merge with stable

contrib/perf.py

@@ -1,1889 +1,1946 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 threading
 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
 try:
     from mercurial import pycompat
     getargspec = pycompat.getargspec  # added to module after 4.5
 except (ImportError, AttributeError):
     import inspect
     getargspec = inspect.getargspec
 
 try:
     # 4.7+
     queue = pycompat.queue.Queue
 except (AttributeError, ImportError):
     # <4.7.
     try:
         queue = pycompat.queue
     except (AttributeError, ImportError):
         queue = util.queue
 
 try:
     from mercurial import logcmdutil
     makelogtemplater = logcmdutil.maketemplater
 except (AttributeError, ImportError):
     try:
         makelogtemplater = cmdutil.makelogtemplater
     except (AttributeError, ImportError):
         makelogtemplater = None
 
 # 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'):
     command = cmdutil.command(cmdtable)
     if 'norepo' not in getargspec(command).args:
         # 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
 
 try:
     import mercurial.registrar
     import mercurial.configitems
     configtable = {}
     configitem = mercurial.registrar.configitem(configtable)
     configitem('perf', 'presleep',
         default=mercurial.configitems.dynamicdefault,
     )
     configitem('perf', 'stub',
         default=mercurial.configitems.dynamicdefault,
     )
     configitem('perf', 'parentscount',
         default=mercurial.configitems.dynamicdefault,
     )
     configitem('perf', 'all-timing',
         default=mercurial.configitems.dynamicdefault,
     )
 except (ImportError, AttributeError):
     pass
 
 def getlen(ui):
     if ui.configbool("perf", "stub", False):
         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", False):
         return functools.partial(stub_timer, fm), fm
 
     # experimental config: perf.all-timing
     displayall = ui.configbool("perf", "all-timing", False)
     return functools.partial(_timer, fm, displayall=displayall), fm
 
 def stub_timer(fm, func, title=None):
     func()
 
 def _timer(fm, func, title=None, displayall=False):
     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)
     def display(role, entry):
         prefix = ''
         if role != 'best':
             prefix = '%s.' % role
         fm.plain('!')
         fm.write(prefix + 'wall', ' wall %f', entry[0])
         fm.write(prefix + 'comb', ' comb %f', entry[1] + entry[2])
         fm.write(prefix + 'user', ' user %f', entry[1])
         fm.write(prefix + 'sys',  ' sys %f', entry[2])
         fm.write(prefix + 'count',  ' (%s of %d)', role, count)
         fm.plain('\n')
     results.sort()
     min_val = results[0]
     display('best', min_val)
     if displayall:
         max_val = results[-1]
         display('max', max_val)
         avg = tuple([sum(x) / count for x in zip(*results)])
         display('avg', avg)
         median = results[len(results) // 2]
         display('median', median)
 
 # 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, 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])
         opts['dry_run'] = True
         timer(lambda: scmutil.addremove(repo, matcher, "", opts))
     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('perfbundleread', formatteropts, 'BUNDLE')
 def perfbundleread(ui, repo, bundlepath, **opts):
     """Benchmark reading of bundle files.
 
     This command is meant to isolate the I/O part of bundle reading as
     much as possible.
     """
     from mercurial import (
         bundle2,
         exchange,
         streamclone,
     )
 
     def makebench(fn):
         def run():
             with open(bundlepath, 'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 fn(bundle)
 
         return run
 
     def makereadnbytes(size):
         def run():
             with open(bundlepath, 'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 while bundle.read(size):
                     pass
 
         return run
 
     def makestdioread(size):
         def run():
             with open(bundlepath, 'rb') as fh:
                 while fh.read(size):
                     pass
 
         return run
 
     # bundle1
 
     def deltaiter(bundle):
         for delta in bundle.deltaiter():
             pass
 
     def iterchunks(bundle):
         for chunk in bundle.getchunks():
             pass
 
     # bundle2
 
     def forwardchunks(bundle):
         for chunk in bundle._forwardchunks():
             pass
 
     def iterparts(bundle):
         for part in bundle.iterparts():
             pass
 
     def iterpartsseekable(bundle):
         for part in bundle.iterparts(seekable=True):
             pass
 
     def seek(bundle):
         for part in bundle.iterparts(seekable=True):
             part.seek(0, os.SEEK_END)
 
     def makepartreadnbytes(size):
         def run():
             with open(bundlepath, 'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 for part in bundle.iterparts():
                     while part.read(size):
                         pass
 
         return run
 
     benches = [
         (makestdioread(8192), 'read(8k)'),
         (makestdioread(16384), 'read(16k)'),
         (makestdioread(32768), 'read(32k)'),
         (makestdioread(131072), 'read(128k)'),
     ]
 
     with open(bundlepath, 'rb') as fh:
         bundle = exchange.readbundle(ui, fh, bundlepath)
 
         if isinstance(bundle, changegroup.cg1unpacker):
             benches.extend([
                 (makebench(deltaiter), 'cg1 deltaiter()'),
                 (makebench(iterchunks), 'cg1 getchunks()'),
                 (makereadnbytes(8192), 'cg1 read(8k)'),
                 (makereadnbytes(16384), 'cg1 read(16k)'),
                 (makereadnbytes(32768), 'cg1 read(32k)'),
                 (makereadnbytes(131072), 'cg1 read(128k)'),
             ])
         elif isinstance(bundle, bundle2.unbundle20):
             benches.extend([
                 (makebench(forwardchunks), 'bundle2 forwardchunks()'),
                 (makebench(iterparts), 'bundle2 iterparts()'),
                 (makebench(iterpartsseekable), 'bundle2 iterparts() seekable'),
                 (makebench(seek), 'bundle2 part seek()'),
                 (makepartreadnbytes(8192), 'bundle2 part read(8k)'),
                 (makepartreadnbytes(16384), 'bundle2 part read(16k)'),
                 (makepartreadnbytes(32768), 'bundle2 part read(32k)'),
                 (makepartreadnbytes(131072), 'bundle2 part read(128k)'),
             ])
         elif isinstance(bundle, streamclone.streamcloneapplier):
             raise error.Abort('stream clone bundles not supported')
         else:
             raise error.Abort('unhandled bundle type: %s' % type(bundle))
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         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
     nodes = [cl.lookup(r) for r in repo.revs(rev or 'all()')]
     bundler = changegroup.getbundler(version, repo)
 
     def d():
         state, chunks = bundler._generatechangelog(cl, nodes)
         for chunk in chunks:
             pass
 
     timer, fm = gettimer(ui, opts)
 
     # Terminal printing can interfere with timing. So disable it.
     with ui.configoverride({('progress', 'disable'): True}):
         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.hasdir('a')
         del dirstate._map._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():
         repo.dirstate.hasdir("a")
         del repo.dirstate._map._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._map.filefoldmap.get('a')
         del dirstate._map.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._map.dirfoldmap.get('a')
         del dirstate._map.dirfoldmap
         del dirstate._map._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('perfphasesremote',
+         [], "[DEST]")
+def perfphasesremote(ui, repo, dest=None, **opts):
+    """benchmark time needed to analyse phases of the remote server"""
+    from mercurial.node import (
+        bin,
+    )
+    from mercurial import (
+        exchange,
+        hg,
+        phases,
+    )
+    timer, fm = gettimer(ui, opts)
+
+    path = ui.paths.getpath(dest, default=('default-push', 'default'))
+    if not path:
+        raise error.abort(('default repository not configured!'),
+                         hint=("see 'hg help config.paths'"))
+    dest = path.pushloc or path.loc
+    branches = (path.branch, opts.get('branch') or [])
+    ui.status(('analysing phase of %s\n') % util.hidepassword(dest))
+    revs, checkout = hg.addbranchrevs(repo, repo, branches, opts.get('rev'))
+    other = hg.peer(repo, opts, dest)
+
+    # easier to perform discovery through the operation
+    op = exchange.pushoperation(repo, other)
+    exchange._pushdiscoverychangeset(op)
+
+    remotesubset = op.fallbackheads
+
+    with other.commandexecutor() as e:
+        remotephases = e.callcommand('listkeys',
+                       {'namespace': 'phases'}).result()
+    del other
+    publishing = remotephases.get('publishing', False)
+    if publishing:
+        ui.status(('publishing: yes\n'))
+    else:
+        ui.status(('publishing: no\n'))
+
+    nodemap = repo.changelog.nodemap
+    nonpublishroots = 0
+    for nhex, phase in remotephases.iteritems():
+        if nhex == 'publishing': # ignore data related to publish option
+            continue
+        node = bin(nhex)
+        if node in nodemap and int(phase):
+            nonpublishroots += 1
+    ui.status(('number of roots: %d\n') % len(remotephases))
+    ui.status(('number of known non public roots: %d\n') % nonpublishroots)
+    def d():
+        phases.remotephasessummary(repo,
+                                   remotesubset,
+                                   remotephases)
+    timer(d)
+    fm.end()
+
 @command('perfmanifest',[
             ('m', 'manifest-rev', False, 'Look up a manifest node revision'),
             ('', 'clear-disk', False, 'clear on-disk caches too'),
          ], 'REV|NODE')
 def perfmanifest(ui, repo, rev, manifest_rev=False, clear_disk=False, **opts):
     """benchmark the time to read a manifest from disk and return a usable
     dict-like object
 
     Manifest caches are cleared before retrieval."""
     timer, fm = gettimer(ui, opts)
     if not manifest_rev:
         ctx = scmutil.revsingle(repo, rev, rev)
         t = ctx.manifestnode()
     else:
         t = repo.manifestlog._revlog.lookup(rev)
     def d():
         repo.manifestlog.clearcaches(clear_persisted_data=clear_disk)
         repo.manifestlog[t].read()
     timer(d)
     fm.end()
 
 @command('perfchangeset', formatteropts)
 def perfchangeset(ui, repo, rev, **opts):
     timer, fm = gettimer(ui, opts)
     n = scmutil.revsingle(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('perflinelogedits',
          [('n', 'edits', 10000, 'number of edits'),
           ('', 'max-hunk-lines', 10, 'max lines in a hunk'),
          ], norepo=True)
 def perflinelogedits(ui, **opts):
     from mercurial import linelog
 
     edits = opts['edits']
     maxhunklines = opts['max_hunk_lines']
 
     maxb1 = 100000
     random.seed(0)
     randint = random.randint
     currentlines = 0
     arglist = []
     for rev in xrange(edits):
         a1 = randint(0, currentlines)
         a2 = randint(a1, min(currentlines, a1 + maxhunklines))
         b1 = randint(0, maxb1)
         b2 = randint(b1, b1 + maxhunklines)
         currentlines += (b2 - b1) - (a2 - a1)
         arglist.append((rev, a1, a2, b1, b2))
 
     def d():
         ll = linelog.linelog()
         for args in arglist:
             ll.replacelines(*args)
 
     timer, fm = gettimer(ui, opts)
     timer(d)
     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 = scmutil.revsingle(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 repo.changelog.revs(start=(len(repo) - 1), stop=-1):
             ctx = repo[i]
             ctx.branch() # read changelog data (in addition to the index)
     timer(moonwalk)
     fm.end()
 
 @command('perftemplating',
          [('r', 'rev', [], 'revisions to run the template on'),
          ] + formatteropts)
 def perftemplating(ui, repo, testedtemplate=None, **opts):
     """test the rendering time of a given template"""
     if makelogtemplater is None:
         raise error.Abort(("perftemplating not available with this Mercurial"),
                           hint="use 4.3 or later")
 
     nullui = ui.copy()
     nullui.fout = open(os.devnull, 'wb')
     nullui.disablepager()
     revs = opts.get('rev')
     if not revs:
         revs = ['all()']
     revs = list(scmutil.revrange(repo, revs))
 
     defaulttemplate = ('{date|shortdate} [{rev}:{node|short}]'
                        ' {author|person}: {desc|firstline}\n')
     if testedtemplate is None:
         testedtemplate = defaulttemplate
     displayer = makelogtemplater(nullui, repo, testedtemplate)
     def format():
         for r in revs:
             ctx = repo[r]
             displayer.show(ctx)
             displayer.flush(ctx)
 
     timer, fm = gettimer(ui, opts)
     timer(format)
     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
     lock = repo.lock()
     s.fncache._load()
     tr = repo.transaction('perffncachewrite')
     tr.addbackup('fncache')
     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()
 
 def _bdiffworker(q, blocks, xdiff, ready, done):
     while not done.is_set():
         pair = q.get()
         while pair is not None:
             if xdiff:
                 mdiff.bdiff.xdiffblocks(*pair)
             elif blocks:
                 mdiff.bdiff.blocks(*pair)
             else:
                 mdiff.textdiff(*pair)
             q.task_done()
             pair = q.get()
         q.task_done() # for the None one
         with ready:
             ready.wait()
 
 @command('perfbdiff', revlogopts + formatteropts + [
     ('', 'count', 1, 'number of revisions to test (when using --startrev)'),
     ('', 'alldata', False, 'test bdiffs for all associated revisions'),
     ('', 'threads', 0, 'number of thread to use (disable with 0)'),
     ('', 'blocks', False, 'test computing diffs into blocks'),
     ('', 'xdiff', False, 'use xdiff algorithm'),
     ],
 
     '-c|-m|FILE REV')
 def perfbdiff(ui, repo, file_, rev=None, count=None, threads=0, **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).
     """
     opts = pycompat.byteskwargs(opts)
 
     if opts['xdiff'] and not opts['blocks']:
         raise error.CommandError('perfbdiff', '--xdiff requires --blocks')
 
     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')
 
     blocks = opts['blocks']
     xdiff = opts['xdiff']
     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)))
 
     withthreads = threads > 0
     if not withthreads:
         def d():
             for pair in textpairs:
                 if xdiff:
                     mdiff.bdiff.xdiffblocks(*pair)
                 elif blocks:
                     mdiff.bdiff.blocks(*pair)
                 else:
                     mdiff.textdiff(*pair)
     else:
         q = queue()
         for i in xrange(threads):
             q.put(None)
         ready = threading.Condition()
         done = threading.Event()
         for i in xrange(threads):
             threading.Thread(target=_bdiffworker,
                              args=(q, blocks, xdiff, ready, done)).start()
         q.join()
         def d():
             for pair in textpairs:
                 q.put(pair)
             for i in xrange(threads):
                 q.put(None)
             with ready:
                 ready.notify_all()
             q.join()
     timer, fm = gettimer(ui, opts)
     timer(d)
     fm.end()
 
     if withthreads:
         done.set()
         for i in xrange(threads):
             q.put(None)
         with ready:
             ready.notify_all()
 
 @command('perfunidiff', revlogopts + formatteropts + [
     ('', 'count', 1, 'number of revisions to test (when using --startrev)'),
     ('', 'alldata', False, 'test unidiffs for all associated revisions'),
     ], '-c|-m|FILE REV')
 def perfunidiff(ui, repo, file_, rev=None, count=None, **opts):
     """benchmark a unified diff between revisions
 
     This doesn't include any copy tracing - it's just a unified diff
     of the texts.
 
     By default, benchmark a diff between its delta parent and itself.
 
     With ``--count``, benchmark diffs between delta parents and self for N
     revisions starting at the specified revision.
 
     With ``--alldata``, assume the requested revision is a changeset and
     measure diffs 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('perfunidiff', 'invalid arguments')
 
     textpairs = []
 
     r = cmdutil.openrevlog(repo, 'perfunidiff', 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 left, right in textpairs:
             # The date strings don't matter, so we pass empty strings.
             headerlines, hunks = mdiff.unidiff(
                 left, '', right, '', 'left', 'right', binary=False)
             # consume iterators in roughly the way patch.py does
             b'\n'.join(headerlines)
             b''.join(sum((list(hlines) for hrange, hlines in hunks), []))
     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, *filternames, **opts):
     """benchmark the update of a branchmap
 
     This benchmarks the full repo.branchmap() call with read and write disabled
     """
     full = opts.get("full", False)
     clear_revbranch = opts.get("clear_revbranch", False)
     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)
     if filternames:
         possiblefilters &= set(filternames)
     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()
     if not filternames or 'unfiltered' in filternames:
         # 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:
             printname = name
             if name is None:
                 printname = 'unfiltered'
             timer(getbranchmap(name), title=str(printname))
     finally:
         branchcacheread.restore()
         branchcachewrite.restore()
     fm.end()
 
 @command('perfbranchmapload', [
      ('f', 'filter', '', 'Specify repoview filter'),
      ('', 'list', False, 'List brachmap filter caches'),
     ] + formatteropts)
 def perfbranchmapread(ui, repo, filter='', list=False, **opts):
     """benchmark reading the branchmap"""
     if list:
         for name, kind, st in repo.cachevfs.readdir(stat=True):
             if name.startswith('branch2'):
                 filtername = name.partition('-')[2] or 'unfiltered'
                 ui.status('%s - %s\n'
                           % (filtername, util.bytecount(st.st_size)))
         return
     if filter:
         repo = repoview.repoview(repo, filter)
     else:
         repo = repo.unfiltered()
     # try once without timer, the filter may not be cached
     if branchmap.read(repo) is None:
         raise error.Abort('No brachmap cached for %s repo'
                           % (filter or 'unfiltered'))
     timer, fm = gettimer(ui, opts)
     timer(lambda: branchmap.read(repo) and None)
     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)

mercurial/phases.py

@@ -1,698 +1,728 b''
 """ Mercurial phases support code
 
     ---
 
     Copyright 2011 Pierre-Yves David <[e-mail]>
                    Logilab SA        <[e-mail]>
                    Augie Fackler     <[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.
 
     ---
 
 This module implements most phase logic in mercurial.
 
 
 Basic Concept
 =============
 
 A 'changeset phase' is an indicator that tells us how a changeset is
 manipulated and communicated. The details of each phase is described
 below, here we describe the properties they have in common.
 
