revlog: introduce an explicit tracking of what the revlog is about

Since the dawn of time, people have been forced to rely to lossy introspection
of the index filename to determine what the purpose and role of the revlog they
encounter is. This is hacky, error prone, inflexible, abstraction-leaky,
<insert-your-own-complaints-here>.

In f63299ee7e4d Raphaël introduced a new attribute to track this information:
`revlog_kind`. However it is initialized in an odd place and various instances
end up not having it set. In addition is only tracking some of the information
we end up having to introspect in various pieces of code.

So we add a new attribute that holds more data and is more strictly enforced.
This work is done in collaboration with Raphaël.

The `revlog_kind` one will be removed/adapted in the next changeset. We expect
to be able to clean up various existing piece of code and to simplify coming
work around the newer revlog format.

Differential Revision: https://phab.mercurial-scm.org/D10352

contrib/dumprevlog

@@ -1,47 +1,55 b''
 #!/usr/bin/env python3
 # Dump revlogs as raw data stream
 # $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump
 
 from __future__ import absolute_import, print_function
 
 import sys
 from mercurial.node import hex
 from mercurial import (
     encoding,
     pycompat,
     revlog,
 )
 from mercurial.utils import procutil
 
+from mercurial.revlogutils import (
+    constants as revlog_constants,
+)
+
 for fp in (sys.stdin, sys.stdout, sys.stderr):
     procutil.setbinary(fp)
 
 
 def binopen(path, mode=b'rb'):
     if b'b' not in mode:
         mode = mode + b'b'
     return open(path, pycompat.sysstr(mode))
 
 
 binopen.options = {}
 
 
 def printb(data, end=b'\n'):
     sys.stdout.flush()
     procutil.stdout.write(data + end)
 
 
 for f in sys.argv[1:]:
-    r = revlog.revlog(binopen, encoding.strtolocal(f))
+    r = revlog.revlog(
+        binopen,
+        target=(revlog_constants.KIND_OTHER, b'dump-revlog'),
+        indexfile=encoding.strtolocal(f),
+    )
     print("file:", f)
     for i in r:
         n = r.node(i)
         p = r.parents(n)
         d = r.revision(n)
         printb(b"node: %s" % hex(n))
         printb(b"linkrev: %d" % r.linkrev(i))
         printb(b"parents: %s %s" % (hex(p[0]), hex(p[1])))
         printb(b"length: %d" % len(d))
         printb(b"-start-")
         printb(d)
         printb(b"-end-")

contrib/perf.py

@@ -1,3927 +1,3944 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
+
+import mercurial.revlog
 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
 
+try:
+    from mercurial.revlogutils import constants as revlog_constants
+
+    perf_rl_kind = (revlog_constants.KIND_OTHER, b'created-by-perf')
+
+    def revlog(opener, *args, **kwargs):
+        return mercurial.revlog.revlog(opener, perf_rl_kind, *args, **kwargs)
+
+
+except (ImportError, AttributeError):
+    perf_rl_kind = None
+
+    def revlog(opener, *args, **kwargs):
+        return mercurial.revlog.revlog(opener, *args, **kwargs)
+
 
 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 '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 '_tagscache' in vars(repo):
                 del repo.__dict__['_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, '_clcachekey', None)
         object.__setattr__(repo, '_clcache', None)
     clearfilecache(repo.unfiltered(), 'changelog')
 
 
 # perf commands
 
 
 @command(b'perf::walk|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'perf::annotate|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'perf::status|perfstatus',
     [
         (b'u', b'unknown', False, b'ask status to look for unknown files'),
         (b'', b'dirstate', False, b'benchmark the internal dirstate call'),
     ]
     + formatteropts,
 )
 def perfstatus(ui, repo, **opts):
     """benchmark the performance of a single status call
 
     The repository data are preserved between each call.
 
     By default, only the status of the tracked file are requested. If
     `--unknown` is passed, the "unknown" files are also tracked.
     """
     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)
     if opts[b'dirstate']:
         dirstate = repo.dirstate
         m = scmutil.matchall(repo)
         unknown = opts[b'unknown']
 
         def status_dirstate():
             s = dirstate.status(
                 m, subrepos=[], ignored=False, clean=False, unknown=unknown
             )
             sum(map(bool, s))
 
         timer(status_dirstate)
     else:
         timer(lambda: sum(map(len, repo.status(unknown=opts[b'unknown']))))
     fm.end()
 
 
 @command(b'perf::addremove|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 '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'):
         # <= hg-5.2
         from mercurial.node import nullid, nullrev
 
         cl._nodecache = {nullid: nullrev}
         cl._nodepos = None
 
 
 @command(b'perf::heads|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'perf::tags|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'perf::ancestors|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'perf::ancestorset|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'perf::discovery|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)
 
     try:
         from mercurial.utils.urlutil import get_unique_pull_path
 
         path = get_unique_pull_path(b'perfdiscovery', repo, ui, path)[0]
     except ImportError:
         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'perf::bookmarks|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'perf::bundleread|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'perf::changegroupchangelog|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'perf::dirs|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'perf::dirstate|perfdirstate',
     [
         (
             b'',
             b'iteration',
             None,
             b'benchmark a full iteration for the dirstate',
         ),
         (
             b'',
             b'contains',
             None,
             b'benchmark a large amount of `nf in dirstate` calls',
         ),
     ]
     + formatteropts,
 )
 def perfdirstate(ui, repo, **opts):
     """benchmap the time of various distate operations
 
     By default benchmark the time necessary to load a dirstate from scratch.
     The dirstate is loaded to the point were a "contains" request can be
     answered.
     """
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     b"a" in repo.dirstate
 
     if opts[b'iteration'] and opts[b'contains']:
         msg = b'only specify one of --iteration or --contains'
         raise error.Abort(msg)
 
     if opts[b'iteration']:
         setup = None
         dirstate = repo.dirstate
 
         def d():
             for f in dirstate:
                 pass
 
     elif opts[b'contains']:
         setup = None
         dirstate = repo.dirstate
         allfiles = list(dirstate)
         # also add file path that will be "missing" from the dirstate
         allfiles.extend([f[::-1] for f in allfiles])
 
         def d():
             for f in allfiles:
                 f in dirstate
 
     else:
 
         def setup():
             repo.dirstate.invalidate()
 
         def d():
             b"a" in repo.dirstate
 
     timer(d, setup=setup)
     fm.end()
 
 
 @command(b'perf::dirstatedirs|perfdirstatedirs', formatteropts)
 def perfdirstatedirs(ui, repo, **opts):
     """benchmap a 'dirstate.hasdir' call from an empty `dirs` cache"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     repo.dirstate.hasdir(b"a")
 
     def setup():
         del repo.dirstate._map._dirs
 
     def d():
         repo.dirstate.hasdir(b"a")
 
     timer(d, setup=setup)
     fm.end()
 
 
 @command(b'perf::dirstatefoldmap|perfdirstatefoldmap', formatteropts)
 def perfdirstatefoldmap(ui, repo, **opts):
     """benchmap a `dirstate._map.filefoldmap.get()` request
 
     The dirstate filefoldmap cache is dropped between every request.
     """
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     dirstate._map.filefoldmap.get(b'a')
 
     def setup():
         del dirstate._map.filefoldmap
 
     def d():
         dirstate._map.filefoldmap.get(b'a')
 
     timer(d, setup=setup)
     fm.end()
 
 
 @command(b'perf::dirfoldmap|perfdirfoldmap', formatteropts)
 def perfdirfoldmap(ui, repo, **opts):
     """benchmap a `dirstate._map.dirfoldmap.get()` request
 
     The dirstate dirfoldmap cache is dropped between every request.
     """
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     dirstate = repo.dirstate
     dirstate._map.dirfoldmap.get(b'a')
 
     def setup():
         del dirstate._map.dirfoldmap
         del dirstate._map._dirs
 
     def d():
         dirstate._map.dirfoldmap.get(b'a')
 
     timer(d, setup=setup)
     fm.end()
 
 
 @command(b'perf::dirstatewrite|perfdirstatewrite', formatteropts)
 def perfdirstatewrite(ui, repo, **opts):
     """benchmap the time it take to write a dirstate on disk"""
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
     ds = repo.dirstate
     b"a" in ds
 
     def setup():
         ds._dirty = True
 
     def d():
         ds.write(repo.currenttransaction())
 
     timer(d, setup=setup)
     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'perf::mergecalculate|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'perf::mergecopies|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'perf::pathcopies|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'perf::phases|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'perf::phasesremote|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.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.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.statusnoi18n(b'publishing: yes\n')
     else:
         ui.statusnoi18n(b'publishing: no\n')
 
     has_node = getattr(repo.changelog.index, 'has_node', None)
     if has_node is None:
         has_node = repo.changelog.nodemap.__contains__
     nonpublishroots = 0
     for nhex, phase in remotephases.iteritems():
         if nhex == b'publishing':  # ignore data related to publish option
             continue
         node = bin(nhex)
         if has_node(node) and int(phase):
             nonpublishroots += 1
     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'perf::manifest|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 node'
                 )
 
     def d():
         repo.manifestlog.clearcaches(clear_persisted_data=clear_disk)
         repo.manifestlog[t].read()
 
     timer(d)
     fm.end()
 
 
 @command(b'perf::changeset|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'perf::ignore|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'perf::index|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'perf::nodemap|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[b'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(b'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)
         cl = makecl(unfi)
         if util.safehasattr(cl.index, 'get_rev'):
             nodeget[0] = cl.index.get_rev
         else:
             nodeget[0] = cl.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'perf::startup|perfstartup', formatteropts)
 def perfstartup(ui, repo, **opts):
     opts = _byteskwargs(opts)
     timer, fm = gettimer(ui, opts)
 
     def d():
         if os.name != 'nt':
             os.system(
                 b"HGRCPATH= %s version -q > /dev/null" % fsencode(sys.argv[0])
             )
         else:
             os.environ['HGRCPATH'] = r' '
             os.system("%s version -q > NUL" % sys.argv[0])
 
     timer(d)
     fm.end()
 
 
 @command(b'perf::parents|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'perf::ctxfiles|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'perf::rawfiles|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'perf::lookup|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'perf::linelogedits|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'perf::revrange|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'perf::nodelookup|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")
+
+    cl = revlog(getsvfs(repo), indexfile=b"00changelog.i")
 
     def d():
         cl.rev(n)
         clearcaches(cl)
 
     timer(d)
     fm.end()
 
 
 @command(
     b'perf::log|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'perf::moonwalk|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'perf::templating|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, '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):
     # 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'perf::helper-mergecopies|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('only(%d, %d)', p1.rev(), b.rev())),
                 b'p1.nbmissingfiles': len(p1missing),
                 b'p2.node': p2.hex(),
                 b'p2.nbrevs': len(repo.revs('only(%d, %d)', p2.rev(), b.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)
                 end = util.timer()
                 data['p2.time'] = end - begin
                 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'perf::helper-pathcopies|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('only(%d, %d)', p, b)),
                     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:
         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'perf::cca|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'perf::fncacheload|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'perf::fncachewrite|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'perf::fncacheencode|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'perf::bdiff|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'perf::unidiff|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'perf::diffwd|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 = {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'perf::revlogindex|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:
         inline = header & (1 << 16)
     else:
         raise error.Abort(b'unsupported revlog version: %d' % version)
 
-    parse_index_v1 = getattr(revlog, 'parse_index_v1', None)
+    parse_index_v1 = getattr(mercurial.revlog, 'parse_index_v1', None)
     if parse_index_v1 is None:
-        parse_index_v1 = revlog.revlogio().parseindex
+        parse_index_v1 = mercurial.revlog.revlogio().parseindex
 
     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)
+        revlog(opener, indexfile=indexfile)
 
     def read():
         with opener(indexfile) as fh:
             fh.read()
 
     def parseindex():
         parse_index_v1(data, inline)
 
     def getentry(revornode):
         index = parse_index_v1(data, inline)[0]
         index[revornode]
 
     def getentries(revs, count=1):
         index = parse_index_v1(data, inline)[0]
 
         for i in range(count):
             for rev in revs:
                 index[rev]
 
     def resolvenode(node):
         index = parse_index_v1(data, inline)[0]
         rev = getattr(index, 'rev', None)
         if rev is None:
             nodemap = getattr(parse_index_v1(data, inline)[0], 'nodemap', None)
             # This only works for the C code.
             if nodemap is None:
                 return
             rev = nodemap.__getitem__
 
         try:
             rev(node)
         except error.RevlogError:
             pass
 
     def resolvenodes(nodes, count=1):
         index = parse_index_v1(data, inline)[0]
         rev = getattr(index, 'rev', None)
         if rev is None:
             nodemap = getattr(parse_index_v1(data, inline)[0], 'nodemap', None)
             # This only works for the C code.
             if nodemap is None:
                 return
             rev = nodemap.__getitem__
 
         for i in range(count):
             for node in nodes:
                 try:
                     rev(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'perf::revlogrevisions|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'perf::revlogwrite|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(
+        dest = 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'perf::revlogchunks|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 = {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'perf::revlogrevision|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
         try:
             iosize = r.index.entry_size
         except AttributeError:
             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'perf::revset|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'perf::volatilesets|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'perf::branchmap|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=printname)
     finally:
         branchcacheread.restore()
         branchcachewrite.restore()
     fm.end()
 
 
 @command(
     b'perf::branchmapupdate|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'perf::branchmapload|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'perf::loadmarkers|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(repo, svfs)))
     fm.end()
 
 
 @command(
     b'perf::lrucachedict|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'perf::write|perfwrite',
     formatteropts
     + [
         (b'', b'write-method', b'write', b'ui write method'),
         (b'', b'nlines', 100, b'number of lines'),
         (b'', b'nitems', 100, b'number of items (per line)'),
         (b'', b'item', b'x', b'item that is written'),
         (b'', b'batch-line', None, b'pass whole line to write method at once'),
         (b'', b'flush-line', None, b'flush after each line'),
     ],
 )
 def perfwrite(ui, repo, **opts):
     """microbenchmark ui.write (and others)"""
     opts = _byteskwargs(opts)
 
     write = getattr(ui, _sysstr(opts[b'write_method']))
     nlines = int(opts[b'nlines'])
     nitems = int(opts[b'nitems'])
     item = opts[b'item']
     batch_line = opts.get(b'batch_line')
     flush_line = opts.get(b'flush_line')
 
     if batch_line:
         line = item * nitems + b'\n'
 
     def benchmark():
         for i in pycompat.xrange(nlines):
             if batch_line:
                 write(line)
             else:
                 for i in pycompat.xrange(nitems):
                     write(item)
                 write(b'\n')
             if flush_line:
                 ui.flush()
         ui.flush()
 
     timer, fm = gettimer(ui, opts)
     timer(benchmark)
     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'perf::progress|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()

contrib/undumprevlog

@@ -1,48 +1,56 b''
 #!/usr/bin/env python3
 # Undump a dump from dumprevlog
 # $ hg init
 # $ undumprevlog < repo.dump
 
 from __future__ import absolute_import, print_function
 
 import sys
 from mercurial.node import bin
 from mercurial import (
     encoding,
     revlog,
     transaction,
     vfs as vfsmod,
 )
 from mercurial.utils import procutil
 
+from mercurial.revlogutils import (
+    constants as revlog_constants,
+)
+
 for fp in (sys.stdin, sys.stdout, sys.stderr):
     procutil.setbinary(fp)
 
 opener = vfsmod.vfs(b'.', False)
 tr = transaction.transaction(
     sys.stderr.write, opener, {b'store': opener}, b"undump.journal"
 )
 while True:
     l = sys.stdin.readline()
     if not l:
         break
     if l.startswith("file:"):
         f = encoding.strtolocal(l[6:-1])
-        r = revlog.revlog(opener, f)
+        r = revlog.revlog(
+            opener,
+            target=(revlog_constants.KIND_OTHER, b'undump-revlog'),
+            indexfile=f,
+        )
         procutil.stdout.write(b'%s\n' % f)
     elif l.startswith("node:"):
         n = bin(l[6:-1])
     elif l.startswith("linkrev:"):
         lr = int(l[9:-1])
     elif l.startswith("parents:"):
         p = l[9:-1].split()
         p1 = bin(p[0])
         p2 = bin(p[1])
     elif l.startswith("length:"):
         length = int(l[8:-1])
         sys.stdin.readline()  # start marker
         d = encoding.strtolocal(sys.stdin.read(length))
         sys.stdin.readline()  # end marker
         r.addrevision(d, tr, lr, p1, p2)
 
 tr.close()

mercurial/bundlerepo.py

@@ -1,693 +1,712 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[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.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from __future__ import absolute_import
 
 import os
 import shutil
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
 )
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     encoding,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     pathutil,
     phases,
     pycompat,
     revlog,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     urlutil,
 )
 
+from .revlogutils import (
+    constants as revlog_constants,
+)
+
 
 class bundlerevlog(revlog.revlog):
-    def __init__(self, opener, indexfile, cgunpacker, linkmapper):
+    def __init__(self, opener, target, indexfile, cgunpacker, linkmapper):
         # How it works:
         # To retrieve a revision, we need to know the offset of the revision in
         # the bundle (an unbundle object). We store this offset in the index
         # (start). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
-        revlog.revlog.__init__(self, opener, indexfile)
+        revlog.revlog.__init__(self, opener, target=target, indexfile=indexfile)
         self.bundle = cgunpacker
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set()  # used by 'bundle()' revset expression
         for deltadata in cgunpacker.deltaiter():
             node, p1, p2, cs, deltabase, delta, flags, sidedata = deltadata
 
             size = len(delta)
             start = cgunpacker.tell() - size
 
             if self.index.has_node(node):
                 # this can happen if two branches make the same change
                 self.bundlerevs.add(self.index.rev(node))
                 continue
             if cs == node:
                 linkrev = nullrev
             else:
                 linkrev = linkmapper(cs)
 
             for p in (p1, p2):
                 if not self.index.has_node(p):
                     raise error.LookupError(
                         p, self.indexfile, _(b"unknown parent")
                     )
 
             if not self.index.has_node(deltabase):
                 raise LookupError(
                     deltabase, self.indexfile, _(b'unknown delta base')
                 )
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (
                 revlog.offset_type(start, flags),
                 size,
                 -1,
                 baserev,
                 linkrev,
                 self.rev(p1),
                 self.rev(p2),
                 node,
             )
             self.index.append(e)
             self.bundlerevs.add(n)
             n += 1
 
     def _chunk(self, rev, df=None):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def _rawtext(self, node, rev, _df=None):
         if rev is None:
             rev = self.rev(node)
         validated = False
         rawtext = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._revisioncache and self._revisioncache[1] == iterrev:
                 rawtext = self._revisioncache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if iterrev == nullrev:
             rawtext = b''
         elif rawtext is None:
             r = super(bundlerevlog, self)._rawtext(
                 self.node(iterrev), iterrev, _df=_df
             )
             __, rawtext, validated = r
         if chain:
             validated = False
         while chain:
             delta = self._chunk(chain.pop())
             rawtext = mdiff.patches(rawtext, [delta])
         return rev, rawtext, validated
 
     def addrevision(self, *args, **kwargs):
         raise NotImplementedError
 
     def addgroup(self, *args, **kwargs):
         raise NotImplementedError
 
     def strip(self, *args, **kwargs):
         raise NotImplementedError
 
     def checksize(self):
         raise NotImplementedError
 
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, cgunpacker):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(
-            self, opener, self.indexfile, cgunpacker, linkmapper
+            self,
+            opener,
+            (revlog_constants.KIND_CHANGELOG, None),
+            self.indexfile,
+            cgunpacker,
+            linkmapper,
         )
 
 
 class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
     def __init__(
         self,
         nodeconstants,
         opener,
         cgunpacker,
         linkmapper,
         dirlogstarts=None,
         dir=b'',
     ):
         manifest.manifestrevlog.__init__(self, nodeconstants, opener, tree=dir)
         bundlerevlog.__init__(
-            self, opener, self.indexfile, cgunpacker, linkmapper
+            self,
+            opener,
+            (revlog_constants.KIND_MANIFESTLOG, dir),
+            self.indexfile,
+            cgunpacker,
+            linkmapper,
         )
         if dirlogstarts is None:
             dirlogstarts = {}
             if self.bundle.version == b"03":
                 dirlogstarts = _getfilestarts(self.bundle)
         self._dirlogstarts = dirlogstarts
         self._linkmapper = linkmapper
 
     def dirlog(self, d):
         if d in self._dirlogstarts:
             self.bundle.seek(self._dirlogstarts[d])
             return bundlemanifest(
                 self.nodeconstants,
                 self.opener,
                 self.bundle,
                 self._linkmapper,
                 self._dirlogstarts,
                 dir=d,
             )
         return super(bundlemanifest, self).dirlog(d)
 
 
 class bundlefilelog(filelog.filelog):
     def __init__(self, opener, path, cgunpacker, linkmapper):
         filelog.filelog.__init__(self, opener, path)
         self._revlog = bundlerevlog(
-            opener, self.indexfile, cgunpacker, linkmapper
+            opener,
+            # XXX should use the unencoded path
+            target=(revlog_constants.KIND_FILELOG, path),
+            indexfile=self.indexfile,
+            cgunpacker=cgunpacker,
+            linkmapper=linkmapper,
         )
 
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
         if util.safehasattr(self, 'opener'):
             self.opener = vfsmod.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 
 def _getfilestarts(cgunpacker):
     filespos = {}
     for chunkdata in iter(cgunpacker.filelogheader, {}):
         fname = chunkdata[b'filename']
         filespos[fname] = cgunpacker.tell()
         for chunk in iter(lambda: cgunpacker.deltachunk(None), {}):
             pass
     return filespos
 
 
 class bundlerepository(object):
     """A repository instance that is a union of a local repo and a bundle.
 
     Instances represent a read-only repository composed of a local repository
     with the contents of a bundle file applied. The repository instance is
     conceptually similar to the state of a repository after an
     ``hg unbundle`` operation. However, the contents of the bundle are never
     applied to the actual base repository.
 
