dirstate: use keyword arguments to clarify walk()'s callers

The arguments are especially non-obvious because the order is
different from dirstate.status().

Differential Revision: https://phab.mercurial-scm.org/D846

contrib/perf.py

@@ -1,1491 +1,1492 b''
 # perf.py - performance test routines
 '''helper extension to measure performance'''
 
 # "historical portability" policy of perf.py:
 #
 # We have to do:
 # - make perf.py "loadable" with as wide Mercurial version as possible
 #   This doesn't mean that perf commands work correctly with that Mercurial.
 #   BTW, perf.py itself has been available since 1.1 (or eb240755386d).
 # - make historical perf command work correctly with as wide Mercurial
 #   version as possible
 #
 # We have to do, if possible with reasonable cost:
 # - make recent perf command for historical feature work correctly
 #   with early Mercurial
 #
 # We don't have to do:
 # - make perf command for recent feature work correctly with early
 #   Mercurial
 
 from __future__ import absolute_import
 import functools
 import gc
 import os
 import random
 import struct
 import sys
 import time
 from mercurial import (
     changegroup,
     cmdutil,
     commands,
     copies,
     error,
     extensions,
     mdiff,
     merge,
     revlog,
     util,
 )
 
 # for "historical portability":
 # try to import modules separately (in dict order), and ignore
 # failure, because these aren't available with early Mercurial
 try:
     from mercurial import branchmap # since 2.5 (or bcee63733aad)
 except ImportError:
     pass
 try:
     from mercurial import obsolete # since 2.3 (or ad0d6c2b3279)
 except ImportError:
     pass
 try:
     from mercurial import registrar # since 3.7 (or 37d50250b696)
     dir(registrar) # forcibly load it
 except ImportError:
     registrar = None
 try:
     from mercurial import repoview # since 2.5 (or 3a6ddacb7198)
 except ImportError:
     pass
 try:
     from mercurial import scmutil # since 1.9 (or 8b252e826c68)
 except ImportError:
     pass
 
 # for "historical portability":
 # define util.safehasattr forcibly, because util.safehasattr has been
 # available since 1.9.3 (or 94b200a11cf7)
 _undefined = object()
 def safehasattr(thing, attr):
     return getattr(thing, attr, _undefined) is not _undefined
 setattr(util, 'safehasattr', safehasattr)
 
 # for "historical portability":
 # define util.timer forcibly, because util.timer has been available
 # since ae5d60bb70c9
 if safehasattr(time, 'perf_counter'):
     util.timer = time.perf_counter
 elif os.name == 'nt':
     util.timer = time.clock
 else:
     util.timer = time.time
 
 # for "historical portability":
 # use locally defined empty option list, if formatteropts isn't
 # available, because commands.formatteropts has been available since
 # 3.2 (or 7a7eed5176a4), even though formatting itself has been
 # available since 2.2 (or ae5f92e154d3)
 formatteropts = getattr(cmdutil, "formatteropts",
                         getattr(commands, "formatteropts", []))
 
 # for "historical portability":
 # use locally defined option list, if debugrevlogopts isn't available,
 # because commands.debugrevlogopts has been available since 3.7 (or
 # 5606f7d0d063), even though cmdutil.openrevlog() has been available
 # since 1.9 (or a79fea6b3e77).
 revlogopts = getattr(cmdutil, "debugrevlogopts",
                      getattr(commands, "debugrevlogopts", [
         ('c', 'changelog', False, ('open changelog')),
         ('m', 'manifest', False, ('open manifest')),
         ('', 'dir', False, ('open directory manifest')),
         ]))
 
 cmdtable = {}
 
 # for "historical portability":
 # define parsealiases locally, because cmdutil.parsealiases has been
 # available since 1.5 (or 6252852b4332)
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 if safehasattr(registrar, 'command'):
     command = registrar.command(cmdtable)
 elif safehasattr(cmdutil, 'command'):
     import inspect
     command = cmdutil.command(cmdtable)
     if 'norepo' not in inspect.getargspec(command)[0]:
         # for "historical portability":
         # wrap original cmdutil.command, because "norepo" option has
         # been available since 3.1 (or 75a96326cecb)
         _command = command
         def command(name, options=(), synopsis=None, norepo=False):
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return _command(name, list(options), synopsis)
 else:
     # for "historical portability":
     # define "@command" annotation locally, because cmdutil.command
     # has been available since 1.9 (or 2daa5179e73f)
     def command(name, options=(), synopsis=None, norepo=False):
         def decorator(func):
             if synopsis:
                 cmdtable[name] = func, list(options), synopsis
             else:
                 cmdtable[name] = func, list(options)
             if norepo:
                 commands.norepo += ' %s' % ' '.join(parsealiases(name))
             return func
         return decorator
 
 def getlen(ui):
     if ui.configbool("perf", "stub"):
         return lambda x: 1
     return len
 
 def gettimer(ui, opts=None):
     """return a timer function and formatter: (timer, formatter)
 
     This function exists to gather the creation of formatter in a single
     place instead of duplicating it in all performance commands."""
 
     # enforce an idle period before execution to counteract power management
     # experimental config: perf.presleep
     time.sleep(getint(ui, "perf", "presleep", 1))
 
     if opts is None:
         opts = {}
     # redirect all to stderr unless buffer api is in use
     if not ui._buffers:
         ui = ui.copy()
         uifout = safeattrsetter(ui, 'fout', ignoremissing=True)
         if uifout:
             # for "historical portability":
             # ui.fout/ferr have been available since 1.9 (or 4e1ccd4c2b6d)
             uifout.set(ui.ferr)
 
     # get a formatter
     uiformatter = getattr(ui, 'formatter', None)
     if uiformatter:
         fm = uiformatter('perf', opts)
     else:
         # for "historical portability":
         # define formatter locally, because ui.formatter has been
         # available since 2.2 (or ae5f92e154d3)
         from mercurial import node
         class defaultformatter(object):
             """Minimized composition of baseformatter and plainformatter
             """
             def __init__(self, ui, topic, opts):
                 self._ui = ui
                 if ui.debugflag:
                     self.hexfunc = node.hex
                 else:
                     self.hexfunc = node.short
             def __nonzero__(self):
                 return False
             __bool__ = __nonzero__
             def startitem(self):
                 pass
             def data(self, **data):
                 pass
             def write(self, fields, deftext, *fielddata, **opts):
                 self._ui.write(deftext % fielddata, **opts)
             def condwrite(self, cond, fields, deftext, *fielddata, **opts):
                 if cond:
                     self._ui.write(deftext % fielddata, **opts)
             def plain(self, text, **opts):
                 self._ui.write(text, **opts)
             def end(self):
                 pass
         fm = defaultformatter(ui, 'perf', opts)
 
     # stub function, runs code only once instead of in a loop
     # experimental config: perf.stub
     if ui.configbool("perf", "stub"):
         return functools.partial(stub_timer, fm), fm
     return functools.partial(_timer, fm), fm
 
 def stub_timer(fm, func, title=None):
     func()
 
 def _timer(fm, func, title=None):
     gc.collect()
     results = []
     begin = util.timer()
     count = 0
     while True:
         ostart = os.times()
         cstart = util.timer()
         r = func()
         cstop = util.timer()
         ostop = os.times()
         count += 1
         a, b = ostart, ostop
         results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
         if cstop - begin > 3 and count >= 100:
             break
         if cstop - begin > 10 and count >= 3:
             break
 
     fm.startitem()
 
     if title:
         fm.write('title', '! %s\n', title)
     if r:
         fm.write('result', '! result: %s\n', r)
     m = min(results)
     fm.plain('!')
     fm.write('wall', ' wall %f', m[0])
     fm.write('comb', ' comb %f', m[1] + m[2])
     fm.write('user', ' user %f', m[1])
     fm.write('sys',  ' sys %f', m[2])
     fm.write('count',  ' (best of %d)', count)
     fm.plain('\n')
 
 # utilities for historical portability
 
 def getint(ui, section, name, default):
     # for "historical portability":
     # ui.configint has been available since 1.9 (or fa2b596db182)
     v = ui.config(section, name, None)
     if v is None:
         return default
     try:
         return int(v)
     except ValueError:
         raise error.ConfigError(("%s.%s is not an integer ('%s')")
                                 % (section, name, v))
 
 def safeattrsetter(obj, name, ignoremissing=False):
     """Ensure that 'obj' has 'name' attribute before subsequent setattr
 
     This function is aborted, if 'obj' doesn't have 'name' attribute
     at runtime. This avoids overlooking removal of an attribute, which
     breaks assumption of performance measurement, in the future.
 
     This function returns the object to (1) assign a new value, and
     (2) restore an original value to the attribute.
 
     If 'ignoremissing' is true, missing 'name' attribute doesn't cause
     abortion, and this function returns None. This is useful to
     examine an attribute, which isn't ensured in all Mercurial
     versions.
     """
     if not util.safehasattr(obj, name):
         if ignoremissing:
             return None
         raise error.Abort(("missing attribute %s of %s might break assumption"
                            " of performance measurement") % (name, obj))
 
     origvalue = getattr(obj, name)
     class attrutil(object):
         def set(self, newvalue):
             setattr(obj, name, newvalue)
         def restore(self):
             setattr(obj, name, origvalue)
 
     return attrutil()
 
 # utilities to examine each internal API changes
 
 def getbranchmapsubsettable():
     # for "historical portability":
     # subsettable is defined in:
     # - branchmap since 2.9 (or 175c6fd8cacc)
     # - repoview since 2.5 (or 59a9f18d4587)
     for mod in (branchmap, repoview):
         subsettable = getattr(mod, 'subsettable', None)
         if subsettable:
             return subsettable
 
     # bisecting in bcee63733aad::59a9f18d4587 can reach here (both
     # branchmap and repoview modules exist, but subsettable attribute
     # doesn't)
     raise error.Abort(("perfbranchmap not available with this Mercurial"),
                       hint="use 2.5 or later")
 
 def getsvfs(repo):
     """Return appropriate object to access files under .hg/store
     """
     # for "historical portability":
     # repo.svfs has been available since 2.3 (or 7034365089bf)
     svfs = getattr(repo, 'svfs', None)
     if svfs:
         return svfs
     else:
         return getattr(repo, 'sopener')
 
 def getvfs(repo):
     """Return appropriate object to access files under .hg
     """
     # for "historical portability":
     # repo.vfs has been available since 2.3 (or 7034365089bf)
     vfs = getattr(repo, 'vfs', None)
     if vfs:
         return vfs
     else:
         return getattr(repo, 'opener')
 
 def repocleartagscachefunc(repo):
     """Return the function to clear tags cache according to repo internal API
     """
     if util.safehasattr(repo, '_tagscache'): # since 2.0 (or 9dca7653b525)
         # in this case, setattr(repo, '_tagscache', None) or so isn't
         # correct way to clear tags cache, because existing code paths
         # expect _tagscache to be a structured object.
         def clearcache():
             # _tagscache has been filteredpropertycache since 2.5 (or
             # 98c867ac1330), and delattr() can't work in such case
             if '_tagscache' in vars(repo):
                 del repo.__dict__['_tagscache']
         return clearcache
 
     repotags = safeattrsetter(repo, '_tags', ignoremissing=True)
     if repotags: # since 1.4 (or 5614a628d173)
         return lambda : repotags.set(None)
 
     repotagscache = safeattrsetter(repo, 'tagscache', ignoremissing=True)
     if repotagscache: # since 0.6 (or d7df759d0e97)
         return lambda : repotagscache.set(None)
 
     # Mercurial earlier than 0.6 (or d7df759d0e97) logically reaches
     # this point, but it isn't so problematic, because:
     # - repo.tags of such Mercurial isn't "callable", and repo.tags()
     #   in perftags() causes failure soon
     # - perf.py itself has been available since 1.1 (or eb240755386d)
     raise error.Abort(("tags API of this hg command is unknown"))
 
 # utilities to clear cache
 
 def clearfilecache(repo, attrname):
     unfi = repo.unfiltered()
     if attrname in vars(unfi):
         delattr(unfi, attrname)
     unfi._filecache.pop(attrname, None)
 
 # perf commands
 
 @command('perfwalk', formatteropts)
 def perfwalk(ui, repo, *pats, **opts):
     timer, fm = gettimer(ui, opts)
     m = scmutil.match(repo[None], pats, {})
-    timer(lambda: len(list(repo.dirstate.walk(m, [], True, False))))
+    timer(lambda: len(list(repo.dirstate.walk(m, subrepos=[], unknown=True,
+                                              ignored=False))))
     fm.end()
 
 @command('perfannotate', formatteropts)
 def perfannotate(ui, repo, f, **opts):
     timer, fm = gettimer(ui, opts)
     fc = repo['.'][f]
     timer(lambda: len(fc.annotate(True)))
     fm.end()
 
 @command('perfstatus',
          [('u', 'unknown', False,
            'ask status to look for unknown files')] + formatteropts)
 def perfstatus(ui, repo, **opts):
     #m = match.always(repo.root, repo.getcwd())
     #timer(lambda: sum(map(len, repo.dirstate.status(m, [], False, False,
     #                                                False))))
     timer, fm = gettimer(ui, opts)
     timer(lambda: sum(map(len, repo.status(unknown=opts['unknown']))))
     fm.end()
 
 @command('perfaddremove', formatteropts)
 def perfaddremove(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     try:
         oldquiet = repo.ui.quiet
         repo.ui.quiet = True
         matcher = scmutil.match(repo[None])
         timer(lambda: scmutil.addremove(repo, matcher, "", dry_run=True))
     finally:
         repo.ui.quiet = oldquiet
         fm.end()
 
 def clearcaches(cl):
     # behave somewhat consistently across internal API changes
     if util.safehasattr(cl, 'clearcaches'):
         cl.clearcaches()
     elif util.safehasattr(cl, '_nodecache'):
         from mercurial.node import nullid, nullrev
         cl._nodecache = {nullid: nullrev}
         cl._nodepos = None
 
 @command('perfheads', formatteropts)
 def perfheads(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.headrevs())
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perftags', formatteropts)
 def perftags(ui, repo, **opts):
     import mercurial.changelog
     import mercurial.manifest
     timer, fm = gettimer(ui, opts)
     svfs = getsvfs(repo)
     repocleartagscache = repocleartagscachefunc(repo)
     def t():
         repo.changelog = mercurial.changelog.changelog(svfs)
         repo.manifestlog = mercurial.manifest.manifestlog(svfs, repo)
         repocleartagscache()
         return len(repo.tags())
     timer(t)
     fm.end()
 
 @command('perfancestors', formatteropts)
 def perfancestors(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     heads = repo.changelog.headrevs()
     def d():
         for a in repo.changelog.ancestors(heads):
             pass
     timer(d)
     fm.end()
 
 @command('perfancestorset', formatteropts)
 def perfancestorset(ui, repo, revset, **opts):
     timer, fm = gettimer(ui, opts)
     revs = repo.revs(revset)
     heads = repo.changelog.headrevs()
     def d():
         s = repo.changelog.ancestors(heads)
         for rev in revs:
             rev in s
     timer(d)
     fm.end()
 
 @command('perfbookmarks', formatteropts)
 def perfbookmarks(ui, repo, **opts):
     """benchmark parsing bookmarks from disk to memory"""
     timer, fm = gettimer(ui, opts)
     def d():
         clearfilecache(repo, '_bookmarks')
         repo._bookmarks
     timer(d)
     fm.end()
 
 @command('perfchangegroupchangelog', formatteropts +
          [('', 'version', '02', 'changegroup version'),
           ('r', 'rev', '', 'revisions to add to changegroup')])
 def perfchangegroupchangelog(ui, repo, version='02', rev=None, **opts):
     """Benchmark producing a changelog group for a changegroup.
 
     This measures the time spent processing the changelog during a
     bundle operation. This occurs during `hg bundle` and on a server
     processing a `getbundle` wire protocol request (handles clones
     and pull requests).
 
     By default, all revisions are added to the changegroup.
     """
     cl = repo.changelog
     revs = [cl.lookup(r) for r in repo.revs(rev or 'all()')]
     bundler = changegroup.getbundler(version, repo)
 
     def lookup(node):
         # The real bundler reads the revision in order to access the
         # manifest node and files list. Do that here.
         cl.read(node)
         return node
 
     def d():
         for chunk in bundler.group(revs, cl, lookup):
             pass
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
 @command('perfdirs', formatteropts)
 def perfdirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate.dirs()
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstate', formatteropts)
 def perfdirstate(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         repo.dirstate.invalidate()
         "a" in repo.dirstate
     timer(d)
     fm.end()
 
 @command('perfdirstatedirs', formatteropts)
 def perfdirstatedirs(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     "a" in repo.dirstate
     def d():
         "a" in repo.dirstate._dirs
         del repo.dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatefoldmap', formatteropts)
 def perfdirstatefoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._filefoldmap.get('a')
         del dirstate._filefoldmap
     timer(d)
     fm.end()
 
 @command('perfdirfoldmap', formatteropts)
 def perfdirfoldmap(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     'a' in dirstate
     def d():
         dirstate._dirfoldmap.get('a')
         del dirstate._dirfoldmap
         del dirstate._dirs
     timer(d)
     fm.end()
 
 @command('perfdirstatewrite', formatteropts)
 def perfdirstatewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     ds = repo.dirstate
     "a" in ds
     def d():
         ds._dirty = True
         ds.write(repo.currenttransaction())
     timer(d)
     fm.end()
 
 @command('perfmergecalculate',
          [('r', 'rev', '.', 'rev to merge against')] + formatteropts)
 def perfmergecalculate(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     wctx = repo[None]
     rctx = scmutil.revsingle(repo, rev, rev)
     ancestor = wctx.ancestor(rctx)
     # we don't want working dir files to be stat'd in the benchmark, so prime
     # that cache
     wctx.dirty()
     def d():
         # acceptremote is True because we don't want prompts in the middle of
         # our benchmark
         merge.calculateupdates(repo, wctx, rctx, [ancestor], False, False,
                                acceptremote=True, followcopies=True)
     timer(d)
     fm.end()
 
 @command('perfpathcopies', [], "REV REV")
 def perfpathcopies(ui, repo, rev1, rev2, **opts):
     timer, fm = gettimer(ui, opts)
     ctx1 = scmutil.revsingle(repo, rev1, rev1)
     ctx2 = scmutil.revsingle(repo, rev2, rev2)
     def d():
         copies.pathcopies(ctx1, ctx2)
     timer(d)
     fm.end()
 
 @command('perfphases',
          [('', 'full', False, 'include file reading time too'),
          ], "")
 def perfphases(ui, repo, **opts):
     """benchmark phasesets computation"""
     timer, fm = gettimer(ui, opts)
     _phases = repo._phasecache
     full = opts.get('full')
     def d():
         phases = _phases
         if full:
             clearfilecache(repo, '_phasecache')
             phases = repo._phasecache
         phases.invalidate()
         phases.loadphaserevs(repo)
     timer(d)
     fm.end()
 
 @command('perfmanifest', [], 'REV')
 def perfmanifest(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     ctx = scmutil.revsingle(repo, rev, rev)
     t = ctx.manifestnode()
     def d():
         repo.manifestlog.clearcaches()
         repo.manifestlog[t].read()
     timer(d)
     fm.end()
 
 @command('perfchangeset', formatteropts)
 def perfchangeset(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     n = repo[rev].node()
     def d():
         repo.changelog.read(n)
         #repo.changelog._cache = None
     timer(d)
     fm.end()
 
 @command('perfindex', formatteropts)
 def perfindex(ui, repo, **opts):
     import mercurial.revlog
     timer, fm = gettimer(ui, opts)
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo["tip"].node()
     svfs = getsvfs(repo)
     def d():
         cl = mercurial.revlog.revlog(svfs, "00changelog.i")
         cl.rev(n)
     timer(d)
     fm.end()
 
 @command('perfstartup', formatteropts)
 def perfstartup(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     cmd = sys.argv[0]
     def d():
         if os.name != 'nt':
             os.system("HGRCPATH= %s version -q > /dev/null" % cmd)
         else:
             os.environ['HGRCPATH'] = ' '
             os.system("%s version -q > NUL" % cmd)
     timer(d)
     fm.end()
 
 @command('perfparents', formatteropts)
 def perfparents(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     # control the number of commits perfparents iterates over
     # experimental config: perf.parentscount
     count = getint(ui, "perf", "parentscount", 1000)
     if len(repo.changelog) < count:
         raise error.Abort("repo needs %d commits for this test" % count)
     repo = repo.unfiltered()
     nl = [repo.changelog.node(i) for i in xrange(count)]
     def d():
         for n in nl:
             repo.changelog.parents(n)
     timer(d)
     fm.end()
 
 @command('perfctxfiles', formatteropts)
 def perfctxfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     def d():
         len(repo[x].files())
     timer(d)
     fm.end()
 
 @command('perfrawfiles', formatteropts)
 def perfrawfiles(ui, repo, x, **opts):
     x = int(x)
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
     def d():
         len(cl.read(x)[3])
     timer(d)
     fm.end()
 
 @command('perflookup', formatteropts)
 def perflookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: len(repo.lookup(rev)))
     fm.end()
 
 @command('perfrevrange', formatteropts)
 def perfrevrange(ui, repo, *specs, **opts):
     timer, fm = gettimer(ui, opts)
     revrange = scmutil.revrange
     timer(lambda: len(revrange(repo, specs)))
     fm.end()
 
 @command('perfnodelookup', formatteropts)
 def perfnodelookup(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     import mercurial.revlog
     mercurial.revlog._prereadsize = 2**24 # disable lazy parser in old hg
     n = repo[rev].node()
     cl = mercurial.revlog.revlog(getsvfs(repo), "00changelog.i")
     def d():
         cl.rev(n)
         clearcaches(cl)
     timer(d)
     fm.end()
 
 @command('perflog',
          [('', 'rename', False, 'ask log to follow renames')] + formatteropts)
 def perflog(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                copies=opts.get('rename')))
     ui.popbuffer()
     fm.end()
 
 @command('perfmoonwalk', formatteropts)
 def perfmoonwalk(ui, repo, **opts):
     """benchmark walking the changelog backwards
 
     This also loads the changelog data for each revision in the changelog.
     """
     timer, fm = gettimer(ui, opts)
     def moonwalk():
         for i in xrange(len(repo), -1, -1):
             ctx = repo[i]
             ctx.branch() # read changelog data (in addition to the index)
     timer(moonwalk)
     fm.end()
 
 @command('perftemplating', formatteropts)
 def perftemplating(ui, repo, rev=None, **opts):
     if rev is None:
         rev=[]
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=rev, date='', user='',
                                template='{date|shortdate} [{rev}:{node|short}]'
                                ' {author|person}: {desc|firstline}\n'))
     ui.popbuffer()
     fm.end()
 
 @command('perfcca', formatteropts)
 def perfcca(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     timer(lambda: scmutil.casecollisionauditor(ui, False, repo.dirstate))
     fm.end()
 
 @command('perffncacheload', formatteropts)
 def perffncacheload(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     def d():
         s.fncache._load()
     timer(d)
     fm.end()
 
 @command('perffncachewrite', formatteropts)
 def perffncachewrite(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     lock = repo.lock()
     tr = repo.transaction('perffncachewrite')
     def d():
         s.fncache._dirty = True
         s.fncache.write(tr)
     timer(d)
     tr.close()
     lock.release()
     fm.end()
 
 @command('perffncacheencode', formatteropts)
 def perffncacheencode(ui, repo, **opts):
     timer, fm = gettimer(ui, opts)
     s = repo.store
     s.fncache._load()
     def d():
         for p in s.fncache.entries:
             s.encode(p)
     timer(d)
     fm.end()
 
 @command('perfbdiff', revlogopts + formatteropts + [
     ('', 'count', 1, 'number of revisions to test (when using --startrev)'),
     ('', 'alldata', False, 'test bdiffs for all associated revisions')],
     '-c|-m|FILE REV')
 def perfbdiff(ui, repo, file_, rev=None, count=None, **opts):
     """benchmark a bdiff between revisions
 
     By default, benchmark a bdiff between its delta parent and itself.
 
     With ``--count``, benchmark bdiffs between delta parents and self for N
     revisions starting at the specified revision.
 
     With ``--alldata``, assume the requested revision is a changeset and
     measure bdiffs for all changes related to that changeset (manifest
     and filelogs).
     """
     if opts['alldata']:
         opts['changelog'] = True
 
     if opts.get('changelog') or opts.get('manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('perfbdiff', 'invalid arguments')
 
     textpairs = []
 
     r = cmdutil.openrevlog(repo, 'perfbdiff', file_, opts)
 
     startrev = r.rev(r.lookup(rev))
     for rev in range(startrev, min(startrev + count, len(r) - 1)):
         if opts['alldata']:
             # Load revisions associated with changeset.
             ctx = repo[rev]
             mtext = repo.manifestlog._revlog.revision(ctx.manifestnode())
             for pctx in ctx.parents():
                 pman = repo.manifestlog._revlog.revision(pctx.manifestnode())
                 textpairs.append((pman, mtext))
 
             # Load filelog revisions by iterating manifest delta.
             man = ctx.manifest()
             pman = ctx.p1().manifest()
             for filename, change in pman.diff(man).items():
                 fctx = repo.file(filename)
                 f1 = fctx.revision(change[0][0] or -1)
                 f2 = fctx.revision(change[1][0] or -1)
                 textpairs.append((f1, f2))
         else:
             dp = r.deltaparent(rev)
             textpairs.append((r.revision(dp), r.revision(rev)))
 
     def d():
         for pair in textpairs:
             mdiff.textdiff(*pair)
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
 @command('perfdiffwd', formatteropts)
 def perfdiffwd(ui, repo, **opts):
     """Profile diff of working directory changes"""
     timer, fm = gettimer(ui, opts)
     options = {
         'w': 'ignore_all_space',
         'b': 'ignore_space_change',
         'B': 'ignore_blank_lines',
         }
 
     for diffopt in ('', 'w', 'b', 'B', 'wB'):
         opts = dict((options[c], '1') for c in diffopt)
         def d():
             ui.pushbuffer()
             commands.diff(ui, repo, **opts)
             ui.popbuffer()
         title = 'diffopts: %s' % (diffopt and ('-' + diffopt) or 'none')
         timer(d, title)
     fm.end()
 
 @command('perfrevlogindex', revlogopts + formatteropts,
          '-c|-m|FILE')
 def perfrevlogindex(ui, repo, file_=None, **opts):
     """Benchmark operations against a revlog index.
 
     This tests constructing a revlog instance, reading index data,
     parsing index data, and performing various operations related to
     index data.
     """
 
     rl = cmdutil.openrevlog(repo, 'perfrevlogindex', file_, opts)
 
     opener = getattr(rl, 'opener')  # trick linter
     indexfile = rl.indexfile
     data = opener.read(indexfile)
 
     header = struct.unpack('>I', data[0:4])[0]
     version = header & 0xFFFF
     if version == 1:
         revlogio = revlog.revlogio()
         inline = header & (1 << 16)
     else:
         raise error.Abort(('unsupported revlog version: %d') % version)
 
     rllen = len(rl)
 
     node0 = rl.node(0)
     node25 = rl.node(rllen // 4)
     node50 = rl.node(rllen // 2)
     node75 = rl.node(rllen // 4 * 3)
     node100 = rl.node(rllen - 1)
 
     allrevs = range(rllen)
     allrevsrev = list(reversed(allrevs))
     allnodes = [rl.node(rev) for rev in range(rllen)]
     allnodesrev = list(reversed(allnodes))
 
     def constructor():
         revlog.revlog(opener, indexfile)
 
     def read():
         with opener(indexfile) as fh:
             fh.read()
 
     def parseindex():
         revlogio.parseindex(data, inline)
 
     def getentry(revornode):
         index = revlogio.parseindex(data, inline)[0]
         index[revornode]
 
     def getentries(revs, count=1):
         index = revlogio.parseindex(data, inline)[0]
 
         for i in range(count):
             for rev in revs:
                 index[rev]
 
     def resolvenode(node):
         nodemap = revlogio.parseindex(data, inline)[1]
         # This only works for the C code.
         if nodemap is None:
             return
 
         try:
             nodemap[node]
         except error.RevlogError:
             pass
 
     def resolvenodes(nodes, count=1):
         nodemap = revlogio.parseindex(data, inline)[1]
         if nodemap is None:
             return
 
         for i in range(count):
             for node in nodes:
                 try:
                     nodemap[node]
                 except error.RevlogError:
                     pass
 
     benches = [
         (constructor, 'revlog constructor'),
         (read, 'read'),
         (parseindex, 'create index object'),
         (lambda: getentry(0), 'retrieve index entry for rev 0'),
         (lambda: resolvenode('a' * 20), 'look up missing node'),
         (lambda: resolvenode(node0), 'look up node at rev 0'),
         (lambda: resolvenode(node25), 'look up node at 1/4 len'),
         (lambda: resolvenode(node50), 'look up node at 1/2 len'),
         (lambda: resolvenode(node75), 'look up node at 3/4 len'),
         (lambda: resolvenode(node100), 'look up node at tip'),
         # 2x variation is to measure caching impact.
         (lambda: resolvenodes(allnodes),
          'look up all nodes (forward)'),
         (lambda: resolvenodes(allnodes, 2),
          'look up all nodes 2x (forward)'),
         (lambda: resolvenodes(allnodesrev),
          'look up all nodes (reverse)'),
         (lambda: resolvenodes(allnodesrev, 2),
          'look up all nodes 2x (reverse)'),
         (lambda: getentries(allrevs),
          'retrieve all index entries (forward)'),
         (lambda: getentries(allrevs, 2),
          'retrieve all index entries 2x (forward)'),
         (lambda: getentries(allrevsrev),
          'retrieve all index entries (reverse)'),
         (lambda: getentries(allrevsrev, 2),
          'retrieve all index entries 2x (reverse)'),
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevlogrevisions', revlogopts + formatteropts +
          [('d', 'dist', 100, 'distance between the revisions'),
           ('s', 'startrev', 0, 'revision to start reading at'),
           ('', 'reverse', False, 'read in reverse')],
          '-c|-m|FILE')
 def perfrevlogrevisions(ui, repo, file_=None, startrev=0, reverse=False,
                         **opts):
     """Benchmark reading a series of revisions from a revlog.
 
     By default, we read every ``-d/--dist`` revision from 0 to tip of
     the specified revlog.
 
     The start revision can be defined via ``-s/--startrev``.
     """
     rl = cmdutil.openrevlog(repo, 'perfrevlogrevisions', file_, opts)
     rllen = getlen(ui)(rl)
 
     def d():
         rl.clearcaches()
 
         beginrev = startrev
         endrev = rllen
         dist = opts['dist']
 
         if reverse:
             beginrev, endrev = endrev, beginrev
             dist = -1 * dist
 
         for x in xrange(beginrev, endrev, dist):
             # Old revisions don't support passing int.
             n = rl.node(x)
             rl.revision(n)
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
 @command('perfrevlogchunks', revlogopts + formatteropts +
          [('e', 'engines', '', 'compression engines to use'),
           ('s', 'startrev', 0, 'revision to start at')],
          '-c|-m|FILE')
 def perfrevlogchunks(ui, repo, file_=None, engines=None, startrev=0, **opts):
     """Benchmark operations on revlog chunks.
 
     Logically, each revlog is a collection of fulltext revisions. However,
     stored within each revlog are "chunks" of possibly compressed data. This
     data needs to be read and decompressed or compressed and written.
 