 Like bookmarks, phases are not stored in history and thus are not
 permanent and leave no audit trail.
 
 First, no changeset can be in two phases at once. Phases are ordered,
 so they can be considered from lowest to highest. The default, lowest
 phase is 'public' - this is the normal phase of existing changesets. A
 child changeset can not be in a lower phase than its parents.
 
 These phases share a hierarchy of traits:
 
             immutable shared
     public:     X        X
     draft:               X
     secret:
 
 Local commits are draft by default.
 
 Phase Movement and Exchange
 ===========================
 
 Phase data is exchanged by pushkey on pull and push. Some servers have
 a publish option set, we call such a server a "publishing server".
 Pushing a draft changeset to a publishing server changes the phase to
 public.
 
 A small list of fact/rules define the exchange of phase:
 
 * old client never changes server states
 * pull never changes server states
 * publish and old server changesets are seen as public by client
 * any secret changeset seen in another repository is lowered to at
   least draft
 
 Here is the final table summing up the 49 possible use cases of phase
 exchange:
 
                            server
                   old     publish      non-publish
                  N   X    N   D   P    N   D   P
     old client
     pull
      N           -   X/X  -   X/D X/P  -   X/D X/P
      X           -   X/X  -   X/D X/P  -   X/D X/P
     push
      X           X/X X/X  X/P X/P X/P  X/D X/D X/P
     new client
     pull
      N           -   P/X  -   P/D P/P  -   D/D P/P
      D           -   P/X  -   P/D P/P  -   D/D P/P
      P           -   P/X  -   P/D P/P  -   P/D P/P
     push
      D           P/X P/X  P/P P/P P/P  D/D D/D P/P
      P           P/X P/X  P/P P/P P/P  P/P P/P P/P
 
 Legend:
 
     A/B = final state on client / state on server
 
     * N = new/not present,
     * P = public,
     * D = draft,
     * X = not tracked (i.e., the old client or server has no internal
           way of recording the phase.)
 
     passive = only pushes
 
 
     A cell here can be read like this:
 
     "When a new client pushes a draft changeset (D) to a publishing
     server where it's not present (N), it's marked public on both
     sides (P/P)."
 
 Note: old client behave as a publishing server with draft only content
 - other people see it as public
 - content is pushed as draft
 
 """
 
 from __future__ import absolute_import
 
 import errno
 import struct
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from . import (
     error,
     pycompat,
     smartset,
     txnutil,
     util,
 )
 
 _fphasesentry = struct.Struct('>i20s')
 
 allphases = public, draft, secret = range(3)
 trackedphases = allphases[1:]
 phasenames = ['public', 'draft', 'secret']
 mutablephases = tuple(allphases[1:])
 remotehiddenphases = tuple(allphases[2:])
 
 def _readroots(repo, phasedefaults=None):
     """Read phase roots from disk
 
     phasedefaults is a list of fn(repo, roots) callable, which are
     executed if the phase roots file does not exist. When phases are
     being initialized on an existing repository, this could be used to
     set selected changesets phase to something else than public.
 
     Return (roots, dirty) where dirty is true if roots differ from
     what is being stored.
     """
     repo = repo.unfiltered()
     dirty = False
     roots = [set() for i in allphases]
     try:
         f, pending = txnutil.trypending(repo.root, repo.svfs, 'phaseroots')
         try:
             for line in f:
                 phase, nh = line.split()
                 roots[int(phase)].add(bin(nh))
         finally:
             f.close()
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         if phasedefaults:
             for f in phasedefaults:
                 roots = f(repo, roots)
         dirty = True
     return roots, dirty
 
 def binaryencode(phasemapping):
     """encode a 'phase -> nodes' mapping into a binary stream
 
     Since phases are integer the mapping is actually a python list:
     [[PUBLIC_HEADS], [DRAFTS_HEADS], [SECRET_HEADS]]
     """
     binarydata = []
     for phase, nodes in enumerate(phasemapping):
         for head in nodes:
             binarydata.append(_fphasesentry.pack(phase, head))
     return ''.join(binarydata)
 
 def binarydecode(stream):
     """decode a binary stream into a 'phase -> nodes' mapping
 
     Since phases are integer the mapping is actually a python list."""
     headsbyphase = [[] for i in allphases]
     entrysize = _fphasesentry.size
     while True:
         entry = stream.read(entrysize)
         if len(entry) < entrysize:
             if entry:
                 raise error.Abort(_('bad phase-heads stream'))
             break
         phase, node = _fphasesentry.unpack(entry)
         headsbyphase[phase].append(node)
     return headsbyphase
 
 def _trackphasechange(data, rev, old, new):
     """add a phase move the <data> dictionnary
 
     If data is None, nothing happens.
     """
     if data is None:
         return
     existing = data.get(rev)
     if existing is not None:
         old = existing[0]
     data[rev] = (old, new)
 
 class phasecache(object):
     def __init__(self, repo, phasedefaults, _load=True):
         if _load:
             # Cheap trick to allow shallow-copy without copy module
             self.phaseroots, self.dirty = _readroots(repo, phasedefaults)
             self._loadedrevslen = 0
             self._phasesets = None
             self.filterunknown(repo)
             self.opener = repo.svfs
 
     def getrevset(self, repo, phases, subset=None):
         """return a smartset for the given phases"""
         self.loadphaserevs(repo) # ensure phase's sets are loaded
         phases = set(phases)
         if public not in phases:
             # fast path: _phasesets contains the interesting sets,
             # might only need a union and post-filtering.
             if len(phases) == 1:
                 [p] = phases
                 revs = self._phasesets[p]
             else:
                 revs = set.union(*[self._phasesets[p] for p in phases])
             if repo.changelog.filteredrevs:
                 revs = revs - repo.changelog.filteredrevs
             if subset is None:
                 return smartset.baseset(revs)
             else:
                 return subset & smartset.baseset(revs)
         else:
             phases = set(allphases).difference(phases)
             if not phases:
                 return smartset.fullreposet(repo)
             if len(phases) == 1:
                 [p] = phases
                 revs = self._phasesets[p]
             else:
                 revs = set.union(*[self._phasesets[p] for p in phases])
             if subset is None:
                 subset = smartset.fullreposet(repo)
             if not revs:
                 return subset
             return subset.filter(lambda r: r not in revs)
 
     def copy(self):
         # Shallow copy meant to ensure isolation in
         # advance/retractboundary(), nothing more.
         ph = self.__class__(None, None, _load=False)
         ph.phaseroots = self.phaseroots[:]
         ph.dirty = self.dirty
         ph.opener = self.opener
         ph._loadedrevslen = self._loadedrevslen
         ph._phasesets = self._phasesets
         return ph
 
     def replace(self, phcache):
         """replace all values in 'self' with content of phcache"""
         for a in ('phaseroots', 'dirty', 'opener', '_loadedrevslen',
                   '_phasesets'):
             setattr(self, a, getattr(phcache, a))
 
     def _getphaserevsnative(self, repo):
         repo = repo.unfiltered()
         nativeroots = []
         for phase in trackedphases:
             nativeroots.append(pycompat.maplist(repo.changelog.rev,
                                                 self.phaseroots[phase]))
         return repo.changelog.computephases(nativeroots)
 
     def _computephaserevspure(self, repo):
         repo = repo.unfiltered()
         cl = repo.changelog
         self._phasesets = [set() for phase in allphases]
         roots = pycompat.maplist(cl.rev, self.phaseroots[secret])
         if roots:
             ps = set(cl.descendants(roots))
             for root in roots:
                 ps.add(root)
             self._phasesets[secret] = ps
         roots = pycompat.maplist(cl.rev, self.phaseroots[draft])
         if roots:
             ps = set(cl.descendants(roots))
             for root in roots:
                 ps.add(root)
             ps.difference_update(self._phasesets[secret])
             self._phasesets[draft] = ps
         self._loadedrevslen = len(cl)
 
     def loadphaserevs(self, repo):
         """ensure phase information is loaded in the object"""
         if self._phasesets is None:
             try:
                 res = self._getphaserevsnative(repo)
                 self._loadedrevslen, self._phasesets = res
             except AttributeError:
                 self._computephaserevspure(repo)
 
     def invalidate(self):
         self._loadedrevslen = 0
         self._phasesets = None
 
     def phase(self, repo, rev):
         # We need a repo argument here to be able to build _phasesets
         # if necessary. The repository instance is not stored in
         # phasecache to avoid reference cycles. The changelog instance
         # is not stored because it is a filecache() property and can
         # be replaced without us being notified.
         if rev == nullrev:
             return public
         if rev < nullrev:
             raise ValueError(_('cannot lookup negative revision'))
         if rev >= self._loadedrevslen:
             self.invalidate()
             self.loadphaserevs(repo)
         for phase in trackedphases:
             if rev in self._phasesets[phase]:
                 return phase
         return public
 
     def write(self):
         if not self.dirty:
             return
         f = self.opener('phaseroots', 'w', atomictemp=True, checkambig=True)
         try:
             self._write(f)
         finally:
             f.close()
 
     def _write(self, fp):
         for phase, roots in enumerate(self.phaseroots):
             for h in sorted(roots):
                 fp.write('%i %s\n' % (phase, hex(h)))
         self.dirty = False
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
         tr.addfilegenerator('phase', ('phaseroots',), self._write)
         tr.hookargs['phases_moved'] = '1'
 
     def registernew(self, repo, tr, targetphase, nodes):
         repo = repo.unfiltered()
         self._retractboundary(repo, tr, targetphase, nodes)
         if tr is not None and 'phases' in tr.changes:
             phasetracking = tr.changes['phases']
             torev = repo.changelog.rev
             phase = self.phase
             for n in nodes:
                 rev = torev(n)
                 revphase = phase(repo, rev)
                 _trackphasechange(phasetracking, rev, None, revphase)
         repo.invalidatevolatilesets()
 
     def advanceboundary(self, repo, tr, targetphase, nodes, dryrun=None):
         """Set all 'nodes' to phase 'targetphase'
 
         Nodes with a phase lower than 'targetphase' are not affected.
 
         If dryrun is True, no actions will be performed
 
         Returns a set of revs whose phase is changed or should be changed
         """
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get('phases')
 
         repo = repo.unfiltered()
 
         changes = set() # set of revisions to be changed
         delroots = [] # set of root deleted by this path
         for phase in pycompat.xrange(targetphase + 1, len(allphases)):
             # filter nodes that are not in a compatible phase already
             nodes = [n for n in nodes
                      if self.phase(repo, repo[n].rev()) >= phase]
             if not nodes:
                 break # no roots to move anymore
 
             olds = self.phaseroots[phase]
 
             affected = repo.revs('%ln::%ln', olds, nodes)
             changes.update(affected)
             if dryrun:
                 continue
             for r in affected:
                 _trackphasechange(phasetracking, r, self.phase(repo, r),
                                   targetphase)
 
             roots = set(ctx.node() for ctx in repo.set(
                     'roots((%ln::) - %ld)', olds, affected))
             if olds != roots:
                 self._updateroots(phase, roots, tr)
                 # some roots may need to be declared for lower phases
                 delroots.extend(olds - roots)
         if not dryrun:
             # declare deleted root in the target phase
             if targetphase != 0:
                 self._retractboundary(repo, tr, targetphase, delroots)
             repo.invalidatevolatilesets()
         return changes
 
     def retractboundary(self, repo, tr, targetphase, nodes):
         oldroots = self.phaseroots[:targetphase + 1]
         if tr is None:
             phasetracking = None
         else:
             phasetracking = tr.changes.get('phases')
         repo = repo.unfiltered()
         if (self._retractboundary(repo, tr, targetphase, nodes)
             and phasetracking is not None):
 
             # find the affected revisions
             new = self.phaseroots[targetphase]
             old = oldroots[targetphase]
             affected = set(repo.revs('(%ln::) - (%ln::)', new, old))
 
             # find the phase of the affected revision
             for phase in pycompat.xrange(targetphase, -1, -1):
                 if phase:
                     roots = oldroots[phase]
                     revs = set(repo.revs('%ln::%ld', roots, affected))
                     affected -= revs
                 else: # public phase
                     revs = affected
                 for r in revs:
                     _trackphasechange(phasetracking, r, phase, targetphase)
         repo.invalidatevolatilesets()
 
     def _retractboundary(self, repo, tr, targetphase, nodes):
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
 
         repo = repo.unfiltered()
         currentroots = self.phaseroots[targetphase]
         finalroots = oldroots = set(currentroots)
         newroots = [n for n in nodes
                     if self.phase(repo, repo[n].rev()) < targetphase]
         if newroots:
 
             if nullid in newroots:
                 raise error.Abort(_('cannot change null revision phase'))
             currentroots = currentroots.copy()
             currentroots.update(newroots)
 
             # Only compute new roots for revs above the roots that are being
             # retracted.
             minnewroot = min(repo[n].rev() for n in newroots)
             aboveroots = [n for n in currentroots
                           if repo[n].rev() >= minnewroot]
             updatedroots = repo.set('roots(%ln::)', aboveroots)
 
             finalroots = set(n for n in currentroots if repo[n].rev() <
                              minnewroot)
             finalroots.update(ctx.node() for ctx in updatedroots)
         if finalroots != oldroots:
             self._updateroots(targetphase, finalroots, tr)
             return True
         return False
 
     def filterunknown(self, repo):
         """remove unknown nodes from the phase boundary
 
         Nothing is lost as unknown nodes only hold data for their descendants.
         """
         filtered = False
         nodemap = repo.changelog.nodemap # to filter unknown nodes
         for phase, nodes in enumerate(self.phaseroots):
             missing = sorted(node for node in nodes if node not in nodemap)
             if missing:
                 for mnode in missing:
                     repo.ui.debug(
                         'removing unknown node %s from %i-phase boundary\n'
                         % (short(mnode), phase))
                 nodes.symmetric_difference_update(missing)
                 filtered = True
         if filtered:
             self.dirty = True
         # filterunknown is called by repo.destroyed, we may have no changes in
         # root but _phasesets contents is certainly invalid (or at least we
         # have not proper way to check that). related to issue 3858.
         #
         # The other caller is __init__ that have no _phasesets initialized
         # anyway. If this change we should consider adding a dedicated
         # "destroyed" function to phasecache or a proper cache key mechanism
         # (see branchmap one)
         self.invalidate()
 
 def advanceboundary(repo, tr, targetphase, nodes, dryrun=None):
     """Add nodes to a phase changing other nodes phases if necessary.
 
     This function move boundary *forward* this means that all nodes
     are set in the target phase or kept in a *lower* phase.
 
     Simplify boundary to contains phase roots only.
 
     If dryrun is True, no actions will be performed
 
     Returns a set of revs whose phase is changed or should be changed
     """
     phcache = repo._phasecache.copy()
     changes = phcache.advanceboundary(repo, tr, targetphase, nodes,
                                       dryrun=dryrun)
     if not dryrun:
         repo._phasecache.replace(phcache)
     return changes
 
 def retractboundary(repo, tr, targetphase, nodes):
     """Set nodes back to a phase changing other nodes phases if
     necessary.
 
     This function move boundary *backward* this means that all nodes
     are set in the target phase or kept in a *higher* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.retractboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def registernew(repo, tr, targetphase, nodes):
     """register a new revision and its phase
 
     Code adding revisions to the repository should use this function to
     set new changeset in their target phase (or higher).
     """
     phcache = repo._phasecache.copy()
     phcache.registernew(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def listphases(repo):
     """List phases root for serialization over pushkey"""
     # Use ordered dictionary so behavior is deterministic.
     keys = util.sortdict()
     value = '%i' % draft
     cl = repo.unfiltered().changelog
     for root in repo._phasecache.phaseroots[draft]:
         if repo._phasecache.phase(repo, cl.rev(root)) <= draft:
             keys[hex(root)] = value
 
     if repo.publishing():
         # Add an extra data to let remote know we are a publishing
         # repo. Publishing repo can't just pretend they are old repo.
         # When pushing to a publishing repo, the client still need to
         # push phase boundary
         #
         # Push do not only push changeset. It also push phase data.
         # New phase data may apply to common changeset which won't be
         # push (as they are common). Here is a very simple example:
         #
         # 1) repo A push changeset X as draft to repo B
         # 2) repo B make changeset X public
         # 3) repo B push to repo A. X is not pushed but the data that
         #    X as now public should
         #
         # The server can't handle it on it's own as it has no idea of
         # client phase data.
         keys['publishing'] = 'True'
     return keys
 
 def pushphase(repo, nhex, oldphasestr, newphasestr):
     """List phases root for serialization over pushkey"""
     repo = repo.unfiltered()
     with repo.lock():
         currentphase = repo[nhex].phase()
         newphase = abs(int(newphasestr)) # let's avoid negative index surprise
         oldphase = abs(int(oldphasestr)) # let's avoid negative index surprise
         if currentphase == oldphase and newphase < oldphase:
             with repo.transaction('pushkey-phase') as tr:
                 advanceboundary(repo, tr, newphase, [bin(nhex)])
             return True
         elif currentphase == newphase:
             # raced, but got correct result
             return True
         else:
             return False
 
 def subsetphaseheads(repo, subset):
     """Finds the phase heads for a subset of a history
 
     Returns a list indexed by phase number where each item is a list of phase
     head nodes.
     """
     cl = repo.changelog
 
     headsbyphase = [[] for i in allphases]
     # No need to keep track of secret phase; any heads in the subset that
     # are not mentioned are implicitly secret.
     for phase in allphases[:-1]:
         revset = "heads(%%ln & %s())" % phasenames[phase]
         headsbyphase[phase] = [cl.node(r) for r in repo.revs(revset, subset)]
     return headsbyphase
 
 def updatephases(repo, trgetter, headsbyphase):
     """Updates the repo with the given phase heads"""
     # Now advance phase boundaries of all but secret phase
     #
     # run the update (and fetch transaction) only if there are actually things
     # to update. This avoid creating empty transaction during no-op operation.
 
     for phase in allphases[:-1]:
         revset = '%%ln - %s()' % phasenames[phase]
         heads = [c.node() for c in repo.set(revset, headsbyphase[phase])]
         if heads:
             advanceboundary(repo, trgetter(), phase, heads)
 
 def analyzeremotephases(repo, subset, roots):
     """Compute phases heads and root in a subset of node from root dict
 
     * subset is heads of the subset
     * roots is {<nodeid> => phase} mapping. key and value are string.
 