     Instances constructed directly are not usable as repository objects.
     Use instance() or makebundlerepository() to create instances.
     """
 
     def __init__(self, bundlepath, url, tempparent):
         self._tempparent = tempparent
         self._url = url
 
         self.ui.setconfig(b'phases', b'publish', False, b'bundlerepo')
 
         self.tempfile = None
         f = util.posixfile(bundlepath, b"rb")
         bundle = exchange.readbundle(self.ui, f, bundlepath)
 
         if isinstance(bundle, bundle2.unbundle20):
             self._bundlefile = bundle
             self._cgunpacker = None
 
             cgpart = None
             for part in bundle.iterparts(seekable=True):
                 if part.type == b'changegroup':
                     if cgpart:
                         raise NotImplementedError(
                             b"can't process multiple changegroups"
                         )
                     cgpart = part
 
                 self._handlebundle2part(bundle, part)
 
             if not cgpart:
                 raise error.Abort(_(b"No changegroups found"))
 
             # This is required to placate a later consumer, which expects
             # the payload offset to be at the beginning of the changegroup.
             # We need to do this after the iterparts() generator advances
             # because iterparts() will seek to end of payload after the
             # generator returns control to iterparts().
             cgpart.seek(0, os.SEEK_SET)
 
         elif isinstance(bundle, changegroup.cg1unpacker):
             if bundle.compressed():
                 f = self._writetempbundle(
                     bundle.read, b'.hg10un', header=b'HG10UN'
                 )
                 bundle = exchange.readbundle(self.ui, f, bundlepath, self.vfs)
 
             self._bundlefile = bundle
             self._cgunpacker = bundle
         else:
             raise error.Abort(
                 _(b'bundle type %s cannot be read') % type(bundle)
             )
 
         # dict with the mapping 'filename' -> position in the changegroup.
         self._cgfilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(
             self,
             None,
             phases.draft,
             [ctx.node() for ctx in self[self.firstnewrev :]],
         )
 
     def _handlebundle2part(self, bundle, part):
         if part.type != b'changegroup':
             return
 
         cgstream = part
         version = part.params.get(b'version', b'01')
         legalcgvers = changegroup.supportedincomingversions(self)
         if version not in legalcgvers:
             msg = _(b'Unsupported changegroup version: %s')
             raise error.Abort(msg % version)
         if bundle.compressed():
             cgstream = self._writetempbundle(part.read, b'.cg%sun' % version)
 
         self._cgunpacker = changegroup.getunbundler(version, cgstream, b'UN')
 
     def _writetempbundle(self, readfn, suffix, header=b''):
         """Write a temporary file to disk"""
         fdtemp, temp = self.vfs.mkstemp(prefix=b"hg-bundle-", suffix=suffix)
         self.tempfile = temp
 
         with os.fdopen(fdtemp, 'wb') as fptemp:
             fptemp.write(header)
             while True:
                 chunk = readfn(2 ** 18)
                 if not chunk:
                     break
                 fptemp.write(chunk)
 
         return self.vfs.open(self.tempfile, mode=b"rb")
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self._cgunpacker.changelogheader()
         c = bundlechangelog(self.svfs, self._cgunpacker)
         self.manstart = self._cgunpacker.tell()
         return c
 
     def _refreshchangelog(self):
         # changelog for bundle repo are not filecache, this method is not
         # applicable.
         pass
 
     @localrepo.unfilteredpropertycache
     def manifestlog(self):
         self._cgunpacker.seek(self.manstart)
         # consume the header if it exists
         self._cgunpacker.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         rootstore = bundlemanifest(
             self.nodeconstants, self.svfs, self._cgunpacker, linkmapper
         )
         self.filestart = self._cgunpacker.tell()
 
         return manifest.manifestlog(
             self.svfs, self, rootstore, self.narrowmatch()
         )
 
     def _consumemanifest(self):
         """Consumes the manifest portion of the bundle, setting filestart so the
         file portion can be read."""
         self._cgunpacker.seek(self.manstart)
         self._cgunpacker.manifestheader()
         for delta in self._cgunpacker.deltaiter():
             pass
         self.filestart = self._cgunpacker.tell()
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifestlog
 
         # If filestart was not set by self.manifestlog, that means the
         # manifestlog implementation did not consume the manifests from the
         # changegroup (ex: it might be consuming trees from a separate bundle2
         # part instead). So we need to manually consume it.
         if 'filestart' not in self.__dict__:
             self._consumemanifest()
 
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self._cgfilespos:
             self._cgunpacker.seek(self.filestart)
             self._cgfilespos = _getfilestarts(self._cgunpacker)
 
         if f in self._cgfilespos:
             self._cgunpacker.seek(self._cgfilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self._cgunpacker, linkmapper)
         else:
             return super(bundlerepository, self).file(f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self._bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return encoding.getcwd()  # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=None):
         if p2 is None:
             p2 = self.nullid
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _(b"setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 
 def instance(ui, path, create, intents=None, createopts=None):
     if create:
         raise error.Abort(_(b'cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config(b"bundle", b"mainreporoot")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(encoding.getcwd())
         if parentpath is None:
             parentpath = b''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = encoding.getcwd()
         if parentpath == cwd:
             parentpath = b''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd) :]
     u = urlutil.url(path)
     path = u.localpath()
     if u.scheme == b'bundle':
         s = path.split(b"+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
 
     return makebundlerepository(ui, repopath, bundlename)
 
 
 def makebundlerepository(ui, repopath, bundlepath):
     """Make a bundle repository object based on repo and bundle paths."""
     if repopath:
         url = b'bundle:%s+%s' % (util.expandpath(repopath), bundlepath)
     else:
         url = b'bundle:%s' % bundlepath
 
     # Because we can't make any guarantees about the type of the base
     # repository, we can't have a static class representing the bundle
     # repository. We also can't make any guarantees about how to even
     # call the base repository's constructor!
     #
     # So, our strategy is to go through ``localrepo.instance()`` to construct
     # a repo instance. Then, we dynamically create a new type derived from
     # both it and our ``bundlerepository`` class which overrides some
     # functionality. We then change the type of the constructed repository
     # to this new type and initialize the bundle-specific bits of it.
 
     try:
         repo = localrepo.instance(ui, repopath, create=False)
         tempparent = None
     except error.RepoError:
         tempparent = pycompat.mkdtemp()
         try:
             repo = localrepo.instance(ui, tempparent, create=True)
         except Exception:
             shutil.rmtree(tempparent)
             raise
 
     class derivedbundlerepository(bundlerepository, repo.__class__):
         pass
 
     repo.__class__ = derivedbundlerepository
     bundlerepository.__init__(repo, bundlepath, url, tempparent)
 
     return repo
 
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 
 def getremotechanges(
     ui, repo, peer, onlyheads=None, bundlename=None, force=False
 ):
     """obtains a bundle of changes incoming from peer
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "peer" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "peer" and the one returned
       here.
     """
     tmp = discovery.findcommonincoming(repo, peer, heads=onlyheads, force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], peer.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = peer.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if peer repo is not local)
 
         # developer config: devel.legacy.exchange
         legexc = ui.configlist(b'devel', b'legacy.exchange')
         forcebundle1 = b'bundle2' not in legexc and b'bundle1' in legexc
         canbundle2 = (
             not forcebundle1
             and peer.capable(b'getbundle')
             and peer.capable(b'bundle2')
         )
         if canbundle2:
             with peer.commandexecutor() as e:
                 b2 = e.callcommand(
                     b'getbundle',
                     {
                         b'source': b'incoming',
                         b'common': common,
                         b'heads': rheads,
                         b'bundlecaps': exchange.caps20to10(
                             repo, role=b'client'
                         ),
                         b'cg': True,
                     },
                 ).result()
 
                 fname = bundle = changegroup.writechunks(
                     ui, b2._forwardchunks(), bundlename
                 )
         else:
             if peer.capable(b'getbundle'):
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'getbundle',
                         {
                             b'source': b'incoming',
                             b'common': common,
                             b'heads': rheads,
                         },
                     ).result()
             elif onlyheads is None and not peer.capable(b'changegroupsubset'):
                 # compat with older servers when pulling all remote heads
 
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'changegroup',
                         {
                             b'nodes': incoming,
                             b'source': b'incoming',
                         },
                     ).result()
 
                 rheads = None
             else:
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'changegroupsubset',
                         {
                             b'bases': incoming,
                             b'heads': rheads,
                             b'source': b'incoming',
                         },
                     ).result()
 
             if localrepo:
                 bundletype = b"HG10BZ"
             else:
                 bundletype = b"HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename, bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = makebundlerepository(
                 repo.baseui, repo.root, fname
             )
 
             # this repo contains local and peer now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev :]]
 
         with peer.commandexecutor() as e:
             remotephases = e.callcommand(
                 b'listkeys',
                 {
                     b'namespace': b'phases',
                 },
             ).result()
 
         pullop = exchange.pulloperation(bundlerepo, peer, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         peer.close()
 
     return (localrepo, csets, cleanup)

mercurial/changelog.py

@@ -1,622 +1,626 b''
 # changelog.py - changelog class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import (
     bin,
     hex,
 )
 from .thirdparty import attr
 
 from . import (
     encoding,
     error,
     metadata,
     pycompat,
     revlog,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
-from .revlogutils import flagutil
+from .revlogutils import (
+    constants as revlog_constants,
+    flagutil,
+)
 
 _defaultextra = {b'branch': b'default'}
 
 
 def _string_escape(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
     >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)s12ab%(cr)scd%(bs)s%(nl)s" % d
     >>> s
     'ab\\ncd\\\\\\\\n\\x0012ab\\rcd\\\\\\n'
     >>> res = _string_escape(s)
     >>> s == _string_unescape(res)
     True
     """
     # subset of the string_escape codec
     text = (
         text.replace(b'\\', b'\\\\')
         .replace(b'\n', b'\\n')
         .replace(b'\r', b'\\r')
     )
     return text.replace(b'\0', b'\\0')
 
 
 def _string_unescape(text):
     if b'\\0' in text:
         # fix up \0 without getting into trouble with \\0
         text = text.replace(b'\\\\', b'\\\\\n')
         text = text.replace(b'\\0', b'\0')
         text = text.replace(b'\n', b'')
     return stringutil.unescapestr(text)
 
 
 def decodeextra(text):
     """
     >>> from .pycompat import bytechr as chr
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
     >>> sorted(decodeextra(encodeextra({b'foo': b'bar',
     ...                                 b'baz': chr(92) + chr(0) + b'2'})
     ...                    ).items())
     [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
     """
     extra = _defaultextra.copy()
     for l in text.split(b'\0'):
         if l:
             k, v = _string_unescape(l).split(b':', 1)
             extra[k] = v
     return extra
 
 
 def encodeextra(d):
     # keys must be sorted to produce a deterministic changelog entry
     items = [_string_escape(b'%s:%s' % (k, d[k])) for k in sorted(d)]
     return b"\0".join(items)
 
 
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return b'\n'.join([l.rstrip() for l in desc.splitlines()]).strip(b'\n')
 
 
 class appender(object):
     """the changelog index must be updated last on disk, so we use this class
     to delay writes to it"""
 
     def __init__(self, vfs, name, mode, buf):
         self.data = buf
         fp = vfs(name, mode)
         self.fp = fp
         self.offset = fp.tell()
         self.size = vfs.fstat(fp).st_size
         self._end = self.size
 
     def end(self):
         return self._end
 
     def tell(self):
         return self.offset
 
     def flush(self):
         pass
 
     @property
     def closed(self):
         return self.fp.closed
 
     def close(self):
         self.fp.close()
 
     def seek(self, offset, whence=0):
         '''virtual file offset spans real file and data'''
         if whence == 0:
             self.offset = offset
         elif whence == 1:
             self.offset += offset
         elif whence == 2:
             self.offset = self.end() + offset
         if self.offset < self.size:
             self.fp.seek(self.offset)
 
     def read(self, count=-1):
         '''only trick here is reads that span real file and data'''
         ret = b""
         if self.offset < self.size:
             s = self.fp.read(count)
             ret = s
             self.offset += len(s)
             if count > 0:
                 count -= len(s)
         if count != 0:
             doff = self.offset - self.size
             self.data.insert(0, b"".join(self.data))
             del self.data[1:]
             s = self.data[0][doff : doff + count]
             self.offset += len(s)
             ret += s
         return ret
 
     def write(self, s):
         self.data.append(bytes(s))
         self.offset += len(s)
         self._end += len(s)
 
     def __enter__(self):
         self.fp.__enter__()
         return self
 
     def __exit__(self, *args):
         return self.fp.__exit__(*args)
 
 
 class _divertopener(object):
     def __init__(self, opener, target):
         self._opener = opener
         self._target = target
 
     def __call__(self, name, mode=b'r', checkambig=False, **kwargs):
         if name != self._target:
             return self._opener(name, mode, **kwargs)
         return self._opener(name + b".a", mode, **kwargs)
 
     def __getattr__(self, attr):
         return getattr(self._opener, attr)
 
 
 def _delayopener(opener, target, buf):
     """build an opener that stores chunks in 'buf' instead of 'target'"""
 
     def _delay(name, mode=b'r', checkambig=False, **kwargs):
         if name != target:
             return opener(name, mode, **kwargs)
         assert not kwargs
         return appender(opener, name, mode, buf)
 
     return _delay
 
 
 @attr.s
 class _changelogrevision(object):
     # Extensions might modify _defaultextra, so let the constructor below pass
     # it in
     extra = attr.ib()
     manifest = attr.ib()
     user = attr.ib(default=b'')
     date = attr.ib(default=(0, 0))
     files = attr.ib(default=attr.Factory(list))
     filesadded = attr.ib(default=None)
     filesremoved = attr.ib(default=None)
     p1copies = attr.ib(default=None)
     p2copies = attr.ib(default=None)
     description = attr.ib(default=b'')
     branchinfo = attr.ib(default=(_defaultextra[b'branch'], False))
 
 
 class changelogrevision(object):
     """Holds results of a parsed changelog revision.
 
     Changelog revisions consist of multiple pieces of data, including
     the manifest node, user, and date. This object exposes a view into
     the parsed object.
     """
 
     __slots__ = (
         '_offsets',
         '_text',
         '_sidedata',
         '_cpsd',
         '_changes',
     )
 
     def __new__(cls, cl, text, sidedata, cpsd):
         if not text:
             return _changelogrevision(extra=_defaultextra, manifest=cl.nullid)
 
         self = super(changelogrevision, cls).__new__(cls)
         # We could return here and implement the following as an __init__.
         # But doing it here is equivalent and saves an extra function call.
 
         # format used:
         # nodeid\n        : manifest node in ascii
         # user\n          : user, no \n or \r allowed
         # time tz extra\n : date (time is int or float, timezone is int)
         #                 : extra is metadata, encoded and separated by '\0'
         #                 : older versions ignore it
         # files\n\n       : files modified by the cset, no \n or \r allowed
         # (.*)            : comment (free text, ideally utf-8)
         #
         # changelog v0 doesn't use extra
 
         nl1 = text.index(b'\n')
         nl2 = text.index(b'\n', nl1 + 1)
         nl3 = text.index(b'\n', nl2 + 1)
 
         # The list of files may be empty. Which means nl3 is the first of the
         # double newline that precedes the description.
         if text[nl3 + 1 : nl3 + 2] == b'\n':
             doublenl = nl3
         else:
             doublenl = text.index(b'\n\n', nl3 + 1)
 
         self._offsets = (nl1, nl2, nl3, doublenl)
         self._text = text
         self._sidedata = sidedata
         self._cpsd = cpsd
         self._changes = None
 
         return self
 
     @property
     def manifest(self):
         return bin(self._text[0 : self._offsets[0]])
 
     @property
     def user(self):
         off = self._offsets
         return encoding.tolocal(self._text[off[0] + 1 : off[1]])
 
     @property
     def _rawdate(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1 : off[2]]
         return dateextra.split(b' ', 2)[0:2]
 
     @property
     def _rawextra(self):
         off = self._offsets
         dateextra = self._text[off[1] + 1 : off[2]]
         fields = dateextra.split(b' ', 2)
         if len(fields) != 3:
             return None
 
         return fields[2]
 
     @property
     def date(self):
         raw = self._rawdate
         time = float(raw[0])
         # Various tools did silly things with the timezone.
         try:
             timezone = int(raw[1])
         except ValueError:
             timezone = 0
 
         return time, timezone
 
     @property
     def extra(self):
         raw = self._rawextra
         if raw is None:
             return _defaultextra
 
         return decodeextra(raw)
 
     @property
     def changes(self):
         if self._changes is not None:
             return self._changes
         if self._cpsd:
             changes = metadata.decode_files_sidedata(self._sidedata)
         else:
             changes = metadata.ChangingFiles(
                 touched=self.files or (),
                 added=self.filesadded or (),
                 removed=self.filesremoved or (),
                 p1_copies=self.p1copies or {},
                 p2_copies=self.p2copies or {},
             )
         self._changes = changes
         return changes
 
     @property
     def files(self):
         if self._cpsd:
             return sorted(self.changes.touched)
         off = self._offsets
         if off[2] == off[3]:
             return []
 
         return self._text[off[2] + 1 : off[3]].split(b'\n')
 
     @property
     def filesadded(self):
         if self._cpsd:
             return self.changes.added
         else:
             rawindices = self.extra.get(b'filesadded')
         if rawindices is None:
             return None
         return metadata.decodefileindices(self.files, rawindices)
 
     @property
     def filesremoved(self):
         if self._cpsd:
             return self.changes.removed
         else:
             rawindices = self.extra.get(b'filesremoved')
         if rawindices is None:
             return None
         return metadata.decodefileindices(self.files, rawindices)
 
     @property
     def p1copies(self):
         if self._cpsd:
             return self.changes.copied_from_p1
         else:
             rawcopies = self.extra.get(b'p1copies')
         if rawcopies is None:
             return None
         return metadata.decodecopies(self.files, rawcopies)
 
     @property
     def p2copies(self):
         if self._cpsd:
             return self.changes.copied_from_p2
         else:
             rawcopies = self.extra.get(b'p2copies')
         if rawcopies is None:
             return None
         return metadata.decodecopies(self.files, rawcopies)
 
     @property
     def description(self):
         return encoding.tolocal(self._text[self._offsets[3] + 2 :])
 
     @property
     def branchinfo(self):
         extra = self.extra
         return encoding.tolocal(extra.get(b"branch")), b'close' in extra
 
 
 class changelog(revlog.revlog):
     def __init__(self, opener, trypending=False, concurrencychecker=None):
         """Load a changelog revlog using an opener.
 
         If ``trypending`` is true, we attempt to load the index from a
         ``00changelog.i.a`` file instead of the default ``00changelog.i``.
         The ``00changelog.i.a`` file contains index (and possibly inline
         revision) data for a transaction that hasn't been finalized yet.
         It exists in a separate file to facilitate readers (such as
         hooks processes) accessing data before a transaction is finalized.
 
         ``concurrencychecker`` will be passed to the revlog init function, see
         the documentation there.
         """
         if trypending and opener.exists(b'00changelog.i.a'):
             indexfile = b'00changelog.i.a'
         else:
             indexfile = b'00changelog.i'
 
         datafile = b'00changelog.d'
         revlog.revlog.__init__(
             self,
             opener,
-            indexfile,
+            target=(revlog_constants.KIND_CHANGELOG, None),
+            indexfile=indexfile,
             datafile=datafile,
             checkambig=True,
             mmaplargeindex=True,
             persistentnodemap=opener.options.get(b'persistent-nodemap', False),
             concurrencychecker=concurrencychecker,
         )
 
         if self._initempty and (self.version & 0xFFFF == revlog.REVLOGV1):
             # changelogs don't benefit from generaldelta.
 
             self.version &= ~revlog.FLAG_GENERALDELTA
             self._generaldelta = False
 
         # Delta chains for changelogs tend to be very small because entries
         # tend to be small and don't delta well with each. So disable delta
         # chains.
         self._storedeltachains = False
 
         self._realopener = opener
         self._delayed = False
         self._delaybuf = None
         self._divert = False
         self._filteredrevs = frozenset()
         self._filteredrevs_hashcache = {}
         self._copiesstorage = opener.options.get(b'copies-storage')
         self.revlog_kind = b'changelog'
 
     @property
     def filteredrevs(self):
         return self._filteredrevs
 
     @filteredrevs.setter
     def filteredrevs(self, val):
         # Ensure all updates go through this function
         assert isinstance(val, frozenset)
         self._filteredrevs = val
         self._filteredrevs_hashcache = {}
 
     def delayupdate(self, tr):
         """delay visibility of index updates to other readers"""
 
         if not self._delayed:
             if len(self) == 0:
                 self._divert = True
                 if self._realopener.exists(self.indexfile + b'.a'):
                     self._realopener.unlink(self.indexfile + b'.a')
                 self.opener = _divertopener(self._realopener, self.indexfile)
             else:
                 self._delaybuf = []
                 self.opener = _delayopener(
                     self._realopener, self.indexfile, self._delaybuf
                 )
         self._delayed = True
         tr.addpending(b'cl-%i' % id(self), self._writepending)
         tr.addfinalize(b'cl-%i' % id(self), self._finalize)
 
     def _finalize(self, tr):
         """finalize index updates"""
         self._delayed = False
         self.opener = self._realopener
         # move redirected index data back into place
         if self._divert:
             assert not self._delaybuf
             tmpname = self.indexfile + b".a"
             nfile = self.opener.open(tmpname)
             nfile.close()
             self.opener.rename(tmpname, self.indexfile, checkambig=True)
         elif self._delaybuf:
             fp = self.opener(self.indexfile, b'a', checkambig=True)
             fp.write(b"".join(self._delaybuf))
             fp.close()
             self._delaybuf = None
         self._divert = False
         # split when we're done
         self._enforceinlinesize(tr)
 
     def _writepending(self, tr):
         """create a file containing the unfinalized state for
         pretxnchangegroup"""
         if self._delaybuf:
             # make a temporary copy of the index
             fp1 = self._realopener(self.indexfile)
             pendingfilename = self.indexfile + b".a"
             # register as a temp file to ensure cleanup on failure
             tr.registertmp(pendingfilename)
             # write existing data
             fp2 = self._realopener(pendingfilename, b"w")
             fp2.write(fp1.read())
             # add pending data
             fp2.write(b"".join(self._delaybuf))
             fp2.close()
             # switch modes so finalize can simply rename
             self._delaybuf = None
             self._divert = True
             self.opener = _divertopener(self._realopener, self.indexfile)
 
         if self._divert:
             return True
 
         return False
 
     def _enforceinlinesize(self, tr, fp=None):
         if not self._delayed:
             revlog.revlog._enforceinlinesize(self, tr, fp)
 
     def read(self, nodeorrev):
         """Obtain data from a parsed changelog revision.
 
