cleanup: mark some ui.(status|note|warn|write) calls as not needing i18n

These used to be marked with no-op parens, but black removes those now
and this is more explicit.

# skip-blame: fallout from mass reformatting

Differential Revision: https://phab.mercurial-scm.org/D6996

contrib/debugshell.py

@@ -1,65 +1,65 b''
 # debugshell extension
 """a python shell with repo, changelog & manifest objects"""
 
 from __future__ import absolute_import
 import code
 import mercurial
 import sys
 from mercurial import (
     demandimport,
     pycompat,
     registrar,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 
 def pdb(ui, repo, msg, **opts):
     objects = {
         'mercurial': mercurial,
         'repo': repo,
         'cl': repo.changelog,
         'mf': repo.manifestlog,
     }
 
     code.interact(msg, local=objects)
 
 
 def ipdb(ui, repo, msg, **opts):
     import IPython
 
     cl = repo.changelog
     mf = repo.manifestlog
     cl, mf  # use variables to appease pyflakes
 
     IPython.embed()
 
 
 @command(b'debugshell|dbsh', [])
 def debugshell(ui, repo, **opts):
     bannermsg = "loaded repo : %s\n" "using source: %s" % (
         pycompat.sysstr(repo.root),
         mercurial.__path__[0],
     )
 
     pdbmap = {'pdb': 'code', 'ipdb': 'IPython'}
 
     debugger = ui.config(b"ui", b"debugger")
     if not debugger:
         debugger = 'pdb'
     else:
         debugger = pycompat.sysstr(debugger)
 
     # if IPython doesn't exist, fallback to code.interact
     try:
         with demandimport.deactivated():
             __import__(pdbmap[debugger])
     except ImportError:
-        ui.warn(
+        ui.warnnoi18n(
             b"%s debugger specified but %s module was not found\n"
             % (debugger, pdbmap[debugger])
         )
         debugger = b'pdb'
 
     getattr(sys.modules[__name__], debugger)(ui, repo, bannermsg, **opts)

contrib/perf.py

@@ -1,3744 +1,3744 b''
 # perf.py - performance test routines
 '''helper extension to measure performance
 
 Configurations
 ==============
 
 ``perf``
 --------
 
 ``all-timing``
     When set, additional statistics will be reported for each benchmark: best,
     worst, median average. If not set only the best timing is reported
     (default: off).
 
 ``presleep``
   number of second to wait before any group of runs (default: 1)
 
 ``pre-run``
   number of run to perform before starting measurement.
 
 ``profile-benchmark``
   Enable profiling for the benchmarked section.
   (The first iteration is benchmarked)
 
 ``run-limits``
   Control the number of runs each benchmark will perform. The option value
   should be a list of `<time>-<numberofrun>` pairs. After each run the
   conditions are considered in order with the following logic:
 
       If benchmark has been running for <time> seconds, and we have performed
       <numberofrun> iterations, stop the benchmark,
 
   The default value is: `3.0-100, 10.0-3`
 
 ``stub``
     When set, benchmarks will only be run once, useful for testing
     (default: off)
 '''
 
 # "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 contextlib
 import functools
 import gc
 import os
 import random
 import shutil
 import struct
 import sys
 import tempfile
 import threading
 import time
 from mercurial import (
     changegroup,
     cmdutil,
     commands,
     copies,
     error,
     extensions,
     hg,
     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.utils import repoviewutil  # since 5.0
 except ImportError:
     repoviewutil = None
 try:
     from mercurial import scmutil  # since 1.9 (or 8b252e826c68)
 except ImportError:
     pass
 try:
     from mercurial import setdiscovery  # since 1.9 (or cb98fed52495)
 except ImportError:
     pass
 
 try:
     from mercurial import profiling
 except ImportError:
     profiling = None
 
 
 def identity(a):
     return a
 
 
 try:
     from mercurial import pycompat
 
     getargspec = pycompat.getargspec  # added to module after 4.5
     _byteskwargs = pycompat.byteskwargs  # since 4.1 (or fbc3f73dc802)
     _sysstr = pycompat.sysstr  # since 4.0 (or 2219f4f82ede)
     _bytestr = pycompat.bytestr  # since 4.2 (or b70407bd84d5)
     _xrange = pycompat.xrange  # since 4.8 (or 7eba8f83129b)
     fsencode = pycompat.fsencode  # since 3.9 (or f4a5e0e86a7e)
     if pycompat.ispy3:
         _maxint = sys.maxsize  # per py3 docs for replacing maxint
     else:
         _maxint = sys.maxint
 except (NameError, ImportError, AttributeError):
     import inspect
 
     getargspec = inspect.getargspec
     _byteskwargs = identity
     _bytestr = str
     fsencode = identity  # no py3 support
     _maxint = sys.maxint  # no py3 support
     _sysstr = lambda x: x  # no py3 support
     _xrange = xrange
 
 try:
     # 4.7+
     queue = pycompat.queue.Queue
 except (NameError, AttributeError, ImportError):
     # <4.7.
     try:
         queue = pycompat.queue
     except (NameError, AttributeError, ImportError):
         import Queue as 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, _sysstr(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 == b'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",
         [
             (b'c', b'changelog', False, b'open changelog'),
             (b'm', b'manifest', False, b'open manifest'),
             (b'', b'dir', False, b'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.split(b"|")
 
 
 if safehasattr(registrar, 'command'):
     command = registrar.command(cmdtable)
 elif safehasattr(cmdutil, 'command'):
     command = cmdutil.command(cmdtable)
     if b'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 += b' %s' % b' '.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 += b' %s' % b' '.join(parsealiases(name))
             return func
 
         return decorator
 
 
 try:
     import mercurial.registrar
     import mercurial.configitems
 
     configtable = {}
     configitem = mercurial.registrar.configitem(configtable)
     configitem(
         b'perf',
         b'presleep',
         default=mercurial.configitems.dynamicdefault,
         experimental=True,
     )
     configitem(
         b'perf',
         b'stub',
         default=mercurial.configitems.dynamicdefault,
         experimental=True,
     )
     configitem(
         b'perf',
         b'parentscount',
         default=mercurial.configitems.dynamicdefault,
         experimental=True,
     )
     configitem(
         b'perf',
         b'all-timing',
         default=mercurial.configitems.dynamicdefault,
         experimental=True,
     )
     configitem(
         b'perf', b'pre-run', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf',
         b'profile-benchmark',
         default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf',
         b'run-limits',
         default=mercurial.configitems.dynamicdefault,
         experimental=True,
     )
 except (ImportError, AttributeError):
     pass
 except TypeError:
     # compatibility fix for a11fd395e83f
     # hg version: 5.2
     configitem(
         b'perf', b'presleep', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf', b'stub', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf', b'parentscount', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf', b'all-timing', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf', b'pre-run', default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf',
         b'profile-benchmark',
         default=mercurial.configitems.dynamicdefault,
     )
     configitem(
         b'perf', b'run-limits', default=mercurial.configitems.dynamicdefault,
     )
 
 
 def getlen(ui):
     if ui.configbool(b"perf", b"stub", False):
         return lambda x: 1
     return len
 
 
 class noop(object):
     """dummy context manager"""
 
     def __enter__(self):
         pass
 
     def __exit__(self, *args):
         pass
 
 
 NOOPCTX = noop()
 
 
 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, b"perf", b"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, b'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(b'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, b'perf', opts)
 
     # stub function, runs code only once instead of in a loop
     # experimental config: perf.stub
     if ui.configbool(b"perf", b"stub", False):
         return functools.partial(stub_timer, fm), fm
 
     # experimental config: perf.all-timing
     displayall = ui.configbool(b"perf", b"all-timing", False)
 
     # experimental config: perf.run-limits
     limitspec = ui.configlist(b"perf", b"run-limits", [])
     limits = []
     for item in limitspec:
         parts = item.split(b'-', 1)
         if len(parts) < 2:
             ui.warn((b'malformatted run limit entry, missing "-": %s\n' % item))
             continue
         try:
             time_limit = float(_sysstr(parts[0]))
         except ValueError as e:
             ui.warn(
                 (
                     b'malformatted run limit entry, %s: %s\n'
                     % (_bytestr(e), item)
                 )
             )
             continue
         try:
             run_limit = int(_sysstr(parts[1]))
         except ValueError as e:
             ui.warn(
                 (
                     b'malformatted run limit entry, %s: %s\n'
                     % (_bytestr(e), item)
                 )
             )
             continue
         limits.append((time_limit, run_limit))
     if not limits:
         limits = DEFAULTLIMITS
 
     profiler = None
     if profiling is not None:
         if ui.configbool(b"perf", b"profile-benchmark", False):
             profiler = profiling.profile(ui)
 
     prerun = getint(ui, b"perf", b"pre-run", 0)
     t = functools.partial(
         _timer,
         fm,
         displayall=displayall,
         limits=limits,
         prerun=prerun,
         profiler=profiler,
     )
     return t, fm
 
 
 def stub_timer(fm, func, setup=None, title=None):
     if setup is not None:
         setup()
     func()
 
 
 @contextlib.contextmanager
 def timeone():
     r = []
     ostart = os.times()
     cstart = util.timer()
     yield r
     cstop = util.timer()
     ostop = os.times()
     a, b = ostart, ostop
     r.append((cstop - cstart, b[0] - a[0], b[1] - a[1]))
 
 
 # list of stop condition (elapsed time, minimal run count)
 DEFAULTLIMITS = (
     (3.0, 100),
     (10.0, 3),
 )
 
 
 def _timer(
     fm,
     func,
     setup=None,
     title=None,
     displayall=False,
     limits=DEFAULTLIMITS,
     prerun=0,
     profiler=None,
 ):
     gc.collect()
     results = []
     begin = util.timer()
     count = 0
     if profiler is None:
         profiler = NOOPCTX
     for i in range(prerun):
         if setup is not None:
             setup()
         func()
     keepgoing = True
     while keepgoing:
         if setup is not None:
             setup()
         with profiler:
             with timeone() as item:
                 r = func()
         profiler = NOOPCTX
         count += 1
         results.append(item[0])
         cstop = util.timer()
         # Look for a stop condition.
         elapsed = cstop - begin
         for t, mincount in limits:
             if elapsed >= t and count >= mincount:
                 keepgoing = False
                 break
 
     formatone(fm, results, title=title, result=r, displayall=displayall)
 
 
 def formatone(fm, timings, title=None, result=None, displayall=False):
 
     count = len(timings)
 
     fm.startitem()
 
     if title:
         fm.write(b'title', b'! %s\n', title)
     if result:
         fm.write(b'result', b'! result: %s\n', result)
 
     def display(role, entry):
         prefix = b''
         if role != b'best':
             prefix = b'%s.' % role
         fm.plain(b'!')
         fm.write(prefix + b'wall', b' wall %f', entry[0])
         fm.write(prefix + b'comb', b' comb %f', entry[1] + entry[2])
         fm.write(prefix + b'user', b' user %f', entry[1])
         fm.write(prefix + b'sys', b' sys %f', entry[2])
         fm.write(prefix + b'count', b' (%s of %%d)' % role, count)
         fm.plain(b'\n')
 
     timings.sort()
     min_val = timings[0]
     display(b'best', min_val)
     if displayall:
         max_val = timings[-1]
         display(b'max', max_val)
         avg = tuple([sum(x) / count for x in zip(*timings)])
         display(b'avg', avg)
         median = timings[len(timings) // 2]
         display(b'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(
             b"%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(
             (
                 b"missing attribute %s of %s might break assumption"
                 b" of performance measurement"
             )
             % (name, obj)
         )
 
     origvalue = getattr(obj, _sysstr(name))
 
     class attrutil(object):
         def set(self, newvalue):
             setattr(obj, _sysstr(name), newvalue)
 
         def restore(self):
             setattr(obj, _sysstr(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)
     # - repoviewutil since 5.0
     for mod in (branchmap, repoview, repoviewutil):
         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(
         b"perfbranchmap not available with this Mercurial",
         hint=b"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, b'_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 b'_tagscache' in vars(repo):
                 del repo.__dict__[b'_tagscache']
 
         return clearcache
 
     repotags = safeattrsetter(repo, b'_tags', ignoremissing=True)
     if repotags:  # since 1.4 (or 5614a628d173)
         return lambda: repotags.set(None)
 
     repotagscache = safeattrsetter(repo, b'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(b"tags API of this hg command is unknown")
 
 
 # utilities to clear cache
 
 
 def clearfilecache(obj, attrname):
     unfiltered = getattr(obj, 'unfiltered', None)
     if unfiltered is not None:
         obj = obj.unfiltered()
     if attrname in vars(obj):
         delattr(obj, attrname)
     obj._filecache.pop(attrname, None)
 
 
 def clearchangelog(repo):
     if repo is not repo.unfiltered():
         object.__setattr__(repo, r'_clcachekey', None)
         object.__setattr__(repo, r'_clcache', None)
     clearfilecache(repo.unfiltered(), 'changelog')
 
 
 # perf commands
 
 
 @command(b'perfwalk', formatteropts)
 def perfwalk(ui, repo, *pats, **opts):
     opts = _byteskwargs(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(b'perfannotate', formatteropts)
 def perfannotate(ui, repo, f, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     fc = repo[b'.'][f]
     timer(lambda: len(fc.annotate(True)))
     fm.end()
 
 
 @command(
     b'perfstatus',
     [(b'u', b'unknown', False, b'ask status to look for unknown files')]
     + formatteropts,
 )
 def perfstatus(ui, repo, **opts):
     opts = _byteskwargs(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[b'unknown']))))
     fm.end()
 
 
 @command(b'perfaddremove', formatteropts)
 def perfaddremove(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     try:
         oldquiet = repo.ui.quiet
         repo.ui.quiet = True
         matcher = scmutil.match(repo[None])
         opts[b'dry_run'] = True
         if b'uipathfn' in getargspec(scmutil.addremove).args:
             uipathfn = scmutil.getuipathfn(repo)
             timer(lambda: scmutil.addremove(repo, matcher, b"", uipathfn, opts))
         else:
             timer(lambda: scmutil.addremove(repo, matcher, b"", opts))
     finally:
         repo.ui.quiet = oldquiet
         fm.end()
 
 
 def clearcaches(cl):
     # behave somewhat consistently across internal API changes
     if util.safehasattr(cl, b'clearcaches'):
         cl.clearcaches()
     elif util.safehasattr(cl, b'_nodecache'):
         from mercurial.node import nullid, nullrev
 
         cl._nodecache = {nullid: nullrev}
         cl._nodepos = None
 
 
 @command(b'perfheads', formatteropts)
 def perfheads(ui, repo, **opts):
     """benchmark the computation of a changelog heads"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
 
     def s():
         clearcaches(cl)
 
     def d():
         len(cl.headrevs())
 
     timer(d, setup=s)
     fm.end()
 
 
 @command(
     b'perftags',
     formatteropts
     + [(b'', b'clear-revlogs', False, b'refresh changelog and manifest'),],
 )
 def perftags(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     repocleartagscache = repocleartagscachefunc(repo)
     clearrevlogs = opts[b'clear_revlogs']
 
     def s():
         if clearrevlogs:
             clearchangelog(repo)
             clearfilecache(repo.unfiltered(), 'manifest')
         repocleartagscache()
 
     def t():
         return len(repo.tags())
 
     timer(t, setup=s)
     fm.end()
 
 
 @command(b'perfancestors', formatteropts)
 def perfancestors(ui, repo, **opts):
     opts = _byteskwargs(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(b'perfancestorset', formatteropts)
 def perfancestorset(ui, repo, revset, **opts):
     opts = _byteskwargs(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(b'perfdiscovery', formatteropts, b'PATH')
 def perfdiscovery(ui, repo, path, **opts):
     """benchmark discovery between local repo and the peer at given path
     """
     repos = [repo, None]
     timer, fm = gettimer(ui, opts)
     path = ui.expandpath(path)
 
     def s():
         repos[1] = hg.peer(ui, opts, path)
 
     def d():
         setdiscovery.findcommonheads(ui, *repos)
 
     timer(d, setup=s)
     fm.end()
 
 
 @command(
     b'perfbookmarks',
     formatteropts
     + [(b'', b'clear-revlogs', False, b'refresh changelog and manifest'),],
 )
 def perfbookmarks(ui, repo, **opts):
     """benchmark parsing bookmarks from disk to memory"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
 
     clearrevlogs = opts[b'clear_revlogs']
 
     def s():
         if clearrevlogs:
             clearchangelog(repo)
         clearfilecache(repo, b'_bookmarks')
 
     def d():
         repo._bookmarks
 
     timer(d, setup=s)
     fm.end()
 
 
 @command(b'perfbundleread', formatteropts, b'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,
     )
 
     opts = _byteskwargs(opts)
 
     def makebench(fn):
         def run():
             with open(bundlepath, b'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 fn(bundle)
 
         return run
 
     def makereadnbytes(size):
         def run():
             with open(bundlepath, b'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 while bundle.read(size):
                     pass
 
         return run
 
     def makestdioread(size):
         def run():
             with open(bundlepath, b'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, b'rb') as fh:
                 bundle = exchange.readbundle(ui, fh, bundlepath)
                 for part in bundle.iterparts():
                     while part.read(size):
                         pass
 
         return run
 
     benches = [
         (makestdioread(8192), b'read(8k)'),
         (makestdioread(16384), b'read(16k)'),
         (makestdioread(32768), b'read(32k)'),
         (makestdioread(131072), b'read(128k)'),
     ]
 
     with open(bundlepath, b'rb') as fh:
         bundle = exchange.readbundle(ui, fh, bundlepath)
 
         if isinstance(bundle, changegroup.cg1unpacker):
             benches.extend(
                 [
                     (makebench(deltaiter), b'cg1 deltaiter()'),
                     (makebench(iterchunks), b'cg1 getchunks()'),
                     (makereadnbytes(8192), b'cg1 read(8k)'),
                     (makereadnbytes(16384), b'cg1 read(16k)'),
                     (makereadnbytes(32768), b'cg1 read(32k)'),
                     (makereadnbytes(131072), b'cg1 read(128k)'),
                 ]
             )
         elif isinstance(bundle, bundle2.unbundle20):
             benches.extend(
                 [
                     (makebench(forwardchunks), b'bundle2 forwardchunks()'),
                     (makebench(iterparts), b'bundle2 iterparts()'),
                     (
                         makebench(iterpartsseekable),
                         b'bundle2 iterparts() seekable',
                     ),
                     (makebench(seek), b'bundle2 part seek()'),
                     (makepartreadnbytes(8192), b'bundle2 part read(8k)'),
                     (makepartreadnbytes(16384), b'bundle2 part read(16k)'),
                     (makepartreadnbytes(32768), b'bundle2 part read(32k)'),
                     (makepartreadnbytes(131072), b'bundle2 part read(128k)'),
                 ]
             )
         elif isinstance(bundle, streamclone.streamcloneapplier):
             raise error.Abort(b'stream clone bundles not supported')
         else:
             raise error.Abort(b'unhandled bundle type: %s' % type(bundle))
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 
 @command(
     b'perfchangegroupchangelog',
     formatteropts
     + [
         (b'', b'cgversion', b'02', b'changegroup version'),
         (b'r', b'rev', b'', b'revisions to add to changegroup'),
     ],
 )
 def perfchangegroupchangelog(ui, repo, cgversion=b'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.
     """
     opts = _byteskwargs(opts)
     cl = repo.changelog
     nodes = [cl.lookup(r) for r in repo.revs(rev or b'all()')]
     bundler = changegroup.getbundler(cgversion, 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({(b'progress', b'disable'): True}):
         timer(d)
 
     fm.end()
 
 
 @command(b'perfdirs', formatteropts)
 def perfdirs(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     b'a' in dirstate
 
     def d():
         dirstate.hasdir(b'a')
         del dirstate._map._dirs
 
     timer(d)
     fm.end()
 
 
 @command(b'perfdirstate', formatteropts)
 def perfdirstate(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     b"a" in repo.dirstate
 
     def d():
         repo.dirstate.invalidate()
         b"a" in repo.dirstate
 
     timer(d)
     fm.end()
 
 
 @command(b'perfdirstatedirs', formatteropts)
 def perfdirstatedirs(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     b"a" in repo.dirstate
 
     def d():
         repo.dirstate.hasdir(b"a")
         del repo.dirstate._map._dirs
 
     timer(d)
     fm.end()
 
 
 @command(b'perfdirstatefoldmap', formatteropts)
 def perfdirstatefoldmap(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     b'a' in dirstate
 
     def d():
         dirstate._map.filefoldmap.get(b'a')
         del dirstate._map.filefoldmap
 
     timer(d)
     fm.end()
 
 
 @command(b'perfdirfoldmap', formatteropts)
 def perfdirfoldmap(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     b'a' in dirstate
 
     def d():
         dirstate._map.dirfoldmap.get(b'a')
         del dirstate._map.dirfoldmap
         del dirstate._map._dirs
 
     timer(d)
     fm.end()
 
 
 @command(b'perfdirstatewrite', formatteropts)
 def perfdirstatewrite(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     ds = repo.dirstate
     b"a" in ds
 
     def d():
         ds._dirty = True
         ds.write(repo.currenttransaction())
 
     timer(d)
     fm.end()
 
 
 def _getmergerevs(repo, opts):
     """parse command argument to return rev involved in merge
 
     input: options dictionnary with `rev`, `from` and `bse`
     output: (localctx, otherctx, basectx)
     """
     if opts[b'from']:
         fromrev = scmutil.revsingle(repo, opts[b'from'])
         wctx = repo[fromrev]
     else:
         wctx = repo[None]
         # we don't want working dir files to be stat'd in the benchmark, so
         # prime that cache
         wctx.dirty()
     rctx = scmutil.revsingle(repo, opts[b'rev'], opts[b'rev'])
     if opts[b'base']:
         fromrev = scmutil.revsingle(repo, opts[b'base'])
         ancestor = repo[fromrev]
     else:
         ancestor = wctx.ancestor(rctx)
     return (wctx, rctx, ancestor)
 
 
 @command(
     b'perfmergecalculate',
     [
         (b'r', b'rev', b'.', b'rev to merge against'),
         (b'', b'from', b'', b'rev to merge from'),
         (b'', b'base', b'', b'the revision to use as base'),
     ]
     + formatteropts,
 )
 def perfmergecalculate(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
 
     wctx, rctx, ancestor = _getmergerevs(repo, opts)
 
     def d():
         # acceptremote is True because we don't want prompts in the middle of
         # our benchmark
         merge.calculateupdates(
             repo,
             wctx,
             rctx,
             [ancestor],
             branchmerge=False,
             force=False,
             acceptremote=True,
             followcopies=True,
         )
 
     timer(d)
     fm.end()
 
 
 @command(
     b'perfmergecopies',
     [
         (b'r', b'rev', b'.', b'rev to merge against'),
         (b'', b'from', b'', b'rev to merge from'),
         (b'', b'base', b'', b'the revision to use as base'),
     ]
     + formatteropts,
 )
 def perfmergecopies(ui, repo, **opts):
     """measure runtime of `copies.mergecopies`"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     wctx, rctx, ancestor = _getmergerevs(repo, opts)
 
     def d():
         # acceptremote is True because we don't want prompts in the middle of
         # our benchmark
         copies.mergecopies(repo, wctx, rctx, ancestor)
 
     timer(d)
     fm.end()
 
 
 @command(b'perfpathcopies', [], b"REV REV")
 def perfpathcopies(ui, repo, rev1, rev2, **opts):
     """benchmark the copy tracing logic"""
     opts = _byteskwargs(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(
     b'perfphases',
     [(b'', b'full', False, b'include file reading time too'),],
     b"",
 )
 def perfphases(ui, repo, **opts):
     """benchmark phasesets computation"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     _phases = repo._phasecache
     full = opts.get(b'full')
 
     def d():
         phases = _phases
         if full:
             clearfilecache(repo, b'_phasecache')
             phases = repo._phasecache
         phases.invalidate()
         phases.loadphaserevs(repo)
 
     timer(d)
     fm.end()
 
 
 @command(b'perfphasesremote', [], b"[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,
     )
 
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
 
     path = ui.paths.getpath(dest, default=(b'default-push', b'default'))
     if not path:
         raise error.Abort(
             b'default repository not configured!',
             hint=b"see 'hg help config.paths'",
         )
     dest = path.pushloc or path.loc
-    ui.status(b'analysing phase of %s\n' % util.hidepassword(dest))
+    ui.statusnoi18n(b'analysing phase of %s\n' % util.hidepassword(dest))
     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(
             b'listkeys', {b'namespace': b'phases'}
         ).result()
     del other
     publishing = remotephases.get(b'publishing', False)
     if publishing:
-        ui.status(b'publishing: yes\n')
+        ui.statusnoi18n(b'publishing: yes\n')
     else:
-        ui.status(b'publishing: no\n')
+        ui.statusnoi18n(b'publishing: no\n')
 
     nodemap = repo.changelog.nodemap
     nonpublishroots = 0
     for nhex, phase in remotephases.iteritems():
         if nhex == b'publishing':  # ignore data related to publish option
             continue
         node = bin(nhex)
         if node in nodemap and int(phase):
             nonpublishroots += 1
-    ui.status(b'number of roots: %d\n' % len(remotephases))
-    ui.status(b'number of known non public roots: %d\n' % nonpublishroots)
+    ui.statusnoi18n(b'number of roots: %d\n' % len(remotephases))
+    ui.statusnoi18n(b'number of known non public roots: %d\n' % nonpublishroots)
 
     def d():
         phases.remotephasessummary(repo, remotesubset, remotephases)
 
     timer(d)
     fm.end()
 
 
 @command(
     b'perfmanifest',
     [
         (b'm', b'manifest-rev', False, b'Look up a manifest node revision'),
         (b'', b'clear-disk', False, b'clear on-disk caches too'),
     ]
     + formatteropts,
     b'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."""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     if not manifest_rev:
         ctx = scmutil.revsingle(repo, rev, rev)
         t = ctx.manifestnode()
     else:
         from mercurial.node import bin
 
         if len(rev) == 40:
             t = bin(rev)
         else:
             try:
                 rev = int(rev)
 
                 if util.safehasattr(repo.manifestlog, b'getstorage'):
                     t = repo.manifestlog.getstorage(b'').node(rev)
                 else:
                     t = repo.manifestlog._revlog.lookup(rev)
             except ValueError:
                 raise error.Abort(
                     b'manifest revision must be integer or full ' b'node'
                 )
 
     def d():
         repo.manifestlog.clearcaches(clear_persisted_data=clear_disk)
         repo.manifestlog[t].read()
 
     timer(d)
     fm.end()
 
 
 @command(b'perfchangeset', formatteropts)
 def perfchangeset(ui, repo, rev, **opts):
     opts = _byteskwargs(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(b'perfignore', formatteropts)
 def perfignore(ui, repo, **opts):
     """benchmark operation related to computing ignore"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
 
     def setupone():
         dirstate.invalidate()
         clearfilecache(dirstate, b'_ignore')
 
     def runone():
         dirstate._ignore
 
     timer(runone, setup=setupone, title=b"load")
     fm.end()
 
 
 @command(
     b'perfindex',
     [
         (b'', b'rev', [], b'revision to be looked up (default tip)'),
         (b'', b'no-lookup', None, b'do not revision lookup post creation'),
     ]
     + formatteropts,
 )
 def perfindex(ui, repo, **opts):
     """benchmark index creation time followed by a lookup
 
     The default is to look `tip` up. Depending on the index implementation,
     the revision looked up can matters. For example, an implementation
     scanning the index will have a faster lookup time for `--rev tip` than for
     `--rev 0`. The number of looked up revisions and their order can also
     matters.
 
     Example of useful set to test:
     * tip
     * 0
     * -10:
     * :10
     * -10: + :10
     * :10: + -10:
     * -10000:
     * -10000: + 0
 
     It is not currently possible to check for lookup of a missing node. For
     deeper lookup benchmarking, checkout the `perfnodemap` command."""
     import mercurial.revlog
 
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     mercurial.revlog._prereadsize = 2 ** 24  # disable lazy parser in old hg
     if opts[b'no_lookup']:
         if opts['rev']:
             raise error.Abort('--no-lookup and --rev are mutually exclusive')
         nodes = []
     elif not opts[b'rev']:
         nodes = [repo[b"tip"].node()]
     else:
         revs = scmutil.revrange(repo, opts[b'rev'])
         cl = repo.changelog
         nodes = [cl.node(r) for r in revs]
 
     unfi = repo.unfiltered()
     # find the filecache func directly
     # This avoid polluting the benchmark with the filecache logic
     makecl = unfi.__class__.changelog.func
 
     def setup():
         # probably not necessary, but for good measure
         clearchangelog(unfi)
 
     def d():
         cl = makecl(unfi)
         for n in nodes:
             cl.rev(n)
 
     timer(d, setup=setup)
     fm.end()
 
 
 @command(
     b'perfnodemap',
     [
         (b'', b'rev', [], b'revision to be looked up (default tip)'),
         (b'', b'clear-caches', True, b'clear revlog cache between calls'),
     ]
     + formatteropts,
 )
 def perfnodemap(ui, repo, **opts):
     """benchmark the time necessary to look up revision from a cold nodemap
 
     Depending on the implementation, the amount and order of revision we look
     up can varies. Example of useful set to test:
     * tip
     * 0
     * -10:
     * :10
     * -10: + :10
     * :10: + -10:
     * -10000:
     * -10000: + 0
 
     The command currently focus on valid binary lookup. Benchmarking for
     hexlookup, prefix lookup and missing lookup would also be valuable.
     """
     import mercurial.revlog
 
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     mercurial.revlog._prereadsize = 2 ** 24  # disable lazy parser in old hg
 
     unfi = repo.unfiltered()
     clearcaches = opts['clear_caches']
     # find the filecache func directly
     # This avoid polluting the benchmark with the filecache logic
     makecl = unfi.__class__.changelog.func
     if not opts[b'rev']:
         raise error.Abort('use --rev to specify revisions to look up')
     revs = scmutil.revrange(repo, opts[b'rev'])
     cl = repo.changelog
     nodes = [cl.node(r) for r in revs]
 
     # use a list to pass reference to a nodemap from one closure to the next
     nodeget = [None]
 
     def setnodeget():
         # probably not necessary, but for good measure
         clearchangelog(unfi)
         nodeget[0] = makecl(unfi).nodemap.get
 
     def d():
         get = nodeget[0]
         for n in nodes:
             get(n)
 
     setup = None
     if clearcaches:
 
         def setup():
             setnodeget()
 
     else:
         setnodeget()
         d()  # prewarm the data structure
     timer(d, setup=setup)
     fm.end()
 
 
 @command(b'perfstartup', formatteropts)
 def perfstartup(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
 
     def d():
         if os.name != r'nt':
             os.system(
                 b"HGRCPATH= %s version -q > /dev/null" % fsencode(sys.argv[0])
             )
         else:
             os.environ[r'HGRCPATH'] = r' '
             os.system(r"%s version -q > NUL" % sys.argv[0])
 
     timer(d)
     fm.end()
 
 
 @command(b'perfparents', formatteropts)
 def perfparents(ui, repo, **opts):
     """benchmark the time necessary to fetch one changeset's parents.
 
     The fetch is done using the `node identifier`, traversing all object layers
     from the repository object. The first N revisions will be used for this
     benchmark. N is controlled by the ``perf.parentscount`` config option
     (default: 1000).
     """
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     # control the number of commits perfparents iterates over
     # experimental config: perf.parentscount
     count = getint(ui, b"perf", b"parentscount", 1000)
     if len(repo.changelog) < count:
         raise error.Abort(b"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(b'perfctxfiles', formatteropts)
 def perfctxfiles(ui, repo, x, **opts):
     opts = _byteskwargs(opts)
     x = int(x)
     timer, fm = gettimer(ui, opts)
 
     def d():
         len(repo[x].files())
 
     timer(d)
     fm.end()
 
 
 @command(b'perfrawfiles', formatteropts)
 def perfrawfiles(ui, repo, x, **opts):
     opts = _byteskwargs(opts)
     x = int(x)
     timer, fm = gettimer(ui, opts)
     cl = repo.changelog
 
     def d():
         len(cl.read(x)[3])
 
     timer(d)
     fm.end()
 
 
 @command(b'perflookup', formatteropts)
 def perflookup(ui, repo, rev, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     timer(lambda: len(repo.lookup(rev)))
     fm.end()
 
 
 @command(
     b'perflinelogedits',
     [
         (b'n', b'edits', 10000, b'number of edits'),
         (b'', b'max-hunk-lines', 10, b'max lines in a hunk'),
     ],
     norepo=True,
 )
 def perflinelogedits(ui, **opts):
     from mercurial import linelog
 
     opts = _byteskwargs(opts)
 
     edits = opts[b'edits']
     maxhunklines = opts[b'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(b'perfrevrange', formatteropts)
 def perfrevrange(ui, repo, *specs, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     revrange = scmutil.revrange
     timer(lambda: len(revrange(repo, specs)))
     fm.end()
 
 
 @command(b'perfnodelookup', formatteropts)
 def perfnodelookup(ui, repo, rev, **opts):
     opts = _byteskwargs(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), b"00changelog.i")
 
     def d():
         cl.rev(n)
         clearcaches(cl)
 
     timer(d)
     fm.end()
 
 
 @command(
     b'perflog',
     [(b'', b'rename', False, b'ask log to follow renames')] + formatteropts,
 )
 def perflog(ui, repo, rev=None, **opts):
     opts = _byteskwargs(opts)
     if rev is None:
         rev = []
     timer, fm = gettimer(ui, opts)
     ui.pushbuffer()
     timer(
         lambda: commands.log(
             ui, repo, rev=rev, date=b'', user=b'', copies=opts.get(b'rename')
         )
     )
     ui.popbuffer()
     fm.end()
 
 
 @command(b'perfmoonwalk', formatteropts)
 def perfmoonwalk(ui, repo, **opts):
     """benchmark walking the changelog backwards
 
     This also loads the changelog data for each revision in the changelog.
     """
     opts = _byteskwargs(opts)
     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(
     b'perftemplating',
     [(b'r', b'rev', [], b'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(
             b"perftemplating not available with this Mercurial",
             hint=b"use 4.3 or later",
         )
 
     opts = _byteskwargs(opts)
 
     nullui = ui.copy()
     nullui.fout = open(os.devnull, r'wb')
     nullui.disablepager()
     revs = opts.get(b'rev')
     if not revs:
         revs = [b'all()']
     revs = list(scmutil.revrange(repo, revs))
 
     defaulttemplate = (
         b'{date|shortdate} [{rev}:{node|short}]'
         b' {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()
 
 
 def _displaystats(ui, opts, entries, data):
     pass
     # use a second formatter because the data are quite different, not sure
     # how it flies with the templater.
     fm = ui.formatter(b'perf-stats', opts)
     for key, title in entries:
         values = data[key]
         nbvalues = len(data)
         values.sort()
         stats = {
             'key': key,
             'title': title,
             'nbitems': len(values),
             'min': values[0][0],
             '10%': values[(nbvalues * 10) // 100][0],
             '25%': values[(nbvalues * 25) // 100][0],
             '50%': values[(nbvalues * 50) // 100][0],
             '75%': values[(nbvalues * 75) // 100][0],
             '80%': values[(nbvalues * 80) // 100][0],
             '85%': values[(nbvalues * 85) // 100][0],
             '90%': values[(nbvalues * 90) // 100][0],
             '95%': values[(nbvalues * 95) // 100][0],
             '99%': values[(nbvalues * 99) // 100][0],
             'max': values[-1][0],
         }
         fm.startitem()
         fm.data(**stats)
         # make node pretty for the human output
         fm.plain('### %s (%d items)\n' % (title, len(values)))
         lines = [
             'min',
             '10%',
             '25%',
             '50%',
             '75%',
             '80%',
             '85%',
             '90%',
             '95%',
             '99%',
             'max',
         ]
         for l in lines:
             fm.plain('%s: %s\n' % (l, stats[l]))
     fm.end()
 
 
 @command(
     b'perfhelper-mergecopies',
     formatteropts
     + [
         (b'r', b'revs', [], b'restrict search to these revisions'),
         (b'', b'timing', False, b'provides extra data (costly)'),
         (b'', b'stats', False, b'provides statistic about the measured data'),
     ],
 )
 def perfhelpermergecopies(ui, repo, revs=[], **opts):
     """find statistics about potential parameters for `perfmergecopies`
 
     This command find (base, p1, p2) triplet relevant for copytracing
     benchmarking in the context of a merge.  It reports values for some of the
     parameters that impact merge copy tracing time during merge.
 
     If `--timing` is set, rename detection is run and the associated timing
     will be reported. The extra details come at the cost of slower command
     execution.
 