     Accept unknown element input
     """
     repo = repo.unfiltered()
     # build list from dictionary
     draftroots = []
     nodemap = repo.changelog.nodemap # to filter unknown nodes
     for nhex, phase in roots.iteritems():
         if nhex == 'publishing': # ignore data related to publish option
             continue
         node = bin(nhex)
         phase = int(phase)
         if phase == public:
             if node != nullid:
                 repo.ui.warn(_('ignoring inconsistent public root'
                                ' from remote: %s\n') % nhex)
         elif phase == draft:
             if node in nodemap:
                 draftroots.append(node)
         else:
             repo.ui.warn(_('ignoring unexpected root from remote: %i %s\n')
                          % (phase, nhex))
     # compute heads
     publicheads = newheads(repo, subset, draftroots)
     return publicheads, draftroots
 
 class remotephasessummary(object):
     """summarize phase information on the remote side
 
     :publishing: True is the remote is publishing
     :publicheads: list of remote public phase heads (nodes)
     :draftheads: list of remote draft phase heads (nodes)
     :draftroots: list of remote draft phase root (nodes)
     """
 
     def __init__(self, repo, remotesubset, remoteroots):
         unfi = repo.unfiltered()
         self._allremoteroots = remoteroots
 
         self.publishing = remoteroots.get('publishing', False)
 
         ana = analyzeremotephases(repo, remotesubset, remoteroots)
         self.publicheads, self.draftroots = ana
         # Get the list of all "heads" revs draft on remote
         dheads = unfi.set('heads(%ln::%ln)', self.draftroots, remotesubset)
         self.draftheads = [c.node() for c in dheads]
 
 def newheads(repo, heads, roots):
     """compute new head of a subset minus another
 
     * `heads`: define the first subset
     * `roots`: define the second we subtract from the first"""
+    # prevent an import cycle
+    # phases > dagop > patch > copies > scmutil > obsolete > obsutil > phases
+    from . import dagop
+
     repo = repo.unfiltered()
-    revs = repo.revs('heads(::%ln - (%ln::%ln))', heads, roots, heads)
-    return pycompat.maplist(repo.changelog.node, revs)
+    cl = repo.changelog
+    rev = cl.nodemap.get
+    if not roots:
+        return heads
+    if not heads or heads == [nullrev]:
+        return []
+    # The logic operated on revisions, convert arguments early for convenience
+    new_heads = set(rev(n) for n in heads if n != nullid)
+    roots = [rev(n) for n in roots]
+    if not heads or not roots:
+        return heads
+    # compute the area we need to remove
+    affected_zone = repo.revs("(%ld::%ld)", roots, new_heads)
+    # heads in the area are no longer heads
+    new_heads.difference_update(affected_zone)
+    # revisions in the area have children outside of it,
+    # They might be new heads
+    candidates = repo.revs("parents(%ld + (%ld and merge())) and not null",
+                           roots, affected_zone)
+    candidates -= affected_zone
+    if new_heads or candidates:
+        # remove candidate that are ancestors of other heads
+        new_heads.update(candidates)
+        prunestart = repo.revs("parents(%ld) and not null", new_heads)
+        pruned = dagop.reachableroots(repo, candidates, prunestart)
+        new_heads.difference_update(pruned)
+
+    return pycompat.maplist(cl.node, sorted(new_heads))
 
 def newcommitphase(ui):
     """helper to get the target phase of new commit
 
     Handle all possible values for the phases.new-commit options.
 
     """
     v = ui.config('phases', 'new-commit')
     try:
         return phasenames.index(v)
     except ValueError:
         try:
             return int(v)
         except ValueError:
             msg = _("phases.new-commit: not a valid phase name ('%s')")
             raise error.ConfigError(msg % v)
 
 def hassecret(repo):
     """utility function that check if a repo have any secret changeset."""
     return bool(repo._phasecache.phaseroots[2])
 
 def preparehookargs(node, old, new):
     if old is None:
         old = ''
     else:
         old = phasenames[old]
     return {'node': node,
             'oldphase': old,
             'phase': phasenames[new]}

mercurial/revlog.py

@@ -1,3008 +1,3020 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import hashlib
 import heapq
 import os
 import re
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     wdirfilenodeids,
     wdirhex,
     wdirid,
     wdirrev,
 )
 from .i18n import _
 from .thirdparty import (
     attr,
 )
 from . import (
     ancestor,
     error,
     mdiff,
     policy,
     pycompat,
     templatefilters,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 parsers = policy.importmod(r'parsers')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # revlog header flags
 REVLOGV0 = 0
 REVLOGV1 = 1
 # Dummy value until file format is finalized.
 # Reminder: change the bounds check in revlog.__init__ when this is changed.
 REVLOGV2 = 0xDEAD
 FLAG_INLINE_DATA = (1 << 16)
 FLAG_GENERALDELTA = (1 << 17)
 REVLOG_DEFAULT_FLAGS = FLAG_INLINE_DATA
 REVLOG_DEFAULT_FORMAT = REVLOGV1
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGV1_FLAGS = FLAG_INLINE_DATA | FLAG_GENERALDELTA
 REVLOGV2_FLAGS = REVLOGV1_FLAGS
 
 # revlog index flags
 REVIDX_ISCENSORED = (1 << 15) # revision has censor metadata, must be verified
 REVIDX_ELLIPSIS = (1 << 14) # revision hash does not match data (narrowhg)
 REVIDX_EXTSTORED = (1 << 13) # revision data is stored externally
 REVIDX_DEFAULT_FLAGS = 0
 # stable order in which flags need to be processed and their processors applied
 REVIDX_FLAGS_ORDER = [
     REVIDX_ISCENSORED,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
 ]
 REVIDX_KNOWN_FLAGS = util.bitsfrom(REVIDX_FLAGS_ORDER)
 # bitmark for flags that could cause rawdata content change
 REVIDX_RAWTEXT_CHANGING_FLAGS = REVIDX_ISCENSORED | REVIDX_EXTSTORED
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 RevlogError = error.RevlogError
 LookupError = error.LookupError
 AmbiguousPrefixLookupError = error.AmbiguousPrefixLookupError
 CensoredNodeError = error.CensoredNodeError
 ProgrammingError = error.ProgrammingError
 
 # Store flag processors (cf. 'addflagprocessor()' to register)
 _flagprocessors = {
     REVIDX_ISCENSORED: None,
 }
 
 _mdre = re.compile('\1\n')
 def parsemeta(text):
     """return (metadatadict, metadatasize)"""
     # text can be buffer, so we can't use .startswith or .index
     if text[:2] != '\1\n':
         return None, None
     s = _mdre.search(text, 2).start()
     mtext = text[2:s]
     meta = {}
     for l in mtext.splitlines():
         k, v = l.split(": ", 1)
         meta[k] = v
     return meta, (s + 2)
 
 def packmeta(meta, text):
     keys = sorted(meta)
     metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
     return "\1\n%s\1\n%s" % (metatext, text)
 
 def _censoredtext(text):
     m, offs = parsemeta(text)
     return m and "censored" in m
 
 def addflagprocessor(flag, processor):
     """Register a flag processor on a revision data flag.
 
     Invariant:
     - Flags need to be defined in REVIDX_KNOWN_FLAGS and REVIDX_FLAGS_ORDER,
       and REVIDX_RAWTEXT_CHANGING_FLAGS if they can alter rawtext.
     - Only one flag processor can be registered on a specific flag.
     - flagprocessors must be 3-tuples of functions (read, write, raw) with the
       following signatures:
           - (read)  f(self, rawtext) -> text, bool
           - (write) f(self, text) -> rawtext, bool
           - (raw)   f(self, rawtext) -> bool
       "text" is presented to the user. "rawtext" is stored in revlog data, not
       directly visible to the user.
       The boolean returned by these transforms is used to determine whether
       the returned text can be used for hash integrity checking. For example,
       if "write" returns False, then "text" is used to generate hash. If
       "write" returns True, that basically means "rawtext" returned by "write"
       should be used to generate hash. Usually, "write" and "read" return
       different booleans. And "raw" returns a same boolean as "write".
 
       Note: The 'raw' transform is used for changegroup generation and in some
       debug commands. In this case the transform only indicates whether the
       contents can be used for hash integrity checks.
     """
     if not flag & REVIDX_KNOWN_FLAGS:
         msg = _("cannot register processor on unknown flag '%#x'.") % (flag)
         raise ProgrammingError(msg)
     if flag not in REVIDX_FLAGS_ORDER:
         msg = _("flag '%#x' undefined in REVIDX_FLAGS_ORDER.") % (flag)
         raise ProgrammingError(msg)
     if flag in _flagprocessors:
         msg = _("cannot register multiple processors on flag '%#x'.") % (flag)
         raise error.Abort(msg)
     _flagprocessors[flag] = processor
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     if (type & ~REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError('unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 _nullhash = hashlib.sha1(nullid)
 
 def hash(text, p1, p2):
     """generate a hash from the given text and its parent hashes
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = _nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         if p1 < p2:
             a = p1
             b = p2
         else:
             a = p2
             b = p1
         s = hashlib.sha1(a)
         s.update(b)
     s.update(text)
     return s.digest()
 
 class _testrevlog(object):
     """minimalist fake revlog to use in doctests"""
 
     def __init__(self, data, density=0.5, mingap=0):
         """data is an list of revision payload boundaries"""
         self._data = data
         self._srdensitythreshold = density
         self._srmingapsize = mingap
 
     def start(self, rev):
         if rev == 0:
             return 0
         return self._data[rev - 1]
 
     def end(self, rev):
         return self._data[rev]
 
     def length(self, rev):
         return self.end(rev) - self.start(rev)
 
     def __len__(self):
         return len(self._data)
 
 def _trimchunk(revlog, revs, startidx, endidx=None):
     """returns revs[startidx:endidx] without empty trailing revs
 
     Doctest Setup
     >>> revlog = _testrevlog([
     ...  5,  #0
     ...  10, #1
     ...  12, #2
     ...  12, #3 (empty)
     ...  17, #4
     ...  21, #5
     ...  21, #6 (empty)
     ... ])
 
     Contiguous cases:
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 0)
     [0, 1, 2, 3, 4, 5]
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 0, 5)
     [0, 1, 2, 3, 4]
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 0, 4)
     [0, 1, 2]
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 2, 4)
     [2]
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 3)
     [3, 4, 5]
     >>> _trimchunk(revlog, [0, 1, 2, 3, 4, 5, 6], 3, 5)
     [3, 4]
 
     Discontiguous cases:
     >>> _trimchunk(revlog, [1, 3, 5, 6], 0)
     [1, 3, 5]
     >>> _trimchunk(revlog, [1, 3, 5, 6], 0, 2)
     [1]
     >>> _trimchunk(revlog, [1, 3, 5, 6], 1, 3)
     [3, 5]
     >>> _trimchunk(revlog, [1, 3, 5, 6], 1)
     [3, 5]
     """
     length = revlog.length
 
     if endidx is None:
         endidx = len(revs)
 
-    # Trim empty revs at the end, but never the very first revision of a chain
-    while endidx > 1 and endidx > startidx and length(revs[endidx - 1]) == 0:
+    # If we have a non-emtpy delta candidate, there are nothing to trim
+    if revs[endidx - 1] < len(revlog):
+        # Trim empty revs at the end, except the very first revision of a chain
+        while (endidx > 1
+                and endidx > startidx
+                and length(revs[endidx - 1]) == 0):
         endidx -= 1
 
     return revs[startidx:endidx]
 
-def _segmentspan(revlog, revs):
+def _segmentspan(revlog, revs, deltainfo=None):
     """Get the byte span of a segment of revisions
 
     revs is a sorted array of revision numbers
 
     >>> revlog = _testrevlog([
     ...  5,  #0
     ...  10, #1
     ...  12, #2
     ...  12, #3 (empty)
     ...  17, #4
     ... ])
 
     >>> _segmentspan(revlog, [0, 1, 2, 3, 4])
     17
     >>> _segmentspan(revlog, [0, 4])
     17
     >>> _segmentspan(revlog, [3, 4])
     5
     >>> _segmentspan(revlog, [1, 2, 3,])
     7
     >>> _segmentspan(revlog, [1, 3])
     7
     """
     if not revs:
         return 0
-    return revlog.end(revs[-1]) - revlog.start(revs[0])
+    if deltainfo is not None and len(revlog) <= revs[-1]:
+        if len(revs) == 1:
+            return deltainfo.deltalen
+        offset = revlog.end(len(revlog) - 1)
+        end = deltainfo.deltalen + offset
+    else:
+        end = revlog.end(revs[-1])
+    return end - revlog.start(revs[0])
 
 def _slicechunk(revlog, revs, deltainfo=None, targetsize=None):
     """slice revs to reduce the amount of unrelated data to be read from disk.
 
     ``revs`` is sliced into groups that should be read in one time.
     Assume that revs are sorted.
 
     The initial chunk is sliced until the overall density (payload/chunks-span
     ratio) is above `revlog._srdensitythreshold`. No gap smaller than
     `revlog._srmingapsize` is skipped.
 
     If `targetsize` is set, no chunk larger than `targetsize` will be yield.
     For consistency with other slicing choice, this limit won't go lower than
     `revlog._srmingapsize`.
 
     If individual revisions chunk are larger than this limit, they will still
     be raised individually.
 
     >>> revlog = _testrevlog([
     ...  5,  #00 (5)
     ...  10, #01 (5)
     ...  12, #02 (2)
     ...  12, #03 (empty)
     ...  27, #04 (15)
     ...  31, #05 (4)
     ...  31, #06 (empty)
     ...  42, #07 (11)
     ...  47, #08 (5)
     ...  47, #09 (empty)
     ...  48, #10 (1)
     ...  51, #11 (3)
     ...  74, #12 (23)
     ...  85, #13 (11)
     ...  86, #14 (1)
     ...  91, #15 (5)
     ... ])
 
     >>> list(_slicechunk(revlog, list(range(16))))
     [[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]]
     >>> list(_slicechunk(revlog, [0, 15]))
     [[0], [15]]
     >>> list(_slicechunk(revlog, [0, 11, 15]))
     [[0], [11], [15]]
     >>> list(_slicechunk(revlog, [0, 11, 13, 15]))
     [[0], [11, 13, 15]]
     >>> list(_slicechunk(revlog, [1, 2, 3, 5, 8, 10, 11, 14]))
     [[1, 2], [5, 8, 10, 11], [14]]
 
     Slicing with a maximum chunk size
     >>> list(_slicechunk(revlog, [0, 11, 13, 15], targetsize=15))
     [[0], [11], [13], [15]]
     >>> list(_slicechunk(revlog, [0, 11, 13, 15], targetsize=20))
     [[0], [11], [13, 15]]
     """
     if targetsize is not None:
         targetsize = max(targetsize, revlog._srmingapsize)
     # targetsize should not be specified when evaluating delta candidates:
     # * targetsize is used to ensure we stay within specification when reading,
     # * deltainfo is used to pick are good delta chain when writing.
     if not (deltainfo is None or targetsize is None):
         msg = 'cannot use `targetsize` with a `deltainfo`'
         raise error.ProgrammingError(msg)
     for chunk in _slicechunktodensity(revlog, revs,
                                       deltainfo,
                                       revlog._srdensitythreshold,
                                       revlog._srmingapsize):
         for subchunk in _slicechunktosize(revlog, chunk, targetsize):
             yield subchunk
 
 def _slicechunktosize(revlog, revs, targetsize=None):
     """slice revs to match the target size
 
     This is intended to be used on chunk that density slicing selected by that
     are still too large compared to the read garantee of revlog. This might
     happens when "minimal gap size" interrupted the slicing or when chain are
     built in a way that create large blocks next to each other.
 
     >>> revlog = _testrevlog([
     ...  3,  #0 (3)
     ...  5,  #1 (2)
     ...  6,  #2 (1)
     ...  8,  #3 (2)
     ...  8,  #4 (empty)
     ...  11, #5 (3)
     ...  12, #6 (1)
     ...  13, #7 (1)
     ...  14, #8 (1)
     ... ])
 
     Cases where chunk is already small enough
     >>> list(_slicechunktosize(revlog, [0], 3))
     [[0]]
     >>> list(_slicechunktosize(revlog, [6, 7], 3))
     [[6, 7]]
     >>> list(_slicechunktosize(revlog, [0], None))
     [[0]]
     >>> list(_slicechunktosize(revlog, [6, 7], None))
     [[6, 7]]
 
     cases where we need actual slicing
     >>> list(_slicechunktosize(revlog, [0, 1], 3))
     [[0], [1]]
     >>> list(_slicechunktosize(revlog, [1, 3], 3))
     [[1], [3]]
     >>> list(_slicechunktosize(revlog, [1, 2, 3], 3))
     [[1, 2], [3]]
     >>> list(_slicechunktosize(revlog, [3, 5], 3))
     [[3], [5]]
     >>> list(_slicechunktosize(revlog, [3, 4, 5], 3))
     [[3], [5]]
     >>> list(_slicechunktosize(revlog, [5, 6, 7, 8], 3))
     [[5], [6, 7, 8]]
     >>> list(_slicechunktosize(revlog, [0, 1, 2, 3, 4, 5, 6, 7, 8], 3))
     [[0], [1, 2], [3], [5], [6, 7, 8]]
 
     Case with too large individual chunk (must return valid chunk)
     >>> list(_slicechunktosize(revlog, [0, 1], 2))
     [[0], [1]]
     >>> list(_slicechunktosize(revlog, [1, 3], 1))
     [[1], [3]]
     >>> list(_slicechunktosize(revlog, [3, 4, 5], 2))
     [[3], [5]]
     """
     assert targetsize is None or 0 <= targetsize
     if targetsize is None or _segmentspan(revlog, revs) <= targetsize:
         yield revs
         return
 
     startrevidx = 0
     startdata = revlog.start(revs[0])
     endrevidx = 0
     iterrevs = enumerate(revs)
     next(iterrevs) # skip first rev.
     for idx, r in iterrevs:
         span = revlog.end(r) - startdata
         if span <= targetsize:
             endrevidx = idx
         else:
             chunk = _trimchunk(revlog, revs, startrevidx, endrevidx + 1)
             if chunk:
                 yield chunk
             startrevidx = idx
             startdata = revlog.start(r)
             endrevidx = idx
     yield _trimchunk(revlog, revs, startrevidx)
 
 def _slicechunktodensity(revlog, revs, deltainfo=None, targetdensity=0.5,
                          mingapsize=0):
     """slice revs to reduce the amount of unrelated data to be read from disk.
 