     This command measures the time it takes to read+decompress and recompress
     chunks in a revlog. It effectively isolates I/O and compression performance.
     For measurements of higher-level operations like resolving revisions,
     see ``perfrevlogrevisions`` and ``perfrevlogrevision``.
     """
     rl = cmdutil.openrevlog(repo, 'perfrevlogchunks', file_, opts)
 
     # _chunkraw was renamed to _getsegmentforrevs.
     try:
         segmentforrevs = rl._getsegmentforrevs
     except AttributeError:
         segmentforrevs = rl._chunkraw
 
     # Verify engines argument.
     if engines:
         engines = set(e.strip() for e in engines.split(','))
         for engine in engines:
             try:
                 util.compressionengines[engine]
             except KeyError:
                 raise error.Abort('unknown compression engine: %s' % engine)
     else:
         engines = []
         for e in util.compengines:
             engine = util.compengines[e]
             try:
                 if engine.available():
                     engine.revlogcompressor().compress('dummy')
                     engines.append(e)
             except NotImplementedError:
                 pass
 
     revs = list(rl.revs(startrev, len(rl) - 1))
 
     def rlfh(rl):
         if rl._inline:
             return getsvfs(repo)(rl.indexfile)
         else:
             return getsvfs(repo)(rl.datafile)
 
     def doread():
         rl.clearcaches()
         for rev in revs:
             segmentforrevs(rev, rev)
 
     def doreadcachedfh():
         rl.clearcaches()
         fh = rlfh(rl)
         for rev in revs:
             segmentforrevs(rev, rev, df=fh)
 
     def doreadbatch():
         rl.clearcaches()
         segmentforrevs(revs[0], revs[-1])
 
     def doreadbatchcachedfh():
         rl.clearcaches()
         fh = rlfh(rl)
         segmentforrevs(revs[0], revs[-1], df=fh)
 
     def dochunk():
         rl.clearcaches()
         fh = rlfh(rl)
         for rev in revs:
             rl._chunk(rev, df=fh)
 
     chunks = [None]
 
     def dochunkbatch():
         rl.clearcaches()
         fh = rlfh(rl)
         # Save chunks as a side-effect.
         chunks[0] = rl._chunks(revs, df=fh)
 
     def docompress(compressor):
         rl.clearcaches()
 
         try:
             # Swap in the requested compression engine.
             oldcompressor = rl._compressor
             rl._compressor = compressor
             for chunk in chunks[0]:
                 rl.compress(chunk)
         finally:
             rl._compressor = oldcompressor
 
     benches = [
         (lambda: doread(), 'read'),
         (lambda: doreadcachedfh(), 'read w/ reused fd'),
         (lambda: doreadbatch(), 'read batch'),
         (lambda: doreadbatchcachedfh(), 'read batch w/ reused fd'),
         (lambda: dochunk(), 'chunk'),
         (lambda: dochunkbatch(), 'chunk batch'),
     ]
 
     for engine in sorted(engines):
         compressor = util.compengines[engine].revlogcompressor()
         benches.append((functools.partial(docompress, compressor),
                         'compress w/ %s' % engine))
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevlogrevision', revlogopts + formatteropts +
          [('', 'cache', False, 'use caches instead of clearing')],
          '-c|-m|FILE REV')
 def perfrevlogrevision(ui, repo, file_, rev=None, cache=None, **opts):
     """Benchmark obtaining a revlog revision.
 
     Obtaining a revlog revision consists of roughly the following steps:
 
     1. Compute the delta chain
     2. Obtain the raw chunks for that delta chain
     3. Decompress each raw chunk
     4. Apply binary patches to obtain fulltext
     5. Verify hash of fulltext
 
     This command measures the time spent in each of these phases.
     """
     if opts.get('changelog') or opts.get('manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError('perfrevlogrevision', 'invalid arguments')
 
     r = cmdutil.openrevlog(repo, 'perfrevlogrevision', file_, opts)
 
     # _chunkraw was renamed to _getsegmentforrevs.
     try:
         segmentforrevs = r._getsegmentforrevs
     except AttributeError:
         segmentforrevs = r._chunkraw
 
     node = r.lookup(rev)
     rev = r.rev(node)
 
     def getrawchunks(data, chain):
         start = r.start
         length = r.length
         inline = r._inline
         iosize = r._io.size
         buffer = util.buffer
         offset = start(chain[0])
 
         chunks = []
         ladd = chunks.append
 
         for rev in chain:
             chunkstart = start(rev)
             if inline:
                 chunkstart += (rev + 1) * iosize
             chunklength = length(rev)
             ladd(buffer(data, chunkstart - offset, chunklength))
 
         return chunks
 
     def dodeltachain(rev):
         if not cache:
             r.clearcaches()
         r._deltachain(rev)
 
     def doread(chain):
         if not cache:
             r.clearcaches()
         segmentforrevs(chain[0], chain[-1])
 
     def dorawchunks(data, chain):
         if not cache:
             r.clearcaches()
         getrawchunks(data, chain)
 
     def dodecompress(chunks):
         decomp = r.decompress
         for chunk in chunks:
             decomp(chunk)
 
     def dopatch(text, bins):
         if not cache:
             r.clearcaches()
         mdiff.patches(text, bins)
 
     def dohash(text):
         if not cache:
             r.clearcaches()
         r.checkhash(text, node, rev=rev)
 
     def dorevision():
         if not cache:
             r.clearcaches()
         r.revision(node)
 
     chain = r._deltachain(rev)[0]
     data = segmentforrevs(chain[0], chain[-1])[1]
     rawchunks = getrawchunks(data, chain)
     bins = r._chunks(chain)
     text = str(bins[0])
     bins = bins[1:]
     text = mdiff.patches(text, bins)
 
     benches = [
         (lambda: dorevision(), 'full'),
         (lambda: dodeltachain(rev), 'deltachain'),
         (lambda: doread(chain), 'read'),
         (lambda: dorawchunks(data, chain), 'rawchunks'),
         (lambda: dodecompress(rawchunks), 'decompress'),
         (lambda: dopatch(text, bins), 'patch'),
         (lambda: dohash(text), 'hash'),
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfrevset',
          [('C', 'clear', False, 'clear volatile cache between each call.'),
           ('', 'contexts', False, 'obtain changectx for each revision')]
          + formatteropts, "REVSET")
 def perfrevset(ui, repo, expr, clear=False, contexts=False, **opts):
     """benchmark the execution time of a revset
 
     Use the --clean option if need to evaluate the impact of build volatile
     revisions set cache on the revset execution. Volatile cache hold filtered
     and obsolete related cache."""
     timer, fm = gettimer(ui, opts)
     def d():
         if clear:
             repo.invalidatevolatilesets()
         if contexts:
             for ctx in repo.set(expr): pass
         else:
             for r in repo.revs(expr): pass
     timer(d)
     fm.end()
 
 @command('perfvolatilesets',
          [('', 'clear-obsstore', False, 'drop obsstore between each call.'),
          ] + formatteropts)
 def perfvolatilesets(ui, repo, *names, **opts):
     """benchmark the computation of various volatile set
 
     Volatile set computes element related to filtering and obsolescence."""
     timer, fm = gettimer(ui, opts)
     repo = repo.unfiltered()
 
     def getobs(name):
         def d():
             repo.invalidatevolatilesets()
             if opts['clear_obsstore']:
                 clearfilecache(repo, 'obsstore')
             obsolete.getrevs(repo, name)
         return d
 
     allobs = sorted(obsolete.cachefuncs)
     if names:
         allobs = [n for n in allobs if n in names]
 
     for name in allobs:
         timer(getobs(name), title=name)
 
     def getfiltered(name):
         def d():
             repo.invalidatevolatilesets()
             if opts['clear_obsstore']:
                 clearfilecache(repo, 'obsstore')
             repoview.filterrevs(repo, name)
         return d
 
     allfilter = sorted(repoview.filtertable)
     if names:
         allfilter = [n for n in allfilter if n in names]
 
     for name in allfilter:
         timer(getfiltered(name), title=name)
     fm.end()
 
 @command('perfbranchmap',
          [('f', 'full', False,
            'Includes build time of subset'),
           ('', 'clear-revbranch', False,
            'purge the revbranch cache between computation'),
          ] + formatteropts)
 def perfbranchmap(ui, repo, full=False, clear_revbranch=False, **opts):
     """benchmark the update of a branchmap
 
     This benchmarks the full repo.branchmap() call with read and write disabled
     """
     timer, fm = gettimer(ui, opts)
     def getbranchmap(filtername):
         """generate a benchmark function for the filtername"""
         if filtername is None:
             view = repo
         else:
             view = repo.filtered(filtername)
         def d():
             if clear_revbranch:
                 repo.revbranchcache()._clear()
             if full:
                 view._branchcaches.clear()
             else:
                 view._branchcaches.pop(filtername, None)
             view.branchmap()
         return d
     # add filter in smaller subset to bigger subset
     possiblefilters = set(repoview.filtertable)
     subsettable = getbranchmapsubsettable()
     allfilters = []
     while possiblefilters:
         for name in possiblefilters:
             subset = subsettable.get(name)
             if subset not in possiblefilters:
                 break
         else:
             assert False, 'subset cycle %s!' % possiblefilters
         allfilters.append(name)
         possiblefilters.remove(name)
 
     # warm the cache
     if not full:
         for name in allfilters:
             repo.filtered(name).branchmap()
     # add unfiltered
     allfilters.append(None)
 
     branchcacheread = safeattrsetter(branchmap, 'read')
     branchcachewrite = safeattrsetter(branchmap.branchcache, 'write')
     branchcacheread.set(lambda repo: None)
     branchcachewrite.set(lambda bc, repo: None)
     try:
         for name in allfilters:
             timer(getbranchmap(name), title=str(name))
     finally:
         branchcacheread.restore()
         branchcachewrite.restore()
     fm.end()
 
 @command('perfloadmarkers')
 def perfloadmarkers(ui, repo):
     """benchmark the time to parse the on-disk markers for a repo
 
     Result is the number of markers in the repo."""
     timer, fm = gettimer(ui)
     svfs = getsvfs(repo)
     timer(lambda: len(obsolete.obsstore(svfs)))
     fm.end()
 
 @command('perflrucachedict', formatteropts +
     [('', 'size', 4, 'size of cache'),
      ('', 'gets', 10000, 'number of key lookups'),
      ('', 'sets', 10000, 'number of key sets'),
      ('', 'mixed', 10000, 'number of mixed mode operations'),
      ('', 'mixedgetfreq', 50, 'frequency of get vs set ops in mixed mode')],
     norepo=True)
 def perflrucache(ui, size=4, gets=10000, sets=10000, mixed=10000,
                  mixedgetfreq=50, **opts):
     def doinit():
         for i in xrange(10000):
             util.lrucachedict(size)
 
     values = []
     for i in xrange(size):
         values.append(random.randint(0, sys.maxint))
 
     # Get mode fills the cache and tests raw lookup performance with no
     # eviction.
     getseq = []
     for i in xrange(gets):
         getseq.append(random.choice(values))
 
     def dogets():
         d = util.lrucachedict(size)
         for v in values:
             d[v] = v
         for key in getseq:
             value = d[key]
             value # silence pyflakes warning
 
     # Set mode tests insertion speed with cache eviction.
     setseq = []
     for i in xrange(sets):
         setseq.append(random.randint(0, sys.maxint))
 
     def dosets():
         d = util.lrucachedict(size)
         for v in setseq:
             d[v] = v
 
     # Mixed mode randomly performs gets and sets with eviction.
     mixedops = []
     for i in xrange(mixed):
         r = random.randint(0, 100)
         if r < mixedgetfreq:
             op = 0
         else:
             op = 1
 
         mixedops.append((op, random.randint(0, size * 2)))
 
     def domixed():
         d = util.lrucachedict(size)
 
         for op, v in mixedops:
             if op == 0:
                 try:
                     d[v]
                 except KeyError:
                     pass
             else:
                 d[v] = v
 
     benches = [
         (doinit, 'init'),
         (dogets, 'gets'),
         (dosets, 'sets'),
         (domixed, 'mixed')
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 @command('perfwrite', formatteropts)
 def perfwrite(ui, repo, **opts):
     """microbenchmark ui.write
     """
     timer, fm = gettimer(ui, opts)
     def write():
         for i in range(100000):
             ui.write(('Testing write performance\n'))
     timer(write)
     fm.end()
 
 def uisetup(ui):
     if (util.safehasattr(cmdutil, 'openrevlog') and
         not util.safehasattr(commands, 'debugrevlogopts')):
         # for "historical portability":
         # In this case, Mercurial should be 1.9 (or a79fea6b3e77) -
         # 3.7 (or 5606f7d0d063). Therefore, '--dir' option for
         # openrevlog() should cause failure, because it has been
         # available since 3.5 (or 49c583ca48c4).
         def openrevlog(orig, repo, cmd, file_, opts):
             if opts.get('dir') and not util.safehasattr(repo, 'dirlog'):
                 raise error.Abort("This version doesn't support --dir option",
                                   hint="use 3.5 or later")
             return orig(repo, cmd, file_, opts)
         extensions.wrapfunction(cmdutil, 'openrevlog', openrevlog)

hgext/largefiles/lfutil.py

@@ -1,670 +1,673 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''largefiles utility code: must not import other modules in this package.'''
 from __future__ import absolute_import
 
 import copy
 import hashlib
 import os
 import platform
 import stat
 
 from mercurial.i18n import _
 
 from mercurial import (
     dirstate,
     encoding,
     error,
     httpconnection,
     match as matchmod,
     node,
     pycompat,
     scmutil,
     sparse,
     util,
     vfs as vfsmod,
 )
 
 shortname = '.hglf'
 shortnameslash = shortname + '/'
 longname = 'largefiles'
 
 # -- Private worker functions ------------------------------------------
 
 def getminsize(ui, assumelfiles, opt, default=10):
     lfsize = opt
     if not lfsize and assumelfiles:
         lfsize = ui.config(longname, 'minsize', default=default)
     if lfsize:
         try:
             lfsize = float(lfsize)
         except ValueError:
             raise error.Abort(_('largefiles: size must be number (not %s)\n')
                              % lfsize)
     if lfsize is None:
         raise error.Abort(_('minimum size for largefiles must be specified'))
     return lfsize
 
 def link(src, dest):
     """Try to create hardlink - if that fails, efficiently make a copy."""
     util.makedirs(os.path.dirname(dest))
     try:
         util.oslink(src, dest)
     except OSError:
         # if hardlinks fail, fallback on atomic copy
         with open(src, 'rb') as srcf, util.atomictempfile(dest) as dstf:
             for chunk in util.filechunkiter(srcf):
                 dstf.write(chunk)
         os.chmod(dest, os.stat(src).st_mode)
 
 def usercachepath(ui, hash):
     '''Return the correct location in the "global" largefiles cache for a file
     with the given hash.
     This cache is used for sharing of largefiles across repositories - both
     to preserve download bandwidth and storage space.'''
     return os.path.join(_usercachedir(ui), hash)
 
 def _usercachedir(ui):
     '''Return the location of the "global" largefiles cache.'''
     path = ui.configpath(longname, 'usercache', None)
     if path:
         return path
     if pycompat.osname == 'nt':
         appdata = encoding.environ.get('LOCALAPPDATA',\
                         encoding.environ.get('APPDATA'))
         if appdata:
             return os.path.join(appdata, longname)
     elif platform.system() == 'Darwin':
         home = encoding.environ.get('HOME')
         if home:
             return os.path.join(home, 'Library', 'Caches', longname)
     elif pycompat.osname == 'posix':
         path = encoding.environ.get('XDG_CACHE_HOME')
         if path:
             return os.path.join(path, longname)
         home = encoding.environ.get('HOME')
         if home:
             return os.path.join(home, '.cache', longname)
     else:
         raise error.Abort(_('unknown operating system: %s\n')
                           % pycompat.osname)
     raise error.Abort(_('unknown %s usercache location') % longname)
 
 def inusercache(ui, hash):
     path = usercachepath(ui, hash)
     return os.path.exists(path)
 
 def findfile(repo, hash):
     '''Return store path of the largefile with the specified hash.
     As a side effect, the file might be linked from user cache.
     Return None if the file can't be found locally.'''
     path, exists = findstorepath(repo, hash)
     if exists:
         repo.ui.note(_('found %s in store\n') % hash)
         return path
     elif inusercache(repo.ui, hash):
         repo.ui.note(_('found %s in system cache\n') % hash)
         path = storepath(repo, hash)
         link(usercachepath(repo.ui, hash), path)
         return path
     return None
 
 class largefilesdirstate(dirstate.dirstate):
     def __getitem__(self, key):
         return super(largefilesdirstate, self).__getitem__(unixpath(key))
     def normal(self, f):
         return super(largefilesdirstate, self).normal(unixpath(f))
     def remove(self, f):
         return super(largefilesdirstate, self).remove(unixpath(f))
     def add(self, f):
         return super(largefilesdirstate, self).add(unixpath(f))
     def drop(self, f):
         return super(largefilesdirstate, self).drop(unixpath(f))
     def forget(self, f):
         return super(largefilesdirstate, self).forget(unixpath(f))
     def normallookup(self, f):
         return super(largefilesdirstate, self).normallookup(unixpath(f))
     def _ignore(self, f):
         return False
     def write(self, tr=False):
         # (1) disable PENDING mode always
         #     (lfdirstate isn't yet managed as a part of the transaction)
         # (2) avoid develwarn 'use dirstate.write with ....'
         super(largefilesdirstate, self).write(None)
 
 def openlfdirstate(ui, repo, create=True):
     '''
     Return a dirstate object that tracks largefiles: i.e. its root is
     the repo root, but it is saved in .hg/largefiles/dirstate.
     '''
     vfs = repo.vfs
     lfstoredir = longname
     opener = vfsmod.vfs(vfs.join(lfstoredir))
     lfdirstate = largefilesdirstate(opener, ui, repo.root,
                                     repo.dirstate._validate,
                                     lambda: sparse.matcher(repo))
 
     # If the largefiles dirstate does not exist, populate and create
     # it. This ensures that we create it on the first meaningful
     # largefiles operation in a new clone.
     if create and not vfs.exists(vfs.join(lfstoredir, 'dirstate')):
         matcher = getstandinmatcher(repo)
-        standins = repo.dirstate.walk(matcher, [], False, False)
+        standins = repo.dirstate.walk(matcher, subrepos=[], unknown=False,
+                                      ignored=False)
 
         if len(standins) > 0:
             vfs.makedirs(lfstoredir)
 
         for standin in standins:
             lfile = splitstandin(standin)
             lfdirstate.normallookup(lfile)
     return lfdirstate
 
 def lfdirstatestatus(lfdirstate, repo):
     pctx = repo['.']
     match = matchmod.always(repo.root, repo.getcwd())
     unsure, s = lfdirstate.status(match, [], False, False, False)
     modified, clean = s.modified, s.clean
     for lfile in unsure:
         try:
             fctx = pctx[standin(lfile)]
         except LookupError:
             fctx = None
         if not fctx or readasstandin(fctx) != hashfile(repo.wjoin(lfile)):
             modified.append(lfile)
         else:
             clean.append(lfile)
             lfdirstate.normal(lfile)
     return s
 
 def listlfiles(repo, rev=None, matcher=None):
     '''return a list of largefiles in the working copy or the
     specified changeset'''
 
     if matcher is None:
         matcher = getstandinmatcher(repo)
 
     # ignore unknown files in working directory
     return [splitstandin(f)
             for f in repo[rev].walk(matcher)
             if rev is not None or repo.dirstate[f] != '?']
 
 def instore(repo, hash, forcelocal=False):
     '''Return true if a largefile with the given hash exists in the store'''
     return os.path.exists(storepath(repo, hash, forcelocal))
 
 def storepath(repo, hash, forcelocal=False):
     '''Return the correct location in the repository largefiles store for a
     file with the given hash.'''
     if not forcelocal and repo.shared():
         return repo.vfs.reljoin(repo.sharedpath, longname, hash)
     return repo.vfs.join(longname, hash)
 
 def findstorepath(repo, hash):
     '''Search through the local store path(s) to find the file for the given
     hash.  If the file is not found, its path in the primary store is returned.
     The return value is a tuple of (path, exists(path)).
     '''
     # For shared repos, the primary store is in the share source.  But for
     # backward compatibility, force a lookup in the local store if it wasn't
     # found in the share source.
     path = storepath(repo, hash, False)
 
     if instore(repo, hash):
         return (path, True)
     elif repo.shared() and instore(repo, hash, True):
         return storepath(repo, hash, True), True
 
     return (path, False)
 
 def copyfromcache(repo, hash, filename):
     '''Copy the specified largefile from the repo or system cache to
     filename in the repository. Return true on success or false if the
     file was not found in either cache (which should not happened:
     this is meant to be called only after ensuring that the needed
     largefile exists in the cache).'''
     wvfs = repo.wvfs
     path = findfile(repo, hash)
     if path is None:
         return False
     wvfs.makedirs(wvfs.dirname(wvfs.join(filename)))
     # The write may fail before the file is fully written, but we
     # don't use atomic writes in the working copy.
     with open(path, 'rb') as srcfd, wvfs(filename, 'wb') as destfd:
         gothash = copyandhash(
             util.filechunkiter(srcfd), destfd)
     if gothash != hash:
         repo.ui.warn(_('%s: data corruption in %s with hash %s\n')
                      % (filename, path, gothash))
         wvfs.unlink(filename)
         return False
     return True
 
 def copytostore(repo, ctx, file, fstandin):
     wvfs = repo.wvfs
     hash = readasstandin(ctx[fstandin])
     if instore(repo, hash):
         return
     if wvfs.exists(file):
         copytostoreabsolute(repo, wvfs.join(file), hash)
     else:
         repo.ui.warn(_("%s: largefile %s not available from local store\n") %
                      (file, hash))
 
 def copyalltostore(repo, node):
     '''Copy all largefiles in a given revision to the store'''
 
     ctx = repo[node]
     for filename in ctx.files():
         realfile = splitstandin(filename)
         if realfile is not None and filename in ctx.manifest():
             copytostore(repo, ctx, realfile, filename)
 
 def copytostoreabsolute(repo, file, hash):
     if inusercache(repo.ui, hash):
         link(usercachepath(repo.ui, hash), storepath(repo, hash))
     else:
         util.makedirs(os.path.dirname(storepath(repo, hash)))
         with open(file, 'rb') as srcf:
             with util.atomictempfile(storepath(repo, hash),
                                      createmode=repo.store.createmode) as dstf:
                 for chunk in util.filechunkiter(srcf):
                     dstf.write(chunk)
         linktousercache(repo, hash)
 
 def linktousercache(repo, hash):
     '''Link / copy the largefile with the specified hash from the store
     to the cache.'''
     path = usercachepath(repo.ui, hash)
     link(storepath(repo, hash), path)
 
 def getstandinmatcher(repo, rmatcher=None):
     '''Return a match object that applies rmatcher to the standin directory'''
     wvfs = repo.wvfs
     standindir = shortname
 
     # no warnings about missing files or directories
     badfn = lambda f, msg: None
 
     if rmatcher and not rmatcher.always():
         pats = [wvfs.join(standindir, pat) for pat in rmatcher.files()]
         if not pats:
             pats = [wvfs.join(standindir)]
         match = scmutil.match(repo[None], pats, badfn=badfn)
     else:
         # no patterns: relative to repo root
         match = scmutil.match(repo[None], [wvfs.join(standindir)], badfn=badfn)
     return match
 
 def composestandinmatcher(repo, rmatcher):
     '''Return a matcher that accepts standins corresponding to the
     files accepted by rmatcher. Pass the list of files in the matcher
     as the paths specified by the user.'''
     smatcher = getstandinmatcher(repo, rmatcher)
     isstandin = smatcher.matchfn
     def composedmatchfn(f):
         return isstandin(f) and rmatcher.matchfn(splitstandin(f))
     smatcher.matchfn = composedmatchfn
 
     return smatcher
 
 def standin(filename):
     '''Return the repo-relative path to the standin for the specified big
     file.'''
     # Notes:
     # 1) Some callers want an absolute path, but for instance addlargefiles
     #    needs it repo-relative so it can be passed to repo[None].add().  So
     #    leave it up to the caller to use repo.wjoin() to get an absolute path.
     # 2) Join with '/' because that's what dirstate always uses, even on
     #    Windows. Change existing separator to '/' first in case we are
     #    passed filenames from an external source (like the command line).
     return shortnameslash + util.pconvert(filename)
 
 def isstandin(filename):
     '''Return true if filename is a big file standin. filename must be
     in Mercurial's internal form (slash-separated).'''
     return filename.startswith(shortnameslash)
 
 def splitstandin(filename):
     # Split on / because that's what dirstate always uses, even on Windows.
     # Change local separator to / first just in case we are passed filenames
     # from an external source (like the command line).
     bits = util.pconvert(filename).split('/', 1)
     if len(bits) == 2 and bits[0] == shortname:
         return bits[1]
     else:
         return None
 
 def updatestandin(repo, lfile, standin):
     """Re-calculate hash value of lfile and write it into standin
 
     This assumes that "lfutil.standin(lfile) == standin", for efficiency.
     """
     file = repo.wjoin(lfile)
     if repo.wvfs.exists(lfile):
         hash = hashfile(file)
         executable = getexecutable(file)
         writestandin(repo, standin, hash, executable)
     else:
         raise error.Abort(_('%s: file not found!') % lfile)
 
 def readasstandin(fctx):
     '''read hex hash from given filectx of standin file
 
     This encapsulates how "standin" data is stored into storage layer.'''
     return fctx.data().strip()
 
 def writestandin(repo, standin, hash, executable):
     '''write hash to <repo.root>/<standin>'''
     repo.wwrite(standin, hash + '\n', executable and 'x' or '')
 
 def copyandhash(instream, outfile):
     '''Read bytes from instream (iterable) and write them to outfile,
     computing the SHA-1 hash of the data along the way. Return the hash.'''
     hasher = hashlib.sha1('')
     for data in instream:
         hasher.update(data)
         outfile.write(data)
     return hasher.hexdigest()
 
 def hashfile(file):
     if not os.path.exists(file):
         return ''
     with open(file, 'rb') as fd:
         return hexsha1(fd)
 
 def getexecutable(filename):
     mode = os.stat(filename).st_mode
     return ((mode & stat.S_IXUSR) and
             (mode & stat.S_IXGRP) and
             (mode & stat.S_IXOTH))
 
 def urljoin(first, second, *arg):
     def join(left, right):
         if not left.endswith('/'):
             left += '/'
         if right.startswith('/'):
             right = right[1:]
         return left + right
 
     url = join(first, second)
     for a in arg:
         url = join(url, a)
     return url
 
 def hexsha1(fileobj):
     """hexsha1 returns the hex-encoded sha1 sum of the data in the file-like
     object data"""
     h = hashlib.sha1()
     for chunk in util.filechunkiter(fileobj):
         h.update(chunk)
     return h.hexdigest()
 
 def httpsendfile(ui, filename):
     return httpconnection.httpsendfile(ui, filename, 'rb')
 
 def unixpath(path):
     '''Return a version of path normalized for use with the lfdirstate.'''
     return util.pconvert(os.path.normpath(path))
 
 def islfilesrepo(repo):
     '''Return true if the repo is a largefile repo.'''
     if ('largefiles' in repo.requirements and
             any(shortnameslash in f[0] for f in repo.store.datafiles())):
         return True
 
     return any(openlfdirstate(repo.ui, repo, False))
 
 class storeprotonotcapable(Exception):
     def __init__(self, storetypes):
         self.storetypes = storetypes
 
 def getstandinsstate(repo):
     standins = []
     matcher = getstandinmatcher(repo)
     wctx = repo[None]
-    for standin in repo.dirstate.walk(matcher, [], False, False):
+    for standin in repo.dirstate.walk(matcher, subrepos=[], unknown=False,
+                                      ignored=False):
         lfile = splitstandin(standin)
         try:
             hash = readasstandin(wctx[standin])
         except IOError:
             hash = None
         standins.append((lfile, hash))
     return standins
 
 def synclfdirstate(repo, lfdirstate, lfile, normallookup):
     lfstandin = standin(lfile)
     if lfstandin in repo.dirstate:
         stat = repo.dirstate._map[lfstandin]
         state, mtime = stat[0], stat[3]
     else:
         state, mtime = '?', -1
     if state == 'n':
         if (normallookup or mtime < 0 or
             not repo.wvfs.exists(lfile)):
             # state 'n' doesn't ensure 'clean' in this case
             lfdirstate.normallookup(lfile)
         else:
             lfdirstate.normal(lfile)
     elif state == 'm':
         lfdirstate.normallookup(lfile)
     elif state == 'r':
         lfdirstate.remove(lfile)
     elif state == 'a':
         lfdirstate.add(lfile)
     elif state == '?':
         lfdirstate.drop(lfile)
 
 def markcommitted(orig, ctx, node):
     repo = ctx.repo()
 
     orig(node)
 
     # ATTENTION: "ctx.files()" may differ from "repo[node].files()"
     # because files coming from the 2nd parent are omitted in the latter.
     #
     # The former should be used to get targets of "synclfdirstate",
     # because such files:
     # - are marked as "a" by "patch.patch()" (e.g. via transplant), and
     # - have to be marked as "n" after commit, but
     # - aren't listed in "repo[node].files()"
 
     lfdirstate = openlfdirstate(repo.ui, repo)
     for f in ctx.files():
         lfile = splitstandin(f)
         if lfile is not None:
             synclfdirstate(repo, lfdirstate, lfile, False)
     lfdirstate.write()
 
     # As part of committing, copy all of the largefiles into the cache.
     #
     # Using "node" instead of "ctx" implies additional "repo[node]"
     # lookup while copyalltostore(), but can omit redundant check for
     # files comming from the 2nd parent, which should exist in store
     # at merging.
     copyalltostore(repo, node)
 
 def getlfilestoupdate(oldstandins, newstandins):
     changedstandins = set(oldstandins).symmetric_difference(set(newstandins))
     filelist = []
     for f in changedstandins:
         if f[0] not in filelist:
             filelist.append(f[0])
     return filelist
 
 def getlfilestoupload(repo, missing, addfunc):
     for i, n in enumerate(missing):
         repo.ui.progress(_('finding outgoing largefiles'), i,
             unit=_('revisions'), total=len(missing))
         parents = [p for p in repo[n].parents() if p != node.nullid]
 
         oldlfstatus = repo.lfstatus
         repo.lfstatus = False
         try:
             ctx = repo[n]
         finally:
             repo.lfstatus = oldlfstatus
 
         files = set(ctx.files())
         if len(parents) == 2:
             mc = ctx.manifest()
             mp1 = ctx.parents()[0].manifest()
             mp2 = ctx.parents()[1].manifest()
             for f in mp1:
                 if f not in mc:
                     files.add(f)
             for f in mp2:
                 if f not in mc:
                     files.add(f)
             for f in mc:
                 if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                     files.add(f)
         for fn in files:
             if isstandin(fn) and fn in ctx:
                 addfunc(fn, readasstandin(ctx[fn]))
     repo.ui.progress(_('finding outgoing largefiles'), None)
 
 def updatestandinsbymatch(repo, match):
     '''Update standins in the working directory according to specified match
 
     This returns (possibly modified) ``match`` object to be used for
     subsequent commit process.
     '''
 
     ui = repo.ui
 
     # Case 1: user calls commit with no specific files or
     # include/exclude patterns: refresh and commit all files that
     # are "dirty".
     if match is None or match.always():
         # Spend a bit of time here to get a list of files we know
         # are modified so we can compare only against those.
         # It can cost a lot of time (several seconds)
         # otherwise to update all standins if the largefiles are
         # large.
         lfdirstate = openlfdirstate(ui, repo)
         dirtymatch = matchmod.always(repo.root, repo.getcwd())
         unsure, s = lfdirstate.status(dirtymatch, [], False, False,
                                       False)
         modifiedfiles = unsure + s.modified + s.added + s.removed
         lfiles = listlfiles(repo)
         # this only loops through largefiles that exist (not
         # removed/renamed)
         for lfile in lfiles:
             if lfile in modifiedfiles:
                 fstandin = standin(lfile)
                 if repo.wvfs.exists(fstandin):
                     # this handles the case where a rebase is being
                     # performed and the working copy is not updated
                     # yet.
                     if repo.wvfs.exists(lfile):
                         updatestandin(repo, lfile, fstandin)
 
         return match
 
     lfiles = listlfiles(repo)
     match._files = repo._subdirlfs(match.files(), lfiles)
 
     # Case 2: user calls commit with specified patterns: refresh
     # any matching big files.
     smatcher = composestandinmatcher(repo, match)
-    standins = repo.dirstate.walk(smatcher, [], False, False)
+    standins = repo.dirstate.walk(smatcher, subrepos=[], unknown=False,
+                                  ignored=False)
 
     # No matching big files: get out of the way and pass control to
     # the usual commit() method.
     if not standins:
         return match
 
     # Refresh all matching big files.  It's possible that the
     # commit will end up failing, in which case the big files will
     # stay refreshed.  No harm done: the user modified them and
     # asked to commit them, so sooner or later we're going to
     # refresh the standins.  Might as well leave them refreshed.
     lfdirstate = openlfdirstate(ui, repo)
     for fstandin in standins:
         lfile = splitstandin(fstandin)
         if lfdirstate[lfile] != 'r':
             updatestandin(repo, lfile, fstandin)
 
     # Cook up a new matcher that only matches regular files or
     # standins corresponding to the big files requested by the
     # user.  Have to modify _files to prevent commit() from
     # complaining "not tracked" for big files.
     match = copy.copy(match)
     origmatchfn = match.matchfn
 
     # Check both the list of largefiles and the list of
     # standins because if a largefile was removed, it
     # won't be in the list of largefiles at this point
     match._files += sorted(standins)
 
     actualfiles = []
     for f in match._files:
         fstandin = standin(f)
 
         # For largefiles, only one of the normal and standin should be
         # committed (except if one of them is a remove).  In the case of a
         # standin removal, drop the normal file if it is unknown to dirstate.
         # Thus, skip plain largefile names but keep the standin.
         if f in lfiles or fstandin in standins:
             if repo.dirstate[fstandin] != 'r':
                 if repo.dirstate[f] != 'r':
                     continue
             elif repo.dirstate[f] == '?':
                 continue
 
         actualfiles.append(f)
     match._files = actualfiles
 
     def matchfn(f):
         if origmatchfn(f):
             return f not in lfiles
         else:
             return f in standins
 
     match.matchfn = matchfn
 
     return match
 
 class automatedcommithook(object):
     '''Stateful hook to update standins at the 1st commit of resuming
 
     For efficiency, updating standins in the working directory should
     be avoided while automated committing (like rebase, transplant and
     so on), because they should be updated before committing.
 