         Returns a 6-tuple of:
 
            - manifest node in binary
            - author/user as a localstr
            - date as a 2-tuple of (time, timezone)
            - list of files
            - commit message as a localstr
            - dict of extra metadata
 
         Unless you need to access all fields, consider calling
         ``changelogrevision`` instead, as it is faster for partial object
         access.
         """
         d, s = self._revisiondata(nodeorrev)
         c = changelogrevision(
             self, d, s, self._copiesstorage == b'changeset-sidedata'
         )
         return (c.manifest, c.user, c.date, c.files, c.description, c.extra)
 
     def changelogrevision(self, nodeorrev):
         """Obtain a ``changelogrevision`` for a node or revision."""
         text, sidedata = self._revisiondata(nodeorrev)
         return changelogrevision(
             self, text, sidedata, self._copiesstorage == b'changeset-sidedata'
         )
 
     def readfiles(self, nodeorrev):
         """
         short version of read that only returns the files modified by the cset
         """
         text = self.revision(nodeorrev)
         if not text:
             return []
         last = text.index(b"\n\n")
         l = text[:last].split(b'\n')
         return l[3:]
 
     def add(
         self,
         manifest,
         files,
         desc,
         transaction,
         p1,
         p2,
         user,
         date=None,
         extra=None,
     ):
         # Convert to UTF-8 encoded bytestrings as the very first
         # thing: calling any method on a localstr object will turn it
         # into a str object and the cached UTF-8 string is thus lost.
         user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
 
         user = user.strip()
         # An empty username or a username with a "\n" will make the
         # revision text contain two "\n\n" sequences -> corrupt
         # repository since read cannot unpack the revision.
         if not user:
             raise error.StorageError(_(b"empty username"))
         if b"\n" in user:
             raise error.StorageError(
                 _(b"username %r contains a newline") % pycompat.bytestr(user)
             )
 
         desc = stripdesc(desc)
 
         if date:
             parseddate = b"%d %d" % dateutil.parsedate(date)
         else:
             parseddate = b"%d %d" % dateutil.makedate()
         if extra:
             branch = extra.get(b"branch")
             if branch in (b"default", b""):
                 del extra[b"branch"]
             elif branch in (b".", b"null", b"tip"):
                 raise error.StorageError(
                     _(b'the name \'%s\' is reserved') % branch
                 )
         sortedfiles = sorted(files.touched)
         flags = 0
         sidedata = None
         if self._copiesstorage == b'changeset-sidedata':
             if files.has_copies_info:
                 flags |= flagutil.REVIDX_HASCOPIESINFO
             sidedata = metadata.encode_files_sidedata(files)
 
         if extra:
             extra = encodeextra(extra)
             parseddate = b"%s %s" % (parseddate, extra)
         l = [hex(manifest), user, parseddate] + sortedfiles + [b"", desc]
         text = b"\n".join(l)
         rev = self.addrevision(
             text, transaction, len(self), p1, p2, sidedata=sidedata, flags=flags
         )
         return self.node(rev)
 
     def branchinfo(self, rev):
         """return the branch name and open/close state of a revision
 
         This function exists because creating a changectx object
         just to access this is costly."""
         return self.changelogrevision(rev).branchinfo
 
     def _nodeduplicatecallback(self, transaction, rev):
         # keep track of revisions that got "re-added", eg: unbunde of know rev.
         #
         # We track them in a list to preserve their order from the source bundle
         duplicates = transaction.changes.setdefault(b'revduplicates', [])
         duplicates.append(rev)

mercurial/cmdutil.py

@@ -1,3920 +1,3928 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import copy as copymod
 import errno
 import os
 import re
 
 from .i18n import _
 from .node import (
     hex,
     nullrev,
     short,
 )
 from .pycompat import (
     getattr,
     open,
     setattr,
 )
 from .thirdparty import attr
 
 from . import (
     bookmarks,
     changelog,
     copies,
     crecord as crecordmod,
     dirstateguard,
     encoding,
     error,
     formatter,
     logcmdutil,
     match as matchmod,
     merge as mergemod,
     mergestate as mergestatemod,
     mergeutil,
     obsolete,
     patch,
     pathutil,
     phases,
     pycompat,
     repair,
     revlog,
     rewriteutil,
     scmutil,
     state as statemod,
     subrepoutil,
     templatekw,
     templater,
     util,
     vfs as vfsmod,
 )
 
 from .utils import (
     dateutil,
     stringutil,
 )
 
+from .revlogutils import (
+    constants as revlog_constants,
+)
+
 if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Dict,
     )
 
     for t in (Any, Dict):
         assert t
 
 stringio = util.stringio
 
 # templates of common command options
 
 dryrunopts = [
     (b'n', b'dry-run', None, _(b'do not perform actions, just print output')),
 ]
 
 confirmopts = [
     (b'', b'confirm', None, _(b'ask before applying actions')),
 ]
 
 remoteopts = [
     (b'e', b'ssh', b'', _(b'specify ssh command to use'), _(b'CMD')),
     (
         b'',
         b'remotecmd',
         b'',
         _(b'specify hg command to run on the remote side'),
         _(b'CMD'),
     ),
     (
         b'',
         b'insecure',
         None,
         _(b'do not verify server certificate (ignoring web.cacerts config)'),
     ),
 ]
 
 walkopts = [
     (
         b'I',
         b'include',
         [],
         _(b'include names matching the given patterns'),
         _(b'PATTERN'),
     ),
     (
         b'X',
         b'exclude',
         [],
         _(b'exclude names matching the given patterns'),
         _(b'PATTERN'),
     ),
 ]
 
 commitopts = [
     (b'm', b'message', b'', _(b'use text as commit message'), _(b'TEXT')),
     (b'l', b'logfile', b'', _(b'read commit message from file'), _(b'FILE')),
 ]
 
 commitopts2 = [
     (
         b'd',
         b'date',
         b'',
         _(b'record the specified date as commit date'),
         _(b'DATE'),
     ),
     (
         b'u',
         b'user',
         b'',
         _(b'record the specified user as committer'),
         _(b'USER'),
     ),
 ]
 
 commitopts3 = [
     (b'D', b'currentdate', None, _(b'record the current date as commit date')),
     (b'U', b'currentuser', None, _(b'record the current user as committer')),
 ]
 
 formatteropts = [
     (b'T', b'template', b'', _(b'display with template'), _(b'TEMPLATE')),
 ]
 
 templateopts = [
     (
         b'',
         b'style',
         b'',
         _(b'display using template map file (DEPRECATED)'),
         _(b'STYLE'),
     ),
     (b'T', b'template', b'', _(b'display with template'), _(b'TEMPLATE')),
 ]
 
 logopts = [
     (b'p', b'patch', None, _(b'show patch')),
     (b'g', b'git', None, _(b'use git extended diff format')),
     (b'l', b'limit', b'', _(b'limit number of changes displayed'), _(b'NUM')),
     (b'M', b'no-merges', None, _(b'do not show merges')),
     (b'', b'stat', None, _(b'output diffstat-style summary of changes')),
     (b'G', b'graph', None, _(b"show the revision DAG")),
 ] + templateopts
 
 diffopts = [
     (b'a', b'text', None, _(b'treat all files as text')),
     (
         b'g',
         b'git',
         None,
         _(b'use git extended diff format (DEFAULT: diff.git)'),
     ),
     (b'', b'binary', None, _(b'generate binary diffs in git mode (default)')),
     (b'', b'nodates', None, _(b'omit dates from diff headers')),
 ]
 
 diffwsopts = [
     (
         b'w',
         b'ignore-all-space',
         None,
         _(b'ignore white space when comparing lines'),
     ),
     (
         b'b',
         b'ignore-space-change',
         None,
         _(b'ignore changes in the amount of white space'),
     ),
     (
         b'B',
         b'ignore-blank-lines',
         None,
         _(b'ignore changes whose lines are all blank'),
     ),
     (
         b'Z',
         b'ignore-space-at-eol',
         None,
         _(b'ignore changes in whitespace at EOL'),
     ),
 ]
 
 diffopts2 = (
     [
         (b'', b'noprefix', None, _(b'omit a/ and b/ prefixes from filenames')),
         (
             b'p',
             b'show-function',
             None,
             _(
                 b'show which function each change is in (DEFAULT: diff.showfunc)'
             ),
         ),
         (b'', b'reverse', None, _(b'produce a diff that undoes the changes')),
     ]
     + diffwsopts
     + [
         (
             b'U',
             b'unified',
             b'',
             _(b'number of lines of context to show'),
             _(b'NUM'),
         ),
         (b'', b'stat', None, _(b'output diffstat-style summary of changes')),
         (
             b'',
             b'root',
             b'',
             _(b'produce diffs relative to subdirectory'),
             _(b'DIR'),
         ),
     ]
 )
 
 mergetoolopts = [
     (b't', b'tool', b'', _(b'specify merge tool'), _(b'TOOL')),
 ]
 
 similarityopts = [
     (
         b's',
         b'similarity',
         b'',
         _(b'guess renamed files by similarity (0<=s<=100)'),
         _(b'SIMILARITY'),
     )
 ]
 
 subrepoopts = [(b'S', b'subrepos', None, _(b'recurse into subrepositories'))]
 
 debugrevlogopts = [
     (b'c', b'changelog', False, _(b'open changelog')),
     (b'm', b'manifest', False, _(b'open manifest')),
     (b'', b'dir', b'', _(b'open directory manifest')),
 ]
 
 # special string such that everything below this line will be ingored in the
 # editor text
 _linebelow = b"^HG: ------------------------ >8 ------------------------$"
 
 
 def check_at_most_one_arg(opts, *args):
     """abort if more than one of the arguments are in opts
 
     Returns the unique argument or None if none of them were specified.
     """
 
     def to_display(name):
         return pycompat.sysbytes(name).replace(b'_', b'-')
 
     previous = None
     for x in args:
         if opts.get(x):
             if previous:
                 raise error.InputError(
                     _(b'cannot specify both --%s and --%s')
                     % (to_display(previous), to_display(x))
                 )
             previous = x
     return previous
 
 
 def check_incompatible_arguments(opts, first, others):
     """abort if the first argument is given along with any of the others
 
     Unlike check_at_most_one_arg(), `others` are not mutually exclusive
     among themselves, and they're passed as a single collection.
     """
     for other in others:
         check_at_most_one_arg(opts, first, other)
 
 
 def resolvecommitoptions(ui, opts):
     """modify commit options dict to handle related options
 
     The return value indicates that ``rewrite.update-timestamp`` is the reason
     the ``date`` option is set.
     """
     check_at_most_one_arg(opts, b'date', b'currentdate')
     check_at_most_one_arg(opts, b'user', b'currentuser')
 
     datemaydiffer = False  # date-only change should be ignored?
 
     if opts.get(b'currentdate'):
         opts[b'date'] = b'%d %d' % dateutil.makedate()
     elif (
         not opts.get(b'date')
         and ui.configbool(b'rewrite', b'update-timestamp')
         and opts.get(b'currentdate') is None
     ):
         opts[b'date'] = b'%d %d' % dateutil.makedate()
         datemaydiffer = True
 
     if opts.get(b'currentuser'):
         opts[b'user'] = ui.username()
 
     return datemaydiffer
 
 
 def checknotesize(ui, opts):
     """ make sure note is of valid format """
 
     note = opts.get(b'note')
     if not note:
         return
 
     if len(note) > 255:
         raise error.InputError(_(b"cannot store a note of more than 255 bytes"))
     if b'\n' in note:
         raise error.InputError(_(b"note cannot contain a newline"))
 
 
 def ishunk(x):
     hunkclasses = (crecordmod.uihunk, patch.recordhunk)
     return isinstance(x, hunkclasses)
 
 
 def newandmodified(chunks, originalchunks):
     newlyaddedandmodifiedfiles = set()
     alsorestore = set()
     for chunk in chunks:
         if (
             ishunk(chunk)
             and chunk.header.isnewfile()
             and chunk not in originalchunks
         ):
             newlyaddedandmodifiedfiles.add(chunk.header.filename())
             alsorestore.update(
                 set(chunk.header.files()) - {chunk.header.filename()}
             )
     return newlyaddedandmodifiedfiles, alsorestore
 
 
 def parsealiases(cmd):
     base_aliases = cmd.split(b"|")
     all_aliases = set(base_aliases)
     extra_aliases = []
     for alias in base_aliases:
         if b'-' in alias:
             folded_alias = alias.replace(b'-', b'')
             if folded_alias not in all_aliases:
                 all_aliases.add(folded_alias)
                 extra_aliases.append(folded_alias)
     base_aliases.extend(extra_aliases)
     return base_aliases
 
 
 def setupwrapcolorwrite(ui):
     # wrap ui.write so diff output can be labeled/colorized
     def wrapwrite(orig, *args, **kw):
         label = kw.pop('label', b'')
         for chunk, l in patch.difflabel(lambda: args):
             orig(chunk, label=label + l)
 
     oldwrite = ui.write
 
     def wrap(*args, **kwargs):
         return wrapwrite(oldwrite, *args, **kwargs)
 
     setattr(ui, 'write', wrap)
     return oldwrite
 
 
 def filterchunks(ui, originalhunks, usecurses, testfile, match, operation=None):
     try:
         if usecurses:
             if testfile:
                 recordfn = crecordmod.testdecorator(
                     testfile, crecordmod.testchunkselector
                 )
             else:
                 recordfn = crecordmod.chunkselector
 
             return crecordmod.filterpatch(
                 ui, originalhunks, recordfn, operation
             )
     except crecordmod.fallbackerror as e:
         ui.warn(b'%s\n' % e)
         ui.warn(_(b'falling back to text mode\n'))
 
     return patch.filterpatch(ui, originalhunks, match, operation)
 
 
 def recordfilter(ui, originalhunks, match, operation=None):
     """Prompts the user to filter the originalhunks and return a list of
     selected hunks.
     *operation* is used for to build ui messages to indicate the user what
     kind of filtering they are doing: reverting, committing, shelving, etc.
     (see patch.filterpatch).
     """
     usecurses = crecordmod.checkcurses(ui)
     testfile = ui.config(b'experimental', b'crecordtest')
     oldwrite = setupwrapcolorwrite(ui)
     try:
         newchunks, newopts = filterchunks(
             ui, originalhunks, usecurses, testfile, match, operation
         )
     finally:
         ui.write = oldwrite
     return newchunks, newopts
 
 
 def dorecord(
     ui, repo, commitfunc, cmdsuggest, backupall, filterfn, *pats, **opts
 ):
     opts = pycompat.byteskwargs(opts)
     if not ui.interactive():
         if cmdsuggest:
             msg = _(b'running non-interactively, use %s instead') % cmdsuggest
         else:
             msg = _(b'running non-interactively')
         raise error.InputError(msg)
 
     # make sure username is set before going interactive
     if not opts.get(b'user'):
         ui.username()  # raise exception, username not provided
 
     def recordfunc(ui, repo, message, match, opts):
         """This is generic record driver.
 
         Its job is to interactively filter local changes, and
         accordingly prepare working directory into a state in which the
         job can be delegated to a non-interactive commit command such as
         'commit' or 'qrefresh'.
 
         After the actual job is done by non-interactive command, the
         working directory is restored to its original state.
 
         In the end we'll record interesting changes, and everything else
         will be left in place, so the user can continue working.
         """
         if not opts.get(b'interactive-unshelve'):
             checkunfinished(repo, commit=True)
         wctx = repo[None]
         merge = len(wctx.parents()) > 1
         if merge:
             raise error.InputError(
                 _(
                     b'cannot partially commit a merge '
                     b'(use "hg commit" instead)'
                 )
             )
 
         def fail(f, msg):
             raise error.InputError(b'%s: %s' % (f, msg))
 
         force = opts.get(b'force')
         if not force:
             match = matchmod.badmatch(match, fail)
 
         status = repo.status(match=match)
 
         overrides = {(b'ui', b'commitsubrepos'): True}
 
         with repo.ui.configoverride(overrides, b'record'):
             # subrepoutil.precommit() modifies the status
             tmpstatus = scmutil.status(
                 copymod.copy(status.modified),
                 copymod.copy(status.added),
                 copymod.copy(status.removed),
                 copymod.copy(status.deleted),
                 copymod.copy(status.unknown),
                 copymod.copy(status.ignored),
                 copymod.copy(status.clean),  # pytype: disable=wrong-arg-count
             )
 
             # Force allows -X subrepo to skip the subrepo.
             subs, commitsubs, newstate = subrepoutil.precommit(
                 repo.ui, wctx, tmpstatus, match, force=True
             )
             for s in subs:
                 if s in commitsubs:
                     dirtyreason = wctx.sub(s).dirtyreason(True)
                     raise error.Abort(dirtyreason)
 
         if not force:
             repo.checkcommitpatterns(wctx, match, status, fail)
         diffopts = patch.difffeatureopts(
             ui,
             opts=opts,
             whitespace=True,
             section=b'commands',
             configprefix=b'commit.interactive.',
         )
         diffopts.nodates = True
         diffopts.git = True
         diffopts.showfunc = True
         originaldiff = patch.diff(repo, changes=status, opts=diffopts)
         originalchunks = patch.parsepatch(originaldiff)
         match = scmutil.match(repo[None], pats)
 
         # 1. filter patch, since we are intending to apply subset of it
         try:
             chunks, newopts = filterfn(ui, originalchunks, match)
         except error.PatchError as err:
             raise error.InputError(_(b'error parsing patch: %s') % err)
         opts.update(newopts)
 
         # We need to keep a backup of files that have been newly added and
         # modified during the recording process because there is a previous
         # version without the edit in the workdir. We also will need to restore
         # files that were the sources of renames so that the patch application
         # works.
         newlyaddedandmodifiedfiles, alsorestore = newandmodified(
             chunks, originalchunks
         )
         contenders = set()
         for h in chunks:
             try:
                 contenders.update(set(h.files()))
             except AttributeError:
                 pass
 
         changed = status.modified + status.added + status.removed
         newfiles = [f for f in changed if f in contenders]
         if not newfiles:
             ui.status(_(b'no changes to record\n'))
             return 0
 
         modified = set(status.modified)
 
         # 2. backup changed files, so we can restore them in the end
 
         if backupall:
             tobackup = changed
         else:
             tobackup = [
                 f
                 for f in newfiles
                 if f in modified or f in newlyaddedandmodifiedfiles
             ]
         backups = {}
         if tobackup:
             backupdir = repo.vfs.join(b'record-backups')
             try:
                 os.mkdir(backupdir)
             except OSError as err:
                 if err.errno != errno.EEXIST:
                     raise
         try:
             # backup continues
             for f in tobackup:
                 fd, tmpname = pycompat.mkstemp(
                     prefix=os.path.basename(f) + b'.', dir=backupdir
                 )
                 os.close(fd)
                 ui.debug(b'backup %r as %r\n' % (f, tmpname))
                 util.copyfile(repo.wjoin(f), tmpname, copystat=True)
                 backups[f] = tmpname
 
             fp = stringio()
             for c in chunks:
                 fname = c.filename()
                 if fname in backups:
                     c.write(fp)
             dopatch = fp.tell()
             fp.seek(0)
 
             # 2.5 optionally review / modify patch in text editor
             if opts.get(b'review', False):
                 patchtext = (
                     crecordmod.diffhelptext
                     + crecordmod.patchhelptext
                     + fp.read()
                 )
                 reviewedpatch = ui.edit(
                     patchtext, b"", action=b"diff", repopath=repo.path
                 )
                 fp.truncate(0)
                 fp.write(reviewedpatch)
                 fp.seek(0)
 
             [os.unlink(repo.wjoin(c)) for c in newlyaddedandmodifiedfiles]
             # 3a. apply filtered patch to clean repo  (clean)
             if backups:
                 m = scmutil.matchfiles(repo, set(backups.keys()) | alsorestore)
                 mergemod.revert_to(repo[b'.'], matcher=m)
 
             # 3b. (apply)
             if dopatch:
                 try:
                     ui.debug(b'applying patch\n')
                     ui.debug(fp.getvalue())
                     patch.internalpatch(ui, repo, fp, 1, eolmode=None)
                 except error.PatchError as err:
                     raise error.InputError(pycompat.bytestr(err))
             del fp
 
             # 4. We prepared working directory according to filtered
             #    patch. Now is the time to delegate the job to
             #    commit/qrefresh or the like!
 
             # Make all of the pathnames absolute.
             newfiles = [repo.wjoin(nf) for nf in newfiles]
             return commitfunc(ui, repo, *newfiles, **pycompat.strkwargs(opts))
         finally:
             # 5. finally restore backed-up files
             try:
                 dirstate = repo.dirstate
                 for realname, tmpname in pycompat.iteritems(backups):
                     ui.debug(b'restoring %r to %r\n' % (tmpname, realname))
 
                     if dirstate[realname] == b'n':
                         # without normallookup, restoring timestamp
                         # may cause partially committed files
                         # to be treated as unmodified
                         dirstate.normallookup(realname)
 
                     # copystat=True here and above are a hack to trick any
                     # editors that have f open that we haven't modified them.
                     #
                     # Also note that this racy as an editor could notice the
                     # file's mtime before we've finished writing it.
                     util.copyfile(tmpname, repo.wjoin(realname), copystat=True)
                     os.unlink(tmpname)
                 if tobackup:
                     os.rmdir(backupdir)
             except OSError:
                 pass
 
     def recordinwlock(ui, repo, message, match, opts):
         with repo.wlock():
             return recordfunc(ui, repo, message, match, opts)
 
     return commit(ui, repo, recordinwlock, pats, opts)
 
 
 class dirnode(object):
     """
     Represent a directory in user working copy with information required for
     the purpose of tersing its status.
 
     path is the path to the directory, without a trailing '/'
 
     statuses is a set of statuses of all files in this directory (this includes
     all the files in all the subdirectories too)
 
     files is a list of files which are direct child of this directory
 
     subdirs is a dictionary of sub-directory name as the key and it's own
     dirnode object as the value
     """
 
     def __init__(self, dirpath):
         self.path = dirpath
         self.statuses = set()
         self.files = []
         self.subdirs = {}
 
     def _addfileindir(self, filename, status):
         """Add a file in this directory as a direct child."""
         self.files.append((filename, status))
 
     def addfile(self, filename, status):
         """
         Add a file to this directory or to its direct parent directory.
 
         If the file is not direct child of this directory, we traverse to the
         directory of which this file is a direct child of and add the file
         there.
         """
 
         # the filename contains a path separator, it means it's not the direct
         # child of this directory
         if b'/' in filename:
             subdir, filep = filename.split(b'/', 1)
 
             # does the dirnode object for subdir exists
             if subdir not in self.subdirs:
                 subdirpath = pathutil.join(self.path, subdir)
                 self.subdirs[subdir] = dirnode(subdirpath)
 
             # try adding the file in subdir
             self.subdirs[subdir].addfile(filep, status)
 
         else:
             self._addfileindir(filename, status)
 
         if status not in self.statuses:
             self.statuses.add(status)
 
     def iterfilepaths(self):
         """Yield (status, path) for files directly under this directory."""
         for f, st in self.files:
             yield st, pathutil.join(self.path, f)
 
     def tersewalk(self, terseargs):
         """
         Yield (status, path) obtained by processing the status of this
         dirnode.
 
         terseargs is the string of arguments passed by the user with `--terse`
         flag.
 
         Following are the cases which can happen:
 
         1) All the files in the directory (including all the files in its
         subdirectories) share the same status and the user has asked us to terse
         that status. -> yield (status, dirpath).  dirpath will end in '/'.
 
         2) Otherwise, we do following:
 
                 a) Yield (status, filepath)  for all the files which are in this
                     directory (only the ones in this directory, not the subdirs)
 
                 b) Recurse the function on all the subdirectories of this
                    directory
         """
 
         if len(self.statuses) == 1:
             onlyst = self.statuses.pop()
 
             # Making sure we terse only when the status abbreviation is
             # passed as terse argument
             if onlyst in terseargs:
                 yield onlyst, self.path + b'/'
                 return
 
         # add the files to status list
         for st, fpath in self.iterfilepaths():
             yield st, fpath
 
         # recurse on the subdirs
         for dirobj in self.subdirs.values():
             for st, fpath in dirobj.tersewalk(terseargs):
                 yield st, fpath
 
 
 def tersedir(statuslist, terseargs):
     """
     Terse the status if all the files in a directory shares the same status.
 
     statuslist is scmutil.status() object which contains a list of files for
     each status.
     terseargs is string which is passed by the user as the argument to `--terse`
     flag.
 