     ``revs`` is sliced into groups that should be read in one time.
     Assume that revs are sorted.
 
     ``deltainfo`` is a _deltainfo instance of a revision that we would append
     to the top of the revlog.
 
     The initial chunk is sliced until the overall density (payload/chunks-span
     ratio) is above `targetdensity`. No gap smaller than `mingapsize` is
     skipped.
 
     >>> revlog = _testrevlog([
     ...  5,  #00 (5)
     ...  10, #01 (5)
     ...  12, #02 (2)
     ...  12, #03 (empty)
     ...  27, #04 (15)
     ...  31, #05 (4)
     ...  31, #06 (empty)
     ...  42, #07 (11)
     ...  47, #08 (5)
     ...  47, #09 (empty)
     ...  48, #10 (1)
     ...  51, #11 (3)
     ...  74, #12 (23)
     ...  85, #13 (11)
     ...  86, #14 (1)
     ...  91, #15 (5)
     ... ])
 
     >>> list(_slicechunktodensity(revlog, list(range(16))))
     [[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]]
     >>> list(_slicechunktodensity(revlog, [0, 15]))
     [[0], [15]]
     >>> list(_slicechunktodensity(revlog, [0, 11, 15]))
     [[0], [11], [15]]
     >>> list(_slicechunktodensity(revlog, [0, 11, 13, 15]))
     [[0], [11, 13, 15]]
     >>> list(_slicechunktodensity(revlog, [1, 2, 3, 5, 8, 10, 11, 14]))
     [[1, 2], [5, 8, 10, 11], [14]]
     >>> list(_slicechunktodensity(revlog, [1, 2, 3, 5, 8, 10, 11, 14],
     ...                           mingapsize=20))
     [[1, 2, 3, 5, 8, 10, 11], [14]]
     >>> list(_slicechunktodensity(revlog, [1, 2, 3, 5, 8, 10, 11, 14],
     ...                           targetdensity=0.95))
     [[1, 2], [5], [8, 10, 11], [14]]
     >>> list(_slicechunktodensity(revlog, [1, 2, 3, 5, 8, 10, 11, 14],
     ...                           targetdensity=0.95, mingapsize=12))
     [[1, 2], [5, 8, 10, 11], [14]]
     """
     start = revlog.start
     length = revlog.length
 
     if len(revs) <= 1:
         yield revs
         return
 
     nextrev = len(revlog)
     nextoffset = revlog.end(nextrev - 1)
 
     if deltainfo is None:
         deltachainspan = _segmentspan(revlog, revs)
         chainpayload = sum(length(r) for r in revs)
     else:
         deltachainspan = deltainfo.distance
         chainpayload = deltainfo.compresseddeltalen
 
     if deltachainspan < mingapsize:
         yield revs
         return
 
     readdata = deltachainspan
 
     if deltachainspan:
         density = chainpayload / float(deltachainspan)
     else:
         density = 1.0
 
     if density >= targetdensity:
         yield revs
         return
 
-    if deltainfo is not None:
+    if deltainfo is not None and deltainfo.deltalen:
         revs = list(revs)
         revs.append(nextrev)
 
     # Store the gaps in a heap to have them sorted by decreasing size
     gapsheap = []
     heapq.heapify(gapsheap)
     prevend = None
     for i, rev in enumerate(revs):
         if rev < nextrev:
             revstart = start(rev)
             revlen = length(rev)
         else:
             revstart = nextoffset
             revlen = deltainfo.deltalen
 
         # Skip empty revisions to form larger holes
         if revlen == 0:
             continue
 
         if prevend is not None:
             gapsize = revstart - prevend
             # only consider holes that are large enough
             if gapsize > mingapsize:
                 heapq.heappush(gapsheap, (-gapsize, i))
 
         prevend = revstart + revlen
 
     # Collect the indices of the largest holes until the density is acceptable
     indicesheap = []
     heapq.heapify(indicesheap)
     while gapsheap and density < targetdensity:
         oppgapsize, gapidx = heapq.heappop(gapsheap)
 
         heapq.heappush(indicesheap, gapidx)
 
         # the gap sizes are stored as negatives to be sorted decreasingly
         # by the heap
         readdata -= (-oppgapsize)
         if readdata > 0:
             density = chainpayload / float(readdata)
         else:
             density = 1.0
 
     # Cut the revs at collected indices
     previdx = 0
     while indicesheap:
         idx = heapq.heappop(indicesheap)
 
         chunk = _trimchunk(revlog, revs, previdx, idx)
         if chunk:
             yield chunk
 
         previdx = idx
 
     chunk = _trimchunk(revlog, revs, previdx)
     if chunk:
         yield chunk
 
 @attr.s(slots=True, frozen=True)
 class _deltainfo(object):
     distance = attr.ib()
     deltalen = attr.ib()
     data = attr.ib()
     base = attr.ib()
     chainbase = attr.ib()
     chainlen = attr.ib()
     compresseddeltalen = attr.ib()
 
 class _deltacomputer(object):
     def __init__(self, revlog):
         self.revlog = revlog
 
     def _getcandidaterevs(self, p1, p2, cachedelta):
         """
         Provides revisions that present an interest to be diffed against,
         grouped by level of easiness.
         """
         revlog = self.revlog
         gdelta = revlog._generaldelta
         curr = len(revlog)
         prev = curr - 1
         p1r, p2r = revlog.rev(p1), revlog.rev(p2)
 
         # should we try to build a delta?
         if prev != nullrev and revlog.storedeltachains:
             tested = set()
             # This condition is true most of the time when processing
             # changegroup data into a generaldelta repo. The only time it
             # isn't true is if this is the first revision in a delta chain
             # or if ``format.generaldelta=true`` disabled ``lazydeltabase``.
             if cachedelta and gdelta and revlog._lazydeltabase:
                 # Assume what we received from the server is a good choice
                 # build delta will reuse the cache
                 yield (cachedelta[0],)
                 tested.add(cachedelta[0])
 
             if gdelta:
                 # exclude already lazy tested base if any
                 parents = [p for p in (p1r, p2r)
                            if p != nullrev and p not in tested]
 
                 if not revlog._deltabothparents and len(parents) == 2:
                     parents.sort()
                     # To minimize the chance of having to build a fulltext,
                     # pick first whichever parent is closest to us (max rev)
                     yield (parents[1],)
                     # then the other one (min rev) if the first did not fit
                     yield (parents[0],)
                     tested.update(parents)
                 elif len(parents) > 0:
                     # Test all parents (1 or 2), and keep the best candidate
                     yield parents
                     tested.update(parents)
 
             if prev not in tested:
                 # other approach failed try against prev to hopefully save us a
                 # fulltext.
                 yield (prev,)
                 tested.add(prev)
 
     def buildtext(self, revinfo, fh):
         """Builds a fulltext version of a revision
 
         revinfo: _revisioninfo instance that contains all needed info
         fh:      file handle to either the .i or the .d revlog file,
                  depending on whether it is inlined or not
         """
         btext = revinfo.btext
         if btext[0] is not None:
             return btext[0]
 
         revlog = self.revlog
         cachedelta = revinfo.cachedelta
         flags = revinfo.flags
         node = revinfo.node
 
         baserev = cachedelta[0]
         delta = cachedelta[1]
         # special case deltas which replace entire base; no need to decode
         # base revision. this neatly avoids censored bases, which throw when
         # they're decoded.
         hlen = struct.calcsize(">lll")
         if delta[:hlen] == mdiff.replacediffheader(revlog.rawsize(baserev),
                                                    len(delta) - hlen):
             btext[0] = delta[hlen:]
         else:
             # deltabase is rawtext before changed by flag processors, which is
             # equivalent to non-raw text
             basetext = revlog.revision(baserev, _df=fh, raw=False)
             btext[0] = mdiff.patch(basetext, delta)
 
         try:
             res = revlog._processflags(btext[0], flags, 'read', raw=True)
             btext[0], validatehash = res
             if validatehash:
                 revlog.checkhash(btext[0], node, p1=revinfo.p1, p2=revinfo.p2)
             if flags & REVIDX_ISCENSORED:
                 raise RevlogError(_('node %s is not censored') % node)
         except CensoredNodeError:
             # must pass the censored index flag to add censored revisions
             if not flags & REVIDX_ISCENSORED:
                 raise
         return btext[0]
 
     def _builddeltadiff(self, base, revinfo, fh):
         revlog = self.revlog
         t = self.buildtext(revinfo, fh)
         if revlog.iscensored(base):
             # deltas based on a censored revision must replace the
             # full content in one patch, so delta works everywhere
             header = mdiff.replacediffheader(revlog.rawsize(base), len(t))
             delta = header + t
         else:
             ptext = revlog.revision(base, _df=fh, raw=True)
             delta = mdiff.textdiff(ptext, t)
 
         return delta
 
     def _builddeltainfo(self, revinfo, base, fh):
         # can we use the cached delta?
         if revinfo.cachedelta and revinfo.cachedelta[0] == base:
             delta = revinfo.cachedelta[1]
         else:
             delta = self._builddeltadiff(base, revinfo, fh)
         revlog = self.revlog
         header, data = revlog.compress(delta)
         deltalen = len(header) + len(data)
         chainbase = revlog.chainbase(base)
         offset = revlog.end(len(revlog) - 1)
         dist = deltalen + offset - revlog.start(chainbase)
         if revlog._generaldelta:
             deltabase = base
         else:
             deltabase = chainbase
         chainlen, compresseddeltalen = revlog._chaininfo(base)
         chainlen += 1
         compresseddeltalen += deltalen
         return _deltainfo(dist, deltalen, (header, data), deltabase,
                          chainbase, chainlen, compresseddeltalen)
 
     def finddeltainfo(self, revinfo, fh):
         """Find an acceptable delta against a candidate revision
 
         revinfo: information about the revision (instance of _revisioninfo)
         fh:      file handle to either the .i or the .d revlog file,
                  depending on whether it is inlined or not
 
         Returns the first acceptable candidate revision, as ordered by
         _getcandidaterevs
         """
         if not revinfo.textlen:
             return None # empty file do not need delta
 
         cachedelta = revinfo.cachedelta
         p1 = revinfo.p1
         p2 = revinfo.p2
         revlog = self.revlog
 
         deltalength = self.revlog.length
         deltaparent = self.revlog.deltaparent
 
         deltainfo = None
         deltas_limit = revinfo.textlen * LIMIT_DELTA2TEXT
         for candidaterevs in self._getcandidaterevs(p1, p2, cachedelta):
             # filter out delta base that will never produce good delta
             candidaterevs = [r for r in candidaterevs
                              if self.revlog.length(r) <= deltas_limit]
             nominateddeltas = []
             for candidaterev in candidaterevs:
                 # skip over empty delta (no need to include them in a chain)
                 while candidaterev != nullrev and not deltalength(candidaterev):
                     candidaterev = deltaparent(candidaterev)
                 # no need to try a delta against nullid, this will be handled
                 # by fulltext later.
                 if candidaterev == nullrev:
                     continue
                 # no delta for rawtext-changing revs (see "candelta" for why)
                 if revlog.flags(candidaterev) & REVIDX_RAWTEXT_CHANGING_FLAGS:
                     continue
                 candidatedelta = self._builddeltainfo(revinfo, candidaterev, fh)
                 if revlog._isgooddeltainfo(candidatedelta, revinfo):
                     nominateddeltas.append(candidatedelta)
             if nominateddeltas:
                 deltainfo = min(nominateddeltas, key=lambda x: x.deltalen)
                 break
 
         return deltainfo
 
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
     node:       expected hash of the revision
     p1, p2:     parent revs of the revision
     btext:      built text cache consisting of a one-element list
     cachedelta: (baserev, uncompressed_delta) or None
     flags:      flags associated to the revision storage
 
     One of btext[0] or cachedelta must be set.
     """
     node = attr.ib()
     p1 = attr.ib()
     p2 = attr.ib()
     btext = attr.ib()
     textlen = attr.ib()
     cachedelta = attr.ib()
     flags = attr.ib()
 
 # index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 indexformatv0 = struct.Struct(">4l20s20s20s")
 indexformatv0_pack = indexformatv0.pack
 indexformatv0_unpack = indexformatv0.unpack
 
 class revlogoldindex(list):
     def __getitem__(self, i):
         if i == -1:
             return (0, 0, 0, -1, -1, -1, -1, nullid)
         return list.__getitem__(self, i)
 
 # maximum <delta-chain-data>/<revision-text-length> ratio
 LIMIT_DELTA2TEXT = 2
 
 class revlogoldio(object):
     def __init__(self):
         self.size = indexformatv0.size
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap = {nullid: nullrev}
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = indexformatv0_unpack(cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         return revlogoldindex(index), nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise RevlogError(_('index entry flags need revlog version 1'))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return indexformatv0_pack(*e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = struct.Struct(">Qiiiiii20s12x")
 indexformatng_pack = indexformatng.pack
 versionformat = struct.Struct(">I")
 versionformat_pack = versionformat.pack
 versionformat_unpack = versionformat.unpack
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7fffffff
 
 class revlogio(object):
     def __init__(self):
         self.size = indexformatng.size
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
         p = indexformatng_pack(*entry)
         if rev == 0:
             p = versionformat_pack(version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
     """
     def __init__(self, opener, indexfile, datafile=None, checkambig=False,
                  mmaplargeindex=False, censorable=False):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + ".d")
         self.opener = opener
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._cache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, '')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = []
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._nodecache = {nullid: nullrev}
         self._nodepos = None
         self._compengine = 'zlib'
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         mmapindexthreshold = None
         v = REVLOG_DEFAULT_VERSION
         opts = getattr(opener, 'options', None)
         if opts is not None:
             if 'revlogv2' in opts:
                 # version 2 revlogs always use generaldelta.
                 v = REVLOGV2 | FLAG_GENERALDELTA | FLAG_INLINE_DATA
             elif 'revlogv1' in opts:
                 if 'generaldelta' in opts:
                     v |= FLAG_GENERALDELTA
             else:
                 v = 0
             if 'chunkcachesize' in opts:
                 self._chunkcachesize = opts['chunkcachesize']
             if 'maxchainlen' in opts:
                 self._maxchainlen = opts['maxchainlen']
             if 'deltabothparents' in opts:
                 self._deltabothparents = opts['deltabothparents']
             self._lazydeltabase = bool(opts.get('lazydeltabase', False))
             if 'compengine' in opts:
                 self._compengine = opts['compengine']
             if 'maxdeltachainspan' in opts:
                 self._maxdeltachainspan = opts['maxdeltachainspan']
             if mmaplargeindex and 'mmapindexthreshold' in opts:
                 mmapindexthreshold = opts['mmapindexthreshold']
             self._sparserevlog = bool(opts.get('sparse-revlog', False))
             withsparseread = bool(opts.get('with-sparse-read', False))
             # sparse-revlog forces sparse-read
             self._withsparseread = self._sparserevlog or withsparseread
             if 'sparse-read-density-threshold' in opts:
                 self._srdensitythreshold = opts['sparse-read-density-threshold']
             if 'sparse-read-min-gap-size' in opts:
                 self._srmingapsize = opts['sparse-read-min-gap-size']
 
         if self._chunkcachesize <= 0:
             raise RevlogError(_('revlog chunk cache size %r is not greater '
                                 'than 0') % self._chunkcachesize)
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise RevlogError(_('revlog chunk cache size %r is not a power '
                                 'of 2') % self._chunkcachesize)
 
         indexdata = ''
         self._initempty = True
         try:
             with self._indexfp() as f:
                 if (mmapindexthreshold is not None and
                         self.opener.fstat(f).st_size >= mmapindexthreshold):
                     indexdata = util.buffer(util.mmapread(f))
                 else:
                     indexdata = f.read()
             if len(indexdata) > 0:
                 v = versionformat_unpack(indexdata[:4])[0]
                 self._initempty = False
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.version = v
         self._inline = v & FLAG_INLINE_DATA
         self._generaldelta = v & FLAG_GENERALDELTA
         flags = v & ~0xFFFF
         fmt = v & 0xFFFF
         if fmt == REVLOGV0:
             if flags:
                 raise RevlogError(_('unknown flags (%#04x) in version %d '
                                     'revlog %s') %
                                   (flags >> 16, fmt, self.indexfile))
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise RevlogError(_('unknown flags (%#04x) in version %d '
                                     'revlog %s') %
                                   (flags >> 16, fmt, self.indexfile))
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise RevlogError(_('unknown flags (%#04x) in version %d '
                                     'revlog %s') %
                                   (flags >> 16, fmt, self.indexfile))
         else:
             raise RevlogError(_('unknown version (%d) in revlog %s') %
                               (fmt, self.indexfile))
 
         self.storedeltachains = True
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(indexdata, self._inline)
         except (ValueError, IndexError):
             raise RevlogError(_("index %s is corrupted") % (self.indexfile))
         self.index, nodemap, self._chunkcache = d
         if nodemap is not None:
             self.nodemap = self._nodecache = nodemap
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = {}
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def _compressor(self):
         return util.compengines[self._compengine].revlogcompressor()
 
     def _indexfp(self, mode='r'):
         """file object for the revlog's index file"""
         args = {r'mode': mode}
         if mode != 'r':
             args[r'checkambig'] = self._checkambig
         if mode == 'w':
             args[r'atomictemp'] = True
         return self.opener(self.indexfile, **args)
 
     def _datafp(self, mode='r'):
         """file object for the revlog's data file"""
         return self.opener(self.datafile, mode=mode)
 