     Since rename detection is only run once, other factors might easily
     affect the precision of the timing. However it should give a good
     approximation of which revision triplets are very costly.
     """
     opts = _byteskwargs(opts)
     fm = ui.formatter(b'perf', opts)
     dotiming = opts[b'timing']
     dostats = opts[b'stats']
 
     output_template = [
         ("base", "%(base)12s"),
         ("p1", "%(p1.node)12s"),
         ("p2", "%(p2.node)12s"),
         ("p1.nb-revs", "%(p1.nbrevs)12d"),
         ("p1.nb-files", "%(p1.nbmissingfiles)12d"),
         ("p1.renames", "%(p1.renamedfiles)12d"),
         ("p1.time", "%(p1.time)12.3f"),
         ("p2.nb-revs", "%(p2.nbrevs)12d"),
         ("p2.nb-files", "%(p2.nbmissingfiles)12d"),
         ("p2.renames", "%(p2.renamedfiles)12d"),
         ("p2.time", "%(p2.time)12.3f"),
         ("renames", "%(nbrenamedfiles)12d"),
         ("total.time", "%(time)12.3f"),
     ]
     if not dotiming:
         output_template = [
             i
             for i in output_template
             if not ('time' in i[0] or 'renames' in i[0])
         ]
     header_names = [h for (h, v) in output_template]
     output = ' '.join([v for (h, v) in output_template]) + '\n'
     header = ' '.join(['%12s'] * len(header_names)) + '\n'
     fm.plain(header % tuple(header_names))
 
     if not revs:
         revs = ['all()']
     revs = scmutil.revrange(repo, revs)
 
     if dostats:
         alldata = {
             'nbrevs': [],
             'nbmissingfiles': [],
         }
         if dotiming:
             alldata['parentnbrenames'] = []
             alldata['totalnbrenames'] = []
             alldata['parenttime'] = []
             alldata['totaltime'] = []
 
     roi = repo.revs('merge() and %ld', revs)
     for r in roi:
         ctx = repo[r]
         p1 = ctx.p1()
         p2 = ctx.p2()
         bases = repo.changelog._commonancestorsheads(p1.rev(), p2.rev())
         for b in bases:
             b = repo[b]
             p1missing = copies._computeforwardmissing(b, p1)
             p2missing = copies._computeforwardmissing(b, p2)
             data = {
                 b'base': b.hex(),
                 b'p1.node': p1.hex(),
                 b'p1.nbrevs': len(repo.revs('%d::%d', b.rev(), p1.rev())),
                 b'p1.nbmissingfiles': len(p1missing),
                 b'p2.node': p2.hex(),
                 b'p2.nbrevs': len(repo.revs('%d::%d', b.rev(), p2.rev())),
                 b'p2.nbmissingfiles': len(p2missing),
             }
             if dostats:
                 if p1missing:
                     alldata['nbrevs'].append(
                         (data['p1.nbrevs'], b.hex(), p1.hex())
                     )
                     alldata['nbmissingfiles'].append(
                         (data['p1.nbmissingfiles'], b.hex(), p1.hex())
                     )
                 if p2missing:
                     alldata['nbrevs'].append(
                         (data['p2.nbrevs'], b.hex(), p2.hex())
                     )
                     alldata['nbmissingfiles'].append(
                         (data['p2.nbmissingfiles'], b.hex(), p2.hex())
                     )
             if dotiming:
                 begin = util.timer()
                 mergedata = copies.mergecopies(repo, p1, p2, b)
                 end = util.timer()
                 # not very stable timing since we did only one run
                 data['time'] = end - begin
                 # mergedata contains five dicts: "copy", "movewithdir",
                 # "diverge", "renamedelete" and "dirmove".
                 # The first 4 are about renamed file so lets count that.
                 renames = len(mergedata[0])
                 renames += len(mergedata[1])
                 renames += len(mergedata[2])
                 renames += len(mergedata[3])
                 data['nbrenamedfiles'] = renames
                 begin = util.timer()
                 p1renames = copies.pathcopies(b, p1)
                 end = util.timer()
                 data['p1.time'] = end - begin
                 begin = util.timer()
                 p2renames = copies.pathcopies(b, p2)
                 data['p2.time'] = end - begin
                 end = util.timer()
                 data['p1.renamedfiles'] = len(p1renames)
                 data['p2.renamedfiles'] = len(p2renames)
 
                 if dostats:
                     if p1missing:
                         alldata['parentnbrenames'].append(
                             (data['p1.renamedfiles'], b.hex(), p1.hex())
                         )
                         alldata['parenttime'].append(
                             (data['p1.time'], b.hex(), p1.hex())
                         )
                     if p2missing:
                         alldata['parentnbrenames'].append(
                             (data['p2.renamedfiles'], b.hex(), p2.hex())
                         )
                         alldata['parenttime'].append(
                             (data['p2.time'], b.hex(), p2.hex())
                         )
                     if p1missing or p2missing:
                         alldata['totalnbrenames'].append(
                             (
                                 data['nbrenamedfiles'],
                                 b.hex(),
                                 p1.hex(),
                                 p2.hex(),
                             )
                         )
                         alldata['totaltime'].append(
                             (data['time'], b.hex(), p1.hex(), p2.hex())
                         )
             fm.startitem()
             fm.data(**data)
             # make node pretty for the human output
             out = data.copy()
             out['base'] = fm.hexfunc(b.node())
             out['p1.node'] = fm.hexfunc(p1.node())
             out['p2.node'] = fm.hexfunc(p2.node())
             fm.plain(output % out)
 
     fm.end()
     if dostats:
         # use a second formatter because the data are quite different, not sure
         # how it flies with the templater.
         entries = [
             ('nbrevs', 'number of revision covered'),
             ('nbmissingfiles', 'number of missing files at head'),
         ]
         if dotiming:
             entries.append(
                 ('parentnbrenames', 'rename from one parent to base')
             )
             entries.append(('totalnbrenames', 'total number of renames'))
             entries.append(('parenttime', 'time for one parent'))
             entries.append(('totaltime', 'time for both parents'))
         _displaystats(ui, opts, entries, alldata)
 
 
 @command(
     b'perfhelper-pathcopies',
     formatteropts
     + [
         (b'r', b'revs', [], b'restrict search to these revisions'),
         (b'', b'timing', False, b'provides extra data (costly)'),
         (b'', b'stats', False, b'provides statistic about the measured data'),
     ],
 )
 def perfhelperpathcopies(ui, repo, revs=[], **opts):
     """find statistic about potential parameters for the `perftracecopies`
 
     This command find source-destination pair relevant for copytracing testing.
     It report value for some of the parameters that impact copy tracing time.
 
     If `--timing` is set, rename detection is run and the associated timing
     will be reported. The extra details comes at the cost of a slower command
     execution.
 
     Since the rename detection is only run once, other factors might easily
     affect the precision of the timing. However it should give a good
     approximation of which revision pairs are very costly.
     """
     opts = _byteskwargs(opts)
     fm = ui.formatter(b'perf', opts)
     dotiming = opts[b'timing']
     dostats = opts[b'stats']
 
     if dotiming:
         header = '%12s %12s %12s %12s %12s %12s\n'
         output = (
             "%(source)12s %(destination)12s "
             "%(nbrevs)12d %(nbmissingfiles)12d "
             "%(nbrenamedfiles)12d %(time)18.5f\n"
         )
         header_names = (
             "source",
             "destination",
             "nb-revs",
             "nb-files",
             "nb-renames",
             "time",
         )
         fm.plain(header % header_names)
     else:
         header = '%12s %12s %12s %12s\n'
         output = (
             "%(source)12s %(destination)12s "
             "%(nbrevs)12d %(nbmissingfiles)12d\n"
         )
         fm.plain(header % ("source", "destination", "nb-revs", "nb-files"))
 
     if not revs:
         revs = ['all()']
     revs = scmutil.revrange(repo, revs)
 
     if dostats:
         alldata = {
             'nbrevs': [],
             'nbmissingfiles': [],
         }
         if dotiming:
             alldata['nbrenames'] = []
             alldata['time'] = []
 
     roi = repo.revs('merge() and %ld', revs)
     for r in roi:
         ctx = repo[r]
         p1 = ctx.p1().rev()
         p2 = ctx.p2().rev()
         bases = repo.changelog._commonancestorsheads(p1, p2)
         for p in (p1, p2):
             for b in bases:
                 base = repo[b]
                 parent = repo[p]
                 missing = copies._computeforwardmissing(base, parent)
                 if not missing:
                     continue
                 data = {
                     b'source': base.hex(),
                     b'destination': parent.hex(),
                     b'nbrevs': len(repo.revs('%d::%d', b, p)),
                     b'nbmissingfiles': len(missing),
                 }
                 if dostats:
                     alldata['nbrevs'].append(
                         (data['nbrevs'], base.hex(), parent.hex(),)
                     )
                     alldata['nbmissingfiles'].append(
                         (data['nbmissingfiles'], base.hex(), parent.hex(),)
                     )
                 if dotiming:
                     begin = util.timer()
                     renames = copies.pathcopies(base, parent)
                     end = util.timer()
                     # not very stable timing since we did only one run
                     data['time'] = end - begin
                     data['nbrenamedfiles'] = len(renames)
                     if dostats:
                         alldata['time'].append(
                             (data['time'], base.hex(), parent.hex(),)
                         )
                         alldata['nbrenames'].append(
                             (data['nbrenamedfiles'], base.hex(), parent.hex(),)
                         )
                 fm.startitem()
                 fm.data(**data)
                 out = data.copy()
                 out['source'] = fm.hexfunc(base.node())
                 out['destination'] = fm.hexfunc(parent.node())
                 fm.plain(output % out)
 
     fm.end()
     if dostats:
         # use a second formatter because the data are quite different, not sure
         # how it flies with the templater.
         fm = ui.formatter(b'perf', opts)
         entries = [
             ('nbrevs', 'number of revision covered'),
             ('nbmissingfiles', 'number of missing files at head'),
         ]
         if dotiming:
             entries.append(('nbrenames', 'renamed files'))
             entries.append(('time', 'time'))
         _displaystats(ui, opts, entries, alldata)
 
 
 @command(b'perfcca', formatteropts)
 def perfcca(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     timer(lambda: scmutil.casecollisionauditor(ui, False, repo.dirstate))
     fm.end()
 
 
 @command(b'perffncacheload', formatteropts)
 def perffncacheload(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     s = repo.store
 
     def d():
         s.fncache._load()
 
     timer(d)
     fm.end()
 
 
 @command(b'perffncachewrite', formatteropts)
 def perffncachewrite(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     s = repo.store
     lock = repo.lock()
     s.fncache._load()
     tr = repo.transaction(b'perffncachewrite')
     tr.addbackup(b'fncache')
 
     def d():
         s.fncache._dirty = True
         s.fncache.write(tr)
 
     timer(d)
     tr.close()
     lock.release()
     fm.end()
 
 
 @command(b'perffncacheencode', formatteropts)
 def perffncacheencode(ui, repo, **opts):
     opts = _byteskwargs(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()
 
 
 def _manifestrevision(repo, mnode):
     ml = repo.manifestlog
 
     if util.safehasattr(ml, b'getstorage'):
         store = ml.getstorage(b'')
     else:
         store = ml._revlog
 
     return store.revision(mnode)
 
 
 @command(
     b'perfbdiff',
     revlogopts
     + formatteropts
     + [
         (
             b'',
             b'count',
             1,
             b'number of revisions to test (when using --startrev)',
         ),
         (b'', b'alldata', False, b'test bdiffs for all associated revisions'),
         (b'', b'threads', 0, b'number of thread to use (disable with 0)'),
         (b'', b'blocks', False, b'test computing diffs into blocks'),
         (b'', b'xdiff', False, b'use xdiff algorithm'),
     ],
     b'-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 = _byteskwargs(opts)
 
     if opts[b'xdiff'] and not opts[b'blocks']:
         raise error.CommandError(b'perfbdiff', b'--xdiff requires --blocks')
 
     if opts[b'alldata']:
         opts[b'changelog'] = True
 
     if opts.get(b'changelog') or opts.get(b'manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError(b'perfbdiff', b'invalid arguments')
 
     blocks = opts[b'blocks']
     xdiff = opts[b'xdiff']
     textpairs = []
 
     r = cmdutil.openrevlog(repo, b'perfbdiff', file_, opts)
 
     startrev = r.rev(r.lookup(rev))
     for rev in range(startrev, min(startrev + count, len(r) - 1)):
         if opts[b'alldata']:
             # Load revisions associated with changeset.
             ctx = repo[rev]
             mtext = _manifestrevision(repo, ctx.manifestnode())
             for pctx in ctx.parents():
                 pman = _manifestrevision(repo, 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(
     b'perfunidiff',
     revlogopts
     + formatteropts
     + [
         (
             b'',
             b'count',
             1,
             b'number of revisions to test (when using --startrev)',
         ),
         (b'', b'alldata', False, b'test unidiffs for all associated revisions'),
     ],
     b'-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).
     """
     opts = _byteskwargs(opts)
     if opts[b'alldata']:
         opts[b'changelog'] = True
 
     if opts.get(b'changelog') or opts.get(b'manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError(b'perfunidiff', b'invalid arguments')
 
     textpairs = []
 
     r = cmdutil.openrevlog(repo, b'perfunidiff', file_, opts)
 
     startrev = r.rev(r.lookup(rev))
     for rev in range(startrev, min(startrev + count, len(r) - 1)):
         if opts[b'alldata']:
             # Load revisions associated with changeset.
             ctx = repo[rev]
             mtext = _manifestrevision(repo, ctx.manifestnode())
             for pctx in ctx.parents():
                 pman = _manifestrevision(repo, 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, b'', right, b'', b'left', b'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(b'perfdiffwd', formatteropts)
 def perfdiffwd(ui, repo, **opts):
     """Profile diff of working directory changes"""
     opts = _byteskwargs(opts)
     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], b'1') for c in diffopt)
 
         def d():
             ui.pushbuffer()
             commands.diff(ui, repo, **opts)
             ui.popbuffer()
 
         diffopt = diffopt.encode('ascii')
         title = b'diffopts: %s' % (diffopt and (b'-' + diffopt) or b'none')
         timer(d, title=title)
     fm.end()
 
 
 @command(b'perfrevlogindex', revlogopts + formatteropts, b'-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.
     """
 
     opts = _byteskwargs(opts)
 
     rl = cmdutil.openrevlog(repo, b'perfrevlogindex', file_, opts)
 
     opener = getattr(rl, 'opener')  # trick linter
     indexfile = rl.indexfile
     data = opener.read(indexfile)
 
     header = struct.unpack(b'>I', data[0:4])[0]
     version = header & 0xFFFF
     if version == 1:
         revlogio = revlog.revlogio()
         inline = header & (1 << 16)
     else:
         raise error.Abort(b'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, b'revlog constructor'),
         (read, b'read'),
         (parseindex, b'create index object'),
         (lambda: getentry(0), b'retrieve index entry for rev 0'),
         (lambda: resolvenode(b'a' * 20), b'look up missing node'),
         (lambda: resolvenode(node0), b'look up node at rev 0'),
         (lambda: resolvenode(node25), b'look up node at 1/4 len'),
         (lambda: resolvenode(node50), b'look up node at 1/2 len'),
         (lambda: resolvenode(node75), b'look up node at 3/4 len'),
         (lambda: resolvenode(node100), b'look up node at tip'),
         # 2x variation is to measure caching impact.
         (lambda: resolvenodes(allnodes), b'look up all nodes (forward)'),
         (lambda: resolvenodes(allnodes, 2), b'look up all nodes 2x (forward)'),
         (lambda: resolvenodes(allnodesrev), b'look up all nodes (reverse)'),
         (
             lambda: resolvenodes(allnodesrev, 2),
             b'look up all nodes 2x (reverse)',
         ),
         (lambda: getentries(allrevs), b'retrieve all index entries (forward)'),
         (
             lambda: getentries(allrevs, 2),
             b'retrieve all index entries 2x (forward)',
         ),
         (
             lambda: getentries(allrevsrev),
             b'retrieve all index entries (reverse)',
         ),
         (
             lambda: getentries(allrevsrev, 2),
             b'retrieve all index entries 2x (reverse)',
         ),
     ]
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 
 @command(
     b'perfrevlogrevisions',
     revlogopts
     + formatteropts
     + [
         (b'd', b'dist', 100, b'distance between the revisions'),
         (b's', b'startrev', 0, b'revision to start reading at'),
         (b'', b'reverse', False, b'read in reverse'),
     ],
     b'-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``.
     """
     opts = _byteskwargs(opts)
 
     rl = cmdutil.openrevlog(repo, b'perfrevlogrevisions', file_, opts)
     rllen = getlen(ui)(rl)
 
     if startrev < 0:
         startrev = rllen + startrev
 
     def d():
         rl.clearcaches()
 
         beginrev = startrev
         endrev = rllen
         dist = opts[b'dist']
 
         if reverse:
             beginrev, endrev = endrev - 1, beginrev - 1
             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(
     b'perfrevlogwrite',
     revlogopts
     + formatteropts
     + [
         (b's', b'startrev', 1000, b'revision to start writing at'),
         (b'', b'stoprev', -1, b'last revision to write'),
         (b'', b'count', 3, b'number of passes to perform'),
         (b'', b'details', False, b'print timing for every revisions tested'),
         (b'', b'source', b'full', b'the kind of data feed in the revlog'),
         (b'', b'lazydeltabase', True, b'try the provided delta first'),
         (b'', b'clear-caches', True, b'clear revlog cache between calls'),
     ],
     b'-c|-m|FILE',
 )
 def perfrevlogwrite(ui, repo, file_=None, startrev=1000, stoprev=-1, **opts):
     """Benchmark writing a series of revisions to a revlog.
 
     Possible source values are:
     * `full`: add from a full text (default).
     * `parent-1`: add from a delta to the first parent
     * `parent-2`: add from a delta to the second parent if it exists
                   (use a delta from the first parent otherwise)
     * `parent-smallest`: add from the smallest delta (either p1 or p2)
     * `storage`: add from the existing precomputed deltas
 
     Note: This performance command measures performance in a custom way. As a
     result some of the global configuration of the 'perf' command does not
     apply to it:
 
     * ``pre-run``: disabled
 
     * ``profile-benchmark``: disabled
 
     * ``run-limits``: disabled use --count instead
     """
     opts = _byteskwargs(opts)
 
     rl = cmdutil.openrevlog(repo, b'perfrevlogwrite', file_, opts)
     rllen = getlen(ui)(rl)
     if startrev < 0:
         startrev = rllen + startrev
     if stoprev < 0:
         stoprev = rllen + stoprev
 
     lazydeltabase = opts['lazydeltabase']
     source = opts['source']
     clearcaches = opts['clear_caches']
     validsource = (
         b'full',
         b'parent-1',
         b'parent-2',
         b'parent-smallest',
         b'storage',
     )
     if source not in validsource:
         raise error.Abort('invalid source type: %s' % source)
 
     ### actually gather results
     count = opts['count']
     if count <= 0:
         raise error.Abort('invalide run count: %d' % count)
     allresults = []
     for c in range(count):
         timing = _timeonewrite(
             ui,
             rl,
             source,
             startrev,
             stoprev,
             c + 1,
             lazydeltabase=lazydeltabase,
             clearcaches=clearcaches,
         )
         allresults.append(timing)
 
     ### consolidate the results in a single list
     results = []
     for idx, (rev, t) in enumerate(allresults[0]):
         ts = [t]
         for other in allresults[1:]:
             orev, ot = other[idx]
             assert orev == rev
             ts.append(ot)
         results.append((rev, ts))
     resultcount = len(results)
 
     ### Compute and display relevant statistics
 
     # get a formatter
     fm = ui.formatter(b'perf', opts)
     displayall = ui.configbool(b"perf", b"all-timing", False)
 
     # print individual details if requested
     if opts['details']:
         for idx, item in enumerate(results, 1):
             rev, data = item
             title = 'revisions #%d of %d, rev %d' % (idx, resultcount, rev)
             formatone(fm, data, title=title, displayall=displayall)
 
     # sorts results by median time
     results.sort(key=lambda x: sorted(x[1])[len(x[1]) // 2])
     # list of (name, index) to display)
     relevants = [
         ("min", 0),
         ("10%", resultcount * 10 // 100),
         ("25%", resultcount * 25 // 100),
         ("50%", resultcount * 70 // 100),
         ("75%", resultcount * 75 // 100),
         ("90%", resultcount * 90 // 100),
         ("95%", resultcount * 95 // 100),
         ("99%", resultcount * 99 // 100),
         ("99.9%", resultcount * 999 // 1000),
         ("99.99%", resultcount * 9999 // 10000),
         ("99.999%", resultcount * 99999 // 100000),
         ("max", -1),
     ]
     if not ui.quiet:
         for name, idx in relevants:
             data = results[idx]
             title = '%s of %d, rev %d' % (name, resultcount, data[0])
             formatone(fm, data[1], title=title, displayall=displayall)
 
     # XXX summing that many float will not be very precise, we ignore this fact
     # for now
     totaltime = []
     for item in allresults:
         totaltime.append(
             (
                 sum(x[1][0] for x in item),
                 sum(x[1][1] for x in item),
                 sum(x[1][2] for x in item),
             )
         )
     formatone(
         fm,
         totaltime,
         title="total time (%d revs)" % resultcount,
         displayall=displayall,
     )
     fm.end()
 
 
 class _faketr(object):
     def add(s, x, y, z=None):
         return None
 
 
 def _timeonewrite(
     ui,
     orig,
     source,
     startrev,
     stoprev,
     runidx=None,
     lazydeltabase=True,
     clearcaches=True,
 ):
     timings = []
     tr = _faketr()
     with _temprevlog(ui, orig, startrev) as dest:
         dest._lazydeltabase = lazydeltabase
         revs = list(orig.revs(startrev, stoprev))
         total = len(revs)
         topic = 'adding'
         if runidx is not None:
             topic += ' (run #%d)' % runidx
         # Support both old and new progress API
         if util.safehasattr(ui, 'makeprogress'):
             progress = ui.makeprogress(topic, unit='revs', total=total)
 
             def updateprogress(pos):
                 progress.update(pos)
 
             def completeprogress():
                 progress.complete()
 
         else:
 
             def updateprogress(pos):
                 ui.progress(topic, pos, unit='revs', total=total)
 
             def completeprogress():
                 ui.progress(topic, None, unit='revs', total=total)
 
         for idx, rev in enumerate(revs):
             updateprogress(idx)
             addargs, addkwargs = _getrevisionseed(orig, rev, tr, source)
             if clearcaches:
                 dest.index.clearcaches()
                 dest.clearcaches()
             with timeone() as r:
                 dest.addrawrevision(*addargs, **addkwargs)
             timings.append((rev, r[0]))
         updateprogress(total)
         completeprogress()
     return timings
 
 
 def _getrevisionseed(orig, rev, tr, source):
     from mercurial.node import nullid
 
     linkrev = orig.linkrev(rev)
     node = orig.node(rev)
     p1, p2 = orig.parents(node)
     flags = orig.flags(rev)
     cachedelta = None
     text = None
 
     if source == b'full':
         text = orig.revision(rev)
     elif source == b'parent-1':
         baserev = orig.rev(p1)
         cachedelta = (baserev, orig.revdiff(p1, rev))
     elif source == b'parent-2':
         parent = p2
         if p2 == nullid:
             parent = p1
         baserev = orig.rev(parent)
         cachedelta = (baserev, orig.revdiff(parent, rev))
     elif source == b'parent-smallest':
         p1diff = orig.revdiff(p1, rev)
         parent = p1
         diff = p1diff
         if p2 != nullid:
             p2diff = orig.revdiff(p2, rev)
             if len(p1diff) > len(p2diff):
                 parent = p2
                 diff = p2diff
         baserev = orig.rev(parent)
         cachedelta = (baserev, diff)
     elif source == b'storage':
         baserev = orig.deltaparent(rev)
         cachedelta = (baserev, orig.revdiff(orig.node(baserev), rev))
 
     return (
         (text, tr, linkrev, p1, p2),
         {'node': node, 'flags': flags, 'cachedelta': cachedelta},
     )
 
 
 @contextlib.contextmanager
 def _temprevlog(ui, orig, truncaterev):
     from mercurial import vfs as vfsmod
 
     if orig._inline:
         raise error.Abort('not supporting inline revlog (yet)')
     revlogkwargs = {}
     k = 'upperboundcomp'
     if util.safehasattr(orig, k):
         revlogkwargs[k] = getattr(orig, k)
 
     origindexpath = orig.opener.join(orig.indexfile)
     origdatapath = orig.opener.join(orig.datafile)
     indexname = 'revlog.i'
     dataname = 'revlog.d'
 
     tmpdir = tempfile.mkdtemp(prefix='tmp-hgperf-')
     try:
         # copy the data file in a temporary directory
         ui.debug('copying data in %s\n' % tmpdir)
         destindexpath = os.path.join(tmpdir, 'revlog.i')
         destdatapath = os.path.join(tmpdir, 'revlog.d')
         shutil.copyfile(origindexpath, destindexpath)
         shutil.copyfile(origdatapath, destdatapath)
 
         # remove the data we want to add again
         ui.debug('truncating data to be rewritten\n')
         with open(destindexpath, 'ab') as index:
             index.seek(0)
             index.truncate(truncaterev * orig._io.size)
         with open(destdatapath, 'ab') as data:
             data.seek(0)
             data.truncate(orig.start(truncaterev))
 
         # instantiate a new revlog from the temporary copy
         ui.debug('truncating adding to be rewritten\n')
         vfs = vfsmod.vfs(tmpdir)
         vfs.options = getattr(orig.opener, 'options', None)
 
         dest = revlog.revlog(
             vfs, indexfile=indexname, datafile=dataname, **revlogkwargs
         )
         if dest._inline:
             raise error.Abort('not supporting inline revlog (yet)')
         # make sure internals are initialized
         dest.revision(len(dest) - 1)
         yield dest
         del dest, vfs
     finally:
         shutil.rmtree(tmpdir, True)
 
 
 @command(
     b'perfrevlogchunks',
     revlogopts
     + formatteropts
     + [
         (b'e', b'engines', b'', b'compression engines to use'),
         (b's', b'startrev', 0, b'revision to start at'),
     ],
     b'-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``.
     """
     opts = _byteskwargs(opts)
 
     rl = cmdutil.openrevlog(repo, b'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(b','))
         for engine in engines:
             try:
                 util.compressionengines[engine]
             except KeyError:
                 raise error.Abort(b'unknown compression engine: %s' % engine)
     else:
         engines = []
         for e in util.compengines:
             engine = util.compengines[e]
             try:
                 if engine.available():
                     engine.revlogcompressor().compress(b'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(), b'read'),
         (lambda: doreadcachedfh(), b'read w/ reused fd'),
         (lambda: doreadbatch(), b'read batch'),
         (lambda: doreadbatchcachedfh(), b'read batch w/ reused fd'),
         (lambda: dochunk(), b'chunk'),
         (lambda: dochunkbatch(), b'chunk batch'),
     ]
 
     for engine in sorted(engines):
         compressor = util.compengines[engine].revlogcompressor()
         benches.append(
             (
                 functools.partial(docompress, compressor),
                 b'compress w/ %s' % engine,
             )
         )
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 
 @command(
     b'perfrevlogrevision',
     revlogopts
     + formatteropts
     + [(b'', b'cache', False, b'use caches instead of clearing')],
     b'-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. Slice the delta chain if applicable
     3. Obtain the raw chunks for that delta chain
     4. Decompress each raw chunk
     5. Apply binary patches to obtain fulltext
     6. Verify hash of fulltext
 
     This command measures the time spent in each of these phases.
     """
     opts = _byteskwargs(opts)
 
     if opts.get(b'changelog') or opts.get(b'manifest'):
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError(b'perfrevlogrevision', b'invalid arguments')
 
     r = cmdutil.openrevlog(repo, b'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
 
         chunks = []
         ladd = chunks.append
         for idx, item in enumerate(chain):
             offset = start(item[0])
             bits = data[idx]
             for rev in item:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(buffer(bits, chunkstart - offset, chunklength))
 
         return chunks
 
     def dodeltachain(rev):
         if not cache:
             r.clearcaches()
         r._deltachain(rev)
 
     def doread(chain):
         if not cache:
             r.clearcaches()
         for item in slicedchain:
             segmentforrevs(item[0], item[-1])
 
     def doslice(r, chain, size):
         for s in slicechunk(r, chain, targetsize=size):
             pass
 
     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)
 
     try:
         from mercurial.revlogutils.deltas import slicechunk
     except ImportError:
         slicechunk = getattr(revlog, '_slicechunk', None)
 
     size = r.length(rev)
     chain = r._deltachain(rev)[0]
     if not getattr(r, '_withsparseread', False):
         slicedchain = (chain,)
     else:
         slicedchain = tuple(slicechunk(r, chain, targetsize=size))
     data = [segmentforrevs(seg[0], seg[-1])[1] for seg in slicedchain]
     rawchunks = getrawchunks(data, slicedchain)
     bins = r._chunks(chain)
     text = bytes(bins[0])
     bins = bins[1:]
     text = mdiff.patches(text, bins)
 
     benches = [
         (lambda: dorevision(), b'full'),
         (lambda: dodeltachain(rev), b'deltachain'),
         (lambda: doread(chain), b'read'),
     ]
 
     if getattr(r, '_withsparseread', False):
         slicing = (lambda: doslice(r, chain, size), b'slice-sparse-chain')
         benches.append(slicing)
 
     benches.extend(
         [
             (lambda: dorawchunks(data, slicedchain), b'rawchunks'),
             (lambda: dodecompress(rawchunks), b'decompress'),
             (lambda: dopatch(text, bins), b'patch'),
             (lambda: dohash(text), b'hash'),
         ]
     )
 
     timer, fm = gettimer(ui, opts)
     for fn, title in benches:
         timer(fn, title=title)
     fm.end()
 
 
 @command(
     b'perfrevset',
     [
         (b'C', b'clear', False, b'clear volatile cache between each call.'),
         (b'', b'contexts', False, b'obtain changectx for each revision'),
     ]
     + formatteropts,
     b"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."""
     opts = _byteskwargs(opts)
 
     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(
     b'perfvolatilesets',
     [(b'', b'clear-obsstore', False, b'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."""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     repo = repo.unfiltered()
 
     def getobs(name):
         def d():
             repo.invalidatevolatilesets()
             if opts[b'clear_obsstore']:
                 clearfilecache(repo, b'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[b'clear_obsstore']:
                 clearfilecache(repo, b'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(
     b'perfbranchmap',
     [
         (b'f', b'full', False, b'Includes build time of subset'),
         (
             b'',
             b'clear-revbranch',
             False,
             b'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
     """
     opts = _byteskwargs(opts)
     full = opts.get(b"full", False)
     clear_revbranch = opts.get(b"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)
         if util.safehasattr(view._branchcaches, '_per_filter'):
             filtered = view._branchcaches._per_filter
         else:
             # older versions
             filtered = view._branchcaches
 
         def d():
             if clear_revbranch:
                 repo.revbranchcache()._clear()
             if full:
                 view._branchcaches.clear()
             else:
                 filtered.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, b'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 b'unfiltered' in filternames:
         # add unfiltered
         allfilters.append(None)
 
     if util.safehasattr(branchmap.branchcache, 'fromfile'):
         branchcacheread = safeattrsetter(branchmap.branchcache, b'fromfile')
         branchcacheread.set(classmethod(lambda *args: None))
     else:
         # older versions
         branchcacheread = safeattrsetter(branchmap, b'read')
         branchcacheread.set(lambda *args: None)
     branchcachewrite = safeattrsetter(branchmap.branchcache, b'write')
     branchcachewrite.set(lambda *args: None)
     try:
         for name in allfilters:
             printname = name
             if name is None:
                 printname = b'unfiltered'
             timer(getbranchmap(name), title=str(printname))
     finally:
         branchcacheread.restore()
         branchcachewrite.restore()
     fm.end()
 
 
 @command(
     b'perfbranchmapupdate',
     [
         (b'', b'base', [], b'subset of revision to start from'),
         (b'', b'target', [], b'subset of revision to end with'),
         (b'', b'clear-caches', False, b'clear cache between each runs'),
     ]
     + formatteropts,
 )
 def perfbranchmapupdate(ui, repo, base=(), target=(), **opts):
     """benchmark branchmap update from for <base> revs to <target> revs
 
     If `--clear-caches` is passed, the following items will be reset before
     each update:
         * the changelog instance and associated indexes
         * the rev-branch-cache instance
 
     Examples:
 
        # update for the one last revision
        $ hg perfbranchmapupdate --base 'not tip' --target 'tip'
 
        $ update for change coming with a new branch
        $ hg perfbranchmapupdate --base 'stable' --target 'default'
     """
     from mercurial import branchmap
     from mercurial import repoview
 
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     clearcaches = opts[b'clear_caches']
     unfi = repo.unfiltered()
     x = [None]  # used to pass data between closure
 
     # we use a `list` here to avoid possible side effect from smartset
     baserevs = list(scmutil.revrange(repo, base))
     targetrevs = list(scmutil.revrange(repo, target))
     if not baserevs:
         raise error.Abort(b'no revisions selected for --base')
     if not targetrevs:
         raise error.Abort(b'no revisions selected for --target')
 
     # make sure the target branchmap also contains the one in the base
     targetrevs = list(set(baserevs) | set(targetrevs))
     targetrevs.sort()
 
     cl = repo.changelog
     allbaserevs = list(cl.ancestors(baserevs, inclusive=True))
     allbaserevs.sort()
     alltargetrevs = frozenset(cl.ancestors(targetrevs, inclusive=True))
 
     newrevs = list(alltargetrevs.difference(allbaserevs))
     newrevs.sort()
 
     allrevs = frozenset(unfi.changelog.revs())
     basefilterrevs = frozenset(allrevs.difference(allbaserevs))
     targetfilterrevs = frozenset(allrevs.difference(alltargetrevs))
 
     def basefilter(repo, visibilityexceptions=None):
         return basefilterrevs
 
     def targetfilter(repo, visibilityexceptions=None):
         return targetfilterrevs
 
     msg = b'benchmark of branchmap with %d revisions with %d new ones\n'
     ui.status(msg % (len(allbaserevs), len(newrevs)))
     if targetfilterrevs:
         msg = b'(%d revisions still filtered)\n'
         ui.status(msg % len(targetfilterrevs))
 
     try:
         repoview.filtertable[b'__perf_branchmap_update_base'] = basefilter
         repoview.filtertable[b'__perf_branchmap_update_target'] = targetfilter
 
         baserepo = repo.filtered(b'__perf_branchmap_update_base')
         targetrepo = repo.filtered(b'__perf_branchmap_update_target')
 
         # try to find an existing branchmap to reuse
         subsettable = getbranchmapsubsettable()
         candidatefilter = subsettable.get(None)
         while candidatefilter is not None:
             candidatebm = repo.filtered(candidatefilter).branchmap()
             if candidatebm.validfor(baserepo):
                 filtered = repoview.filterrevs(repo, candidatefilter)
                 missing = [r for r in allbaserevs if r in filtered]
                 base = candidatebm.copy()
                 base.update(baserepo, missing)
                 break
             candidatefilter = subsettable.get(candidatefilter)
         else:
             # no suitable subset where found
             base = branchmap.branchcache()
             base.update(baserepo, allbaserevs)
 
         def setup():
             x[0] = base.copy()
             if clearcaches:
                 unfi._revbranchcache = None
                 clearchangelog(repo)
 
         def bench():
             x[0].update(targetrepo, newrevs)
 
         timer(bench, setup=setup)
         fm.end()
     finally:
         repoview.filtertable.pop(b'__perf_branchmap_update_base', None)
         repoview.filtertable.pop(b'__perf_branchmap_update_target', None)
 
 
 @command(
     b'perfbranchmapload',
     [
         (b'f', b'filter', b'', b'Specify repoview filter'),
         (b'', b'list', False, b'List brachmap filter caches'),
         (b'', b'clear-revlogs', False, b'refresh changelog and manifest'),
     ]
     + formatteropts,
 )
 def perfbranchmapload(ui, repo, filter=b'', list=False, **opts):
     """benchmark reading the branchmap"""
     opts = _byteskwargs(opts)
     clearrevlogs = opts[b'clear_revlogs']
 
     if list:
         for name, kind, st in repo.cachevfs.readdir(stat=True):
             if name.startswith(b'branch2'):
                 filtername = name.partition(b'-')[2] or b'unfiltered'
                 ui.status(
                     b'%s - %s\n' % (filtername, util.bytecount(st.st_size))
                 )
         return
     if not filter:
         filter = None
     subsettable = getbranchmapsubsettable()
     if filter is None:
         repo = repo.unfiltered()
     else:
         repo = repoview.repoview(repo, filter)
 
     repo.branchmap()  # make sure we have a relevant, up to date branchmap
 
     try:
         fromfile = branchmap.branchcache.fromfile
     except AttributeError:
         # older versions
         fromfile = branchmap.read
 
     currentfilter = filter
     # try once without timer, the filter may not be cached
     while fromfile(repo) is None:
         currentfilter = subsettable.get(currentfilter)
         if currentfilter is None:
             raise error.Abort(
                 b'No branchmap cached for %s repo' % (filter or b'unfiltered')
             )
         repo = repo.filtered(currentfilter)
     timer, fm = gettimer(ui, opts)
 
     def setup():
         if clearrevlogs:
             clearchangelog(repo)
 
     def bench():
         fromfile(repo)
 
     timer(bench, setup=setup)
     fm.end()
 
 
 @command(b'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(
     b'perflrucachedict',
     formatteropts
     + [
         (b'', b'costlimit', 0, b'maximum total cost of items in cache'),
         (b'', b'mincost', 0, b'smallest cost of items in cache'),
         (b'', b'maxcost', 100, b'maximum cost of items in cache'),
         (b'', b'size', 4, b'size of cache'),
         (b'', b'gets', 10000, b'number of key lookups'),
         (b'', b'sets', 10000, b'number of key sets'),
         (b'', b'mixed', 10000, b'number of mixed mode operations'),
         (
             b'',
             b'mixedgetfreq',
             50,
             b'frequency of get vs set ops in mixed mode',
         ),
     ],
     norepo=True,
 )
 def perflrucache(
     ui,
     mincost=0,
     maxcost=100,
     costlimit=0,
     size=4,
     gets=10000,
     sets=10000,
     mixed=10000,
     mixedgetfreq=50,
     **opts
 ):
     opts = _byteskwargs(opts)
 
     def doinit():
         for i in _xrange(10000):
             util.lrucachedict(size)
 
     costrange = list(range(mincost, maxcost + 1))
 
     values = []
     for i in _xrange(size):
         values.append(random.randint(0, _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
 
     def dogetscost():
         d = util.lrucachedict(size, maxcost=costlimit)
         for i, v in enumerate(values):
             d.insert(v, v, cost=costs[i])
         for key in getseq:
             try:
                 value = d[key]
                 value  # silence pyflakes warning
             except KeyError:
                 pass
 