     The function makes a tree of objects of dirnode class, and at each node it
     stores the information required to know whether we can terse a certain
     directory or not.
     """
     # the order matters here as that is used to produce final list
     allst = (b'm', b'a', b'r', b'd', b'u', b'i', b'c')
 
     # checking the argument validity
     for s in pycompat.bytestr(terseargs):
         if s not in allst:
             raise error.InputError(_(b"'%s' not recognized") % s)
 
     # creating a dirnode object for the root of the repo
     rootobj = dirnode(b'')
     pstatus = (
         b'modified',
         b'added',
         b'deleted',
         b'clean',
         b'unknown',
         b'ignored',
         b'removed',
     )
 
     tersedict = {}
     for attrname in pstatus:
         statuschar = attrname[0:1]
         for f in getattr(statuslist, attrname):
             rootobj.addfile(f, statuschar)
         tersedict[statuschar] = []
 
     # we won't be tersing the root dir, so add files in it
     for st, fpath in rootobj.iterfilepaths():
         tersedict[st].append(fpath)
 
     # process each sub-directory and build tersedict
     for subdir in rootobj.subdirs.values():
         for st, f in subdir.tersewalk(terseargs):
             tersedict[st].append(f)
 
     tersedlist = []
     for st in allst:
         tersedict[st].sort()
         tersedlist.append(tersedict[st])
 
     return scmutil.status(*tersedlist)
 
 
 def _commentlines(raw):
     '''Surround lineswith a comment char and a new line'''
     lines = raw.splitlines()
     commentedlines = [b'# %s' % line for line in lines]
     return b'\n'.join(commentedlines) + b'\n'
 
 
 @attr.s(frozen=True)
 class morestatus(object):
     reporoot = attr.ib()
     unfinishedop = attr.ib()
     unfinishedmsg = attr.ib()
     activemerge = attr.ib()
     unresolvedpaths = attr.ib()
     _formattedpaths = attr.ib(init=False, default=set())
     _label = b'status.morestatus'
 
     def formatfile(self, path, fm):
         self._formattedpaths.add(path)
         if self.activemerge and path in self.unresolvedpaths:
             fm.data(unresolved=True)
 
     def formatfooter(self, fm):
         if self.unfinishedop or self.unfinishedmsg:
             fm.startitem()
             fm.data(itemtype=b'morestatus')
 
         if self.unfinishedop:
             fm.data(unfinished=self.unfinishedop)
             statemsg = (
                 _(b'The repository is in an unfinished *%s* state.')
                 % self.unfinishedop
             )
             fm.plain(b'%s\n' % _commentlines(statemsg), label=self._label)
         if self.unfinishedmsg:
             fm.data(unfinishedmsg=self.unfinishedmsg)
 
         # May also start new data items.
         self._formatconflicts(fm)
 
         if self.unfinishedmsg:
             fm.plain(
                 b'%s\n' % _commentlines(self.unfinishedmsg), label=self._label
             )
 
     def _formatconflicts(self, fm):
         if not self.activemerge:
             return
 
         if self.unresolvedpaths:
             mergeliststr = b'\n'.join(
                 [
                     b'    %s'
                     % util.pathto(self.reporoot, encoding.getcwd(), path)
                     for path in self.unresolvedpaths
                 ]
             )
             msg = (
                 _(
                     b'''Unresolved merge conflicts:
 
 %s
 
 To mark files as resolved:  hg resolve --mark FILE'''
                 )
                 % mergeliststr
             )
 
             # If any paths with unresolved conflicts were not previously
             # formatted, output them now.
             for f in self.unresolvedpaths:
                 if f in self._formattedpaths:
                     # Already output.
                     continue
                 fm.startitem()
                 # We can't claim to know the status of the file - it may just
                 # have been in one of the states that were not requested for
                 # display, so it could be anything.
                 fm.data(itemtype=b'file', path=f, unresolved=True)
 
         else:
             msg = _(b'No unresolved merge conflicts.')
 
         fm.plain(b'%s\n' % _commentlines(msg), label=self._label)
 
 
 def readmorestatus(repo):
     """Returns a morestatus object if the repo has unfinished state."""
     statetuple = statemod.getrepostate(repo)
     mergestate = mergestatemod.mergestate.read(repo)
     activemerge = mergestate.active()
     if not statetuple and not activemerge:
         return None
 
     unfinishedop = unfinishedmsg = unresolved = None
     if statetuple:
         unfinishedop, unfinishedmsg = statetuple
     if activemerge:
         unresolved = sorted(mergestate.unresolved())
     return morestatus(
         repo.root, unfinishedop, unfinishedmsg, activemerge, unresolved
     )
 
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     allcmds = []
     for e in keys:
         aliases = parsealiases(e)
         allcmds.extend(aliases)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith(b"debug") or found.startswith(b"debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice, allcmds
 
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice, allcmds = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = sorted(choice)
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return list(choice.values())[0]
 
     raise error.UnknownCommand(cmd, allcmds)
 
 
 def changebranch(ui, repo, revs, label, opts):
     """ Change the branch name of given revs to label """
 
     with repo.wlock(), repo.lock(), repo.transaction(b'branches'):
         # abort in case of uncommitted merge or dirty wdir
         bailifchanged(repo)
         revs = scmutil.revrange(repo, revs)
         if not revs:
             raise error.InputError(b"empty revision set")
         roots = repo.revs(b'roots(%ld)', revs)
         if len(roots) > 1:
             raise error.InputError(
                 _(b"cannot change branch of non-linear revisions")
             )
         rewriteutil.precheck(repo, revs, b'change branch of')
 
         root = repo[roots.first()]
         rpb = {parent.branch() for parent in root.parents()}
         if (
             not opts.get(b'force')
             and label not in rpb
             and label in repo.branchmap()
         ):
             raise error.InputError(
                 _(b"a branch of the same name already exists")
             )
 
         # make sure only topological heads
         if repo.revs(b'heads(%ld) - head()', revs):
             raise error.InputError(
                 _(b"cannot change branch in middle of a stack")
             )
 
         replacements = {}
         # avoid import cycle mercurial.cmdutil -> mercurial.context ->
         # mercurial.subrepo -> mercurial.cmdutil
         from . import context
 
         for rev in revs:
             ctx = repo[rev]
             oldbranch = ctx.branch()
             # check if ctx has same branch
             if oldbranch == label:
                 continue
 
             def filectxfn(repo, newctx, path):
                 try:
                     return ctx[path]
                 except error.ManifestLookupError:
                     return None
 
             ui.debug(
                 b"changing branch of '%s' from '%s' to '%s'\n"
                 % (hex(ctx.node()), oldbranch, label)
             )
             extra = ctx.extra()
             extra[b'branch_change'] = hex(ctx.node())
             # While changing branch of set of linear commits, make sure that
             # we base our commits on new parent rather than old parent which
             # was obsoleted while changing the branch
             p1 = ctx.p1().node()
             p2 = ctx.p2().node()
             if p1 in replacements:
                 p1 = replacements[p1][0]
             if p2 in replacements:
                 p2 = replacements[p2][0]
 
             mc = context.memctx(
                 repo,
                 (p1, p2),
                 ctx.description(),
                 ctx.files(),
                 filectxfn,
                 user=ctx.user(),
                 date=ctx.date(),
                 extra=extra,
                 branch=label,
             )
 
             newnode = repo.commitctx(mc)
             replacements[ctx.node()] = (newnode,)
             ui.debug(b'new node id is %s\n' % hex(newnode))
 
         # create obsmarkers and move bookmarks
         scmutil.cleanupnodes(
             repo, replacements, b'branch-change', fixphase=True
         )
 
         # move the working copy too
         wctx = repo[None]
         # in-progress merge is a bit too complex for now.
         if len(wctx.parents()) == 1:
             newid = replacements.get(wctx.p1().node())
             if newid is not None:
                 # avoid import cycle mercurial.cmdutil -> mercurial.hg ->
                 # mercurial.cmdutil
                 from . import hg
 
                 hg.update(repo, newid[0], quietempty=True)
 
         ui.status(_(b"changed branch on %d changesets\n") % len(replacements))
 
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, b".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 
 def bailifchanged(repo, merge=True, hint=None):
     """enforce the precondition that working directory must be clean.
 
     'merge' can be set to false if a pending uncommitted merge should be
     ignored (such as when 'update --check' runs).
 
     'hint' is the usual hint given to Abort exception.
     """
 
     if merge and repo.dirstate.p2() != repo.nullid:
         raise error.StateError(_(b'outstanding uncommitted merge'), hint=hint)
     st = repo.status()
     if st.modified or st.added or st.removed or st.deleted:
         raise error.StateError(_(b'uncommitted changes'), hint=hint)
     ctx = repo[None]
     for s in sorted(ctx.substate):
         ctx.sub(s).bailifchanged(hint=hint)
 
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
 
     check_at_most_one_arg(opts, b'message', b'logfile')
 
     message = opts.get(b'message')
     logfile = opts.get(b'logfile')
 
     if not message and logfile:
         try:
             if isstdiofilename(logfile):
                 message = ui.fin.read()
             else:
                 message = b'\n'.join(util.readfile(logfile).splitlines())
         except IOError as inst:
             raise error.Abort(
                 _(b"can't read commit message '%s': %s")
                 % (logfile, encoding.strtolocal(inst.strerror))
             )
     return message
 
 
 def mergeeditform(ctxorbool, baseformname):
     """return appropriate editform name (referencing a committemplate)
 
     'ctxorbool' is either a ctx to be committed, or a bool indicating whether
     merging is committed.
 
     This returns baseformname with '.merge' appended if it is a merge,
     otherwise '.normal' is appended.
     """
     if isinstance(ctxorbool, bool):
         if ctxorbool:
             return baseformname + b".merge"
     elif len(ctxorbool.parents()) > 1:
         return baseformname + b".merge"
 
     return baseformname + b".normal"
 
 
 def getcommiteditor(
     edit=False, finishdesc=None, extramsg=None, editform=b'', **opts
 ):
     """get appropriate commit message editor according to '--edit' option
 
     'finishdesc' is a function to be called with edited commit message
     (= 'description' of the new changeset) just after editing, but
     before checking empty-ness. It should return actual text to be
     stored into history. This allows to change description before
     storing.
 
     'extramsg' is a extra message to be shown in the editor instead of
     'Leave message empty to abort commit' line. 'HG: ' prefix and EOL
     is automatically added.
 
     'editform' is a dot-separated list of names, to distinguish
     the purpose of commit text editing.
 
     'getcommiteditor' returns 'commitforceeditor' regardless of
     'edit', if one of 'finishdesc' or 'extramsg' is specified, because
     they are specific for usage in MQ.
     """
     if edit or finishdesc or extramsg:
         return lambda r, c, s: commitforceeditor(
             r, c, s, finishdesc=finishdesc, extramsg=extramsg, editform=editform
         )
     elif editform:
         return lambda r, c, s: commiteditor(r, c, s, editform=editform)
     else:
         return commiteditor
 
 
 def _escapecommandtemplate(tmpl):
     parts = []
     for typ, start, end in templater.scantemplate(tmpl, raw=True):
         if typ == b'string':
             parts.append(stringutil.escapestr(tmpl[start:end]))
         else:
             parts.append(tmpl[start:end])
     return b''.join(parts)
 
 
 def rendercommandtemplate(ui, tmpl, props):
     r"""Expand a literal template 'tmpl' in a way suitable for command line
 
     '\' in outermost string is not taken as an escape character because it
     is a directory separator on Windows.
 
     >>> from . import ui as uimod
     >>> ui = uimod.ui()
     >>> rendercommandtemplate(ui, b'c:\\{path}', {b'path': b'foo'})
     'c:\\foo'
     >>> rendercommandtemplate(ui, b'{"c:\\{path}"}', {'path': b'foo'})
     'c:{path}'
     """
     if not tmpl:
         return tmpl
     t = formatter.maketemplater(ui, _escapecommandtemplate(tmpl))
     return t.renderdefault(props)
 
 
 def rendertemplate(ctx, tmpl, props=None):
     """Expand a literal template 'tmpl' byte-string against one changeset
 
     Each props item must be a stringify-able value or a callable returning
     such value, i.e. no bare list nor dict should be passed.
     """
     repo = ctx.repo()
     tres = formatter.templateresources(repo.ui, repo)
     t = formatter.maketemplater(
         repo.ui, tmpl, defaults=templatekw.keywords, resources=tres
     )
     mapping = {b'ctx': ctx}
     if props:
         mapping.update(props)
     return t.renderdefault(mapping)
 
 
 def format_changeset_summary(ui, ctx, command=None, default_spec=None):
     """Format a changeset summary (one line)."""
     spec = None
     if command:
         spec = ui.config(
             b'command-templates', b'oneline-summary.%s' % command, None
         )
     if not spec:
         spec = ui.config(b'command-templates', b'oneline-summary')
     if not spec:
         spec = default_spec
     if not spec:
         spec = (
             b'{separate(" ", '
             b'label("oneline-summary.changeset", "{rev}:{node|short}")'
             b', '
             b'join(filter(namespaces % "{ifeq(namespace, "branches", "", join(names % "{label("oneline-summary.{namespace}", name)}", " "))}"), " ")'
             b')} '
             b'"{label("oneline-summary.desc", desc|firstline)}"'
         )
     text = rendertemplate(ctx, spec)
     return text.split(b'\n')[0]
 
 
 def _buildfntemplate(pat, total=None, seqno=None, revwidth=None, pathname=None):
     r"""Convert old-style filename format string to template string
 
     >>> _buildfntemplate(b'foo-%b-%n.patch', seqno=0)
     'foo-{reporoot|basename}-{seqno}.patch'
     >>> _buildfntemplate(b'%R{tags % "{tag}"}%H')
     '{rev}{tags % "{tag}"}{node}'
 
     '\' in outermost strings has to be escaped because it is a directory
     separator on Windows:
 
     >>> _buildfntemplate(b'c:\\tmp\\%R\\%n.patch', seqno=0)
     'c:\\\\tmp\\\\{rev}\\\\{seqno}.patch'
     >>> _buildfntemplate(b'\\\\foo\\bar.patch')
     '\\\\\\\\foo\\\\bar.patch'
     >>> _buildfntemplate(b'\\{tags % "{tag}"}')
     '\\\\{tags % "{tag}"}'
 
     but inner strings follow the template rules (i.e. '\' is taken as an
     escape character):
 
     >>> _buildfntemplate(br'{"c:\tmp"}', seqno=0)
     '{"c:\\tmp"}'
     """
     expander = {
         b'H': b'{node}',
         b'R': b'{rev}',
         b'h': b'{node|short}',
         b'm': br'{sub(r"[^\w]", "_", desc|firstline)}',
         b'r': b'{if(revwidth, pad(rev, revwidth, "0", left=True), rev)}',
         b'%': b'%',
         b'b': b'{reporoot|basename}',
     }
     if total is not None:
         expander[b'N'] = b'{total}'
     if seqno is not None:
         expander[b'n'] = b'{seqno}'
     if total is not None and seqno is not None:
         expander[b'n'] = b'{pad(seqno, total|stringify|count, "0", left=True)}'
     if pathname is not None:
         expander[b's'] = b'{pathname|basename}'
         expander[b'd'] = b'{if(pathname|dirname, pathname|dirname, ".")}'
         expander[b'p'] = b'{pathname}'
 
     newname = []
     for typ, start, end in templater.scantemplate(pat, raw=True):
         if typ != b'string':
             newname.append(pat[start:end])
             continue
         i = start
         while i < end:
             n = pat.find(b'%', i, end)
             if n < 0:
                 newname.append(stringutil.escapestr(pat[i:end]))
                 break
             newname.append(stringutil.escapestr(pat[i:n]))
             if n + 2 > end:
                 raise error.Abort(
                     _(b"incomplete format spec in output filename")
                 )
             c = pat[n + 1 : n + 2]
             i = n + 2
             try:
                 newname.append(expander[c])
             except KeyError:
                 raise error.Abort(
                     _(b"invalid format spec '%%%s' in output filename") % c
                 )
     return b''.join(newname)
 
 
 def makefilename(ctx, pat, **props):
     if not pat:
         return pat
     tmpl = _buildfntemplate(pat, **props)
     # BUG: alias expansion shouldn't be made against template fragments
     # rewritten from %-format strings, but we have no easy way to partially
     # disable the expansion.
     return rendertemplate(ctx, tmpl, pycompat.byteskwargs(props))
 
 
 def isstdiofilename(pat):
     """True if the given pat looks like a filename denoting stdin/stdout"""
     return not pat or pat == b'-'
 
 
 class _unclosablefile(object):
     def __init__(self, fp):
         self._fp = fp
 
     def close(self):
         pass
 
     def __iter__(self):
         return iter(self._fp)
 
     def __getattr__(self, attr):
         return getattr(self._fp, attr)
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         pass
 
 
 def makefileobj(ctx, pat, mode=b'wb', **props):
     writable = mode not in (b'r', b'rb')
 
     if isstdiofilename(pat):
         repo = ctx.repo()
         if writable:
             fp = repo.ui.fout
         else:
             fp = repo.ui.fin
         return _unclosablefile(fp)
     fn = makefilename(ctx, pat, **props)
     return open(fn, mode)
 
 
 def openstorage(repo, cmd, file_, opts, returnrevlog=False):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts[b'changelog']
     mf = opts[b'manifest']
     dir = opts[b'dir']
     msg = None
     if cl and mf:
         msg = _(b'cannot specify --changelog and --manifest at the same time')
     elif cl and dir:
         msg = _(b'cannot specify --changelog and --dir at the same time')
     elif cl or mf or dir:
         if file_:
             msg = _(b'cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _(
                 b'cannot specify --changelog or --manifest or --dir '
                 b'without a repository'
             )
     if msg:
         raise error.InputError(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.unfiltered().changelog
         elif dir:
             if not scmutil.istreemanifest(repo):
                 raise error.InputError(
                     _(
                         b"--dir can only be used on repos with "
                         b"treemanifest enabled"
                     )
                 )
             if not dir.endswith(b'/'):
                 dir = dir + b'/'
             dirlog = repo.manifestlog.getstorage(dir)
             if len(dirlog):
                 r = dirlog
         elif mf:
             r = repo.manifestlog.getstorage(b'')
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
 
         # Not all storage may be revlogs. If requested, try to return an actual
         # revlog instance.
         if returnrevlog:
             if isinstance(r, revlog.revlog):
                 pass
             elif util.safehasattr(r, b'_revlog'):
                 r = r._revlog  # pytype: disable=attribute-error
             elif r is not None:
                 raise error.InputError(
                     _(b'%r does not appear to be a revlog') % r
                 )
 
     if not r:
         if not returnrevlog:
             raise error.InputError(_(b'cannot give path to non-revlog'))
 
         if not file_:
             raise error.CommandError(cmd, _(b'invalid arguments'))
         if not os.path.isfile(file_):
             raise error.InputError(_(b"revlog '%s' not found") % file_)
+
+        target = (revlog_constants.KIND_OTHER, b'free-form:%s' % file_)
         r = revlog.revlog(
-            vfsmod.vfs(encoding.getcwd(), audit=False), file_[:-2] + b".i"
+            vfsmod.vfs(encoding.getcwd(), audit=False),
+            target=target,
+            indexfile=file_[:-2] + b".i",
         )
     return r
 
 
 def openrevlog(repo, cmd, file_, opts):
     """Obtain a revlog backing storage of an item.
 
     This is similar to ``openstorage()`` except it always returns a revlog.
 
     In most cases, a caller cares about the main storage object - not the
     revlog backing it. Therefore, this function should only be used by code
     that needs to examine low-level revlog implementation details. e.g. debug
     commands.
     """
     return openstorage(repo, cmd, file_, opts, returnrevlog=True)
 
 
 def copy(ui, repo, pats, opts, rename=False):
     check_incompatible_arguments(opts, b'forget', [b'dry_run'])
 
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     forget = opts.get(b"forget")
     after = opts.get(b"after")
     dryrun = opts.get(b"dry_run")
     rev = opts.get(b'at_rev')
     if rev:
         if not forget and not after:
             # TODO: Remove this restriction and make it also create the copy
             #       targets (and remove the rename source if rename==True).
             raise error.InputError(_(b'--at-rev requires --after'))
         ctx = scmutil.revsingle(repo, rev)
         if len(ctx.parents()) > 1:
             raise error.InputError(
                 _(b'cannot mark/unmark copy in merge commit')
             )
     else:
         ctx = repo[None]
 
     pctx = ctx.p1()
 
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
 
     if forget:
         if ctx.rev() is None:
             new_ctx = ctx
         else:
             if len(ctx.parents()) > 1:
                 raise error.InputError(_(b'cannot unmark copy in merge commit'))
             # avoid cycle context -> subrepo -> cmdutil
             from . import context
 
             rewriteutil.precheck(repo, [ctx.rev()], b'uncopy')
             new_ctx = context.overlayworkingctx(repo)
             new_ctx.setbase(ctx.p1())
             mergemod.graft(repo, ctx, wctx=new_ctx)
 
         match = scmutil.match(ctx, pats, opts)
 
         current_copies = ctx.p1copies()
         current_copies.update(ctx.p2copies())
 
         uipathfn = scmutil.getuipathfn(repo)
         for f in ctx.walk(match):
             if f in current_copies:
                 new_ctx[f].markcopied(None)
             elif match.exact(f):
                 ui.warn(
                     _(
                         b'%s: not unmarking as copy - file is not marked as copied\n'
                     )
                     % uipathfn(f)
                 )
 
         if ctx.rev() is not None:
             with repo.lock():
                 mem_ctx = new_ctx.tomemctx_for_amend(ctx)
                 new_node = mem_ctx.commit()
 
                 if repo.dirstate.p1() == ctx.node():
                     with repo.dirstate.parentchange():
                         scmutil.movedirstate(repo, repo[new_node])
                 replacements = {ctx.node(): [new_node]}
                 scmutil.cleanupnodes(
                     repo, replacements, b'uncopy', fixphase=True
                 )
 
         return
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise error.InputError(_(b'no source or destination specified'))
     if len(pats) == 1:
         raise error.InputError(_(b'no destination specified'))
     dest = pats.pop()
 
     def walkpat(pat):
         srcs = []
         # TODO: Inline and simplify the non-working-copy version of this code
         # since it shares very little with the working-copy version of it.
         ctx_to_walk = ctx if ctx.rev() is None else pctx
         m = scmutil.match(ctx_to_walk, [pat], opts, globbed=True)
         for abs in ctx_to_walk.walk(m):
             rel = uipathfn(abs)
             exact = m.exact(abs)
             if abs not in ctx:
                 if abs in pctx:
                     if not after:
                         if exact:
                             ui.warn(
                                 _(
                                     b'%s: not copying - file has been marked '
                                     b'for remove\n'
                                 )
                                 % rel
                             )
                         continue
                 else:
                     if exact:
                         ui.warn(
                             _(b'%s: not copying - file is not managed\n') % rel
                         )
                     continue
 
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     if ctx.rev() is not None:
         rewriteutil.precheck(repo, [ctx.rev()], b'uncopy')
         absdest = pathutil.canonpath(repo.root, cwd, dest)
         if ctx.hasdir(absdest):
             raise error.InputError(
                 _(b'%s: --at-rev does not support a directory as destination')
                 % uipathfn(absdest)
             )
         if absdest not in ctx:
             raise error.InputError(
                 _(b'%s: copy destination does not exist in %s')
                 % (uipathfn(absdest), ctx)
             )
 