     But the 1st commit of resuming automated committing (e.g. ``rebase
     --continue``) should update them, because largefiles may be
     modified manually.
     '''
     def __init__(self, resuming):
         self.resuming = resuming
 
     def __call__(self, repo, match):
         if self.resuming:
             self.resuming = False # avoids updating at subsequent commits
             return updatestandinsbymatch(repo, match)
         else:
             return match
 
 def getstatuswriter(ui, repo, forcibly=None):
     '''Return the function to write largefiles specific status out
 
     If ``forcibly`` is ``None``, this returns the last element of
     ``repo._lfstatuswriters`` as "default" writer function.
 
     Otherwise, this returns the function to always write out (or
     ignore if ``not forcibly``) status.
     '''
     if forcibly is None and util.safehasattr(repo, '_largefilesenabled'):
         return repo._lfstatuswriters[-1]
     else:
         if forcibly:
             return ui.status # forcibly WRITE OUT
         else:
             return lambda *msg, **opts: None # forcibly IGNORE

mercurial/cmdutil.py

@@ -1,3882 +1,3882 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import itertools
 import os
 import re
 import tempfile
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     nullrev,
     short,
 )
 
 from . import (
     bookmarks,
     changelog,
     copies,
     crecord as crecordmod,
     dirstateguard,
     encoding,
     error,
     formatter,
     graphmod,
     match as matchmod,
     obsolete,
     patch,
     pathutil,
     pycompat,
     registrar,
     revlog,
     revset,
     scmutil,
     smartset,
     templatekw,
     templater,
     util,
     vfs as vfsmod,
 )
 stringio = util.stringio
 
 # templates of common command options
 
 dryrunopts = [
     ('n', 'dry-run', None,
      _('do not perform actions, just print output')),
 ]
 
 remoteopts = [
     ('e', 'ssh', '',
      _('specify ssh command to use'), _('CMD')),
     ('', 'remotecmd', '',
      _('specify hg command to run on the remote side'), _('CMD')),
     ('', 'insecure', None,
      _('do not verify server certificate (ignoring web.cacerts config)')),
 ]
 
 walkopts = [
     ('I', 'include', [],
      _('include names matching the given patterns'), _('PATTERN')),
     ('X', 'exclude', [],
      _('exclude names matching the given patterns'), _('PATTERN')),
 ]
 
 commitopts = [
     ('m', 'message', '',
      _('use text as commit message'), _('TEXT')),
     ('l', 'logfile', '',
      _('read commit message from file'), _('FILE')),
 ]
 
 commitopts2 = [
     ('d', 'date', '',
      _('record the specified date as commit date'), _('DATE')),
     ('u', 'user', '',
      _('record the specified user as committer'), _('USER')),
 ]
 
 # hidden for now
 formatteropts = [
     ('T', 'template', '',
      _('display with template (EXPERIMENTAL)'), _('TEMPLATE')),
 ]
 
 templateopts = [
     ('', 'style', '',
      _('display using template map file (DEPRECATED)'), _('STYLE')),
     ('T', 'template', '',
      _('display with template'), _('TEMPLATE')),
 ]
 
 logopts = [
     ('p', 'patch', None, _('show patch')),
     ('g', 'git', None, _('use git extended diff format')),
     ('l', 'limit', '',
      _('limit number of changes displayed'), _('NUM')),
     ('M', 'no-merges', None, _('do not show merges')),
     ('', 'stat', None, _('output diffstat-style summary of changes')),
     ('G', 'graph', None, _("show the revision DAG")),
 ] + templateopts
 
 diffopts = [
     ('a', 'text', None, _('treat all files as text')),
     ('g', 'git', None, _('use git extended diff format')),
     ('', 'binary', None, _('generate binary diffs in git mode (default)')),
     ('', 'nodates', None, _('omit dates from diff headers'))
 ]
 
 diffwsopts = [
     ('w', 'ignore-all-space', None,
      _('ignore white space when comparing lines')),
     ('b', 'ignore-space-change', None,
      _('ignore changes in the amount of white space')),
     ('B', 'ignore-blank-lines', None,
      _('ignore changes whose lines are all blank')),
     ('Z', 'ignore-space-at-eol', None,
      _('ignore changes in whitespace at EOL')),
 ]
 
 diffopts2 = [
     ('', 'noprefix', None, _('omit a/ and b/ prefixes from filenames')),
     ('p', 'show-function', None, _('show which function each change is in')),
     ('', 'reverse', None, _('produce a diff that undoes the changes')),
 ] + diffwsopts + [
     ('U', 'unified', '',
      _('number of lines of context to show'), _('NUM')),
     ('', 'stat', None, _('output diffstat-style summary of changes')),
     ('', 'root', '', _('produce diffs relative to subdirectory'), _('DIR')),
 ]
 
 mergetoolopts = [
     ('t', 'tool', '', _('specify merge tool')),
 ]
 
 similarityopts = [
     ('s', 'similarity', '',
      _('guess renamed files by similarity (0<=s<=100)'), _('SIMILARITY'))
 ]
 
 subrepoopts = [
     ('S', 'subrepos', None,
      _('recurse into subrepositories'))
 ]
 
 debugrevlogopts = [
     ('c', 'changelog', False, _('open changelog')),
     ('m', 'manifest', False, _('open manifest')),
     ('', 'dir', '', _('open directory manifest')),
 ]
 
 # special string such that everything below this line will be ingored in the
 # editor text
 _linebelow = "^HG: ------------------------ >8 ------------------------$"
 
 def ishunk(x):
     hunkclasses = (crecordmod.uihunk, patch.recordhunk)
     return isinstance(x, hunkclasses)
 
 def newandmodified(chunks, originalchunks):
     newlyaddedandmodifiedfiles = set()
     for chunk in chunks:
         if ishunk(chunk) and chunk.header.isnewfile() and chunk not in \
             originalchunks:
             newlyaddedandmodifiedfiles.add(chunk.header.filename())
     return newlyaddedandmodifiedfiles
 
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 def setupwrapcolorwrite(ui):
     # wrap ui.write so diff output can be labeled/colorized
     def wrapwrite(orig, *args, **kw):
         label = kw.pop('label', '')
         for chunk, l in patch.difflabel(lambda: args):
             orig(chunk, label=label + l)
 
     oldwrite = ui.write
     def wrap(*args, **kwargs):
         return wrapwrite(oldwrite, *args, **kwargs)
     setattr(ui, 'write', wrap)
     return oldwrite
 
 def filterchunks(ui, originalhunks, usecurses, testfile, operation=None):
     if usecurses:
         if testfile:
             recordfn = crecordmod.testdecorator(testfile,
                                                 crecordmod.testchunkselector)
         else:
             recordfn = crecordmod.chunkselector
 
         return crecordmod.filterpatch(ui, originalhunks, recordfn, operation)
 
     else:
         return patch.filterpatch(ui, originalhunks, operation)
 
 def recordfilter(ui, originalhunks, operation=None):
     """ Prompts the user to filter the originalhunks and return a list of
     selected hunks.
     *operation* is used for to build ui messages to indicate the user what
     kind of filtering they are doing: reverting, committing, shelving, etc.
     (see patch.filterpatch).
     """
     usecurses = crecordmod.checkcurses(ui)
     testfile = ui.config('experimental', 'crecordtest')
     oldwrite = setupwrapcolorwrite(ui)
     try:
         newchunks, newopts = filterchunks(ui, originalhunks, usecurses,
                                           testfile, operation)
     finally:
         ui.write = oldwrite
     return newchunks, newopts
 
 def dorecord(ui, repo, commitfunc, cmdsuggest, backupall,
             filterfn, *pats, **opts):
     from . import merge as mergemod
     opts = pycompat.byteskwargs(opts)
     if not ui.interactive():
         if cmdsuggest:
             msg = _('running non-interactively, use %s instead') % cmdsuggest
         else:
             msg = _('running non-interactively')
         raise error.Abort(msg)
 
     # make sure username is set before going interactive
     if not opts.get('user'):
         ui.username() # raise exception, username not provided
 
     def recordfunc(ui, repo, message, match, opts):
         """This is generic record driver.
 
         Its job is to interactively filter local changes, and
         accordingly prepare working directory into a state in which the
         job can be delegated to a non-interactive commit command such as
         'commit' or 'qrefresh'.
 
         After the actual job is done by non-interactive command, the
         working directory is restored to its original state.
 
         In the end we'll record interesting changes, and everything else
         will be left in place, so the user can continue working.
         """
 
         checkunfinished(repo, commit=True)
         wctx = repo[None]
         merge = len(wctx.parents()) > 1
         if merge:
             raise error.Abort(_('cannot partially commit a merge '
                                '(use "hg commit" instead)'))
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         force = opts.get('force')
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         status = repo.status(match=match)
         if not force:
             repo.checkcommitpatterns(wctx, vdirs, match, status, fail)
         diffopts = patch.difffeatureopts(ui, opts=opts, whitespace=True)
         diffopts.nodates = True
         diffopts.git = True
         diffopts.showfunc = True
         originaldiff = patch.diff(repo, changes=status, opts=diffopts)
         originalchunks = patch.parsepatch(originaldiff)
 
         # 1. filter patch, since we are intending to apply subset of it
         try:
             chunks, newopts = filterfn(ui, originalchunks)
         except error.PatchError as err:
             raise error.Abort(_('error parsing patch: %s') % err)
         opts.update(newopts)
 
         # We need to keep a backup of files that have been newly added and
         # modified during the recording process because there is a previous
         # version without the edit in the workdir
         newlyaddedandmodifiedfiles = newandmodified(chunks, originalchunks)
         contenders = set()
         for h in chunks:
             try:
                 contenders.update(set(h.files()))
             except AttributeError:
                 pass
 
         changed = status.modified + status.added + status.removed
         newfiles = [f for f in changed if f in contenders]
         if not newfiles:
             ui.status(_('no changes to record\n'))
             return 0
 
         modified = set(status.modified)
 
         # 2. backup changed files, so we can restore them in the end
 
         if backupall:
             tobackup = changed
         else:
             tobackup = [f for f in newfiles if f in modified or f in \
                     newlyaddedandmodifiedfiles]
         backups = {}
         if tobackup:
             backupdir = repo.vfs.join('record-backups')
             try:
                 os.mkdir(backupdir)
             except OSError as err:
                 if err.errno != errno.EEXIST:
                     raise
         try:
             # backup continues
             for f in tobackup:
                 fd, tmpname = tempfile.mkstemp(prefix=f.replace('/', '_')+'.',
                                                dir=backupdir)
                 os.close(fd)
                 ui.debug('backup %r as %r\n' % (f, tmpname))
                 util.copyfile(repo.wjoin(f), tmpname, copystat=True)
                 backups[f] = tmpname
 
             fp = stringio()
             for c in chunks:
                 fname = c.filename()
                 if fname in backups:
                     c.write(fp)
             dopatch = fp.tell()
             fp.seek(0)
 
             # 2.5 optionally review / modify patch in text editor
             if opts.get('review', False):
                 patchtext = (crecordmod.diffhelptext
                              + crecordmod.patchhelptext
                              + fp.read())
                 reviewedpatch = ui.edit(patchtext, "",
                                         action="diff",
                                         repopath=repo.path)
                 fp.truncate(0)
                 fp.write(reviewedpatch)
                 fp.seek(0)
 
             [os.unlink(repo.wjoin(c)) for c in newlyaddedandmodifiedfiles]
             # 3a. apply filtered patch to clean repo  (clean)
             if backups:
                 # Equivalent to hg.revert
                 m = scmutil.matchfiles(repo, backups.keys())
                 mergemod.update(repo, repo.dirstate.p1(),
                         False, True, matcher=m)
 
             # 3b. (apply)
             if dopatch:
                 try:
                     ui.debug('applying patch\n')
                     ui.debug(fp.getvalue())
                     patch.internalpatch(ui, repo, fp, 1, eolmode=None)
                 except error.PatchError as err:
                     raise error.Abort(str(err))
             del fp
 
             # 4. We prepared working directory according to filtered
             #    patch. Now is the time to delegate the job to
             #    commit/qrefresh or the like!
 
             # Make all of the pathnames absolute.
             newfiles = [repo.wjoin(nf) for nf in newfiles]
             return commitfunc(ui, repo, *newfiles, **opts)
         finally:
             # 5. finally restore backed-up files
             try:
                 dirstate = repo.dirstate
                 for realname, tmpname in backups.iteritems():
                     ui.debug('restoring %r to %r\n' % (tmpname, realname))
 
                     if dirstate[realname] == 'n':
                         # without normallookup, restoring timestamp
                         # may cause partially committed files
                         # to be treated as unmodified
                         dirstate.normallookup(realname)
 
                     # copystat=True here and above are a hack to trick any
                     # editors that have f open that we haven't modified them.
                     #
                     # Also note that this racy as an editor could notice the
                     # file's mtime before we've finished writing it.
                     util.copyfile(tmpname, repo.wjoin(realname), copystat=True)
                     os.unlink(tmpname)
                 if tobackup:
                     os.rmdir(backupdir)
             except OSError:
                 pass
 
     def recordinwlock(ui, repo, message, match, opts):
         with repo.wlock():
             return recordfunc(ui, repo, message, match, opts)
 
     return commit(ui, repo, recordinwlock, pats, opts)
 
 def tersestatus(root, statlist, status, ignorefn, ignore):
     """
     Returns a list of statuses with directory collapsed if all the files in the
     directory has the same status.
     """
 
     def numfiles(dirname):
         """
         Calculates the number of tracked files in a given directory which also
         includes files which were removed or deleted. Considers ignored files
         if ignore argument is True or 'i' is present in status argument.
         """
         if lencache.get(dirname):
             return lencache[dirname]
         if 'i' in status or ignore:
             def match(localpath):
                 absolutepath = os.path.join(root, localpath)
                 if os.path.isdir(absolutepath) and isemptydir(absolutepath):
                     return True
                 return False
         else:
             def match(localpath):
                 # there can be directory whose all the files are ignored and
                 # hence the drectory should also be ignored while counting
                 # number of files or subdirs in it's parent directory. This
                 # checks the same.
                 # XXX: We need a better logic here.
                 if os.path.isdir(os.path.join(root, localpath)):
                     return isignoreddir(localpath)
                 else:
                     # XXX: there can be files which have the ignored pattern but
                     # are not ignored. That leads to bug in counting number of
                     # tracked files in the directory.
                     return ignorefn(localpath)
         lendir = 0
         abspath = os.path.join(root, dirname)
         # There might be cases when a directory does not exists as the whole
         # directory can be removed and/or deleted.
         try:
             for f in os.listdir(abspath):
                 localpath = os.path.join(dirname, f)
                 if not match(localpath):
                     lendir += 1
         except OSError:
             pass
         lendir += len(absentdir.get(dirname, []))
         lencache[dirname] = lendir
         return lendir
 
     def isemptydir(abspath):
         """
         Check whether a directory is empty or not, i.e. there is no files in the
         directory and all its subdirectories.
         """
         for f in os.listdir(abspath):
             fullpath = os.path.join(abspath, f)
             if os.path.isdir(fullpath):
                 # recursion here
                 ret = isemptydir(fullpath)
                 if not ret:
                     return False
             else:
                 return False
         return True
 
     def isignoreddir(localpath):
         """Return True if `localpath` directory is ignored or contains only
         ignored files and should hence be considered ignored.
         """
         dirpath = os.path.join(root, localpath)
         if ignorefn(dirpath):
             return True
         for f in os.listdir(dirpath):
             filepath = os.path.join(dirpath, f)
             if os.path.isdir(filepath):
                 # recursion here
                 ret = isignoreddir(os.path.join(localpath, f))
                 if not ret:
                     return False
             else:
                 if not ignorefn(os.path.join(localpath, f)):
                     return False
         return True
 
     def absentones(removedfiles, missingfiles):
         """
         Returns a dictionary of directories with files in it which are either
         removed or missing (deleted) in them.
         """
         absentdir = {}
         absentfiles = removedfiles + missingfiles
         while absentfiles:
             f = absentfiles.pop()
             par = os.path.dirname(f)
             if par == '':
                 continue
             # we need to store files rather than number of files as some files
             # or subdirectories in a directory can be counted twice. This is
             # also we have used sets here.
             try:
                 absentdir[par].add(f)
             except KeyError:
                 absentdir[par] = set([f])
             absentfiles.append(par)
         return absentdir
 
     indexes = {'m': 0, 'a': 1, 'r': 2, 'd': 3, 'u': 4, 'i': 5, 'c': 6}
     # get a dictonary of directories and files which are missing as os.listdir()
     # won't be able to list them.
     absentdir = absentones(statlist[2], statlist[3])
     finalrs = [[]] * len(indexes)
     didsomethingchanged = False
     # dictionary to store number of files and subdir in a directory so that we
     # don't compute that again.
     lencache = {}
 
     for st in pycompat.bytestr(status):
 
         try:
             ind = indexes[st]
         except KeyError:
             # TODO: Need a better error message here
             raise error.Abort("'%s' not recognized" % st)
 
         sfiles = statlist[ind]
         if not sfiles:
             continue
         pardict = {}
         for a in sfiles:
             par = os.path.dirname(a)
             pardict.setdefault(par, []).append(a)
 
         rs = []
         newls = []
         for par, files in sorted(pardict.iteritems()):
             lenpar = numfiles(par)
             if lenpar == len(files):
                 newls.append(par)
 
         if not newls:
             continue
 
         while newls:
             newel = newls.pop()
             if newel == '':
                 continue
             parn = os.path.dirname(newel)
             pardict[newel] = []
             # Adding pycompat.ossep as newel is a directory.
             pardict.setdefault(parn, []).append(newel + pycompat.ossep)
             lenpar = numfiles(parn)
             if lenpar == len(pardict[parn]):
                 newls.append(parn)
 
         # dict.values() for Py3 compatibility
         for files in pardict.values():
             rs.extend(files)
 
         rs.sort()
         finalrs[ind] = rs
         didsomethingchanged = True
 
     # If nothing is changed, make sure the order of files is preserved.
     if not didsomethingchanged:
         return statlist
 
     for x in xrange(len(indexes)):
         if not finalrs[x]:
             finalrs[x] = statlist[x]
 
     return finalrs
 
 def _commentlines(raw):
     '''Surround lineswith a comment char and a new line'''
     lines = raw.splitlines()
     commentedlines = ['# %s' % line for line in lines]
     return '\n'.join(commentedlines) + '\n'
 
 def _conflictsmsg(repo):
     # avoid merge cycle
     from . import merge as mergemod
     mergestate = mergemod.mergestate.read(repo)
     if not mergestate.active():
         return
 
     m = scmutil.match(repo[None])
     unresolvedlist = [f for f in mergestate.unresolved() if m(f)]
     if unresolvedlist:
         mergeliststr = '\n'.join(
             ['    %s' % os.path.relpath(
                 os.path.join(repo.root, path),
                 pycompat.getcwd()) for path in unresolvedlist])
         msg = _('''Unresolved merge conflicts:
 
 %s
 
 To mark files as resolved:  hg resolve --mark FILE''') % mergeliststr
     else:
         msg = _('No unresolved merge conflicts.')
 
     return _commentlines(msg)
 
 def _helpmessage(continuecmd, abortcmd):
     msg = _('To continue:                %s\n'
             'To abort:                   %s') % (continuecmd, abortcmd)
     return _commentlines(msg)
 
 def _rebasemsg():
     return _helpmessage('hg rebase --continue', 'hg rebase --abort')
 
 def _histeditmsg():
     return _helpmessage('hg histedit --continue', 'hg histedit --abort')
 
 def _unshelvemsg():
     return _helpmessage('hg unshelve --continue', 'hg unshelve --abort')
 
 def _updatecleanmsg(dest=None):
     warning = _('warning: this will discard uncommitted changes')
     return 'hg update --clean %s    (%s)' % (dest or '.', warning)
 
 def _graftmsg():
     # tweakdefaults requires `update` to have a rev hence the `.`
     return _helpmessage('hg graft --continue', _updatecleanmsg())
 
 def _mergemsg():
     # tweakdefaults requires `update` to have a rev hence the `.`
      return _helpmessage('hg commit', _updatecleanmsg())
 
 def _bisectmsg():
     msg = _('To mark the changeset good:    hg bisect --good\n'
             'To mark the changeset bad:     hg bisect --bad\n'
             'To abort:                      hg bisect --reset\n')
     return _commentlines(msg)
 
 def fileexistspredicate(filename):
     return lambda repo: repo.vfs.exists(filename)
 
 def _mergepredicate(repo):
     return len(repo[None].parents()) > 1
 
 STATES = (
     # (state, predicate to detect states, helpful message function)
     ('histedit', fileexistspredicate('histedit-state'), _histeditmsg),
     ('bisect', fileexistspredicate('bisect.state'), _bisectmsg),
     ('graft', fileexistspredicate('graftstate'), _graftmsg),
     ('unshelve', fileexistspredicate('unshelverebasestate'), _unshelvemsg),
     ('rebase', fileexistspredicate('rebasestate'), _rebasemsg),
     # The merge state is part of a list that will be iterated over.
     # They need to be last because some of the other unfinished states may also
     # be in a merge or update state (eg. rebase, histedit, graft, etc).
     # We want those to have priority.
     ('merge', _mergepredicate, _mergemsg),
 )
 
 def _getrepostate(repo):
     # experimental config: commands.status.skipstates
     skip = set(repo.ui.configlist('commands', 'status.skipstates'))
     for state, statedetectionpredicate, msgfn in STATES:
         if state in skip:
             continue
         if statedetectionpredicate(repo):
             return (state, statedetectionpredicate, msgfn)
 
 def morestatus(repo, fm):
     statetuple = _getrepostate(repo)
     label = 'status.morestatus'
     if statetuple:
         fm.startitem()
         state, statedetectionpredicate, helpfulmsg = statetuple
         statemsg = _('The repository is in an unfinished *%s* state.') % state
         fm.write('statemsg', '%s\n',  _commentlines(statemsg), label=label)
         conmsg = _conflictsmsg(repo)
         if conmsg:
             fm.write('conflictsmsg', '%s\n', conmsg, label=label)
         if helpfulmsg:
             helpmsg = helpfulmsg()
             fm.write('helpmsg', '%s\n', helpmsg, label=label)
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "^log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     allcmds = []
     for e in keys:
         aliases = parsealiases(e)
         allcmds.extend(aliases)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith("debug") or found.startswith("debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice, allcmds
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice, allcmds = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = sorted(choice)
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return list(choice.values())[0]
 
     raise error.UnknownCommand(cmd, allcmds)
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def bailifchanged(repo, merge=True, hint=None):
     """ enforce the precondition that working directory must be clean.
 
     'merge' can be set to false if a pending uncommitted merge should be
     ignored (such as when 'update --check' runs).
 
     'hint' is the usual hint given to Abort exception.
     """
 
     if merge and repo.dirstate.p2() != nullid:
         raise error.Abort(_('outstanding uncommitted merge'), hint=hint)
     modified, added, removed, deleted = repo.status()[:4]
     if modified or added or removed or deleted:
         raise error.Abort(_('uncommitted changes'), hint=hint)
     ctx = repo[None]
     for s in sorted(ctx.substate):
         ctx.sub(s).bailifchanged(hint=hint)
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
     message = opts.get('message')
     logfile = opts.get('logfile')
 
     if message and logfile:
         raise error.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if isstdiofilename(logfile):
                 message = ui.fin.read()
             else:
                 message = '\n'.join(util.readfile(logfile).splitlines())
         except IOError as inst:
             raise error.Abort(_("can't read commit message '%s': %s") %
                              (logfile, encoding.strtolocal(inst.strerror)))
     return message
 
 def mergeeditform(ctxorbool, baseformname):
     """return appropriate editform name (referencing a committemplate)
 
     'ctxorbool' is either a ctx to be committed, or a bool indicating whether
     merging is committed.
 
     This returns baseformname with '.merge' appended if it is a merge,
     otherwise '.normal' is appended.
     """
     if isinstance(ctxorbool, bool):
         if ctxorbool:
             return baseformname + ".merge"
     elif 1 < len(ctxorbool.parents()):
         return baseformname + ".merge"
 
     return baseformname + ".normal"
 
 def getcommiteditor(edit=False, finishdesc=None, extramsg=None,
                     editform='', **opts):
     """get appropriate commit message editor according to '--edit' option
 
     'finishdesc' is a function to be called with edited commit message
     (= 'description' of the new changeset) just after editing, but
     before checking empty-ness. It should return actual text to be
     stored into history. This allows to change description before
     storing.
 
     'extramsg' is a extra message to be shown in the editor instead of
     'Leave message empty to abort commit' line. 'HG: ' prefix and EOL
     is automatically added.
 
     'editform' is a dot-separated list of names, to distinguish
     the purpose of commit text editing.
 
     'getcommiteditor' returns 'commitforceeditor' regardless of
     'edit', if one of 'finishdesc' or 'extramsg' is specified, because
     they are specific for usage in MQ.
     """
     if edit or finishdesc or extramsg:
         return lambda r, c, s: commitforceeditor(r, c, s,
                                                  finishdesc=finishdesc,
                                                  extramsg=extramsg,
                                                  editform=editform)
     elif editform:
         return lambda r, c, s: commiteditor(r, c, s, editform=editform)
     else:
         return commiteditor
 
 def loglimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get('limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise error.Abort(_('limit must be a positive integer'))
         if limit <= 0:
             raise error.Abort(_('limit must be positive'))
     else:
         limit = None
     return limit
 
 def makefilename(repo, pat, node, desc=None,
                   total=None, seqno=None, revwidth=None, pathname=None):
     node_expander = {
         'H': lambda: hex(node),
         'R': lambda: str(repo.changelog.rev(node)),
         'h': lambda: short(node),
         'm': lambda: re.sub('[^\w]', '_', str(desc))
         }
     expander = {
         '%': lambda: '%',
         'b': lambda: os.path.basename(repo.root),
         }
 
     try:
         if node:
             expander.update(node_expander)
         if node:
             expander['r'] = (lambda:
                     str(repo.changelog.rev(node)).zfill(revwidth or 0))
         if total is not None:
             expander['N'] = lambda: str(total)
         if seqno is not None:
             expander['n'] = lambda: str(seqno)
         if total is not None and seqno is not None:
             expander['n'] = lambda: str(seqno).zfill(len(str(total)))
         if pathname is not None:
             expander['s'] = lambda: os.path.basename(pathname)
             expander['d'] = lambda: os.path.dirname(pathname) or '.'
             expander['p'] = lambda: pathname
 
         newname = []
         patlen = len(pat)
         i = 0
         while i < patlen:
             c = pat[i:i + 1]
             if c == '%':
                 i += 1
                 c = pat[i:i + 1]
                 c = expander[c]()
             newname.append(c)
             i += 1
         return ''.join(newname)
     except KeyError as inst:
         raise error.Abort(_("invalid format spec '%%%s' in output filename") %
                          inst.args[0])
 
 def isstdiofilename(pat):
     """True if the given pat looks like a filename denoting stdin/stdout"""
     return not pat or pat == '-'
 
 class _unclosablefile(object):
     def __init__(self, fp):
         self._fp = fp
 
     def close(self):
         pass
 
     def __iter__(self):
         return iter(self._fp)
 
     def __getattr__(self, attr):
         return getattr(self._fp, attr)
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         pass
 
 def makefileobj(repo, pat, node=None, desc=None, total=None,
                 seqno=None, revwidth=None, mode='wb', modemap=None,
                 pathname=None):
 
     writable = mode not in ('r', 'rb')
 
     if isstdiofilename(pat):
         if writable:
             fp = repo.ui.fout
         else:
             fp = repo.ui.fin
         return _unclosablefile(fp)
     fn = makefilename(repo, pat, node, desc, total, seqno, revwidth, pathname)
     if modemap is not None:
         mode = modemap.get(fn, mode)
         if mode == 'wb':
             modemap[fn] = 'ab'
     return open(fn, mode)
 
 def openrevlog(repo, cmd, file_, opts):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts['changelog']
     mf = opts['manifest']
     dir = opts['dir']
     msg = None
     if cl and mf:
         msg = _('cannot specify --changelog and --manifest at the same time')
     elif cl and dir:
         msg = _('cannot specify --changelog and --dir at the same time')
     elif cl or mf or dir:
         if file_:
             msg = _('cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _('cannot specify --changelog or --manifest or --dir '
                     'without a repository')
     if msg:
         raise error.Abort(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.unfiltered().changelog
         elif dir:
             if 'treemanifest' not in repo.requirements:
                 raise error.Abort(_("--dir can only be used on repos with "
                                    "treemanifest enabled"))
             dirlog = repo.manifestlog._revlog.dirlog(dir)
             if len(dirlog):
                 r = dirlog
         elif mf:
             r = repo.manifestlog._revlog
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
     if not r:
         if not file_:
             raise error.CommandError(cmd, _('invalid arguments'))
         if not os.path.isfile(file_):
             raise error.Abort(_("revlog '%s' not found") % file_)
         r = revlog.revlog(vfsmod.vfs(pycompat.getcwd(), audit=False),
                           file_[:-2] + ".i")
     return r
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get("after")
     dryrun = opts.get("dry_run")
     wctx = repo[None]
 
     def walkpat(pat):
         srcs = []
         if after:
             badstates = '?'
         else:
             badstates = '?r'
         m = scmutil.match(wctx, [pat], opts, globbed=True)
         for abs in wctx.walk(m):
             state = repo.dirstate[abs]
             rel = m.rel(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
                 if exact and state == 'r':
                     ui.warn(_('%s: not copying - file has been marked for'
                               ' remove\n') % rel)
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if '/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit('/', 1)
             abstarget = repo.dirstate.normalize(abspath) + '/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(_('%s: not overwriting - %s collides with %s\n') %
                     (reltarget, repo.pathto(abssrc, cwd),
                      repo.pathto(prevsrc, cwd)))
             return
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if (repo.dirstate.normalize(abssrc) ==
                 repo.dirstate.normalize(abstarget)):
                 if not rename:
                     ui.warn(_("%s: can't copy - same file\n") % reltarget)
                     return
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in 'mn':
             if not opts['force']:
                 if state in 'mn':
                     msg = _('%s: not overwriting - file already committed\n')
                     if after:
                         flags = '--after --force'
                     else:
                         flags = '--force'
                     if rename:
                         hint = _('(hg rename %s to replace the file by '
                                  'recording a rename)\n') % flags
                     else:
                         hint = _('(hg copy %s to replace the file by '
                                  'recording a copy)\n') % flags
                 else:
                     msg = _('%s: not overwriting - file exists\n')
                     if rename:
                         hint = _('(hg rename --after to record the rename)\n')
                     else:
                         hint = _('(hg copy --after to record the copy)\n')
                 ui.warn(msg % reltarget)
                 ui.warn(hint)
                 return
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(_('%s: not recording move - %s does not exist\n') %
                             (relsrc, reltarget))
                 else:
                     ui.warn(_('%s: not recording copy - %s does not exist\n') %
                             (relsrc, reltarget))
                 return
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or '.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + "~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     util.copyfile(src, target)
                 srcexists = True
             except IOError as inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working directory\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, encoding.strtolocal(inst.strerror)))
                     return True # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_('moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_('copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(ui, repo, wctx, abssrc, abstarget,
                              dryrun=dryrun, cwd=cwd)
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 repo.wvfs.unlinkpath(abssrc)
             wctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(pycompat.ossep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(pycompat.ossep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(pycompat.ossep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest,
                                              util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(dest,
                                         os.path.basename(util.localpath(p)))
                 else:
                     res = lambda p: dest
         return res
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise error.Abort(_('no source or destination specified'))
     if len(pats) == 1:
         raise error.Abort(_('no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise error.Abort(_('with multiple sources, destination must be an '
                                'existing directory'))
         if util.endswithsep(dest):
             raise error.Abort(_('destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise error.Abort(_('no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     if errors:
         ui.warn(_('(consider using --after)\n'))
 
     return errors != 0
 
 ## facility to let extension process additional data into an import patch
 # list of identifier to be executed in order
 extrapreimport = []  # run before commit
 extrapostimport = [] # run after commit
 # mapping from identifier to actual import function
 #
 # 'preimport' are run before the commit is made and are provided the following
 # arguments:
 # - repo: the localrepository instance,
 # - patchdata: data extracted from patch header (cf m.patch.patchheadermap),
 # - extra: the future extra dictionary of the changeset, please mutate it,
 # - opts: the import options.
 # XXX ideally, we would just pass an ctx ready to be computed, that would allow
 # mutation of in memory commit and more. Feel free to rework the code to get
 # there.
 extrapreimportmap = {}
 # 'postimport' are run after the commit is made and are provided the following
 # argument:
 # - ctx: the changectx created by import.
 extrapostimportmap = {}
 
 def tryimportone(ui, repo, hunk, parents, opts, msgs, updatefunc):
     """Utility function used by commands.import to import a single patch
 
     This function is explicitly defined here to help the evolve extension to
     wrap this part of the import logic.
 