     # Set mode tests insertion speed with cache eviction.
     setseq = []
     costs = []
     for i in _xrange(sets):
         setseq.append(random.randint(0, _maxint))
         costs.append(random.choice(costrange))
 
     def doinserts():
         d = util.lrucachedict(size)
         for v in setseq:
             d.insert(v, v)
 
     def doinsertscost():
         d = util.lrucachedict(size, maxcost=costlimit)
         for i, v in enumerate(setseq):
             d.insert(v, v, cost=costs[i])
 
     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), random.choice(costrange))
         )
 
     def domixed():
         d = util.lrucachedict(size)
 
         for op, v, cost in mixedops:
             if op == 0:
                 try:
                     d[v]
                 except KeyError:
                     pass
             else:
                 d[v] = v
 
     def domixedcost():
         d = util.lrucachedict(size, maxcost=costlimit)
 
         for op, v, cost in mixedops:
             if op == 0:
                 try:
                     d[v]
                 except KeyError:
                     pass
             else:
                 d.insert(v, v, cost=cost)
 
     benches = [
         (doinit, b'init'),
     ]
 
     if costlimit:
         benches.extend(
             [
                 (dogetscost, b'gets w/ cost limit'),
                 (doinsertscost, b'inserts w/ cost limit'),
                 (domixedcost, b'mixed w/ cost limit'),
             ]
         )
     else:
         benches.extend(
             [
                 (dogets, b'gets'),
                 (doinserts, b'inserts'),
                 (dosets, b'sets'),
                 (domixed, b'mixed'),
             ]
         )
 
     for fn, title in benches:
         timer, fm = gettimer(ui, opts)
         timer(fn, title=title)
         fm.end()
 
 
 @command(b'perfwrite', formatteropts)
 def perfwrite(ui, repo, **opts):
     """microbenchmark ui.write
     """
     opts = _byteskwargs(opts)
 
     timer, fm = gettimer(ui, opts)
 
     def write():
         for i in range(100000):
-            ui.write(b'Testing write performance\n')
+            ui.writenoi18n(b'Testing write performance\n')
 
     timer(write)
     fm.end()
 
 
 def uisetup(ui):
     if util.safehasattr(cmdutil, b'openrevlog') and not util.safehasattr(
         commands, b'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(b'dir') and not util.safehasattr(repo, b'dirlog'):
                 raise error.Abort(
                     b"This version doesn't support --dir option",
                     hint=b"use 3.5 or later",
                 )
             return orig(repo, cmd, file_, opts)
 
         extensions.wrapfunction(cmdutil, b'openrevlog', openrevlog)
 
 
 @command(
     b'perfprogress',
     formatteropts
     + [
         (b'', b'topic', b'topic', b'topic for progress messages'),
         (b'c', b'total', 1000000, b'total value we are progressing to'),
     ],
     norepo=True,
 )
 def perfprogress(ui, topic=None, total=None, **opts):
     """printing of progress bars"""
     opts = _byteskwargs(opts)
 
     timer, fm = gettimer(ui, opts)
 
     def doprogress():
         with ui.makeprogress(topic, total=total) as progress:
             for i in _xrange(total):
                 progress.increment()
 
     timer(doprogress)
     fm.end()

doc/check-seclevel.py

@@ -1,227 +1,227 b''
 #!/usr/bin/env python
 #
 # checkseclevel - checking section title levels in each online help document
 
 from __future__ import absolute_import
 
 import optparse
 import os
 import sys
 
 # import from the live mercurial repo
 os.environ['HGMODULEPOLICY'] = 'py'
 sys.path.insert(0, "..")
 from mercurial import demandimport
 
 demandimport.enable()
 from mercurial import (
     commands,
     extensions,
     help,
     minirst,
     ui as uimod,
 )
 
 table = commands.table
 helptable = help.helptable
 
 level2mark = [b'"', b'=', b'-', b'.', b'#']
 reservedmarks = [b'"']
 
 mark2level = {}
 for m, l in zip(level2mark, range(len(level2mark))):
     if m not in reservedmarks:
         mark2level[m] = l
 
 initlevel_topic = 0
 initlevel_cmd = 1
 initlevel_ext = 1
 initlevel_ext_cmd = 3
 
 
 def showavailables(ui, initlevel):
     avail = '    available marks and order of them in this help: %s\n' % (
         ', '.join(['%r' % (m * 4) for m in level2mark[initlevel + 1 :]])
     )
     ui.warn(avail.encode('utf-8'))
 
 
 def checkseclevel(ui, doc, name, initlevel):
-    ui.note('checking "%s"\n' % name)
+    ui.notenoi18n('checking "%s"\n' % name)
     if not isinstance(doc, bytes):
         doc = doc.encode('utf-8')
     blocks, pruned = minirst.parse(doc, 0, ['verbose'])
     errorcnt = 0
     curlevel = initlevel
     for block in blocks:
         if block[b'type'] != b'section':
             continue
         mark = block[b'underline']
         title = block[b'lines'][0]
         if (mark not in mark2level) or (mark2level[mark] <= initlevel):
             ui.warn(
                 (
                     'invalid section mark %r for "%s" of %s\n'
                     % (mark * 4, title, name)
                 ).encode('utf-8')
             )
             showavailables(ui, initlevel)
             errorcnt += 1
             continue
         nextlevel = mark2level[mark]
         if curlevel < nextlevel and curlevel + 1 != nextlevel:
-            ui.warn('gap of section level at "%s" of %s\n' % (title, name))
+            ui.warnnoi18n('gap of section level at "%s" of %s\n' % (title, name))
             showavailables(ui, initlevel)
             errorcnt += 1
             continue
-        ui.note(
+        ui.notenoi18n(
             'appropriate section level for "%s %s"\n'
             % (mark * (nextlevel * 2), title)
         )
         curlevel = nextlevel
 
     return errorcnt
 
 
 def checkcmdtable(ui, cmdtable, namefmt, initlevel):
     errorcnt = 0
     for k, entry in cmdtable.items():
         name = k.split(b"|")[0].lstrip(b"^")
         if not entry[0].__doc__:
-            ui.note('skip checking %s: no help document\n' % (namefmt % name))
+            ui.notenoi18n('skip checking %s: no help document\n' % (namefmt % name))
             continue
         errorcnt += checkseclevel(
             ui, entry[0].__doc__, namefmt % name, initlevel
         )
     return errorcnt
 
 
 def checkhghelps(ui):
     errorcnt = 0
     for h in helptable:
         names, sec, doc = h[0:3]
         if callable(doc):
             doc = doc(ui)
         errorcnt += checkseclevel(
             ui, doc, '%s help topic' % names[0], initlevel_topic
         )
 
     errorcnt += checkcmdtable(ui, table, '%s command', initlevel_cmd)
 
     for name in sorted(
         list(extensions.enabled()) + list(extensions.disabled())
     ):
         mod = extensions.load(ui, name, None)
         if not mod.__doc__:
-            ui.note('skip checking %s extension: no help document\n' % name)
+            ui.notenoi18n('skip checking %s extension: no help document\n' % name)
             continue
         errorcnt += checkseclevel(
             ui, mod.__doc__, '%s extension' % name, initlevel_ext
         )
 
         cmdtable = getattr(mod, 'cmdtable', None)
         if cmdtable:
             errorcnt += checkcmdtable(
                 ui,
                 cmdtable,
                 '%%s command of %s extension' % name,
                 initlevel_ext_cmd,
             )
     return errorcnt
 
 
 def checkfile(ui, filename, initlevel):
     if filename == '-':
         filename = 'stdin'
         doc = sys.stdin.read()
     else:
         with open(filename) as fp:
             doc = fp.read()
 
-    ui.note(
+    ui.notenoi18n(
         'checking input from %s with initlevel %d\n' % (filename, initlevel)
     )
     return checkseclevel(ui, doc, 'input from %s' % filename, initlevel)
 
 
 def main():
     optparser = optparse.OptionParser(
         """%prog [options]
 
 This checks all help documents of Mercurial (topics, commands,
 extensions and commands of them), if no file is specified by --file
 option.
 """
     )
     optparser.add_option(
         "-v", "--verbose", help="enable additional output", action="store_true"
     )
     optparser.add_option(
         "-d", "--debug", help="debug mode", action="store_true"
     )
     optparser.add_option(
         "-f",
         "--file",
         help="filename to read in (or '-' for stdin)",
         action="store",
         default="",
     )
 
     optparser.add_option(
         "-t",
         "--topic",
         help="parse file as help topic",
         action="store_const",
         dest="initlevel",
         const=0,
     )
     optparser.add_option(
         "-c",
         "--command",
         help="parse file as help of core command",
         action="store_const",
         dest="initlevel",
         const=1,
     )
     optparser.add_option(
         "-e",
         "--extension",
         help="parse file as help of extension",
         action="store_const",
         dest="initlevel",
         const=1,
     )
     optparser.add_option(
         "-C",
         "--extension-command",
         help="parse file as help of extension command",
         action="store_const",
         dest="initlevel",
         const=3,
     )
 
     optparser.add_option(
         "-l",
         "--initlevel",
         help="set initial section level manually",
         action="store",
         type="int",
         default=0,
     )
 
     (options, args) = optparser.parse_args()
 
     ui = uimod.ui.load()
     ui.setconfig(b'ui', b'verbose', options.verbose, b'--verbose')
     ui.setconfig(b'ui', b'debug', options.debug, b'--debug')
 
     if options.file:
         if checkfile(ui, options.file, options.initlevel):
             sys.exit(1)
     else:
         if checkhghelps(ui):
             sys.exit(1)
 
 
 if __name__ == "__main__":
     main()

hgext/convert/cvsps.py

@@ -1,1073 +1,1073 b''
 # Mercurial built-in replacement for cvsps.
 #
 # Copyright 2008, Frank Kingswood <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import functools
 import os
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     hook,
     pycompat,
     util,
 )
 from mercurial.utils import (
     dateutil,
     procutil,
     stringutil,
 )
 
 pickle = util.pickle
 
 
 class logentry(object):
     '''Class logentry has the following attributes:
         .author    - author name as CVS knows it
         .branch    - name of branch this revision is on
         .branches  - revision tuple of branches starting at this revision
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time, tz) tuple
         .dead      - true if file revision is dead
         .file      - Name of file
         .lines     - a tuple (+lines, -lines) or None
         .parent    - Previous revision of this entry
         .rcs       - name of file as returned from CVS
         .revision  - revision number as tuple
         .tags      - list of tags on the file
         .synthetic - is this a synthetic "file ... added on ..." revision?
         .mergepoint - the branch that has been merged from (if present in
                       rlog output) or None
         .branchpoints - the branches that start at the current entry or empty
     '''
 
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = (
             r"%s=%r" % (k, self.__dict__[k]) for k in sorted(self.__dict__)
         )
         return r"%s(%s)" % (type(self).__name__, r", ".join(items))
 
 
 class logerror(Exception):
     pass
 
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath(b'/foo/bar')
     '/foo/bar'
     >>> getrepopath(b'c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:10/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:10c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:[e-mail]:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b'user@server/path/to/repository')
     '/path/to/repository'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # CVSpath is splitted into parts and then position of the first occurrence
     # of the '/' char after the '@' is located. The solution is the rest of the
     # string after that '/' sign including it
 
     parts = cvspath.split(b':')
     atposition = parts[-1].find(b'@')
     start = 0
 
     if atposition != -1:
         start = atposition
 
     repopath = parts[-1][parts[-1].find(b'/', start) :]
     return repopath
 
 
 def createlog(ui, directory=None, root=b"", rlog=True, cache=None):
     '''Collect the CVS rlog'''
 
     # Because we store many duplicate commit log messages, reusing strings
     # saves a lot of memory and pickle storage space.
     _scache = {}
 
     def scache(s):
         b"return a shared version of a string"
         return _scache.setdefault(s, s)
 
     ui.status(_(b'collecting CVS rlog\n'))
 
     log = []  # list of logentry objects containing the CVS state
 
     # patterns to match in CVS (r)log output, by state of use
     re_00 = re.compile(b'RCS file: (.+)$')
     re_01 = re.compile(b'cvs \\[r?log aborted\\]: (.+)$')
     re_02 = re.compile(b'cvs (r?log|server): (.+)\n$')
     re_03 = re.compile(
         b"(Cannot access.+CVSROOT)|" b"(can't create temporary directory.+)$"
     )
     re_10 = re.compile(b'Working file: (.+)$')
     re_20 = re.compile(b'symbolic names:')
     re_30 = re.compile(b'\t(.+): ([\\d.]+)$')
     re_31 = re.compile(b'----------------------------$')
     re_32 = re.compile(
         b'======================================='
         b'======================================$'
     )
     re_50 = re.compile(br'revision ([\d.]+)(\s+locked by:\s+.+;)?$')
     re_60 = re.compile(
         br'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
         br'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
         br'(\s+commitid:\s+([^;]+);)?'
         br'(.*mergepoint:\s+([^;]+);)?'
     )
     re_70 = re.compile(b'branches: (.+);$')
 
     file_added_re = re.compile(br'file [^/]+ was (initially )?added on branch')
 
     prefix = b''  # leading path to strip of what we get from CVS
 
     if directory is None:
         # Current working directory
 
         # Get the real directory in the repository
         try:
             with open(os.path.join(b'CVS', b'Repository'), b'rb') as f:
                 prefix = f.read().strip()
             directory = prefix
             if prefix == b".":
                 prefix = b""
         except IOError:
             raise logerror(_(b'not a CVS sandbox'))
 
         if prefix and not prefix.endswith(pycompat.ossep):
             prefix += pycompat.ossep
 
         # Use the Root file in the sandbox, if it exists
         try:
             root = open(os.path.join(b'CVS', b'Root'), b'rb').read().strip()
         except IOError:
             pass
 
     if not root:
         root = encoding.environ.get(b'CVSROOT', b'')
 
     # read log cache if one exists
     oldlog = []
     date = None
 
     if cache:
         cachedir = os.path.expanduser(b'~/.hg.cvsps')
         if not os.path.exists(cachedir):
             os.mkdir(cachedir)
 
         # The cvsps cache pickle needs a uniquified name, based on the
         # repository location. The address may have all sort of nasties
         # in it, slashes, colons and such. So here we take just the
         # alphanumeric characters, concatenated in a way that does not
         # mix up the various components, so that
         #    :pserver:user@server:/path
         # and
         #    /pserver/user/server/path
         # are mapped to different cache file names.
         cachefile = root.split(b":") + [directory, b"cache"]
         cachefile = [b'-'.join(re.findall(br'\w+', s)) for s in cachefile if s]
         cachefile = os.path.join(
             cachedir, b'.'.join([s for s in cachefile if s])
         )
 
     if cache == b'update':
         try:
             ui.note(_(b'reading cvs log cache %s\n') % cachefile)
             oldlog = pickle.load(open(cachefile, b'rb'))
             for e in oldlog:
                 if not (
                     util.safehasattr(e, b'branchpoints')
                     and util.safehasattr(e, b'commitid')
                     and util.safehasattr(e, b'mergepoint')
                 ):
                     ui.status(_(b'ignoring old cache\n'))
                     oldlog = []
                     break
 
             ui.note(_(b'cache has %d log entries\n') % len(oldlog))
         except Exception as e:
             ui.note(_(b'error reading cache: %r\n') % e)
 
         if oldlog:
             date = oldlog[-1].date  # last commit date as a (time,tz) tuple
             date = dateutil.datestr(date, b'%Y/%m/%d %H:%M:%S %1%2')
 
     # build the CVS commandline
     cmd = [b'cvs', b'-q']
     if root:
         cmd.append(b'-d%s' % root)
         p = util.normpath(getrepopath(root))
         if not p.endswith(b'/'):
             p += b'/'
         if prefix:
             # looks like normpath replaces "" by "."
             prefix = p + util.normpath(prefix)
         else:
             prefix = p
     cmd.append([b'log', b'rlog'][rlog])
     if date:
         # no space between option and date string
         cmd.append(b'-d>%s' % date)
     cmd.append(directory)
 
     # state machine begins here
     tags = {}  # dictionary of revisions on current file with their tags
     branchmap = {}  # mapping between branch names and revision numbers
     rcsmap = {}
     state = 0
     store = False  # set when a new record can be appended
 
     cmd = [procutil.shellquote(arg) for arg in cmd]
     ui.note(_(b"running %s\n") % (b' '.join(cmd)))
     ui.debug(b"prefix=%r directory=%r root=%r\n" % (prefix, directory, root))
 
     pfp = procutil.popen(b' '.join(cmd), b'rb')
     peek = util.fromnativeeol(pfp.readline())
     while True:
         line = peek
         if line == b'':
             break
         peek = util.fromnativeeol(pfp.readline())
         if line.endswith(b'\n'):
             line = line[:-1]
         # ui.debug('state=%d line=%r\n' % (state, line))
 
         if state == 0:
             # initial state, consume input until we see 'RCS file'
             match = re_00.match(line)
             if match:
                 rcs = match.group(1)
                 tags = {}
                 if rlog:
                     filename = util.normpath(rcs[:-2])
                     if filename.startswith(prefix):
                         filename = filename[len(prefix) :]
                     if filename.startswith(b'/'):
                         filename = filename[1:]
                     if filename.startswith(b'Attic/'):
                         filename = filename[6:]
                     else:
                         filename = filename.replace(b'/Attic/', b'/')
                     state = 2
                     continue
                 state = 1
                 continue
             match = re_01.match(line)
             if match:
                 raise logerror(match.group(1))
             match = re_02.match(line)
             if match:
                 raise logerror(match.group(2))
             if re_03.match(line):
                 raise logerror(line)
 
         elif state == 1:
             # expect 'Working file' (only when using log instead of rlog)
             match = re_10.match(line)
             assert match, _(b'RCS file must be followed by working file')
             filename = util.normpath(match.group(1))
             state = 2
 
         elif state == 2:
             # expect 'symbolic names'
             if re_20.match(line):
                 branchmap = {}
                 state = 3
 
         elif state == 3:
             # read the symbolic names and store as tags
             match = re_30.match(line)
             if match:
                 rev = [int(x) for x in match.group(2).split(b'.')]
 
                 # Convert magic branch number to an odd-numbered one
                 revn = len(rev)
                 if revn > 3 and (revn % 2) == 0 and rev[-2] == 0:
                     rev = rev[:-2] + rev[-1:]
                 rev = tuple(rev)
 
                 if rev not in tags:
                     tags[rev] = []
                 tags[rev].append(match.group(1))
                 branchmap[match.group(1)] = match.group(2)
 
             elif re_31.match(line):
                 state = 5
             elif re_32.match(line):
                 state = 0
 
         elif state == 4:
             # expecting '------' separator before first revision
             if re_31.match(line):
                 state = 5
             else:
                 assert not re_32.match(line), _(
                     b'must have at least ' b'some revisions'
                 )
 
         elif state == 5:
             # expecting revision number and possibly (ignored) lock indication
             # we create the logentry here from values stored in states 0 to 4,
             # as this state is re-entered for subsequent revisions of a file.
             match = re_50.match(line)
             assert match, _(b'expected revision number')
             e = logentry(
                 rcs=scache(rcs),
                 file=scache(filename),
                 revision=tuple([int(x) for x in match.group(1).split(b'.')]),
                 branches=[],
                 parent=None,
                 commitid=None,
                 mergepoint=None,
                 branchpoints=set(),
             )
 
             state = 6
 
         elif state == 6:
             # expecting date, author, state, lines changed
             match = re_60.match(line)
             assert match, _(b'revision must be followed by date line')
             d = match.group(1)
             if d[2] == b'/':
                 # Y2K
                 d = b'19' + d
 
             if len(d.split()) != 3:
                 # cvs log dates always in GMT
                 d = d + b' UTC'
             e.date = dateutil.parsedate(
                 d,
                 [
                     b'%y/%m/%d %H:%M:%S',
                     b'%Y/%m/%d %H:%M:%S',
                     b'%Y-%m-%d %H:%M:%S',
                 ],
             )
             e.author = scache(match.group(2))
             e.dead = match.group(3).lower() == b'dead'
 
             if match.group(5):
                 if match.group(6):
                     e.lines = (int(match.group(5)), int(match.group(6)))
                 else:
                     e.lines = (int(match.group(5)), 0)
             elif match.group(6):
                 e.lines = (0, int(match.group(6)))
             else:
                 e.lines = None
 
             if match.group(7):  # cvs 1.12 commitid
                 e.commitid = match.group(8)
 
             if match.group(9):  # cvsnt mergepoint
                 myrev = match.group(10).split(b'.')
                 if len(myrev) == 2:  # head
                     e.mergepoint = b'HEAD'
                 else:
                     myrev = b'.'.join(myrev[:-2] + [b'0', myrev[-2]])
                     branches = [b for b in branchmap if branchmap[b] == myrev]
                     assert len(branches) == 1, (
                         b'unknown branch: %s' % e.mergepoint
                     )
                     e.mergepoint = branches[0]
 
             e.comment = []
             state = 7
 
         elif state == 7:
             # read the revision numbers of branches that start at this revision
             # or store the commit log message otherwise
             m = re_70.match(line)
             if m:
                 e.branches = [
                     tuple([int(y) for y in x.strip().split(b'.')])
                     for x in m.group(1).split(b';')
                 ]
                 state = 8
             elif re_31.match(line) and re_50.match(peek):
                 state = 5
                 store = True
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         elif state == 8:
             # store commit log message
             if re_31.match(line):
                 cpeek = peek
                 if cpeek.endswith(b'\n'):
                     cpeek = cpeek[:-1]
                 if re_50.match(cpeek):
                     state = 5
                     store = True
                 else:
                     e.comment.append(line)
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         # When a file is added on a branch B1, CVS creates a synthetic
         # dead trunk revision 1.1 so that the branch has a root.
         # Likewise, if you merge such a file to a later branch B2 (one
         # that already existed when the file was added on B1), CVS
         # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
         # these revisions now, but mark them synthetic so
         # createchangeset() can take care of them.
         if (
             store
             and e.dead
             and e.revision[-1] == 1
             and len(e.comment) == 1  # 1.1 or 1.1.x.1
             and file_added_re.match(e.comment[0])
         ):
             ui.debug(
                 b'found synthetic revision in %s: %r\n' % (e.rcs, e.comment[0])
             )
             e.synthetic = True
 
         if store:
             # clean up the results and save in the log.
             store = False
             e.tags = sorted([scache(x) for x in tags.get(e.revision, [])])
             e.comment = scache(b'\n'.join(e.comment))
 
             revn = len(e.revision)
             if revn > 3 and (revn % 2) == 0:
                 e.branch = tags.get(e.revision[:-1], [None])[0]
             else:
                 e.branch = None
 
             # find the branches starting from this revision
             branchpoints = set()
             for branch, revision in branchmap.iteritems():
                 revparts = tuple([int(i) for i in revision.split(b'.')])
                 if len(revparts) < 2:  # bad tags
                     continue
                 if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                     # normal branch
                     if revparts[:-2] == e.revision:
                         branchpoints.add(branch)
                 elif revparts == (1, 1, 1):  # vendor branch
                     if revparts in e.branches:
                         branchpoints.add(branch)
             e.branchpoints = branchpoints
 
             log.append(e)
 
             rcsmap[e.rcs.replace(b'/Attic/', b'/')] = e.rcs
 
             if len(log) % 100 == 0:
                 ui.status(
                     stringutil.ellipsis(b'%d %s' % (len(log), e.file), 80)
                     + b'\n'
                 )
 
     log.sort(key=lambda x: (x.rcs, x.revision))
 
     # find parent revisions of individual files
     versions = {}
     for e in sorted(oldlog, key=lambda x: (x.rcs, x.revision)):
         rcs = e.rcs.replace(b'/Attic/', b'/')
         if rcs in rcsmap:
             e.rcs = rcsmap[rcs]
         branch = e.revision[:-1]
         versions[(e.rcs, branch)] = e.revision
 
     for e in log:
         branch = e.revision[:-1]
         p = versions.get((e.rcs, branch), None)
         if p is None:
             p = e.revision[:-2]
         e.parent = p
         versions[(e.rcs, branch)] = e.revision
 
     # update the log cache
     if cache:
         if log:
             # join up the old and new logs
             log.sort(key=lambda x: x.date)
 
             if oldlog and oldlog[-1].date >= log[0].date:
                 raise logerror(
                     _(
                         b'log cache overlaps with new log entries,'
                         b' re-run without cache.'
                     )
                 )
 
             log = oldlog + log
 
             # write the new cachefile
             ui.note(_(b'writing cvs log cache %s\n') % cachefile)
             pickle.dump(log, open(cachefile, b'wb'))
         else:
             log = oldlog
 
     ui.status(_(b'%d log entries\n') % len(log))
 
     encodings = ui.configlist(b'convert', b'cvsps.logencoding')
     if encodings:
 
         def revstr(r):
             # this is needed, because logentry.revision is a tuple of "int"
             # (e.g. (1, 2) for "1.2")
             return b'.'.join(pycompat.maplist(pycompat.bytestr, r))
 
         for entry in log:
             comment = entry.comment
             for e in encodings:
                 try:
                     entry.comment = comment.decode(pycompat.sysstr(e)).encode(
                         'utf-8'
                     )
                     if ui.debugflag:
                         ui.debug(
                             b"transcoding by %s: %s of %s\n"
                             % (e, revstr(entry.revision), entry.file)
                         )
                     break
                 except UnicodeDecodeError:
                     pass  # try next encoding
                 except LookupError as inst:  # unknown encoding, maybe
                     raise error.Abort(
                         inst,
                         hint=_(
                             b'check convert.cvsps.logencoding' b' configuration'
                         ),
                     )
             else:
                 raise error.Abort(
                     _(
                         b"no encoding can transcode"
                         b" CVS log message for %s of %s"
                     )
                     % (revstr(entry.revision), entry.file),
                     hint=_(
                         b'check convert.cvsps.logencoding' b' configuration'
                     ),
                 )
 
     hook.hook(ui, None, b"cvslog", True, log=log)
 
     return log
 
 
 class changeset(object):
     '''Class changeset has the following attributes:
         .id        - integer identifying this changeset (list index)
         .author    - author name as CVS knows it
         .branch    - name of branch this changeset is on, or None
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time,tz) tuple
         .entries   - list of logentry objects in this changeset
         .parents   - list of one or two parent changesets
         .tags      - list of tags on this changeset
         .synthetic - from synthetic revision "file ... added on branch ..."
         .mergepoint- the branch that has been merged from or None
         .branchpoints- the branches that start at the current entry or empty
     '''
 
     def __init__(self, **entries):
         self.id = None
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = (
             b"%s=%r" % (k, self.__dict__[k]) for k in sorted(self.__dict__)
         )
         return b"%s(%s)" % (type(self).__name__, b", ".join(items))
 
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_(b'creating changesets\n'))
 
     # try to order commitids by date
     mindate = {}
     for e in log:
         if e.commitid:
             if e.commitid not in mindate:
                 mindate[e.commitid] = e.date
             else:
                 mindate[e.commitid] = min(e.date, mindate[e.commitid])
 
     # Merge changesets
     log.sort(
         key=lambda x: (
             mindate.get(x.commitid, (-1, 0)),
             x.commitid or b'',
             x.comment,
             x.author,
             x.branch or b'',
             x.date,
             x.branchpoints,
         )
     )
 
     changesets = []
     files = set()
     c = None
     for i, e in enumerate(log):
 
         # Check if log entry belongs to the current changeset or not.
 
         # Since CVS is file-centric, two different file revisions with
         # different branchpoints should be treated as belonging to two
         # different changesets (and the ordering is important and not
         # honoured by cvsps at this point).
         #
         # Consider the following case:
         # foo 1.1 branchpoints: [MYBRANCH]
         # bar 1.1 branchpoints: [MYBRANCH, MYBRANCH2]
         #
         # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
         # later version of foo may be in MYBRANCH2, so foo should be the
         # first changeset and bar the next and MYBRANCH and MYBRANCH2
         # should both start off of the bar changeset. No provisions are
         # made to ensure that this is, in fact, what happens.
         if not (
             c
             and e.branchpoints == c.branchpoints
             and (  # cvs commitids
                 (e.commitid is not None and e.commitid == c.commitid)
                 or (  # no commitids, use fuzzy commit detection
                     (e.commitid is None or c.commitid is None)
                     and e.comment == c.comment
                     and e.author == c.author
                     and e.branch == c.branch
                     and (
                         (c.date[0] + c.date[1])
                         <= (e.date[0] + e.date[1])
                         <= (c.date[0] + c.date[1]) + fuzz
                     )
                     and e.file not in files
                 )
             )
         ):
             c = changeset(
                 comment=e.comment,
                 author=e.author,
                 branch=e.branch,
                 date=e.date,
                 entries=[],
                 mergepoint=e.mergepoint,
                 branchpoints=e.branchpoints,
                 commitid=e.commitid,
             )
             changesets.append(c)
 
             files = set()
             if len(changesets) % 100 == 0:
                 t = b'%d %s' % (len(changesets), repr(e.comment)[1:-1])
                 ui.status(stringutil.ellipsis(t, 80) + b'\n')
 
         c.entries.append(e)
         files.add(e.file)
         c.date = e.date  # changeset date is date of latest commit in it
 
     # Mark synthetic changesets
 
     for c in changesets:
         # Synthetic revisions always get their own changeset, because
         # the log message includes the filename.  E.g. if you add file3
         # and file4 on a branch, you get four log entries and three
         # changesets:
         #   "File file3 was added on branch ..." (synthetic, 1 entry)
         #   "File file4 was added on branch ..." (synthetic, 1 entry)
         #   "Add file3 and file4 to fix ..."     (real, 2 entries)
         # Hence the check for 1 entry here.
         c.synthetic = len(c.entries) == 1 and c.entries[0].synthetic
 
     # Sort files in each changeset
 
     def entitycompare(l, r):
         b'Mimic cvsps sorting order'
         l = l.file.split(b'/')
         r = r.file.split(b'/')
         nl = len(l)
         nr = len(r)
         n = min(nl, nr)
         for i in range(n):
             if i + 1 == nl and nl < nr:
                 return -1
             elif i + 1 == nr and nl > nr:
                 return +1
             elif l[i] < r[i]:
                 return -1
             elif l[i] > r[i]:
                 return +1
         return 0
 
     for c in changesets:
         c.entries.sort(key=functools.cmp_to_key(entitycompare))
 
     # Sort changesets by date
 
     odd = set()
 
     def cscmp(l, r):
         d = sum(l.date) - sum(r.date)
         if d:
             return d
 
         # detect vendor branches and initial commits on a branch
         le = {}
         for e in l.entries:
             le[e.rcs] = e.revision
         re = {}
         for e in r.entries:
             re[e.rcs] = e.revision
 
         d = 0
         for e in l.entries:
             if re.get(e.rcs, None) == e.parent:
                 assert not d
                 d = 1
                 break
 
         for e in r.entries:
             if le.get(e.rcs, None) == e.parent:
                 if d:
                     odd.add((l, r))
                 d = -1
                 break
         # By this point, the changesets are sufficiently compared that
         # we don't really care about ordering. However, this leaves
         # some race conditions in the tests, so we compare on the
         # number of files modified, the files contained in each
         # changeset, and the branchpoints in the change to ensure test
         # output remains stable.
 
         # recommended replacement for cmp from
         # https://docs.python.org/3.0/whatsnew/3.0.html
         c = lambda x, y: (x > y) - (x < y)
         # Sort bigger changes first.
         if not d:
             d = c(len(l.entries), len(r.entries))
         # Try sorting by filename in the change.
         if not d:
             d = c([e.file for e in l.entries], [e.file for e in r.entries])
         # Try and put changes without a branch point before ones with
         # a branch point.
         if not d:
             d = c(len(l.branchpoints), len(r.branchpoints))
         return d
 
     changesets.sort(key=functools.cmp_to_key(cscmp))
 
     # Collect tags
 
     globaltags = {}
     for c in changesets:
         for e in c.entries:
             for tag in e.tags:
                 # remember which is the latest changeset to have this tag
                 globaltags[tag] = c
 
     for c in changesets:
         tags = set()
         for e in c.entries:
             tags.update(e.tags)
         # remember tags only if this is the latest changeset to have it
         c.tags = sorted(tag for tag in tags if globaltags[tag] is c)
 
     # Find parent changesets, handle {{mergetobranch BRANCHNAME}}
     # by inserting dummy changesets with two parents, and handle
     # {{mergefrombranch BRANCHNAME}} by setting two parents.
 
     if mergeto is None:
         mergeto = br'{{mergetobranch ([-\w]+)}}'
     if mergeto:
         mergeto = re.compile(mergeto)
 
     if mergefrom is None:
         mergefrom = br'{{mergefrombranch ([-\w]+)}}'
     if mergefrom:
         mergefrom = re.compile(mergefrom)
 
     versions = {}  # changeset index where we saw any particular file version
     branches = {}  # changeset index where we saw a branch
     n = len(changesets)
     i = 0
     while i < n:
         c = changesets[i]
 
         for f in c.entries:
             versions[(f.rcs, f.revision)] = i
 
         p = None
         if c.branch in branches:
             p = branches[c.branch]
         else:
             # first changeset on a new branch
             # the parent is a changeset with the branch in its
             # branchpoints such that it is the latest possible
             # commit without any intervening, unrelated commits.
 
             for candidate in pycompat.xrange(i):
                 if c.branch not in changesets[candidate].branchpoints:
                     if p is not None:
                         break
                     continue
                 p = candidate
 
         c.parents = []
         if p is not None:
             p = changesets[p]
 
             # Ensure no changeset has a synthetic changeset as a parent.
             while p.synthetic:
                 assert len(p.parents) <= 1, _(
                     b'synthetic changeset cannot have multiple parents'
                 )
                 if p.parents:
                     p = p.parents[0]
                 else:
                     p = None
                     break
 
             if p is not None:
                 c.parents.append(p)
 
         if c.mergepoint:
             if c.mergepoint == b'HEAD':
                 c.mergepoint = None
             c.parents.append(changesets[branches[c.mergepoint]])
 
         if mergefrom:
             m = mergefrom.search(c.comment)
             if m:
                 m = m.group(1)
                 if m == b'HEAD':
                     m = None
                 try:
                     candidate = changesets[branches[m]]
                 except KeyError:
                     ui.warn(
                         _(
                             b"warning: CVS commit message references "
                             b"non-existent branch %r:\n%s\n"
                         )
                         % (pycompat.bytestr(m), c.comment)
                     )
                 if m in branches and c.branch != m and not candidate.synthetic:
                     c.parents.append(candidate)
 
         if mergeto:
             m = mergeto.search(c.comment)
             if m:
                 if m.groups():
                     m = m.group(1)
                     if m == b'HEAD':
                         m = None
                 else:
                     m = None  # if no group found then merge to HEAD
                 if m in branches and c.branch != m:
                     # insert empty changeset for merge
                     cc = changeset(
                         author=c.author,
                         branch=m,
                         date=c.date,
                         comment=b'convert-repo: CVS merge from branch %s'
                         % c.branch,
                         entries=[],
                         tags=[],
                         parents=[changesets[branches[m]], c],
                     )
                     changesets.insert(i + 1, cc)
                     branches[m] = i + 1
 
                     # adjust our loop counters now we have inserted a new entry
                     n += 1
                     i += 2
                     continue
 
         branches[c.branch] = i
         i += 1
 
     # Drop synthetic changesets (safe now that we have ensured no other
     # changesets can have them as parents).
     i = 0
     while i < len(changesets):
         if changesets[i].synthetic:
             del changesets[i]
         else:
             i += 1
 
     # Number changesets
 
     for i, c in enumerate(changesets):
         c.id = i + 1
 
     if odd:
         for l, r in odd:
             if l.id is not None and r.id is not None:
                 ui.warn(
                     _(b'changeset %d is both before and after %d\n')
                     % (l.id, r.id)
                 )
 
     ui.status(_(b'%d changeset entries\n') % len(changesets))
 
     hook.hook(ui, None, b"cvschangesets", True, changesets=changesets)
 
     return changesets
 
 
 def debugcvsps(ui, *args, **opts):
     '''Read CVS rlog for current directory or named path in
     repository, and convert the log to changesets based on matching
     commit log entries and dates.
     '''
     opts = pycompat.byteskwargs(opts)
     if opts[b"new_cache"]:
         cache = b"write"
     elif opts[b"update_cache"]:
         cache = b"update"
     else:
         cache = None
 
     revisions = opts[b"revisions"]
 
     try:
         if args:
             log = []
             for d in args:
                 log += createlog(ui, d, root=opts[b"root"], cache=cache)
         else:
             log = createlog(ui, root=opts[b"root"], cache=cache)
     except logerror as e:
         ui.write(b"%r\n" % e)
         return
 
     changesets = createchangeset(ui, log, opts[b"fuzz"])
     del log
 
     # Print changesets (optionally filtered)
 
     off = len(revisions)
     branches = {}  # latest version number in each branch
     ancestors = {}  # parent branch
     for cs in changesets:
 
         if opts[b"ancestors"]:
             if cs.branch not in branches and cs.parents and cs.parents[0].id:
                 ancestors[cs.branch] = (
                     changesets[cs.parents[0].id - 1].branch,
                     cs.parents[0].id,
                 )
             branches[cs.branch] = cs.id
 
         # limit by branches
         if (
             opts[b"branches"]
             and (cs.branch or b'HEAD') not in opts[b"branches"]
         ):
             continue
 
         if not off:
             # Note: trailing spaces on several lines here are needed to have
             #       bug-for-bug compatibility with cvsps.
             ui.write(b'---------------------\n')
             ui.write((b'PatchSet %d \n' % cs.id))
             ui.write(
                 (
                     b'Date: %s\n'
                     % dateutil.datestr(cs.date, b'%Y/%m/%d %H:%M:%S %1%2')
                 )
             )
             ui.write((b'Author: %s\n' % cs.author))
             ui.write((b'Branch: %s\n' % (cs.branch or b'HEAD')))
             ui.write(
                 (
                     b'Tag%s: %s \n'
                     % (
                         [b'', b's'][len(cs.tags) > 1],
                         b','.join(cs.tags) or b'(none)',
                     )
                 )
             )
             if cs.branchpoints:
-                ui.write(
+                ui.writenoi18n(
                     b'Branchpoints: %s \n' % b', '.join(sorted(cs.branchpoints))
                 )
             if opts[b"parents"] and cs.parents:
                 if len(cs.parents) > 1:
                     ui.write(
                         (
                             b'Parents: %s\n'
                             % (b','.join([(b"%d" % p.id) for p in cs.parents]))
                         )
                     )
                 else:
                     ui.write((b'Parent: %d\n' % cs.parents[0].id))
 
             if opts[b"ancestors"]:
                 b = cs.branch
                 r = []
                 while b:
                     b, c = ancestors[b]
                     r.append(b'%s:%d:%d' % (b or b"HEAD", c, branches[b]))
                 if r:
                     ui.write((b'Ancestors: %s\n' % (b','.join(r))))
 
-            ui.write(b'Log:\n')
+            ui.writenoi18n(b'Log:\n')
             ui.write(b'%s\n\n' % cs.comment)
-            ui.write(b'Members: \n')
+            ui.writenoi18n(b'Members: \n')
             for f in cs.entries:
                 fn = f.file
                 if fn.startswith(opts[b"prefix"]):
                     fn = fn[len(opts[b"prefix"]) :]
                 ui.write(
                     b'\t%s:%s->%s%s \n'
                     % (
                         fn,
                         b'.'.join([b"%d" % x for x in f.parent]) or b'INITIAL',
                         b'.'.join([(b"%d" % x) for x in f.revision]),
                         [b'', b'(DEAD)'][f.dead],
                     )
                 )
             ui.write(b'\n')
 
         # have we seen the start tag?
         if revisions and off:
             if revisions[0] == (b"%d" % cs.id) or revisions[0] in cs.tags:
                 off = False
 
         # see if we reached the end tag
         if len(revisions) > 1 and not off:
             if revisions[1] == (b"%d" % cs.id) or revisions[1] in cs.tags:
                 break

hgext/hgk.py

@@ -1,385 +1,385 b''
 # Minimal support for git commands on an hg repository
 #
 # Copyright 2005, 2006 Chris Mason <[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.
 