         # avoid cycle context -> subrepo -> cmdutil
         from . import context
 
         copylist = []
         for pat in pats:
             srcs = walkpat(pat)
             if not srcs:
                 continue
             for abs, rel, exact in srcs:
                 copylist.append(abs)
 
         if not copylist:
             raise error.InputError(_(b'no files to copy'))
         # TODO: Add support for `hg cp --at-rev . foo bar dir` and
         # `hg cp --at-rev . dir1 dir2`, preferably unifying the code with the
         # existing functions below.
         if len(copylist) != 1:
             raise error.InputError(_(b'--at-rev requires a single source'))
 
         new_ctx = context.overlayworkingctx(repo)
         new_ctx.setbase(ctx.p1())
         mergemod.graft(repo, ctx, wctx=new_ctx)
 
         new_ctx.markcopied(absdest, copylist[0])
 
         with repo.lock():
             mem_ctx = new_ctx.tomemctx_for_amend(ctx)
             new_node = mem_ctx.commit()
 
             if repo.dirstate.p1() == ctx.node():
                 with repo.dirstate.parentchange():
                     scmutil.movedirstate(repo, repo[new_node])
             replacements = {ctx.node(): [new_node]}
             scmutil.cleanupnodes(repo, replacements, b'copy', fixphase=True)
 
         return
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if b'/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit(b'/', 1)
             abstarget = repo.dirstate.normalize(abspath) + b'/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(
                 _(b'%s: not overwriting - %s collides with %s\n')
                 % (
                     reltarget,
                     repo.pathto(abssrc, cwd),
                     repo.pathto(prevsrc, cwd),
                 )
             )
             return True  # report a failure
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if repo.dirstate.normalize(abssrc) == repo.dirstate.normalize(
                 abstarget
             ):
                 if not rename:
                     ui.warn(_(b"%s: can't copy - same file\n") % reltarget)
                     return True  # report a failure
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in b'mn':
             if not opts[b'force']:
                 if state in b'mn':
                     msg = _(b'%s: not overwriting - file already committed\n')
                     if after:
                         flags = b'--after --force'
                     else:
                         flags = b'--force'
                     if rename:
                         hint = (
                             _(
                                 b"('hg rename %s' to replace the file by "
                                 b'recording a rename)\n'
                             )
                             % flags
                         )
                     else:
                         hint = (
                             _(
                                 b"('hg copy %s' to replace the file by "
                                 b'recording a copy)\n'
                             )
                             % flags
                         )
                 else:
                     msg = _(b'%s: not overwriting - file exists\n')
                     if rename:
                         hint = _(
                             b"('hg rename --after' to record the rename)\n"
                         )
                     else:
                         hint = _(b"('hg copy --after' to record the copy)\n")
                 ui.warn(msg % reltarget)
                 ui.warn(hint)
                 return True  # report a failure
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(
                         _(b'%s: not recording move - %s does not exist\n')
                         % (relsrc, reltarget)
                     )
                 else:
                     ui.warn(
                         _(b'%s: not recording copy - %s does not exist\n')
                         % (relsrc, reltarget)
                     )
                 return True  # report a failure
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or b'.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + b"~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     # Preserve stat info on renames, not on copies; this matches
                     # Linux CLI behavior.
                     util.copyfile(src, target, copystat=rename)
                 srcexists = True
             except IOError as inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_(b'%s: deleted in working directory\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(
                         _(b'%s: cannot copy - %s\n')
                         % (relsrc, encoding.strtolocal(inst.strerror))
                     )
                     return True  # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_(b'moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_(b'copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(
             ui, repo, ctx, abssrc, abstarget, dryrun=dryrun, cwd=cwd
         )
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 rmdir = repo.ui.configbool(b'experimental', b'removeemptydirs')
                 repo.wvfs.unlinkpath(abssrc, rmdir=rmdir)
             ctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(pycompat.ossep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(
                 dest, os.path.basename(util.localpath(p))
             )
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(
                 dest, os.path.basename(util.localpath(p))
             )
         else:
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(pycompat.ossep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(pycompat.ossep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(
                         dest, os.path.basename(util.localpath(p))
                     )
                 else:
                     res = lambda p: dest
         return res
 
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise error.InputError(
                 _(
                     b'with multiple sources, destination must be an '
                     b'existing directory'
                 )
             )
         if util.endswithsep(dest):
             raise error.InputError(
                 _(b'destination %s is not a directory') % dest
             )
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise error.InputError(_(b'no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     return errors != 0
 
 
 ## facility to let extension process additional data into an import patch
 # list of identifier to be executed in order
 extrapreimport = []  # run before commit
 extrapostimport = []  # run after commit
 # mapping from identifier to actual import function
 #
 # 'preimport' are run before the commit is made and are provided the following
 # arguments:
 # - repo: the localrepository instance,
 # - patchdata: data extracted from patch header (cf m.patch.patchheadermap),
 # - extra: the future extra dictionary of the changeset, please mutate it,
 # - opts: the import options.
 # XXX ideally, we would just pass an ctx ready to be computed, that would allow
 # mutation of in memory commit and more. Feel free to rework the code to get
 # there.
 extrapreimportmap = {}
 # 'postimport' are run after the commit is made and are provided the following
 # argument:
 # - ctx: the changectx created by import.
 extrapostimportmap = {}
 
 
 def tryimportone(ui, repo, patchdata, parents, opts, msgs, updatefunc):
     """Utility function used by commands.import to import a single patch
 
     This function is explicitly defined here to help the evolve extension to
     wrap this part of the import logic.
 
     The API is currently a bit ugly because it a simple code translation from
     the import command. Feel free to make it better.
 
     :patchdata: a dictionary containing parsed patch data (such as from
                 ``patch.extract()``)
     :parents: nodes that will be parent of the created commit
     :opts: the full dict of option passed to the import command
     :msgs: list to save commit message to.
            (used in case we need to save it when failing)
     :updatefunc: a function that update a repo to a given node
                  updatefunc(<repo>, <node>)
     """
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     tmpname = patchdata.get(b'filename')
     message = patchdata.get(b'message')
     user = opts.get(b'user') or patchdata.get(b'user')
     date = opts.get(b'date') or patchdata.get(b'date')
     branch = patchdata.get(b'branch')
     nodeid = patchdata.get(b'nodeid')
     p1 = patchdata.get(b'p1')
     p2 = patchdata.get(b'p2')
 
     nocommit = opts.get(b'no_commit')
     importbranch = opts.get(b'import_branch')
     update = not opts.get(b'bypass')
     strip = opts[b"strip"]
     prefix = opts[b"prefix"]
     sim = float(opts.get(b'similarity') or 0)
 
     if not tmpname:
         return None, None, False
 
     rejects = False
 
     cmdline_message = logmessage(ui, opts)
     if cmdline_message:
         # pickup the cmdline msg
         message = cmdline_message
     elif message:
         # pickup the patch msg
         message = message.strip()
     else:
         # launch the editor
         message = None
     ui.debug(b'message:\n%s\n' % (message or b''))
 
     if len(parents) == 1:
         parents.append(repo[nullrev])
     if opts.get(b'exact'):
         if not nodeid or not p1:
             raise error.InputError(_(b'not a Mercurial patch'))
         p1 = repo[p1]
         p2 = repo[p2 or nullrev]
     elif p2:
         try:
             p1 = repo[p1]
             p2 = repo[p2]
             # Without any options, consider p2 only if the
             # patch is being applied on top of the recorded
             # first parent.
             if p1 != parents[0]:
                 p1 = parents[0]
                 p2 = repo[nullrev]
         except error.RepoError:
             p1, p2 = parents
         if p2.rev() == nullrev:
             ui.warn(
                 _(
                     b"warning: import the patch as a normal revision\n"
                     b"(use --exact to import the patch as a merge)\n"
                 )
             )
     else:
         p1, p2 = parents
 
     n = None
     if update:
         if p1 != parents[0]:
             updatefunc(repo, p1.node())
         if p2 != parents[1]:
             repo.setparents(p1.node(), p2.node())
 
         if opts.get(b'exact') or importbranch:
             repo.dirstate.setbranch(branch or b'default')
 
         partial = opts.get(b'partial', False)
         files = set()
         try:
             patch.patch(
                 ui,
                 repo,
                 tmpname,
                 strip=strip,
                 prefix=prefix,
                 files=files,
                 eolmode=None,
                 similarity=sim / 100.0,
             )
         except error.PatchError as e:
             if not partial:
                 raise error.Abort(pycompat.bytestr(e))
             if partial:
                 rejects = True
 
         files = list(files)
         if nocommit:
             if message:
                 msgs.append(message)
         else:
             if opts.get(b'exact') or p2:
                 # If you got here, you either use --force and know what
                 # you are doing or used --exact or a merge patch while
                 # being updated to its first parent.
                 m = None
             else:
                 m = scmutil.matchfiles(repo, files or [])
             editform = mergeeditform(repo[None], b'import.normal')
             if opts.get(b'exact'):
                 editor = None
             else:
                 editor = getcommiteditor(
                     editform=editform, **pycompat.strkwargs(opts)
                 )
             extra = {}
             for idfunc in extrapreimport:
                 extrapreimportmap[idfunc](repo, patchdata, extra, opts)
             overrides = {}
             if partial:
                 overrides[(b'ui', b'allowemptycommit')] = True
             if opts.get(b'secret'):
                 overrides[(b'phases', b'new-commit')] = b'secret'
             with repo.ui.configoverride(overrides, b'import'):
                 n = repo.commit(
                     message, user, date, match=m, editor=editor, extra=extra
                 )
                 for idfunc in extrapostimport:
                     extrapostimportmap[idfunc](repo[n])
     else:
         if opts.get(b'exact') or importbranch:
             branch = branch or b'default'
         else:
             branch = p1.branch()
         store = patch.filestore()
         try:
             files = set()
             try:
                 patch.patchrepo(
                     ui,
                     repo,
                     p1,
                     store,
                     tmpname,
                     strip,
                     prefix,
                     files,
                     eolmode=None,
                 )
             except error.PatchError as e:
                 raise error.Abort(stringutil.forcebytestr(e))
             if opts.get(b'exact'):
                 editor = None
             else:
                 editor = getcommiteditor(editform=b'import.bypass')
             memctx = context.memctx(
                 repo,
                 (p1.node(), p2.node()),
                 message,
                 files=files,
                 filectxfn=store,
                 user=user,
                 date=date,
                 branch=branch,
                 editor=editor,
             )
 
             overrides = {}
             if opts.get(b'secret'):
                 overrides[(b'phases', b'new-commit')] = b'secret'
             with repo.ui.configoverride(overrides, b'import'):
                 n = memctx.commit()
         finally:
             store.close()
     if opts.get(b'exact') and nocommit:
         # --exact with --no-commit is still useful in that it does merge
         # and branch bits
         ui.warn(_(b"warning: can't check exact import with --no-commit\n"))
     elif opts.get(b'exact') and (not n or hex(n) != nodeid):
         raise error.Abort(_(b'patch is damaged or loses information'))
     msg = _(b'applied to working directory')
     if n:
         # i18n: refers to a short changeset id
         msg = _(b'created %s') % short(n)
     return msg, n, rejects
 
 
 # facility to let extensions include additional data in an exported patch
 # list of identifiers to be executed in order
 extraexport = []
 # mapping from identifier to actual export function
 # function as to return a string to be added to the header or None
 # it is given two arguments (sequencenumber, changectx)
 extraexportmap = {}
 
 
 def _exportsingle(repo, ctx, fm, match, switch_parent, seqno, diffopts):
     node = scmutil.binnode(ctx)
     parents = [p.node() for p in ctx.parents() if p]
     branch = ctx.branch()
     if switch_parent:
         parents.reverse()
 
     if parents:
         prev = parents[0]
     else:
         prev = repo.nullid
 
     fm.context(ctx=ctx)
     fm.plain(b'# HG changeset patch\n')
     fm.write(b'user', b'# User %s\n', ctx.user())
     fm.plain(b'# Date %d %d\n' % ctx.date())
     fm.write(b'date', b'#      %s\n', fm.formatdate(ctx.date()))
     fm.condwrite(
         branch and branch != b'default', b'branch', b'# Branch %s\n', branch
     )
     fm.write(b'node', b'# Node ID %s\n', hex(node))
     fm.plain(b'# Parent  %s\n' % hex(prev))
     if len(parents) > 1:
         fm.plain(b'# Parent  %s\n' % hex(parents[1]))
     fm.data(parents=fm.formatlist(pycompat.maplist(hex, parents), name=b'node'))
 
     # TODO: redesign extraexportmap function to support formatter
     for headerid in extraexport:
         header = extraexportmap[headerid](seqno, ctx)
         if header is not None:
             fm.plain(b'# %s\n' % header)
 
     fm.write(b'desc', b'%s\n', ctx.description().rstrip())
     fm.plain(b'\n')
 
     if fm.isplain():
         chunkiter = patch.diffui(repo, prev, node, match, opts=diffopts)
         for chunk, label in chunkiter:
             fm.plain(chunk, label=label)
     else:
         chunkiter = patch.diff(repo, prev, node, match, opts=diffopts)
         # TODO: make it structured?
         fm.data(diff=b''.join(chunkiter))
 
 
 def _exportfile(repo, revs, fm, dest, switch_parent, diffopts, match):
     """Export changesets to stdout or a single file"""
     for seqno, rev in enumerate(revs, 1):
         ctx = repo[rev]
         if not dest.startswith(b'<'):
             repo.ui.note(b"%s\n" % dest)
         fm.startitem()
         _exportsingle(repo, ctx, fm, match, switch_parent, seqno, diffopts)
 
 
 def _exportfntemplate(
     repo, revs, basefm, fntemplate, switch_parent, diffopts, match
 ):
     """Export changesets to possibly multiple files"""
     total = len(revs)
     revwidth = max(len(str(rev)) for rev in revs)
     filemap = util.sortdict()  # filename: [(seqno, rev), ...]
 
     for seqno, rev in enumerate(revs, 1):
         ctx = repo[rev]
         dest = makefilename(
             ctx, fntemplate, total=total, seqno=seqno, revwidth=revwidth
         )
         filemap.setdefault(dest, []).append((seqno, rev))
 
     for dest in filemap:
         with formatter.maybereopen(basefm, dest) as fm:
             repo.ui.note(b"%s\n" % dest)
             for seqno, rev in filemap[dest]:
                 fm.startitem()
                 ctx = repo[rev]
                 _exportsingle(
                     repo, ctx, fm, match, switch_parent, seqno, diffopts
                 )
 
 
 def _prefetchchangedfiles(repo, revs, match):
     allfiles = set()
     for rev in revs:
         for file in repo[rev].files():
             if not match or match(file):
                 allfiles.add(file)
     match = scmutil.matchfiles(repo, allfiles)
     revmatches = [(rev, match) for rev in revs]
     scmutil.prefetchfiles(repo, revmatches)
 
 
 def export(
     repo,
     revs,
     basefm,
     fntemplate=b'hg-%h.patch',
     switch_parent=False,
     opts=None,
     match=None,
 ):
     """export changesets as hg patches
 
     Args:
       repo: The repository from which we're exporting revisions.
       revs: A list of revisions to export as revision numbers.
       basefm: A formatter to which patches should be written.
       fntemplate: An optional string to use for generating patch file names.
       switch_parent: If True, show diffs against second parent when not nullid.
                      Default is false, which always shows diff against p1.
       opts: diff options to use for generating the patch.
       match: If specified, only export changes to files matching this matcher.
 
     Returns:
       Nothing.
 
     Side Effect:
       "HG Changeset Patch" data is emitted to one of the following
       destinations:
         fntemplate specified: Each rev is written to a unique file named using
                             the given template.
         Otherwise: All revs will be written to basefm.
     """
     _prefetchchangedfiles(repo, revs, match)
 
     if not fntemplate:
         _exportfile(
             repo, revs, basefm, b'<unnamed>', switch_parent, opts, match
         )
     else:
         _exportfntemplate(
             repo, revs, basefm, fntemplate, switch_parent, opts, match
         )
 
 
 def exportfile(repo, revs, fp, switch_parent=False, opts=None, match=None):
     """Export changesets to the given file stream"""
     _prefetchchangedfiles(repo, revs, match)
 
     dest = getattr(fp, 'name', b'<unnamed>')
     with formatter.formatter(repo.ui, fp, b'export', {}) as fm:
         _exportfile(repo, revs, fm, dest, switch_parent, opts, match)
 
 
 def showmarker(fm, marker, index=None):
     """utility function to display obsolescence marker in a readable way
 
     To be used by debug function."""
     if index is not None:
         fm.write(b'index', b'%i ', index)
     fm.write(b'prednode', b'%s ', hex(marker.prednode()))
     succs = marker.succnodes()
     fm.condwrite(
         succs,
         b'succnodes',
         b'%s ',
         fm.formatlist(map(hex, succs), name=b'node'),
     )
     fm.write(b'flag', b'%X ', marker.flags())
     parents = marker.parentnodes()
     if parents is not None:
         fm.write(
             b'parentnodes',
             b'{%s} ',
             fm.formatlist(map(hex, parents), name=b'node', sep=b', '),
         )
     fm.write(b'date', b'(%s) ', fm.formatdate(marker.date()))
     meta = marker.metadata().copy()
     meta.pop(b'date', None)
     smeta = pycompat.rapply(pycompat.maybebytestr, meta)
     fm.write(
         b'metadata', b'{%s}', fm.formatdict(smeta, fmt=b'%r: %r', sep=b', ')
     )
     fm.plain(b'\n')
 
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
     mrevs = repo.revs(b'date(%s)', date)
     try:
         rev = mrevs.max()
     except ValueError:
         raise error.InputError(_(b"revision matching date not found"))
 
     ui.status(
         _(b"found revision %d from %s\n")
         % (rev, dateutil.datestr(repo[rev].date()))
     )
     return b'%d' % rev
 
 
 def add(ui, repo, match, prefix, uipathfn, explicitonly, **opts):
     bad = []
 
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
 
     match = repo.narrowmatch(match, includeexact=True)
     badmatch = matchmod.badmatch(match, badfn)
     dirstate = repo.dirstate
     # We don't want to just call wctx.walk here, since it would return a lot of
     # clean files, which we aren't interested in and takes time.
     for f in sorted(
         dirstate.walk(
             badmatch,
             subrepos=sorted(wctx.substate),
             unknown=True,
             ignored=False,
             full=False,
         )
     ):
         exact = match.exact(f)
         if exact or not explicitonly and f not in wctx and repo.wvfs.lexists(f):
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(
                     _(b'adding %s\n') % uipathfn(f), label=b'ui.addremove.added'
                 )
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             subprefix = repo.wvfs.reljoin(prefix, subpath)
             subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
             if opts.get('subrepos'):
                 bad.extend(
                     sub.add(ui, submatch, subprefix, subuipathfn, False, **opts)
                 )
             else:
                 bad.extend(
                     sub.add(ui, submatch, subprefix, subuipathfn, True, **opts)
                 )
         except error.LookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     if not opts.get('dry_run'):
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 
 def addwebdirpath(repo, serverpath, webconf):
     webconf[serverpath] = repo.root
     repo.ui.debug(b'adding %s = %s\n' % (serverpath, repo.root))
 
     for r in repo.revs(b'filelog("path:.hgsub")'):
         ctx = repo[r]
         for subpath in ctx.substate:
             ctx.sub(subpath).addwebdirpath(serverpath, webconf)
 
 
 def forget(
     ui, repo, match, prefix, uipathfn, explicitonly, dryrun, interactive
 ):
     if dryrun and interactive:
         raise error.InputError(
             _(b"cannot specify both --dry-run and --interactive")
         )
     bad = []
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     wctx = repo[None]
     forgot = []
 
     s = repo.status(match=matchmod.badmatch(match, badfn), clean=True)
     forget = sorted(s.modified + s.added + s.deleted + s.clean)
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         submatch = matchmod.subdirmatcher(subpath, match)
         subprefix = repo.wvfs.reljoin(prefix, subpath)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         try:
             subbad, subforgot = sub.forget(
                 submatch,
                 subprefix,
                 subuipathfn,
                 dryrun=dryrun,
                 interactive=interactive,
             )
             bad.extend([subpath + b'/' + f for f in subbad])
             forgot.extend([subpath + b'/' + f for f in subforgot])
         except error.LookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not repo.wvfs.isdir(f):
                 if f not in forgot:
                     if repo.wvfs.exists(f):
                         # Don't complain if the exact case match wasn't given.
                         # But don't do this until after checking 'forgot', so
                         # that subrepo files aren't normalized, and this op is
                         # purely from data cached by the status walk above.
                         if repo.dirstate.normalize(f) in repo.dirstate:
                             continue
                         ui.warn(
                             _(
                                 b'not removing %s: '
                                 b'file is already untracked\n'
                             )
                             % uipathfn(f)
                         )
                     bad.append(f)
 
     if interactive:
         responses = _(
             b'[Ynsa?]'
             b'$$ &Yes, forget this file'
             b'$$ &No, skip this file'
             b'$$ &Skip remaining files'
             b'$$ Include &all remaining files'
             b'$$ &? (display help)'
         )
         for filename in forget[:]:
             r = ui.promptchoice(
                 _(b'forget %s %s') % (uipathfn(filename), responses)
             )
             if r == 4:  # ?
                 while r == 4:
                     for c, t in ui.extractchoices(responses)[1]:
                         ui.write(b'%s - %s\n' % (c, encoding.lower(t)))
                     r = ui.promptchoice(
                         _(b'forget %s %s') % (uipathfn(filename), responses)
                     )
             if r == 0:  # yes
                 continue
             elif r == 1:  # no
                 forget.remove(filename)
             elif r == 2:  # Skip
                 fnindex = forget.index(filename)
                 del forget[fnindex:]
                 break
             elif r == 3:  # All
                 break
 
     for f in forget:
         if ui.verbose or not match.exact(f) or interactive:
             ui.status(
                 _(b'removing %s\n') % uipathfn(f), label=b'ui.addremove.removed'
             )
 
     if not dryrun:
         rejected = wctx.forget(forget, prefix)
         bad.extend(f for f in rejected if f in match.files())
         forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 
 def files(ui, ctx, m, uipathfn, fm, fmt, subrepos):
     ret = 1
 
     needsfctx = ui.verbose or {b'size', b'flags'} & fm.datahint()
     if fm.isplain() and not needsfctx:
         # Fast path. The speed-up comes from skipping the formatter, and batching
         # calls to ui.write.
         buf = []
         for f in ctx.matches(m):
             buf.append(fmt % uipathfn(f))
             if len(buf) > 100:
                 ui.write(b''.join(buf))
                 del buf[:]
             ret = 0
         if buf:
             ui.write(b''.join(buf))
     else:
         for f in ctx.matches(m):
             fm.startitem()
             fm.context(ctx=ctx)
             if needsfctx:
                 fc = ctx[f]
                 fm.write(b'size flags', b'% 10d % 1s ', fc.size(), fc.flags())
             fm.data(path=f)
             fm.plain(fmt % uipathfn(f))
             ret = 0
 
     for subpath in sorted(ctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         if subrepos or m.exact(subpath) or any(submatch.files()):
             sub = ctx.sub(subpath)
             try:
                 recurse = m.exact(subpath) or subrepos
                 if (
                     sub.printfiles(ui, submatch, subuipathfn, fm, fmt, recurse)
                     == 0
                 ):
                     ret = 0
             except error.LookupError:
                 ui.status(
                     _(b"skipping missing subrepository: %s\n")
                     % uipathfn(subpath)
                 )
 
     return ret
 
 
 def remove(
     ui, repo, m, prefix, uipathfn, after, force, subrepos, dryrun, warnings=None
 ):
     ret = 0
     s = repo.status(match=m, clean=True)
     modified, added, deleted, clean = s.modified, s.added, s.deleted, s.clean
 
     wctx = repo[None]
 
     if warnings is None:
         warnings = []
         warn = True
     else:
         warn = False
 
     subs = sorted(wctx.substate)
     progress = ui.makeprogress(
         _(b'searching'), total=len(subs), unit=_(b'subrepos')
     )
     for subpath in subs:
         submatch = matchmod.subdirmatcher(subpath, m)
         subprefix = repo.wvfs.reljoin(prefix, subpath)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         if subrepos or m.exact(subpath) or any(submatch.files()):
             progress.increment()
             sub = wctx.sub(subpath)
             try:
                 if sub.removefiles(
                     submatch,
                     subprefix,
                     subuipathfn,
                     after,
                     force,
                     subrepos,
                     dryrun,
                     warnings,
                 ):
                     ret = 1
             except error.LookupError:
                 warnings.append(
                     _(b"skipping missing subrepository: %s\n")
                     % uipathfn(subpath)
                 )
     progress.complete()
 
     # warn about failure to delete explicit files/dirs
     deleteddirs = pathutil.dirs(deleted)
     files = m.files()
     progress = ui.makeprogress(
         _(b'deleting'), total=len(files), unit=_(b'files')
     )
     for f in files:
 
         def insubrepo():
             for subpath in wctx.substate:
                 if f.startswith(subpath + b'/'):
                     return True
             return False
 
         progress.increment()
         isdir = f in deleteddirs or wctx.hasdir(f)
         if f in repo.dirstate or isdir or f == b'.' or insubrepo() or f in subs:
             continue
 
         if repo.wvfs.exists(f):
             if repo.wvfs.isdir(f):
                 warnings.append(
                     _(b'not removing %s: no tracked files\n') % uipathfn(f)
                 )
             else:
                 warnings.append(
                     _(b'not removing %s: file is untracked\n') % uipathfn(f)
                 )
         # missing files will generate a warning elsewhere
         ret = 1
     progress.complete()
 
     if force:
         list = modified + deleted + clean + added
     elif after:
         list = deleted
         remaining = modified + added + clean
         progress = ui.makeprogress(
             _(b'skipping'), total=len(remaining), unit=_(b'files')
         )
         for f in remaining:
             progress.increment()
             if ui.verbose or (f in files):
                 warnings.append(
                     _(b'not removing %s: file still exists\n') % uipathfn(f)
                 )
             ret = 1
         progress.complete()
     else:
         list = deleted + clean
         progress = ui.makeprogress(
             _(b'skipping'), total=(len(modified) + len(added)), unit=_(b'files')
         )
         for f in modified:
             progress.increment()
             warnings.append(
                 _(
                     b'not removing %s: file is modified (use -f'
                     b' to force removal)\n'
                 )
                 % uipathfn(f)
             )
             ret = 1
         for f in added:
             progress.increment()
             warnings.append(
                 _(
                     b"not removing %s: file has been marked for add"
                     b" (use 'hg forget' to undo add)\n"
                 )
                 % uipathfn(f)
             )
             ret = 1
         progress.complete()
 
     list = sorted(list)
     progress = ui.makeprogress(
         _(b'deleting'), total=len(list), unit=_(b'files')
     )
     for f in list:
         if ui.verbose or not m.exact(f):
             progress.increment()
             ui.status(
                 _(b'removing %s\n') % uipathfn(f), label=b'ui.addremove.removed'
             )
     progress.complete()
 
     if not dryrun:
         with repo.wlock():
             if not after:
                 for f in list:
                     if f in added:
                         continue  # we never unlink added files on remove
                     rmdir = repo.ui.configbool(
                         b'experimental', b'removeemptydirs'
                     )
                     repo.wvfs.unlinkpath(f, ignoremissing=True, rmdir=rmdir)
             repo[None].forget(list)
 
     if warn:
         for warning in warnings:
             ui.warn(warning)
 
     return ret
 
 
 def _catfmtneedsdata(fm):
     return not fm.datahint() or b'data' in fm.datahint()
 
 
 def _updatecatformatter(fm, ctx, matcher, path, decode):
     """Hook for adding data to the formatter used by ``hg cat``.
 