     @contextlib.contextmanager
     def _datareadfp(self, existingfp=None):
         """file object suitable to read data"""
         if existingfp is not None:
             yield existingfp
         else:
             if self._inline:
                 func = self._indexfp
             else:
                 func = self._datafp
             with func() as fp:
                 yield fp
 
     def tip(self):
         return self.node(len(self.index) - 1)
     def __contains__(self, rev):
         return 0 <= rev < len(self)
     def __len__(self):
         return len(self.index)
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         step = 1
         length = len(self)
         if stop is not None:
             if start > stop:
                 step = -1
             stop += step
             if stop > length:
                 stop = length
         else:
             stop = length
         return pycompat.xrange(start, stop, step)
 
     @util.propertycache
     def nodemap(self):
         if self.index:
             # populate mapping down to the initial node
             node0 = self.index[0][7]  # get around changelog filtering
             self.rev(node0)
         return self._nodecache
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if ((self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS)
             or (self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS)):
             return False
         return True
 
     def clearcaches(self):
         self._cache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, '')
         self._pcache = {}
 
         try:
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except TypeError:
             raise
         except RevlogError:
             # parsers.c radix tree lookup failed
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise LookupError(node, self.indexfile, _('no node'))
         except KeyError:
             # pure python cache lookup failed
             n = self._nodecache
             i = self.index
             p = self._nodepos
             if p is None:
                 p = len(i) - 1
             else:
                 assert p < len(i)
             for r in pycompat.xrange(p, -1, -1):
                 v = i[r][7]
                 n[v] = r
                 if v == node:
                     self._nodepos = r - 1
                     return r
             if node == wdirid or node in wdirfilenodeids:
                 raise error.WdirUnsupported
             raise LookupError(node, self.indexfile, _('no node'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(rev, raw=True)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev, raw=False))
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
         return entry[5], entry[6]
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse topological order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         return ancestor.lazyancestors(self.parentrevs, revs, stoprev=stoprev,
                                       inclusive=inclusive)
 
     def descendants(self, revs):
         """Generate the descendants of 'revs' in revision order.
 
         Yield a sequence of revision numbers starting with a child of
         some rev in revs, i.e., each revision is *not* considered a
         descendant of itself.  Results are ordered by revision number (a
         topological sort)."""
         first = min(revs)
         if first == nullrev:
             for i in self:
                 yield i
             return
 
         seen = set(revs)
         for i in self.revs(start=first + 1):
             for x in self.parentrevs(i):
                 if x != nullrev and x in seen:
                     seen.add(i)
                     yield i
                     break
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in heads.iteritems() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self):
         try:
             return self.index.headrevs()
         except AttributeError:
             return self._headrevs()
 
     def computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = set([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = {startrev}
         heads = {startrev}
 
         parentrevs = self.parentrevs
         for r in self.revs(start=startrev + 1):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable.add(r)
                     heads.add(r)
                 if p in heads and p not in stoprevs:
                     heads.remove(p)
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError): # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         commonancestorsheads is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return a in self._commonancestorsheads(a, b)
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if "%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = wdirhex.startswith(id)
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     raise RevlogError
                 return partial
             if maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             return None
         except RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise AmbiguousPrefixLookupError(id, self.indexfile,
                                                  _('ambiguous identifier'))
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[:l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [n for n in nl if hex(n).startswith(id) and
                       self.hasnode(n)]
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise AmbiguousPrefixLookupError(id, self.indexfile,
                                                      _('ambiguous identifier'))
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise LookupError(id, self.indexfile, _('no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
         def isvalid(prefix):
             try:
                 node = self._partialmatch(prefix)
             except error.RevlogError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if node is None:
                 raise LookupError(node, self.indexfile, _('no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == 'f' for c in prefix)
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except RevlogError:
                 if node != wdirid:
                     raise LookupError(node, self.indexfile, _('no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == wdirid:
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, 41):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return hash(text, p1, p2) != node
 
     def _cachesegment(self, offset, data):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _readsegment(self, offset, length, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (((offset + length + cachesize) & ~(cachesize - 1))
                       - realoffset)
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
             return util.buffer(d, offset - realoffset, length)
         return d
 
     def _getsegment(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._readsegment(offset, length, df=df)
 
     def _getsegmentforrevs(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self._io.size
             end += (endrev + 1) * self._io.size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self._io.size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = _slicechunk(self, revs, targetsize=targetsize)
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, df=df)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev, df=df) for rev in revschunk]
 
             decomp = self.decompress
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(decomp(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.revision(rev1, raw=True),
                               self.revision(rev2, raw=True))
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         raw - an optional argument specifying if the revision data is to be
         treated as raw data when applying flag transforms. 'raw' should be set
         to True when generating changegroups or in debug commands.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         cachedrev = None
         flags = None
         rawtext = None
         if node == nullid:
             return ""
         if self._cache:
             if self._cache[0] == node:
                 # _cache only stores rawtext
                 if raw:
                     return self._cache[2]
                 # duplicated, but good for perf
                 if rev is None:
                     rev = self.rev(node)
                 if flags is None:
                     flags = self.flags(rev)
                 # no extra flags set, no flag processor runs, text = rawtext
                 if flags == REVIDX_DEFAULT_FLAGS:
                     return self._cache[2]
                 # rawtext is reusable. need to run flag processor
                 rawtext = self._cache[2]
 
             cachedrev = self._cache[1]
 
         # look up what we need to read
         if rawtext is None:
             if rev is None:
                 rev = self.rev(node)
 
             chain, stopped = self._deltachain(rev, stoprev=cachedrev)
             if stopped:
                 rawtext = self._cache[2]
 
             # drop cache to save memory
             self._cache = None
 
             targetsize = None
             rawsize = self.index[rev][2]
             if 0 <= rawsize:
                 targetsize = 4 * rawsize
 
             bins = self._chunks(chain, df=_df, targetsize=targetsize)
             if rawtext is None:
                 rawtext = bytes(bins[0])
                 bins = bins[1:]
 
             rawtext = mdiff.patches(rawtext, bins)
             self._cache = (node, rev, rawtext)
 
         if flags is None:
             if rev is None:
                 rev = self.rev(node)
             flags = self.flags(rev)
 
         text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)
         if validatehash:
             self.checkhash(text, node, rev=rev)
 
         return text
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return hash(text, p1, p2)
 
     def _processflags(self, text, flags, operation, raw=False):
         """Inspect revision data flags and applies transforms defined by
         registered flag processors.
 
         ``text`` - the revision data to process
         ``flags`` - the revision flags
         ``operation`` - the operation being performed (read or write)
         ``raw`` - an optional argument describing if the raw transform should be
         applied.
 
         This method processes the flags in the order (or reverse order if
         ``operation`` is 'write') defined by REVIDX_FLAGS_ORDER, applying the
         flag processors registered for present flags. The order of flags defined
         in REVIDX_FLAGS_ORDER needs to be stable to allow non-commutativity.
 
         Returns a 2-tuple of ``(text, validatehash)`` where ``text`` is the
         processed text and ``validatehash`` is a bool indicating whether the
         returned text should be checked for hash integrity.
 
         Note: If the ``raw`` argument is set, it has precedence over the
         operation and will only update the value of ``validatehash``.
         """
         # fast path: no flag processors will run
         if flags == 0:
             return text, True
         if not operation in ('read', 'write'):
             raise ProgrammingError(_("invalid '%s' operation ") % (operation))
         # Check all flags are known.
         if flags & ~REVIDX_KNOWN_FLAGS:
             raise RevlogError(_("incompatible revision flag '%#x'") %
                               (flags & ~REVIDX_KNOWN_FLAGS))
         validatehash = True
         # Depending on the operation (read or write), the order might be
         # reversed due to non-commutative transforms.
         orderedflags = REVIDX_FLAGS_ORDER
         if operation == 'write':
             orderedflags = reversed(orderedflags)
 
         for flag in orderedflags:
             # If a flagprocessor has been registered for a known flag, apply the
             # related operation transform and update result tuple.
             if flag & flags:
                 vhash = True
 
                 if flag not in _flagprocessors:
                     message = _("missing processor for flag '%#x'") % (flag)
                     raise RevlogError(message)
 
                 processor = _flagprocessors[flag]
                 if processor is not None:
                     readtransform, writetransform, rawtransform = processor
 
                     if raw:
                         vhash = rawtransform(self, text)
                     elif operation == 'read':
                         text, vhash = readtransform(self, text)
                     else: # write operation
                         text, vhash = writetransform(self, text)
                 validatehash = validatehash and vhash
 
         return text, validatehash
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise RevlogError(_("integrity check failed on %s:%s")
                     % (self.indexfile, pycompat.bytestr(revornode)))
         except RevlogError:
             if self._censorable and _censoredtext(text):
                 raise error.CensoredNodeError(self.indexfile, node, text)
             raise
 
     def _enforceinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         tiprev = len(self) - 1
         if (not self._inline or
             (self.start(tiprev) + self.length(tiprev)) < _maxinline):
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise RevlogError(_("%s not found in the transaction")
                               % self.indexfile)
 
         trindex = trinfo[2]
         if trindex is not None:
             dataoff = self.start(trindex)
         else:
             # revlog was stripped at start of transaction, use all leftover data
             trindex = len(self) - 1
             dataoff = self.end(tiprev)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
 
         with self._datafp('w') as df:
             for r in self:
                 df.write(self._getsegmentforrevs(r, r)[1])
 
         with self._indexfp('w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             io = self._io
             for i in self:
                 e = io.packentry(self.index[i], self.node, self.version, i)
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None,
                     node=None, flags=REVIDX_DEFAULT_FLAGS, deltacomputer=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         node - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         flags - the known flags to set on the revision
         deltacomputer - an optional _deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise RevlogError(_("attempted to add linkrev -1 to %s")
                               % self.indexfile)
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = self._processflags(text, flags, 'write')
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise RevlogError(
                 _("%s: size of %d bytes exceeds maximum revlog storage of 2GiB")
                 % (self.indexfile, len(rawtext)))
 
         node = node or self.hash(rawtext, p1, p2)
         if node in self.nodemap:
             return node
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(rawtext, transaction, link, p1, p2, node,
                                    flags, cachedelta=cachedelta,
                                    deltacomputer=deltacomputer)
 
     def addrawrevision(self, rawtext, transaction, link, p1, p2, node, flags,
                        cachedelta=None, deltacomputer=None):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp("a+")
         ifh = self._indexfp("a+")
         try:
             return self._addrevision(node, rawtext, transaction, link, p1, p2,
                                      flags, cachedelta, ifh, dfh,
                                      deltacomputer=deltacomputer)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return '', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return '', compressed
 
         if data[0:1] == '\0':
             return '', data
         return 'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == 'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise RevlogError(_('revlog decompress error: %s') %
                                   stringutil.forcebytestr(e))
         # '\0' is more common than 'u' so it goes first.
         elif t == '\0':
             return data
         elif t == 'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor()
                 self._decompressors[t] = compressor
             except KeyError:
                 raise RevlogError(_('unknown compression type %r') % t)
 
         return compressor.decompress(data)
 
     def _isgooddeltainfo(self, deltainfo, revinfo):
         """Returns True if the given delta is good. Good means that it is within
         the disk span, disk size, and chain length bounds that we know to be
         performant."""
         if deltainfo is None:
             return False
 
         # - 'deltainfo.distance' is the distance from the base revision --
         #   bounding it limits the amount of I/O we need to do.
         # - 'deltainfo.compresseddeltalen' is the sum of the total size of
         #   deltas we need to apply -- bounding it limits the amount of CPU
         #   we consume.
 
         if self._sparserevlog:
             # As sparse-read will be used, we can consider that the distance,
             # instead of being the span of the whole chunk,
             # is the span of the largest read chunk
             base = deltainfo.base
 
             if base != nullrev:
                 deltachain = self._deltachain(base)[0]
             else:
                 deltachain = []
 
             chunks = _slicechunk(self, deltachain, deltainfo)
-            distance = max(map(lambda revs:_segmentspan(self, revs), chunks))
+            all_span = [_segmentspan(self, revs, deltainfo) for revs in chunks]
+            distance = max(all_span)
         else:
             distance = deltainfo.distance
 
         textlen = revinfo.textlen
         defaultmax = textlen * 4
         maxdist = self._maxdeltachainspan
         if not maxdist:
             maxdist = distance # ensure the conditional pass
         maxdist = max(maxdist, defaultmax)
         if self._sparserevlog and maxdist < self._srmingapsize:
             # In multiple place, we are ignoring irrelevant data range below a
             # certain size. Be also apply this tradeoff here and relax span
             # constraint for small enought content.
             maxdist = self._srmingapsize
 
         # Bad delta from read span:
         #
         #   If the span of data read is larger than the maximum allowed.
         if maxdist < distance:
             return False
 
         # Bad delta from new delta size:
         #
         #   If the delta size is larger than the target text, storing the
         #   delta will be inefficient.
         if textlen < deltainfo.deltalen:
             return False
 
         # Bad delta from cumulated payload size:
         #
         #   If the sum of delta get larger than K * target text length.
         if textlen * LIMIT_DELTA2TEXT < deltainfo.compresseddeltalen:
             return False
 
         # Bad delta from chain length:
         #
         #   If the number of delta in the chain gets too high.
         if self._maxchainlen and  self._maxchainlen < deltainfo.chainlen:
             return False
 
         return True
 
     def _addrevision(self, node, rawtext, transaction, link, p1, p2, flags,
                      cachedelta, ifh, dfh, alwayscache=False,
                      deltacomputer=None):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == nullid:
             raise RevlogError(_("%s: attempt to add null revision") %
                               (self.indexfile))
         if node == wdirid or node in wdirfilenodeids:
             raise RevlogError(_("%s: attempt to add wdir revision") %
                               (self.indexfile))
 
         if self._inline:
             fh = ifh
         else:
             fh = dfh
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
         offset = self.end(prev)
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(revlog.size(self, cachedelta[0]),
                                         cachedelta[1])
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = _deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         # no delta for flag processor revision (see "candelta" for why)
         # not calling candelta since only one revision needs test, also to
         # avoid overhead fetching flags again.
         if flags & REVIDX_RAWTEXT_CHANGING_FLAGS:
             deltainfo = None
         else:
             deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         if deltainfo is not None:
             base = deltainfo.base
             chainbase = deltainfo.chainbase
             data = deltainfo.data
             l = deltainfo.deltalen
         else:
             rawtext = deltacomputer.buildtext(revinfo, fh)
             data = self.compress(rawtext)
             l = len(data[1]) + len(data[0])
             base = chainbase = curr
 
         e = (offset_type(offset, flags), l, textlen,
              base, link, p1r, p2r, node)
         self.index.append(e)
         self.nodemap[node] = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         self._writeentry(transaction, ifh, dfh, entry, data, link, offset)
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer._buildtext(revinfo, fh)
 
         if type(rawtext) == bytes: # only accept immutable objects
             self._cache = (node, curr, rawtext)
         self._chainbasecache[curr] = chainbase
         return node
 
     def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self._enforceinlinesize(transaction, ifh)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         nodes = []
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp("a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self._datafp("a+")
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
         try:
             deltacomputer = _deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 nodes.append(node)
 
                 if node in self.nodemap:
                     # this can happen if two branches make the same change
                     continue
 
                 for p in (p1, p2):
                     if p not in self.nodemap:
                         raise LookupError(p, self.indexfile,
                                           _('unknown parent'))
 
                 if deltabase not in self.nodemap:
                     raise LookupError(deltabase, self.indexfile,
                                       _('unknown delta base'))
 
                 baserev = self.rev(deltabase)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(self.indexfile,
                                                       self.node(baserev))
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
                 # We're only using addgroup() in the context of changegroup
                 # generation so the revision data can always be handled as raw
                 # by the flagprocessor.
                 self._addrevision(node, None, transaction, link,
                                   p1, p2, flags, (baserev, delta),
                                   ifh, dfh,
                                   alwayscache=bool(addrevisioncb),
                                   deltacomputer=deltacomputer)
 
                 if addrevisioncb:
                     addrevisioncb(self, node)
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp("a+")
                     ifh = self._indexfp("a+")
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
         return nodes
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         # Fragile heuristic: unless new file meta keys are added alphabetically
         # preceding "censored", all censored revisions are prefixed by
         # "\1\ncensored:". A delta producing such a censored revision must be a
         # full-replacement delta, so we inspect the first and only patch in the
         # delta for this prefix.
         hlen = struct.calcsize(">lll")
         if len(delta) <= hlen:
             return False
 
         oldlen = self.rawsize(baserev)
         newlen = len(delta) - hlen
         if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
             return False
 
         add = "\1\ncensored:"
         addlen = len(add)
         return newlen >= addlen and delta[hlen:hlen + addlen] == add
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         brokenrevs = set()
         strippoint = len(self)
 
         heads = {}
         futurelargelinkrevs = set()
         for head in self.headrevs():
             headlinkrev = self.linkrev(head)
             heads[head] = headlinkrev
             if headlinkrev >= minlink:
                 futurelargelinkrevs.add(headlinkrev)
 
         # This algorithm involves walking down the rev graph, starting at the
         # heads. Since the revs are topologically sorted according to linkrev,
         # once all head linkrevs are below the minlink, we know there are
         # no more revs that could have a linkrev greater than minlink.
         # So we can stop walking.
         while futurelargelinkrevs:
             strippoint -= 1
             linkrev = heads.pop(strippoint)
 
             if linkrev < minlink:
                 brokenrevs.add(strippoint)
             else:
                 futurelargelinkrevs.remove(linkrev)
 
             for p in self.parentrevs(strippoint):
                 if p != nullrev:
                     plinkrev = self.linkrev(p)
                     heads[p] = plinkrev
                     if plinkrev >= minlink:
                         futurelargelinkrevs.add(plinkrev)
 
         return strippoint, brokenrevs
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._cache = None
         self._chaininfocache = {}
         self._chunkclear()
         for x in pycompat.xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
         self._nodepos = None
 
     def checksize(self):
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, 2)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     DELTAREUSEALWAYS = 'always'
     DELTAREUSESAMEREVS = 'samerevs'
     DELTAREUSENEVER = 'never'
 
     DELTAREUSEFULLADD = 'fulladd'
 
     DELTAREUSEALL = {'always', 'samerevs', 'never', 'fulladd'}
 
     def clone(self, tr, destrevlog, addrevisioncb=None,
               deltareuse=DELTAREUSESAMEREVS, deltabothparents=None):
         """Copy this revlog to another, possibly with format changes.
 