 '''browse the repository in a graphical way
 
 The hgk extension allows browsing the history of a repository in a
 graphical way. It requires Tcl/Tk version 8.4 or later. (Tcl/Tk is not
 distributed with Mercurial.)
 
 hgk consists of two parts: a Tcl script that does the displaying and
 querying of information, and an extension to Mercurial named hgk.py,
 which provides hooks for hgk to get information. hgk can be found in
 the contrib directory, and the extension is shipped in the hgext
 repository, and needs to be enabled.
 
 The :hg:`view` command will launch the hgk Tcl script. For this command
 to work, hgk must be in your search path. Alternately, you can specify
 the path to hgk in your configuration file::
 
   [hgk]
   path = /location/of/hgk
 
 hgk can make use of the extdiff extension to visualize revisions.
 Assuming you had already configured extdiff vdiff command, just add::
 
   [hgk]
   vdiff=vdiff
 
 Revisions context menu will now display additional entries to fire
 vdiff on hovered and selected revisions.
 '''
 
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     nullrev,
     short,
 )
 from mercurial import (
     commands,
     obsolete,
     patch,
     pycompat,
     registrar,
     scmutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem(
     b'hgk', b'path', default=b'hgk',
 )
 
 
 @command(
     b'debug-diff-tree',
     [
         (b'p', b'patch', None, _(b'generate patch')),
         (b'r', b'recursive', None, _(b'recursive')),
         (b'P', b'pretty', None, _(b'pretty')),
         (b's', b'stdin', None, _(b'stdin')),
         (b'C', b'copy', None, _(b'detect copies')),
         (b'S', b'search', b"", _(b'search')),
     ],
     b'[OPTION]... NODE1 NODE2 [FILE]...',
     inferrepo=True,
 )
 def difftree(ui, repo, node1=None, node2=None, *files, **opts):
     """diff trees from two commits"""
 
     def __difftree(repo, node1, node2, files=None):
         assert node2 is not None
         if files is None:
             files = []
         mmap = repo[node1].manifest()
         mmap2 = repo[node2].manifest()
         m = scmutil.match(repo[node1], files)
         modified, added, removed = repo.status(node1, node2, m)[:3]
         empty = short(nullid)
 
         for f in modified:
             # TODO get file permissions
-            ui.write(
+            ui.writenoi18n(
                 b":100664 100664 %s %s M\t%s\t%s\n"
                 % (short(mmap[f]), short(mmap2[f]), f, f)
             )
         for f in added:
-            ui.write(
+            ui.writenoi18n(
                 b":000000 100664 %s %s N\t%s\t%s\n"
                 % (empty, short(mmap2[f]), f, f)
             )
         for f in removed:
-            ui.write(
+            ui.writenoi18n(
                 b":100664 000000 %s %s D\t%s\t%s\n"
                 % (short(mmap[f]), empty, f, f)
             )
 
     ##
 
     while True:
         if opts[r'stdin']:
             line = ui.fin.readline()
             if not line:
                 break
             line = line.rstrip(pycompat.oslinesep).split(b' ')
             node1 = line[0]
             if len(line) > 1:
                 node2 = line[1]
             else:
                 node2 = None
         node1 = repo.lookup(node1)
         if node2:
             node2 = repo.lookup(node2)
         else:
             node2 = node1
             node1 = repo.changelog.parents(node1)[0]
         if opts[r'patch']:
             if opts[r'pretty']:
                 catcommit(ui, repo, node2, b"")
             m = scmutil.match(repo[node1], files)
             diffopts = patch.difffeatureopts(ui)
             diffopts.git = True
             chunks = patch.diff(repo, node1, node2, match=m, opts=diffopts)
             for chunk in chunks:
                 ui.write(chunk)
         else:
             __difftree(repo, node1, node2, files=files)
         if not opts[r'stdin']:
             break
 
 
 def catcommit(ui, repo, n, prefix, ctx=None):
     nlprefix = b'\n' + prefix
     if ctx is None:
         ctx = repo[n]
     # use ctx.node() instead ??
     ui.write((b"tree %s\n" % short(ctx.changeset()[0])))
     for p in ctx.parents():
         ui.write((b"parent %s\n" % p))
 
     date = ctx.date()
     description = ctx.description().replace(b"\0", b"")
     ui.write((b"author %s %d %d\n" % (ctx.user(), int(date[0]), date[1])))
 
     if b'committer' in ctx.extra():
         ui.write((b"committer %s\n" % ctx.extra()[b'committer']))
 
     ui.write((b"revision %d\n" % ctx.rev()))
     ui.write((b"branch %s\n" % ctx.branch()))
     if obsolete.isenabled(repo, obsolete.createmarkersopt):
         if ctx.obsolete():
-            ui.write(b"obsolete\n")
+            ui.writenoi18n(b"obsolete\n")
     ui.write((b"phase %s\n\n" % ctx.phasestr()))
 
     if prefix != b"":
         ui.write(
             b"%s%s\n" % (prefix, description.replace(b'\n', nlprefix).strip())
         )
     else:
         ui.write(description + b"\n")
     if prefix:
         ui.write(b'\0')
 
 
 @command(b'debug-merge-base', [], _(b'REV REV'))
 def base(ui, repo, node1, node2):
     """output common ancestor information"""
     node1 = repo.lookup(node1)
     node2 = repo.lookup(node2)
     n = repo.changelog.ancestor(node1, node2)
     ui.write(short(n) + b"\n")
 
 
 @command(
     b'debug-cat-file',
     [(b's', b'stdin', None, _(b'stdin'))],
     _(b'[OPTION]... TYPE FILE'),
     inferrepo=True,
 )
 def catfile(ui, repo, type=None, r=None, **opts):
     """cat a specific revision"""
     # in stdin mode, every line except the commit is prefixed with two
     # spaces.  This way the our caller can find the commit without magic
     # strings
     #
     prefix = b""
     if opts[r'stdin']:
         line = ui.fin.readline()
         if not line:
             return
         (type, r) = line.rstrip(pycompat.oslinesep).split(b' ')
         prefix = b"    "
     else:
         if not type or not r:
             ui.warn(_(b"cat-file: type or revision not supplied\n"))
             commands.help_(ui, b'cat-file')
 
     while r:
         if type != b"commit":
             ui.warn(_(b"aborting hg cat-file only understands commits\n"))
             return 1
         n = repo.lookup(r)
         catcommit(ui, repo, n, prefix)
         if opts[r'stdin']:
             line = ui.fin.readline()
             if not line:
                 break
             (type, r) = line.rstrip(pycompat.oslinesep).split(b' ')
         else:
             break
 
 
 # git rev-tree is a confusing thing.  You can supply a number of
 # commit sha1s on the command line, and it walks the commit history
 # telling you which commits are reachable from the supplied ones via
 # a bitmask based on arg position.
 # you can specify a commit to stop at by starting the sha1 with ^
 def revtree(ui, args, repo, full=b"tree", maxnr=0, parents=False):
     def chlogwalk():
         count = len(repo)
         i = count
         l = [0] * 100
         chunk = 100
         while True:
             if chunk > i:
                 chunk = i
                 i = 0
             else:
                 i -= chunk
 
             for x in pycompat.xrange(chunk):
                 if i + x >= count:
                     l[chunk - x :] = [0] * (chunk - x)
                     break
                 if full is not None:
                     if (i + x) in repo:
                         l[x] = repo[i + x]
                         l[x].changeset()  # force reading
                 else:
                     if (i + x) in repo:
                         l[x] = 1
             for x in pycompat.xrange(chunk - 1, -1, -1):
                 if l[x] != 0:
                     yield (i + x, full is not None and l[x] or None)
             if i == 0:
                 break
 
     # calculate and return the reachability bitmask for sha
     def is_reachable(ar, reachable, sha):
         if len(ar) == 0:
             return 1
         mask = 0
         for i in pycompat.xrange(len(ar)):
             if sha in reachable[i]:
                 mask |= 1 << i
 
         return mask
 
     reachable = []
     stop_sha1 = []
     want_sha1 = []
     count = 0
 
     # figure out which commits they are asking for and which ones they
     # want us to stop on
     for i, arg in enumerate(args):
         if arg.startswith(b'^'):
             s = repo.lookup(arg[1:])
             stop_sha1.append(s)
             want_sha1.append(s)
         elif arg != b'HEAD':
             want_sha1.append(repo.lookup(arg))
 
     # calculate the graph for the supplied commits
     for i, n in enumerate(want_sha1):
         reachable.append(set())
         visit = [n]
         reachable[i].add(n)
         while visit:
             n = visit.pop(0)
             if n in stop_sha1:
                 continue
             for p in repo.changelog.parents(n):
                 if p not in reachable[i]:
                     reachable[i].add(p)
                     visit.append(p)
                 if p in stop_sha1:
                     continue
 
     # walk the repository looking for commits that are in our
     # reachability graph
     for i, ctx in chlogwalk():
         if i not in repo:
             continue
         n = repo.changelog.node(i)
         mask = is_reachable(want_sha1, reachable, n)
         if mask:
             parentstr = b""
             if parents:
                 pp = repo.changelog.parents(n)
                 if pp[0] != nullid:
                     parentstr += b" " + short(pp[0])
                 if pp[1] != nullid:
                     parentstr += b" " + short(pp[1])
             if not full:
                 ui.write(b"%s%s\n" % (short(n), parentstr))
             elif full == b"commit":
                 ui.write(b"%s%s\n" % (short(n), parentstr))
                 catcommit(ui, repo, n, b'    ', ctx)
             else:
                 (p1, p2) = repo.changelog.parents(n)
                 (h, h1, h2) = map(short, (n, p1, p2))
                 (i1, i2) = map(repo.changelog.rev, (p1, p2))
 
                 date = ctx.date()[0]
                 ui.write(b"%s %s:%s" % (date, h, mask))
                 mask = is_reachable(want_sha1, reachable, p1)
                 if i1 != nullrev and mask > 0:
                     ui.write(b"%s:%s " % (h1, mask)),
                 mask = is_reachable(want_sha1, reachable, p2)
                 if i2 != nullrev and mask > 0:
                     ui.write(b"%s:%s " % (h2, mask))
                 ui.write(b"\n")
             if maxnr and count >= maxnr:
                 break
             count += 1
 
 
 # git rev-list tries to order things by date, and has the ability to stop
 # at a given commit without walking the whole repo.  TODO add the stop
 # parameter
 @command(
     b'debug-rev-list',
     [
         (b'H', b'header', None, _(b'header')),
         (b't', b'topo-order', None, _(b'topo-order')),
         (b'p', b'parents', None, _(b'parents')),
         (b'n', b'max-count', 0, _(b'max-count')),
     ],
     b'[OPTION]... REV...',
 )
 def revlist(ui, repo, *revs, **opts):
     """print revisions"""
     if opts[b'header']:
         full = b"commit"
     else:
         full = None
     copy = [x for x in revs]
     revtree(ui, copy, repo, full, opts[r'max_count'], opts[r'parents'])
 
 
 @command(
     b'view',
     [(b'l', b'limit', b'', _(b'limit number of changes displayed'), _(b'NUM'))],
     _(b'[-l LIMIT] [REVRANGE]'),
     helpcategory=command.CATEGORY_CHANGE_NAVIGATION,
 )
 def view(ui, repo, *etc, **opts):
     b"start interactive history viewer"
     opts = pycompat.byteskwargs(opts)
     os.chdir(repo.root)
     optstr = b' '.join([b'--%s %s' % (k, v) for k, v in opts.iteritems() if v])
     if repo.filtername is None:
         optstr += b'--hidden'
 
     cmd = ui.config(b"hgk", b"path") + b" %s %s" % (optstr, b" ".join(etc))
     ui.debug(b"running %s\n" % cmd)
     ui.system(cmd, blockedtag=b'hgk_view')

hgext/keyword.py

@@ -1,886 +1,886 b''
 # keyword.py - $Keyword$ expansion for Mercurial
 #
 # Copyright 2007-2015 Christian Ebert <[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.
 #
 # $Id$
 #
 # Keyword expansion hack against the grain of a Distributed SCM
 #
 # There are many good reasons why this is not needed in a distributed
 # SCM, still it may be useful in very small projects based on single
 # files (like LaTeX packages), that are mostly addressed to an
 # audience not running a version control system.
 #
 # For in-depth discussion refer to
 # <https://mercurial-scm.org/wiki/KeywordPlan>.
 #
 # Keyword expansion is based on Mercurial's changeset template mappings.
 #
 # Binary files are not touched.
 #
 # Files to act upon/ignore are specified in the [keyword] section.
 # Customized keyword template mappings in the [keywordmaps] section.
 #
 # Run 'hg help keyword' and 'hg kwdemo' to get info on configuration.
 
 '''expand keywords in tracked files
 
 This extension expands RCS/CVS-like or self-customized $Keywords$ in
 tracked text files selected by your configuration.
 
 Keywords are only expanded in local repositories and not stored in the
 change history. The mechanism can be regarded as a convenience for the
 current user or for archive distribution.
 
 Keywords expand to the changeset data pertaining to the latest change
 relative to the working directory parent of each file.
 
 Configuration is done in the [keyword], [keywordset] and [keywordmaps]
 sections of hgrc files.
 
 Example::
 
     [keyword]
     # expand keywords in every python file except those matching "x*"
     **.py =
     x*    = ignore
 
     [keywordset]
     # prefer svn- over cvs-like default keywordmaps
     svn = True
 
 .. note::
 
    The more specific you are in your filename patterns the less you
    lose speed in huge repositories.
 
 For [keywordmaps] template mapping and expansion demonstration and
 control run :hg:`kwdemo`. See :hg:`help templates` for a list of
 available templates and filters.
 
 Three additional date template filters are provided:
 
 :``utcdate``:    "2006/09/18 15:13:13"
 :``svnutcdate``: "2006-09-18 15:13:13Z"
 :``svnisodate``: "2006-09-18 08:13:13 -700 (Mon, 18 Sep 2006)"
 
 The default template mappings (view with :hg:`kwdemo -d`) can be
 replaced with customized keywords and templates. Again, run
 :hg:`kwdemo` to control the results of your configuration changes.
 
 Before changing/disabling active keywords, you must run :hg:`kwshrink`
 to avoid storing expanded keywords in the change history.
 
 To force expansion after enabling it, or a configuration change, run
 :hg:`kwexpand`.
 
 Expansions spanning more than one line and incremental expansions,
 like CVS' $Log$, are not supported. A keyword template map "Log =
 {desc}" expands to the first line of the changeset description.
 '''
 
 
 from __future__ import absolute_import
 
 import os
 import re
 import weakref
 
 from mercurial.i18n import _
 from mercurial.hgweb import webcommands
 
 from mercurial import (
     cmdutil,
     context,
     dispatch,
     error,
     extensions,
     filelog,
     localrepo,
     logcmdutil,
     match,
     patch,
     pathutil,
     pycompat,
     registrar,
     scmutil,
     templatefilters,
     templateutil,
     util,
 )
 from mercurial.utils import (
     dateutil,
     stringutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 # hg commands that do not act on keywords
 nokwcommands = (
     b'add addremove annotate bundle export grep incoming init log'
     b' outgoing push tip verify convert email glog'
 )
 
 # webcommands that do not act on keywords
 nokwwebcommands = b'annotate changeset rev filediff diff comparison'
 
 # hg commands that trigger expansion only when writing to working dir,
 # not when reading filelog, and unexpand when reading from working dir
 restricted = (
     b'merge kwexpand kwshrink record qrecord resolve transplant'
     b' unshelve rebase graft backout histedit fetch'
 )
 
 # names of extensions using dorecord
 recordextensions = b'record'
 
 colortable = {
     b'kwfiles.enabled': b'green bold',
     b'kwfiles.deleted': b'cyan bold underline',
     b'kwfiles.enabledunknown': b'green',
     b'kwfiles.ignored': b'bold',
     b'kwfiles.ignoredunknown': b'none',
 }
 
 templatefilter = registrar.templatefilter()
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem(
     b'keywordset', b'svn', default=False,
 )
 # date like in cvs' $Date
 @templatefilter(b'utcdate', intype=templateutil.date)
 def utcdate(date):
     '''Date. Returns a UTC-date in this format: "2009/08/18 11:00:13".
     '''
     dateformat = b'%Y/%m/%d %H:%M:%S'
     return dateutil.datestr((date[0], 0), dateformat)
 
 
 # date like in svn's $Date
 @templatefilter(b'svnisodate', intype=templateutil.date)
 def svnisodate(date):
     '''Date. Returns a date in this format: "2009-08-18 13:00:13
     +0200 (Tue, 18 Aug 2009)".
     '''
     return dateutil.datestr(date, b'%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)')
 
 
 # date like in svn's $Id
 @templatefilter(b'svnutcdate', intype=templateutil.date)
 def svnutcdate(date):
     '''Date. Returns a UTC-date in this format: "2009-08-18
     11:00:13Z".
     '''
     dateformat = b'%Y-%m-%d %H:%M:%SZ'
     return dateutil.datestr((date[0], 0), dateformat)
 
 
 # make keyword tools accessible
 kwtools = {b'hgcmd': b''}
 
 
 def _defaultkwmaps(ui):
     '''Returns default keywordmaps according to keywordset configuration.'''
     templates = {
         b'Revision': b'{node|short}',
         b'Author': b'{author|user}',
     }
     kwsets = (
         {
             b'Date': b'{date|utcdate}',
             b'RCSfile': b'{file|basename},v',
             b'RCSFile': b'{file|basename},v',  # kept for backwards compatibility
             # with hg-keyword
             b'Source': b'{root}/{file},v',
             b'Id': b'{file|basename},v {node|short} {date|utcdate} {author|user}',
             b'Header': b'{root}/{file},v {node|short} {date|utcdate} {author|user}',
         },
         {
             b'Date': b'{date|svnisodate}',
             b'Id': b'{file|basename},v {node|short} {date|svnutcdate} {author|user}',
             b'LastChangedRevision': b'{node|short}',
             b'LastChangedBy': b'{author|user}',
             b'LastChangedDate': b'{date|svnisodate}',
         },
     )
     templates.update(kwsets[ui.configbool(b'keywordset', b'svn')])
     return templates
 
 
 def _shrinktext(text, subfunc):
     '''Helper for keyword expansion removal in text.
     Depending on subfunc also returns number of substitutions.'''
     return subfunc(br'$\1$', text)
 
 
 def _preselect(wstatus, changed):
     '''Retrieves modified and added files from a working directory state
     and returns the subset of each contained in given changed files
     retrieved from a change context.'''
     modified = [f for f in wstatus.modified if f in changed]
     added = [f for f in wstatus.added if f in changed]
     return modified, added
 
 
 class kwtemplater(object):
     '''
     Sets up keyword templates, corresponding keyword regex, and
     provides keyword substitution functions.
     '''
 
     def __init__(self, ui, repo, inc, exc):
         self.ui = ui
         self._repo = weakref.ref(repo)
         self.match = match.match(repo.root, b'', [], inc, exc)
         self.restrict = kwtools[b'hgcmd'] in restricted.split()
         self.postcommit = False
 
         kwmaps = self.ui.configitems(b'keywordmaps')
         if kwmaps:  # override default templates
             self.templates = dict(kwmaps)
         else:
             self.templates = _defaultkwmaps(self.ui)
 
     @property
     def repo(self):
         return self._repo()
 
     @util.propertycache
     def escape(self):
         '''Returns bar-separated and escaped keywords.'''
         return b'|'.join(map(stringutil.reescape, self.templates.keys()))
 
     @util.propertycache
     def rekw(self):
         '''Returns regex for unexpanded keywords.'''
         return re.compile(br'\$(%s)\$' % self.escape)
 
     @util.propertycache
     def rekwexp(self):
         '''Returns regex for expanded keywords.'''
         return re.compile(br'\$(%s): [^$\n\r]*? \$' % self.escape)
 
     def substitute(self, data, path, ctx, subfunc):
         '''Replaces keywords in data with expanded template.'''
 
         def kwsub(mobj):
             kw = mobj.group(1)
             ct = logcmdutil.maketemplater(
                 self.ui, self.repo, self.templates[kw]
             )
             self.ui.pushbuffer()
             ct.show(ctx, root=self.repo.root, file=path)
             ekw = templatefilters.firstline(self.ui.popbuffer())
             return b'$%s: %s $' % (kw, ekw)
 
         return subfunc(kwsub, data)
 
     def linkctx(self, path, fileid):
         '''Similar to filelog.linkrev, but returns a changectx.'''
         return self.repo.filectx(path, fileid=fileid).changectx()
 
     def expand(self, path, node, data):
         '''Returns data with keywords expanded.'''
         if (
             not self.restrict
             and self.match(path)
             and not stringutil.binary(data)
         ):
             ctx = self.linkctx(path, node)
             return self.substitute(data, path, ctx, self.rekw.sub)
         return data
 
     def iskwfile(self, cand, ctx):
         '''Returns subset of candidates which are configured for keyword
         expansion but are not symbolic links.'''
         return [f for f in cand if self.match(f) and b'l' not in ctx.flags(f)]
 
     def overwrite(self, ctx, candidates, lookup, expand, rekw=False):
         '''Overwrites selected files expanding/shrinking keywords.'''
         if self.restrict or lookup or self.postcommit:  # exclude kw_copy
             candidates = self.iskwfile(candidates, ctx)
         if not candidates:
             return
         kwcmd = self.restrict and lookup  # kwexpand/kwshrink
         if self.restrict or expand and lookup:
             mf = ctx.manifest()
         if self.restrict or rekw:
             re_kw = self.rekw
         else:
             re_kw = self.rekwexp
         if expand:
             msg = _(b'overwriting %s expanding keywords\n')
         else:
             msg = _(b'overwriting %s shrinking keywords\n')
         for f in candidates:
             if self.restrict:
                 data = self.repo.file(f).read(mf[f])
             else:
                 data = self.repo.wread(f)
             if stringutil.binary(data):
                 continue
             if expand:
                 parents = ctx.parents()
                 if lookup:
                     ctx = self.linkctx(f, mf[f])
                 elif self.restrict and len(parents) > 1:
                     # merge commit
                     # in case of conflict f is in modified state during
                     # merge, even if f does not differ from f in parent
                     for p in parents:
                         if f in p and not p[f].cmp(ctx[f]):
                             ctx = p[f].changectx()
                             break
                 data, found = self.substitute(data, f, ctx, re_kw.subn)
             elif self.restrict:
                 found = re_kw.search(data)
             else:
                 data, found = _shrinktext(data, re_kw.subn)
             if found:
                 self.ui.note(msg % f)
                 fp = self.repo.wvfs(f, b"wb", atomictemp=True)
                 fp.write(data)
                 fp.close()
                 if kwcmd:
                     self.repo.dirstate.normal(f)
                 elif self.postcommit:
                     self.repo.dirstate.normallookup(f)
 
     def shrink(self, fname, text):
         '''Returns text with all keyword substitutions removed.'''
         if self.match(fname) and not stringutil.binary(text):
             return _shrinktext(text, self.rekwexp.sub)
         return text
 
     def shrinklines(self, fname, lines):
         '''Returns lines with keyword substitutions removed.'''
         if self.match(fname):
             text = b''.join(lines)
             if not stringutil.binary(text):
                 return _shrinktext(text, self.rekwexp.sub).splitlines(True)
         return lines
 
     def wread(self, fname, data):
         '''If in restricted mode returns data read from wdir with
         keyword substitutions removed.'''
         if self.restrict:
             return self.shrink(fname, data)
         return data
 
 
 class kwfilelog(filelog.filelog):
     '''
     Subclass of filelog to hook into its read, add, cmp methods.
     Keywords are "stored" unexpanded, and processed on reading.
     '''
 
     def __init__(self, opener, kwt, path):
         super(kwfilelog, self).__init__(opener, path)
         self.kwt = kwt
         self.path = path
 
     def read(self, node):
         '''Expands keywords when reading filelog.'''
         data = super(kwfilelog, self).read(node)
         if self.renamed(node):
             return data
         return self.kwt.expand(self.path, node, data)
 
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).add(text, meta, tr, link, p1, p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).cmp(node, text)
 
 
 def _status(ui, repo, wctx, kwt, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if kwt:
         opts = pycompat.byteskwargs(opts)
         return repo.status(
             match=scmutil.match(wctx, pats, opts),
             clean=True,
             unknown=opts.get(b'unknown') or opts.get(b'all'),
         )
     if ui.configitems(b'keyword'):
         raise error.Abort(_(b'[keyword] patterns cannot match'))
     raise error.Abort(_(b'no [keyword] patterns configured'))
 
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to kwtemplater.overwrite.'''
     wctx = repo[None]
     if len(wctx.parents()) > 1:
         raise error.Abort(_(b'outstanding uncommitted merge'))
     kwt = getattr(repo, '_keywordkwt', None)
     with repo.wlock():
         status = _status(ui, repo, wctx, kwt, *pats, **opts)
         if status.modified or status.added or status.removed or status.deleted:
             raise error.Abort(_(b'outstanding uncommitted changes'))
         kwt.overwrite(wctx, status.clean, True, expand)
 
 
 @command(
     b'kwdemo',
     [
         (b'd', b'default', None, _(b'show default keyword template maps')),
         (b'f', b'rcfile', b'', _(b'read maps from rcfile'), _(b'FILE')),
     ],
     _(b'hg kwdemo [-d] [-f RCFILE] [TEMPLATEMAP]...'),
     optionalrepo=True,
 )
 def demo(ui, repo, *args, **opts):
     '''print [keywordmaps] configuration and an expansion example
 
     Show current, custom, or default keyword template maps and their
     expansions.
 
     Extend the current configuration by specifying maps as arguments
     and using -f/--rcfile to source an external hgrc file.
 
     Use -d/--default to disable current configuration.
 
     See :hg:`help templates` for information on templates and filters.
     '''
 
     def demoitems(section, items):
         ui.write(b'[%s]\n' % section)
         for k, v in sorted(items):
             if isinstance(v, bool):
                 v = stringutil.pprint(v)
             ui.write(b'%s = %s\n' % (k, v))
 
     fn = b'demo.txt'
     tmpdir = pycompat.mkdtemp(b'', b'kwdemo.')
     ui.note(_(b'creating temporary repository at %s\n') % tmpdir)
     if repo is None:
         baseui = ui
     else:
         baseui = repo.baseui
     repo = localrepo.instance(baseui, tmpdir, create=True)
     ui.setconfig(b'keyword', fn, b'', b'keyword')
     svn = ui.configbool(b'keywordset', b'svn')
     # explicitly set keywordset for demo output
     ui.setconfig(b'keywordset', b'svn', svn, b'keyword')
 
     uikwmaps = ui.configitems(b'keywordmaps')
     if args or opts.get(r'rcfile'):
         ui.status(_(b'\n\tconfiguration using custom keyword template maps\n'))
         if uikwmaps:
             ui.status(_(b'\textending current template maps\n'))
         if opts.get(r'default') or not uikwmaps:
             if svn:
                 ui.status(_(b'\toverriding default svn keywordset\n'))
             else:
                 ui.status(_(b'\toverriding default cvs keywordset\n'))
         if opts.get(r'rcfile'):
             ui.readconfig(opts.get(b'rcfile'))
         if args:
             # simulate hgrc parsing
             rcmaps = b'[keywordmaps]\n%s\n' % b'\n'.join(args)
             repo.vfs.write(b'hgrc', rcmaps)
             ui.readconfig(repo.vfs.join(b'hgrc'))
         kwmaps = dict(ui.configitems(b'keywordmaps'))
     elif opts.get(r'default'):
         if svn:
             ui.status(_(b'\n\tconfiguration using default svn keywordset\n'))
         else:
             ui.status(_(b'\n\tconfiguration using default cvs keywordset\n'))
         kwmaps = _defaultkwmaps(ui)
         if uikwmaps:
             ui.status(_(b'\tdisabling current template maps\n'))
             for k, v in kwmaps.iteritems():
                 ui.setconfig(b'keywordmaps', k, v, b'keyword')
     else:
         ui.status(_(b'\n\tconfiguration using current keyword template maps\n'))
         if uikwmaps:
             kwmaps = dict(uikwmaps)
         else:
             kwmaps = _defaultkwmaps(ui)
 
     uisetup(ui)
     reposetup(ui, repo)
-    ui.write(b'[extensions]\nkeyword =\n')
+    ui.writenoi18n(b'[extensions]\nkeyword =\n')
     demoitems(b'keyword', ui.configitems(b'keyword'))
     demoitems(b'keywordset', ui.configitems(b'keywordset'))
     demoitems(b'keywordmaps', kwmaps.iteritems())
     keywords = b'$' + b'$\n$'.join(sorted(kwmaps.keys())) + b'$\n'
     repo.wvfs.write(fn, keywords)
     repo[None].add([fn])
     ui.note(_(b'\nkeywords written to %s:\n') % fn)
     ui.note(keywords)
     with repo.wlock():
         repo.dirstate.setbranch(b'demobranch')
     for name, cmd in ui.configitems(b'hooks'):
         if name.split(b'.', 1)[0].find(b'commit') > -1:
             repo.ui.setconfig(b'hooks', name, b'', b'keyword')
     msg = _(b'hg keyword configuration and expansion example')
     ui.note((b"hg ci -m '%s'\n" % msg))
     repo.commit(text=msg)
     ui.status(_(b'\n\tkeywords expanded\n'))
     ui.write(repo.wread(fn))
     repo.wvfs.rmtree(repo.root)
 
 
 @command(
     b'kwexpand',
     cmdutil.walkopts,
     _(b'hg kwexpand [OPTION]... [FILE]...'),
     inferrepo=True,
 )
 def expand(ui, repo, *pats, **opts):
     '''expand keywords in the working directory
 
     Run after (re)enabling keyword expansion.
 
     kwexpand refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to True
     _kwfwrite(ui, repo, True, *pats, **opts)
 
 
 @command(
     b'kwfiles',
     [
         (b'A', b'all', None, _(b'show keyword status flags of all files')),
         (b'i', b'ignore', None, _(b'show files excluded from expansion')),
         (b'u', b'unknown', None, _(b'only show unknown (not tracked) files')),
     ]
     + cmdutil.walkopts,
     _(b'hg kwfiles [OPTION]... [FILE]...'),
     inferrepo=True,
 )
 def files(ui, repo, *pats, **opts):
     '''show files configured for keyword expansion
 
     List which files in the working directory are matched by the
     [keyword] configuration patterns.
 
     Useful to prevent inadvertent keyword expansion and to speed up
     execution by including only files that are actual candidates for
     expansion.
 
     See :hg:`help keyword` on how to construct patterns both for
     inclusion and exclusion of files.
 
     With -A/--all and -v/--verbose the codes used to show the status
     of files are::
 
       K = keyword expansion candidate
       k = keyword expansion candidate (not tracked)
       I = ignored
       i = ignored (not tracked)
     '''
     kwt = getattr(repo, '_keywordkwt', None)
     wctx = repo[None]
     status = _status(ui, repo, wctx, kwt, *pats, **opts)
     if pats:
         cwd = repo.getcwd()
     else:
         cwd = b''
     files = []
     opts = pycompat.byteskwargs(opts)
     if not opts.get(b'unknown') or opts.get(b'all'):
         files = sorted(status.modified + status.added + status.clean)
     kwfiles = kwt.iskwfile(files, wctx)
     kwdeleted = kwt.iskwfile(status.deleted, wctx)
     kwunknown = kwt.iskwfile(status.unknown, wctx)
     if not opts.get(b'ignore') or opts.get(b'all'):
         showfiles = kwfiles, kwdeleted, kwunknown
     else:
         showfiles = [], [], []
     if opts.get(b'all') or opts.get(b'ignore'):
         showfiles += (
             [f for f in files if f not in kwfiles],
             [f for f in status.unknown if f not in kwunknown],
         )
     kwlabels = b'enabled deleted enabledunknown ignored ignoredunknown'.split()
     kwstates = zip(kwlabels, pycompat.bytestr(b'K!kIi'), showfiles)
     fm = ui.formatter(b'kwfiles', opts)
     fmt = b'%.0s%s\n'
     if opts.get(b'all') or ui.verbose:
         fmt = b'%s %s\n'
     for kwstate, char, filenames in kwstates:
         label = b'kwfiles.' + kwstate
         for f in filenames:
             fm.startitem()
             fm.data(kwstatus=char, path=f)
             fm.plain(fmt % (char, repo.pathto(f, cwd)), label=label)
     fm.end()
 
 
 @command(
     b'kwshrink',
     cmdutil.walkopts,
     _(b'hg kwshrink [OPTION]... [FILE]...'),
     inferrepo=True,
 )
 def shrink(ui, repo, *pats, **opts):
     '''revert expanded keywords in the working directory
 
     Must be run before changing/disabling active keywords.
 
     kwshrink refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to False
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 
 # monkeypatches
 
 
 def kwpatchfile_init(orig, self, ui, gp, backend, store, eolmode=None):
     '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
     rejects or conflicts due to expanded keywords in working dir.'''
     orig(self, ui, gp, backend, store, eolmode)
     kwt = getattr(getattr(backend, 'repo', None), '_keywordkwt', None)
     if kwt:
         # shrink keywords read from working dir
         self.lines = kwt.shrinklines(self.fname, self.lines)
 
 
 def kwdiff(orig, repo, *args, **kwargs):
     '''Monkeypatch patch.diff to avoid expansion.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt:
         restrict = kwt.restrict
         kwt.restrict = True
     try:
         for chunk in orig(repo, *args, **kwargs):
             yield chunk
     finally:
         if kwt:
             kwt.restrict = restrict
 
 
 def kwweb_skip(orig, web):
     '''Wraps webcommands.x turning off keyword expansion.'''
     kwt = getattr(web.repo, '_keywordkwt', None)
     if kwt:
         origmatch = kwt.match
         kwt.match = util.never
     try:
         for chunk in orig(web):
             yield chunk
     finally:
         if kwt:
             kwt.match = origmatch
 
 
 def kw_amend(orig, ui, repo, old, extra, pats, opts):
     '''Wraps cmdutil.amend expanding keywords after amend.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, old, extra, pats, opts)
     with repo.wlock():
         kwt.postcommit = True
         newid = orig(ui, repo, old, extra, pats, opts)
         if newid != old.node():
             ctx = repo[newid]
             kwt.restrict = True
             kwt.overwrite(ctx, ctx.files(), False, True)
             kwt.restrict = False
         return newid
 
 
 def kw_copy(orig, ui, repo, pats, opts, rename=False):
     '''Wraps cmdutil.copy so that copy/rename destinations do not
     contain expanded keywords.
     Note that the source of a regular file destination may also be a
     symlink:
     hg cp sym x                -> x is symlink
     cp sym x; hg cp -A sym x   -> x is file (maybe expanded keywords)
     For the latter we have to follow the symlink to find out whether its
     target is configured for expansion and we therefore must unexpand the
     keywords in the destination.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, pats, opts, rename)
     with repo.wlock():
         orig(ui, repo, pats, opts, rename)
         if opts.get(b'dry_run'):
             return
         wctx = repo[None]
         cwd = repo.getcwd()
 
         def haskwsource(dest):
             '''Returns true if dest is a regular file and configured for
             expansion or a symlink which points to a file configured for
             expansion. '''
             source = repo.dirstate.copied(dest)
             if b'l' in wctx.flags(source):
                 source = pathutil.canonpath(
                     repo.root, cwd, os.path.realpath(source)
                 )
             return kwt.match(source)
 
         candidates = [
             f
             for f in repo.dirstate.copies()
             if b'l' not in wctx.flags(f) and haskwsource(f)
         ]
         kwt.overwrite(wctx, candidates, False, False)
 
 
 def kw_dorecord(orig, ui, repo, commitfunc, *pats, **opts):
     '''Wraps record.dorecord expanding keywords after recording.'''
     kwt = getattr(repo, '_keywordkwt', None)
     if kwt is None:
         return orig(ui, repo, commitfunc, *pats, **opts)
     with repo.wlock():
         # record returns 0 even when nothing has changed
         # therefore compare nodes before and after
         kwt.postcommit = True
         ctx = repo[b'.']
         wstatus = ctx.status()
         ret = orig(ui, repo, commitfunc, *pats, **opts)
         recctx = repo[b'.']
         if ctx != recctx:
             modified, added = _preselect(wstatus, recctx.files())
             kwt.restrict = False
             kwt.overwrite(recctx, modified, False, True)
             kwt.overwrite(recctx, added, False, True, True)
             kwt.restrict = True
         return ret
 
 
 def kwfilectx_cmp(orig, self, fctx):
     if fctx._customcmp:
         return fctx.cmp(self)
     kwt = getattr(self._repo, '_keywordkwt', None)
     if kwt is None:
         return orig(self, fctx)
     # keyword affects data size, comparing wdir and filelog size does
     # not make sense
     if (
         fctx._filenode is None
         and (
             self._repo._encodefilterpats
             or kwt.match(fctx.path())
             and b'l' not in fctx.flags()
             or self.size() - 4 == fctx.size()
         )
         or self.size() == fctx.size()
     ):
         return self._filelog.cmp(self._filenode, fctx.data())
     return True
 
 
 def uisetup(ui):
     ''' Monkeypatches dispatch._parse to retrieve user command.
     Overrides file method to return kwfilelog instead of filelog
     if file matches user configuration.
     Wraps commit to overwrite configured files with updated
     keyword substitutions.
     Monkeypatches patch and webcommands.'''
 
     def kwdispatch_parse(orig, ui, args):
         '''Monkeypatch dispatch._parse to obtain running hg command.'''
         cmd, func, args, options, cmdoptions = orig(ui, args)
         kwtools[b'hgcmd'] = cmd
         return cmd, func, args, options, cmdoptions
 
     extensions.wrapfunction(dispatch, b'_parse', kwdispatch_parse)
 
     extensions.wrapfunction(context.filectx, b'cmp', kwfilectx_cmp)
     extensions.wrapfunction(patch.patchfile, b'__init__', kwpatchfile_init)
     extensions.wrapfunction(patch, b'diff', kwdiff)
     extensions.wrapfunction(cmdutil, b'amend', kw_amend)
     extensions.wrapfunction(cmdutil, b'copy', kw_copy)
     extensions.wrapfunction(cmdutil, b'dorecord', kw_dorecord)
     for c in nokwwebcommands.split():
         extensions.wrapfunction(webcommands, c, kwweb_skip)
 
 
 def reposetup(ui, repo):
     '''Sets up repo as kwrepo for keyword substitution.'''
 
     try:
         if (
             not repo.local()
             or kwtools[b'hgcmd'] in nokwcommands.split()
             or b'.hg' in util.splitpath(repo.root)
             or repo._url.startswith(b'bundle:')
         ):
             return
     except AttributeError:
         pass
 
     inc, exc = [], [b'.hg*']
     for pat, opt in ui.configitems(b'keyword'):
         if opt != b'ignore':
             inc.append(pat)
         else:
             exc.append(pat)
     if not inc:
         return
 
     kwt = kwtemplater(ui, repo, inc, exc)
 
     class kwrepo(repo.__class__):
         def file(self, f):
             if f[0] == b'/':
                 f = f[1:]
             return kwfilelog(self.svfs, kwt, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             return kwt.wread(filename, data)
 
         def commit(self, *args, **opts):
             # use custom commitctx for user commands
             # other extensions can still wrap repo.commitctx directly
             self.commitctx = self.kwcommitctx
             try:
                 return super(kwrepo, self).commit(*args, **opts)
             finally:
                 del self.commitctx
 
         def kwcommitctx(self, ctx, error=False, origctx=None):
             n = super(kwrepo, self).commitctx(ctx, error, origctx)
             # no lock needed, only called from repo.commit() which already locks
             if not kwt.postcommit:
                 restrict = kwt.restrict
                 kwt.restrict = True
                 kwt.overwrite(
                     self[n], sorted(ctx.added() + ctx.modified()), False, True
                 )
                 kwt.restrict = restrict
             return n
 
         def rollback(self, dryrun=False, force=False):
             with self.wlock():
                 origrestrict = kwt.restrict
                 try:
                     if not dryrun:
                         changed = self[b'.'].files()
                     ret = super(kwrepo, self).rollback(dryrun, force)
                     if not dryrun:
                         ctx = self[b'.']
                         modified, added = _preselect(ctx.status(), changed)
                         kwt.restrict = False
                         kwt.overwrite(ctx, modified, True, True)
                         kwt.overwrite(ctx, added, True, False)
                     return ret
                 finally:
                     kwt.restrict = origrestrict
 
     repo.__class__ = kwrepo
     repo._keywordkwt = kwt

hgext/phabricator.py

@@ -1,1256 +1,1256 b''
 # phabricator.py - simple Phabricator integration
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """simple Phabricator integration (EXPERIMENTAL)
 
 This extension provides a ``phabsend`` command which sends a stack of
 changesets to Phabricator, and a ``phabread`` command which prints a stack of
 revisions in a format suitable for :hg:`import`, and a ``phabupdate`` command
 to update statuses in batch.
 