     Extensions (e.g., lfs) can wrap this to inject keywords/data, but must call
     this method first."""
 
     # data() can be expensive to fetch (e.g. lfs), so don't fetch it if it
     # wasn't requested.
     data = b''
     if _catfmtneedsdata(fm):
         data = ctx[path].data()
         if decode:
             data = ctx.repo().wwritedata(path, data)
     fm.startitem()
     fm.context(ctx=ctx)
     fm.write(b'data', b'%s', data)
     fm.data(path=path)
 
 
 def cat(ui, repo, ctx, matcher, basefm, fntemplate, prefix, **opts):
     err = 1
     opts = pycompat.byteskwargs(opts)
 
     def write(path):
         filename = None
         if fntemplate:
             filename = makefilename(
                 ctx, fntemplate, pathname=os.path.join(prefix, path)
             )
             # attempt to create the directory if it does not already exist
             try:
                 os.makedirs(os.path.dirname(filename))
             except OSError:
                 pass
         with formatter.maybereopen(basefm, filename) as fm:
             _updatecatformatter(fm, ctx, matcher, path, opts.get(b'decode'))
 
     # Automation often uses hg cat on single files, so special case it
     # for performance to avoid the cost of parsing the manifest.
     if len(matcher.files()) == 1 and not matcher.anypats():
         file = matcher.files()[0]
         mfl = repo.manifestlog
         mfnode = ctx.manifestnode()
         try:
             if mfnode and mfl[mfnode].find(file)[0]:
                 if _catfmtneedsdata(basefm):
                     scmutil.prefetchfiles(repo, [(ctx.rev(), matcher)])
                 write(file)
                 return 0
         except KeyError:
             pass
 
     if _catfmtneedsdata(basefm):
         scmutil.prefetchfiles(repo, [(ctx.rev(), matcher)])
 
     for abs in ctx.walk(matcher):
         write(abs)
         err = 0
 
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, matcher)
             subprefix = os.path.join(prefix, subpath)
             if not sub.cat(
                 submatch,
                 basefm,
                 fntemplate,
                 subprefix,
                 **pycompat.strkwargs(opts)
             ):
                 err = 0
         except error.RepoLookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     return err
 
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get(b'date')
     if date:
         opts[b'date'] = dateutil.parsedate(date)
     message = logmessage(ui, opts)
     matcher = scmutil.match(repo[None], pats, opts)
 
     dsguard = None
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get(b'addremove'):
         dsguard = dirstateguard.dirstateguard(repo, b'commit')
     with dsguard or util.nullcontextmanager():
         if dsguard:
             relative = scmutil.anypats(pats, opts)
             uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=relative)
             if scmutil.addremove(repo, matcher, b"", uipathfn, opts) != 0:
                 raise error.Abort(
                     _(b"failed to mark all new/missing files as added/removed")
                 )
 
         return commitfunc(ui, repo, message, matcher, opts)
 
 
 def samefile(f, ctx1, ctx2):
     if f in ctx1.manifest():
         a = ctx1.filectx(f)
         if f in ctx2.manifest():
             b = ctx2.filectx(f)
             return not a.cmp(b) and a.flags() == b.flags()
         else:
             return False
     else:
         return f not in ctx2.manifest()
 
 
 def amend(ui, repo, old, extra, pats, opts):
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     # amend will reuse the existing user if not specified, but the obsolete
     # marker creation requires that the current user's name is specified.
     if obsolete.isenabled(repo, obsolete.createmarkersopt):
         ui.username()  # raise exception if username not set
 
     ui.note(_(b'amending changeset %s\n') % old)
     base = old.p1()
 
     with repo.wlock(), repo.lock(), repo.transaction(b'amend'):
         # Participating changesets:
         #
         # wctx     o - workingctx that contains changes from working copy
         #          |   to go into amending commit
         #          |
         # old      o - changeset to amend
         #          |
         # base     o - first parent of the changeset to amend
         wctx = repo[None]
 
         # Copy to avoid mutating input
         extra = extra.copy()
         # Update extra dict from amended commit (e.g. to preserve graft
         # source)
         extra.update(old.extra())
 
         # Also update it from the from the wctx
         extra.update(wctx.extra())
 
         # date-only change should be ignored?
         datemaydiffer = resolvecommitoptions(ui, opts)
 
         date = old.date()
         if opts.get(b'date'):
             date = dateutil.parsedate(opts.get(b'date'))
         user = opts.get(b'user') or old.user()
 
         if len(old.parents()) > 1:
             # ctx.files() isn't reliable for merges, so fall back to the
             # slower repo.status() method
             st = base.status(old)
             files = set(st.modified) | set(st.added) | set(st.removed)
         else:
             files = set(old.files())
 
         # add/remove the files to the working copy if the "addremove" option
         # was specified.
         matcher = scmutil.match(wctx, pats, opts)
         relative = scmutil.anypats(pats, opts)
         uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=relative)
         if opts.get(b'addremove') and scmutil.addremove(
             repo, matcher, b"", uipathfn, opts
         ):
             raise error.Abort(
                 _(b"failed to mark all new/missing files as added/removed")
             )
 
         # Check subrepos. This depends on in-place wctx._status update in
         # subrepo.precommit(). To minimize the risk of this hack, we do
         # nothing if .hgsub does not exist.
         if b'.hgsub' in wctx or b'.hgsub' in old:
             subs, commitsubs, newsubstate = subrepoutil.precommit(
                 ui, wctx, wctx._status, matcher
             )
             # amend should abort if commitsubrepos is enabled
             assert not commitsubs
             if subs:
                 subrepoutil.writestate(repo, newsubstate)
 
         ms = mergestatemod.mergestate.read(repo)
         mergeutil.checkunresolved(ms)
 
         filestoamend = {f for f in wctx.files() if matcher(f)}
 
         changes = len(filestoamend) > 0
         if changes:
             # Recompute copies (avoid recording a -> b -> a)
             copied = copies.pathcopies(base, wctx, matcher)
             if old.p2:
                 copied.update(copies.pathcopies(old.p2(), wctx, matcher))
 
             # Prune files which were reverted by the updates: if old
             # introduced file X and the file was renamed in the working
             # copy, then those two files are the same and
             # we can discard X from our list of files. Likewise if X
             # was removed, it's no longer relevant. If X is missing (aka
             # deleted), old X must be preserved.
             files.update(filestoamend)
             files = [
                 f
                 for f in files
                 if (f not in filestoamend or not samefile(f, wctx, base))
             ]
 
             def filectxfn(repo, ctx_, path):
                 try:
                     # If the file being considered is not amongst the files
                     # to be amended, we should return the file context from the
                     # old changeset. This avoids issues when only some files in
                     # the working copy are being amended but there are also
                     # changes to other files from the old changeset.
                     if path not in filestoamend:
                         return old.filectx(path)
 
                     # Return None for removed files.
                     if path in wctx.removed():
                         return None
 
                     fctx = wctx[path]
                     flags = fctx.flags()
                     mctx = context.memfilectx(
                         repo,
                         ctx_,
                         fctx.path(),
                         fctx.data(),
                         islink=b'l' in flags,
                         isexec=b'x' in flags,
                         copysource=copied.get(path),
                     )
                     return mctx
                 except KeyError:
                     return None
 
         else:
             ui.note(_(b'copying changeset %s to %s\n') % (old, base))
 
             # Use version of files as in the old cset
             def filectxfn(repo, ctx_, path):
                 try:
                     return old.filectx(path)
                 except KeyError:
                     return None
 
         # See if we got a message from -m or -l, if not, open the editor with
         # the message of the changeset to amend.
         message = logmessage(ui, opts)
 
         editform = mergeeditform(old, b'commit.amend')
 
         if not message:
             message = old.description()
             # Default if message isn't provided and --edit is not passed is to
             # invoke editor, but allow --no-edit. If somehow we don't have any
             # description, let's always start the editor.
             doedit = not message or opts.get(b'edit') in [True, None]
         else:
             # Default if message is provided is to not invoke editor, but allow
             # --edit.
             doedit = opts.get(b'edit') is True
         editor = getcommiteditor(edit=doedit, editform=editform)
 
         pureextra = extra.copy()
         extra[b'amend_source'] = old.hex()
 
         new = context.memctx(
             repo,
             parents=[base.node(), old.p2().node()],
             text=message,
             files=files,
             filectxfn=filectxfn,
             user=user,
             date=date,
             extra=extra,
             editor=editor,
         )
 
         newdesc = changelog.stripdesc(new.description())
         if (
             (not changes)
             and newdesc == old.description()
             and user == old.user()
             and (date == old.date() or datemaydiffer)
             and pureextra == old.extra()
         ):
             # nothing changed. continuing here would create a new node
             # anyway because of the amend_source noise.
             #
             # This not what we expect from amend.
             return old.node()
 
         commitphase = None
         if opts.get(b'secret'):
             commitphase = phases.secret
         newid = repo.commitctx(new)
         ms.reset()
 
         # Reroute the working copy parent to the new changeset
         repo.setparents(newid, repo.nullid)
 
         # Fixing the dirstate because localrepo.commitctx does not update
         # it. This is rather convenient because we did not need to update
         # the dirstate for all the files in the new commit which commitctx
         # could have done if it updated the dirstate. Now, we can
         # selectively update the dirstate only for the amended files.
         dirstate = repo.dirstate
 
         # Update the state of the files which were added and modified in the
         # amend to "normal" in the dirstate. We need to use "normallookup" since
         # the files may have changed since the command started; using "normal"
         # would mark them as clean but with uncommitted contents.
         normalfiles = set(wctx.modified() + wctx.added()) & filestoamend
         for f in normalfiles:
             dirstate.normallookup(f)
 
         # Update the state of files which were removed in the amend
         # to "removed" in the dirstate.
         removedfiles = set(wctx.removed()) & filestoamend
         for f in removedfiles:
             dirstate.drop(f)
 
         mapping = {old.node(): (newid,)}
         obsmetadata = None
         if opts.get(b'note'):
             obsmetadata = {b'note': encoding.fromlocal(opts[b'note'])}
         backup = ui.configbool(b'rewrite', b'backup-bundle')
         scmutil.cleanupnodes(
             repo,
             mapping,
             b'amend',
             metadata=obsmetadata,
             fixphase=True,
             targetphase=commitphase,
             backup=backup,
         )
 
     return newid
 
 
 def commiteditor(repo, ctx, subs, editform=b''):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(
         repo, ctx, subs, editform=editform, unchangedmessagedetection=True
     )
 
 
 def commitforceeditor(
     repo,
     ctx,
     subs,
     finishdesc=None,
     extramsg=None,
     editform=b'',
     unchangedmessagedetection=False,
 ):
     if not extramsg:
         extramsg = _(b"Leave message empty to abort commit.")
 
     forms = [e for e in editform.split(b'.') if e]
     forms.insert(0, b'changeset')
     templatetext = None
     while forms:
         ref = b'.'.join(forms)
         if repo.ui.config(b'committemplate', ref):
             templatetext = committext = buildcommittemplate(
                 repo, ctx, subs, extramsg, ref
             )
             break
         forms.pop()
     else:
         committext = buildcommittext(repo, ctx, subs, extramsg)
 
     # run editor in the repository root
     olddir = encoding.getcwd()
     os.chdir(repo.root)
 
     # make in-memory changes visible to external process
     tr = repo.currenttransaction()
     repo.dirstate.write(tr)
     pending = tr and tr.writepending() and repo.root
 
     editortext = repo.ui.edit(
         committext,
         ctx.user(),
         ctx.extra(),
         editform=editform,
         pending=pending,
         repopath=repo.path,
         action=b'commit',
     )
     text = editortext
 
     # strip away anything below this special string (used for editors that want
     # to display the diff)
     stripbelow = re.search(_linebelow, text, flags=re.MULTILINE)
     if stripbelow:
         text = text[: stripbelow.start()]
 
     text = re.sub(b"(?m)^HG:.*(\n|$)", b"", text)
     os.chdir(olddir)
 
     if finishdesc:
         text = finishdesc(text)
     if not text.strip():
         raise error.InputError(_(b"empty commit message"))
     if unchangedmessagedetection and editortext == templatetext:
         raise error.InputError(_(b"commit message unchanged"))
 
     return text
 
 
 def buildcommittemplate(repo, ctx, subs, extramsg, ref):
     ui = repo.ui
     spec = formatter.reference_templatespec(ref)
     t = logcmdutil.changesettemplater(ui, repo, spec)
     t.t.cache.update(
         (k, templater.unquotestring(v))
         for k, v in repo.ui.configitems(b'committemplate')
     )
 
     if not extramsg:
         extramsg = b''  # ensure that extramsg is string
 
     ui.pushbuffer()
     t.show(ctx, extramsg=extramsg)
     return ui.popbuffer()
 
 
 def hgprefix(msg):
     return b"\n".join([b"HG: %s" % a for a in msg.split(b"\n") if a])
 
 
 def buildcommittext(repo, ctx, subs, extramsg):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append(b"")
     edittext.append(b"")  # Empty line between message and comments.
     edittext.append(
         hgprefix(
             _(
                 b"Enter commit message."
                 b"  Lines beginning with 'HG:' are removed."
             )
         )
     )
     edittext.append(hgprefix(extramsg))
     edittext.append(b"HG: --")
     edittext.append(hgprefix(_(b"user: %s") % ctx.user()))
     if ctx.p2():
         edittext.append(hgprefix(_(b"branch merge")))
     if ctx.branch():
         edittext.append(hgprefix(_(b"branch '%s'") % ctx.branch()))
     if bookmarks.isactivewdirparent(repo):
         edittext.append(hgprefix(_(b"bookmark '%s'") % repo._activebookmark))
     edittext.extend([hgprefix(_(b"subrepo %s") % s) for s in subs])
     edittext.extend([hgprefix(_(b"added %s") % f) for f in added])
     edittext.extend([hgprefix(_(b"changed %s") % f) for f in modified])
     edittext.extend([hgprefix(_(b"removed %s") % f) for f in removed])
     if not added and not modified and not removed:
         edittext.append(hgprefix(_(b"no files changed")))
     edittext.append(b"")
 
     return b"\n".join(edittext)
 
 
 def commitstatus(repo, node, branch, bheads=None, tip=None, opts=None):
     if opts is None:
         opts = {}
     ctx = repo[node]
     parents = ctx.parents()
 
     if tip is not None and repo.changelog.tip() == tip:
         # avoid reporting something like "committed new head" when
         # recommitting old changesets, and issue a helpful warning
         # for most instances
         repo.ui.warn(_(b"warning: commit already existed in the repository!\n"))
     elif (
         not opts.get(b'amend')
         and bheads
         and node not in bheads
         and not any(
             p.node() in bheads and p.branch() == branch for p in parents
         )
     ):
         repo.ui.status(_(b'created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get(b'close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(
                     _(b'reopening closed branch head %d\n') % r.rev()
                 )
 
     if repo.ui.debugflag:
         repo.ui.write(
             _(b'committed changeset %d:%s\n') % (ctx.rev(), ctx.hex())
         )
     elif repo.ui.verbose:
         repo.ui.write(_(b'committed changeset %d:%s\n') % (ctx.rev(), ctx))
 
 
 def postcommitstatus(repo, pats, opts):
     return repo.status(match=scmutil.match(repo[None], pats, opts))
 
 
 def revert(ui, repo, ctx, *pats, **opts):
     opts = pycompat.byteskwargs(opts)
     parent, p2 = repo.dirstate.parents()
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == p2:
         parent = p2
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other. in both cases, filesets should be evaluated against
     # workingctx to get consistent result (issue4497). this means 'set:**'
     # cannot be used to select missing files from target rev.
 
     # `names` is a mapping for all elements in working copy and target revision
     # The mapping is in the form:
     #   <abs path in repo> -> (<path from CWD>, <exactly specified by matcher?>)
     names = {}
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
 
     with repo.wlock():
         ## filling of the `names` mapping
         # walk dirstate to fill `names`
 
         interactive = opts.get(b'interactive', False)
         wctx = repo[None]
         m = scmutil.match(wctx, pats, opts)
 
         # we'll need this later
         targetsubs = sorted(s for s in wctx.substate if m(s))
 
         if not m.always():
             matcher = matchmod.badmatch(m, lambda x, y: False)
             for abs in wctx.walk(matcher):
                 names[abs] = m.exact(abs)
 
             # walk target manifest to fill `names`
 
             def badfn(path, msg):
                 if path in names:
                     return
                 if path in ctx.substate:
                     return
                 path_ = path + b'/'
                 for f in names:
                     if f.startswith(path_):
                         return
                 ui.warn(b"%s: %s\n" % (uipathfn(path), msg))
 
             for abs in ctx.walk(matchmod.badmatch(m, badfn)):
                 if abs not in names:
                     names[abs] = m.exact(abs)
 
             # Find status of all file in `names`.
             m = scmutil.matchfiles(repo, names)
 
             changes = repo.status(
                 node1=node, match=m, unknown=True, ignored=True, clean=True
             )
         else:
             changes = repo.status(node1=node, match=m)
             for kind in changes:
                 for abs in kind:
                     names[abs] = m.exact(abs)
 
             m = scmutil.matchfiles(repo, names)
 
         modified = set(changes.modified)
         added = set(changes.added)
         removed = set(changes.removed)
         _deleted = set(changes.deleted)
         unknown = set(changes.unknown)
         unknown.update(changes.ignored)
         clean = set(changes.clean)
         modadded = set()
 
         # We need to account for the state of the file in the dirstate,
         # even when we revert against something else than parent. This will
         # slightly alter the behavior of revert (doing back up or not, delete
         # or just forget etc).
         if parent == node:
             dsmodified = modified
             dsadded = added
             dsremoved = removed
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
             modified, added, removed = set(), set(), set()
         else:
             changes = repo.status(node1=parent, match=m)
             dsmodified = set(changes.modified)
             dsadded = set(changes.added)
             dsremoved = set(changes.removed)
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
 
             # only take into account for removes between wc and target
             clean |= dsremoved - removed
             dsremoved &= removed
             # distinct between dirstate remove and other
             removed -= dsremoved
 
             modadded = added & dsmodified
             added -= modadded
 
             # tell newly modified apart.
             dsmodified &= modified
             dsmodified |= modified & dsadded  # dirstate added may need backup
             modified -= dsmodified
 
             # We need to wait for some post-processing to update this set
             # before making the distinction. The dirstate will be used for
             # that purpose.
             dsadded = added
 
         # in case of merge, files that are actually added can be reported as
         # modified, we need to post process the result
         if p2 != repo.nullid:
             mergeadd = set(dsmodified)
             for path in dsmodified:
                 if path in mf:
                     mergeadd.remove(path)
             dsadded |= mergeadd
             dsmodified -= mergeadd
 
         # if f is a rename, update `names` to also revert the source
         for f in localchanges:
             src = repo.dirstate.copied(f)
             # XXX should we check for rename down to target node?
             if src and src not in names and repo.dirstate[src] == b'r':
                 dsremoved.add(src)
                 names[src] = True
 
         # determine the exact nature of the deleted changesets
         deladded = set(_deleted)
         for path in _deleted:
             if path in mf:
                 deladded.remove(path)
         deleted = _deleted - deladded
 
         # distinguish between file to forget and the other
         added = set()
         for abs in dsadded:
             if repo.dirstate[abs] != b'a':
                 added.add(abs)
         dsadded -= added
 
         for abs in deladded:
             if repo.dirstate[abs] == b'a':
                 dsadded.add(abs)
         deladded -= dsadded
 
         # For files marked as removed, we check if an unknown file is present at
         # the same path. If a such file exists it may need to be backed up.
         # Making the distinction at this stage helps have simpler backup
         # logic.
         removunk = set()
         for abs in removed:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 removunk.add(abs)
         removed -= removunk
 
         dsremovunk = set()
         for abs in dsremoved:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 dsremovunk.add(abs)
         dsremoved -= dsremovunk
 
         # action to be actually performed by revert
         # (<list of file>, message>) tuple
         actions = {
             b'revert': ([], _(b'reverting %s\n')),
             b'add': ([], _(b'adding %s\n')),
             b'remove': ([], _(b'removing %s\n')),
             b'drop': ([], _(b'removing %s\n')),
             b'forget': ([], _(b'forgetting %s\n')),
             b'undelete': ([], _(b'undeleting %s\n')),
             b'noop': (None, _(b'no changes needed to %s\n')),
             b'unknown': (None, _(b'file not managed: %s\n')),
         }
 