     The API is currently a bit ugly because it a simple code translation from
     the import command. Feel free to make it better.
 
     :hunk: a patch (as a binary string)
     :parents: nodes that will be parent of the created commit
     :opts: the full dict of option passed to the import command
     :msgs: list to save commit message to.
            (used in case we need to save it when failing)
     :updatefunc: a function that update a repo to a given node
                  updatefunc(<repo>, <node>)
     """
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
     extractdata = patch.extract(ui, hunk)
     tmpname = extractdata.get('filename')
     message = extractdata.get('message')
     user = opts.get('user') or extractdata.get('user')
     date = opts.get('date') or extractdata.get('date')
     branch = extractdata.get('branch')
     nodeid = extractdata.get('nodeid')
     p1 = extractdata.get('p1')
     p2 = extractdata.get('p2')
 
     nocommit = opts.get('no_commit')
     importbranch = opts.get('import_branch')
     update = not opts.get('bypass')
     strip = opts["strip"]
     prefix = opts["prefix"]
     sim = float(opts.get('similarity') or 0)
     if not tmpname:
         return (None, None, False)
 
     rejects = False
 
     try:
         cmdline_message = logmessage(ui, opts)
         if cmdline_message:
             # pickup the cmdline msg
             message = cmdline_message
         elif message:
             # pickup the patch msg
             message = message.strip()
         else:
             # launch the editor
             message = None
         ui.debug('message:\n%s\n' % message)
 
         if len(parents) == 1:
             parents.append(repo[nullid])
         if opts.get('exact'):
             if not nodeid or not p1:
                 raise error.Abort(_('not a Mercurial patch'))
             p1 = repo[p1]
             p2 = repo[p2 or nullid]
         elif p2:
             try:
                 p1 = repo[p1]
                 p2 = repo[p2]
                 # Without any options, consider p2 only if the
                 # patch is being applied on top of the recorded
                 # first parent.
                 if p1 != parents[0]:
                     p1 = parents[0]
                     p2 = repo[nullid]
             except error.RepoError:
                 p1, p2 = parents
             if p2.node() == nullid:
                 ui.warn(_("warning: import the patch as a normal revision\n"
                           "(use --exact to import the patch as a merge)\n"))
         else:
             p1, p2 = parents
 
         n = None
         if update:
             if p1 != parents[0]:
                 updatefunc(repo, p1.node())
             if p2 != parents[1]:
                 repo.setparents(p1.node(), p2.node())
 
             if opts.get('exact') or importbranch:
                 repo.dirstate.setbranch(branch or 'default')
 
             partial = opts.get('partial', False)
             files = set()
             try:
                 patch.patch(ui, repo, tmpname, strip=strip, prefix=prefix,
                             files=files, eolmode=None, similarity=sim / 100.0)
             except error.PatchError as e:
                 if not partial:
                     raise error.Abort(str(e))
                 if partial:
                     rejects = True
 
             files = list(files)
             if nocommit:
                 if message:
                     msgs.append(message)
             else:
                 if opts.get('exact') or p2:
                     # If you got here, you either use --force and know what
                     # you are doing or used --exact or a merge patch while
                     # being updated to its first parent.
                     m = None
                 else:
                     m = scmutil.matchfiles(repo, files or [])
                 editform = mergeeditform(repo[None], 'import.normal')
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform=editform, **opts)
                 extra = {}
                 for idfunc in extrapreimport:
                     extrapreimportmap[idfunc](repo, extractdata, extra, opts)
                 overrides = {}
                 if partial:
                     overrides[('ui', 'allowemptycommit')] = True
                 with repo.ui.configoverride(overrides, 'import'):
                     n = repo.commit(message, user,
                                     date, match=m,
                                     editor=editor, extra=extra)
                     for idfunc in extrapostimport:
                         extrapostimportmap[idfunc](repo[n])
         else:
             if opts.get('exact') or importbranch:
                 branch = branch or 'default'
             else:
                 branch = p1.branch()
             store = patch.filestore()
             try:
                 files = set()
                 try:
                     patch.patchrepo(ui, repo, p1, store, tmpname, strip, prefix,
                                     files, eolmode=None)
                 except error.PatchError as e:
                     raise error.Abort(str(e))
                 if opts.get('exact'):
                     editor = None
                 else:
                     editor = getcommiteditor(editform='import.bypass')
                 memctx = context.memctx(repo, (p1.node(), p2.node()),
                                             message,
                                             files=files,
                                             filectxfn=store,
                                             user=user,
                                             date=date,
                                             branch=branch,
                                             editor=editor)
                 n = memctx.commit()
             finally:
                 store.close()
         if opts.get('exact') and nocommit:
             # --exact with --no-commit is still useful in that it does merge
             # and branch bits
             ui.warn(_("warning: can't check exact import with --no-commit\n"))
         elif opts.get('exact') and hex(n) != nodeid:
             raise error.Abort(_('patch is damaged or loses information'))
         msg = _('applied to working directory')
         if n:
             # i18n: refers to a short changeset id
             msg = _('created %s') % short(n)
         return (msg, n, rejects)
     finally:
         os.unlink(tmpname)
 
 # facility to let extensions include additional data in an exported patch
 # list of identifiers to be executed in order
 extraexport = []
 # mapping from identifier to actual export function
 # function as to return a string to be added to the header or None
 # it is given two arguments (sequencenumber, changectx)
 extraexportmap = {}
 
 def _exportsingle(repo, ctx, match, switch_parent, rev, seqno, write, diffopts):
     node = scmutil.binnode(ctx)
     parents = [p.node() for p in ctx.parents() if p]
     branch = ctx.branch()
     if switch_parent:
         parents.reverse()
 
     if parents:
         prev = parents[0]
     else:
         prev = nullid
 
     write("# HG changeset patch\n")
     write("# User %s\n" % ctx.user())
     write("# Date %d %d\n" % ctx.date())
     write("#      %s\n" % util.datestr(ctx.date()))
     if branch and branch != 'default':
         write("# Branch %s\n" % branch)
     write("# Node ID %s\n" % hex(node))
     write("# Parent  %s\n" % hex(prev))
     if len(parents) > 1:
         write("# Parent  %s\n" % hex(parents[1]))
 
     for headerid in extraexport:
         header = extraexportmap[headerid](seqno, ctx)
         if header is not None:
             write('# %s\n' % header)
     write(ctx.description().rstrip())
     write("\n\n")
 
     for chunk, label in patch.diffui(repo, prev, node, match, opts=diffopts):
         write(chunk, label=label)
 
 def export(repo, revs, fntemplate='hg-%h.patch', fp=None, switch_parent=False,
            opts=None, match=None):
     '''export changesets as hg patches
 
     Args:
       repo: The repository from which we're exporting revisions.
       revs: A list of revisions to export as revision numbers.
       fntemplate: An optional string to use for generating patch file names.
       fp: An optional file-like object to which patches should be written.
       switch_parent: If True, show diffs against second parent when not nullid.
                      Default is false, which always shows diff against p1.
       opts: diff options to use for generating the patch.
       match: If specified, only export changes to files matching this matcher.
 
     Returns:
       Nothing.
 
     Side Effect:
       "HG Changeset Patch" data is emitted to one of the following
       destinations:
         fp is specified: All revs are written to the specified
                          file-like object.
         fntemplate specified: Each rev is written to a unique file named using
                             the given template.
         Neither fp nor template specified: All revs written to repo.ui.write()
     '''
 
     total = len(revs)
     revwidth = max(len(str(rev)) for rev in revs)
     filemode = {}
 
     write = None
     dest = '<unnamed>'
     if fp:
         dest = getattr(fp, 'name', dest)
         def write(s, **kw):
             fp.write(s)
     elif not fntemplate:
         write = repo.ui.write
 
     for seqno, rev in enumerate(revs, 1):
         ctx = repo[rev]
         fo = None
         if not fp and fntemplate:
             desc_lines = ctx.description().rstrip().split('\n')
             desc = desc_lines[0]    #Commit always has a first line.
             fo = makefileobj(repo, fntemplate, ctx.node(), desc=desc,
                              total=total, seqno=seqno, revwidth=revwidth,
                              mode='wb', modemap=filemode)
             dest = fo.name
             def write(s, **kw):
                 fo.write(s)
         if not dest.startswith('<'):
             repo.ui.note("%s\n" % dest)
         _exportsingle(
             repo, ctx, match, switch_parent, rev, seqno, write, opts)
         if fo is not None:
             fo.close()
 
 def diffordiffstat(ui, repo, diffopts, node1, node2, match,
                    changes=None, stat=False, fp=None, prefix='',
                    root='', listsubrepos=False):
     '''show diff or diffstat.'''
     if fp is None:
         write = ui.write
     else:
         def write(s, **kw):
             fp.write(s)
 
     if root:
         relroot = pathutil.canonpath(repo.root, repo.getcwd(), root)
     else:
         relroot = ''
     if relroot != '':
         # XXX relative roots currently don't work if the root is within a
         # subrepo
         uirelroot = match.uipath(relroot)
         relroot += '/'
         for matchroot in match.files():
             if not matchroot.startswith(relroot):
                 ui.warn(_('warning: %s not inside relative root %s\n') % (
                     match.uipath(matchroot), uirelroot))
 
     if stat:
         diffopts = diffopts.copy(context=0)
         width = 80
         if not ui.plain():
             width = ui.termwidth()
         chunks = patch.diff(repo, node1, node2, match, changes, diffopts,
                             prefix=prefix, relroot=relroot)
         for chunk, label in patch.diffstatui(util.iterlines(chunks),
                                              width=width):
             write(chunk, label=label)
     else:
         for chunk, label in patch.diffui(repo, node1, node2, match,
                                          changes, diffopts, prefix=prefix,
                                          relroot=relroot):
             write(chunk, label=label)
 
     if listsubrepos:
         ctx1 = repo[node1]
         ctx2 = repo[node2]
         for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
             tempnode2 = node2
             try:
                 if node2 is not None:
                     tempnode2 = ctx2.substate[subpath][1]
             except KeyError:
                 # A subrepo that existed in node1 was deleted between node1 and
                 # node2 (inclusive). Thus, ctx2's substate won't contain that
                 # subpath. The best we can do is to ignore it.
                 tempnode2 = None
             submatch = matchmod.subdirmatcher(subpath, match)
             sub.diff(ui, diffopts, tempnode2, submatch, changes=changes,
                      stat=stat, fp=fp, prefix=prefix)
 
 def _changesetlabels(ctx):
     labels = ['log.changeset', 'changeset.%s' % ctx.phasestr()]
     if ctx.obsolete():
         labels.append('changeset.obsolete')
     if ctx.isunstable():
         labels.append('changeset.unstable')
         for instability in ctx.instabilities():
             labels.append('instability.%s' % instability)
     return ' '.join(labels)
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, matchfn, diffopts, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.matchfn = matchfn
         self.diffopts = diffopts
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
 
     def flush(self, ctx):
         rev = ctx.rev()
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
             return 1
         return 0
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, matchfn=None, **props):
         props = pycompat.byteskwargs(props)
         if self.buffered:
             self.ui.pushbuffer(labeled=True)
             self._show(ctx, copies, matchfn, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer()
         else:
             self._show(ctx, copies, matchfn, props)
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         rev = ctx.rev()
 
         if self.ui.quiet:
             self.ui.write("%s\n" % scmutil.formatchangeid(ctx),
                           label='log.node')
             return
 
         date = util.datestr(ctx.date())
 
         # i18n: column positioning for "hg log"
         self.ui.write(_("changeset:   %s\n") % scmutil.formatchangeid(ctx),
                       label=_changesetlabels(ctx))
 
         # branches are shown first before any other names due to backwards
         # compatibility
         branch = ctx.branch()
         # don't show the default branch name
         if branch != 'default':
             # i18n: column positioning for "hg log"
             self.ui.write(_("branch:      %s\n") % branch,
                           label='log.branch')
 
         for nsname, ns in self.repo.names.iteritems():
             # branches has special logic already handled above, so here we just
             # skip it
             if nsname == 'branches':
                 continue
             # we will use the templatename as the color name since those two
             # should be the same
             for name in ns.names(self.repo, changenode):
                 self.ui.write(ns.logfmt % name,
                               label='log.%s' % ns.colorname)
         if self.ui.debugflag:
             # i18n: column positioning for "hg log"
             self.ui.write(_("phase:       %s\n") % ctx.phasestr(),
                           label='log.phase')
         for pctx in scmutil.meaningfulparents(self.repo, ctx):
             label = 'log.parent changeset.%s' % pctx.phasestr()
             # i18n: column positioning for "hg log"
             self.ui.write(_("parent:      %s\n") % scmutil.formatchangeid(pctx),
                           label=label)
 
         if self.ui.debugflag and rev is not None:
             mnode = ctx.manifestnode()
             mrev = self.repo.manifestlog._revlog.rev(mnode)
             # i18n: column positioning for "hg log"
             self.ui.write(_("manifest:    %s\n")
                           % scmutil.formatrevnode(self.ui, mrev, mnode),
                           label='ui.debug log.manifest')
         # i18n: column positioning for "hg log"
         self.ui.write(_("user:        %s\n") % ctx.user(),
                       label='log.user')
         # i18n: column positioning for "hg log"
         self.ui.write(_("date:        %s\n") % date,
                       label='log.date')
 
         if ctx.isunstable():
             # i18n: column positioning for "hg log"
             instabilities = ctx.instabilities()
             self.ui.write(_("instability: %s\n") % ', '.join(instabilities),
                           label='log.instability')
 
         self._exthook(ctx)
 
         if self.ui.debugflag:
             files = ctx.p1().status(ctx)[:3]
             for key, value in zip([# i18n: column positioning for "hg log"
                                    _("files:"),
                                    # i18n: column positioning for "hg log"
                                    _("files+:"),
                                    # i18n: column positioning for "hg log"
                                    _("files-:")], files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)),
                                   label='ui.debug log.files')
         elif ctx.files() and self.ui.verbose:
             # i18n: column positioning for "hg log"
             self.ui.write(_("files:       %s\n") % " ".join(ctx.files()),
                           label='ui.note log.files')
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             # i18n: column positioning for "hg log"
             self.ui.write(_("copies:      %s\n") % ' '.join(copies),
                           label='ui.note log.copies')
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, util.escapestr(value)),
                               label='ui.debug log.extra')
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"),
                               label='ui.note log.description')
                 self.ui.write(description,
                               label='ui.note log.description')
                 self.ui.write("\n\n")
             else:
                 # i18n: column positioning for "hg log"
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0],
                               label='log.summary')
         self.ui.write("\n")
 
         self.showpatch(ctx, matchfn)
 
     def _exthook(self, ctx):
         '''empty method used by extension as a hook point
         '''
         pass
 
     def showpatch(self, ctx, matchfn):
         if not matchfn:
             matchfn = self.matchfn
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.diffallopts(self.ui, self.diffopts)
             node = ctx.node()
             prev = ctx.p1().node()
             if stat:
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
             if diff:
                 if stat:
                     self.ui.write("\n")
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
             self.ui.write("\n")
 
 class jsonchangeset(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, matchfn, diffopts, buffered):
         changeset_printer.__init__(self, ui, repo, matchfn, diffopts, buffered)
         self.cache = {}
         self._first = True
 
     def close(self):
         if not self._first:
             self.ui.write("\n]\n")
         else:
             self.ui.write("[]\n")
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         rev = ctx.rev()
         if rev is None:
             jrev = jnode = 'null'
         else:
             jrev = '%d' % rev
             jnode = '"%s"' % hex(ctx.node())
         j = encoding.jsonescape
 
         if self._first:
             self.ui.write("[\n {")
             self._first = False
         else:
             self.ui.write(",\n {")
 
         if self.ui.quiet:
             self.ui.write(('\n  "rev": %s') % jrev)
             self.ui.write((',\n  "node": %s') % jnode)
             self.ui.write('\n }')
             return
 
         self.ui.write(('\n  "rev": %s') % jrev)
         self.ui.write((',\n  "node": %s') % jnode)
         self.ui.write((',\n  "branch": "%s"') % j(ctx.branch()))
         self.ui.write((',\n  "phase": "%s"') % ctx.phasestr())
         self.ui.write((',\n  "user": "%s"') % j(ctx.user()))
         self.ui.write((',\n  "date": [%d, %d]') % ctx.date())
         self.ui.write((',\n  "desc": "%s"') % j(ctx.description()))
 
         self.ui.write((',\n  "bookmarks": [%s]') %
                       ", ".join('"%s"' % j(b) for b in ctx.bookmarks()))
         self.ui.write((',\n  "tags": [%s]') %
                       ", ".join('"%s"' % j(t) for t in ctx.tags()))
         self.ui.write((',\n  "parents": [%s]') %
                       ", ".join('"%s"' % c.hex() for c in ctx.parents()))
 
         if self.ui.debugflag:
             if rev is None:
                 jmanifestnode = 'null'
             else:
                 jmanifestnode = '"%s"' % hex(ctx.manifestnode())
             self.ui.write((',\n  "manifest": %s') % jmanifestnode)
 
             self.ui.write((',\n  "extra": {%s}') %
                           ", ".join('"%s": "%s"' % (j(k), j(v))
                                     for k, v in ctx.extra().items()))
 
             files = ctx.p1().status(ctx)
             self.ui.write((',\n  "modified": [%s]') %
                           ", ".join('"%s"' % j(f) for f in files[0]))
             self.ui.write((',\n  "added": [%s]') %
                           ", ".join('"%s"' % j(f) for f in files[1]))
             self.ui.write((',\n  "removed": [%s]') %
                           ", ".join('"%s"' % j(f) for f in files[2]))
 
         elif self.ui.verbose:
             self.ui.write((',\n  "files": [%s]') %
                           ", ".join('"%s"' % j(f) for f in ctx.files()))
 
             if copies:
                 self.ui.write((',\n  "copies": {%s}') %
                               ", ".join('"%s": "%s"' % (j(k), j(v))
                                                         for k, v in copies))
 
         matchfn = self.matchfn
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.difffeatureopts(self.ui, self.diffopts, git=True)
             node, prev = ctx.node(), ctx.p1().node()
             if stat:
                 self.ui.pushbuffer()
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
                 self.ui.write((',\n  "diffstat": "%s"')
                               % j(self.ui.popbuffer()))
             if diff:
                 self.ui.pushbuffer()
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
                 self.ui.write((',\n  "diff": "%s"') % j(self.ui.popbuffer()))
 
         self.ui.write("\n }")
 
 class changeset_templater(changeset_printer):
     '''format changeset information.'''
 
     # Arguments before "buffered" used to be positional. Consider not
     # adding/removing arguments before "buffered" to not break callers.
     def __init__(self, ui, repo, tmplspec, matchfn=None, diffopts=None,
                  buffered=False):
         diffopts = diffopts or {}
 
         changeset_printer.__init__(self, ui, repo, matchfn, diffopts, buffered)
         self.t = formatter.loadtemplater(ui, tmplspec,
                                          cache=templatekw.defaulttempl)
         self._counter = itertools.count()
         self.cache = {}
 
         self._tref = tmplspec.ref
         self._parts = {'header': '', 'footer': '',
                        tmplspec.ref: tmplspec.ref,
                        'docheader': '', 'docfooter': '',
                        'separator': ''}
         if tmplspec.mapfile:
             # find correct templates for current mode, for backward
             # compatibility with 'log -v/-q/--debug' using a mapfile
             tmplmodes = [
                 (True, ''),
                 (self.ui.verbose, '_verbose'),
                 (self.ui.quiet, '_quiet'),
                 (self.ui.debugflag, '_debug'),
             ]
             for mode, postfix in tmplmodes:
                 for t in self._parts:
                     cur = t + postfix
                     if mode and cur in self.t:
                         self._parts[t] = cur
         else:
             partnames = [p for p in self._parts.keys() if p != tmplspec.ref]
             m = formatter.templatepartsmap(tmplspec, self.t, partnames)
             self._parts.update(m)
 
         if self._parts['docheader']:
             self.ui.write(templater.stringify(self.t(self._parts['docheader'])))
 
     def close(self):
         if self._parts['docfooter']:
             if not self.footer:
                 self.footer = ""
             self.footer += templater.stringify(self.t(self._parts['docfooter']))
         return super(changeset_templater, self).close()
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         props = props.copy()
         props.update(templatekw.keywords)
         props['templ'] = self.t
         props['ctx'] = ctx
         props['repo'] = self.repo
         props['ui'] = self.repo.ui
         props['index'] = index = next(self._counter)
         props['revcache'] = {'copies': copies}
         props['cache'] = self.cache
         props = pycompat.strkwargs(props)
 
         # write separator, which wouldn't work well with the header part below
         # since there's inherently a conflict between header (across items) and
         # separator (per item)
         if self._parts['separator'] and index > 0:
             self.ui.write(templater.stringify(self.t(self._parts['separator'])))
 
         # write header
         if self._parts['header']:
             h = templater.stringify(self.t(self._parts['header'], **props))
             if self.buffered:
                 self.header[ctx.rev()] = h
             else:
                 if self.lastheader != h:
                     self.lastheader = h
                     self.ui.write(h)
 
         # write changeset metadata, then patch if requested
         key = self._parts[self._tref]
         self.ui.write(templater.stringify(self.t(key, **props)))
         self.showpatch(ctx, matchfn)
 
         if self._parts['footer']:
             if not self.footer:
                 self.footer = templater.stringify(
                     self.t(self._parts['footer'], **props))
 
 def logtemplatespec(tmpl, mapfile):
     if mapfile:
         return formatter.templatespec('changeset', tmpl, mapfile)
     else:
         return formatter.templatespec('', tmpl, None)
 
 def _lookuplogtemplate(ui, tmpl, style):
     """Find the template matching the given template spec or style
 
     See formatter.lookuptemplate() for details.
     """
 
     # ui settings
     if not tmpl and not style: # template are stronger than style
         tmpl = ui.config('ui', 'logtemplate')
         if tmpl:
             return logtemplatespec(templater.unquotestring(tmpl), None)
         else:
             style = util.expandpath(ui.config('ui', 'style'))
 
     if not tmpl and style:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = (templater.templatepath('map-cmdline.' + mapfile)
                        or templater.templatepath(mapfile))
             if mapname:
                 mapfile = mapname
         return logtemplatespec(None, mapfile)
 
     if not tmpl:
         return logtemplatespec(None, None)
 
     return formatter.lookuptemplate(ui, 'changeset', tmpl)
 
 def makelogtemplater(ui, repo, tmpl, buffered=False):
     """Create a changeset_templater from a literal template 'tmpl'"""
     spec = logtemplatespec(tmpl, None)
     return changeset_templater(ui, repo, spec, buffered=buffered)
 
 def show_changeset(ui, repo, opts, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changeset_printer() is done.
     """
     # options
     match = None
     if opts.get('patch') or opts.get('stat'):
         match = scmutil.matchall(repo)
 
     if opts.get('template') == 'json':
         return jsonchangeset(ui, repo, match, opts, buffered)
 
     spec = _lookuplogtemplate(ui, opts.get('template'), opts.get('style'))
 
     if not spec.ref and not spec.tmpl and not spec.mapfile:
         return changeset_printer(ui, repo, match, opts, buffered)
 
     return changeset_templater(ui, repo, spec, match, opts, buffered)
 
 def showmarker(fm, marker, index=None):
     """utility function to display obsolescence marker in a readable way
 
     To be used by debug function."""
     if index is not None:
         fm.write('index', '%i ', index)
     fm.write('prednode', '%s ', hex(marker.prednode()))
     succs = marker.succnodes()
     fm.condwrite(succs, 'succnodes', '%s ',
                  fm.formatlist(map(hex, succs), name='node'))
     fm.write('flag', '%X ', marker.flags())
     parents = marker.parentnodes()
     if parents is not None:
         fm.write('parentnodes', '{%s} ',
                  fm.formatlist(map(hex, parents), name='node', sep=', '))
     fm.write('date', '(%s) ', fm.formatdate(marker.date()))
     meta = marker.metadata().copy()
     meta.pop('date', None)
     fm.write('metadata', '{%s}', fm.formatdict(meta, fmt='%r: %r', sep=', '))
     fm.plain('\n')
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = util.matchdate(date)
     m = scmutil.matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(_("found revision %s from %s\n") %
                       (rev, util.datestr(results[rev])))
             return '%d' % rev
 
     raise error.Abort(_("revision matching date not found"))
 
 def increasingwindows(windowsize=8, sizelimit=512):
     while True:
         yield windowsize
         if windowsize < sizelimit:
             windowsize *= 2
 
 class FileWalkError(Exception):
     pass
 
 def walkfilerevs(repo, match, follow, revs, fncache):
     '''Walks the file history for the matched files.
 
     Returns the changeset revs that are involved in the file history.
 
     Throws FileWalkError if the file history can't be walked using
     filelogs alone.
     '''
     wanted = set()
     copies = []
     minrev, maxrev = min(revs), max(revs)
     def filerevgen(filelog, last):
         """
         Only files, no patterns.  Check the history of each file.
 
         Examines filelog entries within minrev, maxrev linkrev range
         Returns an iterator yielding (linkrev, parentlinkrevs, copied)
         tuples in backwards order
         """
         cl_count = len(repo)
         revs = []
         for j in xrange(0, last + 1):
             linkrev = filelog.linkrev(j)
             if linkrev < minrev:
                 continue
             # only yield rev for which we have the changelog, it can
             # happen while doing "hg log" during a pull or commit
             if linkrev >= cl_count:
                 break
 
             parentlinkrevs = []
             for p in filelog.parentrevs(j):
                 if p != nullrev:
                     parentlinkrevs.append(filelog.linkrev(p))
             n = filelog.node(j)
             revs.append((linkrev, parentlinkrevs,
                          follow and filelog.renamed(n)))
 
         return reversed(revs)
     def iterfiles():
         pctx = repo['.']
         for filename in match.files():
             if follow:
                 if filename not in pctx:
                     raise error.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % filename)
                 yield filename, pctx[filename].filenode()
             else:
                 yield filename, None
         for filename_node in copies:
             yield filename_node
 
     for file_, node in iterfiles():
         filelog = repo.file(file_)
         if not len(filelog):
             if node is None:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _('cannot follow nonexistent file: "%s"') % file_)
                 raise FileWalkError("Cannot walk via filelog")
             else:
                 continue
 
         if node is None:
             last = len(filelog) - 1
         else:
             last = filelog.rev(node)
 
         # keep track of all ancestors of the file
         ancestors = {filelog.linkrev(last)}
 
         # iterate from latest to oldest revision
         for rev, flparentlinkrevs, copied in filerevgen(filelog, last):
             if not follow:
                 if rev > maxrev:
                     continue
             else:
                 # Note that last might not be the first interesting
                 # rev to us:
                 # if the file has been changed after maxrev, we'll
                 # have linkrev(last) > maxrev, and we still need
                 # to explore the file graph
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
             fncache.setdefault(rev, []).append(file_)
             wanted.add(rev)
             if copied:
                 copies.append(copied)
 
     return wanted
 
 class _followfilter(object):
     def __init__(self, repo, onlyfirst=False):
         self.repo = repo
         self.startrev = nullrev
         self.roots = set()
         self.onlyfirst = onlyfirst
 
     def match(self, rev):
         def realparents(rev):
             if self.onlyfirst:
                 return self.repo.changelog.parentrevs(rev)[0:1]
             else:
                 return filter(lambda x: x != nullrev,
                               self.repo.changelog.parentrevs(rev))
 
         if self.startrev == nullrev:
             self.startrev = rev
             return True
 
         if rev > self.startrev:
             # forward: all descendants
             if not self.roots:
                 self.roots.add(self.startrev)
             for parent in realparents(rev):
                 if parent in self.roots:
                     self.roots.add(rev)
                     return True
         else:
             # backwards: all parents
             if not self.roots:
                 self.roots.update(realparents(self.startrev))
             if rev in self.roots:
                 self.roots.remove(rev)
                 self.roots.update(realparents(rev))
                 return True
 
         return False
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     follow = opts.get('follow') or opts.get('follow_first')
     revs = _logrevs(repo, opts)
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or ((match.isexact() or match.prefix()) and
                                    opts.get('removed'))
     fncache = {}
     change = repo.changectx
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if match.always():
         # No files, no patterns.  Display all revs.
         wanted = revs
     elif not slowpath:
         # We only have to read through the filelog to find wanted revisions
 
         try:
             wanted = walkfilerevs(repo, match, follow, revs, fncache)
         except FileWalkError:
             slowpath = True
 
             # We decided to fall back to the slowpath because at least one
             # of the paths was not a file. Check to see if at least one of them
             # existed in history, otherwise simply return
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 return []
 
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise error.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
 
         # The slow path checks files modified in every changeset.
         # This is really slow on large repos, so compute the set lazily.
         class lazywantedset(object):
             def __init__(self):
                 self.set = set()
                 self.revs = set(revs)
 
             # No need to worry about locality here because it will be accessed
             # in the same order as the increasing window below.
             def __contains__(self, value):
                 if value in self.set:
                     return True
                 elif not value in self.revs:
                     return False
                 else:
                     self.revs.discard(value)
                     ctx = change(value)
                     matches = filter(match, ctx.files())
                     if matches:
                         fncache[value] = matches
                         self.set.add(value)
                         return True
                     return False
 
             def discard(self, value):
                 self.revs.discard(value)
                 self.set.discard(value)
 
         wanted = lazywantedset()
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get('prune', ()):
         rev = repo[rev].rev()
         ff = _followfilter(repo)
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted = wanted - [x]
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and match.always():
             ff = _followfilter(repo, onlyfirst=opts.get('follow_first'))
             def want(rev):
                 return ff.match(rev) and rev in wanted
         else:
             def want(rev):
                 return rev in wanted
 
         it = iter(revs)
         stopiteration = False
         for windowsize in increasingwindows():
             nrevs = []
             for i in xrange(windowsize):
                 rev = next(it, None)
                 if rev is None:
                     stopiteration = True
                     break
                 elif want(rev):
                     nrevs.append(rev)
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
                     def fns_generator():
                         for f in ctx.files():
                             if match(f):
                                 yield f
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
 
             if stopiteration:
                 break
 
     return iterate()
 
 def _makefollowlogfilematcher(repo, files, followfirst):
     # When displaying a revision with --patch --follow FILE, we have
     # to know which file of the revision must be diffed. With
     # --follow, we want the names of the ancestors of FILE in the
     # revision, stored in "fcache". "fcache" is populated by
     # reproducing the graph traversal already done by --follow revset
     # and relating revs to file names (which is not "correct" but
     # good enough).
     fcache = {}
     fcacheready = [False]
     pctx = repo['.']
 
     def populate():
         for fn in files:
             fctx = pctx[fn]
             fcache.setdefault(fctx.introrev(), set()).add(fctx.path())
             for c in fctx.ancestors(followfirst=followfirst):
                 fcache.setdefault(c.rev(), set()).add(c.path())
 
     def filematcher(rev):
         if not fcacheready[0]:
             # Lazy initialization
             fcacheready[0] = True
             populate()
         return scmutil.matchfiles(repo, fcache.get(rev, []))
 
     return filematcher
 
 def _makenofollowlogfilematcher(repo, pats, opts):
     '''hook for extensions to override the filematcher for non-follow cases'''
     return None
 
 def _makelogrevset(repo, pats, opts, revs):
     """Return (expr, filematcher) where expr is a revset string built
     from log options and file patterns or None. If --stat or --patch
     are not passed filematcher is None. Otherwise it is a callable
     taking a revision number and returning a match objects filtering
     the files to be detailed when displaying the revision.
     """
     opt2revset = {
         'no_merges':        ('not merge()', None),
         'only_merges':      ('merge()', None),
         '_ancestors':       ('ancestors(%(val)s)', None),
         '_fancestors':      ('_firstancestors(%(val)s)', None),
         '_descendants':     ('descendants(%(val)s)', None),
         '_fdescendants':    ('_firstdescendants(%(val)s)', None),
         '_matchfiles':      ('_matchfiles(%(val)s)', None),
         'date':             ('date(%(val)r)', None),
         'branch':           ('branch(%(val)r)', ' or '),
         '_patslog':         ('filelog(%(val)r)', ' or '),
         '_patsfollow':      ('follow(%(val)r)', ' or '),
         '_patsfollowfirst': ('_followfirst(%(val)r)', ' or '),
         'keyword':          ('keyword(%(val)r)', ' or '),
         'prune':            ('not (%(val)r or ancestors(%(val)r))', ' and '),
         'user':             ('user(%(val)r)', ' or '),
         }
 
     opts = dict(opts)
     # follow or not follow?
     follow = opts.get('follow') or opts.get('follow_first')
     if opts.get('follow_first'):
         followfirst = 1
     else:
         followfirst = 0
     # --follow with FILE behavior depends on revs...
     it = iter(revs)
     startrev = next(it)
     followdescendants = startrev < next(it, startrev)
 