         The destination revlog will contain the same revisions and nodes.
         However, it may not be bit-for-bit identical due to e.g. delta encoding
         differences.
 
         The ``deltareuse`` argument control how deltas from the existing revlog
         are preserved in the destination revlog. The argument can have the
         following values:
 
         DELTAREUSEALWAYS
            Deltas will always be reused (if possible), even if the destination
            revlog would not select the same revisions for the delta. This is the
            fastest mode of operation.
         DELTAREUSESAMEREVS
            Deltas will be reused if the destination revlog would pick the same
            revisions for the delta. This mode strikes a balance between speed
            and optimization.
         DELTAREUSENEVER
            Deltas will never be reused. This is the slowest mode of execution.
            This mode can be used to recompute deltas (e.g. if the diff/delta
            algorithm changes).
 
         Delta computation can be slow, so the choice of delta reuse policy can
         significantly affect run time.
 
         The default policy (``DELTAREUSESAMEREVS``) strikes a balance between
         two extremes. Deltas will be reused if they are appropriate. But if the
         delta could choose a better revision, it will do so. This means if you
         are converting a non-generaldelta revlog to a generaldelta revlog,
         deltas will be recomputed if the delta's parent isn't a parent of the
         revision.
 
         In addition to the delta policy, the ``deltabothparents`` argument
         controls whether to compute deltas against both parents for merges.
         By default, the current default is used.
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(_('value for deltareuse invalid: %s') % deltareuse)
 
         if len(destrevlog):
             raise ValueError(_('destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_('source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_('destination revlog has filtered revisions'))
 
         # lazydeltabase controls whether to reuse a cached delta, if possible.
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
 
             destrevlog._deltabothparents = deltabothparents or oldamd
 
             populatecachedelta = deltareuse in (self.DELTAREUSEALWAYS,
                                                 self.DELTAREUSESAMEREVS)
 
             deltacomputer = _deltacomputer(destrevlog)
             index = self.index
             for rev in self:
                 entry = index[rev]
 
                 # Some classes override linkrev to take filtered revs into
                 # account. Use raw entry from index.
                 flags = entry[0] & 0xffff
                 linkrev = entry[4]
                 p1 = index[entry[5]][7]
                 p2 = index[entry[6]][7]
                 node = entry[7]
 
                 # (Possibly) reuse the delta from the revlog if allowed and
                 # the revlog chunk is a delta.
                 cachedelta = None
                 rawtext = None
                 if populatecachedelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 if not cachedelta:
                     rawtext = self.revision(rev, raw=True)
 
 
                 if deltareuse == self.DELTAREUSEFULLADD:
                     destrevlog.addrevision(rawtext, tr, linkrev, p1, p2,
                                            cachedelta=cachedelta,
                                            node=node, flags=flags,
                                            deltacomputer=deltacomputer)
                 else:
                     ifh = destrevlog.opener(destrevlog.indexfile, 'a+',
                                             checkambig=False)
                     dfh = None
                     if not destrevlog._inline:
                         dfh = destrevlog.opener(destrevlog.datafile, 'a+')
                     try:
                         destrevlog._addrevision(node, rawtext, tr, linkrev, p1,
                                                 p2, flags, cachedelta, ifh, dfh,
                                                 deltacomputer=deltacomputer)
                     finally:
                         if dfh:
                             dfh.close()
                         ifh.close()
 
                 if addrevisioncb:
                     addrevisioncb(self, rev, node)
         finally:
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd

tests/test-bookmarks-pushpull.t

@@ -1,1277 +1,1277 b''
 #testcases b2-pushkey b2-binary
 
 #if b2-pushkey
   $ cat << EOF >> $HGRCPATH
   > [devel]
   > legacy.exchange=bookmarks
   > EOF
 #endif
 
 #require serve
 
   $ cat << EOF >> $HGRCPATH
   > [ui]
   > logtemplate={rev}:{node|short} {desc|firstline}
   > [phases]
   > publish=False
   > [experimental]
   > evolution.createmarkers=True
   > evolution.exchange=True
   > EOF
 
   $ cat > $TESTTMP/hook.sh <<'EOF'
   > echo "test-hook-bookmark: $HG_BOOKMARK:  $HG_OLDNODE -> $HG_NODE"
   > EOF
   $ TESTHOOK="hooks.txnclose-bookmark.test=sh $TESTTMP/hook.sh"
 
 initialize
 
   $ hg init a
   $ cd a
   $ echo 'test' > test
   $ hg commit -Am'test'
   adding test
 
 set bookmarks
 
   $ hg bookmark X
   $ hg bookmark Y
   $ hg bookmark Z
 
 import bookmark by name
 
   $ hg init ../b
   $ cd ../b
   $ hg book Y
   $ hg book
    * Y                         -1:000000000000
   $ hg pull ../a --config "$TESTHOOK"
   pulling from ../a
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   adding remote bookmark X
   updating bookmark Y
   adding remote bookmark Z
   new changesets 4e3505fd9583
   test-hook-bookmark: X:   -> 4e3505fd95835d721066b76e75dbb8cc554d7f77
   test-hook-bookmark: Y:  0000000000000000000000000000000000000000 -> 4e3505fd95835d721066b76e75dbb8cc554d7f77
   test-hook-bookmark: Z:   -> 4e3505fd95835d721066b76e75dbb8cc554d7f77
   (run 'hg update' to get a working copy)
   $ hg bookmarks
      X                         0:4e3505fd9583
    * Y                         0:4e3505fd9583
      Z                         0:4e3505fd9583
   $ hg debugpushkey ../a namespaces
   bookmarks	
   namespaces	
   obsolete	
   phases	
   $ hg debugpushkey ../a bookmarks
   X	4e3505fd95835d721066b76e75dbb8cc554d7f77
   Y	4e3505fd95835d721066b76e75dbb8cc554d7f77
   Z	4e3505fd95835d721066b76e75dbb8cc554d7f77
 
 delete the bookmark to re-pull it
 
   $ hg book -d X
   $ hg pull -B X ../a
   pulling from ../a
   no changes found
   adding remote bookmark X
 
 finally no-op pull
 
   $ hg pull -B X ../a
   pulling from ../a
   no changes found
   $ hg bookmark
      X                         0:4e3505fd9583
    * Y                         0:4e3505fd9583
      Z                         0:4e3505fd9583
 
 export bookmark by name
 
   $ hg bookmark W
   $ hg bookmark foo
   $ hg bookmark foobar
   $ hg push -B W ../a
   pushing to ../a
   searching for changes
   no changes found
   exporting bookmark W
   [1]
   $ hg -R ../a bookmarks
      W                         -1:000000000000
      X                         0:4e3505fd9583
      Y                         0:4e3505fd9583
    * Z                         0:4e3505fd9583
 
 delete a remote bookmark
 
   $ hg book -d W
 
 #if b2-pushkey
 
   $ hg push -B W ../a --config "$TESTHOOK" --debug --config devel.bundle2.debug=yes
   pushing to ../a
   query 1; heads
   searching for changes
   all remote heads known locally
   listing keys for "phases"
   checking for updated bookmarks
   listing keys for "bookmarks"
   no changes found
   bundle2-output-bundle: "HG20", 4 parts total
   bundle2-output: start emission of HG20 stream
   bundle2-output: bundle parameter: 
   bundle2-output: start of parts
   bundle2-output: bundle part: "replycaps"
   bundle2-output-part: "replycaps" 222 bytes payload
   bundle2-output: part 0: "REPLYCAPS"
   bundle2-output: header chunk size: 16
   bundle2-output: payload chunk size: 222
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "check:bookmarks"
   bundle2-output-part: "check:bookmarks" 23 bytes payload
   bundle2-output: part 1: "CHECK:BOOKMARKS"
   bundle2-output: header chunk size: 22
   bundle2-output: payload chunk size: 23
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "check:phases"
-  bundle2-output-part: "check:phases" 48 bytes payload
+  bundle2-output-part: "check:phases" 24 bytes payload
   bundle2-output: part 2: "CHECK:PHASES"
   bundle2-output: header chunk size: 19
-  bundle2-output: payload chunk size: 48
+  bundle2-output: payload chunk size: 24
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "pushkey"
   bundle2-output-part: "pushkey" (params: 4 mandatory) empty payload
   bundle2-output: part 3: "PUSHKEY"
   bundle2-output: header chunk size: 90
   bundle2-output: closing payload chunk
   bundle2-output: end of bundle
   bundle2-input: start processing of HG20 stream
   bundle2-input: reading bundle2 stream parameters
   bundle2-input-bundle: with-transaction
   bundle2-input: start extraction of bundle2 parts
   bundle2-input: part header size: 16
   bundle2-input: part type: "REPLYCAPS"
   bundle2-input: part id: "0"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part replycaps
   bundle2-input-part: "replycaps" supported
   bundle2-input: payload chunk size: 222
   bundle2-input: payload chunk size: 0
   bundle2-input-part: total payload size 222
   bundle2-input: part header size: 22
   bundle2-input: part type: "CHECK:BOOKMARKS"
   bundle2-input: part id: "1"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part check:bookmarks
   bundle2-input-part: "check:bookmarks" supported
   bundle2-input: payload chunk size: 23
   bundle2-input: payload chunk size: 0
   bundle2-input-part: total payload size 23
   bundle2-input: part header size: 19
   bundle2-input: part type: "CHECK:PHASES"
   bundle2-input: part id: "2"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part check:phases
   bundle2-input-part: "check:phases" supported
-  bundle2-input: payload chunk size: 48
+  bundle2-input: payload chunk size: 24
   bundle2-input: payload chunk size: 0
-  bundle2-input-part: total payload size 48
+  bundle2-input-part: total payload size 24
   bundle2-input: part header size: 90
   bundle2-input: part type: "PUSHKEY"
   bundle2-input: part id: "3"
   bundle2-input: part parameters: 4
   bundle2-input: found a handler for part pushkey
   bundle2-input-part: "pushkey" (params: 4 mandatory) supported
   pushing key for "bookmarks:W"
   bundle2-input: payload chunk size: 0
   bundle2-input: part header size: 0
   bundle2-input: end of bundle2 stream
   bundle2-input-bundle: 3 parts total
   running hook txnclose-bookmark.test: sh $TESTTMP/hook.sh
   test-hook-bookmark: W:  0000000000000000000000000000000000000000 -> 
   bundle2-output-bundle: "HG20", 1 parts total
   bundle2-output: start emission of HG20 stream
   bundle2-output: bundle parameter: 
   bundle2-output: start of parts
   bundle2-output: bundle part: "reply:pushkey"
   bundle2-output-part: "reply:pushkey" (params: 0 advisory) empty payload
   bundle2-output: part 0: "REPLY:PUSHKEY"
   bundle2-output: header chunk size: 43
   bundle2-output: closing payload chunk
   bundle2-output: end of bundle
   bundle2-input: start processing of HG20 stream
   bundle2-input: reading bundle2 stream parameters
   bundle2-input-bundle: no-transaction
   bundle2-input: start extraction of bundle2 parts
   bundle2-input: part header size: 43
   bundle2-input: part type: "REPLY:PUSHKEY"
   bundle2-input: part id: "0"
   bundle2-input: part parameters: 2
   bundle2-input: found a handler for part reply:pushkey
   bundle2-input-part: "reply:pushkey" (params: 0 advisory) supported
   bundle2-input: payload chunk size: 0
   bundle2-input: part header size: 0
   bundle2-input: end of bundle2 stream
   bundle2-input-bundle: 0 parts total
   deleting remote bookmark W
   listing keys for "phases"
   [1]
 
 #endif
 #if b2-binary
 
   $ hg push -B W ../a --config "$TESTHOOK" --debug --config devel.bundle2.debug=yes
   pushing to ../a
   query 1; heads
   searching for changes
   all remote heads known locally
   listing keys for "phases"
   checking for updated bookmarks
   listing keys for "bookmarks"
   no changes found
   bundle2-output-bundle: "HG20", 4 parts total
   bundle2-output: start emission of HG20 stream
   bundle2-output: bundle parameter: 
   bundle2-output: start of parts
   bundle2-output: bundle part: "replycaps"
   bundle2-output-part: "replycaps" 222 bytes payload
   bundle2-output: part 0: "REPLYCAPS"
   bundle2-output: header chunk size: 16
   bundle2-output: payload chunk size: 222
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "check:bookmarks"
   bundle2-output-part: "check:bookmarks" 23 bytes payload
   bundle2-output: part 1: "CHECK:BOOKMARKS"
   bundle2-output: header chunk size: 22
   bundle2-output: payload chunk size: 23
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "check:phases"
-  bundle2-output-part: "check:phases" 48 bytes payload
+  bundle2-output-part: "check:phases" 24 bytes payload
   bundle2-output: part 2: "CHECK:PHASES"
   bundle2-output: header chunk size: 19
-  bundle2-output: payload chunk size: 48
+  bundle2-output: payload chunk size: 24
   bundle2-output: closing payload chunk
   bundle2-output: bundle part: "bookmarks"
   bundle2-output-part: "bookmarks" 23 bytes payload
   bundle2-output: part 3: "BOOKMARKS"
   bundle2-output: header chunk size: 16
   bundle2-output: payload chunk size: 23
   bundle2-output: closing payload chunk
   bundle2-output: end of bundle
   bundle2-input: start processing of HG20 stream
   bundle2-input: reading bundle2 stream parameters
   bundle2-input-bundle: with-transaction
   bundle2-input: start extraction of bundle2 parts
   bundle2-input: part header size: 16
   bundle2-input: part type: "REPLYCAPS"
   bundle2-input: part id: "0"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part replycaps
   bundle2-input-part: "replycaps" supported
   bundle2-input: payload chunk size: 222
   bundle2-input: payload chunk size: 0
   bundle2-input-part: total payload size 222
   bundle2-input: part header size: 22
   bundle2-input: part type: "CHECK:BOOKMARKS"
   bundle2-input: part id: "1"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part check:bookmarks
   bundle2-input-part: "check:bookmarks" supported
   bundle2-input: payload chunk size: 23
   bundle2-input: payload chunk size: 0
   bundle2-input-part: total payload size 23
   bundle2-input: part header size: 19
   bundle2-input: part type: "CHECK:PHASES"
   bundle2-input: part id: "2"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part check:phases
   bundle2-input-part: "check:phases" supported
-  bundle2-input: payload chunk size: 48
+  bundle2-input: payload chunk size: 24
   bundle2-input: payload chunk size: 0
-  bundle2-input-part: total payload size 48
+  bundle2-input-part: total payload size 24
   bundle2-input: part header size: 16
   bundle2-input: part type: "BOOKMARKS"
   bundle2-input: part id: "3"
   bundle2-input: part parameters: 0
   bundle2-input: found a handler for part bookmarks
   bundle2-input-part: "bookmarks" supported
   bundle2-input: payload chunk size: 23
   bundle2-input: payload chunk size: 0
   bundle2-input-part: total payload size 23
   bundle2-input: part header size: 0
   bundle2-input: end of bundle2 stream
   bundle2-input-bundle: 3 parts total
   running hook txnclose-bookmark.test: sh $TESTTMP/hook.sh
   test-hook-bookmark: W:  0000000000000000000000000000000000000000 -> 
   bundle2-output-bundle: "HG20", 0 parts total
   bundle2-output: start emission of HG20 stream
   bundle2-output: bundle parameter: 
   bundle2-output: start of parts
   bundle2-output: end of bundle
   bundle2-input: start processing of HG20 stream
   bundle2-input: reading bundle2 stream parameters
   bundle2-input-bundle: no-transaction
   bundle2-input: start extraction of bundle2 parts
   bundle2-input: part header size: 0
   bundle2-input: end of bundle2 stream
   bundle2-input-bundle: 0 parts total
   deleting remote bookmark W
   listing keys for "phases"
   [1]
 
 #endif
 
 export the active bookmark
 
   $ hg bookmark V
   $ hg push -B . ../a
   pushing to ../a
   searching for changes
   no changes found
   exporting bookmark V
   [1]
 
 exporting the active bookmark with 'push -B .'
 demand that one of the bookmarks is activated
 