         # "constant" that convey the backup strategy.
         # All set to `discard` if `no-backup` is set do avoid checking
         # no_backup lower in the code.
         # These values are ordered for comparison purposes
         backupinteractive = 3  # do backup if interactively modified
         backup = 2  # unconditionally do backup
         check = 1  # check if the existing file differs from target
         discard = 0  # never do backup
         if opts.get(b'no_backup'):
             backupinteractive = backup = check = discard
         if interactive:
             dsmodifiedbackup = backupinteractive
         else:
             dsmodifiedbackup = backup
         tobackup = set()
 
         backupanddel = actions[b'remove']
         if not opts.get(b'no_backup'):
             backupanddel = actions[b'drop']
 
         disptable = (
             # dispatch table:
             #   file state
             #   action
             #   make backup
             ## Sets that results that will change file on disk
             # Modified compared to target, no local change
             (modified, actions[b'revert'], discard),
             # Modified compared to target, but local file is deleted
             (deleted, actions[b'revert'], discard),
             # Modified compared to target, local change
             (dsmodified, actions[b'revert'], dsmodifiedbackup),
             # Added since target
             (added, actions[b'remove'], discard),
             # Added in working directory
             (dsadded, actions[b'forget'], discard),
             # Added since target, have local modification
             (modadded, backupanddel, backup),
             # Added since target but file is missing in working directory
             (deladded, actions[b'drop'], discard),
             # Removed since  target, before working copy parent
             (removed, actions[b'add'], discard),
             # Same as `removed` but an unknown file exists at the same path
             (removunk, actions[b'add'], check),
             # Removed since targe, marked as such in working copy parent
             (dsremoved, actions[b'undelete'], discard),
             # Same as `dsremoved` but an unknown file exists at the same path
             (dsremovunk, actions[b'undelete'], check),
             ## the following sets does not result in any file changes
             # File with no modification
             (clean, actions[b'noop'], discard),
             # Existing file, not tracked anywhere
             (unknown, actions[b'unknown'], discard),
         )
 
         for abs, exact in sorted(names.items()):
             # target file to be touch on disk (relative to cwd)
             target = repo.wjoin(abs)
             # search the entry in the dispatch table.
             # if the file is in any of these sets, it was touched in the working
             # directory parent and we are sure it needs to be reverted.
             for table, (xlist, msg), dobackup in disptable:
                 if abs not in table:
                     continue
                 if xlist is not None:
                     xlist.append(abs)
                     if dobackup:
                         # If in interactive mode, don't automatically create
                         # .orig files (issue4793)
                         if dobackup == backupinteractive:
                             tobackup.add(abs)
                         elif backup <= dobackup or wctx[abs].cmp(ctx[abs]):
                             absbakname = scmutil.backuppath(ui, repo, abs)
                             bakname = os.path.relpath(
                                 absbakname, start=repo.root
                             )
                             ui.note(
                                 _(b'saving current version of %s as %s\n')
                                 % (uipathfn(abs), uipathfn(bakname))
                             )
                             if not opts.get(b'dry_run'):
                                 if interactive:
                                     util.copyfile(target, absbakname)
                                 else:
                                     util.rename(target, absbakname)
                     if opts.get(b'dry_run'):
                         if ui.verbose or not exact:
                             ui.status(msg % uipathfn(abs))
                 elif exact:
                     ui.warn(msg % uipathfn(abs))
                 break
 
         if not opts.get(b'dry_run'):
             needdata = (b'revert', b'add', b'undelete')
             oplist = [actions[name][0] for name in needdata]
             prefetch = scmutil.prefetchfiles
             matchfiles = scmutil.matchfiles(
                 repo, [f for sublist in oplist for f in sublist]
             )
             prefetch(
                 repo,
                 [(ctx.rev(), matchfiles)],
             )
             match = scmutil.match(repo[None], pats)
             _performrevert(
                 repo,
                 ctx,
                 names,
                 uipathfn,
                 actions,
                 match,
                 interactive,
                 tobackup,
             )
 
         if targetsubs:
             # Revert the subrepos on the revert list
             for sub in targetsubs:
                 try:
                     wctx.sub(sub).revert(
                         ctx.substate[sub], *pats, **pycompat.strkwargs(opts)
                     )
                 except KeyError:
                     raise error.Abort(
                         b"subrepository '%s' does not exist in %s!"
                         % (sub, short(ctx.node()))
                     )
 
 
 def _performrevert(
     repo,
     ctx,
     names,
     uipathfn,
     actions,
     match,
     interactive=False,
     tobackup=None,
 ):
     """function that actually perform all the actions computed for revert
 
     This is an independent function to let extension to plug in and react to
     the imminent revert.
 
     Make sure you have the working directory locked when calling this function.
     """
     parent, p2 = repo.dirstate.parents()
     node = ctx.node()
     excluded_files = []
 
     def checkout(f):
         fc = ctx[f]
         repo.wwrite(f, fc.data(), fc.flags())
 
     def doremove(f):
         try:
             rmdir = repo.ui.configbool(b'experimental', b'removeemptydirs')
             repo.wvfs.unlinkpath(f, rmdir=rmdir)
         except OSError:
             pass
         repo.dirstate.remove(f)
 
     def prntstatusmsg(action, f):
         exact = names[f]
         if repo.ui.verbose or not exact:
             repo.ui.status(actions[action][1] % uipathfn(f))
 
     audit_path = pathutil.pathauditor(repo.root, cached=True)
     for f in actions[b'forget'][0]:
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"forget added file %s (Yn)?$$ &Yes $$ &No") % uipathfn(f)
             )
             if choice == 0:
                 prntstatusmsg(b'forget', f)
                 repo.dirstate.drop(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'forget', f)
             repo.dirstate.drop(f)
     for f in actions[b'remove'][0]:
         audit_path(f)
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"remove added file %s (Yn)?$$ &Yes $$ &No") % uipathfn(f)
             )
             if choice == 0:
                 prntstatusmsg(b'remove', f)
                 doremove(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'remove', f)
             doremove(f)
     for f in actions[b'drop'][0]:
         audit_path(f)
         prntstatusmsg(b'drop', f)
         repo.dirstate.remove(f)
 
     normal = None
     if node == parent:
         # We're reverting to our parent. If possible, we'd like status
         # to report the file as clean. We have to use normallookup for
         # merges to avoid losing information about merged/dirty files.
         if p2 != repo.nullid:
             normal = repo.dirstate.normallookup
         else:
             normal = repo.dirstate.normal
 
     newlyaddedandmodifiedfiles = set()
     if interactive:
         # Prompt the user for changes to revert
         torevert = [f for f in actions[b'revert'][0] if f not in excluded_files]
         m = scmutil.matchfiles(repo, torevert)
         diffopts = patch.difffeatureopts(
             repo.ui,
             whitespace=True,
             section=b'commands',
             configprefix=b'revert.interactive.',
         )
         diffopts.nodates = True
         diffopts.git = True
         operation = b'apply'
         if node == parent:
             if repo.ui.configbool(
                 b'experimental', b'revert.interactive.select-to-keep'
             ):
                 operation = b'keep'
             else:
                 operation = b'discard'
 
         if operation == b'apply':
             diff = patch.diff(repo, None, ctx.node(), m, opts=diffopts)
         else:
             diff = patch.diff(repo, ctx.node(), None, m, opts=diffopts)
         originalchunks = patch.parsepatch(diff)
 
         try:
 
             chunks, opts = recordfilter(
                 repo.ui, originalchunks, match, operation=operation
             )
             if operation == b'discard':
                 chunks = patch.reversehunks(chunks)
 
         except error.PatchError as err:
             raise error.Abort(_(b'error parsing patch: %s') % err)
 
         # FIXME: when doing an interactive revert of a copy, there's no way of
         # performing a partial revert of the added file, the only option is
         # "remove added file <name> (Yn)?", so we don't need to worry about the
         # alsorestore value. Ideally we'd be able to partially revert
         # copied/renamed files.
         newlyaddedandmodifiedfiles, unusedalsorestore = newandmodified(
             chunks, originalchunks
         )
         if tobackup is None:
             tobackup = set()
         # Apply changes
         fp = stringio()
         # chunks are serialized per file, but files aren't sorted
         for f in sorted({c.header.filename() for c in chunks if ishunk(c)}):
             prntstatusmsg(b'revert', f)
         files = set()
         for c in chunks:
             if ishunk(c):
                 abs = c.header.filename()
                 # Create a backup file only if this hunk should be backed up
                 if c.header.filename() in tobackup:
                     target = repo.wjoin(abs)
                     bakname = scmutil.backuppath(repo.ui, repo, abs)
                     util.copyfile(target, bakname)
                     tobackup.remove(abs)
                 if abs not in files:
                     files.add(abs)
                     if operation == b'keep':
                         checkout(abs)
             c.write(fp)
         dopatch = fp.tell()
         fp.seek(0)
         if dopatch:
             try:
                 patch.internalpatch(repo.ui, repo, fp, 1, eolmode=None)
             except error.PatchError as err:
                 raise error.Abort(pycompat.bytestr(err))
         del fp
     else:
         for f in actions[b'revert'][0]:
             prntstatusmsg(b'revert', f)
             checkout(f)
             if normal:
                 normal(f)
 
     for f in actions[b'add'][0]:
         # Don't checkout modified files, they are already created by the diff
         if f not in newlyaddedandmodifiedfiles:
             prntstatusmsg(b'add', f)
             checkout(f)
             repo.dirstate.add(f)
 
     normal = repo.dirstate.normallookup
     if node == parent and p2 == repo.nullid:
         normal = repo.dirstate.normal
     for f in actions[b'undelete'][0]:
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"add back removed file %s (Yn)?$$ &Yes $$ &No") % f
             )
             if choice == 0:
                 prntstatusmsg(b'undelete', f)
                 checkout(f)
                 normal(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'undelete', f)
             checkout(f)
             normal(f)
 
     copied = copies.pathcopies(repo[parent], ctx)
 
     for f in (
         actions[b'add'][0] + actions[b'undelete'][0] + actions[b'revert'][0]
     ):
         if f in copied:
             repo.dirstate.copy(copied[f], f)
 
 
 # a list of (ui, repo, otherpeer, opts, missing) functions called by
 # commands.outgoing.  "missing" is "missing" of the result of
 # "findcommonoutgoing()"
 outgoinghooks = util.hooks()
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # a list of (ui, repo, opts, changes) functions called by commands.summary.
 #
 # functions should return tuple of booleans below, if 'changes' is None:
 #  (whether-incomings-are-needed, whether-outgoings-are-needed)
 #
 # otherwise, 'changes' is a tuple of tuples below:
 #  - (sourceurl, sourcebranch, sourcepeer, incoming)
 #  - (desturl,   destbranch,   destpeer,   outgoing)
 summaryremotehooks = util.hooks()
 
 
 def checkunfinished(repo, commit=False, skipmerge=False):
     """Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     """
     # Check for non-clearable states first, so things like rebase will take
     # precedence over update.
     for state in statemod._unfinishedstates:
         if (
             state._clearable
             or (commit and state._allowcommit)
             or state._reportonly
         ):
             continue
         if state.isunfinished(repo):
             raise error.StateError(state.msg(), hint=state.hint())
 
     for s in statemod._unfinishedstates:
         if (
             not s._clearable
             or (commit and s._allowcommit)
             or (s._opname == b'merge' and skipmerge)
             or s._reportonly
         ):
             continue
         if s.isunfinished(repo):
             raise error.StateError(s.msg(), hint=s.hint())
 
 
 def clearunfinished(repo):
     """Check for unfinished operations (as above), and clear the ones
     that are clearable.
     """
     for state in statemod._unfinishedstates:
         if state._reportonly:
             continue
         if not state._clearable and state.isunfinished(repo):
             raise error.StateError(state.msg(), hint=state.hint())
 
     for s in statemod._unfinishedstates:
         if s._opname == b'merge' or s._reportonly:
             continue
         if s._clearable and s.isunfinished(repo):
             util.unlink(repo.vfs.join(s._fname))
 
 
 def getunfinishedstate(repo):
     """Checks for unfinished operations and returns statecheck object
     for it"""
     for state in statemod._unfinishedstates:
         if state.isunfinished(repo):
             return state
     return None
 
 
 def howtocontinue(repo):
     """Check for an unfinished operation and return the command to finish
     it.
 
     statemod._unfinishedstates list is checked for an unfinished operation
     and the corresponding message to finish it is generated if a method to
     continue is supported by the operation.
 
     Returns a (msg, warning) tuple. 'msg' is a string and 'warning' is
     a boolean.
     """
     contmsg = _(b"continue: %s")
     for state in statemod._unfinishedstates:
         if not state._continueflag:
             continue
         if state.isunfinished(repo):
             return contmsg % state.continuemsg(), True
     if repo[None].dirty(missing=True, merge=False, branch=False):
         return contmsg % _(b"hg commit"), False
     return None, None
 
 
 def checkafterresolved(repo):
     """Inform the user about the next action after completing hg resolve
 
     If there's a an unfinished operation that supports continue flag,
     howtocontinue will yield repo.ui.warn as the reporter.
 
     Otherwise, it will yield repo.ui.note.
     """
     msg, warning = howtocontinue(repo)
     if msg is not None:
         if warning:
             repo.ui.warn(b"%s\n" % msg)
         else:
             repo.ui.note(b"%s\n" % msg)
 
 
 def wrongtooltocontinue(repo, task):
     """Raise an abort suggesting how to properly continue if there is an
     active task.
 
     Uses howtocontinue() to find the active task.
 
     If there's no task (repo.ui.note for 'hg commit'), it does not offer
     a hint.
     """
     after = howtocontinue(repo)
     hint = None
     if after[1]:
         hint = after[0]
     raise error.StateError(_(b'no %s in progress') % task, hint=hint)
 
 
 def abortgraft(ui, repo, graftstate):
     """abort the interrupted graft and rollbacks to the state before interrupted
     graft"""
     if not graftstate.exists():
         raise error.StateError(_(b"no interrupted graft to abort"))
     statedata = readgraftstate(repo, graftstate)
     newnodes = statedata.get(b'newnodes')
     if newnodes is None:
         # and old graft state which does not have all the data required to abort
         # the graft
         raise error.Abort(_(b"cannot abort using an old graftstate"))
 
     # changeset from which graft operation was started
     if len(newnodes) > 0:
         startctx = repo[newnodes[0]].p1()
     else:
         startctx = repo[b'.']
     # whether to strip or not
     cleanup = False
 
     if newnodes:
         newnodes = [repo[r].rev() for r in newnodes]
         cleanup = True
         # checking that none of the newnodes turned public or is public
         immutable = [c for c in newnodes if not repo[c].mutable()]
         if immutable:
             repo.ui.warn(
                 _(b"cannot clean up public changesets %s\n")
                 % b', '.join(bytes(repo[r]) for r in immutable),
                 hint=_(b"see 'hg help phases' for details"),
             )
             cleanup = False
 
         # checking that no new nodes are created on top of grafted revs
         desc = set(repo.changelog.descendants(newnodes))
         if desc - set(newnodes):
             repo.ui.warn(
                 _(
                     b"new changesets detected on destination "
                     b"branch, can't strip\n"
                 )
             )
             cleanup = False
 
         if cleanup:
             with repo.wlock(), repo.lock():
                 mergemod.clean_update(startctx)
                 # stripping the new nodes created
                 strippoints = [
                     c.node() for c in repo.set(b"roots(%ld)", newnodes)
                 ]
                 repair.strip(repo.ui, repo, strippoints, backup=False)
 
     if not cleanup:
         # we don't update to the startnode if we can't strip
         startctx = repo[b'.']
         mergemod.clean_update(startctx)
 
     ui.status(_(b"graft aborted\n"))
     ui.status(_(b"working directory is now at %s\n") % startctx.hex()[:12])
     graftstate.delete()
     return 0
 
 
 def readgraftstate(repo, graftstate):
     # type: (Any, statemod.cmdstate) -> Dict[bytes, Any]
     """read the graft state file and return a dict of the data stored in it"""
     try:
         return graftstate.read()
     except error.CorruptedState:
         nodes = repo.vfs.read(b'graftstate').splitlines()
         return {b'nodes': nodes}
 
 
 def hgabortgraft(ui, repo):
     """ abort logic for aborting graft using 'hg abort'"""
     with repo.wlock():
         graftstate = statemod.cmdstate(repo, b'graftstate')
         return abortgraft(ui, repo, graftstate)

mercurial/filelog.py

@@ -1,292 +1,299 b''
 # filelog.py - file history class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from .i18n import _
 from .node import nullrev
 from . import (
     error,
     revlog,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .utils import storageutil
+from .revlogutils import (
+    constants as revlog_constants,
+)
 
 
 @interfaceutil.implementer(repository.ifilestorage)
 class filelog(object):
     def __init__(self, opener, path):
         self._revlog = revlog.revlog(
-            opener, b'/'.join((b'data', path + b'.i')), censorable=True
+            opener,
+            # XXX should use the unencoded path
+            target=(revlog_constants.KIND_FILELOG, path),
+            indexfile=b'/'.join((b'data', path + b'.i')),
+            censorable=True,
         )
         # Full name of the user visible file, relative to the repository root.
         # Used by LFS.
         self._revlog.filename = path
         self._revlog.revlog_kind = b'filelog'
         self.nullid = self._revlog.nullid
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def hasnode(self, node):
         if node in (self.nullid, nullrev):
             return False
 
         try:
             self._revlog.rev(node)
             return True
         except (TypeError, ValueError, IndexError, error.LookupError):
             return False
 
     def revs(self, start=0, stop=None):
         return self._revlog.revs(start=start, stop=stop)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, node):
         return storageutil.fileidlookup(
             self._revlog, node, self._revlog.indexfile
         )
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def commonancestorsheads(self, node1, node2):
         return self._revlog.commonancestorsheads(node1, node2)
 
     # Used by dagop.blockdescendants().
     def descendants(self, revs):
         return self._revlog.descendants(revs)
 
     def heads(self, start=None, stop=None):
         return self._revlog.heads(start, stop)
 
     # Used by hgweb, children extension.
     def children(self, node):
         return self._revlog.children(node)
 
     def iscensored(self, rev):
         return self._revlog.iscensored(rev)
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
             sidedata_helpers=sidedata_helpers,
         )
 
     def addrevision(
         self,
         revisiondata,
         transaction,
         linkrev,
         p1,
         p2,
         node=None,
         flags=revlog.REVIDX_DEFAULT_FLAGS,
         cachedelta=None,
     ):
         return self._revlog.addrevision(
             revisiondata,
             transaction,
             linkrev,
             p1,
             p2,
             node=node,
             flags=flags,
             cachedelta=cachedelta,
         )
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         maybemissingparents=False,
     ):
         if maybemissingparents:
             raise error.Abort(
                 _(
                     b'revlog storage does not support missing '
                     b'parents write mode'
                 )
             )
 
         return self._revlog.addgroup(
             deltas,
             linkmapper,
             transaction,
             addrevisioncb=addrevisioncb,
             duplicaterevisioncb=duplicaterevisioncb,
         )
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def censorrevision(self, tr, node, tombstone=b''):
         return self._revlog.censorrevision(tr, node, tombstone=tombstone)
 
     def files(self):
         return self._revlog.files()
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith(b'\1\n'):
             text = storageutil.packmeta(meta, text)
         rev = self.addrevision(text, transaction, link, p1, p2)
         return self.node(rev)
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
         if self.iscensored(rev):
             return 0
 
         # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
         return self._revlog.size(rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         return not storageutil.filedataequivalent(self, node, text)
 
     def verifyintegrity(self, state):
         return self._revlog.verifyintegrity(state)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     # TODO these aren't part of the interface and aren't internal methods.
     # Callers should be fixed to not use them.
 
     # Used by bundlefilelog, unionfilelog.
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     # Used by repo upgrade.
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, filelog):
             raise error.ProgrammingError(b'expected filelog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
 
 class narrowfilelog(filelog):
     """Filelog variation to be used with narrow stores."""
 
     def __init__(self, opener, path, narrowmatch):
         super(narrowfilelog, self).__init__(opener, path)
         self._narrowmatch = narrowmatch
 
     def renamed(self, node):
         res = super(narrowfilelog, self).renamed(node)
 
         # Renames that come from outside the narrowspec are problematic
         # because we may lack the base text for the rename. This can result
         # in code attempting to walk the ancestry or compute a diff
         # encountering a missing revision. We address this by silently
         # removing rename metadata if the source file is outside the
         # narrow spec.
         #
         # A better solution would be to see if the base revision is available,
         # rather than assuming it isn't.
         #
         # An even better solution would be to teach all consumers of rename
         # metadata that the base revision may not be available.
         #
         # TODO consider better ways of doing this.
         if res and not self._narrowmatch(res[0]):
             return None
 
         return res
 
     def size(self, rev):
         # Because we have a custom renamed() that may lie, we need to call
         # the base renamed() to report accurate results.
         node = self.node(rev)
         if super(narrowfilelog, self).renamed(node):
             return len(self.read(node))
         else:
             return super(narrowfilelog, self).size(rev)
 
     def cmp(self, node, text):
         # We don't call `super` because narrow parents can be buggy in case of a
         # ambiguous dirstate. Always take the slow path until there is a better
         # fix, see issue6150.
 
         # Censored files compare against the empty file.
         if self.iscensored(self.rev(node)):
             return text != b''
 
         return self.read(node) != text

mercurial/manifest.py

@@ -1,2382 +1,2386 b''
 # manifest.py - manifest revision class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import heapq
 import itertools
 import struct
 import weakref
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullrev,
 )
 from .pycompat import getattr
 from . import (
     encoding,
     error,
     match as matchmod,
     mdiff,
     pathutil,
     policy,
     pycompat,
     revlog,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
+from .revlogutils import (
+    constants as revlog_constants,
+)
 
 parsers = policy.importmod('parsers')
 propertycache = util.propertycache
 
 # Allow tests to more easily test the alternate path in manifestdict.fastdelta()
 FASTDELTA_TEXTDIFF_THRESHOLD = 1000
 
 
 def _parse(nodelen, data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1:] != b'\n':
         raise ValueError(b'Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError(b'Manifest lines not in sorted order.')
         prev = l
         f, n = l.split(b'\0')
         nl = len(n)
         flags = n[-1:]
         if flags in _manifestflags:
             n = n[:-1]
             nl -= 1
         else:
             flags = b''
         if nl != 2 * nodelen:
             raise ValueError(b'Invalid manifest line')
 
         yield f, bin(n), flags
 
 
 def _text(it):
     files = []
     lines = []
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append(b"%s\0%s%s\n" % (f, hex(n), fl))
 
     _checkforbidden(files)
     return b''.join(lines)
 
 
 class lazymanifestiter(object):
     def __init__(self, lm):
         self.pos = 0
         self.lm = lm
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data[0]
         self.pos += 1
         zeropos = data.find(b'\x00', pos)
         return data[pos:zeropos]
 
     __next__ = next
 
 
 class lazymanifestiterentries(object):
     def __init__(self, lm):
         self.lm = lm
         self.pos = 0
 
     def __iter__(self):
         return self
 
     def next(self):
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             self.pos += 1
             return data
         zeropos = data.find(b'\x00', pos)
         nlpos = data.find(b'\n', pos)
         if zeropos == -1 or nlpos == -1 or nlpos < zeropos:
             raise error.StorageError(b'Invalid manifest line')
         flags = data[nlpos - 1 : nlpos]
         if flags in _manifestflags:
             hlen = nlpos - zeropos - 2
         else:
             hlen = nlpos - zeropos - 1
             flags = b''
         if hlen != 2 * self.lm._nodelen:
             raise error.StorageError(b'Invalid manifest line')
         hashval = unhexlify(
             data, self.lm.extrainfo[self.pos], zeropos + 1, hlen
         )
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
     __next__ = next
 
 
 def unhexlify(data, extra, pos, length):
     s = bin(data[pos : pos + length])
     if extra:
         s += chr(extra & 0xFF)
     return s
 
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 
 _manifestflags = {b'', b'l', b't', b'x'}
 
 
 class _lazymanifest(object):
     """A pure python manifest backed by a byte string.  It is supplimented with
     internal lists as it is modified, until it is compacted back to a pure byte
     string.
 