     # branch and only_branch are really aliases and must be handled at
     # the same time
     opts['branch'] = opts.get('branch', []) + opts.get('only_branch', [])
     opts['branch'] = [repo.lookupbranch(b) for b in opts['branch']]
     # pats/include/exclude are passed to match.match() directly in
     # _matchfiles() revset but walkchangerevs() builds its matcher with
     # scmutil.match(). The difference is input pats are globbed on
     # platforms without shell expansion (windows).
     wctx = repo[None]
     match, pats = scmutil.matchandpats(wctx, pats, opts)
     slowpath = match.anypats() or ((match.isexact() or match.prefix()) and
                                    opts.get('removed'))
     if not slowpath:
         for f in match.files():
             if follow and f not in wctx:
                 # If the file exists, it may be a directory, so let it
                 # take the slow path.
                 if os.path.exists(repo.wjoin(f)):
                     slowpath = True
                     continue
                 else:
                     raise error.Abort(_('cannot follow file not in parent '
                                        'revision: "%s"') % f)
             filelog = repo.file(f)
             if not filelog:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _('cannot follow nonexistent file: "%s"') % f)
                 slowpath = True
 
         # We decided to fall back to the slowpath because at least one
         # of the paths was not a file. Check to see if at least one of them
         # existed in history - in that case, we'll continue down the
         # slowpath; otherwise, we can turn off the slowpath
         if slowpath:
             for path in match.files():
                 if path == '.' or path in repo.store:
                     break
             else:
                 slowpath = False
 
     fpats = ('_patsfollow', '_patsfollowfirst')
     fnopats = (('_ancestors', '_fancestors'),
                ('_descendants', '_fdescendants'))
     if slowpath:
         # See walkchangerevs() slow path.
         #
         # pats/include/exclude cannot be represented as separate
         # revset expressions as their filtering logic applies at file
         # level. For instance "-I a -X a" matches a revision touching
         # "a" and "b" while "file(a) and not file(b)" does
         # not. Besides, filesets are evaluated against the working
         # directory.
         matchargs = ['r:', 'd:relpath']
         for p in pats:
             matchargs.append('p:' + p)
         for p in opts.get('include', []):
             matchargs.append('i:' + p)
         for p in opts.get('exclude', []):
             matchargs.append('x:' + p)
         matchargs = ','.join(('%r' % p) for p in matchargs)
         opts['_matchfiles'] = matchargs
         if follow:
             opts[fnopats[0][followfirst]] = '.'
     else:
         if follow:
             if pats:
                 # follow() revset interprets its file argument as a
                 # manifest entry, so use match.files(), not pats.
                 opts[fpats[followfirst]] = list(match.files())
             else:
                 op = fnopats[followdescendants][followfirst]
                 opts[op] = 'rev(%d)' % startrev
         else:
             opts['_patslog'] = list(pats)
 
     filematcher = None
     if opts.get('patch') or opts.get('stat'):
         # When following files, track renames via a special matcher.
         # If we're forced to take the slowpath it means we're following
         # at least one pattern/directory, so don't bother with rename tracking.
         if follow and not match.always() and not slowpath:
             # _makefollowlogfilematcher expects its files argument to be
             # relative to the repo root, so use match.files(), not pats.
             filematcher = _makefollowlogfilematcher(repo, match.files(),
                                                     followfirst)
         else:
             filematcher = _makenofollowlogfilematcher(repo, pats, opts)
             if filematcher is None:
                 filematcher = lambda rev: match
 
     expr = []
     for op, val in sorted(opts.iteritems()):
         if not val:
             continue
         if op not in opt2revset:
             continue
         revop, andor = opt2revset[op]
         if '%(val)' not in revop:
             expr.append(revop)
         else:
             if not isinstance(val, list):
                 e = revop % {'val': val}
             else:
                 e = '(' + andor.join((revop % {'val': v}) for v in val) + ')'
             expr.append(e)
 
     if expr:
         expr = '(' + ' and '.join(expr) + ')'
     else:
         expr = None
     return expr, filematcher
 
 def _logrevs(repo, opts):
     # Default --rev value depends on --follow but --follow behavior
     # depends on revisions resolved from --rev...
     follow = opts.get('follow') or opts.get('follow_first')
     if opts.get('rev'):
         revs = scmutil.revrange(repo, opts['rev'])
     elif follow and repo.dirstate.p1() == nullid:
         revs = smartset.baseset()
     elif follow:
         revs = repo.revs('reverse(:.)')
     else:
         revs = smartset.spanset(repo)
         revs.reverse()
     return revs
 
 def getgraphlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     limit = loglimit(opts)
     revs = _logrevs(repo, opts)
     if not revs:
         return smartset.baseset(), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if opts.get('rev'):
         # User-specified revs might be unsorted, but don't sort before
         # _makelogrevset because it might depend on the order of revs
         if not (revs.isdescending() or revs.istopo()):
             revs.sort(reverse=True)
     if expr:
         matcher = revset.match(repo.ui, expr)
         revs = matcher(repo, revs)
     if limit is not None:
         limitedrevs = []
         for idx, rev in enumerate(revs):
             if idx >= limit:
                 break
             limitedrevs.append(rev)
         revs = smartset.baseset(limitedrevs)
 
     return revs, expr, filematcher
 
 def getlogrevs(repo, pats, opts):
     """Return (revs, expr, filematcher) where revs is an iterable of
     revision numbers, expr is a revset string built from log options
     and file patterns or None, and used to filter 'revs'. If --stat or
     --patch are not passed filematcher is None. Otherwise it is a
     callable taking a revision number and returning a match objects
     filtering the files to be detailed when displaying the revision.
     """
     limit = loglimit(opts)
     revs = _logrevs(repo, opts)
     if not revs:
         return smartset.baseset([]), None, None
     expr, filematcher = _makelogrevset(repo, pats, opts, revs)
     if expr:
         matcher = revset.match(repo.ui, expr)
         revs = matcher(repo, revs)
     if limit is not None:
         limitedrevs = []
         for idx, r in enumerate(revs):
             if limit <= idx:
                 break
             limitedrevs.append(r)
         revs = smartset.baseset(limitedrevs)
 
     return revs, expr, filematcher
 
 def _graphnodeformatter(ui, displayer):
     spec = ui.config('ui', 'graphnodetemplate')
     if not spec:
         return templatekw.showgraphnode  # fast path for "{graphnode}"
 
     spec = templater.unquotestring(spec)
     templ = formatter.maketemplater(ui, spec)
     cache = {}
     if isinstance(displayer, changeset_templater):
         cache = displayer.cache  # reuse cache of slow templates
     props = templatekw.keywords.copy()
     props['templ'] = templ
     props['cache'] = cache
     def formatnode(repo, ctx):
         props['ctx'] = ctx
         props['repo'] = repo
         props['ui'] = repo.ui
         props['revcache'] = {}
         return templ.render(props)
     return formatnode
 
 def displaygraph(ui, repo, dag, displayer, edgefn, getrenamed=None,
                  filematcher=None, props=None):
     props = props or {}
     formatnode = _graphnodeformatter(ui, displayer)
     state = graphmod.asciistate()
     styles = state['styles']
 
     # only set graph styling if HGPLAIN is not set.
     if ui.plain('graph'):
         # set all edge styles to |, the default pre-3.8 behaviour
         styles.update(dict.fromkeys(styles, '|'))
     else:
         edgetypes = {
             'parent': graphmod.PARENT,
             'grandparent': graphmod.GRANDPARENT,
             'missing': graphmod.MISSINGPARENT
         }
         for name, key in edgetypes.items():
             # experimental config: experimental.graphstyle.*
             styles[key] = ui.config('experimental', 'graphstyle.%s' % name,
                                     styles[key])
             if not styles[key]:
                 styles[key] = None
 
         # experimental config: experimental.graphshorten
         state['graphshorten'] = ui.configbool('experimental', 'graphshorten')
 
     for rev, type, ctx, parents in dag:
         char = formatnode(repo, ctx)
         copies = None
         if getrenamed and ctx.rev():
             copies = []
             for fn in ctx.files():
                 rename = getrenamed(fn, ctx.rev())
                 if rename:
                     copies.append((fn, rename[0]))
         revmatchfn = None
         if filematcher is not None:
             revmatchfn = filematcher(ctx.rev())
         edges = edgefn(type, char, state, rev, parents)
         firstedge = next(edges)
         width = firstedge[2]
         displayer.show(ctx, copies=copies, matchfn=revmatchfn,
                        _graphwidth=width, **props)
         lines = displayer.hunk.pop(rev).split('\n')
         if not lines[-1]:
             del lines[-1]
         displayer.flush(ctx)
         for type, char, width, coldata in itertools.chain([firstedge], edges):
             graphmod.ascii(ui, state, type, char, lines, coldata)
             lines = []
     displayer.close()
 
 def graphlog(ui, repo, pats, opts):
     # Parameters are identical to log command ones
     revs, expr, filematcher = getgraphlogrevs(repo, pats, opts)
     revdag = graphmod.dagwalker(repo, revs)
 
     getrenamed = None
     if opts.get('copies'):
         endrev = None
         if opts.get('rev'):
             endrev = scmutil.revrange(repo, opts.get('rev')).max() + 1
         getrenamed = templatekw.getrenamedfn(repo, endrev=endrev)
 
     ui.pager('log')
     displayer = show_changeset(ui, repo, opts, buffered=True)
     displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges, getrenamed,
                  filematcher)
 
 def checkunsupportedgraphflags(pats, opts):
     for op in ["newest_first"]:
         if op in opts and opts[op]:
             raise error.Abort(_("-G/--graph option is incompatible with --%s")
                              % op.replace("_", "-"))
 
 def graphrevs(repo, nodes, opts):
     limit = loglimit(opts)
     nodes.reverse()
     if limit is not None:
         nodes = nodes[:limit]
     return graphmod.nodes(repo, nodes)
 
 def add(ui, repo, match, prefix, explicitonly, **opts):
     join = lambda f: os.path.join(prefix, f)
     bad = []
 
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
 
     badmatch = matchmod.badmatch(match, badfn)
     dirstate = repo.dirstate
     # We don't want to just call wctx.walk here, since it would return a lot of
     # clean files, which we aren't interested in and takes time.
-    for f in sorted(dirstate.walk(badmatch, sorted(wctx.substate),
-                                  True, False, full=False)):
+    for f in sorted(dirstate.walk(badmatch, subrepos=sorted(wctx.substate),
+                                  unknown=True, ignored=False, full=False)):
         exact = match.exact(f)
         if exact or not explicitonly and f not in wctx and repo.wvfs.lexists(f):
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(_('adding %s\n') % match.rel(f))
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             if opts.get(r'subrepos'):
                 bad.extend(sub.add(ui, submatch, prefix, False, **opts))
             else:
                 bad.extend(sub.add(ui, submatch, prefix, True, **opts))
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not opts.get(r'dry_run'):
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 def addwebdirpath(repo, serverpath, webconf):
     webconf[serverpath] = repo.root
     repo.ui.debug('adding %s = %s\n' % (serverpath, repo.root))
 
     for r in repo.revs('filelog("path:.hgsub")'):
         ctx = repo[r]
         for subpath in ctx.substate:
             ctx.sub(subpath).addwebdirpath(serverpath, webconf)
 
 def forget(ui, repo, match, prefix, explicitonly):
     join = lambda f: os.path.join(prefix, f)
     bad = []
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     wctx = repo[None]
     forgot = []
 
     s = repo.status(match=matchmod.badmatch(match, badfn), clean=True)
     forget = sorted(s.modified + s.added + s.deleted + s.clean)
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             subbad, subforgot = sub.forget(submatch, prefix)
             bad.extend([subpath + '/' + f for f in subbad])
             forgot.extend([subpath + '/' + f for f in subforgot])
         except error.LookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % join(subpath))
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not repo.wvfs.isdir(f):
                 if f not in forgot:
                     if repo.wvfs.exists(f):
                         # Don't complain if the exact case match wasn't given.
                         # But don't do this until after checking 'forgot', so
                         # that subrepo files aren't normalized, and this op is
                         # purely from data cached by the status walk above.
                         if repo.dirstate.normalize(f) in repo.dirstate:
                             continue
                         ui.warn(_('not removing %s: '
                                   'file is already untracked\n')
                                 % match.rel(f))
                     bad.append(f)
 
     for f in forget:
         if ui.verbose or not match.exact(f):
             ui.status(_('removing %s\n') % match.rel(f))
 
     rejected = wctx.forget(forget, prefix)
     bad.extend(f for f in rejected if f in match.files())
     forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 def files(ui, ctx, m, fm, fmt, subrepos):
     rev = ctx.rev()
     ret = 1
     ds = ctx.repo().dirstate
 
     for f in ctx.matches(m):
         if rev is None and ds[f] == 'r':
             continue
         fm.startitem()
         if ui.verbose:
             fc = ctx[f]
             fm.write('size flags', '% 10d % 1s ', fc.size(), fc.flags())
         fm.data(abspath=f)
         fm.write('path', fmt, m.rel(f))
         ret = 0
 
     for subpath in sorted(ctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         if (subrepos or m.exact(subpath) or any(submatch.files())):
             sub = ctx.sub(subpath)
             try:
                 recurse = m.exact(subpath) or subrepos
                 if sub.printfiles(ui, submatch, fm, fmt, recurse) == 0:
                     ret = 0
             except error.LookupError:
                 ui.status(_("skipping missing subrepository: %s\n")
                                % m.abs(subpath))
 
     return ret
 
 def remove(ui, repo, m, prefix, after, force, subrepos, warnings=None):
     join = lambda f: os.path.join(prefix, f)
     ret = 0
     s = repo.status(match=m, clean=True)
     modified, added, deleted, clean = s[0], s[1], s[3], s[6]
 
     wctx = repo[None]
 
     if warnings is None:
         warnings = []
         warn = True
     else:
         warn = False
 
     subs = sorted(wctx.substate)
     total = len(subs)
     count = 0
     for subpath in subs:
         count += 1
         submatch = matchmod.subdirmatcher(subpath, m)
         if subrepos or m.exact(subpath) or any(submatch.files()):
             ui.progress(_('searching'), count, total=total, unit=_('subrepos'))
             sub = wctx.sub(subpath)
             try:
                 if sub.removefiles(submatch, prefix, after, force, subrepos,
                                    warnings):
                     ret = 1
             except error.LookupError:
                 warnings.append(_("skipping missing subrepository: %s\n")
                                % join(subpath))
     ui.progress(_('searching'), None)
 
     # warn about failure to delete explicit files/dirs
     deleteddirs = util.dirs(deleted)
     files = m.files()
     total = len(files)
     count = 0
     for f in files:
         def insubrepo():
             for subpath in wctx.substate:
                 if f.startswith(subpath + '/'):
                     return True
             return False
 
         count += 1
         ui.progress(_('deleting'), count, total=total, unit=_('files'))
         isdir = f in deleteddirs or wctx.hasdir(f)
         if (f in repo.dirstate or isdir or f == '.'
             or insubrepo() or f in subs):
             continue
 
         if repo.wvfs.exists(f):
             if repo.wvfs.isdir(f):
                 warnings.append(_('not removing %s: no tracked files\n')
                         % m.rel(f))
             else:
                 warnings.append(_('not removing %s: file is untracked\n')
                         % m.rel(f))
         # missing files will generate a warning elsewhere
         ret = 1
     ui.progress(_('deleting'), None)
 
     if force:
         list = modified + deleted + clean + added
     elif after:
         list = deleted
         remaining = modified + added + clean
         total = len(remaining)
         count = 0
         for f in remaining:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_('not removing %s: file still exists\n')
                     % m.rel(f))
             ret = 1
         ui.progress(_('skipping'), None)
     else:
         list = deleted + clean
         total = len(modified) + len(added)
         count = 0
         for f in modified:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_('not removing %s: file is modified (use -f'
                       ' to force removal)\n') % m.rel(f))
             ret = 1
         for f in added:
             count += 1
             ui.progress(_('skipping'), count, total=total, unit=_('files'))
             warnings.append(_("not removing %s: file has been marked for add"
                       " (use 'hg forget' to undo add)\n") % m.rel(f))
             ret = 1
         ui.progress(_('skipping'), None)
 
     list = sorted(list)
     total = len(list)
     count = 0
     for f in list:
         count += 1
         if ui.verbose or not m.exact(f):
             ui.progress(_('deleting'), count, total=total, unit=_('files'))
             ui.status(_('removing %s\n') % m.rel(f))
     ui.progress(_('deleting'), None)
 
     with repo.wlock():
         if not after:
             for f in list:
                 if f in added:
                     continue # we never unlink added files on remove
                 repo.wvfs.unlinkpath(f, ignoremissing=True)
         repo[None].forget(list)
 
     if warn:
         for warning in warnings:
             ui.warn(warning)
 
     return ret
 
 def cat(ui, repo, ctx, matcher, basefm, fntemplate, prefix, **opts):
     err = 1
 
     def write(path):
         filename = None
         if fntemplate:
             filename = makefilename(repo, fntemplate, ctx.node(),
                                     pathname=os.path.join(prefix, path))
         with formatter.maybereopen(basefm, filename, opts) as fm:
             data = ctx[path].data()
             if opts.get('decode'):
                 data = repo.wwritedata(path, data)
             fm.startitem()
             fm.write('data', '%s', data)
             fm.data(abspath=path, path=matcher.rel(path))
 
     # Automation often uses hg cat on single files, so special case it
     # for performance to avoid the cost of parsing the manifest.
     if len(matcher.files()) == 1 and not matcher.anypats():
         file = matcher.files()[0]
         mfl = repo.manifestlog
         mfnode = ctx.manifestnode()
         try:
             if mfnode and mfl[mfnode].find(file)[0]:
                 write(file)
                 return 0
         except KeyError:
             pass
 
     for abs in ctx.walk(matcher):
         write(abs)
         err = 0
 
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, matcher)
 
             if not sub.cat(submatch, basefm, fntemplate,
                            os.path.join(prefix, sub._path), **opts):
                 err = 0
         except error.RepoLookupError:
             ui.status(_("skipping missing subrepository: %s\n")
                            % os.path.join(prefix, subpath))
 
     return err
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
     message = logmessage(ui, opts)
     matcher = scmutil.match(repo[None], pats, opts)
 
     dsguard = None
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         dsguard = dirstateguard.dirstateguard(repo, 'commit')
     with dsguard or util.nullcontextmanager():
         if dsguard:
             if scmutil.addremove(repo, matcher, "", opts) != 0:
                 raise error.Abort(
                     _("failed to mark all new/missing files as added/removed"))
 
         return commitfunc(ui, repo, message, matcher, opts)
 
 def samefile(f, ctx1, ctx2):
     if f in ctx1.manifest():
         a = ctx1.filectx(f)
         if f in ctx2.manifest():
             b = ctx2.filectx(f)
             return (not a.cmp(b)
                     and a.flags() == b.flags())
         else:
             return False
     else:
         return f not in ctx2.manifest()
 
 def amend(ui, repo, old, extra, pats, opts):
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     # amend will reuse the existing user if not specified, but the obsolete
     # marker creation requires that the current user's name is specified.
     if obsolete.isenabled(repo, obsolete.createmarkersopt):
         ui.username() # raise exception if username not set
 
     ui.note(_('amending changeset %s\n') % old)
     base = old.p1()
 
     with repo.wlock(), repo.lock(), repo.transaction('amend'):
         # Participating changesets:
         #
         # wctx     o - workingctx that contains changes from working copy
         #          |   to go into amending commit
         #          |
         # old      o - changeset to amend
         #          |
         # base     o - first parent of the changeset to amend
         wctx = repo[None]
 
         # Update extra dict from amended commit (e.g. to preserve graft
         # source)
         extra.update(old.extra())
 
         # Also update it from the from the wctx
         extra.update(wctx.extra())
 
         user = opts.get('user') or old.user()
         date = opts.get('date') or old.date()
 
         # Parse the date to allow comparison between date and old.date()
         date = util.parsedate(date)
 
         if len(old.parents()) > 1:
             # ctx.files() isn't reliable for merges, so fall back to the
             # slower repo.status() method
             files = set([fn for st in repo.status(base, old)[:3]
                          for fn in st])
         else:
             files = set(old.files())
 
         # add/remove the files to the working copy if the "addremove" option
         # was specified.
         matcher = scmutil.match(wctx, pats, opts)
         if (opts.get('addremove')
             and scmutil.addremove(repo, matcher, "", opts)):
             raise error.Abort(
                 _("failed to mark all new/missing files as added/removed"))
 
         filestoamend = set(f for f in wctx.files() if matcher(f))
 
         changes = (len(filestoamend) > 0)
         if changes:
             # Recompute copies (avoid recording a -> b -> a)
             copied = copies.pathcopies(base, wctx, matcher)
             if old.p2:
                 copied.update(copies.pathcopies(old.p2(), wctx, matcher))
 
             # Prune files which were reverted by the updates: if old
             # introduced file X and the file was renamed in the working
             # copy, then those two files are the same and
             # we can discard X from our list of files. Likewise if X
             # was deleted, it's no longer relevant
             files.update(filestoamend)
             files = [f for f in files if not samefile(f, wctx, base)]
 
             def filectxfn(repo, ctx_, path):
                 try:
                     # If the file being considered is not amongst the files
                     # to be amended, we should return the file context from the
                     # old changeset. This avoids issues when only some files in
                     # the working copy are being amended but there are also
                     # changes to other files from the old changeset.
                     if path not in filestoamend:
                         return old.filectx(path)
 
                     fctx = wctx[path]
 
                     # Return None for removed files.
                     if not fctx.exists():
                         return None
 
                     flags = fctx.flags()
                     mctx = context.memfilectx(repo,
                                               fctx.path(), fctx.data(),
                                               islink='l' in flags,
                                               isexec='x' in flags,
                                               copied=copied.get(path))
                     return mctx
                 except KeyError:
                     return None
         else:
             ui.note(_('copying changeset %s to %s\n') % (old, base))
 
             # Use version of files as in the old cset
             def filectxfn(repo, ctx_, path):
                 try:
                     return old.filectx(path)
                 except KeyError:
                     return None
 
         # See if we got a message from -m or -l, if not, open the editor with
         # the message of the changeset to amend.
         message = logmessage(ui, opts)
 
         editform = mergeeditform(old, 'commit.amend')
         editor = getcommiteditor(editform=editform,
                                  **pycompat.strkwargs(opts))
 
         if not message:
             editor = getcommiteditor(edit=True, editform=editform)
             message = old.description()
 
         pureextra = extra.copy()
         extra['amend_source'] = old.hex()
 
         new = context.memctx(repo,
                              parents=[base.node(), old.p2().node()],
                              text=message,
                              files=files,
                              filectxfn=filectxfn,
                              user=user,
                              date=date,
                              extra=extra,
                              editor=editor)
 
         newdesc = changelog.stripdesc(new.description())
         if ((not changes)
             and newdesc == old.description()
             and user == old.user()
             and date == old.date()
             and pureextra == old.extra()):
             # nothing changed. continuing here would create a new node
             # anyway because of the amend_source noise.
             #
             # This not what we expect from amend.
             return old.node()
 
         if opts.get('secret'):
             commitphase = 'secret'
         else:
             commitphase = old.phase()
         overrides = {('phases', 'new-commit'): commitphase}
         with ui.configoverride(overrides, 'amend'):
             newid = repo.commitctx(new)
 
         # Reroute the working copy parent to the new changeset
         repo.setparents(newid, nullid)
         mapping = {old.node(): (newid,)}
         scmutil.cleanupnodes(repo, mapping, 'amend')
 
         # Fixing the dirstate because localrepo.commitctx does not update
         # it. This is rather convenient because we did not need to update
         # the dirstate for all the files in the new commit which commitctx
         # could have done if it updated the dirstate. Now, we can
         # selectively update the dirstate only for the amended files.
         dirstate = repo.dirstate
 
         # Update the state of the files which were added and
         # and modified in the amend to "normal" in the dirstate.
         normalfiles = set(wctx.modified() + wctx.added()) & filestoamend
         for f in normalfiles:
             dirstate.normal(f)
 
         # Update the state of files which were removed in the amend
         # to "removed" in the dirstate.
         removedfiles = set(wctx.removed()) & filestoamend
         for f in removedfiles:
             dirstate.drop(f)
 
     return newid
 
 def commiteditor(repo, ctx, subs, editform=''):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(repo, ctx, subs, editform=editform,
                              unchangedmessagedetection=True)
 
 def commitforceeditor(repo, ctx, subs, finishdesc=None, extramsg=None,
                       editform='', unchangedmessagedetection=False):
     if not extramsg:
         extramsg = _("Leave message empty to abort commit.")
 
     forms = [e for e in editform.split('.') if e]
     forms.insert(0, 'changeset')
     templatetext = None
     while forms:
         ref = '.'.join(forms)
         if repo.ui.config('committemplate', ref):
             templatetext = committext = buildcommittemplate(
                 repo, ctx, subs, extramsg, ref)
             break
         forms.pop()
     else:
         committext = buildcommittext(repo, ctx, subs, extramsg)
 
     # run editor in the repository root
     olddir = pycompat.getcwd()
     os.chdir(repo.root)
 
     # make in-memory changes visible to external process
     tr = repo.currenttransaction()
     repo.dirstate.write(tr)
     pending = tr and tr.writepending() and repo.root
 
     editortext = repo.ui.edit(committext, ctx.user(), ctx.extra(),
                               editform=editform, pending=pending,
                               repopath=repo.path, action='commit')
     text = editortext
 
     # strip away anything below this special string (used for editors that want
     # to display the diff)
     stripbelow = re.search(_linebelow, text, flags=re.MULTILINE)
     if stripbelow:
         text = text[:stripbelow.start()]
 
     text = re.sub("(?m)^HG:.*(\n|$)", "", text)
     os.chdir(olddir)
 
     if finishdesc:
         text = finishdesc(text)
     if not text.strip():
         raise error.Abort(_("empty commit message"))
     if unchangedmessagedetection and editortext == templatetext:
         raise error.Abort(_("commit message unchanged"))
 
     return text
 
 def buildcommittemplate(repo, ctx, subs, extramsg, ref):
     ui = repo.ui
     spec = formatter.templatespec(ref, None, None)
     t = changeset_templater(ui, repo, spec, None, {}, False)
     t.t.cache.update((k, templater.unquotestring(v))
                      for k, v in repo.ui.configitems('committemplate'))
 
     if not extramsg:
         extramsg = '' # ensure that extramsg is string
 
     ui.pushbuffer()
     t.show(ctx, extramsg=extramsg)
     return ui.popbuffer()
 
 def hgprefix(msg):
     return "\n".join(["HG: %s" % a for a in msg.split("\n") if a])
 
 def buildcommittext(repo, ctx, subs, extramsg):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append("")
     edittext.append("") # Empty line between message and comments.
     edittext.append(hgprefix(_("Enter commit message."
                       "  Lines beginning with 'HG:' are removed.")))
     edittext.append(hgprefix(extramsg))
     edittext.append("HG: --")
     edittext.append(hgprefix(_("user: %s") % ctx.user()))
     if ctx.p2():
         edittext.append(hgprefix(_("branch merge")))
     if ctx.branch():
         edittext.append(hgprefix(_("branch '%s'") % ctx.branch()))
     if bookmarks.isactivewdirparent(repo):
         edittext.append(hgprefix(_("bookmark '%s'") % repo._activebookmark))
     edittext.extend([hgprefix(_("subrepo %s") % s) for s in subs])
     edittext.extend([hgprefix(_("added %s") % f) for f in added])
     edittext.extend([hgprefix(_("changed %s") % f) for f in modified])
     edittext.extend([hgprefix(_("removed %s") % f) for f in removed])
     if not added and not modified and not removed:
         edittext.append(hgprefix(_("no files changed")))
     edittext.append("")
 
     return "\n".join(edittext)
 
 def commitstatus(repo, node, branch, bheads=None, opts=None):
     if opts is None:
         opts = {}
     ctx = repo[node]
     parents = ctx.parents()
 
     if (not opts.get('amend') and bheads and node not in bheads and not
         [x for x in parents if x.node() in bheads and x.branch() == branch]):
         repo.ui.status(_('created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get('close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(_('reopening closed branch head %d\n') % r)
 
     if repo.ui.debugflag:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx.hex()))
     elif repo.ui.verbose:
         repo.ui.write(_('committed changeset %d:%s\n') % (int(ctx), ctx))
 
 def postcommitstatus(repo, pats, opts):
     return repo.status(match=scmutil.match(repo[None], pats, opts))
 
 def revert(ui, repo, ctx, parents, *pats, **opts):
     parent, p2 = parents
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == p2:
         parent = p2
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other. in both cases, filesets should be evaluated against
     # workingctx to get consistent result (issue4497). this means 'set:**'
     # cannot be used to select missing files from target rev.
 
