca1352ae8a09
   |/    desc: modify a, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
 
   $ hg merge 1
   merging b and a to b
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m merge
   $ ls
   b
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Copy and move file
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg cp a c
   $ hg mv a b
   $ hg ci -m 'cp a c, mv a b'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q 0
   $ echo b > a
   $ hg ci -m 'mod a'
   created new head
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: ef716627c70bf4ca0bdb623cfb0d6fe5b9acc51e
   |   desc: mod a, phase: draft
   | o  changeset: 4fc3fd13fbdb89ada6b75bfcef3911a689a0dde8
   |/    desc: cp a c, mv a b, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
 
   $ hg rebase -s . -d 1
   rebasing 2:ef716627c70b "mod a" (tip)
   merging b and a to b
   merging c and a to c
   saved backup bundle to $TESTTMP/repo/repo/.hg/strip-backup/ef716627c70b-24681561-rebase.hg (glob)
   $ ls
   b
   c
   $ cat b
   b
   $ cat c
   b
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Do a merge commit with many consequent moves in one branch
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ echo b > a
   $ hg ci -qm 'mod a'
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ hg up -q ".^"
   $ hg mv a b
   $ hg ci -qm 'mv a b'
   $ hg mv b c
   $ hg ci -qm 'mv b c'
   $ hg up -q 1
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   o  changeset: d3efd280421d24f9f229997c19e654761c942a71
   |   desc: mv b c, phase: draft
   o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |   desc: mv a b, phase: draft
   | @  changeset: ef716627c70bf4ca0bdb623cfb0d6fe5b9acc51e
   |/    desc: mod a, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
 
   $ hg merge 3
   merging a and c to c
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -qm 'merge'
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @    changeset: cd29b0d08c0f39bfed4cde1b40e30f419db0c825
   |\    desc: merge, phase: draft
   | o  changeset: d3efd280421d24f9f229997c19e654761c942a71
   | |   desc: mv b c, phase: draft
   | o  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   | |   desc: mv a b, phase: draft
   o |  changeset: ef716627c70bf4ca0bdb623cfb0d6fe5b9acc51e
   |/    desc: mod a, phase: public
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
   $ ls
   c
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Test shelve/unshelve
   $ hg init server
   $ initclient server
   $ cd server
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ cd ..
   $ hg clone -q server repo
   $ initclient repo
   $ cd repo
   $ echo b > a
   $ hg shelve
   shelved as default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg mv a b
   $ hg ci -m 'mv a b'
 
   $ hg log -G -T 'changeset: {node}\n desc: {desc}, phase: {phase}\n'
   @  changeset: 472e38d57782172f6c6abed82a94ca0d998c3a22
   |   desc: mv a b, phase: draft
   o  changeset: 1451231c87572a7d3f92fc210b4b35711c949a98
       desc: initial, phase: public
   $ hg unshelve
   unshelving change 'default'
   rebasing shelved changes
   rebasing 2:45f63161acea "changes to: initial" (tip)
   merging b and a to b
   $ ls
   b
   $ cat b
   b
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Test full copytrace ability on draft branch
 -------------------------------------------
 
 File directory and base name changed in same move
   $ hg init repo
   $ initclient repo
   $ mkdir repo/dir1
   $ cd repo/dir1
   $ echo a > a
   $ hg add a
   $ hg ci -qm initial
   $ cd ..
   $ hg mv -q dir1 dir2
   $ hg mv dir2/a dir2/b
   $ hg ci -qm 'mv a b; mv dir1 dir2'
   $ hg up -q '.^'
   $ cd dir1
   $ echo b >> a
   $ cd ..
   $ hg ci -qm 'mod a'
 
   $ hg log -G -T 'changeset {node}\n desc {desc}, phase: {phase}\n'
   @  changeset 6207d2d318e710b882e3d5ada2a89770efc42c96
   |   desc mod a, phase: draft
   | o  changeset abffdd4e3dfc04bc375034b970299b2a309a1cce
   |/    desc mv a b; mv dir1 dir2, phase: draft
   o  changeset 81973cd24b58db2fdf18ce3d64fb2cc3284e9ab3
       desc initial, phase: draft
 