   $ hg update -r default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (leaving bookmark V)
   $ hg push -B . ../a
   abort: no active bookmark
   [255]
   $ hg update -r V
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (activating bookmark V)
 
 delete the bookmark
 
   $ hg book -d V
   $ hg push -B V ../a
   pushing to ../a
   searching for changes
   no changes found
   deleting remote bookmark V
   [1]
   $ hg up foobar
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (activating bookmark foobar)
 
 push/pull name that doesn't exist
 
   $ hg push -B badname ../a
   pushing to ../a
   searching for changes
   bookmark badname does not exist on the local or remote repository!
   no changes found
   [2]
   $ hg pull -B anotherbadname ../a
   pulling from ../a
   abort: remote bookmark anotherbadname not found!
   [255]
 
 divergent bookmarks
 
   $ cd ../a
   $ echo c1 > f1
   $ hg ci -Am1
   adding f1
   $ hg book -f @
   $ hg book -f X
   $ hg book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         0:4e3505fd9583
      Z                         1:0d2164f0ce0d
 
   $ cd ../b
   $ hg up
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   updating bookmark foobar
   $ echo c2 > f2
   $ hg ci -Am2
   adding f2
   $ hg book -if @
   $ hg book -if X
   $ hg book
      @                         1:9b140be10808
      X                         1:9b140be10808
      Y                         0:4e3505fd9583
      Z                         0:4e3505fd9583
      foo                       -1:000000000000
    * foobar                    1:9b140be10808
 
   $ hg pull --config paths.foo=../a foo --config "$TESTHOOK"
   pulling from $TESTTMP/a
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files (+1 heads)
   divergent bookmark @ stored as @foo
   divergent bookmark X stored as X@foo
   updating bookmark Z
   new changesets 0d2164f0ce0d
   test-hook-bookmark: @foo:   -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   test-hook-bookmark: X@foo:   -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   test-hook-bookmark: Z:  4e3505fd95835d721066b76e75dbb8cc554d7f77 -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   (run 'hg heads' to see heads, 'hg merge' to merge)
   $ hg book
      @                         1:9b140be10808
      @foo                      2:0d2164f0ce0d
      X                         1:9b140be10808
      X@foo                     2:0d2164f0ce0d
      Y                         0:4e3505fd9583
      Z                         2:0d2164f0ce0d
      foo                       -1:000000000000
    * foobar                    1:9b140be10808
 
 (test that too many divergence of bookmark)
 
   $ $PYTHON $TESTDIR/seq.py 1 100 | while read i; do hg bookmarks -r 000000000000 "X@${i}"; done
   $ hg pull ../a
   pulling from ../a
   searching for changes
   no changes found
   warning: failed to assign numbered name to divergent bookmark X
   divergent bookmark @ stored as @1
   $ hg bookmarks | grep '^   X' | grep -v ':000000000000'
      X                         1:9b140be10808
      X@foo                     2:0d2164f0ce0d
 
 (test that remotely diverged bookmarks are reused if they aren't changed)
 
   $ hg bookmarks | grep '^   @'
      @                         1:9b140be10808
      @1                        2:0d2164f0ce0d
      @foo                      2:0d2164f0ce0d
   $ hg pull ../a
   pulling from ../a
   searching for changes
   no changes found
   warning: failed to assign numbered name to divergent bookmark X
   divergent bookmark @ stored as @1
   $ hg bookmarks | grep '^   @'
      @                         1:9b140be10808
      @1                        2:0d2164f0ce0d
      @foo                      2:0d2164f0ce0d
 
   $ $PYTHON $TESTDIR/seq.py 1 100 | while read i; do hg bookmarks -d "X@${i}"; done
   $ hg bookmarks -d "@1"
 
   $ hg push -f ../a
   pushing to ../a
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files (+1 heads)
   $ hg -R ../a book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         0:4e3505fd9583
      Z                         1:0d2164f0ce0d
 
 explicit pull should overwrite the local version (issue4439)
 
   $ hg update -r X
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (activating bookmark X)
   $ hg pull --config paths.foo=../a foo -B . --config "$TESTHOOK"
   pulling from $TESTTMP/a
   no changes found
   divergent bookmark @ stored as @foo
   importing bookmark X
   test-hook-bookmark: @foo:  0d2164f0ce0d8f1d6f94351eba04b794909be66c -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   test-hook-bookmark: X:  9b140be1080824d768c5a4691a564088eede71f9 -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
 
 reinstall state for further testing:
 
   $ hg book -fr 9b140be10808 X
 
 revsets should not ignore divergent bookmarks
 
   $ hg bookmark -fr 1 Z
   $ hg log -r 'bookmark()' --template '{rev}:{node|short} {bookmarks}\n'
   0:4e3505fd9583 Y
   1:9b140be10808 @ X Z foobar
   2:0d2164f0ce0d @foo X@foo
   $ hg log -r 'bookmark("X@foo")' --template '{rev}:{node|short} {bookmarks}\n'
   2:0d2164f0ce0d @foo X@foo
   $ hg log -r 'bookmark("re:X@foo")' --template '{rev}:{node|short} {bookmarks}\n'
   2:0d2164f0ce0d @foo X@foo
 
 update a remote bookmark from a non-head to a head
 
   $ hg up -q Y
   $ echo c3 > f2
   $ hg ci -Am3
   adding f2
   created new head
   $ hg push ../a --config "$TESTHOOK"
   pushing to ../a
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files (+1 heads)
   test-hook-bookmark: Y:  4e3505fd95835d721066b76e75dbb8cc554d7f77 -> f6fc62dde3c0771e29704af56ba4d8af77abcc2f
   updating bookmark Y
   $ hg -R ../a book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         3:f6fc62dde3c0
      Z                         1:0d2164f0ce0d
 
 update a bookmark in the middle of a client pulling changes
 
   $ cd ..
   $ hg clone -q a pull-race
 
 We want to use http because it is stateless and therefore more susceptible to
 race conditions
 
   $ hg serve -R pull-race -p $HGPORT -d --pid-file=pull-race.pid -E main-error.log
   $ cat pull-race.pid >> $DAEMON_PIDS
 
   $ cat <<EOF > $TESTTMP/out_makecommit.sh
   > #!/bin/sh
   > hg ci -Am5
   > echo committed in pull-race
   > EOF
 
   $ hg clone -q http://localhost:$HGPORT/ pull-race2 --config "$TESTHOOK"
   test-hook-bookmark: @:   -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   test-hook-bookmark: X:   -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   test-hook-bookmark: Y:   -> f6fc62dde3c0771e29704af56ba4d8af77abcc2f
   test-hook-bookmark: Z:   -> 0d2164f0ce0d8f1d6f94351eba04b794909be66c
   $ cd pull-race
   $ hg up -q Y
   $ echo c4 > f2
   $ hg ci -Am4
   $ echo c5 > f3
   $ cat <<EOF > .hg/hgrc
   > [hooks]
   > outgoing.makecommit = sh $TESTTMP/out_makecommit.sh
   > EOF
 
 (new config needs a server restart)
 
   $ cd ..
   $ killdaemons.py
   $ hg serve -R pull-race -p $HGPORT -d --pid-file=pull-race.pid -E main-error.log
   $ cat pull-race.pid >> $DAEMON_PIDS
   $ cd pull-race2
   $ hg -R $TESTTMP/pull-race book
      @                         1:0d2164f0ce0d
      X                         1:0d2164f0ce0d
    * Y                         4:b0a5eff05604
      Z                         1:0d2164f0ce0d
   $ hg pull
   pulling from http://localhost:$HGPORT/
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   updating bookmark Y
   new changesets b0a5eff05604
   (run 'hg update' to get a working copy)
   $ hg book
    * @                         1:0d2164f0ce0d
      X                         1:0d2164f0ce0d
      Y                         4:b0a5eff05604
      Z                         1:0d2164f0ce0d
 
 Update a bookmark right after the initial lookup -B (issue4689)
 
   $ echo c6 > ../pull-race/f3 # to be committed during the race
   $ cat <<EOF > $TESTTMP/listkeys_makecommit.sh
   > #!/bin/sh
   > if hg st | grep -q M; then
   >     hg commit -m race
   >     echo committed in pull-race
   > else
   >     exit 0
   > fi
   > EOF
   $ cat <<EOF > ../pull-race/.hg/hgrc
   > [hooks]
   > # If anything to commit, commit it right after the first key listing used
   > # during lookup. This makes the commit appear before the actual getbundle
   > # call.
   > listkeys.makecommit= sh $TESTTMP/listkeys_makecommit.sh
   > EOF
 
 (new config need server restart)
 
   $ killdaemons.py
   $ hg serve -R ../pull-race -p $HGPORT -d --pid-file=../pull-race.pid -E main-error.log
   $ cat ../pull-race.pid >> $DAEMON_PIDS
 
   $ hg -R $TESTTMP/pull-race book
      @                         1:0d2164f0ce0d
      X                         1:0d2164f0ce0d
    * Y                         5:35d1ef0a8d1b
      Z                         1:0d2164f0ce0d
   $ hg update -r Y
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (activating bookmark Y)
   $ hg pull -B .
   pulling from http://localhost:$HGPORT/
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   updating bookmark Y
   new changesets 35d1ef0a8d1b
   (run 'hg update' to get a working copy)
   $ hg book
      @                         1:0d2164f0ce0d
      X                         1:0d2164f0ce0d
    * Y                         5:35d1ef0a8d1b
      Z                         1:0d2164f0ce0d
 
 (done with this section of the test)
 
   $ killdaemons.py
   $ cd ../b
 
 diverging a remote bookmark fails
 
   $ hg up -q 4e3505fd9583
   $ echo c4 > f2
   $ hg ci -Am4
   adding f2
   created new head
   $ echo c5 > f2
   $ hg ci -Am5
   $ hg log -G
   @  5:c922c0139ca0 5
   |
   o  4:4efff6d98829 4
   |
   | o  3:f6fc62dde3c0 3
   |/
   | o  2:0d2164f0ce0d 1
   |/
   | o  1:9b140be10808 2
   |/
   o  0:4e3505fd9583 test
   
 
   $ hg book -f Y
 
   $ cat <<EOF > ../a/.hg/hgrc
   > [web]
   > push_ssl = false
   > allow_push = *
   > EOF
 
   $ hg serve -R ../a -p $HGPORT2 -d --pid-file=../hg2.pid
   $ cat ../hg2.pid >> $DAEMON_PIDS
 
   $ hg push http://localhost:$HGPORT2/
   pushing to http://localhost:$HGPORT2/
   searching for changes
   abort: push creates new remote head c922c0139ca0 with bookmark 'Y'!
   (merge or see 'hg help push' for details about pushing new heads)
   [255]
   $ hg -R ../a book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         3:f6fc62dde3c0
      Z                         1:0d2164f0ce0d
 
 
 Unrelated marker does not alter the decision
 
   $ hg debugobsolete aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
   $ hg push http://localhost:$HGPORT2/
   pushing to http://localhost:$HGPORT2/
   searching for changes
   abort: push creates new remote head c922c0139ca0 with bookmark 'Y'!
   (merge or see 'hg help push' for details about pushing new heads)
   [255]
   $ hg -R ../a book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         3:f6fc62dde3c0
      Z                         1:0d2164f0ce0d
 
 Update to a successor works
 
   $ hg id --debug -r 3
   f6fc62dde3c0771e29704af56ba4d8af77abcc2f
   $ hg id --debug -r 4
   4efff6d98829d9c824c621afd6e3f01865f5439f
   $ hg id --debug -r 5
   c922c0139ca03858f655e4a2af4dd02796a63969 tip Y
   $ hg debugobsolete f6fc62dde3c0771e29704af56ba4d8af77abcc2f cccccccccccccccccccccccccccccccccccccccc
   obsoleted 1 changesets
   $ hg debugobsolete cccccccccccccccccccccccccccccccccccccccc 4efff6d98829d9c824c621afd6e3f01865f5439f
   $ hg push http://localhost:$HGPORT2/
   pushing to http://localhost:$HGPORT2/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 2 changesets with 2 changes to 1 files (+1 heads)
   remote: 2 new obsolescence markers
   remote: obsoleted 1 changesets
   updating bookmark Y
   $ hg -R ../a book
      @                         1:0d2164f0ce0d
    * X                         1:0d2164f0ce0d
      Y                         5:c922c0139ca0
      Z                         1:0d2164f0ce0d
 
 hgweb
 
   $ cat <<EOF > .hg/hgrc
   > [web]
   > push_ssl = false
   > allow_push = *
   > EOF
 
   $ hg serve -p $HGPORT -d --pid-file=../hg.pid -E errors.log
   $ cat ../hg.pid >> $DAEMON_PIDS
   $ cd ../a
 
   $ hg debugpushkey http://localhost:$HGPORT/ namespaces
   bookmarks	
   namespaces	
   obsolete	
   phases	
   $ hg debugpushkey http://localhost:$HGPORT/ bookmarks
   @	9b140be1080824d768c5a4691a564088eede71f9
   X	9b140be1080824d768c5a4691a564088eede71f9
   Y	c922c0139ca03858f655e4a2af4dd02796a63969
   Z	9b140be1080824d768c5a4691a564088eede71f9
   foo	0000000000000000000000000000000000000000
   foobar	9b140be1080824d768c5a4691a564088eede71f9
   $ hg out -B http://localhost:$HGPORT/
   comparing with http://localhost:$HGPORT/
   searching for changed bookmarks
      @                         0d2164f0ce0d
      X                         0d2164f0ce0d
      Z                         0d2164f0ce0d
      foo                                   
      foobar                                
   $ hg push -B Z http://localhost:$HGPORT/
   pushing to http://localhost:$HGPORT/
   searching for changes
   no changes found
   updating bookmark Z
   [1]
   $ hg book -d Z
   $ hg in -B http://localhost:$HGPORT/
   comparing with http://localhost:$HGPORT/
   searching for changed bookmarks
      @                         9b140be10808
      X                         9b140be10808
      Z                         0d2164f0ce0d
      foo                       000000000000
      foobar                    9b140be10808
   $ hg pull -B Z http://localhost:$HGPORT/
   pulling from http://localhost:$HGPORT/
   no changes found
   divergent bookmark @ stored as @1
   divergent bookmark X stored as X@1
   adding remote bookmark Z
   adding remote bookmark foo
   adding remote bookmark foobar
   $ hg clone http://localhost:$HGPORT/ cloned-bookmarks
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 5 changes to 3 files (+2 heads)
   2 new obsolescence markers
   new changesets 4e3505fd9583:c922c0139ca0
   updating to bookmark @
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R cloned-bookmarks bookmarks
    * @                         1:9b140be10808
      X                         1:9b140be10808
      Y                         4:c922c0139ca0
      Z                         2:0d2164f0ce0d
      foo                       -1:000000000000
      foobar                    1:9b140be10808
 
   $ cd ..
 
 Test to show result of bookmarks comparison
 
   $ mkdir bmcomparison
   $ cd bmcomparison
 
   $ hg init source
   $ hg -R source debugbuilddag '+2*2*3*4'
   $ hg -R source log -G --template '{rev}:{node|short}'
   o  4:e7bd5218ca15
   |
   | o  3:6100d3090acf
   |/
   | o  2:fa942426a6fd
   |/
   | o  1:66f7d451a68b
   |/
   o  0:1ea73414a91b
   
   $ hg -R source bookmarks -r 0 SAME
   $ hg -R source bookmarks -r 0 ADV_ON_REPO1
   $ hg -R source bookmarks -r 0 ADV_ON_REPO2
   $ hg -R source bookmarks -r 0 DIFF_ADV_ON_REPO1
   $ hg -R source bookmarks -r 0 DIFF_ADV_ON_REPO2
   $ hg -R source bookmarks -r 1 DIVERGED
 
   $ hg clone -U source repo1
 
 (test that incoming/outgoing exit with 1, if there is no bookmark to
 be exchanged)
 
   $ hg -R repo1 incoming -B
   comparing with $TESTTMP/bmcomparison/source
   searching for changed bookmarks
   no changed bookmarks found
   [1]
   $ hg -R repo1 outgoing -B
   comparing with $TESTTMP/bmcomparison/source
   searching for changed bookmarks
   no changed bookmarks found
   [1]
 
   $ hg -R repo1 bookmarks -f -r 1 ADD_ON_REPO1
   $ hg -R repo1 bookmarks -f -r 2 ADV_ON_REPO1
   $ hg -R repo1 bookmarks -f -r 3 DIFF_ADV_ON_REPO1
   $ hg -R repo1 bookmarks -f -r 3 DIFF_DIVERGED
   $ hg -R repo1 -q --config extensions.mq= strip 4
   $ hg -R repo1 log -G --template '{node|short} ({bookmarks})'
   o  6100d3090acf (DIFF_ADV_ON_REPO1 DIFF_DIVERGED)
   |
   | o  fa942426a6fd (ADV_ON_REPO1)
   |/
   | o  66f7d451a68b (ADD_ON_REPO1 DIVERGED)
   |/
   o  1ea73414a91b (ADV_ON_REPO2 DIFF_ADV_ON_REPO2 SAME)
   
 
   $ hg clone -U source repo2
   $ hg -R repo2 bookmarks -f -r 1 ADD_ON_REPO2
   $ hg -R repo2 bookmarks -f -r 1 ADV_ON_REPO2
   $ hg -R repo2 bookmarks -f -r 2 DIVERGED
   $ hg -R repo2 bookmarks -f -r 4 DIFF_ADV_ON_REPO2
   $ hg -R repo2 bookmarks -f -r 4 DIFF_DIVERGED
   $ hg -R repo2 -q --config extensions.mq= strip 3
   $ hg -R repo2 log -G --template '{node|short} ({bookmarks})'
   o  e7bd5218ca15 (DIFF_ADV_ON_REPO2 DIFF_DIVERGED)
   |
   | o  fa942426a6fd (DIVERGED)
   |/
   | o  66f7d451a68b (ADD_ON_REPO2 ADV_ON_REPO2)
   |/
   o  1ea73414a91b (ADV_ON_REPO1 DIFF_ADV_ON_REPO1 SAME)
   
 
 (test that difference of bookmarks between repositories are fully shown)
 
   $ hg -R repo1 incoming -B repo2 -v
   comparing with repo2
   searching for changed bookmarks
      ADD_ON_REPO2              66f7d451a68b added
      ADV_ON_REPO2              66f7d451a68b advanced
      DIFF_ADV_ON_REPO2         e7bd5218ca15 changed
      DIFF_DIVERGED             e7bd5218ca15 changed
      DIVERGED                  fa942426a6fd diverged
   $ hg -R repo1 outgoing -B repo2 -v
   comparing with repo2
   searching for changed bookmarks
      ADD_ON_REPO1              66f7d451a68b added
      ADD_ON_REPO2                           deleted
      ADV_ON_REPO1              fa942426a6fd advanced
      DIFF_ADV_ON_REPO1         6100d3090acf advanced
      DIFF_ADV_ON_REPO2         1ea73414a91b changed
      DIFF_DIVERGED             6100d3090acf changed
      DIVERGED                  66f7d451a68b diverged
 
   $ hg -R repo2 incoming -B repo1 -v
   comparing with repo1
   searching for changed bookmarks
      ADD_ON_REPO1              66f7d451a68b added
      ADV_ON_REPO1              fa942426a6fd advanced
      DIFF_ADV_ON_REPO1         6100d3090acf changed
      DIFF_DIVERGED             6100d3090acf changed
      DIVERGED                  66f7d451a68b diverged
   $ hg -R repo2 outgoing -B repo1 -v
   comparing with repo1
   searching for changed bookmarks
      ADD_ON_REPO1                           deleted
      ADD_ON_REPO2              66f7d451a68b added
      ADV_ON_REPO2              66f7d451a68b advanced
      DIFF_ADV_ON_REPO1         1ea73414a91b changed
      DIFF_ADV_ON_REPO2         e7bd5218ca15 advanced
      DIFF_DIVERGED             e7bd5218ca15 changed
      DIVERGED                  fa942426a6fd diverged
 
   $ cd ..
 