     # `names` is a mapping for all elements in working copy and target revision
     # The mapping is in the form:
     #   <asb path in repo> -> (<path from CWD>, <exactly specified by matcher?>)
     names = {}
 
     with repo.wlock():
         ## filling of the `names` mapping
         # walk dirstate to fill `names`
 
         interactive = opts.get('interactive', False)
         wctx = repo[None]
         m = scmutil.match(wctx, pats, opts)
 
         # we'll need this later
         targetsubs = sorted(s for s in wctx.substate if m(s))
 
         if not m.always():
             matcher = matchmod.badmatch(m, lambda x, y: False)
             for abs in wctx.walk(matcher):
                 names[abs] = m.rel(abs), m.exact(abs)
 
             # walk target manifest to fill `names`
 
             def badfn(path, msg):
                 if path in names:
                     return
                 if path in ctx.substate:
                     return
                 path_ = path + '/'
                 for f in names:
                     if f.startswith(path_):
                         return
                 ui.warn("%s: %s\n" % (m.rel(path), msg))
 
             for abs in ctx.walk(matchmod.badmatch(m, badfn)):
                 if abs not in names:
                     names[abs] = m.rel(abs), m.exact(abs)
 
             # Find status of all file in `names`.
             m = scmutil.matchfiles(repo, names)
 
             changes = repo.status(node1=node, match=m,
                                   unknown=True, ignored=True, clean=True)
         else:
             changes = repo.status(node1=node, match=m)
             for kind in changes:
                 for abs in kind:
                     names[abs] = m.rel(abs), m.exact(abs)
 
             m = scmutil.matchfiles(repo, names)
 
         modified = set(changes.modified)
         added    = set(changes.added)
         removed  = set(changes.removed)
         _deleted = set(changes.deleted)
         unknown  = set(changes.unknown)
         unknown.update(changes.ignored)
         clean    = set(changes.clean)
         modadded = set()
 
         # We need to account for the state of the file in the dirstate,
         # even when we revert against something else than parent. This will
         # slightly alter the behavior of revert (doing back up or not, delete
         # or just forget etc).
         if parent == node:
             dsmodified = modified
             dsadded = added
             dsremoved = removed
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
             modified, added, removed = set(), set(), set()
         else:
             changes = repo.status(node1=parent, match=m)
             dsmodified = set(changes.modified)
             dsadded    = set(changes.added)
             dsremoved  = set(changes.removed)
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
 
             # only take into account for removes between wc and target
             clean |= dsremoved - removed
             dsremoved &= removed
             # distinct between dirstate remove and other
             removed -= dsremoved
 
             modadded = added & dsmodified
             added -= modadded
 
             # tell newly modified apart.
             dsmodified &= modified
             dsmodified |= modified & dsadded # dirstate added may need backup
             modified -= dsmodified
 
             # We need to wait for some post-processing to update this set
             # before making the distinction. The dirstate will be used for
             # that purpose.
             dsadded = added
 
         # in case of merge, files that are actually added can be reported as
         # modified, we need to post process the result
         if p2 != nullid:
             mergeadd = set(dsmodified)
             for path in dsmodified:
                 if path in mf:
                     mergeadd.remove(path)
             dsadded |= mergeadd
             dsmodified -= mergeadd
 
         # if f is a rename, update `names` to also revert the source
         cwd = repo.getcwd()
         for f in localchanges:
             src = repo.dirstate.copied(f)
             # XXX should we check for rename down to target node?
             if src and src not in names and repo.dirstate[src] == 'r':
                 dsremoved.add(src)
                 names[src] = (repo.pathto(src, cwd), True)
 
         # determine the exact nature of the deleted changesets
         deladded = set(_deleted)
         for path in _deleted:
             if path in mf:
                 deladded.remove(path)
         deleted = _deleted - deladded
 
         # distinguish between file to forget and the other
         added = set()
         for abs in dsadded:
             if repo.dirstate[abs] != 'a':
                 added.add(abs)
         dsadded -= added
 
         for abs in deladded:
             if repo.dirstate[abs] == 'a':
                 dsadded.add(abs)
         deladded -= dsadded
 
         # For files marked as removed, we check if an unknown file is present at
         # the same path. If a such file exists it may need to be backed up.
         # Making the distinction at this stage helps have simpler backup
         # logic.
         removunk = set()
         for abs in removed:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 removunk.add(abs)
         removed -= removunk
 
         dsremovunk = set()
         for abs in dsremoved:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 dsremovunk.add(abs)
         dsremoved -= dsremovunk
 
         # action to be actually performed by revert
         # (<list of file>, message>) tuple
         actions = {'revert': ([], _('reverting %s\n')),
                    'add': ([], _('adding %s\n')),
                    'remove': ([], _('removing %s\n')),
                    'drop': ([], _('removing %s\n')),
                    'forget': ([], _('forgetting %s\n')),
                    'undelete': ([], _('undeleting %s\n')),
                    'noop': (None, _('no changes needed to %s\n')),
                    'unknown': (None, _('file not managed: %s\n')),
                   }
 
         # "constant" that convey the backup strategy.
         # All set to `discard` if `no-backup` is set do avoid checking
         # no_backup lower in the code.
         # These values are ordered for comparison purposes
         backupinteractive = 3 # do backup if interactively modified
         backup = 2  # unconditionally do backup
         check = 1   # check if the existing file differs from target
         discard = 0 # never do backup
         if opts.get('no_backup'):
             backupinteractive = backup = check = discard
         if interactive:
             dsmodifiedbackup = backupinteractive
         else:
             dsmodifiedbackup = backup
         tobackup = set()
 
         backupanddel = actions['remove']
         if not opts.get('no_backup'):
             backupanddel = actions['drop']
 
         disptable = (
             # dispatch table:
             #   file state
             #   action
             #   make backup
 
             ## Sets that results that will change file on disk
             # Modified compared to target, no local change
             (modified,      actions['revert'],   discard),
             # Modified compared to target, but local file is deleted
             (deleted,       actions['revert'],   discard),
             # Modified compared to target, local change
             (dsmodified,    actions['revert'],   dsmodifiedbackup),
             # Added since target
             (added,         actions['remove'],   discard),
             # Added in working directory
             (dsadded,       actions['forget'],   discard),
             # Added since target, have local modification
             (modadded,      backupanddel,        backup),
             # Added since target but file is missing in working directory
             (deladded,      actions['drop'],   discard),
             # Removed since  target, before working copy parent
             (removed,       actions['add'],      discard),
             # Same as `removed` but an unknown file exists at the same path
             (removunk,      actions['add'],      check),
             # Removed since targe, marked as such in working copy parent
             (dsremoved,     actions['undelete'], discard),
             # Same as `dsremoved` but an unknown file exists at the same path
             (dsremovunk,    actions['undelete'], check),
             ## the following sets does not result in any file changes
             # File with no modification
             (clean,         actions['noop'],     discard),
             # Existing file, not tracked anywhere
             (unknown,       actions['unknown'],  discard),
             )
 
         for abs, (rel, exact) in sorted(names.items()):
             # target file to be touch on disk (relative to cwd)
             target = repo.wjoin(abs)
             # search the entry in the dispatch table.
             # if the file is in any of these sets, it was touched in the working
             # directory parent and we are sure it needs to be reverted.
             for table, (xlist, msg), dobackup in disptable:
                 if abs not in table:
                     continue
                 if xlist is not None:
                     xlist.append(abs)
                     if dobackup:
                         # If in interactive mode, don't automatically create
                         # .orig files (issue4793)
                         if dobackup == backupinteractive:
                             tobackup.add(abs)
                         elif (backup <= dobackup or wctx[abs].cmp(ctx[abs])):
                             bakname = scmutil.origpath(ui, repo, rel)
                             ui.note(_('saving current version of %s as %s\n') %
                                     (rel, bakname))
                             if not opts.get('dry_run'):
                                 if interactive:
                                     util.copyfile(target, bakname)
                                 else:
                                     util.rename(target, bakname)
                     if ui.verbose or not exact:
                         if not isinstance(msg, basestring):
                             msg = msg(abs)
                         ui.status(msg % rel)
                 elif exact:
                     ui.warn(msg % rel)
                 break
 
         if not opts.get('dry_run'):
             needdata = ('revert', 'add', 'undelete')
             _revertprefetch(repo, ctx, *[actions[name][0] for name in needdata])
             _performrevert(repo, parents, ctx, actions, interactive, tobackup)
 
         if targetsubs:
             # Revert the subrepos on the revert list
             for sub in targetsubs:
                 try:
                     wctx.sub(sub).revert(ctx.substate[sub], *pats, **opts)
                 except KeyError:
                     raise error.Abort("subrepository '%s' does not exist in %s!"
                                       % (sub, short(ctx.node())))
 
 def _revertprefetch(repo, ctx, *files):
     """Let extension changing the storage layer prefetch content"""
     pass
 
 def _performrevert(repo, parents, ctx, actions, interactive=False,
                    tobackup=None):
     """function that actually perform all the actions computed for revert
 
     This is an independent function to let extension to plug in and react to
     the imminent revert.
 
     Make sure you have the working directory locked when calling this function.
     """
     parent, p2 = parents
     node = ctx.node()
     excluded_files = []
     matcher_opts = {"exclude": excluded_files}
 
     def checkout(f):
         fc = ctx[f]
         repo.wwrite(f, fc.data(), fc.flags())
 
     def doremove(f):
         try:
             repo.wvfs.unlinkpath(f)
         except OSError:
             pass
         repo.dirstate.remove(f)
 
     audit_path = pathutil.pathauditor(repo.root, cached=True)
     for f in actions['forget'][0]:
         if interactive:
             choice = repo.ui.promptchoice(
                 _("forget added file %s (Yn)?$$ &Yes $$ &No") % f)
             if choice == 0:
                 repo.dirstate.drop(f)
             else:
                 excluded_files.append(repo.wjoin(f))
         else:
             repo.dirstate.drop(f)
     for f in actions['remove'][0]:
         audit_path(f)
         if interactive:
             choice = repo.ui.promptchoice(
                 _("remove added file %s (Yn)?$$ &Yes $$ &No") % f)
             if choice == 0:
                 doremove(f)
             else:
                 excluded_files.append(repo.wjoin(f))
         else:
             doremove(f)
     for f in actions['drop'][0]:
         audit_path(f)
         repo.dirstate.remove(f)
 
     normal = None
     if node == parent:
         # We're reverting to our parent. If possible, we'd like status
         # to report the file as clean. We have to use normallookup for
         # merges to avoid losing information about merged/dirty files.
         if p2 != nullid:
             normal = repo.dirstate.normallookup
         else:
             normal = repo.dirstate.normal
 
     newlyaddedandmodifiedfiles = set()
     if interactive:
         # Prompt the user for changes to revert
         torevert = [repo.wjoin(f) for f in actions['revert'][0]]
         m = scmutil.match(ctx, torevert, matcher_opts)
         diffopts = patch.difffeatureopts(repo.ui, whitespace=True)
         diffopts.nodates = True
         diffopts.git = True
         operation = 'discard'
         reversehunks = True
         if node != parent:
             operation = 'revert'
             reversehunks = repo.ui.configbool('experimental',
                 'revertalternateinteractivemode')
         if reversehunks:
             diff = patch.diff(repo, ctx.node(), None, m, opts=diffopts)
         else:
             diff = patch.diff(repo, None, ctx.node(), m, opts=diffopts)
         originalchunks = patch.parsepatch(diff)
 
         try:
 
             chunks, opts = recordfilter(repo.ui, originalchunks,
                                         operation=operation)
             if reversehunks:
                 chunks = patch.reversehunks(chunks)
 
         except error.PatchError as err:
             raise error.Abort(_('error parsing patch: %s') % err)
 
         newlyaddedandmodifiedfiles = newandmodified(chunks, originalchunks)
         if tobackup is None:
             tobackup = set()
         # Apply changes
         fp = stringio()
         for c in chunks:
             # Create a backup file only if this hunk should be backed up
             if ishunk(c) and c.header.filename() in tobackup:
                 abs = c.header.filename()
                 target = repo.wjoin(abs)
                 bakname = scmutil.origpath(repo.ui, repo, m.rel(abs))
                 util.copyfile(target, bakname)
                 tobackup.remove(abs)
             c.write(fp)
         dopatch = fp.tell()
         fp.seek(0)
         if dopatch:
             try:
                 patch.internalpatch(repo.ui, repo, fp, 1, eolmode=None)
             except error.PatchError as err:
                 raise error.Abort(str(err))
         del fp
     else:
         for f in actions['revert'][0]:
             checkout(f)
             if normal:
                 normal(f)
 
     for f in actions['add'][0]:
         # Don't checkout modified files, they are already created by the diff
         if f not in newlyaddedandmodifiedfiles:
             checkout(f)
             repo.dirstate.add(f)
 
     normal = repo.dirstate.normallookup
     if node == parent and p2 == nullid:
         normal = repo.dirstate.normal
     for f in actions['undelete'][0]:
         checkout(f)
         normal(f)
 
     copied = copies.pathcopies(repo[parent], ctx)
 
     for f in actions['add'][0] + actions['undelete'][0] + actions['revert'][0]:
         if f in copied:
             repo.dirstate.copy(copied[f], f)
 
 class command(registrar.command):
     def _doregister(self, func, name, *args, **kwargs):
         func._deprecatedregistrar = True  # flag for deprecwarn in extensions.py
         return super(command, self)._doregister(func, name, *args, **kwargs)
 
 # a list of (ui, repo, otherpeer, opts, missing) functions called by
 # commands.outgoing.  "missing" is "missing" of the result of
 # "findcommonoutgoing()"
 outgoinghooks = util.hooks()
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # a list of (ui, repo, opts, changes) functions called by commands.summary.
 #
 # functions should return tuple of booleans below, if 'changes' is None:
 #  (whether-incomings-are-needed, whether-outgoings-are-needed)
 #
 # otherwise, 'changes' is a tuple of tuples below:
 #  - (sourceurl, sourcebranch, sourcepeer, incoming)
 #  - (desturl,   destbranch,   destpeer,   outgoing)
 summaryremotehooks = util.hooks()
 
 # A list of state files kept by multistep operations like graft.
 # Since graft cannot be aborted, it is considered 'clearable' by update.
 # note: bisect is intentionally excluded
 # (state file, clearable, allowcommit, error, hint)
 unfinishedstates = [
     ('graftstate', True, False, _('graft in progress'),
      _("use 'hg graft --continue' or 'hg update' to abort")),
     ('updatestate', True, False, _('last update was interrupted'),
      _("use 'hg update' to get a consistent checkout"))
     ]
 
 def checkunfinished(repo, commit=False):
     '''Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if commit and allowcommit:
             continue
         if repo.vfs.exists(f):
             raise error.Abort(msg, hint=hint)
 
 def clearunfinished(repo):
     '''Check for unfinished operations (as above), and clear the ones
     that are clearable.
     '''
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if not clearable and repo.vfs.exists(f):
             raise error.Abort(msg, hint=hint)
     for f, clearable, allowcommit, msg, hint in unfinishedstates:
         if clearable and repo.vfs.exists(f):
             util.unlink(repo.vfs.join(f))
 
 afterresolvedstates = [
     ('graftstate',
      _('hg graft --continue')),
     ]
 
 def howtocontinue(repo):
     '''Check for an unfinished operation and return the command to finish
     it.
 
     afterresolvedstates tuples define a .hg/{file} and the corresponding
     command needed to finish it.
 
     Returns a (msg, warning) tuple. 'msg' is a string and 'warning' is
     a boolean.
     '''
     contmsg = _("continue: %s")
     for f, msg in afterresolvedstates:
         if repo.vfs.exists(f):
             return contmsg % msg, True
     if repo[None].dirty(missing=True, merge=False, branch=False):
         return contmsg % _("hg commit"), False
     return None, None
 
 def checkafterresolved(repo):
     '''Inform the user about the next action after completing hg resolve
 
     If there's a matching afterresolvedstates, howtocontinue will yield
     repo.ui.warn as the reporter.
 
     Otherwise, it will yield repo.ui.note.
     '''
     msg, warning = howtocontinue(repo)
     if msg is not None:
         if warning:
             repo.ui.warn("%s\n" % msg)
         else:
             repo.ui.note("%s\n" % msg)
 
 def wrongtooltocontinue(repo, task):
     '''Raise an abort suggesting how to properly continue if there is an
     active task.
 
     Uses howtocontinue() to find the active task.
 
     If there's no task (repo.ui.note for 'hg commit'), it does not offer
     a hint.
     '''
     after = howtocontinue(repo)
     hint = None
     if after[1]:
         hint = after[0]
     raise error.Abort(_('no %s in progress') % task, hint=hint)

mercurial/context.py

@@ -1,2606 +1,2607 b''
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import os
 import re
 import stat
 
 from .i18n import _
 from .node import (
     addednodeid,
     bin,
     hex,
     modifiednodeid,
     nullid,
     nullrev,
     short,
     wdirid,
     wdirnodes,
     wdirrev,
 )
 from . import (
     encoding,
     error,
     fileset,
     match as matchmod,
     mdiff,
     obsolete as obsmod,
     patch,
     pathutil,
     phases,
     pycompat,
     repoview,
     revlog,
     scmutil,
     sparse,
     subrepo,
     util,
 )
 
 propertycache = util.propertycache
 
 nonascii = re.compile(r'[^\x21-\x7f]').search
 
 class basectx(object):
     """A basectx object represents the common logic for its children:
     changectx: read-only context that is already present in the repo,
     workingctx: a context that represents the working directory and can
                 be committed,
     memctx: a context that represents changes in-memory and can also
             be committed."""
     def __new__(cls, repo, changeid='', *args, **kwargs):
         if isinstance(changeid, basectx):
             return changeid
 
         o = super(basectx, cls).__new__(cls)
 
         o._repo = repo
         o._rev = nullrev
         o._node = nullid
 
         return o
 
     def __bytes__(self):
         return short(self.node())
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __int__(self):
         return self.rev()
 
     def __repr__(self):
         return r"<%s %s>" % (type(self).__name__, str(self))
 
     def __eq__(self, other):
         try:
             return type(self) == type(other) and self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         return iter(self._manifest)
 
     def _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results, if this is
         a working copy context. For non-working copy contexts, it just returns
         the normal manifest."""
         return self.manifest()
 
     def _matchstatus(self, other, match):
         """This internal method provides a way for child objects to override the
         match operator.
         """
         return match
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context"""
         # Load earliest manifest first for caching reasons. More specifically,
         # if you have revisions 1000 and 1001, 1001 is probably stored as a
         # delta against 1000. Thus, if you read 1000 first, we'll reconstruct
         # 1000 and cache it so that when you read 1001, we just need to apply a
         # delta to what's in the cache. So that's one full reconstruction + one
         # delta application.
         mf2 = None
         if self.rev() is not None and self.rev() < other.rev():
             mf2 = self._buildstatusmanifest(s)
         mf1 = other._buildstatusmanifest(s)
         if mf2 is None:
             mf2 = self._buildstatusmanifest(s)
 
         modified, added = [], []
         removed = []
         clean = []
         deleted, unknown, ignored = s.deleted, s.unknown, s.ignored
         deletedset = set(deleted)
         d = mf1.diff(mf2, match=match, clean=listclean)
         for fn, value in d.iteritems():
             if fn in deletedset:
                 continue
             if value is None:
                 clean.append(fn)
                 continue
             (node1, flag1), (node2, flag2) = value
             if node1 is None:
                 added.append(fn)
             elif node2 is None:
                 removed.append(fn)
             elif flag1 != flag2:
                 modified.append(fn)
             elif node2 not in wdirnodes:
                 # When comparing files between two commits, we save time by
                 # not comparing the file contents when the nodeids differ.
                 # Note that this means we incorrectly report a reverted change
                 # to a file as a modification.
                 modified.append(fn)
             elif self[fn].cmp(other[fn]):
                 modified.append(fn)
             else:
                 clean.append(fn)
 
         if removed:
             # need to filter files if they are already reported as removed
             unknown = [fn for fn in unknown if fn not in mf1 and
                                                (not match or match(fn))]
             ignored = [fn for fn in ignored if fn not in mf1 and
                                                (not match or match(fn))]
             # if they're deleted, don't report them as removed
             removed = [fn for fn in removed if fn not in deletedset]
 
         return scmutil.status(modified, added, removed, deleted, unknown,
                               ignored, clean)
 
     @propertycache
     def substate(self):
         return subrepo.state(self, self._repo.ui)
 
     def subrev(self, subpath):
         return self.substate[subpath][1]
 
     def rev(self):
         return self._rev
     def node(self):
         return self._node
     def hex(self):
         return hex(self.node())
     def manifest(self):
         return self._manifest
     def manifestctx(self):
         return self._manifestctx
     def repo(self):
         return self._repo
     def phasestr(self):
         return phases.phasenames[self.phase()]
     def mutable(self):
         return self.phase() > phases.public
 
     def getfileset(self, expr):
         return fileset.getfileset(self, expr)
 
     def obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, 'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, 'extinct')
 
     def unstable(self):
         msg = ("'context.unstable' is deprecated, "
                "use 'context.orphan'")
         self._repo.ui.deprecwarn(msg, '4.4')
         return self.orphan()
 
     def orphan(self):
         """True if the changeset is not obsolete but it's ancestor are"""
         return self.rev() in obsmod.getrevs(self._repo, 'orphan')
 
     def bumped(self):
         msg = ("'context.bumped' is deprecated, "
                "use 'context.phasedivergent'")
         self._repo.ui.deprecwarn(msg, '4.4')
         return self.phasedivergent()
 
     def phasedivergent(self):
         """True if the changeset try to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be bumped.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'phasedivergent')
 
     def divergent(self):
         msg = ("'context.divergent' is deprecated, "
                "use 'context.contentdivergent'")
         self._repo.ui.deprecwarn(msg, '4.4')
         return self.contentdivergent()
 
     def contentdivergent(self):
         """Is a successors of a changeset with multiple possible successors set
 
         Only non-public and non-obsolete changesets may be divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'contentdivergent')
 
     def troubled(self):
         msg = ("'context.troubled' is deprecated, "
                "use 'context.isunstable'")
         self._repo.ui.deprecwarn(msg, '4.4')
         return self.isunstable()
 
     def isunstable(self):
         """True if the changeset is either unstable, bumped or divergent"""
         return self.orphan() or self.phasedivergent() or self.contentdivergent()
 
     def troubles(self):
         """Keep the old version around in order to avoid breaking extensions
         about different return values.
         """
         msg = ("'context.troubles' is deprecated, "
                "use 'context.instabilities'")
         self._repo.ui.deprecwarn(msg, '4.4')
 
         troubles = []
         if self.orphan():
             troubles.append('orphan')
         if self.phasedivergent():
             troubles.append('bumped')
         if self.contentdivergent():
             troubles.append('divergent')
         return troubles
 
     def instabilities(self):
         """return the list of instabilities affecting this changeset.
 
         Instabilities are returned as strings. possible values are:
         - orphan,
         - phase-divergent,
         - content-divergent.
         """
         instabilities = []
         if self.orphan():
             instabilities.append('orphan')
         if self.phasedivergent():
             instabilities.append('phase-divergent')
         if self.contentdivergent():
             instabilities.append('content-divergent')
         return instabilities
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         parents = self._parents
         if len(parents) == 2:
             return parents[1]
         return changectx(self._repo, nullrev)
 
     def _fileinfo(self, path):
         if r'_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.ManifestLookupError(self._node, path,
                                                 _('not found in manifest'))
         if r'_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return (self._manifestdelta[path],
                         self._manifestdelta.flags(path))
         mfl = self._repo.manifestlog
         try:
             node, flag = mfl[self._changeset.manifest].find(path)
         except KeyError:
             raise error.ManifestLookupError(self._node, path,
                                             _('not found in manifest'))
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return ''
 
     def sub(self, path, allowcreate=True):
         '''return a subrepo for the stored revision of path, never wdir()'''
         return subrepo.subrepo(self, path, allowcreate=allowcreate)
 
     def nullsub(self, path, pctx):
         return subrepo.nullsubrepo(self, path, pctx)
 
     def workingsub(self, path):
         '''return a subrepo for the stored revision, or wdir if this is a wdir
         context.
         '''
         return subrepo.subrepo(self, path, allowwdir=True)
 
     def match(self, pats=None, include=None, exclude=None, default='glob',
               listsubrepos=False, badfn=None):
         r = self._repo
         return matchmod.match(r.root, r.getcwd(), pats,
                               include, exclude, default,
                               auditor=r.nofsauditor, ctx=self,
                               listsubrepos=listsubrepos, badfn=badfn)
 
     def diff(self, ctx2=None, match=None, **opts):
         """Returns a diff generator for the given contexts and matcher"""
         if ctx2 is None:
             ctx2 = self.p1()
         if ctx2 is not None:
             ctx2 = self._repo[ctx2]
         diffopts = patch.diffopts(self._repo.ui, opts)
         return patch.diff(self._repo, ctx2, self, match=match, opts=diffopts)
 
     def dirs(self):
         return self._manifest.dirs()
 
     def hasdir(self, dir):
         return self._manifest.hasdir(dir)
 
     def status(self, other=None, match=None, listignored=False,
                listclean=False, listunknown=False, listsubrepos=False):
         """return status of files between two nodes or node and working
         directory.
 
         If other is None, compare this node with working directory.
 
         returns (modified, added, removed, deleted, unknown, ignored, clean)
         """
 
         ctx1 = self
         ctx2 = self._repo[other]
 
         # This next code block is, admittedly, fragile logic that tests for
         # reversing the contexts and wouldn't need to exist if it weren't for
         # the fast (and common) code path of comparing the working directory
         # with its first parent.
         #
         # What we're aiming for here is the ability to call:
         #
         # workingctx.status(parentctx)
         #
         # If we always built the manifest for each context and compared those,
         # then we'd be done. But the special case of the above call means we
         # just copy the manifest of the parent.
         reversed = False
         if (not isinstance(ctx1, changectx)
             and isinstance(ctx2, changectx)):
             reversed = True
             ctx1, ctx2 = ctx2, ctx1
 
         match = match or matchmod.always(self._repo.root, self._repo.getcwd())
         match = ctx2._matchstatus(ctx1, match)
         r = scmutil.status([], [], [], [], [], [], [])
         r = ctx2._buildstatus(ctx1, r, match, listignored, listclean,
                               listunknown)
 
         if reversed:
             # Reverse added and removed. Clear deleted, unknown and ignored as
             # these make no sense to reverse.
             r = scmutil.status(r.modified, r.removed, r.added, [], [], [],
                                r.clean)
 
         if listsubrepos:
             for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
                 try:
                     rev2 = ctx2.subrev(subpath)
                 except KeyError:
                     # A subrepo that existed in node1 was deleted between
                     # node1 and node2 (inclusive). Thus, ctx2's substate
                     # won't contain that subpath. The best we can do ignore it.
                     rev2 = None
                 submatch = matchmod.subdirmatcher(subpath, match)
                 s = sub.status(rev2, match=submatch, ignored=listignored,
                                clean=listclean, unknown=listunknown,
                                listsubrepos=True)
                 for rfiles, sfiles in zip(r, s):
                     rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
 
         for l in r:
             l.sort()
 
         return r
 
 def _filterederror(repo, changeid):
     """build an exception to be raised about a filtered changeid
 
     This is extracted in a function to help extensions (eg: evolve) to
     experiment with various message variants."""
     if repo.filtername.startswith('visible'):
         msg = _("hidden revision '%s'") % changeid
         hint = _('use --hidden to access hidden revisions')
         return error.FilteredRepoLookupError(msg, hint=hint)
     msg = _("filtered revision '%s' (not in '%s' subset)")
     msg %= (changeid, repo.filtername)
     return error.FilteredRepoLookupError(msg)
 
 class changectx(basectx):
     """A changecontext object makes access to data related to a particular
     changeset convenient. It represents a read-only context already present in
     the repo."""
     def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
 
         # since basectx.__new__ already took care of copying the object, we
         # don't need to do anything in __init__, so we just exit here
         if isinstance(changeid, basectx):
             return
 
         if changeid == '':
             changeid = '.'
         self._repo = repo
 
         try:
             if isinstance(changeid, int):
                 self._node = repo.changelog.node(changeid)
                 self._rev = changeid
                 return
             if not pycompat.ispy3 and isinstance(changeid, long):
                 changeid = str(changeid)
             if changeid == 'null':
                 self._node = nullid
                 self._rev = nullrev
                 return
             if changeid == 'tip':
                 self._node = repo.changelog.tip()
                 self._rev = repo.changelog.rev(self._node)
                 return
             if changeid == '.' or changeid == repo.dirstate.p1():
                 # this is a hack to delay/avoid loading obsmarkers
                 # when we know that '.' won't be hidden
                 self._node = repo.dirstate.p1()
                 self._rev = repo.unfiltered().changelog.rev(self._node)
                 return
             if len(changeid) == 20:
                 try:
                     self._node = changeid
                     self._rev = repo.changelog.rev(changeid)
                     return
                 except error.FilteredRepoLookupError:
                     raise
                 except LookupError:
                     pass
 
             try:
                 r = int(changeid)
                 if '%d' % r != changeid:
                     raise ValueError
                 l = len(repo.changelog)
                 if r < 0:
                     r += l
                 if r < 0 or r >= l and r != wdirrev:
                     raise ValueError
                 self._rev = r
                 self._node = repo.changelog.node(r)
                 return
             except error.FilteredIndexError:
                 raise
             except (ValueError, OverflowError, IndexError):
                 pass
 
             if len(changeid) == 40:
                 try:
                     self._node = bin(changeid)
                     self._rev = repo.changelog.rev(self._node)
                     return
                 except error.FilteredLookupError:
                     raise
                 except (TypeError, LookupError):
                     pass
 
             # lookup bookmarks through the name interface
             try:
                 self._node = repo.names.singlenode(repo, changeid)
                 self._rev = repo.changelog.rev(self._node)
                 return
             except KeyError:
                 pass
             except error.FilteredRepoLookupError:
                 raise
             except error.RepoLookupError:
                 pass
 
             self._node = repo.unfiltered().changelog._partialmatch(changeid)
             if self._node is not None:
                 self._rev = repo.changelog.rev(self._node)
                 return
 
             # lookup failed
             # check if it might have come from damaged dirstate
             #
             # XXX we could avoid the unfiltered if we had a recognizable
             # exception for filtered changeset access
             if changeid in repo.unfiltered().dirstate.parents():
                 msg = _("working directory has unknown parent '%s'!")
                 raise error.Abort(msg % short(changeid))
             try:
                 if len(changeid) == 20 and nonascii(changeid):
                     changeid = hex(changeid)
             except TypeError:
                 pass
         except (error.FilteredIndexError, error.FilteredLookupError,
                 error.FilteredRepoLookupError):
             raise _filterederror(repo, changeid)
         except IndexError:
             pass
         raise error.RepoLookupError(
             _("unknown revision '%s'") % changeid)
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     __bool__ = __nonzero__
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.changelogrevision(self.rev())
 
     @propertycache
     def _manifest(self):
         return self._manifestctx.read()
 
     @property
     def _manifestctx(self):
         return self._repo.manifestlog[self._changeset.manifest]
 
     @propertycache
     def _manifestdelta(self):
         return self._manifestctx.readdelta()
 
     @propertycache
     def _parents(self):
         repo = self._repo
         p1, p2 = repo.changelog.parentrevs(self._rev)
         if p2 == nullrev:
             return [changectx(repo, p1)]
         return [changectx(repo, p1), changectx(repo, p2)]
 
     def changeset(self):
         c = self._changeset
         return (
             c.manifest,
             c.user,
             c.date,
             c.files,
             c.description,
             c.extra,
         )
     def manifestnode(self):
         return self._changeset.manifest
 
     def user(self):
         return self._changeset.user
     def date(self):
         return self._changeset.date
     def files(self):
         return self._changeset.files
     def description(self):
         return self._changeset.description
     def branch(self):
         return encoding.tolocal(self._changeset.extra.get("branch"))
     def closesbranch(self):
         return 'close' in self._changeset.extra
     def extra(self):
         return self._changeset.extra
     def tags(self):
         return self._repo.nodetags(self._node)
     def bookmarks(self):
         return self._repo.nodebookmarks(self._node)
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, 'visible')
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors([self._rev]):
             yield changectx(self._repo, a)
 
     def descendants(self):
         for d in self._repo.changelog.descendants([self._rev]):
             yield changectx(self._repo, d)
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
     def ancestor(self, c2, warn=False):
         """return the "best" ancestor context of self and c2
 
         If there are multiple candidates, it will show a message and check
         merge.preferancestor configuration before falling back to the
         revlog ancestor."""
         # deal with workingctxs
         n2 = c2._node
         if n2 is None:
             n2 = c2._parents[0]._node
         cahs = self._repo.changelog.commonancestorsheads(self._node, n2)
         if not cahs:
             anc = nullid
         elif len(cahs) == 1:
             anc = cahs[0]
         else:
             # experimental config: merge.preferancestor
             for r in self._repo.ui.configlist('merge', 'preferancestor', ['*']):
                 try:
                     ctx = changectx(self._repo, r)
                 except error.RepoLookupError:
                     continue
                 anc = ctx.node()
                 if anc in cahs:
                     break
             else:
                 anc = self._repo.changelog.ancestor(self._node, n2)
             if warn:
                 self._repo.ui.status(
                     (_("note: using %s as ancestor of %s and %s\n") %
                      (short(anc), short(self._node), short(n2))) +
                     ''.join(_("      alternatively, use --config "
                               "merge.preferancestor=%s\n") %
                             short(n) for n in sorted(cahs) if n != anc))
         return changectx(self._repo, anc)
 
     def descendant(self, other):
         """True if other is descendant of this changeset"""
         return self._repo.changelog.descendant(self._rev, other._rev)
 
     def walk(self, match):
         '''Generates matching file names.'''
 
         # Wrap match.bad method to have message with nodeid
         def bad(fn, msg):
             # The manifest doesn't know about subrepos, so don't complain about
             # paths into valid subrepos.
             if any(fn == s or fn.startswith(s + '/')
                    for s in self.substate):
                 return
             match.bad(fn, _('no such file in rev %s') % self)
 
         m = matchmod.badmatch(match, bad)
         return self._manifest.walk(m)
 
     def matches(self, match):
         return self.walk(match)
 
 class basefilectx(object):
     """A filecontext object represents the common logic for its children:
     filectx: read-only access to a filerevision that is already present
              in the repo,
     workingfilectx: a filecontext that represents files from the working
                     directory,
     memfilectx: a filecontext that represents files in-memory,
     overlayfilectx: duplicate another filecontext with some fields overridden.
     """
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if r'_changeid' in self.__dict__:
             return self._changeid
         elif r'_changectx' in self.__dict__:
             return self._changectx.rev()
         elif r'_descendantrev' in self.__dict__:
             # this file context was created from a revision with a known
             # descendant, we can (lazily) correct for linkrev aliases
             return self._adjustlinkrev(self._descendantrev)
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if r'_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     __bool__ = __nonzero__
 
     def __bytes__(self):
         try:
             return "%s@%s" % (self.path(), self._changectx)
         except error.LookupError:
             return "%s@???" % self.path()
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __repr__(self):
         return "<%s %s>" % (type(self).__name__, str(self))
 
     def __hash__(self):
         try:
             return hash((self._path, self._filenode))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (type(self) == type(other) and self._path == other._path
                     and self._filenode == other._filenode)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filerev(self):
         return self._filerev
     def filenode(self):
         return self._filenode
     @propertycache
     def _flags(self):
         return self._changectx.flags(self._path)
     def flags(self):
         return self._flags
     def filelog(self):
         return self._filelog
     def rev(self):
         return self._changeid
     def linkrev(self):
         return self._filelog.linkrev(self._filerev)
     def node(self):
         return self._changectx.node()
     def hex(self):
         return self._changectx.hex()
     def user(self):
         return self._changectx.user()
     def date(self):
         return self._changectx.date()
     def files(self):
         return self._changectx.files()
     def description(self):
         return self._changectx.description()
     def branch(self):
         return self._changectx.branch()
     def extra(self):
         return self._changectx.extra()
     def phase(self):
         return self._changectx.phase()
     def phasestr(self):
         return self._changectx.phasestr()
     def manifest(self):
         return self._changectx.manifest()
     def changectx(self):
         return self._changectx
     def renamed(self):
         return self._copied
     def repo(self):
         return self._repo
     def size(self):
         return len(self.data())
 
     def path(self):
         return self._path
 
     def isbinary(self):
         try:
             return util.binary(self.data())
         except IOError:
             return False
     def isexec(self):
         return 'x' in self.flags()
     def islink(self):
         return 'l' in self.flags()
 
     def isabsent(self):
         """whether this filectx represents a file not in self._changectx
 
         This is mainly for merge code to detect change/delete conflicts. This is
         expected to be True for all subclasses of basectx."""
         return False
 
     _customcmp = False
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         if fctx._customcmp:
             return fctx.cmp(self)
 
         if (fctx._filenode is None
             and (self._repo._encodefilterpats
                  # if file data starts with '\1\n', empty metadata block is
                  # prepended, which adds 4 bytes to filelog.size().
                  or self.size() - 4 == fctx.size())
             or self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
 
         return True
 
     def _adjustlinkrev(self, srcrev, inclusive=False):
         """return the first ancestor of <srcrev> introducing <fnode>
 
         If the linkrev of the file revision does not point to an ancestor of
         srcrev, we'll walk down the ancestors until we find one introducing
         this file revision.
 