   $ hg rebase -s . -d 1
   rebasing 2:6207d2d318e7 "mod a" (tip)
   merging dir2/b and dir1/a to dir2/b
   saved backup bundle to $TESTTMP/repo/repo/.hg/strip-backup/6207d2d318e7-1c9779ad-rebase.hg (glob)
   $ cat dir2/b
   a
   b
   $ cd ..
   $ rm -rf server
   $ rm -rf repo
 
 Move directory in one merge parent, while adding file to original directory
 in other merge parent. File moved on rebase.
   $ hg init repo
   $ initclient repo
   $ mkdir repo/dir1
   $ cd repo/dir1
   $ echo dummy > dummy
   $ hg add dummy
   $ cd ..
   $ hg ci -qm initial
   $ cd dir1
   $ echo a > a
   $ hg add a
   $ cd ..
   $ hg ci -qm 'hg add dir1/a'
   $ hg up -q '.^'
   $ hg mv -q dir1 dir2
   $ hg ci -qm 'mv dir1 dir2'
 
   $ hg log -G -T 'changeset {node}\n desc {desc}, phase: {phase}\n'
   @  changeset e8919e7df8d036e07b906045eddcd4a42ff1915f
   |   desc mv dir1 dir2, phase: draft
   | o  changeset 7c7c6f339be00f849c3cb2df738ca91db78b32c8
   |/    desc hg add dir1/a, phase: draft
   o  changeset a235dcce55dcf42034c4e374cb200662d0bb4a13
       desc initial, phase: draft
 
   $ hg rebase -s . -d 1
   rebasing 2:e8919e7df8d0 "mv dir1 dir2" (tip)
   saved backup bundle to $TESTTMP/repo/repo/.hg/strip-backup/e8919e7df8d0-f62fab62-rebase.hg (glob)
   $ ls dir2
   a
   dummy
   $ rm -rf server
   $ rm -rf repo
+
+Testing the sourcecommitlimit config
+
+  $ hg init repo
+  $ initclient repo
+  $ cd repo
+  $ echo a > a
+  $ hg ci -Aqm "added a"
+  $ echo "more things" >> a
+  $ hg ci -qm "added more things to a"
+  $ hg up 0
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ echo b > b
+  $ hg ci -Aqm "added b"
+  $ mkdir foo
+  $ hg mv a foo/bar
+  $ hg ci -m "Moved a to foo/bar"
+  $ hg log -G -T 'changeset {node}\n desc {desc}, phase: {phase}\n'
+  @  changeset b4b0f7880e500b5c364a5f07b4a2b167de7a6fb0
+  |   desc Moved a to foo/bar, phase: draft
+  o  changeset 5f6d8a4bf34ab274ccc9f631c2536964b8a3666d
+  |   desc added b, phase: draft
+  | o  changeset 8b6e13696c38e8445a759516474640c2f8dddef6
+  |/    desc added more things to a, phase: draft
+  o  changeset 9092f1db7931481f93b37d5c9fbcfc341bcd7318
+      desc added a, phase: draft
+
+When the sourcecommitlimit is small and we have more drafts, we use heuristics only
+
+  $ hg rebase -s 8b6e13696 -d . --config experimental.copytrace.sourcecommitlimit=0
+  rebasing 1:8b6e13696c38 "added more things to a"
+  other [source] changed a which local [dest] deleted
+  use (c)hanged version, leave (d)eleted, or leave (u)nresolved? u
+  unresolved conflicts (see hg resolve, then hg rebase --continue)
+  [1]
+
+But when we have "sourcecommitlimit > (no. of drafts from base to c1)", we do
+fullcopytracing
+
+  $ hg rebase --abort
+  rebase aborted
+  $ hg rebase -s 8b6e13696 -d .
+  rebasing 1:8b6e13696c38 "added more things to a"
+  merging foo/bar and a to foo/bar
+  saved backup bundle to $TESTTMP/repo/repo/repo/.hg/strip-backup/8b6e13696c38-fc14ac83-rebase.hg (glob)
+  $ cd ..
+  $ rm -rf repo