 By default, Phabricator requires ``Test Plan`` which might prevent some
 changeset from being sent. The requirement could be disabled by changing
 ``differential.require-test-plan-field`` config server side.
 
 Config::
 
     [phabricator]
     # Phabricator URL
     url = https://phab.example.com/
 
     # Repo callsign. If a repo has a URL https://$HOST/diffusion/FOO, then its
     # callsign is "FOO".
     callsign = FOO
 
     # curl command to use. If not set (default), use builtin HTTP library to
     # communicate. If set, use the specified curl command. This could be useful
     # if you need to specify advanced options that is not easily supported by
     # the internal library.
     curlcmd = curl --connect-timeout 2 --retry 3 --silent
 
     [auth]
     example.schemes = https
     example.prefix = phab.example.com
 
     # API token. Get it from https://$HOST/conduit/login/
     example.phabtoken = cli-xxxxxxxxxxxxxxxxxxxxxxxxxxxx
 """
 
 from __future__ import absolute_import
 
 import contextlib
 import itertools
 import json
 import operator
 import re
 
 from mercurial.node import bin, nullid
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     context,
     encoding,
     error,
     exthelper,
     httpconnection as httpconnectionmod,
     mdiff,
     obsutil,
     parser,
     patch,
     phases,
     pycompat,
     scmutil,
     smartset,
     tags,
     templatefilters,
     templateutil,
     url as urlmod,
     util,
 )
 from mercurial.utils import (
     procutil,
     stringutil,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 eh = exthelper.exthelper()
 
 cmdtable = eh.cmdtable
 command = eh.command
 configtable = eh.configtable
 templatekeyword = eh.templatekeyword
 
 # developer config: phabricator.batchsize
 eh.configitem(
     b'phabricator', b'batchsize', default=12,
 )
 eh.configitem(
     b'phabricator', b'callsign', default=None,
 )
 eh.configitem(
     b'phabricator', b'curlcmd', default=None,
 )
 # developer config: phabricator.repophid
 eh.configitem(
     b'phabricator', b'repophid', default=None,
 )
 eh.configitem(
     b'phabricator', b'url', default=None,
 )
 eh.configitem(
     b'phabsend', b'confirm', default=False,
 )
 
 colortable = {
     b'phabricator.action.created': b'green',
     b'phabricator.action.skipped': b'magenta',
     b'phabricator.action.updated': b'magenta',
     b'phabricator.desc': b'',
     b'phabricator.drev': b'bold',
     b'phabricator.node': b'',
 }
 
 _VCR_FLAGS = [
     (
         b'',
         b'test-vcr',
         b'',
         _(
             b'Path to a vcr file. If nonexistent, will record a new vcr transcript'
             b', otherwise will mock all http requests using the specified vcr file.'
             b' (ADVANCED)'
         ),
     ),
 ]
 
 
 def vcrcommand(name, flags, spec, helpcategory=None, optionalrepo=False):
     fullflags = flags + _VCR_FLAGS
 
     def hgmatcher(r1, r2):
         if r1.uri != r2.uri or r1.method != r2.method:
             return False
         r1params = r1.body.split(b'&')
         r2params = r2.body.split(b'&')
         return set(r1params) == set(r2params)
 
     def sanitiserequest(request):
         request.body = re.sub(
             br'cli-[a-z0-9]+', br'cli-hahayouwish', request.body
         )
         return request
 
     def sanitiseresponse(response):
         if r'set-cookie' in response[r'headers']:
             del response[r'headers'][r'set-cookie']
         return response
 
     def decorate(fn):
         def inner(*args, **kwargs):
             cassette = pycompat.fsdecode(kwargs.pop(r'test_vcr', None))
             if cassette:
                 import hgdemandimport
 
                 with hgdemandimport.deactivated():
                     import vcr as vcrmod
                     import vcr.stubs as stubs
 
                     vcr = vcrmod.VCR(
                         serializer=r'json',
                         before_record_request=sanitiserequest,
                         before_record_response=sanitiseresponse,
                         custom_patches=[
                             (
                                 urlmod,
                                 r'httpconnection',
                                 stubs.VCRHTTPConnection,
                             ),
                             (
                                 urlmod,
                                 r'httpsconnection',
                                 stubs.VCRHTTPSConnection,
                             ),
                         ],
                     )
                     vcr.register_matcher(r'hgmatcher', hgmatcher)
                     with vcr.use_cassette(cassette, match_on=[r'hgmatcher']):
                         return fn(*args, **kwargs)
             return fn(*args, **kwargs)
 
         inner.__name__ = fn.__name__
         inner.__doc__ = fn.__doc__
         return command(
             name,
             fullflags,
             spec,
             helpcategory=helpcategory,
             optionalrepo=optionalrepo,
         )(inner)
 
     return decorate
 
 
 def urlencodenested(params):
     """like urlencode, but works with nested parameters.
 
     For example, if params is {'a': ['b', 'c'], 'd': {'e': 'f'}}, it will be
     flattened to {'a[0]': 'b', 'a[1]': 'c', 'd[e]': 'f'} and then passed to
     urlencode. Note: the encoding is consistent with PHP's http_build_query.
     """
     flatparams = util.sortdict()
 
     def process(prefix, obj):
         if isinstance(obj, bool):
             obj = {True: b'true', False: b'false'}[obj]  # Python -> PHP form
         lister = lambda l: [(b'%d' % k, v) for k, v in enumerate(l)]
         items = {list: lister, dict: lambda x: x.items()}.get(type(obj))
         if items is None:
             flatparams[prefix] = obj
         else:
             for k, v in items(obj):
                 if prefix:
                     process(b'%s[%s]' % (prefix, k), v)
                 else:
                     process(k, v)
 
     process(b'', params)
     return util.urlreq.urlencode(flatparams)
 
 
 def readurltoken(ui):
     """return conduit url, token and make sure they exist
 
     Currently read from [auth] config section. In the future, it might
     make sense to read from .arcconfig and .arcrc as well.
     """
     url = ui.config(b'phabricator', b'url')
     if not url:
         raise error.Abort(
             _(b'config %s.%s is required') % (b'phabricator', b'url')
         )
 
     res = httpconnectionmod.readauthforuri(ui, url, util.url(url).user)
     token = None
 
     if res:
         group, auth = res
 
         ui.debug(b"using auth.%s.* for authentication\n" % group)
 
         token = auth.get(b'phabtoken')
 
     if not token:
         raise error.Abort(
             _(b'Can\'t find conduit token associated to %s') % (url,)
         )
 
     return url, token
 
 
 def callconduit(ui, name, params):
     """call Conduit API, params is a dict. return json.loads result, or None"""
     host, token = readurltoken(ui)
     url, authinfo = util.url(b'/'.join([host, b'api', name])).authinfo()
     ui.debug(b'Conduit Call: %s %s\n' % (url, pycompat.byterepr(params)))
     params = params.copy()
     params[b'api.token'] = token
     data = urlencodenested(params)
     curlcmd = ui.config(b'phabricator', b'curlcmd')
     if curlcmd:
         sin, sout = procutil.popen2(
             b'%s -d @- %s' % (curlcmd, procutil.shellquote(url))
         )
         sin.write(data)
         sin.close()
         body = sout.read()
     else:
         urlopener = urlmod.opener(ui, authinfo)
         request = util.urlreq.request(pycompat.strurl(url), data=data)
         with contextlib.closing(urlopener.open(request)) as rsp:
             body = rsp.read()
     ui.debug(b'Conduit Response: %s\n' % body)
     parsed = pycompat.rapply(
         lambda x: encoding.unitolocal(x)
         if isinstance(x, pycompat.unicode)
         else x,
         # json.loads only accepts bytes from py3.6+
         json.loads(encoding.unifromlocal(body)),
     )
     if parsed.get(b'error_code'):
         msg = _(b'Conduit Error (%s): %s') % (
             parsed[b'error_code'],
             parsed[b'error_info'],
         )
         raise error.Abort(msg)
     return parsed[b'result']
 
 
 @vcrcommand(b'debugcallconduit', [], _(b'METHOD'), optionalrepo=True)
 def debugcallconduit(ui, repo, name):
     """call Conduit API
 
     Call parameters are read from stdin as a JSON blob. Result will be written
     to stdout as a JSON blob.
     """
     # json.loads only accepts bytes from 3.6+
     rawparams = encoding.unifromlocal(ui.fin.read())
     # json.loads only returns unicode strings
     params = pycompat.rapply(
         lambda x: encoding.unitolocal(x)
         if isinstance(x, pycompat.unicode)
         else x,
         json.loads(rawparams),
     )
     # json.dumps only accepts unicode strings
     result = pycompat.rapply(
         lambda x: encoding.unifromlocal(x) if isinstance(x, bytes) else x,
         callconduit(ui, name, params),
     )
     s = json.dumps(result, sort_keys=True, indent=2, separators=(u',', u': '))
     ui.write(b'%s\n' % encoding.unitolocal(s))
 
 
 def getrepophid(repo):
     """given callsign, return repository PHID or None"""
     # developer config: phabricator.repophid
     repophid = repo.ui.config(b'phabricator', b'repophid')
     if repophid:
         return repophid
     callsign = repo.ui.config(b'phabricator', b'callsign')
     if not callsign:
         return None
     query = callconduit(
         repo.ui,
         b'diffusion.repository.search',
         {b'constraints': {b'callsigns': [callsign]}},
     )
     if len(query[b'data']) == 0:
         return None
     repophid = query[b'data'][0][b'phid']
     repo.ui.setconfig(b'phabricator', b'repophid', repophid)
     return repophid
 
 
 _differentialrevisiontagre = re.compile(br'\AD([1-9][0-9]*)\Z')
 _differentialrevisiondescre = re.compile(
     br'^Differential Revision:\s*(?P<url>(?:.*)D(?P<id>[1-9][0-9]*))$', re.M
 )
 
 
 def getoldnodedrevmap(repo, nodelist):
     """find previous nodes that has been sent to Phabricator
 
     return {node: (oldnode, Differential diff, Differential Revision ID)}
     for node in nodelist with known previous sent versions, or associated
     Differential Revision IDs. ``oldnode`` and ``Differential diff`` could
     be ``None``.
 
     Examines commit messages like "Differential Revision:" to get the
     association information.
 
     If such commit message line is not found, examines all precursors and their
     tags. Tags with format like "D1234" are considered a match and the node
     with that tag, and the number after "D" (ex. 1234) will be returned.
 
     The ``old node``, if not None, is guaranteed to be the last diff of
     corresponding Differential Revision, and exist in the repo.
     """
     unfi = repo.unfiltered()
     nodemap = unfi.changelog.nodemap
 
     result = {}  # {node: (oldnode?, lastdiff?, drev)}
     toconfirm = {}  # {node: (force, {precnode}, drev)}
     for node in nodelist:
         ctx = unfi[node]
         # For tags like "D123", put them into "toconfirm" to verify later
         precnodes = list(obsutil.allpredecessors(unfi.obsstore, [node]))
         for n in precnodes:
             if n in nodemap:
                 for tag in unfi.nodetags(n):
                     m = _differentialrevisiontagre.match(tag)
                     if m:
                         toconfirm[node] = (0, set(precnodes), int(m.group(1)))
                         continue
 
         # Check commit message
         m = _differentialrevisiondescre.search(ctx.description())
         if m:
             toconfirm[node] = (1, set(precnodes), int(m.group(r'id')))
 
     # Double check if tags are genuine by collecting all old nodes from
     # Phabricator, and expect precursors overlap with it.
     if toconfirm:
         drevs = [drev for force, precs, drev in toconfirm.values()]
         alldiffs = callconduit(
             unfi.ui, b'differential.querydiffs', {b'revisionIDs': drevs}
         )
         getnode = lambda d: bin(getdiffmeta(d).get(b'node', b'')) or None
         for newnode, (force, precset, drev) in toconfirm.items():
             diffs = [
                 d for d in alldiffs.values() if int(d[b'revisionID']) == drev
             ]
 
             # "precursors" as known by Phabricator
             phprecset = set(getnode(d) for d in diffs)
 
             # Ignore if precursors (Phabricator and local repo) do not overlap,
             # and force is not set (when commit message says nothing)
             if not force and not bool(phprecset & precset):
                 tagname = b'D%d' % drev
                 tags.tag(
                     repo,
                     tagname,
                     nullid,
                     message=None,
                     user=None,
                     date=None,
                     local=True,
                 )
                 unfi.ui.warn(
                     _(
                         b'D%s: local tag removed - does not match '
                         b'Differential history\n'
                     )
                     % drev
                 )
                 continue
 
             # Find the last node using Phabricator metadata, and make sure it
             # exists in the repo
             oldnode = lastdiff = None
             if diffs:
                 lastdiff = max(diffs, key=lambda d: int(d[b'id']))
                 oldnode = getnode(lastdiff)
                 if oldnode and oldnode not in nodemap:
                     oldnode = None
 
             result[newnode] = (oldnode, lastdiff, drev)
 
     return result
 
 
 def getdiff(ctx, diffopts):
     """plain-text diff without header (user, commit message, etc)"""
     output = util.stringio()
     for chunk, _label in patch.diffui(
         ctx.repo(), ctx.p1().node(), ctx.node(), None, opts=diffopts
     ):
         output.write(chunk)
     return output.getvalue()
 
 
 def creatediff(ctx):
     """create a Differential Diff"""
     repo = ctx.repo()
     repophid = getrepophid(repo)
     # Create a "Differential Diff" via "differential.createrawdiff" API
     params = {b'diff': getdiff(ctx, mdiff.diffopts(git=True, context=32767))}
     if repophid:
         params[b'repositoryPHID'] = repophid
     diff = callconduit(repo.ui, b'differential.createrawdiff', params)
     if not diff:
         raise error.Abort(_(b'cannot create diff for %s') % ctx)
     return diff
 
 
 def writediffproperties(ctx, diff):
     """write metadata to diff so patches could be applied losslessly"""
     params = {
         b'diff_id': diff[b'id'],
         b'name': b'hg:meta',
         b'data': templatefilters.json(
             {
                 b'user': ctx.user(),
                 b'date': b'%d %d' % ctx.date(),
                 b'branch': ctx.branch(),
                 b'node': ctx.hex(),
                 b'parent': ctx.p1().hex(),
             }
         ),
     }
     callconduit(ctx.repo().ui, b'differential.setdiffproperty', params)
 
     params = {
         b'diff_id': diff[b'id'],
         b'name': b'local:commits',
         b'data': templatefilters.json(
             {
                 ctx.hex(): {
                     b'author': stringutil.person(ctx.user()),
                     b'authorEmail': stringutil.email(ctx.user()),
                     b'time': int(ctx.date()[0]),
                     b'commit': ctx.hex(),
                     b'parents': [ctx.p1().hex()],
                     b'branch': ctx.branch(),
                 },
             }
         ),
     }
     callconduit(ctx.repo().ui, b'differential.setdiffproperty', params)
 
 
 def createdifferentialrevision(
     ctx,
     revid=None,
     parentrevphid=None,
     oldnode=None,
     olddiff=None,
     actions=None,
     comment=None,
 ):
     """create or update a Differential Revision
 
     If revid is None, create a new Differential Revision, otherwise update
     revid. If parentrevphid is not None, set it as a dependency.
 
     If oldnode is not None, check if the patch content (without commit message
     and metadata) has changed before creating another diff.
 
     If actions is not None, they will be appended to the transaction.
     """
     repo = ctx.repo()
     if oldnode:
         diffopts = mdiff.diffopts(git=True, context=32767)
         oldctx = repo.unfiltered()[oldnode]
         neednewdiff = getdiff(ctx, diffopts) != getdiff(oldctx, diffopts)
     else:
         neednewdiff = True
 
     transactions = []
     if neednewdiff:
         diff = creatediff(ctx)
         transactions.append({b'type': b'update', b'value': diff[b'phid']})
         if comment:
             transactions.append({b'type': b'comment', b'value': comment})
     else:
         # Even if we don't need to upload a new diff because the patch content
         # does not change. We might still need to update its metadata so
         # pushers could know the correct node metadata.
         assert olddiff
         diff = olddiff
     writediffproperties(ctx, diff)
 
     # Set the parent Revision every time, so commit re-ordering is picked-up
     if parentrevphid:
         transactions.append(
             {b'type': b'parents.set', b'value': [parentrevphid]}
         )
 
     if actions:
         transactions += actions
 
     # Parse commit message and update related fields.
     desc = ctx.description()
     info = callconduit(
         repo.ui, b'differential.parsecommitmessage', {b'corpus': desc}
     )
     for k, v in info[b'fields'].items():
         if k in [b'title', b'summary', b'testPlan']:
             transactions.append({b'type': k, b'value': v})
 
     params = {b'transactions': transactions}
     if revid is not None:
         # Update an existing Differential Revision
         params[b'objectIdentifier'] = revid
 
     revision = callconduit(repo.ui, b'differential.revision.edit', params)
     if not revision:
         raise error.Abort(_(b'cannot create revision for %s') % ctx)
 
     return revision, diff
 
 
 def userphids(repo, names):
     """convert user names to PHIDs"""
     names = [name.lower() for name in names]
     query = {b'constraints': {b'usernames': names}}
     result = callconduit(repo.ui, b'user.search', query)
     # username not found is not an error of the API. So check if we have missed
     # some names here.
     data = result[b'data']
     resolved = set(entry[b'fields'][b'username'].lower() for entry in data)
     unresolved = set(names) - resolved
     if unresolved:
         raise error.Abort(
             _(b'unknown username: %s') % b' '.join(sorted(unresolved))
         )
     return [entry[b'phid'] for entry in data]
 
 
 @vcrcommand(
     b'phabsend',
     [
         (b'r', b'rev', [], _(b'revisions to send'), _(b'REV')),
         (b'', b'amend', True, _(b'update commit messages')),
         (b'', b'reviewer', [], _(b'specify reviewers')),
         (b'', b'blocker', [], _(b'specify blocking reviewers')),
         (
             b'm',
             b'comment',
             b'',
             _(b'add a comment to Revisions with new/updated Diffs'),
         ),
         (b'', b'confirm', None, _(b'ask for confirmation before sending')),
     ],
     _(b'REV [OPTIONS]'),
     helpcategory=command.CATEGORY_IMPORT_EXPORT,
 )
 def phabsend(ui, repo, *revs, **opts):
     """upload changesets to Phabricator
 
     If there are multiple revisions specified, they will be send as a stack
     with a linear dependencies relationship using the order specified by the
     revset.
 
     For the first time uploading changesets, local tags will be created to
     maintain the association. After the first time, phabsend will check
     obsstore and tags information so it can figure out whether to update an
     existing Differential Revision, or create a new one.
 
     If --amend is set, update commit messages so they have the
     ``Differential Revision`` URL, remove related tags. This is similar to what
     arcanist will do, and is more desired in author-push workflows. Otherwise,
     use local tags to record the ``Differential Revision`` association.
 
     The --confirm option lets you confirm changesets before sending them. You
     can also add following to your configuration file to make it default
     behaviour::
 
         [phabsend]
         confirm = true
 
     phabsend will check obsstore and the above association to decide whether to
     update an existing Differential Revision, or create a new one.
     """
     opts = pycompat.byteskwargs(opts)
     revs = list(revs) + opts.get(b'rev', [])
     revs = scmutil.revrange(repo, revs)
 
     if not revs:
         raise error.Abort(_(b'phabsend requires at least one changeset'))
     if opts.get(b'amend'):
         cmdutil.checkunfinished(repo)
 
     # {newnode: (oldnode, olddiff, olddrev}
     oldmap = getoldnodedrevmap(repo, [repo[r].node() for r in revs])
 
     confirm = ui.configbool(b'phabsend', b'confirm')
     confirm |= bool(opts.get(b'confirm'))
     if confirm:
         confirmed = _confirmbeforesend(repo, revs, oldmap)
         if not confirmed:
             raise error.Abort(_(b'phabsend cancelled'))
 
     actions = []
     reviewers = opts.get(b'reviewer', [])
     blockers = opts.get(b'blocker', [])
     phids = []
     if reviewers:
         phids.extend(userphids(repo, reviewers))
     if blockers:
         phids.extend(
             map(lambda phid: b'blocking(%s)' % phid, userphids(repo, blockers))
         )
     if phids:
         actions.append({b'type': b'reviewers.add', b'value': phids})
 
     drevids = []  # [int]
     diffmap = {}  # {newnode: diff}
 
     # Send patches one by one so we know their Differential Revision PHIDs and
     # can provide dependency relationship
     lastrevphid = None
     for rev in revs:
         ui.debug(b'sending rev %d\n' % rev)
         ctx = repo[rev]
 
         # Get Differential Revision ID
         oldnode, olddiff, revid = oldmap.get(ctx.node(), (None, None, None))
         if oldnode != ctx.node() or opts.get(b'amend'):
             # Create or update Differential Revision
             revision, diff = createdifferentialrevision(
                 ctx,
                 revid,
                 lastrevphid,
                 oldnode,
                 olddiff,
                 actions,
                 opts.get(b'comment'),
             )
             diffmap[ctx.node()] = diff
             newrevid = int(revision[b'object'][b'id'])
             newrevphid = revision[b'object'][b'phid']
             if revid:
                 action = b'updated'
             else:
                 action = b'created'
 
             # Create a local tag to note the association, if commit message
             # does not have it already
             m = _differentialrevisiondescre.search(ctx.description())
             if not m or int(m.group(r'id')) != newrevid:
                 tagname = b'D%d' % newrevid
                 tags.tag(
                     repo,
                     tagname,
                     ctx.node(),
                     message=None,
                     user=None,
                     date=None,
                     local=True,
                 )
         else:
             # Nothing changed. But still set "newrevphid" so the next revision
             # could depend on this one and "newrevid" for the summary line.
             newrevphid = querydrev(repo, b'%d' % revid)[0][b'phid']
             newrevid = revid
             action = b'skipped'
 
         actiondesc = ui.label(
             {
                 b'created': _(b'created'),
                 b'skipped': _(b'skipped'),
                 b'updated': _(b'updated'),
             }[action],
             b'phabricator.action.%s' % action,
         )
         drevdesc = ui.label(b'D%d' % newrevid, b'phabricator.drev')
         nodedesc = ui.label(bytes(ctx), b'phabricator.node')
         desc = ui.label(ctx.description().split(b'\n')[0], b'phabricator.desc')
         ui.write(
             _(b'%s - %s - %s: %s\n') % (drevdesc, actiondesc, nodedesc, desc)
         )
         drevids.append(newrevid)
         lastrevphid = newrevphid
 
     # Update commit messages and remove tags
     if opts.get(b'amend'):
         unfi = repo.unfiltered()
         drevs = callconduit(ui, b'differential.query', {b'ids': drevids})
         with repo.wlock(), repo.lock(), repo.transaction(b'phabsend'):
             wnode = unfi[b'.'].node()
             mapping = {}  # {oldnode: [newnode]}
             for i, rev in enumerate(revs):
                 old = unfi[rev]
                 drevid = drevids[i]
                 drev = [d for d in drevs if int(d[b'id']) == drevid][0]
                 newdesc = getdescfromdrev(drev)
                 # Make sure commit message contain "Differential Revision"
                 if old.description() != newdesc:
                     if old.phase() == phases.public:
                         ui.warn(
                             _(b"warning: not updating public commit %s\n")
                             % scmutil.formatchangeid(old)
                         )
                         continue
                     parents = [
                         mapping.get(old.p1().node(), (old.p1(),))[0],
                         mapping.get(old.p2().node(), (old.p2(),))[0],
                     ]
                     new = context.metadataonlyctx(
                         repo,
                         old,
                         parents=parents,
                         text=newdesc,
                         user=old.user(),
                         date=old.date(),
                         extra=old.extra(),
                     )
 
                     newnode = new.commit()
 
                     mapping[old.node()] = [newnode]
                     # Update diff property
                     # If it fails just warn and keep going, otherwise the DREV
                     # associations will be lost
                     try:
                         writediffproperties(unfi[newnode], diffmap[old.node()])
                     except util.urlerr.urlerror:
-                        ui.warn(b'Failed to update metadata for D%s\n' % drevid)
+                        ui.warnnoi18n(b'Failed to update metadata for D%s\n' % drevid)
                 # Remove local tags since it's no longer necessary
                 tagname = b'D%d' % drevid
                 if tagname in repo.tags():
                     tags.tag(
                         repo,
                         tagname,
                         nullid,
                         message=None,
                         user=None,
                         date=None,
                         local=True,
                     )
             scmutil.cleanupnodes(repo, mapping, b'phabsend', fixphase=True)
             if wnode in mapping:
                 unfi.setparents(mapping[wnode][0])
 
 
 # Map from "hg:meta" keys to header understood by "hg import". The order is
 # consistent with "hg export" output.
 _metanamemap = util.sortdict(
     [
         (b'user', b'User'),
         (b'date', b'Date'),
         (b'branch', b'Branch'),
         (b'node', b'Node ID'),
         (b'parent', b'Parent '),
     ]
 )
 
 
 def _confirmbeforesend(repo, revs, oldmap):
     url, token = readurltoken(repo.ui)
     ui = repo.ui
     for rev in revs:
         ctx = repo[rev]
         desc = ctx.description().splitlines()[0]
         oldnode, olddiff, drevid = oldmap.get(ctx.node(), (None, None, None))
         if drevid:
             drevdesc = ui.label(b'D%s' % drevid, b'phabricator.drev')
         else:
             drevdesc = ui.label(_(b'NEW'), b'phabricator.drev')
 
         ui.write(
             _(b'%s - %s: %s\n')
             % (
                 drevdesc,
                 ui.label(bytes(ctx), b'phabricator.node'),
                 ui.label(desc, b'phabricator.desc'),
             )
         )
 
     if ui.promptchoice(
         _(b'Send the above changes to %s (yn)?' b'$$ &Yes $$ &No') % url
     ):
         return False
 
     return True
 
 
 _knownstatusnames = {
     b'accepted',
     b'needsreview',
     b'needsrevision',
     b'closed',
     b'abandoned',
 }
 
 
 def _getstatusname(drev):
     """get normalized status name from a Differential Revision"""
     return drev[b'statusName'].replace(b' ', b'').lower()
 
 
 # Small language to specify differential revisions. Support symbols: (), :X,
 # +, and -.
 
 _elements = {
     # token-type: binding-strength, primary, prefix, infix, suffix
     b'(': (12, None, (b'group', 1, b')'), None, None),
     b':': (8, None, (b'ancestors', 8), None, None),
     b'&': (5, None, None, (b'and_', 5), None),
     b'+': (4, None, None, (b'add', 4), None),
     b'-': (4, None, None, (b'sub', 4), None),
     b')': (0, None, None, None, None),
     b'symbol': (0, b'symbol', None, None, None),
     b'end': (0, None, None, None, None),
 }
 
 
 def _tokenize(text):
     view = memoryview(text)  # zero-copy slice
     special = b'():+-& '
     pos = 0
     length = len(text)
     while pos < length:
         symbol = b''.join(
             itertools.takewhile(
                 lambda ch: ch not in special, pycompat.iterbytestr(view[pos:])
             )
         )
         if symbol:
             yield (b'symbol', symbol, pos)
             pos += len(symbol)
         else:  # special char, ignore space
             if text[pos] != b' ':
                 yield (text[pos], None, pos)
             pos += 1
     yield (b'end', None, pos)
 
 
 def _parse(text):
     tree, pos = parser.parser(_elements).parse(_tokenize(text))
     if pos != len(text):
         raise error.ParseError(b'invalid token', pos)
     return tree
 
 
 def _parsedrev(symbol):
     """str -> int or None, ex. 'D45' -> 45; '12' -> 12; 'x' -> None"""
     if symbol.startswith(b'D') and symbol[1:].isdigit():
         return int(symbol[1:])
     if symbol.isdigit():
         return int(symbol)
 
 
 def _prefetchdrevs(tree):
     """return ({single-drev-id}, {ancestor-drev-id}) to prefetch"""
     drevs = set()
     ancestordrevs = set()
     op = tree[0]
     if op == b'symbol':
         r = _parsedrev(tree[1])
         if r:
             drevs.add(r)
     elif op == b'ancestors':
         r, a = _prefetchdrevs(tree[1])
         drevs.update(r)
         ancestordrevs.update(r)
         ancestordrevs.update(a)
     else:
         for t in tree[1:]:
             r, a = _prefetchdrevs(t)
             drevs.update(r)
             ancestordrevs.update(a)
     return drevs, ancestordrevs
 
 
 def querydrev(repo, spec):
     """return a list of "Differential Revision" dicts
 
     spec is a string using a simple query language, see docstring in phabread
     for details.
 
     A "Differential Revision dict" looks like:
 
         {
             "id": "2",
             "phid": "PHID-DREV-672qvysjcczopag46qty",
             "title": "example",
             "uri": "https://phab.example.com/D2",
             "dateCreated": "1499181406",
             "dateModified": "1499182103",
             "authorPHID": "PHID-USER-tv3ohwc4v4jeu34otlye",
             "status": "0",
             "statusName": "Needs Review",
             "properties": [],
             "branch": null,
             "summary": "",
             "testPlan": "",
             "lineCount": "2",
             "activeDiffPHID": "PHID-DIFF-xoqnjkobbm6k4dk6hi72",
             "diffs": [
               "3",
               "4",
             ],
             "commits": [],
             "reviewers": [],
             "ccs": [],
             "hashes": [],
             "auxiliary": {
               "phabricator:projects": [],
               "phabricator:depends-on": [
                 "PHID-DREV-gbapp366kutjebt7agcd"
               ]
             },
             "repositoryPHID": "PHID-REPO-hub2hx62ieuqeheznasv",
             "sourcePath": null
         }
     """
 
     def fetch(params):
         """params -> single drev or None"""
         key = (params.get(b'ids') or params.get(b'phids') or [None])[0]
         if key in prefetched:
             return prefetched[key]
         drevs = callconduit(repo.ui, b'differential.query', params)
         # Fill prefetched with the result
         for drev in drevs:
             prefetched[drev[b'phid']] = drev
             prefetched[int(drev[b'id'])] = drev
         if key not in prefetched:
             raise error.Abort(
                 _(b'cannot get Differential Revision %r') % params
             )
         return prefetched[key]
 
     def getstack(topdrevids):
         """given a top, get a stack from the bottom, [id] -> [id]"""
         visited = set()
         result = []
         queue = [{b'ids': [i]} for i in topdrevids]
         while queue:
             params = queue.pop()
             drev = fetch(params)
             if drev[b'id'] in visited:
                 continue
             visited.add(drev[b'id'])
             result.append(int(drev[b'id']))
             auxiliary = drev.get(b'auxiliary', {})
             depends = auxiliary.get(b'phabricator:depends-on', [])
             for phid in depends:
                 queue.append({b'phids': [phid]})
         result.reverse()
         return smartset.baseset(result)
 
     # Initialize prefetch cache
     prefetched = {}  # {id or phid: drev}
 
     tree = _parse(spec)
     drevs, ancestordrevs = _prefetchdrevs(tree)
 
     # developer config: phabricator.batchsize
     batchsize = repo.ui.configint(b'phabricator', b'batchsize')
 
     # Prefetch Differential Revisions in batch
     tofetch = set(drevs)
     for r in ancestordrevs:
         tofetch.update(range(max(1, r - batchsize), r + 1))
     if drevs:
         fetch({b'ids': list(tofetch)})
     validids = sorted(set(getstack(list(ancestordrevs))) | set(drevs))
 
     # Walk through the tree, return smartsets
     def walk(tree):
         op = tree[0]
         if op == b'symbol':
             drev = _parsedrev(tree[1])
             if drev:
                 return smartset.baseset([drev])
             elif tree[1] in _knownstatusnames:
                 drevs = [
                     r
                     for r in validids
                     if _getstatusname(prefetched[r]) == tree[1]
                 ]
                 return smartset.baseset(drevs)
             else:
                 raise error.Abort(_(b'unknown symbol: %s') % tree[1])
         elif op in {b'and_', b'add', b'sub'}:
             assert len(tree) == 3
             return getattr(operator, op)(walk(tree[1]), walk(tree[2]))
         elif op == b'group':
             return walk(tree[1])
         elif op == b'ancestors':
             return getstack(walk(tree[1]))
         else:
             raise error.ProgrammingError(b'illegal tree: %r' % tree)
 
     return [prefetched[r] for r in walk(tree)]
 
 
 def getdescfromdrev(drev):
     """get description (commit message) from "Differential Revision"
 
     This is similar to differential.getcommitmessage API. But we only care
     about limited fields: title, summary, test plan, and URL.
     """
     title = drev[b'title']
     summary = drev[b'summary'].rstrip()
     testplan = drev[b'testPlan'].rstrip()
     if testplan:
         testplan = b'Test Plan:\n%s' % testplan
     uri = b'Differential Revision: %s' % drev[b'uri']
     return b'\n\n'.join(filter(None, [title, summary, testplan, uri]))
 
 
 def getdiffmeta(diff):
     """get commit metadata (date, node, user, p1) from a diff object
 
     The metadata could be "hg:meta", sent by phabsend, like:
 
         "properties": {
           "hg:meta": {
             "date": "1499571514 25200",
             "node": "98c08acae292b2faf60a279b4189beb6cff1414d",
             "user": "Foo Bar <[e-mail]>",
             "parent": "6d0abad76b30e4724a37ab8721d630394070fe16"
           }
         }
 
     Or converted from "local:commits", sent by "arc", like:
 
         "properties": {
           "local:commits": {
             "98c08acae292b2faf60a279b4189beb6cff1414d": {
               "author": "Foo Bar",
               "time": 1499546314,
               "branch": "default",
               "tag": "",
               "commit": "98c08acae292b2faf60a279b4189beb6cff1414d",
               "rev": "98c08acae292b2faf60a279b4189beb6cff1414d",
               "local": "1000",
               "parents": ["6d0abad76b30e4724a37ab8721d630394070fe16"],
               "summary": "...",
               "message": "...",
               "authorEmail": "[e-mail]"
             }
           }
         }
 
     Note: metadata extracted from "local:commits" will lose time zone
     information.
     """
     props = diff.get(b'properties') or {}
     meta = props.get(b'hg:meta')
     if not meta:
         if props.get(b'local:commits'):
             commit = sorted(props[b'local:commits'].values())[0]
             meta = {}
             if b'author' in commit and b'authorEmail' in commit:
                 meta[b'user'] = b'%s <%s>' % (
                     commit[b'author'],
                     commit[b'authorEmail'],
                 )
             if b'time' in commit:
                 meta[b'date'] = b'%d 0' % int(commit[b'time'])
             if b'branch' in commit:
                 meta[b'branch'] = commit[b'branch']
             node = commit.get(b'commit', commit.get(b'rev'))
             if node:
                 meta[b'node'] = node
             if len(commit.get(b'parents', ())) >= 1:
                 meta[b'parent'] = commit[b'parents'][0]
         else:
             meta = {}
     if b'date' not in meta and b'dateCreated' in diff:
         meta[b'date'] = b'%s 0' % diff[b'dateCreated']
     if b'branch' not in meta and diff.get(b'branch'):
         meta[b'branch'] = diff[b'branch']
     if b'parent' not in meta and diff.get(b'sourceControlBaseRevision'):
         meta[b'parent'] = diff[b'sourceControlBaseRevision']
     return meta
 
 
 def readpatch(repo, drevs, write):
     """generate plain-text patch readable by 'hg import'
 
     write is usually ui.write. drevs is what "querydrev" returns, results of
     "differential.query".
     """
     # Prefetch hg:meta property for all diffs
     diffids = sorted(set(max(int(v) for v in drev[b'diffs']) for drev in drevs))
     diffs = callconduit(repo.ui, b'differential.querydiffs', {b'ids': diffids})
 
     # Generate patch for each drev
     for drev in drevs:
         repo.ui.note(_(b'reading D%s\n') % drev[b'id'])
 
         diffid = max(int(v) for v in drev[b'diffs'])
         body = callconduit(
             repo.ui, b'differential.getrawdiff', {b'diffID': diffid}
         )
         desc = getdescfromdrev(drev)
         header = b'# HG changeset patch\n'
 
         # Try to preserve metadata from hg:meta property. Write hg patch
         # headers that can be read by the "import" command. See patchheadermap
         # and extract in mercurial/patch.py for supported headers.
         meta = getdiffmeta(diffs[b'%d' % diffid])
         for k in _metanamemap.keys():
             if k in meta:
                 header += b'# %s %s\n' % (_metanamemap[k], meta[k])
 
         content = b'%s%s\n%s' % (header, desc, body)
         write(content)
 
 
 @vcrcommand(
     b'phabread',
     [(b'', b'stack', False, _(b'read dependencies'))],
     _(b'DREVSPEC [OPTIONS]'),
     helpcategory=command.CATEGORY_IMPORT_EXPORT,
 )
 def phabread(ui, repo, spec, **opts):
     """print patches from Phabricator suitable for importing
 
     DREVSPEC could be a Differential Revision identity, like ``D123``, or just
     the number ``123``. It could also have common operators like ``+``, ``-``,
     ``&``, ``(``, ``)`` for complex queries. Prefix ``:`` could be used to
     select a stack.
 