         :srcrev: the changeset revision we search ancestors from
         :inclusive: if true, the src revision will also be checked
         """
         repo = self._repo
         cl = repo.unfiltered().changelog
         mfl = repo.manifestlog
         # fetch the linkrev
         lkr = self.linkrev()
         # hack to reuse ancestor computation when searching for renames
         memberanc = getattr(self, '_ancestrycontext', None)
         iteranc = None
         if srcrev is None:
             # wctx case, used by workingfilectx during mergecopy
             revs = [p.rev() for p in self._repo[None].parents()]
             inclusive = True # we skipped the real (revless) source
         else:
             revs = [srcrev]
         if memberanc is None:
             memberanc = iteranc = cl.ancestors(revs, lkr,
                                                inclusive=inclusive)
         # check if this linkrev is an ancestor of srcrev
         if lkr not in memberanc:
             if iteranc is None:
                 iteranc = cl.ancestors(revs, lkr, inclusive=inclusive)
             fnode = self._filenode
             path = self._path
             for a in iteranc:
                 ac = cl.read(a) # get changeset data (we avoid object creation)
                 if path in ac[3]: # checking the 'files' field.
                     # The file has been touched, check if the content is
                     # similar to the one we search for.
                     if fnode == mfl[ac[0]].readfast().get(path):
                         return a
             # In theory, we should never get out of that loop without a result.
             # But if manifest uses a buggy file revision (not children of the
             # one it replaces) we could. Such a buggy situation will likely
             # result is crash somewhere else at to some point.
         return lkr
 
     def introrev(self):
         """return the rev of the changeset which introduced this file revision
 
         This method is different from linkrev because it take into account the
         changeset the filectx was created from. It ensures the returned
         revision is one of its ancestors. This prevents bugs from
         'linkrev-shadowing' when a file revision is used by multiple
         changesets.
         """
         lkr = self.linkrev()
         attrs = vars(self)
         noctx = not ('_changeid' in attrs or '_changectx' in attrs)
         if noctx or self.rev() == lkr:
             return self.linkrev()
         return self._adjustlinkrev(self.rev(), inclusive=True)
 
     def _parentfilectx(self, path, fileid, filelog):
         """create parent filectx keeping ancestry info for _adjustlinkrev()"""
         fctx = filectx(self._repo, path, fileid=fileid, filelog=filelog)
         if '_changeid' in vars(self) or '_changectx' in vars(self):
             # If self is associated with a changeset (probably explicitly
             # fed), ensure the created filectx is associated with a
             # changeset that is an ancestor of self.changectx.
             # This lets us later use _adjustlinkrev to get a correct link.
             fctx._descendantrev = self.rev()
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         elif '_descendantrev' in vars(self):
             # Otherwise propagate _descendantrev if we have one associated.
             fctx._descendantrev = self._descendantrev
             fctx._ancestrycontext = getattr(self, '_ancestrycontext', None)
         return fctx
 
     def parents(self):
         _path = self._path
         fl = self._filelog
         parents = self._filelog.parents(self._filenode)
         pl = [(_path, node, fl) for node in parents if node != nullid]
 
         r = fl.renamed(self._filenode)
         if r:
             # - In the simple rename case, both parent are nullid, pl is empty.
             # - In case of merge, only one of the parent is null id and should
             # be replaced with the rename information. This parent is -always-
             # the first one.
             #
             # As null id have always been filtered out in the previous list
             # comprehension, inserting to 0 will always result in "replacing
             # first nullid parent with rename information.
             pl.insert(0, (r[0], r[1], self._repo.file(r[0])))
 
         return [self._parentfilectx(path, fnode, l) for path, fnode, l in pl]
 
     def p1(self):
         return self.parents()[0]
 
     def p2(self):
         p = self.parents()
         if len(p) == 2:
             return p[1]
         return filectx(self._repo, self._path, fileid=-1, filelog=self._filelog)
 
     def annotate(self, follow=False, linenumber=False, skiprevs=None,
                  diffopts=None):
         '''returns a list of tuples of ((ctx, number), line) for each line
         in the file, where ctx is the filectx of the node where
         that line was last changed; if linenumber parameter is true, number is
         the line number at the first appearance in the managed file, otherwise,
         number has a fixed value of False.
         '''
 
         def lines(text):
             if text.endswith("\n"):
                 return text.count("\n")
             return text.count("\n") + int(bool(text))
 
         if linenumber:
             def decorate(text, rev):
                 return ([(rev, i) for i in xrange(1, lines(text) + 1)], text)
         else:
             def decorate(text, rev):
                 return ([(rev, False)] * lines(text), text)
 
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
 
         def parents(f):
             # Cut _descendantrev here to mitigate the penalty of lazy linkrev
             # adjustment. Otherwise, p._adjustlinkrev() would walk changelog
             # from the topmost introrev (= srcrev) down to p.linkrev() if it
             # isn't an ancestor of the srcrev.
             f._changeid
             pl = f.parents()
 
             # Don't return renamed parents if we aren't following.
             if not follow:
                 pl = [p for p in pl if p.path() == f.path()]
 
             # renamed filectx won't have a filelog yet, so set it
             # from the cache to save time
             for p in pl:
                 if not '_filelog' in p.__dict__:
                     p._filelog = getlog(p.path())
 
             return pl
 
         # use linkrev to find the first changeset where self appeared
         base = self
         introrev = self.introrev()
         if self.rev() != introrev:
             base = self.filectx(self.filenode(), changeid=introrev)
         if getattr(base, '_ancestrycontext', None) is None:
             cl = self._repo.changelog
             if introrev is None:
                 # wctx is not inclusive, but works because _ancestrycontext
                 # is used to test filelog revisions
                 ac = cl.ancestors([p.rev() for p in base.parents()],
                                   inclusive=True)
             else:
                 ac = cl.ancestors([introrev], inclusive=True)
             base._ancestrycontext = ac
 
         # This algorithm would prefer to be recursive, but Python is a
         # bit recursion-hostile. Instead we do an iterative
         # depth-first search.
 
         # 1st DFS pre-calculates pcache and needed
         visit = [base]
         pcache = {}
         needed = {base: 1}
         while visit:
             f = visit.pop()
             if f in pcache:
                 continue
             pl = parents(f)
             pcache[f] = pl
             for p in pl:
                 needed[p] = needed.get(p, 0) + 1
                 if p not in pcache:
                     visit.append(p)
 
         # 2nd DFS does the actual annotate
         visit[:] = [base]
         hist = {}
         while visit:
             f = visit[-1]
             if f in hist:
                 visit.pop()
                 continue
 
             ready = True
             pl = pcache[f]
             for p in pl:
                 if p not in hist:
                     ready = False
                     visit.append(p)
             if ready:
                 visit.pop()
                 curr = decorate(f.data(), f)
                 skipchild = False
                 if skiprevs is not None:
                     skipchild = f._changeid in skiprevs
                 curr = _annotatepair([hist[p] for p in pl], f, curr, skipchild,
                                      diffopts)
                 for p in pl:
                     if needed[p] == 1:
                         del hist[p]
                         del needed[p]
                     else:
                         needed[p] -= 1
 
                 hist[f] = curr
                 del pcache[f]
 
         return zip(hist[base][0], hist[base][1].splitlines(True))
 
     def ancestors(self, followfirst=False):
         visit = {}
         c = self
         if followfirst:
             cut = 1
         else:
             cut = None
 
         while True:
             for parent in c.parents()[:cut]:
                 visit[(parent.linkrev(), parent.filenode())] = parent
             if not visit:
                 break
             c = visit.pop(max(visit))
             yield c
 
     def decodeddata(self):
         """Returns `data()` after running repository decoding filters.
 
         This is often equivalent to how the data would be expressed on disk.
         """
         return self._repo.wwritedata(self.path(), self.data())
 
 def _annotatepair(parents, childfctx, child, skipchild, diffopts):
     r'''
     Given parent and child fctxes and annotate data for parents, for all lines
     in either parent that match the child, annotate the child with the parent's
     data.
 
     Additionally, if `skipchild` is True, replace all other lines with parent
     annotate data as well such that child is never blamed for any lines.
 
     >>> oldfctx = b'old'
     >>> p1fctx, p2fctx, childfctx = b'p1', b'p2', b'c'
     >>> olddata = b'a\nb\n'
     >>> p1data = b'a\nb\nc\n'
     >>> p2data = b'a\nc\nd\n'
     >>> childdata = b'a\nb2\nc\nc2\nd\n'
     >>> diffopts = mdiff.diffopts()
 
     >>> def decorate(text, rev):
     ...     return ([(rev, i) for i in xrange(1, text.count(b'\n') + 1)], text)
 
     Basic usage:
 
     >>> oldann = decorate(olddata, oldfctx)
     >>> p1ann = decorate(p1data, p1fctx)
     >>> p1ann = _annotatepair([oldann], p1fctx, p1ann, False, diffopts)
     >>> p1ann[0]
     [('old', 1), ('old', 2), ('p1', 3)]
     >>> p2ann = decorate(p2data, p2fctx)
     >>> p2ann = _annotatepair([oldann], p2fctx, p2ann, False, diffopts)
     >>> p2ann[0]
     [('old', 1), ('p2', 2), ('p2', 3)]
 
     Test with multiple parents (note the difference caused by ordering):
 
     >>> childann = decorate(childdata, childfctx)
     >>> childann = _annotatepair([p1ann, p2ann], childfctx, childann, False,
     ...                          diffopts)
     >>> childann[0]
     [('old', 1), ('c', 2), ('p2', 2), ('c', 4), ('p2', 3)]
 
     >>> childann = decorate(childdata, childfctx)
     >>> childann = _annotatepair([p2ann, p1ann], childfctx, childann, False,
     ...                          diffopts)
     >>> childann[0]
     [('old', 1), ('c', 2), ('p1', 3), ('c', 4), ('p2', 3)]
 
     Test with skipchild (note the difference caused by ordering):
 
     >>> childann = decorate(childdata, childfctx)
     >>> childann = _annotatepair([p1ann, p2ann], childfctx, childann, True,
     ...                          diffopts)
     >>> childann[0]
     [('old', 1), ('old', 2), ('p2', 2), ('p2', 2), ('p2', 3)]
 
     >>> childann = decorate(childdata, childfctx)
     >>> childann = _annotatepair([p2ann, p1ann], childfctx, childann, True,
     ...                          diffopts)
     >>> childann[0]
     [('old', 1), ('old', 2), ('p1', 3), ('p1', 3), ('p2', 3)]
     '''
     pblocks = [(parent, mdiff.allblocks(parent[1], child[1], opts=diffopts))
                for parent in parents]
 
     if skipchild:
         # Need to iterate over the blocks twice -- make it a list
         pblocks = [(p, list(blocks)) for (p, blocks) in pblocks]
     # Mercurial currently prefers p2 over p1 for annotate.
     # TODO: change this?
     for parent, blocks in pblocks:
         for (a1, a2, b1, b2), t in blocks:
             # Changed blocks ('!') or blocks made only of blank lines ('~')
             # belong to the child.
             if t == '=':
                 child[0][b1:b2] = parent[0][a1:a2]
 
     if skipchild:
         # Now try and match up anything that couldn't be matched,
         # Reversing pblocks maintains bias towards p2, matching above
         # behavior.
         pblocks.reverse()
 
         # The heuristics are:
         # * Work on blocks of changed lines (effectively diff hunks with -U0).
         # This could potentially be smarter but works well enough.
         # * For a non-matching section, do a best-effort fit. Match lines in
         #   diff hunks 1:1, dropping lines as necessary.
         # * Repeat the last line as a last resort.
 
         # First, replace as much as possible without repeating the last line.
         remaining = [(parent, []) for parent, _blocks in pblocks]
         for idx, (parent, blocks) in enumerate(pblocks):
             for (a1, a2, b1, b2), _t in blocks:
                 if a2 - a1 >= b2 - b1:
                     for bk in xrange(b1, b2):
                         if child[0][bk][0] == childfctx:
                             ak = min(a1 + (bk - b1), a2 - 1)
                             child[0][bk] = parent[0][ak]
                 else:
                     remaining[idx][1].append((a1, a2, b1, b2))
 
         # Then, look at anything left, which might involve repeating the last
         # line.
         for parent, blocks in remaining:
             for a1, a2, b1, b2 in blocks:
                 for bk in xrange(b1, b2):
                     if child[0][bk][0] == childfctx:
                         ak = min(a1 + (bk - b1), a2 - 1)
                         child[0][bk] = parent[0][ak]
     return child
 
 class filectx(basefilectx):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
     def __init__(self, repo, path, changeid=None, fileid=None,
                  filelog=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (changeid is not None
                 or fileid is not None
                 or changectx is not None), \
                 ("bad args: changeid=%r, fileid=%r, changectx=%r"
                  % (changeid, fileid, changectx))
 
         if filelog is not None:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         try:
             return changectx(self._repo, self._changeid)
         except error.FilteredRepoLookupError:
             # Linkrev may point to any revision in the repository.  When the
             # repository is filtered this may lead to `filectx` trying to build
             # `changectx` for filtered revision. In such case we fallback to
             # creating `changectx` on the unfiltered version of the reposition.
             # This fallback should not be an issue because `changectx` from
             # `filectx` are not used in complex operations that care about
             # filtering.
             #
             # This fallback is a cheap and dirty fix that prevent several
             # crashes. It does not ensure the behavior is correct. However the
             # behavior was not correct before filtering either and "incorrect
             # behavior" is seen as better as "crash"
             #
             # Linkrevs have several serious troubles with filtering that are
             # complicated to solve. Proper handling of the issue here should be
             # considered when solving linkrev issue are on the table.
             return changectx(self._repo.unfiltered(), self._changeid)
 
     def filectx(self, fileid, changeid=None):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(self._repo, self._path, fileid=fileid,
                        filelog=self._filelog, changeid=changeid)
 
     def rawdata(self):
         return self._filelog.revision(self._filenode, raw=True)
 
     def rawflags(self):
         """low-level revlog flags"""
         return self._filelog.flags(self._filerev)
 
     def data(self):
         try:
             return self._filelog.read(self._filenode)
         except error.CensoredNodeError:
             if self._repo.ui.config("censor", "policy") == "ignore":
                 return ""
             raise error.Abort(_("censored node: %s") % short(self._filenode),
                              hint=_("set censor.policy to ignore errors"))
 
     def size(self):
         return self._filelog.size(self._filerev)
 
     @propertycache
     def _copied(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return renamed
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [filectx(self._repo, self._path, fileid=x,
                         filelog=self._filelog) for x in c]
 
 class committablectx(basectx):
     """A committablectx object provides common functionality for a context that
     wants the ability to commit, e.g. workingctx or memctx."""
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = util.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = changes
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if 'branch' not in self._extra:
             try:
                 branch = encoding.fromlocal(self._repo.dirstate.branch())
             except UnicodeDecodeError:
                 raise error.Abort(_('branch name not in UTF-8!'))
             self._extra['branch'] = branch
         if self._extra['branch'] == '':
             self._extra['branch'] = 'default'
 
     def __bytes__(self):
         return bytes(self._parents[0]) + "+"
 
     __str__ = encoding.strmethod(__bytes__)
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def _buildflagfunc(self):
         # Create a fallback function for getting file flags when the
         # filesystem doesn't support them
 
         copiesget = self._repo.dirstate.copies().get
         parents = self.parents()
         if len(parents) < 2:
             # when we have one parent, it's easy: copy from parent
             man = parents[0].manifest()
             def func(f):
                 f = copiesget(f, f)
                 return man.flags(f)
         else:
             # merges are tricky: we try to reconstruct the unstored
             # result from the merge (issue1802)
             p1, p2 = parents
             pa = p1.ancestor(p2)
             m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
 
             def func(f):
                 f = copiesget(f, f) # may be wrong for merges with copies
                 fl1, fl2, fla = m1.flags(f), m2.flags(f), ma.flags(f)
                 if fl1 == fl2:
                     return fl1
                 if fl1 == fla:
                     return fl2
                 if fl2 == fla:
                     return fl1
                 return '' # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     @propertycache
     def _status(self):
         return self._repo.status()
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         ui = self._repo.ui
         date = ui.configdate('devel', 'default-date')
         if date is None:
             date = util.makedate()
         return date
 
     def subrev(self, subpath):
         return None
 
     def manifestnode(self):
         return None
     def user(self):
         return self._user or self._repo.ui.username()
     def date(self):
         return self._date
     def description(self):
         return self._text
     def files(self):
         return sorted(self._status.modified + self._status.added +
                       self._status.removed)
 
     def modified(self):
         return self._status.modified
     def added(self):
         return self._status.added
     def removed(self):
         return self._status.removed
     def deleted(self):
         return self._status.deleted
     def branch(self):
         return encoding.tolocal(self._extra['branch'])
     def closesbranch(self):
         return 'close' in self._extra
     def extra(self):
         return self._extra
 
     def tags(self):
         return []
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.draft # default phase to draft
         for p in self.parents():
             phase = max(phase, p.phase())
         return phase
 
     def hidden(self):
         return False
 
     def children(self):
         return []
 
     def flags(self, path):
         if r'_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return ''
 
     def ancestor(self, c2):
         """return the "best" ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
     def walk(self, match):
         '''Generates matching file names.'''
-        return sorted(self._repo.dirstate.walk(match, sorted(self.substate),
-                                               True, False))
+        return sorted(self._repo.dirstate.walk(match,
+                                               subrepos=sorted(self.substate),
+                                               unknown=True, ignored=False))
 
     def matches(self, match):
         return sorted(self._repo.dirstate.matches(match))
 
     def ancestors(self):
         for p in self._parents:
             yield p
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]):
             yield changectx(self._repo, a)
 
     def markcommitted(self, node):
         """Perform post-commit cleanup necessary after committing this ctx
 
         Specifically, this updates backing stores this working context
         wraps to reflect the fact that the changes reflected by this
         workingctx have been committed.  For example, it marks
         modified and added files as normal in the dirstate.
 
         """
 
         with self._repo.dirstate.parentchange():
             for f in self.modified() + self.added():
                 self._repo.dirstate.normal(f)
             for f in self.removed():
                 self._repo.dirstate.drop(f)
             self._repo.dirstate.setparents(node)
 
         # write changes out explicitly, because nesting wlock at
         # runtime may prevent 'wlock.release()' in 'repo.commit()'
         # from immediately doing so for subsequent changing files
         self._repo.dirstate.write(self._repo.currenttransaction())
 
     def dirty(self, missing=False, merge=True, branch=True):
         return False
 
 class workingctx(committablectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         super(workingctx, self).__init__(repo, text, user, date, extra, changes)
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d[f] != 'r':
                 yield f
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     def hex(self):
         return hex(wdirid)
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(self._repo, path, workingctx=self,
                               filelog=filelog)
 
     def dirty(self, missing=False, merge=True, branch=True):
         "check whether a working directory is modified"
         # check subrepos first
         for s in sorted(self.substate):
             if self.sub(s).dirty(missing=missing):
                 return True
         # check current working dir
         return ((merge and self.p2()) or
                 (branch and self.branch() != self.p1().branch()) or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
     def add(self, list, prefix=""):
         with self._repo.wlock():
             ui, ds = self._repo.ui, self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             lstat = self._repo.wvfs.lstat
             for f in list:
                 # ds.pathto() returns an absolute file when this is invoked from
                 # the keyword extension.  That gets flagged as non-portable on
                 # Windows, since it contains the drive letter and colon.
                 scmutil.checkportable(ui, os.path.join(prefix, f))
                 try:
                     st = lstat(f)
                 except OSError:
                     ui.warn(_("%s does not exist!\n") % uipath(f))
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     ui.warn(_("%s: up to %d MB of RAM may be required "
                               "to manage this file\n"
                               "(use 'hg revert %s' to cancel the "
                               "pending addition)\n")
                             % (f, 3 * st.st_size // 1000000, uipath(f)))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(_("%s not added: only files and symlinks "
                               "supported currently\n") % uipath(f))
                     rejected.append(f)
                 elif ds[f] in 'amn':
                     ui.warn(_("%s already tracked!\n") % uipath(f))
                 elif ds[f] == 'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
 
     def forget(self, files, prefix=""):
         with self._repo.wlock():
             ds = self._repo.dirstate
             uipath = lambda f: ds.pathto(pathutil.join(prefix, f))
             rejected = []
             for f in files:
                 if f not in self._repo.dirstate:
                     self._repo.ui.warn(_("%s not tracked!\n") % uipath(f))
                     rejected.append(f)
                 elif self._repo.dirstate[f] != 'a':
                     self._repo.dirstate.remove(f)
                 else:
                     self._repo.dirstate.drop(f)
             return rejected
 
     def undelete(self, list):
         pctxs = self.parents()
         with self._repo.wlock():
             ds = self._repo.dirstate
             for f in list:
                 if self._repo.dirstate[f] != 'r':
                     self._repo.ui.warn(_("%s not removed!\n") % ds.pathto(f))
                 else:
                     fctx = f in pctxs[0] and pctxs[0][f] or pctxs[1][f]
                     t = fctx.data()
                     self._repo.wwrite(f, t, fctx.flags())
                     self._repo.dirstate.normal(f)
 
     def copy(self, source, dest):
         try:
             st = self._repo.wvfs.lstat(dest)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             self._repo.ui.warn(_("%s does not exist!\n")
                                % self._repo.dirstate.pathto(dest))
             return
         if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
             self._repo.ui.warn(_("copy failed: %s is not a file or a "
                                  "symbolic link\n")
                                % self._repo.dirstate.pathto(dest))
         else:
             with self._repo.wlock():
                 if self._repo.dirstate[dest] in '?':
                     self._repo.dirstate.add(dest)
                 elif self._repo.dirstate[dest] in 'r':
                     self._repo.dirstate.normallookup(dest)
                 self._repo.dirstate.copy(source, dest)
 
     def match(self, pats=None, include=None, exclude=None, default='glob',
               listsubrepos=False, badfn=None):
         r = self._repo
 
         # Only a case insensitive filesystem needs magic to translate user input
         # to actual case in the filesystem.
         icasefs = not util.fscasesensitive(r.root)
         return matchmod.match(r.root, r.getcwd(), pats, include, exclude,
                               default, auditor=r.auditor, ctx=self,
                               listsubrepos=listsubrepos, badfn=badfn,
                               icasefs=icasefs)
 
     def flushall(self):
         pass # For overlayworkingfilectx compatibility.
 
     def _filtersuspectsymlink(self, files):
         if not files or self._repo.dirstate._checklink:
             return files
 
         # Symlink placeholders may get non-symlink-like contents
         # via user error or dereferencing by NFS or Samba servers,
         # so we filter out any placeholders that don't look like a
         # symlink
         sane = []
         for f in files:
             if self.flags(f) == 'l':
                 d = self[f].data()
                 if d == '' or len(d) >= 1024 or '\n' in d or util.binary(d):
                     self._repo.ui.debug('ignoring suspect symlink placeholder'
                                         ' "%s"\n' % f)
                     continue
             sane.append(f)
         return sane
 
     def _checklookup(self, files):
         # check for any possibly clean files
         if not files:
             return [], [], []
 
         modified = []
         deleted = []
         fixup = []
         pctx = self._parents[0]
         # do a full compare of any files that might have changed
         for f in sorted(files):
             try:
                 # This will return True for a file that got replaced by a
                 # directory in the interim, but fixing that is pretty hard.
                 if (f not in pctx or self.flags(f) != pctx.flags(f)
                     or pctx[f].cmp(self[f])):
                     modified.append(f)
                 else:
                     fixup.append(f)
             except (IOError, OSError):
                 # A file become inaccessible in between? Mark it as deleted,
                 # matching dirstate behavior (issue5584).
                 # The dirstate has more complex behavior around whether a
                 # missing file matches a directory, etc, but we don't need to
                 # bother with that: if f has made it to this point, we're sure
                 # it's in the dirstate.
                 deleted.append(f)
 
         return modified, deleted, fixup
 
     def _poststatusfixup(self, status, fixup):
         """update dirstate for files that are actually clean"""
         poststatus = self._repo.postdsstatus()
         if fixup or poststatus:
             try:
                 oldid = self._repo.dirstate.identity()
 
                 # updating the dirstate is optional
                 # so we don't wait on the lock
                 # wlock can invalidate the dirstate, so cache normal _after_
                 # taking the lock
                 with self._repo.wlock(False):
                     if self._repo.dirstate.identity() == oldid:
                         if fixup:
                             normal = self._repo.dirstate.normal
                             for f in fixup:
                                 normal(f)
                             # write changes out explicitly, because nesting
                             # wlock at runtime may prevent 'wlock.release()'
                             # after this block from doing so for subsequent
                             # changing files
                             tr = self._repo.currenttransaction()
                             self._repo.dirstate.write(tr)
 
                         if poststatus:
                             for ps in poststatus:
                                 ps(self, status)
                     else:
                         # in this case, writing changes out breaks
                         # consistency, because .hg/dirstate was
                         # already changed simultaneously after last
                         # caching (see also issue5584 for detail)
                         self._repo.ui.debug('skip updating dirstate: '
                                             'identity mismatch\n')
             except error.LockError:
                 pass
             finally:
                 # Even if the wlock couldn't be grabbed, clear out the list.
                 self._repo.clearpostdsstatus()
 
     def _dirstatestatus(self, match, ignored=False, clean=False, unknown=False):
         '''Gets the status from the dirstate -- internal use only.'''
         listignored, listclean, listunknown = ignored, clean, unknown
         subrepos = []
         if '.hgsub' in self:
             subrepos = sorted(self.substate)
         cmp, s = self._repo.dirstate.status(match, subrepos, listignored,
                                             listclean, listunknown)
 
         # check for any possibly clean files
         fixup = []
         if cmp:
             modified2, deleted2, fixup = self._checklookup(cmp)
             s.modified.extend(modified2)
             s.deleted.extend(deleted2)
 
             if fixup and listclean:
                 s.clean.extend(fixup)
 
         self._poststatusfixup(s, fixup)
 
         if match.always():
             # cache for performance
             if s.unknown or s.ignored or s.clean:
                 # "_status" is cached with list*=False in the normal route
                 self._status = scmutil.status(s.modified, s.added, s.removed,
                                               s.deleted, [], [], [])
             else:
                 self._status = s
 
         return s
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the values in self._status
 
         This reuse the file nodeid from parent, but we use special node
         identifiers for added and modified files. This is used by manifests
         merge to see that files are different and by update logic to avoid
         deleting newly added files.
         """
         return self._buildstatusmanifest(self._status)
 
     def _buildstatusmanifest(self, status):
         """Builds a manifest that includes the given status results."""
         parents = self.parents()
 
         man = parents[0].manifest().copy()
 
         ff = self._flagfunc
         for i, l in ((addednodeid, status.added),
                      (modifiednodeid, status.modified)):
             for f in l:
                 man[f] = i
                 try:
                     man.setflag(f, ff(f))
                 except OSError:
                     pass
 
         for f in status.deleted + status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     def _buildstatus(self, other, s, match, listignored, listclean,
                      listunknown):
         """build a status with respect to another context
 
         This includes logic for maintaining the fast path of status when
         comparing the working directory against its parent, which is to skip
         building a new manifest if self (working directory) is not comparing
         against its parent (repo['.']).
         """
         s = self._dirstatestatus(match, listignored, listclean, listunknown)
         # Filter out symlinks that, in the case of FAT32 and NTFS filesystems,
         # might have accidentally ended up with the entire contents of the file
         # they are supposed to be linking to.
         s.modified[:] = self._filtersuspectsymlink(s.modified)
         if other != self._repo['.']:
             s = super(workingctx, self)._buildstatus(other, s, match,
                                                      listignored, listclean,
                                                      listunknown)
         return s
 
     def _matchstatus(self, other, match):
         """override the match method with a filter for directory patterns
 
         We use inheritance to customize the match.bad method only in cases of
         workingctx since it belongs only to the working directory when
         comparing against the parent changeset.
 
         If we aren't comparing against the working directory's parent, then we
         just use the default match object sent to us.
         """
         if other != self._repo['.']:
             def bad(f, msg):
                 # 'f' may be a directory pattern from 'match.files()',
                 # so 'f not in ctx1' is not enough
                 if f not in other and not other.hasdir(f):
                     self._repo.ui.warn('%s: %s\n' %
                                        (self._repo.dirstate.pathto(f), msg))
             match.bad = bad
         return match
 
     def markcommitted(self, node):
         super(workingctx, self).markcommitted(node)
 
         sparse.aftercommit(self._repo, node)
 
 class committablefilectx(basefilectx):
     """A committablefilectx provides common functionality for a file context
     that wants the ability to commit, e.g. workingfilectx or memfilectx."""
     def __init__(self, repo, path, filelog=None, ctx=None):
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog is not None:
             self._filelog = filelog
         if ctx:
             self._changectx = ctx
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def linkrev(self):
         # linked to self._changectx no matter if file is modified or not
         return self.rev()
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [self._parentfilectx(p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def children(self):
         return []
 
 class workingfilectx(committablefilectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
     def __init__(self, repo, path, filelog=None, workingctx=None):
         super(workingfilectx, self).__init__(repo, path, filelog, workingctx)
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def data(self):
         return self._repo.wread(self._path)
     def renamed(self):
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def size(self):
         return self._repo.wvfs.lstat(self._path).st_size
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (self._repo.wvfs.lstat(self._path).st_mtime, tz)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
     def exists(self):
         return self._repo.wvfs.exists(self._path)
 
     def lexists(self):
         return self._repo.wvfs.lexists(self._path)
 
     def audit(self):
         return self._repo.wvfs.audit(self._path)
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         # fctx should be a filectx (not a workingfilectx)
         # invert comparison to reuse the same code path
         return fctx.cmp(self)
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         self._repo.wvfs.unlinkpath(self._path, ignoremissing=ignoremissing)
 
     def write(self, data, flags, backgroundclose=False):
         """wraps repo.wwrite"""
         self._repo.wwrite(self._path, data, flags,
                           backgroundclose=backgroundclose)
 
     def clearunknown(self):
         """Removes conflicting items in the working directory so that
         ``write()`` can be called successfully.
         """
         wvfs = self._repo.wvfs
         if wvfs.isdir(self._path) and not wvfs.islink(self._path):
             wvfs.removedirs(self._path)
 
     def setflags(self, l, x):
         self._repo.wvfs.setflags(self._path, l, x)
 
 class overlayworkingctx(workingctx):
     """Wraps another mutable context with a write-back cache that can be flushed
     at a later time.
 
     self._cache[path] maps to a dict with keys: {
         'exists': bool?
         'date': date?
         'data': str?
         'flags': str?
     }
     If `exists` is True, `flags` must be non-None and 'date' is non-None. If it
     is `False`, the file was deleted.
     """
 
     def __init__(self, repo, wrappedctx):
         super(overlayworkingctx, self).__init__(repo)
         self._repo = repo
         self._wrappedctx = wrappedctx
         self._clean()
 
     def data(self, path):
         if self.isdirty(path):
             if self._cache[path]['exists']:
                 if self._cache[path]['data']:
                     return self._cache[path]['data']
                 else:
                     # Must fallback here, too, because we only set flags.
                     return self._wrappedctx[path].data()
             else:
                 raise error.ProgrammingError("No such file or directory: %s" %
                                              self._path)
         else:
             return self._wrappedctx[path].data()
 
     def filedate(self, path):
         if self.isdirty(path):
             return self._cache[path]['date']
         else:
             return self._wrappedctx[path].date()
 
     def flags(self, path):
         if self.isdirty(path):
             if self._cache[path]['exists']:
                 return self._cache[path]['flags']
             else:
                 raise error.ProgrammingError("No such file or directory: %s" %
                                              self._path)
         else:
             return self._wrappedctx[path].flags()
 
     def write(self, path, data, flags=''):
         if data is None:
             raise error.ProgrammingError("data must be non-None")
         self._markdirty(path, exists=True, data=data, date=util.makedate(),
                         flags=flags)
 
     def setflags(self, path, l, x):
         self._markdirty(path, exists=True, date=util.makedate(),
                         flags=(l and 'l' or '') + (x and 'x' or ''))
 
     def remove(self, path):
         self._markdirty(path, exists=False)
 
     def exists(self, path):
         """exists behaves like `lexists`, but needs to follow symlinks and
         return False if they are broken.
         """
         if self.isdirty(path):
             # If this path exists and is a symlink, "follow" it by calling
             # exists on the destination path.
             if (self._cache[path]['exists'] and
                         'l' in self._cache[path]['flags']):
                 return self.exists(self._cache[path]['data'].strip())
             else:
                 return self._cache[path]['exists']
         return self._wrappedctx[path].exists()
 
     def lexists(self, path):
         """lexists returns True if the path exists"""
         if self.isdirty(path):
             return self._cache[path]['exists']
         return self._wrappedctx[path].lexists()
 
     def size(self, path):
         if self.isdirty(path):
             if self._cache[path]['exists']:
                 return len(self._cache[path]['data'])
             else:
                 raise error.ProgrammingError("No such file or directory: %s" %
                                              self._path)
         return self._wrappedctx[path].size()
 
     def flushall(self):
         for path in self._writeorder:
             entry = self._cache[path]
             if entry['exists']:
                 self._wrappedctx[path].clearunknown()
                 if entry['data'] is not None:
                     if entry['flags'] is None:
                         raise error.ProgrammingError('data set but not flags')
                     self._wrappedctx[path].write(
                         entry['data'],
                         entry['flags'])
                 else:
                     self._wrappedctx[path].setflags(
                         'l' in entry['flags'],
                         'x' in entry['flags'])
             else:
                 self._wrappedctx[path].remove(path)
         self._clean()
 
     def isdirty(self, path):
         return path in self._cache
 
     def _clean(self):
         self._cache = {}
         self._writeorder = []
 
     def _markdirty(self, path, exists, data=None, date=None, flags=''):
         if path not in self._cache:
             self._writeorder.append(path)
 
         self._cache[path] = {
             'exists': exists,
             'data': data,
             'date': date,
             'flags': flags,
         }
 
     def filectx(self, path, filelog=None):
         return overlayworkingfilectx(self._repo, path, parent=self,
                                      filelog=filelog)
 
 class overlayworkingfilectx(workingfilectx):
     """Wrap a ``workingfilectx`` but intercepts all writes into an in-memory
     cache, which can be flushed through later by calling ``flush()``."""
 
     def __init__(self, repo, path, filelog=None, parent=None):
         super(overlayworkingfilectx, self).__init__(repo, path, filelog,
                                                     parent)
         self._repo = repo
         self._parent = parent
         self._path = path
 
     def ctx(self):
         return self._parent
 
     def data(self):
         return self._parent.data(self._path)
 
     def date(self):
         return self._parent.filedate(self._path)
 
     def exists(self):
         return self.lexists()
 
     def lexists(self):
         return self._parent.exists(self._path)
 
     def renamed(self):
         # Copies are currently tracked in the dirstate as before. Straight copy
         # from workingfilectx.
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def size(self):
         return self._parent.size(self._path)
 
     def audit(self):
         pass
 
     def flags(self):
         return self._parent.flags(self._path)
 
     def setflags(self, islink, isexec):
         return self._parent.setflags(self._path, islink, isexec)
 
     def write(self, data, flags, backgroundclose=False):
         return self._parent.write(self._path, data, flags)
 
     def remove(self, ignoremissing=False):
         return self._parent.remove(self._path)
 
 class workingcommitctx(workingctx):
     """A workingcommitctx object makes access to data related to
     the revision being committed convenient.
 