 Pushing a bookmark should only push the changes required by that
 bookmark, not all outgoing changes:
   $ hg clone http://localhost:$HGPORT/ addmarks
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 5 changes to 3 files (+2 heads)
   2 new obsolescence markers
   new changesets 4e3505fd9583:c922c0139ca0
   updating to bookmark @
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd addmarks
   $ echo foo > foo
   $ hg add foo
   $ hg commit -m 'add foo'
   $ echo bar > bar
   $ hg add bar
   $ hg commit -m 'add bar'
   $ hg co "tip^"
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (leaving bookmark @)
   $ hg book add-foo
   $ hg book -r tip add-bar
 Note: this push *must* push only a single changeset, as that's the point
 of this test.
   $ hg push -B add-foo --traceback
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   exporting bookmark add-foo
 
 pushing a new bookmark on a new head does not require -f if -B is specified
 
   $ hg up -q X
   $ hg book W
   $ echo c5 > f2
   $ hg ci -Am5
   created new head
   $ hg push -B .
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files (+1 heads)
   exporting bookmark W
   $ hg -R ../b id -r W
   cc978a373a53 tip W
 
 pushing an existing but divergent bookmark with -B still requires -f
 
   $ hg clone -q . ../r
   $ hg up -q X
   $ echo 1 > f2
   $ hg ci -qAml
 
   $ cd ../r
   $ hg up -q X
   $ echo 2 > f2
   $ hg ci -qAmr
   $ hg push -B X
   pushing to $TESTTMP/addmarks
   searching for changes
   remote has heads on branch 'default' that are not known locally: a2a606d9ff1b
   abort: push creates new remote head 54694f811df9 with bookmark 'X'!
   (pull and merge or see 'hg help push' for details about pushing new heads)
   [255]
   $ cd ../addmarks
 
 Check summary output for incoming/outgoing bookmarks
 
   $ hg bookmarks -d X
   $ hg bookmarks -d Y
   $ hg summary --remote | grep '^remote:'
   remote: *, 2 incoming bookmarks, 1 outgoing bookmarks (glob)
 
   $ cd ..
 
 pushing an unchanged bookmark should result in no changes
 
   $ hg init unchanged-a
   $ hg init unchanged-b
   $ cd unchanged-a
   $ echo initial > foo
   $ hg commit -A -m initial
   adding foo
   $ hg bookmark @
   $ hg push -B @ ../unchanged-b
   pushing to ../unchanged-b
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   exporting bookmark @
 
   $ hg push -B @ ../unchanged-b
   pushing to ../unchanged-b
   searching for changes
   no changes found
   [1]
 
 Pushing a really long bookmark should work fine (issue5165)
 ===============================================
 
 #if b2-binary
   >>> with open('longname', 'w') as f:
   ...     f.write('wat' * 100) and None
   $ hg book `cat longname`
   $ hg push -B `cat longname` ../unchanged-b
   pushing to ../unchanged-b
   searching for changes
   no changes found
   exporting bookmark (wat){100} (re)
   [1]
   $ hg -R ../unchanged-b book --delete `cat longname`
 
 Test again but forcing bundle2 exchange to make sure that doesn't regress.
 
   $ hg push -B `cat longname` ../unchanged-b --config devel.legacy.exchange=bundle1
   pushing to ../unchanged-b
   searching for changes
   no changes found
   exporting bookmark (wat){100} (re)
   [1]
   $ hg -R ../unchanged-b book --delete `cat longname`
   $ hg book --delete `cat longname`
   $ hg co @
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (activating bookmark @)
 #endif
 
 Check hook preventing push (issue4455)
 ======================================
 
   $ hg bookmarks
    * @                         0:55482a6fb4b1
   $ hg log -G
   @  0:55482a6fb4b1 initial
   
   $ hg init ../issue4455-dest
   $ hg push ../issue4455-dest # changesets only
   pushing to ../issue4455-dest
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   $ cat >> .hg/hgrc << EOF
   > [paths]
   > local=../issue4455-dest/
   > ssh=ssh://user@dummy/issue4455-dest
   > http=http://localhost:$HGPORT/
   > [ui]
   > ssh=$PYTHON "$TESTDIR/dummyssh"
   > EOF
   $ cat >> ../issue4455-dest/.hg/hgrc << EOF
   > [hooks]
   > prepushkey=false
   > [web]
   > push_ssl = false
   > allow_push = *
   > EOF
   $ killdaemons.py
   $ hg serve -R ../issue4455-dest -p $HGPORT -d --pid-file=../issue4455.pid -E ../issue4455-error.log
   $ cat ../issue4455.pid >> $DAEMON_PIDS
 
 Local push
 ----------
 
 #if b2-pushkey
 
   $ hg push -B @ local
   pushing to $TESTTMP/issue4455-dest
   searching for changes
   no changes found
   pushkey-abort: prepushkey hook exited with status 1
   abort: exporting bookmark @ failed!
   [255]
 
 #endif
 #if b2-binary
 
   $ hg push -B @ local
   pushing to $TESTTMP/issue4455-dest
   searching for changes
   no changes found
   abort: prepushkey hook exited with status 1
   [255]
 
 #endif
 
   $ hg -R ../issue4455-dest/ bookmarks
   no bookmarks set
 
 Using ssh
 ---------
 
 #if b2-pushkey
 
   $ hg push -B @ ssh # bundle2+
   pushing to ssh://user@dummy/issue4455-dest
   searching for changes
   no changes found
   remote: pushkey-abort: prepushkey hook exited with status 1
   abort: exporting bookmark @ failed!
   [255]
 
   $ hg -R ../issue4455-dest/ bookmarks
   no bookmarks set
 
   $ hg push -B @ ssh --config devel.legacy.exchange=bundle1
   pushing to ssh://user@dummy/issue4455-dest
   searching for changes
   no changes found
   remote: pushkey-abort: prepushkey hook exited with status 1
   exporting bookmark @ failed!
   [1]
 
 #endif
 #if b2-binary
 
   $ hg push -B @ ssh # bundle2+
   pushing to ssh://user@dummy/issue4455-dest
   searching for changes
   no changes found
   remote: prepushkey hook exited with status 1
   abort: push failed on remote
   [255]
 
 #endif
 
   $ hg -R ../issue4455-dest/ bookmarks
   no bookmarks set
 
 Using http
 ----------
 
 #if b2-pushkey
   $ hg push -B @ http # bundle2+
   pushing to http://localhost:$HGPORT/
   searching for changes
   no changes found
   remote: pushkey-abort: prepushkey hook exited with status 1
   abort: exporting bookmark @ failed!
   [255]
 
   $ hg -R ../issue4455-dest/ bookmarks
   no bookmarks set
 
   $ hg push -B @ http --config devel.legacy.exchange=bundle1
   pushing to http://localhost:$HGPORT/
   searching for changes
   no changes found
   remote: pushkey-abort: prepushkey hook exited with status 1
   exporting bookmark @ failed!
   [1]
 
 #endif
 
 #if b2-binary
 
   $ hg push -B @ ssh # bundle2+
   pushing to ssh://user@dummy/issue4455-dest
   searching for changes
   no changes found
   remote: prepushkey hook exited with status 1
   abort: push failed on remote
   [255]
 
 #endif
 
   $ hg -R ../issue4455-dest/ bookmarks
   no bookmarks set
 
   $ cd ..
 
 Test that pre-pushkey compat for bookmark works as expected (issue5777)
 
   $ cat << EOF >> $HGRCPATH
   > [ui]
   > ssh="$PYTHON" "$TESTDIR/dummyssh"
   > [server]
   > bookmarks-pushkey-compat = yes
   > EOF
 
   $ hg init server
   $ echo foo > server/a
   $ hg -R server book foo
   $ hg -R server commit -Am a
   adding a
   $ hg clone ssh://user@dummy/server client
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   new changesets 79513d0d7716
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Forbid bookmark move on the server
 
   $ cat << EOF >> $TESTDIR/no-bm-move.sh
   > #!/bin/sh
   > echo \$HG_NAMESPACE | grep -v bookmarks
   > EOF
   $ cat << EOF >> server/.hg/hgrc
   > [hooks]
   > prepushkey.no-bm-move= sh $TESTDIR/no-bm-move.sh
   > EOF
 
 pushing changeset is okay
 
   $ echo bar >> client/a
   $ hg -R client commit -m b
   $ hg -R client push
   pushing to ssh://user@dummy/server
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
 
 attempt to move the bookmark is rejected
 
   $ hg -R client book foo -r .
   moving bookmark 'foo' forward from 79513d0d7716
 
 #if b2-pushkey
   $ hg -R client push
   pushing to ssh://user@dummy/server
   searching for changes
   no changes found
   remote: pushkey-abort: prepushkey.no-bm-move hook exited with status 1
   abort: updating bookmark foo failed!
   [255]
 #endif
 #if b2-binary
   $ hg -R client push
   pushing to ssh://user@dummy/server
   searching for changes
   no changes found
   remote: prepushkey.no-bm-move hook exited with status 1
   abort: push failed on remote
   [255]
 #endif

tests/test-contrib-perf.t

@@ -1,215 +1,220 b''
 #require test-repo
 
 Set vars:
 
   $ . "$TESTDIR/helpers-testrepo.sh"
   $ CONTRIBDIR="$TESTDIR/../contrib"
 
 Prepare repo:
 
   $ hg init
 
   $ echo this is file a > a
   $ hg add a
   $ hg commit -m first
 
   $ echo adding to file a >> a
   $ hg commit -m second
 
   $ echo adding more to file a >> a
   $ hg commit -m third
 
   $ hg up -r 0
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo merge-this >> a
   $ hg commit -m merge-able
   created new head
 
   $ hg up -r 2
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 perfstatus
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > perfstatusext=$CONTRIBDIR/perf.py
   > [perf]
   > presleep=0
   > stub=on
   > parentscount=1
   > EOF
   $ hg help perfstatusext
   perfstatusext extension - helper extension to measure performance
   
   list of commands:
   
    perfaddremove
                  (no help text available)
    perfancestors
                  (no help text available)
    perfancestorset
                  (no help text available)
    perfannotate  (no help text available)
    perfbdiff     benchmark a bdiff between revisions
    perfbookmarks
                  benchmark parsing bookmarks from disk to memory
    perfbranchmap
                  benchmark the update of a branchmap
    perfbranchmapload
                  benchmark reading the branchmap
    perfbundleread
                  Benchmark reading of bundle files.
    perfcca       (no help text available)
    perfchangegroupchangelog
                  Benchmark producing a changelog group for a changegroup.
    perfchangeset
                  (no help text available)
    perfctxfiles  (no help text available)
    perfdiffwd    Profile diff of working directory changes
    perfdirfoldmap
                  (no help text available)
    perfdirs      (no help text available)
    perfdirstate  (no help text available)
    perfdirstatedirs
                  (no help text available)
    perfdirstatefoldmap
                  (no help text available)
    perfdirstatewrite
                  (no help text available)
    perffncacheencode
                  (no help text available)
    perffncacheload
                  (no help text available)
    perffncachewrite
                  (no help text available)
    perfheads     (no help text available)
    perfindex     (no help text available)
    perflinelogedits
                  (no help text available)
    perfloadmarkers
                  benchmark the time to parse the on-disk markers for a repo
    perflog       (no help text available)
    perflookup    (no help text available)
    perflrucachedict
                  (no help text available)
    perfmanifest  benchmark the time to read a manifest from disk and return a
                  usable
    perfmergecalculate
                  (no help text available)
    perfmoonwalk  benchmark walking the changelog backwards
    perfnodelookup
                  (no help text available)
    perfparents   (no help text available)
    perfpathcopies
                  (no help text available)
    perfphases    benchmark phasesets computation
+   perfphasesremote
+                 benchmark time needed to analyse phases of the remote server
    perfrawfiles  (no help text available)
    perfrevlogchunks
                  Benchmark operations on revlog chunks.
    perfrevlogindex
                  Benchmark operations against a revlog index.
    perfrevlogrevision
                  Benchmark obtaining a revlog revision.
    perfrevlogrevisions
                  Benchmark reading a series of revisions from a revlog.
    perfrevrange  (no help text available)
    perfrevset    benchmark the execution time of a revset
    perfstartup   (no help text available)
    perfstatus    (no help text available)
    perftags      (no help text available)
    perftemplating
                  test the rendering time of a given template
    perfunidiff   benchmark a unified diff between revisions
    perfvolatilesets
                  benchmark the computation of various volatile set
    perfwalk      (no help text available)
    perfwrite     microbenchmark ui.write
   
   (use 'hg help -v perfstatusext' to show built-in aliases and global options)
   $ hg perfaddremove
   $ hg perfancestors
   $ hg perfancestorset 2
   $ hg perfannotate a
   $ hg perfbdiff -c 1
   $ hg perfbdiff --alldata 1
   $ hg perfunidiff -c 1
   $ hg perfunidiff --alldata 1
   $ hg perfbookmarks
   $ hg perfbranchmap
   $ hg perfcca
   $ hg perfchangegroupchangelog
   $ hg perfchangeset 2
   $ hg perfctxfiles 2
   $ hg perfdiffwd
   $ hg perfdirfoldmap
   $ hg perfdirs
   $ hg perfdirstate
   $ hg perfdirstatedirs
   $ hg perfdirstatefoldmap
   $ hg perfdirstatewrite
 #if repofncache
   $ hg perffncacheencode
   $ hg perffncacheload
   $ hg debugrebuildfncache
   fncache already up to date
   $ hg perffncachewrite
   $ hg debugrebuildfncache
   fncache already up to date
 #endif
   $ hg perfheads
   $ hg perfindex
   $ hg perflinelogedits -n 1
   $ hg perfloadmarkers
   $ hg perflog
   $ hg perflookup 2
   $ hg perflrucache
   $ hg perfmanifest 2
   $ hg perfmergecalculate -r 3
   $ hg perfmoonwalk
   $ hg perfnodelookup 2
   $ hg perfpathcopies 1 2
   $ hg perfrawfiles 2
   $ hg perfrevlogindex -c
 #if reporevlogstore
   $ hg perfrevlogrevisions .hg/store/data/a.i
 #endif
   $ hg perfrevlogrevision -m 0
   $ hg perfrevlogchunks -c
   $ hg perfrevrange
   $ hg perfrevset 'all()'
   $ hg perfstartup
   $ hg perfstatus
   $ hg perftags
   $ hg perftemplating
   $ hg perfvolatilesets
   $ hg perfwalk
   $ hg perfparents
 
 test actual output
 ------------------
 
 normal output:
 
   $ hg perfheads --config perf.stub=no
   ! wall * comb * user * sys * (best of *) (glob)
 
 detailed output:
 
   $ hg perfheads --config perf.all-timing=yes --config perf.stub=no
   ! wall * comb * user * sys * (best of *) (glob)
   ! wall * comb * user * sys * (max of *) (glob)
   ! wall * comb * user * sys * (avg of *) (glob)
   ! wall * comb * user * sys * (median of *) (glob)
 
 Check perf.py for historical portability
 ----------------------------------------
 
   $ cd "$TESTDIR/.."
 
   $ (testrepohg files -r 1.2 glob:mercurial/*.c glob:mercurial/*.py;
   >  testrepohg files -r tip glob:mercurial/*.c glob:mercurial/*.py) |
   > "$TESTDIR"/check-perf-code.py contrib/perf.py
   contrib/perf.py:\d+: (re)
    >     from mercurial import (
    import newer module separately in try clause for early Mercurial
+  contrib/perf.py:\d+: (re)
+   >     from mercurial import (
+   import newer module separately in try clause for early Mercurial
   [1]