     ``abandoned``, ``accepted``, ``closed``, ``needsreview``, ``needsrevision``
     could be used to filter patches by status. For performance reason, they
     only represent a subset of non-status selections and cannot be used alone.
 
     For example, ``:D6+8-(2+D4)`` selects a stack up to D6, plus D8 and exclude
     D2 and D4. ``:D9 & needsreview`` selects "Needs Review" revisions in a
     stack up to D9.
 
     If --stack is given, follow dependencies information and read all patches.
     It is equivalent to the ``:`` operator.
     """
     opts = pycompat.byteskwargs(opts)
     if opts.get(b'stack'):
         spec = b':(%s)' % spec
     drevs = querydrev(repo, spec)
     readpatch(repo, drevs, ui.write)
 
 
 @vcrcommand(
     b'phabupdate',
     [
         (b'', b'accept', False, _(b'accept revisions')),
         (b'', b'reject', False, _(b'reject revisions')),
         (b'', b'abandon', False, _(b'abandon revisions')),
         (b'', b'reclaim', False, _(b'reclaim revisions')),
         (b'm', b'comment', b'', _(b'comment on the last revision')),
     ],
     _(b'DREVSPEC [OPTIONS]'),
     helpcategory=command.CATEGORY_IMPORT_EXPORT,
 )
 def phabupdate(ui, repo, spec, **opts):
     """update Differential Revision in batch
 
     DREVSPEC selects revisions. See :hg:`help phabread` for its usage.
     """
     opts = pycompat.byteskwargs(opts)
     flags = [n for n in b'accept reject abandon reclaim'.split() if opts.get(n)]
     if len(flags) > 1:
         raise error.Abort(_(b'%s cannot be used together') % b', '.join(flags))
 
     actions = []
     for f in flags:
         actions.append({b'type': f, b'value': b'true'})
 
     drevs = querydrev(repo, spec)
     for i, drev in enumerate(drevs):
         if i + 1 == len(drevs) and opts.get(b'comment'):
             actions.append({b'type': b'comment', b'value': opts[b'comment']})
         if actions:
             params = {
                 b'objectIdentifier': drev[b'phid'],
                 b'transactions': actions,
             }
             callconduit(ui, b'differential.revision.edit', params)
 
 
 @eh.templatekeyword(b'phabreview', requires={b'ctx'})
 def template_review(context, mapping):
     """:phabreview: Object describing the review for this changeset.
     Has attributes `url` and `id`.
     """
     ctx = context.resource(mapping, b'ctx')
     m = _differentialrevisiondescre.search(ctx.description())
     if m:
         return templateutil.hybriddict(
             {b'url': m.group(r'url'), b'id': b"D%s" % m.group(r'id'),}
         )
     else:
         tags = ctx.repo().nodetags(ctx.node())
         for t in tags:
             if _differentialrevisiontagre.match(t):
                 url = ctx.repo().ui.config(b'phabricator', b'url')
                 if not url.endswith(b'/'):
                     url += b'/'
                 url += t
 
                 return templateutil.hybriddict({b'url': url, b'id': t,})
     return None

hgext/remotefilelog/debugcommands.py

@@ -1,476 +1,476 b''
 # debugcommands.py - debug logic for remotefilelog
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import hashlib
 import os
 import zlib
 
 from mercurial.node import bin, hex, nullid, short
 from mercurial.i18n import _
 from mercurial import (
     error,
     filelog,
     lock as lockmod,
     node as nodemod,
     pycompat,
     revlog,
 )
 from . import (
     constants,
     datapack,
     fileserverclient,
     historypack,
     repack,
     shallowutil,
 )
 
 
 def debugremotefilelog(ui, path, **opts):
     decompress = opts.get(r'decompress')
 
     size, firstnode, mapping = parsefileblob(path, decompress)
 
     ui.status(_(b"size: %d bytes\n") % size)
     ui.status(_(b"path: %s \n") % path)
     ui.status(_(b"key: %s \n") % (short(firstnode)))
     ui.status(_(b"\n"))
     ui.status(
         _(b"%12s => %12s %13s %13s %12s\n")
         % (b"node", b"p1", b"p2", b"linknode", b"copyfrom")
     )
 
     queue = [firstnode]
     while queue:
         node = queue.pop(0)
         p1, p2, linknode, copyfrom = mapping[node]
         ui.status(
             _(b"%s => %s  %s  %s  %s\n")
             % (short(node), short(p1), short(p2), short(linknode), copyfrom)
         )
         if p1 != nullid:
             queue.append(p1)
         if p2 != nullid:
             queue.append(p2)
 
 
 def buildtemprevlog(repo, file):
     # get filename key
     filekey = nodemod.hex(hashlib.sha1(file).digest())
     filedir = os.path.join(repo.path, b'store/data', filekey)
 
     # sort all entries based on linkrev
     fctxs = []
     for filenode in os.listdir(filedir):
         if b'_old' not in filenode:
             fctxs.append(repo.filectx(file, fileid=bin(filenode)))
 
     fctxs = sorted(fctxs, key=lambda x: x.linkrev())
 
     # add to revlog
     temppath = repo.sjoin(b'data/temprevlog.i')
     if os.path.exists(temppath):
         os.remove(temppath)
     r = filelog.filelog(repo.svfs, b'temprevlog')
 
     class faket(object):
         def add(self, a, b, c):
             pass
 
     t = faket()
     for fctx in fctxs:
         if fctx.node() not in repo:
             continue
 
         p = fctx.filelog().parents(fctx.filenode())
         meta = {}
         if fctx.renamed():
             meta[b'copy'] = fctx.renamed()[0]
             meta[b'copyrev'] = hex(fctx.renamed()[1])
 
         r.add(fctx.data(), meta, t, fctx.linkrev(), p[0], p[1])
 
     return r
 
 
 def debugindex(orig, ui, repo, file_=None, **opts):
     """dump the contents of an index file"""
     if (
         opts.get(r'changelog')
         or opts.get(r'manifest')
         or opts.get(r'dir')
         or not shallowutil.isenabled(repo)
         or not repo.shallowmatch(file_)
     ):
         return orig(ui, repo, file_, **opts)
 
     r = buildtemprevlog(repo, file_)
 
     # debugindex like normal
     format = opts.get(b'format', 0)
     if format not in (0, 1):
         raise error.Abort(_(b"unknown format %d") % format)
 
     generaldelta = r.version & revlog.FLAG_GENERALDELTA
     if generaldelta:
         basehdr = b' delta'
     else:
         basehdr = b'  base'
 
     if format == 0:
         ui.write(
             (
                 b"   rev    offset  length " + basehdr + b" linkrev"
                 b" nodeid       p1           p2\n"
             )
         )
     elif format == 1:
         ui.write(
             (
                 b"   rev flag   offset   length"
                 b"     size " + basehdr + b"   link     p1     p2"
                 b"       nodeid\n"
             )
         )
 
     for i in r:
         node = r.node(i)
         if generaldelta:
             base = r.deltaparent(i)
         else:
             base = r.chainbase(i)
         if format == 0:
             try:
                 pp = r.parents(node)
             except Exception:
                 pp = [nullid, nullid]
             ui.write(
                 b"% 6d % 9d % 7d % 6d % 7d %s %s %s\n"
                 % (
                     i,
                     r.start(i),
                     r.length(i),
                     base,
                     r.linkrev(i),
                     short(node),
                     short(pp[0]),
                     short(pp[1]),
                 )
             )
         elif format == 1:
             pr = r.parentrevs(i)
             ui.write(
                 b"% 6d %04x % 8d % 8d % 8d % 6d % 6d % 6d % 6d %s\n"
                 % (
                     i,
                     r.flags(i),
                     r.start(i),
                     r.length(i),
                     r.rawsize(i),
                     base,
                     r.linkrev(i),
                     pr[0],
                     pr[1],
                     short(node),
                 )
             )
 
 
 def debugindexdot(orig, ui, repo, file_):
     """dump an index DAG as a graphviz dot file"""
     if not shallowutil.isenabled(repo):
         return orig(ui, repo, file_)
 
     r = buildtemprevlog(repo, os.path.basename(file_)[:-2])
 
-    ui.write(b"digraph G {\n")
+    ui.writenoi18n(b"digraph G {\n")
     for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write(b"\t%d -> %d\n" % (r.rev(pp[0]), i))
         if pp[1] != nullid:
             ui.write(b"\t%d -> %d\n" % (r.rev(pp[1]), i))
     ui.write(b"}\n")
 
 
 def verifyremotefilelog(ui, path, **opts):
     decompress = opts.get(r'decompress')
 
     for root, dirs, files in os.walk(path):
         for file in files:
             if file == b"repos":
                 continue
             filepath = os.path.join(root, file)
             size, firstnode, mapping = parsefileblob(filepath, decompress)
             for p1, p2, linknode, copyfrom in mapping.itervalues():
                 if linknode == nullid:
                     actualpath = os.path.relpath(root, path)
                     key = fileserverclient.getcachekey(
                         b"reponame", actualpath, file
                     )
                     ui.status(
                         b"%s %s\n" % (key, os.path.relpath(filepath, path))
                     )
 
 
 def _decompressblob(raw):
     return zlib.decompress(raw)
 
 
 def parsefileblob(path, decompress):
     f = open(path, b"rb")
     try:
         raw = f.read()
     finally:
         f.close()
 
     if decompress:
         raw = _decompressblob(raw)
 
     offset, size, flags = shallowutil.parsesizeflags(raw)
     start = offset + size
 
     firstnode = None
 
     mapping = {}
     while start < len(raw):
         divider = raw.index(b'\0', start + 80)
 
         currentnode = raw[start : (start + 20)]
         if not firstnode:
             firstnode = currentnode
 
         p1 = raw[(start + 20) : (start + 40)]
         p2 = raw[(start + 40) : (start + 60)]
         linknode = raw[(start + 60) : (start + 80)]
         copyfrom = raw[(start + 80) : divider]
 
         mapping[currentnode] = (p1, p2, linknode, copyfrom)
         start = divider + 1
 
     return size, firstnode, mapping
 
 
 def debugdatapack(ui, *paths, **opts):
     for path in paths:
         if b'.data' in path:
             path = path[: path.index(b'.data')]
         ui.write(b"%s:\n" % path)
         dpack = datapack.datapack(path)
         node = opts.get(r'node')
         if node:
             deltachain = dpack.getdeltachain(b'', bin(node))
             dumpdeltachain(ui, deltachain, **opts)
             return
 
         if opts.get(r'long'):
             hashformatter = hex
             hashlen = 42
         else:
             hashformatter = short
             hashlen = 14
 
         lastfilename = None
         totaldeltasize = 0
         totalblobsize = 0
 
         def printtotals():
             if lastfilename is not None:
                 ui.write(b"\n")
             if not totaldeltasize or not totalblobsize:
                 return
             difference = totalblobsize - totaldeltasize
             deltastr = b"%0.1f%% %s" % (
                 (100.0 * abs(difference) / totalblobsize),
                 (b"smaller" if difference > 0 else b"bigger"),
             )
 
-            ui.write(
+            ui.writenoi18n(
                 b"Total:%s%s  %s (%s)\n"
                 % (
                     b"".ljust(2 * hashlen - len(b"Total:")),
                     (b'%d' % totaldeltasize).ljust(12),
                     (b'%d' % totalblobsize).ljust(9),
                     deltastr,
                 )
             )
 
         bases = {}
         nodes = set()
         failures = 0
         for filename, node, deltabase, deltalen in dpack.iterentries():
             bases[node] = deltabase
             if node in nodes:
                 ui.write((b"Bad entry: %s appears twice\n" % short(node)))
                 failures += 1
             nodes.add(node)
             if filename != lastfilename:
                 printtotals()
                 name = b'(empty name)' if filename == b'' else filename
                 ui.write(b"%s:\n" % name)
                 ui.write(
                     b"%s%s%s%s\n"
                     % (
                         b"Node".ljust(hashlen),
                         b"Delta Base".ljust(hashlen),
                         b"Delta Length".ljust(14),
                         b"Blob Size".ljust(9),
                     )
                 )
                 lastfilename = filename
                 totalblobsize = 0
                 totaldeltasize = 0
 
             # Metadata could be missing, in which case it will be an empty dict.
             meta = dpack.getmeta(filename, node)
             if constants.METAKEYSIZE in meta:
                 blobsize = meta[constants.METAKEYSIZE]
                 totaldeltasize += deltalen
                 totalblobsize += blobsize
             else:
                 blobsize = b"(missing)"
             ui.write(
                 b"%s  %s  %s%s\n"
                 % (
                     hashformatter(node),
                     hashformatter(deltabase),
                     (b'%d' % deltalen).ljust(14),
                     pycompat.bytestr(blobsize),
                 )
             )
 
         if filename is not None:
             printtotals()
 
         failures += _sanitycheck(ui, set(nodes), bases)
         if failures > 1:
             ui.warn((b"%d failures\n" % failures))
             return 1
 
 
 def _sanitycheck(ui, nodes, bases):
     """
     Does some basic sanity checking on a packfiles with ``nodes`` ``bases`` (a
     mapping of node->base):
 
     - Each deltabase must itself be a node elsewhere in the pack
     - There must be no cycles
     """
     failures = 0
     for node in nodes:
         seen = set()
         current = node
         deltabase = bases[current]
 
         while deltabase != nullid:
             if deltabase not in nodes:
                 ui.warn(
                     (
                         b"Bad entry: %s has an unknown deltabase (%s)\n"
                         % (short(node), short(deltabase))
                     )
                 )
                 failures += 1
                 break
 
             if deltabase in seen:
                 ui.warn(
                     (
                         b"Bad entry: %s has a cycle (at %s)\n"
                         % (short(node), short(deltabase))
                     )
                 )
                 failures += 1
                 break
 
             current = deltabase
             seen.add(current)
             deltabase = bases[current]
         # Since ``node`` begins a valid chain, reset/memoize its base to nullid
         # so we don't traverse it again.
         bases[node] = nullid
     return failures
 
 
 def dumpdeltachain(ui, deltachain, **opts):
     hashformatter = hex
     hashlen = 40
 
     lastfilename = None
     for filename, node, filename, deltabasenode, delta in deltachain:
         if filename != lastfilename:
             ui.write(b"\n%s\n" % filename)
             lastfilename = filename
         ui.write(
             b"%s  %s  %s  %s\n"
             % (
                 b"Node".ljust(hashlen),
                 b"Delta Base".ljust(hashlen),
                 b"Delta SHA1".ljust(hashlen),
                 b"Delta Length".ljust(6),
             )
         )
 
         ui.write(
             b"%s  %s  %s  %d\n"
             % (
                 hashformatter(node),
                 hashformatter(deltabasenode),
                 nodemod.hex(hashlib.sha1(delta).digest()),
                 len(delta),
             )
         )
 
 
 def debughistorypack(ui, path):
     if b'.hist' in path:
         path = path[: path.index(b'.hist')]
     hpack = historypack.historypack(path)
 
     lastfilename = None
     for entry in hpack.iterentries():
         filename, node, p1node, p2node, linknode, copyfrom = entry
         if filename != lastfilename:
             ui.write(b"\n%s\n" % filename)
             ui.write(
                 b"%s%s%s%s%s\n"
                 % (
                     b"Node".ljust(14),
                     b"P1 Node".ljust(14),
                     b"P2 Node".ljust(14),
                     b"Link Node".ljust(14),
                     b"Copy From",
                 )
             )
             lastfilename = filename
         ui.write(
             b"%s  %s  %s  %s  %s\n"
             % (
                 short(node),
                 short(p1node),
                 short(p2node),
                 short(linknode),
                 copyfrom,
             )
         )
 
 
 def debugwaitonrepack(repo):
     with lockmod.lock(repack.repacklockvfs(repo), b"repacklock", timeout=-1):
         return
 
 
 def debugwaitonprefetch(repo):
     with repo._lock(
         repo.svfs,
         b"prefetchlock",
         True,
         None,
         None,
         _(b'prefetching in %s') % repo.origroot,
     ):
         pass

hgext/show.py

@@ -1,530 +1,530 b''
 # show.py - Extension implementing `hg show`
 #
 # Copyright 2017 Gregory Szorc <[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.
 
 """unified command to show various repository information (EXPERIMENTAL)
 
 This extension provides the :hg:`show` command, which provides a central
 command for displaying commonly-accessed repository data and views of that
 data.
 
 The following config options can influence operation.
 
 ``commands``
 ------------
 
 ``show.aliasprefix``
    List of strings that will register aliases for views. e.g. ``s`` will
    effectively set config options ``alias.s<view> = show <view>`` for all
    views. i.e. `hg swork` would execute `hg show work`.
 
    Aliases that would conflict with existing registrations will not be
    performed.
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial.node import nullrev
 from mercurial import (
     cmdutil,
     commands,
     destutil,
     error,
     formatter,
     graphmod,
     logcmdutil,
     phases,
     pycompat,
     registrar,
     revset,
     revsetlang,
     scmutil,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 revsetpredicate = registrar.revsetpredicate()
 
 
 class showcmdfunc(registrar._funcregistrarbase):
     """Register a function to be invoked for an `hg show <thing>`."""
 
     # Used by _formatdoc().
     _docformat = b'%s -- %s'
 
     def _extrasetup(self, name, func, fmtopic=None, csettopic=None):
         """Called with decorator arguments to register a show view.
 
         ``name`` is the sub-command name.
 
         ``func`` is the function being decorated.
 
         ``fmtopic`` is the topic in the style that will be rendered for
         this view.
 
         ``csettopic`` is the topic in the style to be used for a changeset
         printer.
 
         If ``fmtopic`` is specified, the view function will receive a
         formatter instance. If ``csettopic`` is specified, the view
         function will receive a changeset printer.
         """
         func._fmtopic = fmtopic
         func._csettopic = csettopic
 
 
 showview = showcmdfunc()
 
 
 @command(
     b'show',
     [
         # TODO: Switch this template flag to use cmdutil.formatteropts if
         # 'hg show' becomes stable before --template/-T is stable. For now,
         # we are putting it here without the '(EXPERIMENTAL)' flag because it
         # is an important part of the 'hg show' user experience and the entire
         # 'hg show' experience is experimental.
         (b'T', b'template', b'', b'display with template', _(b'TEMPLATE')),
     ],
     _(b'VIEW'),
     helpcategory=command.CATEGORY_CHANGE_NAVIGATION,
 )
 def show(ui, repo, view=None, template=None):
     """show various repository information
 
     A requested view of repository data is displayed.
 
     If no view is requested, the list of available views is shown and the
     command aborts.
 
     .. note::
 
        There are no backwards compatibility guarantees for the output of this
        command. Output may change in any future Mercurial release.
 
        Consumers wanting stable command output should specify a template via
        ``-T/--template``.
 
     List of available views:
     """
     if ui.plain() and not template:
         hint = _(b'invoke with -T/--template to control output format')
         raise error.Abort(
             _(b'must specify a template in plain mode'), hint=hint
         )
 
     views = showview._table
 
     if not view:
         ui.pager(b'show')
         # TODO consider using formatter here so available views can be
         # rendered to custom format.
         ui.write(_(b'available views:\n'))
         ui.write(b'\n')
 
         for name, func in sorted(views.items()):
             ui.write(b'%s\n' % pycompat.sysbytes(func.__doc__))
 
         ui.write(b'\n')
         raise error.Abort(
             _(b'no view requested'),
             hint=_(b'use "hg show VIEW" to choose a view'),
         )
 
     # TODO use same logic as dispatch to perform prefix matching.
     if view not in views:
         raise error.Abort(
             _(b'unknown view: %s') % view,
             hint=_(b'run "hg show" to see available views'),
         )
 
     template = template or b'show'
 
     fn = views[view]
     ui.pager(b'show')
 
     if fn._fmtopic:
         fmtopic = b'show%s' % fn._fmtopic
         with ui.formatter(fmtopic, {b'template': template}) as fm:
             return fn(ui, repo, fm)
     elif fn._csettopic:
         ref = b'show%s' % fn._csettopic
         spec = formatter.lookuptemplate(ui, ref, template)
         displayer = logcmdutil.changesettemplater(ui, repo, spec, buffered=True)
         return fn(ui, repo, displayer)
     else:
         return fn(ui, repo)
 
 
 @showview(b'bookmarks', fmtopic=b'bookmarks')
 def showbookmarks(ui, repo, fm):
     """bookmarks and their associated changeset"""
     marks = repo._bookmarks
     if not len(marks):
         # This is a bit hacky. Ideally, templates would have a way to
         # specify an empty output, but we shouldn't corrupt JSON while
         # waiting for this functionality.
         if not isinstance(fm, formatter.jsonformatter):
             ui.write(_(b'(no bookmarks set)\n'))
         return
 
     revs = [repo[node].rev() for node in marks.values()]
     active = repo._activebookmark
     longestname = max(len(b) for b in marks)
     nodelen = longestshortest(repo, revs)
 
     for bm, node in sorted(marks.items()):
         fm.startitem()
         fm.context(ctx=repo[node])
         fm.write(b'bookmark', b'%s', bm)
         fm.write(b'node', fm.hexfunc(node), fm.hexfunc(node))
         fm.data(
             active=bm == active, longestbookmarklen=longestname, nodelen=nodelen
         )
 
 
 @showview(b'stack', csettopic=b'stack')
 def showstack(ui, repo, displayer):
     """current line of work"""
     wdirctx = repo[b'.']
     if wdirctx.rev() == nullrev:
         raise error.Abort(
             _(
                 b'stack view only available when there is a '
                 b'working directory'
             )
         )
 
     if wdirctx.phase() == phases.public:
         ui.write(
             _(
                 b'(empty stack; working directory parent is a published '
                 b'changeset)\n'
             )
         )
         return
 
     # TODO extract "find stack" into a function to facilitate
     # customization and reuse.
 
     baserev = destutil.stackbase(ui, repo)
     basectx = None
 
     if baserev is None:
         baserev = wdirctx.rev()
         stackrevs = {wdirctx.rev()}
     else:
         stackrevs = set(repo.revs(b'%d::.', baserev))
 
     ctx = repo[baserev]
     if ctx.p1().rev() != nullrev:
         basectx = ctx.p1()
 
     # And relevant descendants.
     branchpointattip = False
     cl = repo.changelog
 
     for rev in cl.descendants([wdirctx.rev()]):
         ctx = repo[rev]
 
         # Will only happen if . is public.
         if ctx.phase() == phases.public:
             break
 
         stackrevs.add(ctx.rev())
 
         # ctx.children() within a function iterating on descandants
         # potentially has severe performance concerns because revlog.children()
         # iterates over all revisions after ctx's node. However, the number of
         # draft changesets should be a reasonably small number. So even if
         # this is quadratic, the perf impact should be minimal.
         if len(ctx.children()) > 1:
             branchpointattip = True
             break
 
     stackrevs = list(sorted(stackrevs, reverse=True))
 
     # Find likely target heads for the current stack. These are likely
     # merge or rebase targets.
     if basectx:
         # TODO make this customizable?
         newheads = set(
             repo.revs(
                 b'heads(%d::) - %ld - not public()', basectx.rev(), stackrevs
             )
         )
     else:
         newheads = set()
 
     allrevs = set(stackrevs) | newheads | {baserev}
     nodelen = longestshortest(repo, allrevs)
 
     try:
         cmdutil.findcmd(b'rebase', commands.table)
         haverebase = True
     except (error.AmbiguousCommand, error.UnknownCommand):
         haverebase = False
 
     # TODO use templating.
     # TODO consider using graphmod. But it may not be necessary given
     # our simplicity and the customizations required.
     # TODO use proper graph symbols from graphmod
 
     tres = formatter.templateresources(ui, repo)
     shortesttmpl = formatter.maketemplater(
         ui, b'{shortest(node, %d)}' % nodelen, resources=tres
     )
 
     def shortest(ctx):
         return shortesttmpl.renderdefault({b'ctx': ctx, b'node': ctx.hex()})
 
     # We write out new heads to aid in DAG awareness and to help with decision
     # making on how the stack should be reconciled with commits made since the
     # branch point.
     if newheads:
         # Calculate distance from base so we can render the count and so we can
         # sort display order by commit distance.
         revdistance = {}
         for head in newheads:
             # There is some redundancy in DAG traversal here and therefore
             # room to optimize.
             ancestors = cl.ancestors([head], stoprev=basectx.rev())
             revdistance[head] = len(list(ancestors))
 
         sourcectx = repo[stackrevs[-1]]
 
         sortedheads = sorted(
             newheads, key=lambda x: revdistance[x], reverse=True
         )
 
         for i, rev in enumerate(sortedheads):
             ctx = repo[rev]
 
             if i:
                 ui.write(b': ')
             else:
                 ui.write(b'  ')
 
-            ui.write(b'o  ')
+            ui.writenoi18n(b'o  ')
             displayer.show(ctx, nodelen=nodelen)
             displayer.flush(ctx)
             ui.write(b'\n')
 
             if i:
                 ui.write(b':/')
             else:
                 ui.write(b' /')
 
             ui.write(b'    (')
             ui.write(
                 _(b'%d commits ahead') % revdistance[rev],
                 label=b'stack.commitdistance',
             )
 
             if haverebase:
                 # TODO may be able to omit --source in some scenarios
                 ui.write(b'; ')
                 ui.write(
                     (
                         b'hg rebase --source %s --dest %s'
                         % (shortest(sourcectx), shortest(ctx))
                     ),
                     label=b'stack.rebasehint',
                 )
 
             ui.write(b')\n')
 
         ui.write(b':\n:    ')
         ui.write(_(b'(stack head)\n'), label=b'stack.label')
 
     if branchpointattip:
         ui.write(b' \\ /  ')
         ui.write(_(b'(multiple children)\n'), label=b'stack.label')
         ui.write(b'  |\n')
 
     for rev in stackrevs:
         ctx = repo[rev]
         symbol = b'@' if rev == wdirctx.rev() else b'o'
 
         if newheads:
             ui.write(b': ')
         else:
             ui.write(b'  ')
 
         ui.write(symbol, b'  ')
         displayer.show(ctx, nodelen=nodelen)
         displayer.flush(ctx)
         ui.write(b'\n')
 
     # TODO display histedit hint?
 
     if basectx:
         # Vertically and horizontally separate stack base from parent
         # to reinforce stack boundary.
         if newheads:
             ui.write(b':/   ')
         else:
             ui.write(b' /   ')
 
         ui.write(_(b'(stack base)'), b'\n', label=b'stack.label')
-        ui.write(b'o  ')
+        ui.writenoi18n(b'o  ')
 
         displayer.show(basectx, nodelen=nodelen)
         displayer.flush(basectx)
         ui.write(b'\n')
 
 
 @revsetpredicate(b'_underway([commitage[, headage]])')
 def underwayrevset(repo, subset, x):
     args = revset.getargsdict(x, b'underway', b'commitage headage')
     if b'commitage' not in args:
         args[b'commitage'] = None
     if b'headage' not in args:
         args[b'headage'] = None
 
     # We assume callers of this revset add a topographical sort on the
     # result. This means there is no benefit to making the revset lazy
     # since the topographical sort needs to consume all revs.
     #
     # With this in mind, we build up the set manually instead of constructing
     # a complex revset. This enables faster execution.
 
     # Mutable changesets (non-public) are the most important changesets
     # to return. ``not public()`` will also pull in obsolete changesets if
     # there is a non-obsolete changeset with obsolete ancestors. This is
     # why we exclude obsolete changesets from this query.
     rs = b'not public() and not obsolete()'
     rsargs = []
     if args[b'commitage']:
         rs += b' and date(%s)'
         rsargs.append(
             revsetlang.getstring(
                 args[b'commitage'], _(b'commitage requires a string')
             )
         )
 
     mutable = repo.revs(rs, *rsargs)
     relevant = revset.baseset(mutable)
 
     # Add parents of mutable changesets to provide context.
     relevant += repo.revs(b'parents(%ld)', mutable)
 
     # We also pull in (public) heads if they a) aren't closing a branch
     # b) are recent.
     rs = b'head() and not closed()'
     rsargs = []
     if args[b'headage']:
         rs += b' and date(%s)'
         rsargs.append(
             revsetlang.getstring(
                 args[b'headage'], _(b'headage requires a string')
             )
         )
 
     relevant += repo.revs(rs, *rsargs)
 
     # Add working directory parent.
     wdirrev = repo[b'.'].rev()
     if wdirrev != nullrev:
         relevant += revset.baseset({wdirrev})
 
     return subset & relevant
 
 
 @showview(b'work', csettopic=b'work')
 def showwork(ui, repo, displayer):
     """changesets that aren't finished"""
     # TODO support date-based limiting when calling revset.
     revs = repo.revs(b'sort(_underway(), topo)')
     nodelen = longestshortest(repo, revs)
 
     revdag = graphmod.dagwalker(repo, revs)
 
     ui.setconfig(b'experimental', b'graphshorten', True)
     logcmdutil.displaygraph(
         ui,
         repo,
         revdag,
         displayer,
         graphmod.asciiedges,
         props={b'nodelen': nodelen},
     )
 
 
 def extsetup(ui):
     # Alias `hg <prefix><view>` to `hg show <view>`.
     for prefix in ui.configlist(b'commands', b'show.aliasprefix'):
         for view in showview._table:
             name = b'%s%s' % (prefix, view)
 
             choice, allcommands = cmdutil.findpossible(
                 name, commands.table, strict=True
             )
 
             # This alias is already a command name. Don't set it.
             if name in choice:
                 continue
 
             # Same for aliases.
             if ui.config(b'alias', name, None):
                 continue
 
             ui.setconfig(b'alias', name, b'show %s' % view, source=b'show')
 
 
 def longestshortest(repo, revs, minlen=4):
     """Return the length of the longest shortest node to identify revisions.
 
     The result of this function can be used with the ``shortest()`` template
     function to ensure that a value is unique and unambiguous for a given
     set of nodes.
 
     The number of revisions in the repo is taken into account to prevent
     a numeric node prefix from conflicting with an integer revision number.
     If we fail to do this, a value of e.g. ``10023`` could mean either
     revision 10023 or node ``10023abc...``.
     """
     if not revs:
         return minlen
     cl = repo.changelog
     return max(
         len(scmutil.shortesthexnodeidprefix(repo, cl.node(r), minlen))
         for r in revs
     )
 
 
 # Adjust the docstring of the show command so it shows all registered views.
 # This is a bit hacky because it runs at the end of module load. When moved
 # into core or when another extension wants to provide a view, we'll need
 # to do this more robustly.
 # TODO make this more robust.
 def _updatedocstring():
     longest = max(map(len, showview._table.keys()))
     entries = []
     for key in sorted(showview._table.keys()):
         entries.append(
             r'    %s   %s'
             % (
                 pycompat.sysstr(key.ljust(longest)),
                 showview._table[key]._origdoc,
             )
         )
 
     cmdtable[b'show'][0].__doc__ = pycompat.sysstr(b'%s\n\n%s\n    ') % (
         cmdtable[b'show'][0].__doc__.rstrip(),
         pycompat.sysstr(b'\n\n').join(entries),
     )
 
 
 _updatedocstring()

hgext/win32mbcs.py

@@ -1,218 +1,218 b''
 # win32mbcs.py -- MBCS filename support for Mercurial
 #
 # Copyright (c) 2008 Shun-ichi Goto <[e-mail]>
 #
 # Version: 0.3
 # Author:  Shun-ichi Goto <[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.
 #
 
 '''allow the use of MBCS paths with problematic encodings
 
 Some MBCS encodings are not good for some path operations (i.e.
 splitting path, case conversion, etc.) with its encoded bytes. We call
 such a encoding (i.e. shift_jis and big5) as "problematic encoding".
 This extension can be used to fix the issue with those encodings by
 wrapping some functions to convert to Unicode string before path
 operation.
 
 This extension is useful for:
 
 - Japanese Windows users using shift_jis encoding.
 - Chinese Windows users using big5 encoding.
 - All users who use a repository with one of problematic encodings on
   case-insensitive file system.
 
 This extension is not needed for:
 
 - Any user who use only ASCII chars in path.
 - Any user who do not use any of problematic encodings.
 
 Note that there are some limitations on using this extension:
 
 - You should use single encoding in one repository.
 - If the repository path ends with 0x5c, .hg/hgrc cannot be read.
 - win32mbcs is not compatible with fixutf8 extension.
 