     This hides changes in the working directory, if they aren't
     committed in this context.
     """
     def __init__(self, repo, changes,
                  text="", user=None, date=None, extra=None):
         super(workingctx, self).__init__(repo, text, user, date, extra,
                                          changes)
 
     def _dirstatestatus(self, match, ignored=False, clean=False, unknown=False):
         """Return matched files only in ``self._status``
 
         Uncommitted files appear "clean" via this context, even if
         they aren't actually so in the working directory.
         """
         if clean:
             clean = [f for f in self._manifest if f not in self._changedset]
         else:
             clean = []
         return scmutil.status([f for f in self._status.modified if match(f)],
                               [f for f in self._status.added if match(f)],
                               [f for f in self._status.removed if match(f)],
                               [], [], [], clean)
 
     @propertycache
     def _changedset(self):
         """Return the set of files changed in this context
         """
         changed = set(self._status.modified)
         changed.update(self._status.added)
         changed.update(self._status.removed)
         return changed
 
 def makecachingfilectxfn(func):
     """Create a filectxfn that caches based on the path.
 
     We can't use util.cachefunc because it uses all arguments as the cache
     key and this creates a cycle since the arguments include the repo and
     memctx.
     """
     cache = {}
 
     def getfilectx(repo, memctx, path):
         if path not in cache:
             cache[path] = func(repo, memctx, path)
         return cache[path]
 
     return getfilectx
 
 def memfilefromctx(ctx):
     """Given a context return a memfilectx for ctx[path]
 
     This is a convenience method for building a memctx based on another
     context.
     """
     def getfilectx(repo, memctx, path):
         fctx = ctx[path]
         # this is weird but apparently we only keep track of one parent
         # (why not only store that instead of a tuple?)
         copied = fctx.renamed()
         if copied:
             copied = copied[0]
         return memfilectx(repo, path, fctx.data(),
                           islink=fctx.islink(), isexec=fctx.isexec(),
                           copied=copied, memctx=memctx)
 
     return getfilectx
 
 def memfilefrompatch(patchstore):
     """Given a patch (e.g. patchstore object) return a memfilectx
 
     This is a convenience method for building a memctx based on a patchstore.
     """
     def getfilectx(repo, memctx, path):
         data, mode, copied = patchstore.getfile(path)
         if data is None:
             return None
         islink, isexec = mode
         return memfilectx(repo, path, data, islink=islink,
                           isexec=isexec, copied=copied,
                           memctx=memctx)
 
     return getfilectx
 
 class memctx(committablectx):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn return None for recent
     Mercurial. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by util.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
 
     # Mercurial <= 3.1 expects the filectxfn to raise IOError for missing files.
     # Extensions that need to retain compatibility across Mercurial 3.1 can use
     # this field to determine what to do in filectxfn.
     _returnnoneformissingfiles = True
 
     def __init__(self, repo, parents, text, files, filectxfn, user=None,
                  date=None, extra=None, branch=None, editor=False):
         super(memctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [changectx(self._repo, p) for p in (p1, p2)]
         files = sorted(set(files))
         self._files = files
         if branch is not None:
             self._extra['branch'] = encoding.fromlocal(branch)
         self.substate = {}
 
         if isinstance(filectxfn, patch.filestore):
             filectxfn = memfilefrompatch(filectxfn)
         elif not callable(filectxfn):
             # if store is not callable, wrap it in a function
             filectxfn = memfilefromctx(filectxfn)
 
         # memoizing increases performance for e.g. vcs convert scenarios.
         self._filectxfn = makecachingfilectxfn(filectxfn)
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory
 
         Returns None if file doesn't exist and should be removed."""
         return self._filectxfn(self._repo, self, path)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @propertycache
     def _manifest(self):
         """generate a manifest based on the return values of filectxfn"""
 
         # keep this simple for now; just worry about p1
         pctx = self._parents[0]
         man = pctx.manifest().copy()
 
         for f in self._status.modified:
             p1node = nullid
             p2node = nullid
             p = pctx[f].parents() # if file isn't in pctx, check p2?
             if len(p) > 0:
                 p1node = p[0].filenode()
                 if len(p) > 1:
                     p2node = p[1].filenode()
             man[f] = revlog.hash(self[f].data(), p1node, p2node)
 
         for f in self._status.added:
             man[f] = revlog.hash(self[f].data(), nullid, nullid)
 
         for f in self._status.removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified at construction
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "memctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif self[f]:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 class memfilectx(committablefilectx):
     """memfilectx represents an in-memory file to commit.
 
     See memctx and committablefilectx for more details.
     """
     def __init__(self, repo, path, data, islink=False,
                  isexec=False, copied=None, memctx=None):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         super(memfilectx, self).__init__(repo, path, None, memctx)
         self._data = data
         self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
         self._copied = None
         if copied:
             self._copied = (copied, nullid)
 
     def data(self):
         return self._data
 
     def remove(self, ignoremissing=False):
         """wraps unlink for a repo's working directory"""
         # need to figure out what to do here
         del self._changectx[self._path]
 
     def write(self, data, flags):
         """wraps repo.wwrite"""
         self._data = data
 
 class overlayfilectx(committablefilectx):
     """Like memfilectx but take an original filectx and optional parameters to
     override parts of it. This is useful when fctx.data() is expensive (i.e.
     flag processor is expensive) and raw data, flags, and filenode could be
     reused (ex. rebase or mode-only amend a REVIDX_EXTSTORED file).
     """
 
     def __init__(self, originalfctx, datafunc=None, path=None, flags=None,
                  copied=None, ctx=None):
         """originalfctx: filecontext to duplicate
 
         datafunc: None or a function to override data (file content). It is a
         function to be lazy. path, flags, copied, ctx: None or overridden value
 
         copied could be (path, rev), or False. copied could also be just path,
         and will be converted to (path, nullid). This simplifies some callers.
         """
 
         if path is None:
             path = originalfctx.path()
         if ctx is None:
             ctx = originalfctx.changectx()
             ctxmatch = lambda: True
         else:
             ctxmatch = lambda: ctx == originalfctx.changectx()
 
         repo = originalfctx.repo()
         flog = originalfctx.filelog()
         super(overlayfilectx, self).__init__(repo, path, flog, ctx)
 
         if copied is None:
             copied = originalfctx.renamed()
             copiedmatch = lambda: True
         else:
             if copied and not isinstance(copied, tuple):
                 # repo._filecommit will recalculate copyrev so nullid is okay
                 copied = (copied, nullid)
             copiedmatch = lambda: copied == originalfctx.renamed()
 
         # When data, copied (could affect data), ctx (could affect filelog
         # parents) are not overridden, rawdata, rawflags, and filenode may be
         # reused (repo._filecommit should double check filelog parents).
         #
         # path, flags are not hashed in filelog (but in manifestlog) so they do
         # not affect reusable here.
         #
         # If ctx or copied is overridden to a same value with originalfctx,
         # still consider it's reusable. originalfctx.renamed() may be a bit
         # expensive so it's not called unless necessary. Assuming datafunc is
         # always expensive, do not call it for this "reusable" test.
         reusable = datafunc is None and ctxmatch() and copiedmatch()
 
         if datafunc is None:
             datafunc = originalfctx.data
         if flags is None:
             flags = originalfctx.flags()
 
         self._datafunc = datafunc
         self._flags = flags
         self._copied = copied
 
         if reusable:
             # copy extra fields from originalfctx
             attrs = ['rawdata', 'rawflags', '_filenode', '_filerev']
             for attr in attrs:
                 if util.safehasattr(originalfctx, attr):
                     setattr(self, attr, getattr(originalfctx, attr))
 
     def data(self):
         return self._datafunc()
 
 class metadataonlyctx(committablectx):
     """Like memctx but it's reusing the manifest of different commit.
     Intended to be used by lightweight operations that are creating
     metadata-only changes.
 
     Revision information is supplied at initialization time.  'repo' is the
     current localrepo, 'ctx' is original revision which manifest we're reuisng
     'parents' is a sequence of two parent revisions identifiers (pass None for
     every missing parent), 'text' is the commit.
 
     user receives the committer name and defaults to current repository
     username, date is the commit date in any format supported by
     util.parsedate() and defaults to current date, extra is a dictionary of
     metadata or is left empty.
     """
     def __new__(cls, repo, originalctx, *args, **kwargs):
         return super(metadataonlyctx, cls).__new__(cls, repo)
 
     def __init__(self, repo, originalctx, parents=None, text=None, user=None,
                  date=None, extra=None, editor=False):
         if text is None:
             text = originalctx.description()
         super(metadataonlyctx, self).__init__(repo, text, user, date, extra)
         self._rev = None
         self._node = None
         self._originalctx = originalctx
         self._manifestnode = originalctx.manifestnode()
         if parents is None:
             parents = originalctx.parents()
         else:
             parents = [repo[p] for p in parents if p is not None]
         parents = parents[:]
         while len(parents) < 2:
             parents.append(repo[nullid])
         p1, p2 = self._parents = parents
 
         # sanity check to ensure that the reused manifest parents are
         # manifests of our commit parents
         mp1, mp2 = self.manifestctx().parents
         if p1 != nullid and p1.manifestnode() != mp1:
             raise RuntimeError('can\'t reuse the manifest: '
                                'its p1 doesn\'t match the new ctx p1')
         if p2 != nullid and p2.manifestnode() != mp2:
             raise RuntimeError('can\'t reuse the manifest: '
                                'its p2 doesn\'t match the new ctx p2')
 
         self._files = originalctx.files()
         self.substate = {}
 
         if editor:
             self._text = editor(self._repo, self, [])
             self._repo.savecommitmessage(self._text)
 
     def manifestnode(self):
         return self._manifestnode
 
     @property
     def _manifestctx(self):
         return self._repo.manifestlog[self._manifestnode]
 
     def filectx(self, path, filelog=None):
         return self._originalctx.filectx(path, filelog=filelog)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
     @property
     def _manifest(self):
         return self._originalctx.manifest()
 
     @propertycache
     def _status(self):
         """Calculate exact status from ``files`` specified in the ``origctx``
         and parents manifests.
         """
         man1 = self.p1().manifest()
         p2 = self._parents[1]
         # "1 < len(self._parents)" can't be used for checking
         # existence of the 2nd parent, because "metadataonlyctx._parents" is
         # explicitly initialized by the list, of which length is 2.
         if p2.node() != nullid:
             man2 = p2.manifest()
             managing = lambda f: f in man1 or f in man2
         else:
             managing = lambda f: f in man1
 
         modified, added, removed = [], [], []
         for f in self._files:
             if not managing(f):
                 added.append(f)
             elif f in self:
                 modified.append(f)
             else:
                 removed.append(f)
 
         return scmutil.status(modified, added, removed, [], [], [], [])
 
 class arbitraryfilectx(object):
     """Allows you to use filectx-like functions on a file in an arbitrary
     location on disk, possibly not in the working directory.
     """
     def __init__(self, path):
         self._path = path
 
     def cmp(self, otherfilectx):
         return self.data() != otherfilectx.data()
 
     def path(self):
         return self._path
 
     def flags(self):
         return ''
 
     def data(self):
         return util.readfile(self._path)
 
     def decodeddata(self):
         with open(self._path, "rb") as f:
             return f.read()
 
     def remove(self):
         util.unlink(self._path)
 
     def write(self, data, flags):
         assert not flags
         with open(self._path, "w") as f:
             f.write(data)

mercurial/scmutil.py

@@ -1,1123 +1,1123 b''
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import glob
 import hashlib
 import os
 import re
 import socket
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     short,
     wdirid,
     wdirrev,
 )
 
 from . import (
     encoding,
     error,
     match as matchmod,
     obsolete,
     obsutil,
     pathutil,
     phases,
     pycompat,
     revsetlang,
     similar,
     util,
 )
 
 if pycompat.osname == 'nt':
     from . import scmwindows as scmplatform
 else:
     from . import scmposix as scmplatform
 
 termsize = scmplatform.termsize
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
 
     missing = set()
 
     for subpath in ctx2.substate:
         if subpath not in ctx1.substate:
             del subpaths[subpath]
             missing.add(subpath)
 
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
     # Yield an empty subrepo based on ctx1 for anything only in ctx2.  That way,
     # status and diff will have an accurate result when it does
     # 'sub.{status|diff}(rev2)'.  Otherwise, the ctx2 subrepo is compared
     # against itself.
     for subpath in missing:
         yield subpath, ctx2.nullsub(subpath, ctx1)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def callcatch(ui, func):
     """call func() with global exception handling
 
     return func() if no exception happens. otherwise do some error handling
     and return an exit code accordingly. does not handle all exceptions.
     """
     try:
         try:
             return func()
         except: # re-raises
             ui.traceback()
             raise
     # Global exception handling, alphabetically
     # Mercurial-specific first, followed by built-in and library exceptions
     except error.LockHeld as inst:
         if inst.errno == errno.ETIMEDOUT:
             reason = _('timed out waiting for lock held by %r') % inst.locker
         else:
             reason = _('lock held by %r') % inst.locker
         ui.warn(_("abort: %s: %s\n") % (inst.desc or inst.filename, reason))
         if not inst.locker:
             ui.warn(_("(lock might be very busy)\n"))
     except error.LockUnavailable as inst:
         ui.warn(_("abort: could not lock %s: %s\n") %
                (inst.desc or inst.filename,
                 encoding.strtolocal(inst.strerror)))
     except error.OutOfBandError as inst:
         if inst.args:
             msg = _("abort: remote error:\n")
         else:
             msg = _("abort: remote error\n")
         ui.warn(msg)
         if inst.args:
             ui.warn(''.join(inst.args))
         if inst.hint:
             ui.warn('(%s)\n' % inst.hint)
     except error.RepoError as inst:
         ui.warn(_("abort: %s!\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except error.ResponseError as inst:
         ui.warn(_("abort: %s") % inst.args[0])
         if not isinstance(inst.args[1], basestring):
             ui.warn(" %r\n" % (inst.args[1],))
         elif not inst.args[1]:
             ui.warn(_(" empty string\n"))
         else:
             ui.warn("\n%r\n" % util.ellipsis(inst.args[1]))
     except error.CensoredNodeError as inst:
         ui.warn(_("abort: file censored %s!\n") % inst)
     except error.RevlogError as inst:
         ui.warn(_("abort: %s!\n") % inst)
     except error.InterventionRequired as inst:
         ui.warn("%s\n" % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
         return 1
     except error.WdirUnsupported:
         ui.warn(_("abort: working directory revision cannot be specified\n"))
     except error.Abort as inst:
         ui.warn(_("abort: %s\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except ImportError as inst:
         ui.warn(_("abort: %s!\n") % inst)
         m = str(inst).split()[-1]
         if m in "mpatch bdiff".split():
             ui.warn(_("(did you forget to compile extensions?)\n"))
         elif m in "zlib".split():
             ui.warn(_("(is your Python install correct?)\n"))
     except IOError as inst:
         if util.safehasattr(inst, "code"):
             ui.warn(_("abort: %s\n") % inst)
         elif util.safehasattr(inst, "reason"):
             try: # usually it is in the form (errno, strerror)
                 reason = inst.reason.args[1]
             except (AttributeError, IndexError):
                 # it might be anything, for example a string
                 reason = inst.reason
             if isinstance(reason, unicode):
                 # SSLError of Python 2.7.9 contains a unicode
                 reason = encoding.unitolocal(reason)
             ui.warn(_("abort: error: %s\n") % reason)
         elif (util.safehasattr(inst, "args")
               and inst.args and inst.args[0] == errno.EPIPE):
             pass
         elif getattr(inst, "strerror", None):
             if getattr(inst, "filename", None):
                 ui.warn(_("abort: %s: %s\n") % (
                     encoding.strtolocal(inst.strerror), inst.filename))
             else:
                 ui.warn(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
         else:
             raise
     except OSError as inst:
         if getattr(inst, "filename", None) is not None:
             ui.warn(_("abort: %s: '%s'\n") % (
                 encoding.strtolocal(inst.strerror), inst.filename))
         else:
             ui.warn(_("abort: %s\n") % encoding.strtolocal(inst.strerror))
     except MemoryError:
         ui.warn(_("abort: out of memory\n"))
     except SystemExit as inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         return inst.code
     except socket.error as inst:
         ui.warn(_("abort: %s\n") % inst.args[-1])
 
     return -1
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise error.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise error.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise error.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise error.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %s" % (msg, util.shellquote(f))
             if abort:
                 raise error.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = pycompat.osname == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise error.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 def filteredhash(repo, maxrev):
     """build hash of filtered revisions in the current repoview.
 
     Multiple caches perform up-to-date validation by checking that the
     tiprev and tipnode stored in the cache file match the current repository.
     However, this is not sufficient for validating repoviews because the set
     of revisions in the view may change without the repository tiprev and
     tipnode changing.
 
     This function hashes all the revs filtered from the view and returns
     that SHA-1 digest.
     """
     cl = repo.changelog
     if not cl.filteredrevs:
         return None
     key = None
     revs = sorted(r for r in cl.filteredrevs if r <= maxrev)
     if revs:
         s = hashlib.sha1()
         for rev in revs:
             s.update('%d;' % rev)
         key = s.digest()
     return key
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def binnode(ctx):
     """Return binary node id for a given basectx"""
     node = ctx.node()
     if node is None:
         return wdirid
     return node
 
 def intrev(ctx):
     """Return integer for a given basectx that can be used in comparison or
     arithmetic operation"""
     rev = ctx.rev()
     if rev is None:
         return wdirrev
     return rev
 
 def formatchangeid(ctx):
     """Format changectx as '{rev}:{node|formatnode}', which is the default
     template provided by cmdutil.changeset_templater"""
     repo = ctx.repo()
     return formatrevnode(repo.ui, intrev(ctx), binnode(ctx))
 
 def formatrevnode(ui, rev, node):
     """Format given revision and node depending on the current verbosity"""
     if ui.debugflag:
         hexfunc = hex
     else:
         hexfunc = short
     return '%d:%s' % (rev, hexfunc(node))
 
 def revsingle(repo, revspec, default='.', localalias=None):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec], localalias=localalias)
     if not l:
         raise error.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def _pairspec(revspec):
     tree = revsetlang.parse(revspec)
     return tree and tree[0] in ('range', 'rangepre', 'rangepost', 'rangeall')
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise error.Abort(_('empty revision range'))
     if (first == second and len(revs) >= 2
         and not all(revrange(repo, [r]) for r in revs)):
         raise error.Abort(_('empty revision on one side of range'))
 
     # if top-level is range expression, the result must always be a pair
     if first == second and len(revs) == 1 and not _pairspec(revs[0]):
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 def revrange(repo, specs, localalias=None):
     """Execute 1 to many revsets and return the union.
 
     This is the preferred mechanism for executing revsets using user-specified
     config options, such as revset aliases.
 
     The revsets specified by ``specs`` will be executed via a chained ``OR``
     expression. If ``specs`` is empty, an empty result is returned.
 
     ``specs`` can contain integers, in which case they are assumed to be
     revision numbers.
 
     It is assumed the revsets are already formatted. If you have arguments
     that need to be expanded in the revset, call ``revsetlang.formatspec()``
     and pass the result as an element of ``specs``.
 
     Specifying a single revset is allowed.
 
     Returns a ``revset.abstractsmartset`` which is a list-like interface over
     integer revisions.
     """
     allspecs = []
     for spec in specs:
         if isinstance(spec, int):
             spec = revsetlang.formatspec('rev(%d)', spec)
         allspecs.append(spec)
     return repo.anyrevs(allspecs, user=True, localalias=localalias)
 
 def meaningfulparents(repo, ctx):
     """Return list of meaningful (or all if debug) parentrevs for rev.
 
     For merges (two non-nullrev revisions) both parents are meaningful.
     Otherwise the first parent revision is considered meaningful if it
     is not the preceding revision.
     """
     parents = ctx.parents()
     if len(parents) > 1:
         return parents
     if repo.ui.debugflag:
         return [parents[0], repo['null']]
     if parents[0].rev() >= intrev(ctx) - 1:
         return []
     return parents
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=(), opts=None, globbed=False, default='relpath',
                  badfn=None):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches, unless an alternate badfn callback
     is provided.'''
     if pats == ("",):
         pats = []
     if opts is None:
         opts = {}
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     def bad(f, msg):
         ctx.repo().ui.warn("%s: %s\n" % (m.rel(f), msg))
 
     if badfn is None:
         badfn = bad
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                   default, listsubrepos=opts.get('subrepos'), badfn=badfn)
 
     if m.always():
         pats = []
     return m, pats
 
 def match(ctx, pats=(), opts=None, globbed=False, default='relpath',
           badfn=None):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default, badfn=badfn)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files, badfn=None):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files, badfn=badfn)
 
 def origpath(ui, repo, filepath):
     '''customize where .orig files are created
 
     Fetch user defined path from config file: [ui] origbackuppath = <path>
     Fall back to default (filepath with .orig suffix) if not specified
     '''
     origbackuppath = ui.config('ui', 'origbackuppath')
     if origbackuppath is None:
         return filepath + ".orig"
 
     filepathfromroot = os.path.relpath(filepath, start=repo.root)
     fullorigpath = repo.wjoin(origbackuppath, filepathfromroot)
 
     origbackupdir = repo.vfs.dirname(fullorigpath)
     if not repo.vfs.exists(origbackupdir):
         ui.note(_('creating directory: %s\n') % origbackupdir)
         util.makedirs(origbackupdir)
 
     return fullorigpath
 
 class _containsnode(object):
     """proxy __contains__(node) to container.__contains__ which accepts revs"""
 
     def __init__(self, repo, revcontainer):
         self._torev = repo.changelog.rev
         self._revcontains = revcontainer.__contains__
 
     def __contains__(self, node):
         return self._revcontains(self._torev(node))
 
 def cleanupnodes(repo, mapping, operation):
     """do common cleanups when old nodes are replaced by new nodes
 
     That includes writing obsmarkers or stripping nodes, and moving bookmarks.
     (we might also want to move working directory parent in the future)
 
     mapping is {oldnode: [newnode]} or a iterable of nodes if they do not have
     replacements. operation is a string, like "rebase".
     """
     if not util.safehasattr(mapping, 'items'):
         mapping = {n: () for n in mapping}
 
     with repo.transaction('cleanup') as tr:
         # Move bookmarks
         bmarks = repo._bookmarks
         bmarkchanges = []
         allnewnodes = [n for ns in mapping.values() for n in ns]
         for oldnode, newnodes in mapping.items():
             oldbmarks = repo.nodebookmarks(oldnode)
             if not oldbmarks:
                 continue
             from . import bookmarks # avoid import cycle
             if len(newnodes) > 1:
                 # usually a split, take the one with biggest rev number
                 newnode = next(repo.set('max(%ln)', newnodes)).node()
             elif len(newnodes) == 0:
                 # move bookmark backwards
                 roots = list(repo.set('max((::%n) - %ln)', oldnode,
                                       list(mapping)))
                 if roots:
                     newnode = roots[0].node()
                 else:
                     newnode = nullid
             else:
                 newnode = newnodes[0]
             repo.ui.debug('moving bookmarks %r from %s to %s\n' %
                           (oldbmarks, hex(oldnode), hex(newnode)))
             # Delete divergent bookmarks being parents of related newnodes
             deleterevs = repo.revs('parents(roots(%ln & (::%n))) - parents(%n)',
                                    allnewnodes, newnode, oldnode)
             deletenodes = _containsnode(repo, deleterevs)
             for name in oldbmarks:
                 bmarkchanges.append((name, newnode))
                 for b in bookmarks.divergent2delete(repo, deletenodes, name):
                     bmarkchanges.append((b, None))
 
         if bmarkchanges:
             bmarks.applychanges(repo, tr, bmarkchanges)
 
         # Obsolete or strip nodes
         if obsolete.isenabled(repo, obsolete.createmarkersopt):
             # If a node is already obsoleted, and we want to obsolete it
             # without a successor, skip that obssolete request since it's
             # unnecessary. That's the "if s or not isobs(n)" check below.
             # Also sort the node in topology order, that might be useful for
             # some obsstore logic.
             # NOTE: the filtering and sorting might belong to createmarkers.
             # Unfiltered repo is needed since nodes in mapping might be hidden.
             unfi = repo.unfiltered()
             isobs = unfi.obsstore.successors.__contains__
             torev = unfi.changelog.rev
             sortfunc = lambda ns: torev(ns[0])
             rels = [(unfi[n], tuple(unfi[m] for m in s))
                     for n, s in sorted(mapping.items(), key=sortfunc)
                     if s or not isobs(n)]
             obsolete.createmarkers(repo, rels, operation=operation)
         else:
             from . import repair # avoid import cycle
             repair.delayedstrip(repo.ui, repo, list(mapping), operation)
 
 def addremove(repo, matcher, prefix, opts=None, dry_run=None, similarity=None):
     if opts is None:
         opts = {}
     m = matcher
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         if opts.get('subrepos') or m.exact(subpath) or any(submatch.files()):
             sub = wctx.sub(subpath)
             try:
                 if sub.addremove(submatch, prefix, opts, dry_run, similarity):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(_("skipping missing subrepository: %s\n")
                                  % join(subpath))
 
     rejected = []
     def badfn(f, msg):
         if f in m.files():
             m.bad(f, msg)
         rejected.append(f)
 
     badmatch = matchmod.badmatch(m, badfn)
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo,
                                                                     badmatch)
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _('adding %s\n') % m.uipath(abs)
             else:
                 status = _('removing %s\n') % m.uipath(abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files, badfn=lambda x, y: rejected.append(x))
     rejected = []
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root, cached=True)
 
     ctx = repo[None]
     dirstate = repo.dirstate
-    walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
-                                full=False)
+    walkresults = dirstate.walk(matcher, subrepos=sorted(ctx.substate),
+                                unknown=True, ignored=False, full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     with repo.wlock():
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see https://mercurial-scm.org/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 def writerequires(opener, requirements):
     with opener('requires', 'w') as fp:
         for r in sorted(requirements):
             fp.write("%s\n" % r)
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behavior as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         raise NotImplementedError
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__.encode('ascii')
         return self
 
     def __get__(self, obj, type=None):
         # if accessed on the class, return the descriptor itself.
         if obj is None:
             return self
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 def _locksub(repo, lock, envvar, cmd, environ=None, *args, **kwargs):
     if lock is None:
         raise error.LockInheritanceContractViolation(
             'lock can only be inherited while held')
     if environ is None:
         environ = {}
     with lock.inherit() as locker:
         environ[envvar] = locker
         return repo.ui.system(cmd, environ=environ, *args, **kwargs)
 
 def wlocksub(repo, cmd, *args, **kwargs):
     """run cmd as a subprocess that allows inheriting repo's wlock
 
     This can only be called while the wlock is held. This takes all the
     arguments that ui.system does, and returns the exit code of the
     subprocess."""
     return _locksub(repo, repo.currentwlock(), 'HG_WLOCK_LOCKER', cmd, *args,
                     **kwargs)
 
 def gdinitconfig(ui):
     """helper function to know if a repo should be created as general delta
     """
     # experimental config: format.generaldelta
     return (ui.configbool('format', 'generaldelta')
             or ui.configbool('format', 'usegeneraldelta'))
 
 def gddeltaconfig(ui):
     """helper function to know if incoming delta should be optimised
     """
     # experimental config: format.generaldelta
     return ui.configbool('format', 'generaldelta')
 
 class simplekeyvaluefile(object):
     """A simple file with key=value lines
 
     Keys must be alphanumerics and start with a letter, values must not
     contain '\n' characters"""
     firstlinekey = '__firstline'
 
     def __init__(self, vfs, path, keys=None):
         self.vfs = vfs
         self.path = path
 
     def read(self, firstlinenonkeyval=False):
         """Read the contents of a simple key-value file
 
         'firstlinenonkeyval' indicates whether the first line of file should
         be treated as a key-value pair or reuturned fully under the
         __firstline key."""
         lines = self.vfs.readlines(self.path)
         d = {}
         if firstlinenonkeyval:
             if not lines:
                 e = _("empty simplekeyvalue file")
                 raise error.CorruptedState(e)
             # we don't want to include '\n' in the __firstline
             d[self.firstlinekey] = lines[0][:-1]
             del lines[0]
 
         try:
             # the 'if line.strip()' part prevents us from failing on empty
             # lines which only contain '\n' therefore are not skipped
             # by 'if line'
             updatedict = dict(line[:-1].split('=', 1) for line in lines
                                                       if line.strip())
             if self.firstlinekey in updatedict:
                 e = _("%r can't be used as a key")
                 raise error.CorruptedState(e % self.firstlinekey)
             d.update(updatedict)
         except ValueError as e:
             raise error.CorruptedState(str(e))
         return d
 
     def write(self, data, firstline=None):
         """Write key=>value mapping to a file
         data is a dict. Keys must be alphanumerical and start with a letter.
         Values must not contain newline characters.
 
         If 'firstline' is not None, it is written to file before
         everything else, as it is, not in a key=value form"""
         lines = []
         if firstline is not None:
             lines.append('%s\n' % firstline)
 
         for k, v in data.items():
             if k == self.firstlinekey:
                 e = "key name '%s' is reserved" % self.firstlinekey
                 raise error.ProgrammingError(e)
             if not k[0].isalpha():
                 e = "keys must start with a letter in a key-value file"
                 raise error.ProgrammingError(e)
             if not k.isalnum():
                 e = "invalid key name in a simple key-value file"
                 raise error.ProgrammingError(e)
             if '\n' in v:
                 e = "invalid value in a simple key-value file"
                 raise error.ProgrammingError(e)
             lines.append("%s=%s\n" % (k, v))
         with self.vfs(self.path, mode='wb', atomictemp=True) as fp:
             fp.write(''.join(lines))
 
 _reportobsoletedsource = [
     'debugobsolete',
     'pull',
     'push',
     'serve',
     'unbundle',
 ]
 
 def registersummarycallback(repo, otr, txnname=''):
     """register a callback to issue a summary after the transaction is closed
     """
     for source in _reportobsoletedsource:
         if txnname.startswith(source):
             reporef = weakref.ref(repo)
             def reportsummary(tr):
                 """the actual callback reporting the summary"""
                 repo = reporef()
                 obsoleted = obsutil.getobsoleted(repo, tr)
                 if obsoleted:
                     repo.ui.status(_('obsoleted %i changesets\n')
                                    % len(obsoleted))
             otr.addpostclose('00-txnreport', reportsummary)
             break