 By default, win32mbcs uses encoding.encoding decided by Mercurial.
 You can specify the encoding by config option::
 
  [win32mbcs]
  encoding = sjis
 
 It is useful for the users who want to commit with UTF-8 log message.
 '''
 from __future__ import absolute_import
 
 import os
 import sys
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     pycompat,
     registrar,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 # Encoding.encoding may be updated by --encoding option.
 # Use a lambda do delay the resolution.
 configitem(
     b'win32mbcs', b'encoding', default=lambda: encoding.encoding,
 )
 
 _encoding = None  # see extsetup
 
 
 def decode(arg):
     if isinstance(arg, str):
         uarg = arg.decode(_encoding)
         if arg == uarg.encode(_encoding):
             return uarg
         raise UnicodeError(b"Not local encoding")
     elif isinstance(arg, tuple):
         return tuple(map(decode, arg))
     elif isinstance(arg, list):
         return map(decode, arg)
     elif isinstance(arg, dict):
         for k, v in arg.items():
             arg[k] = decode(v)
     return arg
 
 
 def encode(arg):
     if isinstance(arg, pycompat.unicode):
         return arg.encode(_encoding)
     elif isinstance(arg, tuple):
         return tuple(map(encode, arg))
     elif isinstance(arg, list):
         return map(encode, arg)
     elif isinstance(arg, dict):
         for k, v in arg.items():
             arg[k] = encode(v)
     return arg
 
 
 def appendsep(s):
     # ensure the path ends with os.sep, appending it if necessary.
     try:
         us = decode(s)
     except UnicodeError:
         us = s
     if us and us[-1] not in b':/\\':
         s += pycompat.ossep
     return s
 
 
 def basewrapper(func, argtype, enc, dec, args, kwds):
     # check check already converted, then call original
     for arg in args:
         if isinstance(arg, argtype):
             return func(*args, **kwds)
 
     try:
         # convert string arguments, call func, then convert back the
         # return value.
         return enc(func(*dec(args), **dec(kwds)))
     except UnicodeError:
         raise error.Abort(
             _(b"[win32mbcs] filename conversion failed with" b" %s encoding\n")
             % _encoding
         )
 
 
 def wrapper(func, args, kwds):
     return basewrapper(func, pycompat.unicode, encode, decode, args, kwds)
 
 
 def reversewrapper(func, args, kwds):
     return basewrapper(func, str, decode, encode, args, kwds)
 
 
 def wrapperforlistdir(func, args, kwds):
     # Ensure 'path' argument ends with os.sep to avoids
     # misinterpreting last 0x5c of MBCS 2nd byte as path separator.
     if args:
         args = list(args)
         args[0] = appendsep(args[0])
     if b'path' in kwds:
         kwds[b'path'] = appendsep(kwds[b'path'])
     return func(*args, **kwds)
 
 
 def wrapname(name, wrapper):
     module, name = name.rsplit(b'.', 1)
     module = sys.modules[module]
     func = getattr(module, name)
 
     def f(*args, **kwds):
         return wrapper(func, args, kwds)
 
     f.__name__ = func.__name__
     setattr(module, name, f)
 
 
 # List of functions to be wrapped.
 # NOTE: os.path.dirname() and os.path.basename() are safe because
 #       they use result of os.path.split()
 funcs = b'''os.path.join os.path.split os.path.splitext
  os.path.normpath os.makedirs mercurial.util.endswithsep
  mercurial.util.splitpath mercurial.util.fscasesensitive
  mercurial.util.fspath mercurial.util.pconvert mercurial.util.normpath
  mercurial.util.checkwinfilename mercurial.util.checkosfilename
  mercurial.util.split'''
 
 # These functions are required to be called with local encoded string
 # because they expects argument is local encoded string and cause
 # problem with unicode string.
 rfuncs = b'''mercurial.encoding.upper mercurial.encoding.lower
  mercurial.util._filenamebytestr'''
 
 # List of Windows specific functions to be wrapped.
 winfuncs = b'''os.path.splitunc'''
 
 # codec and alias names of sjis and big5 to be faked.
 problematic_encodings = b'''big5 big5-tw csbig5 big5hkscs big5-hkscs
  hkscs cp932 932 ms932 mskanji ms-kanji shift_jis csshiftjis shiftjis
  sjis s_jis shift_jis_2004 shiftjis2004 sjis_2004 sjis2004
  shift_jisx0213 shiftjisx0213 sjisx0213 s_jisx0213 950 cp950 ms950 '''
 
 
 def extsetup(ui):
     # TODO: decide use of config section for this extension
     if (not os.path.supports_unicode_filenames) and (
         pycompat.sysplatform != b'cygwin'
     ):
         ui.warn(_(b"[win32mbcs] cannot activate on this platform.\n"))
         return
     # determine encoding for filename
     global _encoding
     _encoding = ui.config(b'win32mbcs', b'encoding')
     # fake is only for relevant environment.
     if _encoding.lower() in problematic_encodings.split():
         for f in funcs.split():
             wrapname(f, wrapper)
         if pycompat.iswindows:
             for f in winfuncs.split():
                 wrapname(f, wrapper)
         wrapname(b"mercurial.util.listdir", wrapperforlistdir)
         wrapname(b"mercurial.windows.listdir", wrapperforlistdir)
         # wrap functions to be called with local byte string arguments
         for f in rfuncs.split():
             wrapname(f, reversewrapper)
         # Check sys.args manually instead of using ui.debug() because
         # command line options is not yet applied when
         # extensions.loadall() is called.
         if b'--debug' in sys.argv:
-            ui.write(b"[win32mbcs] activated with encoding: %s\n" % _encoding)
+            ui.writenoi18n(b"[win32mbcs] activated with encoding: %s\n" % _encoding)

mercurial/bundle2.py

@@ -1,2555 +1,2555 b''
 # bundle2.py - generic container format to transmit arbitrary data.
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """Handling of the new bundle2 format
 
 The goal of bundle2 is to act as an atomically packet to transmit a set of
 payloads in an application agnostic way. It consist in a sequence of "parts"
 that will be handed to and processed by the application layer.
 
 
 General format architecture
 ===========================
 
 The format is architectured as follow
 
  - magic string
  - stream level parameters
  - payload parts (any number)
  - end of stream marker.
 
 the Binary format
 ============================
 
 All numbers are unsigned and big-endian.
 
 stream level parameters
 ------------------------
 
 Binary format is as follow
 
 :params size: int32
 
   The total number of Bytes used by the parameters
 
 :params value: arbitrary number of Bytes
 
   A blob of `params size` containing the serialized version of all stream level
   parameters.
 
   The blob contains a space separated list of parameters. Parameters with value
   are stored in the form `<name>=<value>`. Both name and value are urlquoted.
 
   Empty name are obviously forbidden.
 
   Name MUST start with a letter. If this first letter is lower case, the
   parameter is advisory and can be safely ignored. However when the first
   letter is capital, the parameter is mandatory and the bundling process MUST
   stop if he is not able to proceed it.
 
   Stream parameters use a simple textual format for two main reasons:
 
   - Stream level parameters should remain simple and we want to discourage any
     crazy usage.
   - Textual data allow easy human inspection of a bundle2 header in case of
     troubles.
 
   Any Applicative level options MUST go into a bundle2 part instead.
 
 Payload part
 ------------------------
 
 Binary format is as follow
 
 :header size: int32
 
   The total number of Bytes used by the part header. When the header is empty
   (size = 0) this is interpreted as the end of stream marker.
 
 :header:
 
     The header defines how to interpret the part. It contains two piece of
     data: the part type, and the part parameters.
 
     The part type is used to route an application level handler, that can
     interpret payload.
 
     Part parameters are passed to the application level handler.  They are
     meant to convey information that will help the application level object to
     interpret the part payload.
 
     The binary format of the header is has follow
 
     :typesize: (one byte)
 
     :parttype: alphanumerical part name (restricted to [a-zA-Z0-9_:-]*)
 
     :partid: A 32bits integer (unique in the bundle) that can be used to refer
              to this part.
 
     :parameters:
 
         Part's parameter may have arbitrary content, the binary structure is::
 
             <mandatory-count><advisory-count><param-sizes><param-data>
 
         :mandatory-count: 1 byte, number of mandatory parameters
 
         :advisory-count:  1 byte, number of advisory parameters
 
         :param-sizes:
 
             N couple of bytes, where N is the total number of parameters. Each
             couple contains (<size-of-key>, <size-of-value) for one parameter.
 
         :param-data:
 
             A blob of bytes from which each parameter key and value can be
             retrieved using the list of size couples stored in the previous
             field.
 
             Mandatory parameters comes first, then the advisory ones.
 
             Each parameter's key MUST be unique within the part.
 
 :payload:
 
     payload is a series of `<chunksize><chunkdata>`.
 
     `chunksize` is an int32, `chunkdata` are plain bytes (as much as
     `chunksize` says)` The payload part is concluded by a zero size chunk.
 
     The current implementation always produces either zero or one chunk.
     This is an implementation limitation that will ultimately be lifted.
 
     `chunksize` can be negative to trigger special case processing. No such
     processing is in place yet.
 
 Bundle processing
 ============================
 
 Each part is processed in order using a "part handler". Handler are registered
 for a certain part type.
 
 The matching of a part to its handler is case insensitive. The case of the
 part type is used to know if a part is mandatory or advisory. If the Part type
 contains any uppercase char it is considered mandatory. When no handler is
 known for a Mandatory part, the process is aborted and an exception is raised.
 If the part is advisory and no handler is known, the part is ignored. When the
 process is aborted, the full bundle is still read from the stream to keep the
 channel usable. But none of the part read from an abort are processed. In the
 future, dropping the stream may become an option for channel we do not care to
 preserve.
 """
 
 from __future__ import absolute_import, division
 
 import collections
 import errno
 import os
 import re
 import string
 import struct
 import sys
 
 from .i18n import _
 from . import (
     bookmarks,
     changegroup,
     encoding,
     error,
     node as nodemod,
     obsolete,
     phases,
     pushkey,
     pycompat,
     streamclone,
     tags,
     url,
     util,
 )
 from .utils import stringutil
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 _fstreamparamsize = b'>i'
 _fpartheadersize = b'>i'
 _fparttypesize = b'>B'
 _fpartid = b'>I'
 _fpayloadsize = b'>i'
 _fpartparamcount = b'>BB'
 
 preferedchunksize = 32768
 
 _parttypeforbidden = re.compile(b'[^a-zA-Z0-9_:-]')
 
 
 def outdebug(ui, message):
     """debug regarding output stream (bundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-output: %s\n' % message)
 
 
 def indebug(ui, message):
     """debug on input stream (unbundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-input: %s\n' % message)
 
 
 def validateparttype(parttype):
     """raise ValueError if a parttype contains invalid character"""
     if _parttypeforbidden.search(parttype):
         raise ValueError(parttype)
 
 
 def _makefpartparamsizes(nbparams):
     """return a struct format to read part parameter sizes
 
     The number parameters is variable so we need to build that format
     dynamically.
     """
     return b'>' + (b'BB' * nbparams)
 
 
 parthandlermapping = {}
 
 
 def parthandler(parttype, params=()):
     """decorator that register a function as a bundle2 part handler
 
     eg::
 
         @parthandler('myparttype', ('mandatory', 'param', 'handled'))
         def myparttypehandler(...):
             '''process a part of type "my part".'''
             ...
     """
     validateparttype(parttype)
 
     def _decorator(func):
         lparttype = parttype.lower()  # enforce lower case matching.
         assert lparttype not in parthandlermapping
         parthandlermapping[lparttype] = func
         func.params = frozenset(params)
         return func
 
     return _decorator
 
 
 class unbundlerecords(object):
     """keep record of what happens during and unbundle
 
     New records are added using `records.add('cat', obj)`. Where 'cat' is a
     category of record and obj is an arbitrary object.
 
     `records['cat']` will return all entries of this category 'cat'.
 
     Iterating on the object itself will yield `('category', obj)` tuples
     for all entries.
 
     All iterations happens in chronological order.
     """
 
     def __init__(self):
         self._categories = {}
         self._sequences = []
         self._replies = {}
 
     def add(self, category, entry, inreplyto=None):
         """add a new record of a given category.
 
         The entry can then be retrieved in the list returned by
         self['category']."""
         self._categories.setdefault(category, []).append(entry)
         self._sequences.append((category, entry))
         if inreplyto is not None:
             self.getreplies(inreplyto).add(category, entry)
 
     def getreplies(self, partid):
         """get the records that are replies to a specific part"""
         return self._replies.setdefault(partid, unbundlerecords())
 
     def __getitem__(self, cat):
         return tuple(self._categories.get(cat, ()))
 
     def __iter__(self):
         return iter(self._sequences)
 
     def __len__(self):
         return len(self._sequences)
 
     def __nonzero__(self):
         return bool(self._sequences)
 
     __bool__ = __nonzero__
 
 
 class bundleoperation(object):
     """an object that represents a single bundling process
 
     Its purpose is to carry unbundle-related objects and states.
 
     A new object should be created at the beginning of each bundle processing.
     The object is to be returned by the processing function.
 
     The object has very little content now it will ultimately contain:
     * an access to the repo the bundle is applied to,
     * a ui object,
     * a way to retrieve a transaction to add changes to the repo,
     * a way to record the result of processing each part,
     * a way to construct a bundle response when applicable.
     """
 
     def __init__(self, repo, transactiongetter, captureoutput=True, source=b''):
         self.repo = repo
         self.ui = repo.ui
         self.records = unbundlerecords()
         self.reply = None
         self.captureoutput = captureoutput
         self.hookargs = {}
         self._gettransaction = transactiongetter
         # carries value that can modify part behavior
         self.modes = {}
         self.source = source
 
     def gettransaction(self):
         transaction = self._gettransaction()
 
         if self.hookargs:
             # the ones added to the transaction supercede those added
             # to the operation.
             self.hookargs.update(transaction.hookargs)
             transaction.hookargs = self.hookargs
 
         # mark the hookargs as flushed.  further attempts to add to
         # hookargs will result in an abort.
         self.hookargs = None
 
         return transaction
 
     def addhookargs(self, hookargs):
         if self.hookargs is None:
             raise error.ProgrammingError(
                 b'attempted to add hookargs to '
                 b'operation after transaction started'
             )
         self.hookargs.update(hookargs)
 
 
 class TransactionUnavailable(RuntimeError):
     pass
 
 
 def _notransaction():
     """default method to get a transaction while processing a bundle
 
     Raise an exception to highlight the fact that no transaction was expected
     to be created"""
     raise TransactionUnavailable()
 
 
 def applybundle(repo, unbundler, tr, source, url=None, **kwargs):
     # transform me into unbundler.apply() as soon as the freeze is lifted
     if isinstance(unbundler, unbundle20):
         tr.hookargs[b'bundle2'] = b'1'
         if source is not None and b'source' not in tr.hookargs:
             tr.hookargs[b'source'] = source
         if url is not None and b'url' not in tr.hookargs:
             tr.hookargs[b'url'] = url
         return processbundle(repo, unbundler, lambda: tr, source=source)
     else:
         # the transactiongetter won't be used, but we might as well set it
         op = bundleoperation(repo, lambda: tr, source=source)
         _processchangegroup(op, unbundler, tr, source, url, **kwargs)
         return op
 
 
 class partiterator(object):
     def __init__(self, repo, op, unbundler):
         self.repo = repo
         self.op = op
         self.unbundler = unbundler
         self.iterator = None
         self.count = 0
         self.current = None
 
     def __enter__(self):
         def func():
             itr = enumerate(self.unbundler.iterparts(), 1)
             for count, p in itr:
                 self.count = count
                 self.current = p
                 yield p
                 p.consume()
                 self.current = None
 
         self.iterator = func()
         return self.iterator
 
     def __exit__(self, type, exc, tb):
         if not self.iterator:
             return
 
         # Only gracefully abort in a normal exception situation. User aborts
         # like Ctrl+C throw a KeyboardInterrupt which is not a base Exception,
         # and should not gracefully cleanup.
         if isinstance(exc, Exception):
             # Any exceptions seeking to the end of the bundle at this point are
             # almost certainly related to the underlying stream being bad.
             # And, chances are that the exception we're handling is related to
             # getting in that bad state. So, we swallow the seeking error and
             # re-raise the original error.
             seekerror = False
             try:
                 if self.current:
                     # consume the part content to not corrupt the stream.
                     self.current.consume()
 
                 for part in self.iterator:
                     # consume the bundle content
                     part.consume()
             except Exception:
                 seekerror = True
 
             # Small hack to let caller code distinguish exceptions from bundle2
             # processing from processing the old format. This is mostly needed
             # to handle different return codes to unbundle according to the type
             # of bundle. We should probably clean up or drop this return code
             # craziness in a future version.
             exc.duringunbundle2 = True
             salvaged = []
             replycaps = None
             if self.op.reply is not None:
                 salvaged = self.op.reply.salvageoutput()
                 replycaps = self.op.reply.capabilities
             exc._replycaps = replycaps
             exc._bundle2salvagedoutput = salvaged
 
             # Re-raising from a variable loses the original stack. So only use
             # that form if we need to.
             if seekerror:
                 raise exc
 
         self.repo.ui.debug(
             b'bundle2-input-bundle: %i parts total\n' % self.count
         )
 
 
 def processbundle(repo, unbundler, transactiongetter=None, op=None, source=b''):
     """This function process a bundle, apply effect to/from a repo
 
     It iterates over each part then searches for and uses the proper handling
     code to process the part. Parts are processed in order.
 
     Unknown Mandatory part will abort the process.
 
     It is temporarily possible to provide a prebuilt bundleoperation to the
     function. This is used to ensure output is properly propagated in case of
     an error during the unbundling. This output capturing part will likely be
     reworked and this ability will probably go away in the process.
     """
     if op is None:
         if transactiongetter is None:
             transactiongetter = _notransaction
         op = bundleoperation(repo, transactiongetter, source=source)
     # todo:
     # - replace this is a init function soon.
     # - exception catching
     unbundler.params
     if repo.ui.debugflag:
         msg = [b'bundle2-input-bundle:']
         if unbundler.params:
             msg.append(b' %i params' % len(unbundler.params))
         if op._gettransaction is None or op._gettransaction is _notransaction:
             msg.append(b' no-transaction')
         else:
             msg.append(b' with-transaction')
         msg.append(b'\n')
         repo.ui.debug(b''.join(msg))
 
     processparts(repo, op, unbundler)
 
     return op
 
 
 def processparts(repo, op, unbundler):
     with partiterator(repo, op, unbundler) as parts:
         for part in parts:
             _processpart(op, part)
 
 
 def _processchangegroup(op, cg, tr, source, url, **kwargs):
     ret = cg.apply(op.repo, tr, source, url, **kwargs)
     op.records.add(b'changegroup', {b'return': ret,})
     return ret
 
 
 def _gethandler(op, part):
     status = b'unknown'  # used by debug output
     try:
         handler = parthandlermapping.get(part.type)
         if handler is None:
             status = b'unsupported-type'
             raise error.BundleUnknownFeatureError(parttype=part.type)
         indebug(op.ui, b'found a handler for part %s' % part.type)
         unknownparams = part.mandatorykeys - handler.params
         if unknownparams:
             unknownparams = list(unknownparams)
             unknownparams.sort()
             status = b'unsupported-params (%s)' % b', '.join(unknownparams)
             raise error.BundleUnknownFeatureError(
                 parttype=part.type, params=unknownparams
             )
         status = b'supported'
     except error.BundleUnknownFeatureError as exc:
         if part.mandatory:  # mandatory parts
             raise
         indebug(op.ui, b'ignoring unsupported advisory part %s' % exc)
         return  # skip to part processing
     finally:
         if op.ui.debugflag:
             msg = [b'bundle2-input-part: "%s"' % part.type]
             if not part.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(part.mandatorykeys)
             nbap = len(part.params) - nbmp
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             msg.append(b' %s\n' % status)
             op.ui.debug(b''.join(msg))
 
     return handler
 
 
 def _processpart(op, part):
     """process a single part from a bundle
 
     The part is guaranteed to have been fully consumed when the function exits
     (even if an exception is raised)."""
     handler = _gethandler(op, part)
     if handler is None:
         return
 
     # handler is called outside the above try block so that we don't
     # risk catching KeyErrors from anything other than the
     # parthandlermapping lookup (any KeyError raised by handler()
     # itself represents a defect of a different variety).
     output = None
     if op.captureoutput and op.reply is not None:
         op.ui.pushbuffer(error=True, subproc=True)
         output = b''
     try:
         handler(op, part)
     finally:
         if output is not None:
             output = op.ui.popbuffer()
         if output:
             outpart = op.reply.newpart(b'output', data=output, mandatory=False)
             outpart.addparam(
                 b'in-reply-to', pycompat.bytestr(part.id), mandatory=False
             )
 
 
 def decodecaps(blob):
     """decode a bundle2 caps bytes blob into a dictionary
 
     The blob is a list of capabilities (one per line)
     Capabilities may have values using a line of the form::
 
         capability=value1,value2,value3
 
     The values are always a list."""
     caps = {}
     for line in blob.splitlines():
         if not line:
             continue
         if b'=' not in line:
             key, vals = line, ()
         else:
             key, vals = line.split(b'=', 1)
             vals = vals.split(b',')
         key = urlreq.unquote(key)
         vals = [urlreq.unquote(v) for v in vals]
         caps[key] = vals
     return caps
 
 
 def encodecaps(caps):
     """encode a bundle2 caps dictionary into a bytes blob"""
     chunks = []
     for ca in sorted(caps):
         vals = caps[ca]
         ca = urlreq.quote(ca)
         vals = [urlreq.quote(v) for v in vals]
         if vals:
             ca = b"%s=%s" % (ca, b','.join(vals))
         chunks.append(ca)
     return b'\n'.join(chunks)
 
 
 bundletypes = {
     b"": (b"", b'UN'),  # only when using unbundle on ssh and old http servers
     # since the unification ssh accepts a header but there
     # is no capability signaling it.
     b"HG20": (),  # special-cased below
     b"HG10UN": (b"HG10UN", b'UN'),
     b"HG10BZ": (b"HG10", b'BZ'),
     b"HG10GZ": (b"HG10GZ", b'GZ'),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = [b'HG10GZ', b'HG10BZ', b'HG10UN']
 
 
 class bundle20(object):
     """represent an outgoing bundle2 container
 
     Use the `addparam` method to add stream level parameter. and `newpart` to
     populate it. Then call `getchunks` to retrieve all the binary chunks of
     data that compose the bundle2 container."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, capabilities=()):
         self.ui = ui
         self._params = []
         self._parts = []
         self.capabilities = dict(capabilities)
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compopts = None
         # If compression is being handled by a consumer of the raw
         # data (e.g. the wire protocol), unsetting this flag tells
         # consumers that the bundle is best left uncompressed.
         self.prefercompressed = True
 
     def setcompression(self, alg, compopts=None):
         """setup core part compression to <alg>"""
         if alg in (None, b'UN'):
             return
         assert not any(n.lower() == b'compression' for n, v in self._params)
         self.addparam(b'Compression', alg)
         self._compengine = util.compengines.forbundletype(alg)
         self._compopts = compopts
 
     @property
     def nbparts(self):
         """total number of parts added to the bundler"""
         return len(self._parts)
 
     # methods used to defines the bundle2 content
     def addparam(self, name, value=None):
         """add a stream level parameter"""
         if not name:
             raise error.ProgrammingError(b'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise error.ProgrammingError(
                 b'non letter first character: %s' % name
             )
         self._params.append((name, value))
 
     def addpart(self, part):
         """add a new part to the bundle2 container
 
         Parts contains the actual applicative payload."""
         assert part.id is None
         part.id = len(self._parts)  # very cheap counter
         self._parts.append(part)
 
     def newpart(self, typeid, *args, **kwargs):
         """create a new part and add it to the containers
 
         As the part is directly added to the containers. For now, this means
         that any failure to properly initialize the part after calling
         ``newpart`` should result in a failure of the whole bundling process.
 
         You can still fall back to manually create and add if you need better
         control."""
         part = bundlepart(typeid, *args, **kwargs)
         self.addpart(part)
         return part
 
     # methods used to generate the bundle2 stream
     def getchunks(self):
         if self.ui.debugflag:
             msg = [b'bundle2-output-bundle: "%s",' % self._magicstring]
             if self._params:
                 msg.append(b' (%i params)' % len(self._params))
             msg.append(b' %i parts total\n' % len(self._parts))
             self.ui.debug(b''.join(msg))
         outdebug(self.ui, b'start emission of %s stream' % self._magicstring)
         yield self._magicstring
         param = self._paramchunk()
         outdebug(self.ui, b'bundle parameter: %s' % param)
         yield _pack(_fstreamparamsize, len(param))
         if param:
             yield param
         for chunk in self._compengine.compressstream(
             self._getcorechunk(), self._compopts
         ):
             yield chunk
 
     def _paramchunk(self):
         """return a encoded version of all stream parameters"""
         blocks = []
         for par, value in self._params:
             par = urlreq.quote(par)
             if value is not None:
                 value = urlreq.quote(value)
                 par = b'%s=%s' % (par, value)
             blocks.append(par)
         return b' '.join(blocks)
 
     def _getcorechunk(self):
         """yield chunk for the core part of the bundle
 
         (all but headers and parameters)"""
         outdebug(self.ui, b'start of parts')
         for part in self._parts:
             outdebug(self.ui, b'bundle part: "%s"' % part.type)
             for chunk in part.getchunks(ui=self.ui):
                 yield chunk
         outdebug(self.ui, b'end of bundle')
         yield _pack(_fpartheadersize, 0)
 
     def salvageoutput(self):
         """return a list with a copy of all output parts in the bundle
 
         This is meant to be used during error handling to make sure we preserve
         server output"""
         salvaged = []
         for part in self._parts:
             if part.type.startswith(b'output'):
                 salvaged.append(part.copy())
         return salvaged
 
 
 class unpackermixin(object):
     """A mixin to extract bytes and struct data from a stream"""
 
     def __init__(self, fp):
         self._fp = fp
 
     def _unpack(self, format):
         """unpack this struct format from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         data = self._readexact(struct.calcsize(format))
         return _unpack(format, data)
 
     def _readexact(self, size):
         """read exactly <size> bytes from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         return changegroup.readexactly(self._fp, size)
 
 
 def getunbundler(ui, fp, magicstring=None):
     """return a valid unbundler object for a given magicstring"""
     if magicstring is None:
         magicstring = changegroup.readexactly(fp, 4)
     magic, version = magicstring[0:2], magicstring[2:4]
     if magic != b'HG':
         ui.debug(
             b"error: invalid magic: %r (version %r), should be 'HG'\n"
             % (magic, version)
         )
         raise error.Abort(_(b'not a Mercurial bundle'))
     unbundlerclass = formatmap.get(version)
     if unbundlerclass is None:
         raise error.Abort(_(b'unknown bundle version %s') % version)
     unbundler = unbundlerclass(ui, fp)
     indebug(ui, b'start processing of %s stream' % magicstring)
     return unbundler
 
 
 class unbundle20(unpackermixin):
     """interpret a bundle2 stream
 
     This class is fed with a binary stream and yields parts through its
     `iterparts` methods."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, fp):
         """If header is specified, we do not read it out of the stream."""
         self.ui = ui
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compressed = None
         super(unbundle20, self).__init__(fp)
 
     @util.propertycache
     def params(self):
         """dictionary of stream level parameters"""
         indebug(self.ui, b'reading bundle2 stream parameters')
         params = {}
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             params = self._processallparams(params)
         return params
 
     def _processallparams(self, paramsblock):
         """"""
         params = util.sortdict()
         for p in paramsblock.split(b' '):
             p = p.split(b'=', 1)
             p = [urlreq.unquote(i) for i in p]
             if len(p) < 2:
                 p.append(None)
             self._processparam(*p)
             params[p[0]] = p[1]
         return params
 
     def _processparam(self, name, value):
         """process a parameter, applying its effect if needed
 
         Parameter starting with a lower case letter are advisory and will be
         ignored when unknown.  Those starting with an upper case letter are
         mandatory and will this function will raise a KeyError when unknown.
 
         Note: no option are currently supported. Any input will be either
               ignored or failing.
         """
         if not name:
             raise ValueError(r'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise ValueError(r'non letter first character: %s' % name)
         try:
             handler = b2streamparamsmap[name.lower()]
         except KeyError:
             if name[0:1].islower():
                 indebug(self.ui, b"ignoring unknown parameter %s" % name)
             else:
                 raise error.BundleUnknownFeatureError(params=(name,))
         else:
             handler(self, name, value)
 
     def _forwardchunks(self):
         """utility to transfer a bundle2 as binary
 
         This is made necessary by the fact the 'getbundle' command over 'ssh'
         have no way to know then the reply end, relying on the bundle to be
         interpreted to know its end. This is terrible and we are sorry, but we
         needed to move forward to get general delta enabled.
         """
         yield self._magicstring
         assert b'params' not in vars(self)
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             self._processallparams(params)
             # The payload itself is decompressed below, so drop
             # the compression parameter passed down to compensate.
             outparams = []
             for p in params.split(b' '):
                 k, v = p.split(b'=', 1)
                 if k.lower() != b'compression':
                     outparams.append(p)
             outparams = b' '.join(outparams)
             yield _pack(_fstreamparamsize, len(outparams))
             yield outparams
         else:
             yield _pack(_fstreamparamsize, paramssize)
         # From there, payload might need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         emptycount = 0
         while emptycount < 2:
             # so we can brainlessly loop
             assert _fpartheadersize == _fpayloadsize
             size = self._unpack(_fpartheadersize)[0]
             yield _pack(_fpartheadersize, size)
             if size:
                 emptycount = 0
             else:
                 emptycount += 1
                 continue
             if size == flaginterrupt:
                 continue
             elif size < 0:
                 raise error.BundleValueError(b'negative chunk size: %i')
             yield self._readexact(size)
 
     def iterparts(self, seekable=False):
         """yield all parts contained in the stream"""
         cls = seekableunbundlepart if seekable else unbundlepart
         # make sure param have been loaded
         self.params
         # From there, payload need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         indebug(self.ui, b'start extraction of bundle2 parts')
         headerblock = self._readpartheader()
         while headerblock is not None:
             part = cls(self.ui, headerblock, self._fp)
             yield part
             # Ensure part is fully consumed so we can start reading the next
             # part.
             part.consume()
 
             headerblock = self._readpartheader()
         indebug(self.ui, b'end of bundle2 stream')
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def compressed(self):
         self.params  # load params
         return self._compressed
 
     def close(self):
         """close underlying file"""
         if util.safehasattr(self._fp, b'close'):
             return self._fp.close()
 
 
 formatmap = {b'20': unbundle20}
 
 b2streamparamsmap = {}
 
 
 def b2streamparamhandler(name):
     """register a handler for a stream level parameter"""
 
     def decorator(func):
         assert name not in formatmap
         b2streamparamsmap[name] = func
         return func
 
     return decorator
 
 
 @b2streamparamhandler(b'compression')
 def processcompression(unbundler, param, value):
     """read compression parameter and install payload decompression"""
     if value not in util.compengines.supportedbundletypes:
         raise error.BundleUnknownFeatureError(params=(param,), values=(value,))
     unbundler._compengine = util.compengines.forbundletype(value)
     if value is not None:
         unbundler._compressed = True
 
 
 class bundlepart(object):
     """A bundle2 part contains application level payload
 
     The part `type` is used to route the part to the application level
     handler.
 
     The part payload is contained in ``part.data``. It could be raw bytes or a
     generator of byte chunks.
 
     You can add parameters to the part using the ``addparam`` method.
     Parameters can be either mandatory (default) or advisory. Remote side
     should be able to safely ignore the advisory ones.
 
     Both data and parameters cannot be modified after the generation has begun.
     """
 
     def __init__(
         self,
         parttype,
         mandatoryparams=(),
         advisoryparams=(),
         data=b'',
         mandatory=True,
     ):
         validateparttype(parttype)
         self.id = None
         self.type = parttype
         self._data = data
         self._mandatoryparams = list(mandatoryparams)
         self._advisoryparams = list(advisoryparams)
         # checking for duplicated entries
         self._seenparams = set()
         for pname, __ in self._mandatoryparams + self._advisoryparams:
             if pname in self._seenparams:
                 raise error.ProgrammingError(b'duplicated params: %s' % pname)
             self._seenparams.add(pname)
         # status of the part's generation:
         # - None: not started,
         # - False: currently generated,
         # - True: generation done.
         self._generated = None
         self.mandatory = mandatory
 
     def __repr__(self):
         cls = b"%s.%s" % (self.__class__.__module__, self.__class__.__name__)
         return b'<%s object at %x; id: %s; type: %s; mandatory: %s>' % (
             cls,
             id(self),
             self.id,
             self.type,
             self.mandatory,
         )
 
     def copy(self):
         """return a copy of the part
 
         The new part have the very same content but no partid assigned yet.
         Parts with generated data cannot be copied."""
         assert not util.safehasattr(self.data, b'next')
         return self.__class__(
             self.type,
             self._mandatoryparams,
             self._advisoryparams,
             self._data,
             self.mandatory,
         )
 
     # methods used to defines the part content
     @property
     def data(self):
         return self._data
 
     @data.setter
     def data(self, data):
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         self._data = data
 
     @property
     def mandatoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._mandatoryparams)
 
     @property
     def advisoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._advisoryparams)
 
     def addparam(self, name, value=b'', mandatory=True):
         """add a parameter to the part
 
         If 'mandatory' is set to True, the remote handler must claim support
         for this parameter or the unbundling will be aborted.
 
         The 'name' and 'value' cannot exceed 255 bytes each.
         """
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         if name in self._seenparams:
             raise ValueError(b'duplicated params: %s' % name)
         self._seenparams.add(name)
         params = self._advisoryparams
         if mandatory:
             params = self._mandatoryparams
         params.append((name, value))
 
     # methods used to generates the bundle2 stream
     def getchunks(self, ui):
         if self._generated is not None:
             raise error.ProgrammingError(b'part can only be consumed once')
         self._generated = False
 
         if ui.debugflag:
             msg = [b'bundle2-output-part: "%s"' % self.type]
             if not self.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(self.mandatoryparams)
             nbap = len(self.advisoryparams)
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             if not self.data:
                 msg.append(b' empty payload')
             elif util.safehasattr(self.data, b'next') or util.safehasattr(
                 self.data, b'__next__'
             ):
                 msg.append(b' streamed payload')
             else:
                 msg.append(b' %i bytes payload' % len(self.data))
             msg.append(b'\n')
             ui.debug(b''.join(msg))
 
         #### header
         if self.mandatory:
             parttype = self.type.upper()
         else:
             parttype = self.type.lower()
         outdebug(ui, b'part %s: "%s"' % (pycompat.bytestr(self.id), parttype))
         ## parttype
         header = [
             _pack(_fparttypesize, len(parttype)),
             parttype,
             _pack(_fpartid, self.id),
         ]
         ## parameters
         # count
         manpar = self.mandatoryparams
         advpar = self.advisoryparams
         header.append(_pack(_fpartparamcount, len(manpar), len(advpar)))
         # size
         parsizes = []
         for key, value in manpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         for key, value in advpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         paramsizes = _pack(_makefpartparamsizes(len(parsizes) // 2), *parsizes)
         header.append(paramsizes)
         # key, value
         for key, value in manpar:
             header.append(key)
             header.append(value)
         for key, value in advpar:
             header.append(key)
             header.append(value)
         ## finalize header
         try:
             headerchunk = b''.join(header)
         except TypeError:
             raise TypeError(
                 r'Found a non-bytes trying to '
                 r'build bundle part header: %r' % header
             )
         outdebug(ui, b'header chunk size: %i' % len(headerchunk))
         yield _pack(_fpartheadersize, len(headerchunk))
         yield headerchunk
         ## payload
         try:
             for chunk in self._payloadchunks():
                 outdebug(ui, b'payload chunk size: %i' % len(chunk))
                 yield _pack(_fpayloadsize, len(chunk))
                 yield chunk
         except GeneratorExit:
             # GeneratorExit means that nobody is listening for our
             # results anyway, so just bail quickly rather than trying
             # to produce an error part.
             ui.debug(b'bundle2-generatorexit\n')
             raise
         except BaseException as exc:
             bexc = stringutil.forcebytestr(exc)
             # backup exception data for later
             ui.debug(
                 b'bundle2-input-stream-interrupt: encoding exception %s' % bexc
             )
             tb = sys.exc_info()[2]
             msg = b'unexpected error: %s' % bexc
             interpart = bundlepart(
                 b'error:abort', [(b'message', msg)], mandatory=False
             )
             interpart.id = 0
             yield _pack(_fpayloadsize, -1)
             for chunk in interpart.getchunks(ui=ui):
                 yield chunk
             outdebug(ui, b'closing payload chunk')
             # abort current part payload
             yield _pack(_fpayloadsize, 0)
             pycompat.raisewithtb(exc, tb)
         # end of payload
         outdebug(ui, b'closing payload chunk')
         yield _pack(_fpayloadsize, 0)
         self._generated = True
 
     def _payloadchunks(self):
         """yield chunks of a the part payload
 
         Exists to handle the different methods to provide data to a part."""
         # we only support fixed size data now.
         # This will be improved in the future.
         if util.safehasattr(self.data, b'next') or util.safehasattr(
             self.data, b'__next__'
         ):
             buff = util.chunkbuffer(self.data)
             chunk = buff.read(preferedchunksize)
             while chunk:
                 yield chunk
                 chunk = buff.read(preferedchunksize)
         elif len(self.data):
             yield self.data
 
 
 flaginterrupt = -1
 
 
 class interrupthandler(unpackermixin):
     """read one part and process it with restricted capability
 
     This allows to transmit exception raised on the producer size during part
     iteration while the consumer is reading a part.
 
     Part processed in this manner only have access to a ui object,"""
 
     def __init__(self, ui, fp):
         super(interrupthandler, self).__init__(fp)
         self.ui = ui
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i\n' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def __call__(self):
 
         self.ui.debug(
             b'bundle2-input-stream-interrupt:' b' opening out of band context\n'
         )
         indebug(self.ui, b'bundle2 stream interruption, looking for a part.')
         headerblock = self._readpartheader()
         if headerblock is None:
             indebug(self.ui, b'no part found during interruption.')
             return
         part = unbundlepart(self.ui, headerblock, self._fp)
         op = interruptoperation(self.ui)
         hardabort = False
         try:
             _processpart(op, part)
         except (SystemExit, KeyboardInterrupt):
             hardabort = True
             raise
         finally:
             if not hardabort:
                 part.consume()
         self.ui.debug(
             b'bundle2-input-stream-interrupt:' b' closing out of band context\n'
         )
 
 
 class interruptoperation(object):
     """A limited operation to be use by part handler during interruption
 
     It only have access to an ui object.
     """
 
     def __init__(self, ui):
         self.ui = ui
         self.reply = None
         self.captureoutput = False
 
     @property
     def repo(self):
         raise error.ProgrammingError(b'no repo access from stream interruption')
 
     def gettransaction(self):
         raise TransactionUnavailable(b'no repo access from stream interruption')
 
 
 def decodepayloadchunks(ui, fh):
     """Reads bundle2 part payload data into chunks.
 
     Part payload data consists of framed chunks. This function takes
     a file handle and emits those chunks.
     """
     dolog = ui.configbool(b'devel', b'bundle2.debug')
     debug = ui.debug
 
     headerstruct = struct.Struct(_fpayloadsize)
     headersize = headerstruct.size
     unpack = headerstruct.unpack
 
     readexactly = changegroup.readexactly
     read = fh.read
 
     chunksize = unpack(readexactly(fh, headersize))[0]
     indebug(ui, b'payload chunk size: %i' % chunksize)
 
     # changegroup.readexactly() is inlined below for performance.
     while chunksize:
         if chunksize >= 0:
             s = read(chunksize)
             if len(s) < chunksize:
                 raise error.Abort(
                     _(
                         b'stream ended unexpectedly '
                         b' (got %d bytes, expected %d)'
                     )
                     % (len(s), chunksize)
                 )
 
             yield s
         elif chunksize == flaginterrupt:
             # Interrupt "signal" detected. The regular stream is interrupted
             # and a bundle2 part follows. Consume it.
             interrupthandler(ui, fh)()
         else:
             raise error.BundleValueError(
                 b'negative payload chunk size: %s' % chunksize
             )
 
         s = read(headersize)
         if len(s) < headersize:
             raise error.Abort(
                 _(b'stream ended unexpectedly ' b' (got %d bytes, expected %d)')
                 % (len(s), chunksize)
             )
 
         chunksize = unpack(s)[0]
 
         # indebug() inlined for performance.
         if dolog:
             debug(b'bundle2-input: payload chunk size: %i\n' % chunksize)
 
 
 class unbundlepart(unpackermixin):
     """a bundle part read from a bundle"""
 
     def __init__(self, ui, header, fp):
         super(unbundlepart, self).__init__(fp)
         self._seekable = util.safehasattr(fp, b'seek') and util.safehasattr(
             fp, b'tell'
         )
         self.ui = ui
         # unbundle state attr
         self._headerdata = header
         self._headeroffset = 0
         self._initialized = False
         self.consumed = False
         # part data
         self.id = None
         self.type = None
         self.mandatoryparams = None
         self.advisoryparams = None
         self.params = None
         self.mandatorykeys = ()
         self._readheader()
         self._mandatory = None
         self._pos = 0
 
     def _fromheader(self, size):
         """return the next <size> byte from the header"""
         offset = self._headeroffset
         data = self._headerdata[offset : (offset + size)]
         self._headeroffset = offset + size
         return data
 
     def _unpackheader(self, format):
         """read given format from header
 
         This automatically compute the size of the format to read."""
         data = self._fromheader(struct.calcsize(format))
         return _unpack(format, data)
 
     def _initparams(self, mandatoryparams, advisoryparams):
         """internal function to setup all logic related parameters"""
         # make it read only to prevent people touching it by mistake.
         self.mandatoryparams = tuple(mandatoryparams)
         self.advisoryparams = tuple(advisoryparams)
         # user friendly UI
         self.params = util.sortdict(self.mandatoryparams)
         self.params.update(self.advisoryparams)
         self.mandatorykeys = frozenset(p[0] for p in mandatoryparams)
 
     def _readheader(self):
         """read the header and setup the object"""
         typesize = self._unpackheader(_fparttypesize)[0]
         self.type = self._fromheader(typesize)
         indebug(self.ui, b'part type: "%s"' % self.type)
         self.id = self._unpackheader(_fpartid)[0]
         indebug(self.ui, b'part id: "%s"' % pycompat.bytestr(self.id))
         # extract mandatory bit from type
         self.mandatory = self.type != self.type.lower()
         self.type = self.type.lower()
         ## reading parameters
         # param count
         mancount, advcount = self._unpackheader(_fpartparamcount)
         indebug(self.ui, b'part parameters: %i' % (mancount + advcount))
         # param size
         fparamsizes = _makefpartparamsizes(mancount + advcount)
         paramsizes = self._unpackheader(fparamsizes)
         # make it a list of couple again
         paramsizes = list(zip(paramsizes[::2], paramsizes[1::2]))
         # split mandatory from advisory
         mansizes = paramsizes[:mancount]
         advsizes = paramsizes[mancount:]
         # retrieve param value
         manparams = []
         for key, value in mansizes:
             manparams.append((self._fromheader(key), self._fromheader(value)))
         advparams = []
         for key, value in advsizes:
             advparams.append((self._fromheader(key), self._fromheader(value)))
         self._initparams(manparams, advparams)
         ## part payload
         self._payloadstream = util.chunkbuffer(self._payloadchunks())
         # we read the data, tell it
         self._initialized = True
 
     def _payloadchunks(self):
         """Generator of decoded chunks in the payload."""
         return decodepayloadchunks(self.ui, self._fp)
 
     def consume(self):
         """Read the part payload until completion.
 
         By consuming the part data, the underlying stream read offset will
         be advanced to the next part (or end of stream).
         """
         if self.consumed:
             return
 
         chunk = self.read(32768)
         while chunk:
             self._pos += len(chunk)
             chunk = self.read(32768)
 
     def read(self, size=None):
         """read payload data"""
         if not self._initialized:
             self._readheader()
         if size is None:
             data = self._payloadstream.read()
         else:
             data = self._payloadstream.read(size)
         self._pos += len(data)
         if size is None or len(data) < size:
             if not self.consumed and self._pos:
                 self.ui.debug(
                     b'bundle2-input-part: total payload size %i\n' % self._pos
                 )
             self.consumed = True
         return data
 
 
 class seekableunbundlepart(unbundlepart):
     """A bundle2 part in a bundle that is seekable.
 
     Regular ``unbundlepart`` instances can only be read once. This class
     extends ``unbundlepart`` to enable bi-directional seeking within the
     part.
 
     Bundle2 part data consists of framed chunks. Offsets when seeking
     refer to the decoded data, not the offsets in the underlying bundle2
     stream.
 
     To facilitate quickly seeking within the decoded data, instances of this
     class maintain a mapping between offsets in the underlying stream and
     the decoded payload. This mapping will consume memory in proportion
     to the number of chunks within the payload (which almost certainly
     increases in proportion with the size of the part).
     """
 
     def __init__(self, ui, header, fp):
         # (payload, file) offsets for chunk starts.
         self._chunkindex = []
 
         super(seekableunbundlepart, self).__init__(ui, header, fp)
 
     def _payloadchunks(self, chunknum=0):
         '''seek to specified chunk and start yielding data'''
         if len(self._chunkindex) == 0:
             assert chunknum == 0, b'Must start with chunk 0'
             self._chunkindex.append((0, self._tellfp()))
         else:
             assert chunknum < len(self._chunkindex), (
                 b'Unknown chunk %d' % chunknum
             )
             self._seekfp(self._chunkindex[chunknum][1])
 
         pos = self._chunkindex[chunknum][0]
 
         for chunk in decodepayloadchunks(self.ui, self._fp):
             chunknum += 1
             pos += len(chunk)
             if chunknum == len(self._chunkindex):
                 self._chunkindex.append((pos, self._tellfp()))
 
             yield chunk
 
     def _findchunk(self, pos):
         '''for a given payload position, return a chunk number and offset'''
         for chunk, (ppos, fpos) in enumerate(self._chunkindex):
             if ppos == pos:
                 return chunk, 0
             elif ppos > pos:
                 return chunk - 1, pos - self._chunkindex[chunk - 1][0]
         raise ValueError(b'Unknown chunk')
 
     def tell(self):
         return self._pos
 
     def seek(self, offset, whence=os.SEEK_SET):
         if whence == os.SEEK_SET:
             newpos = offset
         elif whence == os.SEEK_CUR:
             newpos = self._pos + offset
         elif whence == os.SEEK_END:
             if not self.consumed:
                 # Can't use self.consume() here because it advances self._pos.
                 chunk = self.read(32768)
                 while chunk:
                     chunk = self.read(32768)
             newpos = self._chunkindex[-1][0] - offset
         else:
             raise ValueError(b'Unknown whence value: %r' % (whence,))
 
         if newpos > self._chunkindex[-1][0] and not self.consumed:
             # Can't use self.consume() here because it advances self._pos.
             chunk = self.read(32768)
             while chunk:
                 chunk = self.read(32668)
 
         if not 0 <= newpos <= self._chunkindex[-1][0]:
             raise ValueError(b'Offset out of range')
 
         if self._pos != newpos:
             chunk, internaloffset = self._findchunk(newpos)
             self._payloadstream = util.chunkbuffer(self._payloadchunks(chunk))
             adjust = self.read(internaloffset)
             if len(adjust) != internaloffset:
                 raise error.Abort(_(b'Seek failed\n'))
             self._pos = newpos
 
     def _seekfp(self, offset, whence=0):
         """move the underlying file pointer
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             return self._fp.seek(offset, whence)
         else:
             raise NotImplementedError(_(b'File pointer is not seekable'))
 
     def _tellfp(self):
         """return the file offset, or None if file is not seekable
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             try:
                 return self._fp.tell()
             except IOError as e:
                 if e.errno == errno.ESPIPE:
                     self._seekable = False
                 else:
                     raise
         return None
 
 
 # These are only the static capabilities.
 # Check the 'getrepocaps' function for the rest.
 capabilities = {
     b'HG20': (),
     b'bookmarks': (),
     b'error': (b'abort', b'unsupportedcontent', b'pushraced', b'pushkey'),
     b'listkeys': (),
     b'pushkey': (),
     b'digests': tuple(sorted(util.DIGESTS.keys())),
     b'remote-changegroup': (b'http', b'https'),
     b'hgtagsfnodes': (),
     b'rev-branch-cache': (),
     b'phases': (b'heads',),
     b'stream': (b'v2',),
 }
 
 
 def getrepocaps(repo, allowpushback=False, role=None):
     """return the bundle2 capabilities for a given repo
 
     Exists to allow extensions (like evolution) to mutate the capabilities.
 
     The returned value is used for servers advertising their capabilities as
     well as clients advertising their capabilities to servers as part of
     bundle2 requests. The ``role`` argument specifies which is which.
     """
     if role not in (b'client', b'server'):
         raise error.ProgrammingError(b'role argument must be client or server')
 
     caps = capabilities.copy()
     caps[b'changegroup'] = tuple(
         sorted(changegroup.supportedincomingversions(repo))
     )
     if obsolete.isenabled(repo, obsolete.exchangeopt):
         supportedformat = tuple(b'V%i' % v for v in obsolete.formats)
         caps[b'obsmarkers'] = supportedformat
     if allowpushback:
         caps[b'pushback'] = ()
     cpmode = repo.ui.config(b'server', b'concurrent-push-mode')
     if cpmode == b'check-related':
         caps[b'checkheads'] = (b'related',)
     if b'phases' in repo.ui.configlist(b'devel', b'legacy.exchange'):
         caps.pop(b'phases')
 
     # Don't advertise stream clone support in server mode if not configured.
     if role == b'server':
         streamsupported = repo.ui.configbool(
             b'server', b'uncompressed', untrusted=True
         )
         featuresupported = repo.ui.configbool(b'server', b'bundle2.stream')
 
         if not streamsupported or not featuresupported:
             caps.pop(b'stream')
     # Else always advertise support on client, because payload support
     # should always be advertised.
 
     return caps
 
 
 def bundle2caps(remote):
     """return the bundle capabilities of a peer as dict"""
     raw = remote.capable(b'bundle2')
     if not raw and raw != b'':
         return {}
     capsblob = urlreq.unquote(remote.capable(b'bundle2'))
     return decodecaps(capsblob)
 
 
 def obsmarkersversion(caps):
     """extract the list of supported obsmarkers versions from a bundle2caps dict
     """
     obscaps = caps.get(b'obsmarkers', ())
     return [int(c[1:]) for c in obscaps if c.startswith(b'V')]
 
 
 def writenewbundle(
     ui,
     repo,
     source,
     filename,
     bundletype,
     outgoing,
     opts,
     vfs=None,
     compression=None,
     compopts=None,
 ):
     if bundletype.startswith(b'HG10'):
         cg = changegroup.makechangegroup(repo, outgoing, b'01', source)
         return writebundle(
             ui,
             cg,
             filename,
             bundletype,
             vfs=vfs,
             compression=compression,
             compopts=compopts,
         )
     elif not bundletype.startswith(b'HG20'):
         raise error.ProgrammingError(b'unknown bundle type: %s' % bundletype)
 
     caps = {}
     if b'obsolescence' in opts:
         caps[b'obsmarkers'] = (b'V1',)
     bundle = bundle20(ui, caps)
     bundle.setcompression(compression, compopts)
     _addpartsfromopts(ui, repo, bundle, source, outgoing, opts)
     chunkiter = bundle.getchunks()
 
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def _addpartsfromopts(ui, repo, bundler, source, outgoing, opts):
     # We should eventually reconcile this logic with the one behind
     # 'exchange.getbundle2partsgenerator'.
     #
     # The type of input from 'getbundle' and 'writenewbundle' are a bit
     # different right now. So we keep them separated for now for the sake of
     # simplicity.
 
     # we might not always want a changegroup in such bundle, for example in
     # stream bundles
     if opts.get(b'changegroup', True):
         cgversion = opts.get(b'cg.version')
         if cgversion is None:
             cgversion = changegroup.safeversion(repo)
         cg = changegroup.makechangegroup(repo, outgoing, cgversion, source)
         part = bundler.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         if opts.get(b'phases') and repo.revs(
             b'%ln and secret()', outgoing.missingheads
         ):
             part.addparam(
                 b'targetphase', b'%d' % phases.secret, mandatory=False
             )
 
     if opts.get(b'streamv2', False):
         addpartbundlestream2(bundler, repo, stream=True)
 
     if opts.get(b'tagsfnodescache', True):
         addparttagsfnodescache(repo, bundler, outgoing)
 
     if opts.get(b'revbranchcache', True):
         addpartrevbranchcache(repo, bundler, outgoing)
 
     if opts.get(b'obsolescence', False):
         obsmarkers = repo.obsstore.relevantmarkers(outgoing.missing)
         buildobsmarkerspart(bundler, obsmarkers)
 
     if opts.get(b'phases', False):
         headsbyphase = phases.subsetphaseheads(repo, outgoing.missing)
         phasedata = phases.binaryencode(headsbyphase)
         bundler.newpart(b'phase-heads', data=phasedata)
 
 
 def addparttagsfnodescache(repo, bundler, outgoing):
     # we include the tags fnode cache for the bundle changeset
     # (as an optional parts)
     cache = tags.hgtagsfnodescache(repo.unfiltered())
     chunks = []
 
     # .hgtags fnodes are only relevant for head changesets. While we could
     # transfer values for all known nodes, there will likely be little to
     # no benefit.
     #
     # We don't bother using a generator to produce output data because
     # a) we only have 40 bytes per head and even esoteric numbers of heads
     # consume little memory (1M heads is 40MB) b) we don't want to send the
     # part if we don't have entries and knowing if we have entries requires
     # cache lookups.
     for node in outgoing.missingheads:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode is not None:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart(b'hgtagsfnodes', data=b''.join(chunks))
 
 
 def addpartrevbranchcache(repo, bundler, outgoing):
     # we include the rev branch cache for the bundle changeset
     # (as an optional parts)
     cache = repo.revbranchcache()
     cl = repo.unfiltered().changelog
     branchesdata = collections.defaultdict(lambda: (set(), set()))
     for node in outgoing.missing:
         branch, close = cache.branchinfo(cl.rev(node))
         branchesdata[branch][close].add(node)
 
     def generate():
         for branch, (nodes, closed) in sorted(branchesdata.items()):
             utf8branch = encoding.fromlocal(branch)
             yield rbcstruct.pack(len(utf8branch), len(nodes), len(closed))
             yield utf8branch
             for n in sorted(nodes):
                 yield n
             for n in sorted(closed):
                 yield n
 
     bundler.newpart(b'cache:rev-branch-cache', data=generate(), mandatory=False)
 
 
 def _formatrequirementsspec(requirements):
     requirements = [req for req in requirements if req != b"shared"]
     return urlreq.quote(b','.join(sorted(requirements)))
 
 
 def _formatrequirementsparams(requirements):
     requirements = _formatrequirementsspec(requirements)
     params = b"%s%s" % (urlreq.quote(b"requirements="), requirements)
     return params
 
 
 def addpartbundlestream2(bundler, repo, **kwargs):
     if not kwargs.get(r'stream', False):
         return
 
     if not streamclone.allowservergeneration(repo):
         raise error.Abort(
             _(
                 b'stream data requested but server does not allow '
                 b'this feature'
             ),
             hint=_(
                 b'well-behaved clients should not be '
                 b'requesting stream data from servers not '
                 b'advertising it; the client may be buggy'
             ),
         )
 
     # Stream clones don't compress well. And compression undermines a
     # goal of stream clones, which is to be fast. Communicate the desire
     # to avoid compression to consumers of the bundle.
     bundler.prefercompressed = False
 
     # get the includes and excludes
     includepats = kwargs.get(r'includepats')
     excludepats = kwargs.get(r'excludepats')
 
     narrowstream = repo.ui.configbool(
         b'experimental', b'server.stream-narrow-clones'
     )
 
     if (includepats or excludepats) and not narrowstream:
         raise error.Abort(_(b'server does not support narrow stream clones'))
 
     includeobsmarkers = False
     if repo.obsstore:
         remoteversions = obsmarkersversion(bundler.capabilities)
         if not remoteversions:
             raise error.Abort(
                 _(
                     b'server has obsolescence markers, but client '
                     b'cannot receive them via stream clone'
                 )
             )
         elif repo.obsstore._version in remoteversions:
             includeobsmarkers = True
 
     filecount, bytecount, it = streamclone.generatev2(
         repo, includepats, excludepats, includeobsmarkers
     )
     requirements = _formatrequirementsspec(repo.requirements)
     part = bundler.newpart(b'stream2', data=it)
     part.addparam(b'bytecount', b'%d' % bytecount, mandatory=True)
     part.addparam(b'filecount', b'%d' % filecount, mandatory=True)
     part.addparam(b'requirements', requirements, mandatory=True)
 
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if not markers:
         return None
 
     remoteversions = obsmarkersversion(bundler.capabilities)
     version = obsolete.commonversion(remoteversions)
     if version is None:
         raise ValueError(b'bundler does not support common obsmarker format')
     stream = obsolete.encodemarkers(markers, True, version=version)
     return bundler.newpart(b'obsmarkers', data=stream)
 
 
 def writebundle(
     ui, cg, filename, bundletype, vfs=None, compression=None, compopts=None
 ):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     if bundletype == b"HG20":
         bundle = bundle20(ui)
         bundle.setcompression(compression, compopts)
         part = bundle.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         chunkiter = bundle.getchunks()
     else:
         # compression argument is only for the bundle2 case
         assert compression is None
         if cg.version != b'01':
             raise error.Abort(
                 _(b'old bundle types only supports v1 ' b'changegroups')
             )
         header, comp = bundletypes[bundletype]
         if comp not in util.compengines.supportedbundletypes:
             raise error.Abort(_(b'unknown stream compression type: %s') % comp)
         compengine = util.compengines.forbundletype(comp)
 
         def chunkiter():
             yield header
             for chunk in compengine.compressstream(cg.getchunks(), compopts):
                 yield chunk
 
         chunkiter = chunkiter()
 
     # parse the changegroup data, otherwise we will block
     # in case of sshrepo because we don't know the end of the stream
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def combinechangegroupresults(op):
     """logic to combine 0 or more addchangegroup results into one"""
     results = [r.get(b'return', 0) for r in op.records[b'changegroup']]
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 
 @parthandler(
     b'changegroup', (b'version', b'nbchanges', b'treemanifest', b'targetphase')
 )
 def handlechangegroup(op, inpart):
     """apply a changegroup part on the repo
 
     This is a very early implementation that will massive rework before being
     inflicted to any end-user.
     """
     from . import localrepo
 
     tr = op.gettransaction()
     unpackerversion = inpart.params.get(b'version', b'01')
     # We should raise an appropriate exception here
     cg = changegroup.getunbundler(unpackerversion, inpart, None)
     # the source and url passed here are overwritten by the one contained in
     # the transaction.hookargs argument. So 'bundle2' is a placeholder
     nbchangesets = None
     if b'nbchanges' in inpart.params:
         nbchangesets = int(inpart.params.get(b'nbchanges'))
     if (
         b'treemanifest' in inpart.params
         and b'treemanifest' not in op.repo.requirements
     ):
         if len(op.repo.changelog) != 0:
             raise error.Abort(
                 _(
                     b"bundle contains tree manifests, but local repo is "
                     b"non-empty and does not use tree manifests"
                 )
             )
         op.repo.requirements.add(b'treemanifest')
         op.repo.svfs.options = localrepo.resolvestorevfsoptions(
             op.repo.ui, op.repo.requirements, op.repo.features
         )
         op.repo._writerequirements()
     extrakwargs = {}
     targetphase = inpart.params.get(b'targetphase')
     if targetphase is not None:
         extrakwargs[r'targetphase'] = int(targetphase)
     ret = _processchangegroup(
         op,
         cg,
         tr,
         b'bundle2',
         b'bundle2',
         expectedtotal=nbchangesets,
         **extrakwargs
     )
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup', mandatory=False)
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     assert not inpart.read()
 
 
 _remotechangegroupparams = tuple(
     [b'url', b'size', b'digests']
     + [b'digest:%s' % k for k in util.DIGESTS.keys()]
 )
 
 
 @parthandler(b'remote-changegroup', _remotechangegroupparams)
 def handleremotechangegroup(op, inpart):
     """apply a bundle10 on the repo, given an url and validation information
 
     All the information about the remote bundle to import are given as
     parameters. The parameters include:
       - url: the url to the bundle10.
       - size: the bundle10 file size. It is used to validate what was
         retrieved by the client matches the server knowledge about the bundle.
       - digests: a space separated list of the digest types provided as
         parameters.
       - digest:<digest-type>: the hexadecimal representation of the digest with
         that name. Like the size, it is used to validate what was retrieved by
         the client matches what the server knows about the bundle.
 
     When multiple digest types are given, all of them are checked.
     """
     try:
         raw_url = inpart.params[b'url']
     except KeyError:
         raise error.Abort(_(b'remote-changegroup: missing "%s" param') % b'url')
     parsed_url = util.url(raw_url)
     if parsed_url.scheme not in capabilities[b'remote-changegroup']:
         raise error.Abort(
             _(b'remote-changegroup does not support %s urls')
             % parsed_url.scheme
         )
 
     try:
         size = int(inpart.params[b'size'])
     except ValueError:
         raise error.Abort(
             _(b'remote-changegroup: invalid value for param "%s"') % b'size'
         )
     except KeyError:
         raise error.Abort(
             _(b'remote-changegroup: missing "%s" param') % b'size'
         )
 
     digests = {}
     for typ in inpart.params.get(b'digests', b'').split():
         param = b'digest:%s' % typ
         try:
             value = inpart.params[param]
         except KeyError:
             raise error.Abort(
                 _(b'remote-changegroup: missing "%s" param') % param
             )
         digests[typ] = value
 
     real_part = util.digestchecker(url.open(op.ui, raw_url), size, digests)
 
     tr = op.gettransaction()
     from . import exchange
 
     cg = exchange.readbundle(op.repo.ui, real_part, raw_url)
     if not isinstance(cg, changegroup.cg1unpacker):
         raise error.Abort(
             _(b'%s: not a bundle version 1.0') % util.hidepassword(raw_url)
         )
     ret = _processchangegroup(op, cg, tr, b'bundle2', b'bundle2')
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup')
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     try:
         real_part.validate()
     except error.Abort as e:
         raise error.Abort(
             _(b'bundle at %s is corrupted:\n%s')
             % (util.hidepassword(raw_url), bytes(e))
         )
     assert not inpart.read()
 
 
 @parthandler(b'reply:changegroup', (b'return', b'in-reply-to'))
 def handlereplychangegroup(op, inpart):
     ret = int(inpart.params[b'return'])
     replyto = int(inpart.params[b'in-reply-to'])
     op.records.add(b'changegroup', {b'return': ret}, replyto)
 
 
 @parthandler(b'check:bookmarks')
 def handlecheckbookmarks(op, inpart):
     """check location of bookmarks
 
     This part is to be used to detect push race regarding bookmark, it
     contains binary encoded (bookmark, node) tuple. If the local state does
     not marks the one in the part, a PushRaced exception is raised
     """
     bookdata = bookmarks.binarydecode(inpart)
 
     msgstandard = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" move from %s to %s)'
     )
     msgmissing = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" is missing, expected %s)'
     )
     msgexist = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" set on %s, expected missing)'
     )
     for book, node in bookdata:
         currentnode = op.repo._bookmarks.get(book)
         if currentnode != node:
             if node is None:
                 finalmsg = msgexist % (book, nodemod.short(currentnode))
             elif currentnode is None:
                 finalmsg = msgmissing % (book, nodemod.short(node))
             else:
                 finalmsg = msgstandard % (
                     book,
                     nodemod.short(node),
                     nodemod.short(currentnode),
                 )
             raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'check:heads')
 def handlecheckheads(op, inpart):
     """check that head of the repo did not change
 
     This is used to detect a push race when using unbundle.
     This replaces the "heads" argument of unbundle."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # Trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     if sorted(heads) != sorted(op.repo.heads()):
         raise error.PushRaced(
             b'remote repository changed while pushing - ' b'please try again'
         )
 
 
 @parthandler(b'check:updated-heads')
 def handlecheckupdatedheads(op, inpart):
     """check for race on the heads touched by a push
 
     This is similar to 'check:heads' but focus on the heads actually updated
     during the push. If other activities happen on unrelated heads, it is
     ignored.
 
     This allow server with high traffic to avoid push contention as long as
     unrelated parts of the graph are involved."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
 
     currentheads = set()
     for ls in op.repo.branchmap().iterheads():
         currentheads.update(ls)
 
     for h in heads:
         if h not in currentheads:
             raise error.PushRaced(
                 b'remote repository changed while pushing - '
                 b'please try again'
             )
 
 
 @parthandler(b'check:phases')
 def handlecheckphases(op, inpart):
     """check that phase boundaries of the repository did not change
 
     This is used to detect a push race.
     """
     phasetonodes = phases.binarydecode(inpart)
     unfi = op.repo.unfiltered()
     cl = unfi.changelog
     phasecache = unfi._phasecache
     msg = (
         b'remote repository changed while pushing - please try again '
         b'(%s is %s expected %s)'
     )
     for expectedphase, nodes in enumerate(phasetonodes):
         for n in nodes:
             actualphase = phasecache.phase(unfi, cl.rev(n))
             if actualphase != expectedphase:
                 finalmsg = msg % (
                     nodemod.short(n),
                     phases.phasenames[actualphase],
                     phases.phasenames[expectedphase],
                 )
                 raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'output')
 def handleoutput(op, inpart):
     """forward output captured on the server to the client"""
     for line in inpart.read().splitlines():
         op.ui.status(_(b'remote: %s\n') % line)
 
 
 @parthandler(b'replycaps')
 def handlereplycaps(op, inpart):
     """Notify that a reply bundle should be created
 
     The payload contains the capabilities information for the reply"""
     caps = decodecaps(inpart.read())
     if op.reply is None:
         op.reply = bundle20(op.ui, caps)
 
 
 class AbortFromPart(error.Abort):
     """Sub-class of Abort that denotes an error from a bundle2 part."""
 
 
 @parthandler(b'error:abort', (b'message', b'hint'))
 def handleerrorabort(op, inpart):
     """Used to transmit abort error over the wire"""
     raise AbortFromPart(
         inpart.params[b'message'], hint=inpart.params.get(b'hint')
     )
 
 
 @parthandler(
     b'error:pushkey',
     (b'namespace', b'key', b'new', b'old', b'ret', b'in-reply-to'),
 )
 def handleerrorpushkey(op, inpart):
     """Used to transmit failure of a mandatory pushkey over the wire"""
     kwargs = {}
     for name in (b'namespace', b'key', b'new', b'old', b'ret'):
         value = inpart.params.get(name)
         if value is not None:
             kwargs[name] = value
     raise error.PushkeyFailed(
         inpart.params[b'in-reply-to'], **pycompat.strkwargs(kwargs)
     )
 
 
 @parthandler(b'error:unsupportedcontent', (b'parttype', b'params'))
 def handleerrorunsupportedcontent(op, inpart):
     """Used to transmit unknown content error over the wire"""
     kwargs = {}
     parttype = inpart.params.get(b'parttype')
     if parttype is not None:
         kwargs[b'parttype'] = parttype
     params = inpart.params.get(b'params')
     if params is not None:
         kwargs[b'params'] = params.split(b'\0')
 
     raise error.BundleUnknownFeatureError(**pycompat.strkwargs(kwargs))
 
 
 @parthandler(b'error:pushraced', (b'message',))
 def handleerrorpushraced(op, inpart):
     """Used to transmit push race error over the wire"""
     raise error.ResponseError(_(b'push failed:'), inpart.params[b'message'])
 
 
 @parthandler(b'listkeys', (b'namespace',))
 def handlelistkeys(op, inpart):
     """retrieve pushkey namespace content stored in a bundle2"""
     namespace = inpart.params[b'namespace']
     r = pushkey.decodekeys(inpart.read())
     op.records.add(b'listkeys', (namespace, r))
 
 
 @parthandler(b'pushkey', (b'namespace', b'key', b'old', b'new'))
 def handlepushkey(op, inpart):
     """process a pushkey request"""
     dec = pushkey.decode
     namespace = dec(inpart.params[b'namespace'])
     key = dec(inpart.params[b'key'])
     old = dec(inpart.params[b'old'])
     new = dec(inpart.params[b'new'])
     # Grab the transaction to ensure that we have the lock before performing the
     # pushkey.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     ret = op.repo.pushkey(namespace, key, old, new)
     record = {b'namespace': namespace, b'key': key, b'old': old, b'new': new}
     op.records.add(b'pushkey', record)
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:pushkey')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'return', b'%i' % ret, mandatory=False)
     if inpart.mandatory and not ret:
         kwargs = {}
         for key in (b'namespace', b'key', b'new', b'old', b'ret'):
             if key in inpart.params:
                 kwargs[key] = inpart.params[key]
         raise error.PushkeyFailed(
             partid=b'%d' % inpart.id, **pycompat.strkwargs(kwargs)
         )
 
 
 @parthandler(b'bookmarks')
 def handlebookmark(op, inpart):
     """transmit bookmark information
 
     The part contains binary encoded bookmark information.
 
     The exact behavior of this part can be controlled by the 'bookmarks' mode
     on the bundle operation.
 
     When mode is 'apply' (the default) the bookmark information is applied as
     is to the unbundling repository. Make sure a 'check:bookmarks' part is
     issued earlier to check for push races in such update. This behavior is
     suitable for pushing.
 
     When mode is 'records', the information is recorded into the 'bookmarks'
     records of the bundle operation. This behavior is suitable for pulling.
     """
     changes = bookmarks.binarydecode(inpart)
 
     pushkeycompat = op.repo.ui.configbool(
         b'server', b'bookmarks-pushkey-compat'
     )
     bookmarksmode = op.modes.get(b'bookmarks', b'apply')
 
     if bookmarksmode == b'apply':
         tr = op.gettransaction()
         bookstore = op.repo._bookmarks
         if pushkeycompat:
             allhooks = []
             for book, node in changes:
                 hookargs = tr.hookargs.copy()
                 hookargs[b'pushkeycompat'] = b'1'
                 hookargs[b'namespace'] = b'bookmarks'
                 hookargs[b'key'] = book
                 hookargs[b'old'] = nodemod.hex(bookstore.get(book, b''))
                 hookargs[b'new'] = nodemod.hex(
                     node if node is not None else b''
                 )
                 allhooks.append(hookargs)
 
             for hookargs in allhooks:
                 op.repo.hook(
                     b'prepushkey', throw=True, **pycompat.strkwargs(hookargs)
                 )
 
         bookstore.applychanges(op.repo, op.gettransaction(), changes)
 
         if pushkeycompat:
 
             def runhook():
                 for hookargs in allhooks:
                     op.repo.hook(b'pushkey', **pycompat.strkwargs(hookargs))
 
             op.repo._afterlock(runhook)
 
     elif bookmarksmode == b'records':
         for book, node in changes:
             record = {b'bookmark': book, b'node': node}
             op.records.add(b'bookmarks', record)
     else:
         raise error.ProgrammingError(
             b'unkown bookmark mode: %s' % bookmarksmode
         )
 
 
 @parthandler(b'phase-heads')
 def handlephases(op, inpart):
     """apply phases from bundle part to repo"""
     headsbyphase = phases.binarydecode(inpart)
     phases.updatephases(op.repo.unfiltered(), op.gettransaction, headsbyphase)
 
 
 @parthandler(b'reply:pushkey', (b'return', b'in-reply-to'))
 def handlepushkeyreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'return'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'pushkey', {b'return': ret}, partid)
 
 
 @parthandler(b'obsmarkers')
 def handleobsmarker(op, inpart):
     """add a stream of obsmarkers to the repo"""
     tr = op.gettransaction()
     markerdata = inpart.read()
     if op.ui.config(b'experimental', b'obsmarkers-exchange-debug'):
-        op.ui.write(
+        op.ui.writenoi18n(
             b'obsmarker-exchange: %i bytes received\n' % len(markerdata)
         )
     # The mergemarkers call will crash if marker creation is not enabled.
     # we want to avoid this if the part is advisory.
     if not inpart.mandatory and op.repo.obsstore.readonly:
         op.repo.ui.debug(
             b'ignoring obsolescence markers, feature not enabled\n'
         )
         return
     new = op.repo.obsstore.mergemarkers(tr, markerdata)
     op.repo.invalidatevolatilesets()
     op.records.add(b'obsmarkers', {b'new': new})
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:obsmarkers')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'new', b'%i' % new, mandatory=False)
 
 
 @parthandler(b'reply:obsmarkers', (b'new', b'in-reply-to'))
 def handleobsmarkerreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'new'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'obsmarkers', {b'new': ret}, partid)
 
 
 @parthandler(b'hgtagsfnodes')
 def handlehgtagsfnodes(op, inpart):
     """Applies .hgtags fnodes cache entries to the local repo.
 
     Payload is pairs of 20 byte changeset nodes and filenodes.
     """
     # Grab the transaction so we ensure that we have the lock at this point.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     cache = tags.hgtagsfnodescache(op.repo.unfiltered())
 
     count = 0
     while True:
         node = inpart.read(20)
         fnode = inpart.read(20)
         if len(node) < 20 or len(fnode) < 20:
             op.ui.debug(b'ignoring incomplete received .hgtags fnodes data\n')
             break
         cache.setfnode(node, fnode)
         count += 1
 
     cache.write()
     op.ui.debug(b'applied %i hgtags fnodes cache entries\n' % count)
 
 
 rbcstruct = struct.Struct(b'>III')
 
 
 @parthandler(b'cache:rev-branch-cache')
 def handlerbc(op, inpart):
     """receive a rev-branch-cache payload and update the local cache
 
     The payload is a series of data related to each branch
 
     1) branch name length
     2) number of open heads
     3) number of closed heads
     4) open heads nodes
     5) closed heads nodes
     """
     total = 0
     rawheader = inpart.read(rbcstruct.size)
     cache = op.repo.revbranchcache()
     cl = op.repo.unfiltered().changelog
     while rawheader:
         header = rbcstruct.unpack(rawheader)
         total += header[1] + header[2]
         utf8branch = inpart.read(header[0])
         branch = encoding.tolocal(utf8branch)
         for x in pycompat.xrange(header[1]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, False)
         for x in pycompat.xrange(header[2]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, True)
         rawheader = inpart.read(rbcstruct.size)
     cache.write()
 
 
 @parthandler(b'pushvars')
 def bundle2getvars(op, part):
     '''unbundle a bundle2 containing shellvars on the server'''
     # An option to disable unbundling on server-side for security reasons
     if op.ui.configbool(b'push', b'pushvars.server'):
         hookargs = {}
         for key, value in part.advisoryparams:
             key = key.upper()
             # We want pushed variables to have USERVAR_ prepended so we know
             # they came from the --pushvar flag.
             key = b"USERVAR_" + key
             hookargs[key] = value
         op.addhookargs(hookargs)
 
 
 @parthandler(b'stream2', (b'requirements', b'filecount', b'bytecount'))
 def handlestreamv2bundle(op, part):
 
     requirements = urlreq.unquote(part.params[b'requirements']).split(b',')
     filecount = int(part.params[b'filecount'])
     bytecount = int(part.params[b'bytecount'])
 
     repo = op.repo
     if len(repo):
         msg = _(b'cannot apply stream clone to non empty repository')
         raise error.Abort(msg)
 
     repo.ui.debug(b'applying stream bundle\n')
     streamclone.applybundlev2(repo, part, filecount, bytecount, requirements)
 
 
 def widen_bundle(
     bundler, repo, oldmatcher, newmatcher, common, known, cgversion, ellipses
 ):
     """generates bundle2 for widening a narrow clone
 
     bundler is the bundle to which data should be added
     repo is the localrepository instance
     oldmatcher matches what the client already has
     newmatcher matches what the client needs (including what it already has)
     common is set of common heads between server and client
     known is a set of revs known on the client side (used in ellipses)
     cgversion is the changegroup version to send
     ellipses is boolean value telling whether to send ellipses data or not
 
     returns bundle2 of the data required for extending
     """
     commonnodes = set()
     cl = repo.changelog
     for r in repo.revs(b"::%ln", common):
         commonnodes.add(cl.node(r))
     if commonnodes:
         # XXX: we should only send the filelogs (and treemanifest). user
         # already has the changelog and manifest
         packer = changegroup.getbundler(
             cgversion,
             repo,
             oldmatcher=oldmatcher,
             matcher=newmatcher,
             fullnodes=commonnodes,
         )
         cgdata = packer.generate(
             {nodemod.nullid},
             list(commonnodes),
             False,
             b'narrow_widen',
             changelog=False,
         )
 
         part = bundler.newpart(b'changegroup', data=cgdata)
         part.addparam(b'version', cgversion)
         if b'treemanifest' in repo.requirements:
             part.addparam(b'treemanifest', b'1')
 
     return bundler