     ``data`` is the initial manifest data.
 
     ``positions`` is a list of offsets, one per manifest entry.  Positive
     values are offsets into ``data``, negative values are offsets into the
     ``extradata`` list.  When an entry is removed, its entry is dropped from
     ``positions``.  The values are encoded such that when walking the list and
     indexing into ``data`` or ``extradata`` as appropriate, the entries are
     sorted by filename.
 
     ``extradata`` is a list of (key, hash, flags) for entries that were added or
     modified since the manifest was created or compacted.
     """
 
     def __init__(
         self,
         nodelen,
         data,
         positions=None,
         extrainfo=None,
         extradata=None,
         hasremovals=False,
     ):
         self._nodelen = nodelen
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
             self.hasremovals = False
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
             self.hasremovals = hasremovals
 
     def findlines(self, data):
         if not data:
             return []
         pos = data.find(b"\n")
         if pos == -1 or data[-1:] != b'\n':
             raise ValueError(b"Manifest did not end in a newline.")
         positions = [0]
         prev = data[: data.find(b'\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1 : data.find(b'\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError(b"Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find(b"\n", pos + 1)
         return positions
 
     def _get(self, index):
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos):
         if pos >= 0:
             return self.data[pos : self.data.find(b'\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key):
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key):
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key):
         return self.bsearch(key) != -1
 
     def __getitem__(self, key):
         if not isinstance(key, bytes):
             raise TypeError(b"getitem: manifest keys must be a bytes.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             return (data[1], data[2])
         zeropos = data.find(b'\x00', pos)
         nlpos = data.find(b'\n', zeropos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         if zeropos == -1 or nlpos == -1 or nlpos < zeropos:
             raise error.StorageError(b'Invalid manifest line')
         hlen = nlpos - zeropos - 1
         flags = data[nlpos - 1 : nlpos]
         if flags in _manifestflags:
             hlen -= 1
         else:
             flags = b''
         if hlen != 2 * self._nodelen:
             raise error.StorageError(b'Invalid manifest line')
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, hlen)
         return (hashval, flags)
 
     def __delitem__(self, key):
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1 :]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1 :]
         if cur >= 0:
             # This does NOT unsort the list as far as the search functions are
             # concerned, as they only examine lines mapped by self.positions.
             self.data = self.data[:cur] + b'\x00' + self.data[cur + 1 :]
             self.hasremovals = True
 
     def __setitem__(self, key, value):
         if not isinstance(key, bytes):
             raise TypeError(b"setitem: manifest keys must be a byte string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError(
                 b"Manifest values must be a tuple of (node, flags)."
             )
         hashval = value[0]
         if not isinstance(hashval, bytes) or len(hashval) not in (20, 32):
             raise TypeError(b"node must be a 20-byte or 32-byte byte string")
         flags = value[1]
         if not isinstance(flags, bytes) or len(flags) > 1:
             raise TypeError(b"flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (
                 self.positions[:needle]
                 + [-len(self.extradata)]
                 + self.positions[needle:]
             )
             self.extrainfo = (
                 self.extrainfo[:needle] + [0] + self.extrainfo[needle:]
             )
 
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(
             self._nodelen,
             self.data,
             self.positions,
             self.extrainfo,
             self.extradata,
             self.hasremovals,
         )
 
     def _compact(self):
         # hopefully not called TOO often
         if len(self.extradata) == 0 and not self.hasremovals:
             return
         l = []
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
 
                 # Collect all contiguous entries in the buffer at the current
                 # offset, breaking out only for added/modified items held in
                 # extradata, or a deleted line prior to the next position.
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
 
                     # A removed file has no positions[] entry, but does have an
                     # overwritten first byte.  Break out and find the end of the
                     # current good entry/entries if there is a removed file
                     # before the next position.
                     if (
                         self.hasremovals
                         and self.data.find(b'\n\x00', cur, self.positions[i])
                         != -1
                     ):
                         break
 
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find(b'\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     # Hashes are either 20 bytes (old sha1s) or 32
                     # bytes (new non-sha1).
                     hlen = 20
                     if len(t[1]) > 25:
                         hlen = 32
                     if len(t[1]) > hlen:
                         self.extrainfo[i] = ord(t[1][hlen + 1])
                     offset += len(l[-1])
                     i += 1
         self.data = b''.join(l)
         self.hasremovals = False
         self.extradata = []
 
     def _pack(self, d):
         n = d[1]
         assert len(n) in (20, 32)
         return d[0] + b'\x00' + hex(n) + d[2] + b'\n'
 
     def text(self):
         self._compact()
         return self.data
 
     def diff(self, m2, clean=False):
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, b'')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, b''), (e2, flags)
 
         return diff
 
     def iterentries(self):
         return lazymanifestiterentries(self)
 
     def iterkeys(self):
         return lazymanifestiter(self)
 
     def __iter__(self):
         return lazymanifestiter(self)
 
     def __len__(self):
         return len(self.positions)
 
     def filtercopy(self, filterfn):
         # XXX should be optimized
         c = _lazymanifest(self._nodelen, b'')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     pass
 
 
 @interfaceutil.implementer(repository.imanifestdict)
 class manifestdict(object):
     def __init__(self, nodelen, data=b''):
         self._nodelen = nodelen
         self._lm = _lazymanifest(nodelen, data)
 
     def __getitem__(self, key):
         return self._lm[key][0]
 
     def find(self, key):
         return self._lm[key]
 
     def __len__(self):
         return len(self._lm)
 
     def __nonzero__(self):
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     __bool__ = __nonzero__
 
     def __setitem__(self, key, node):
         self._lm[key] = node, self.flags(key)
 
     def __contains__(self, key):
         if key is None:
             return False
         return key in self._lm
 
     def __delitem__(self, key):
         del self._lm[key]
 
     def __iter__(self):
         return self._lm.__iter__()
 
     def iterkeys(self):
         return self._lm.iterkeys()
 
     def keys(self):
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match is not None:
             match = matchmod.badmatch(match, lambda path, msg: None)
             sm2 = set(m2.walk(match))
             return {f for f in self.walk(match) if f not in sm2}
         return {f for f in self if f not in m2}
 
     @propertycache
     def _dirs(self):
         return pathutil.dirs(self)
 
     def dirs(self):
         return self._dirs
 
     def hasdir(self, dir):
         return dir in self._dirs
 
     def _filesfastpath(self, match):
         """Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files."""
         files = match.files()
         return len(files) < 100 and (
             match.isexact()
             or (match.prefix() and all(fn in self for fn in files))
         )
 
     def walk(self, match):
         """Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         """
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 if fn in self:
                     yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _matches(self, match):
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict(self._nodelen)
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict(self._nodelen)
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(self, m2, match=None, clean=False):
         """Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         """
         if match:
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key, flag):
         if flag not in _manifestflags:
             raise TypeError(b"Invalid manifest flag set.")
         self._lm[key] = self[key], flag
 
     def get(self, key, default=None):
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key):
         try:
             return self._lm[key][1]
         except KeyError:
             return b''
 
     def copy(self):
         c = manifestdict(self._nodelen)
         c._lm = self._lm.copy()
         return c
 
     def items(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iteritems(self):
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self):
         return self._lm.iterentries()
 
     def text(self):
         # most likely uses native version
         return self._lm.text()
 
     def fastdelta(self, base, changes):
         """Given a base manifest text as a bytearray and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [b""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = b"%s\0%s%s\n" % (f, hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                             _(b"failed to remove %s from manifest") % f
                         )
                     l = b""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append([dstart, dend, b"".join(dline)])
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append([dstart, dend, b"".join(dline)])
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = bytearray(self.text())
             deltatext = mdiff.textdiff(
                 util.buffer(base), util.buffer(arraytext)
             )
 
         return arraytext, deltatext
 
 
 def _msearch(m, s, lo=0, hi=None):
     """return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
 
     m should be a buffer, a memoryview or a byte string.
     s is a byte string"""
 
     def advance(i, c):
         while i < lenm and m[i : i + 1] != c:
             i += 1
         return i
 
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1 : start] != b'\n':
             start -= 1
         end = advance(start, b'\0')
         if bytes(m[start:end]) < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, b'\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, b'\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, b'\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 
 def _checkforbidden(l):
     """Check filenames for illegal characters."""
     for f in l:
         if b'\n' in f or b'\r' in f:
             raise error.StorageError(
                 _(b"'\\n' and '\\r' disallowed in filenames: %r")
                 % pycompat.bytestr(f)
             )
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(addlist, x):
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = b"".join(
         struct.pack(b">lll", start, end, len(content)) + content
         for start, end, content in x
     )
     return deltatext, newaddlist
 
 
 def _splittopdir(f):
     if b'/' in f:
         dir, subpath = f.split(b'/', 1)
         return dir + b'/', subpath
     else:
         return b'', f
 
 
 _noop = lambda s: None
 
 
 @interfaceutil.implementer(repository.imanifestdict)
 class treemanifest(object):
     def __init__(self, nodeconstants, dir=b'', text=b''):
         self._dir = dir
         self.nodeconstants = nodeconstants
         self._node = self.nodeconstants.nullid
         self._nodelen = self.nodeconstants.nodelen
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
         self._dirs = {}
         self._lazydirs = {}
         # Using _lazymanifest here is a little slower than plain old dicts
         self._files = {}
         self._flags = {}
         if text:
 
             def readsubtree(subdir, subm):
                 raise AssertionError(
                     b'treemanifest constructor only accepts flat manifests'
                 )
 
             self.parse(text, readsubtree)
             self._dirty = True  # Mark flat manifest dirty after parsing
 
     def _subpath(self, path):
         return self._dir + path
 
     def _loadalllazy(self):
         selfdirs = self._dirs
         subpath = self._subpath
         for d, (node, readsubtree, docopy) in pycompat.iteritems(
             self._lazydirs
         ):
             if docopy:
                 selfdirs[d] = readsubtree(subpath(d), node).copy()
             else:
                 selfdirs[d] = readsubtree(subpath(d), node)
         self._lazydirs = {}
 
     def _loadlazy(self, d):
         v = self._lazydirs.get(d)
         if v:
             node, readsubtree, docopy = v
             if docopy:
                 self._dirs[d] = readsubtree(self._subpath(d), node).copy()
             else:
                 self._dirs[d] = readsubtree(self._subpath(d), node)
             del self._lazydirs[d]
 
     def _loadchildrensetlazy(self, visit):
         if not visit:
             return None
         if visit == b'all' or visit == b'this':
             self._loadalllazy()
             return None
 
         loadlazy = self._loadlazy
         for k in visit:
             loadlazy(k + b'/')
         return visit
 
     def _loaddifflazy(self, t1, t2):
         """load items in t1 and t2 if they're needed for diffing.
 
         The criteria currently is:
         - if it's not present in _lazydirs in either t1 or t2, load it in the
           other (it may already be loaded or it may not exist, doesn't matter)
         - if it's present in _lazydirs in both, compare the nodeid; if it
           differs, load it in both
         """
         toloadlazy = []
         for d, v1 in pycompat.iteritems(t1._lazydirs):
             v2 = t2._lazydirs.get(d)
             if not v2 or v2[0] != v1[0]:
                 toloadlazy.append(d)
         for d, v1 in pycompat.iteritems(t2._lazydirs):
             if d not in t1._lazydirs:
                 toloadlazy.append(d)
 
         for d in toloadlazy:
             t1._loadlazy(d)
             t2._loadlazy(d)
 
     def __len__(self):
         self._load()
         size = len(self._files)
         self._loadalllazy()
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def __nonzero__(self):
         # Faster than "__len() != 0" since it avoids loading sub-manifests
         return not self._isempty()
 
     __bool__ = __nonzero__
 
     def _isempty(self):
         self._load()  # for consistency; already loaded by all callers
         # See if we can skip loading everything.
         if self._files or (
             self._dirs and any(not m._isempty() for m in self._dirs.values())
         ):
             return False
         self._loadalllazy()
         return not self._dirs or all(m._isempty() for m in self._dirs.values())
 
     @encoding.strmethod
     def __repr__(self):
         return (
             b'<treemanifest dir=%s, node=%s, loaded=%r, dirty=%r at 0x%x>'
             % (
                 self._dir,
                 hex(self._node),
                 bool(self._loadfunc is _noop),
                 self._dirty,
                 id(self),
             )
         )
 
     def dir(self):
         """The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory."""
         return self._dir
 
     def node(self):
         """This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         """
         assert not self._dirty
         return self._node
 
     def setnode(self, node):
         self._node = node
         self._dirty = False
 
     def iterentries(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, b'')
             else:
                 for x in n.iterentries():
                     yield x
 
     def items(self):
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in pycompat.iteritems(n):
                     yield f, sn
 
     iteritems = items
 
     def iterkeys(self):
         self._load()
         self._loadalllazy()
         for p in sorted(itertools.chain(self._dirs, self._files)):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p]:
                     yield f
 
     def keys(self):
         return list(self.iterkeys())
 
     def __iter__(self):
         return self.iterkeys()
 
     def __contains__(self, f):
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return False
 
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f, default=None):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return b''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._lazydirs or f in self._dirs:
                 return b''
             return self._flags.get(f, b'')
 
     def find(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, b'')
 
     def __delitem__(self, f):
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def __setitem__(self, f, n):
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(
                     self.nodeconstants, self._subpath(dir)
                 )
             self._dirs[dir].__setitem__(subpath, n)
         else:
             # manifest nodes are either 20 bytes or 32 bytes,
             # depending on the hash in use. Assert this as historically
             # sometimes extra bytes were added.
             assert len(n) in (20, 32)
             self._files[f] = n
         self._dirty = True
 
     def _load(self):
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f, flags):
         """Set the flags (symlink, executable) for path f."""
         if flags not in _manifestflags:
             raise TypeError(b"Invalid manifest flag set.")
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(
                     self.nodeconstants, self._subpath(dir)
                 )
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self):
         copy = treemanifest(self.nodeconstants, self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
 
             def _copyfunc(s):
                 self._load()
                 s._lazydirs = {
                     d: (n, r, True)
                     for d, (n, r, c) in pycompat.iteritems(self._lazydirs)
                 }
                 sdirs = s._dirs
                 for d, v in pycompat.iteritems(self._dirs):
                     sdirs[d] = v.copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
 
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(self, m2, match=None):
         '''Set of files in this manifest that are not in the other'''
         if match and not match.always():
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.filesnotin(m2)
 
         files = set()
 
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
             for d, m1 in pycompat.iteritems(t1._dirs):
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files:
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self):
         return pathutil.dirs(self)
 
     def dirs(self):
         return self._alldirs
 
     def hasdir(self, dir):
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             self._loadlazy(topdir)
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         dirslash = dir + b'/'
         return dirslash in self._dirs or dirslash in self._lazydirs
 
     def walk(self, match):
         """Generates matching file names.
 
         It also reports nonexistent files by marking them bad with match.bad().
         """
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match):
         '''Recursively generates matching file names for walk().'''
         visit = match.visitchildrenset(self._dir[:-1])
         if not visit:
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         visit = self._loadchildrensetlazy(visit)
         for p in sorted(list(self._dirs) + list(self._files)):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 if not visit or p[:-1] in visit:
                     for f in self._dirs[p]._walk(match):
                         yield f
 
     def _matches(self, match):
         """recursively generate a new manifest filtered by the match argument."""
         if match.always():
             return self.copy()
         return self._matches_inner(match)
 
     def _matches_inner(self, match):
         if match.always():
             return self.copy()
 
         visit = match.visitchildrenset(self._dir[:-1])
         if visit == b'all':
             return self.copy()
         ret = treemanifest(self.nodeconstants, self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             # While visitchildrenset *usually* lists only subdirs, this is
             # actually up to the matcher and may have some files in the set().
             # If visit == 'this', we should obviously look at the files in this
             # directory; if visit is a set, and fn is in it, we should inspect
             # fn (but no need to inspect things not in the set).
             if visit != b'this' and fn not in visit:
                 continue
             fullp = self._subpath(fn)
             # visitchildrenset isn't perfect, we still need to call the regular
             # matcher code to further filter results.
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         visit = self._loadchildrensetlazy(visit)
         for dir, subm in pycompat.iteritems(self._dirs):
             if visit and dir[:-1] not in visit:
                 continue
             m = subm._matches_inner(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def fastdelta(self, base, changes):
         raise FastdeltaUnavailable()
 
     def diff(self, m2, match=None, clean=False):
         """Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         """
         if match and not match.always():
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest(self.nodeconstants)
 
         def _iterativediff(t1, t2, stack):
             """compares two tree manifests and append new tree-manifests which
             needs to be compared to stack"""
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
 
             for d, m1 in pycompat.iteritems(t1._dirs):
                 m2 = t2._dirs.get(d, emptytree)
                 stack.append((m1, m2))
 
             for d, m2 in pycompat.iteritems(t2._dirs):
                 if d not in t1._dirs:
                     stack.append((emptytree, m2))
 
             for fn, n1 in pycompat.iteritems(t1._files):
                 fl1 = t1._flags.get(fn, b'')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, b'')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in pycompat.iteritems(t2._files):
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, b'')
                     result[t2._subpath(fn)] = ((None, b''), (n2, fl2))
 
         stackls = []
         _iterativediff(self, m2, stackls)
         while stackls:
             t1, t2 = stackls.pop()
             # stackls is populated in the function call
             _iterativediff(t1, t2, stackls)
         return result
 
     def unmodifiedsince(self, m2):
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(self, text, readsubtree):
         selflazy = self._lazydirs
         for f, n, fl in _parse(self._nodelen, text):
             if fl == b't':
                 f = f + b'/'
                 # False below means "doesn't need to be copied" and can use the
                 # cached value from readsubtree directly.
                 selflazy[f] = (n, readsubtree, False)
             elif b'/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self):
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries())
 
     def dirtext(self):
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         lazydirs = [
             (d[:-1], v[0], b't') for d, v in pycompat.iteritems(self._lazydirs)
         ]
         dirs = [(d[:-1], self._dirs[d]._node, b't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files + lazydirs))
 
     def read(self, gettext, readsubtree):
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
 
         self._loadfunc = _load_for_read
 
     def writesubtrees(self, m1, m2, writesubtree, match):
         self._load()  # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest(self.nodeconstants)
 
         def getnode(m, d):
             ld = m._lazydirs.get(d)
             if ld:
                 return ld[0]
             return m._dirs.get(d, emptytree)._node
 
         # let's skip investigating things that `match` says we do not need.
         visit = match.visitchildrenset(self._dir[:-1])
         visit = self._loadchildrensetlazy(visit)
         if visit == b'this' or visit == b'all':
             visit = None
         for d, subm in pycompat.iteritems(self._dirs):
             if visit and d[:-1] not in visit:
                 continue
             subp1 = getnode(m1, d)
             subp2 = getnode(m2, d)
             if subp1 == self.nodeconstants.nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2, match)
 
     def walksubtrees(self, matcher=None):
         """Returns an iterator of the subtrees of this manifest, including this
         manifest itself.
 
         If `matcher` is provided, it only returns subtrees that match.
         """
         if matcher and not matcher.visitdir(self._dir[:-1]):
             return
         if not matcher or matcher(self._dir[:-1]):
             yield self
 
         self._load()
         # OPT: use visitchildrenset to avoid loading everything.
         self._loadalllazy()
         for d, subm in pycompat.iteritems(self._dirs):
             for subtree in subm.walksubtrees(matcher=matcher):
                 yield subtree
 
 
 class manifestfulltextcache(util.lrucachedict):
     """File-backed LRU cache for the manifest cache
 
     File consists of entries, up to EOF:
 
     - 20 bytes node, 4 bytes length, <length> manifest data
 
     These are written in reverse cache order (oldest to newest).
 
     """
 
     _file = b'manifestfulltextcache'
 
     def __init__(self, max):
         super(manifestfulltextcache, self).__init__(max)
         self._dirty = False
         self._read = False
         self._opener = None
 
     def read(self):
         if self._read or self._opener is None:
             return
 
         try:
             with self._opener(self._file) as fp:
                 set = super(manifestfulltextcache, self).__setitem__
                 # ignore trailing data, this is a cache, corruption is skipped
                 while True:
                     # TODO do we need to do work here for sha1 portability?
                     node = fp.read(20)
                     if len(node) < 20:
                         break
                     try:
                         size = struct.unpack(b'>L', fp.read(4))[0]
                     except struct.error:
                         break
                     value = bytearray(fp.read(size))
                     if len(value) != size:
                         break
                     set(node, value)
         except IOError:
             # the file is allowed to be missing
             pass
 
         self._read = True
         self._dirty = False
 
     def write(self):
         if not self._dirty or self._opener is None:
             return
         # rotate backwards to the first used node
         try:
             with self._opener(
                 self._file, b'w', atomictemp=True, checkambig=True
             ) as fp:
                 node = self._head.prev
                 while True:
                     if node.key in self._cache:
                         fp.write(node.key)
                         fp.write(struct.pack(b'>L', len(node.value)))
                         fp.write(node.value)
                     if node is self._head:
                         break
                     node = node.prev
         except IOError:
             # We could not write the cache (eg: permission error)
             # the content can be missing.
             #
             # We could try harder and see if we could recreate a wcache
             # directory were we coudl write too.
             #
             # XXX the error pass silently, having some way to issue an error
             # log `ui.log` would be nice.
             pass
 
     def __len__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__len__()
 
     def __contains__(self, k):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__contains__(k)
 
     def __iter__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__iter__()
 
     def __getitem__(self, k):
         if not self._read:
             self.read()
         # the cache lru order can change on read
         setdirty = self._cache.get(k) is not self._head
         value = super(manifestfulltextcache, self).__getitem__(k)
         if setdirty:
             self._dirty = True
         return value
 
     def __setitem__(self, k, v):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__setitem__(k, v)
         self._dirty = True
 
     def __delitem__(self, k):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__delitem__(k)
         self._dirty = True
 
     def get(self, k, default=None):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).get(k, default=default)
 
     def clear(self, clear_persisted_data=False):
         super(manifestfulltextcache, self).clear()
         if clear_persisted_data:
             self._dirty = True
             self.write()
         self._read = False
 
 
 # and upper bound of what we expect from compression
 # (real live value seems to be "3")
 MAXCOMPRESSION = 3
 
 
 class FastdeltaUnavailable(Exception):
     """Exception raised when fastdelta isn't usable on a manifest."""
 
 
 @interfaceutil.implementer(repository.imanifeststorage)
 class manifestrevlog(object):
     """A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     """
 
     def __init__(
         self,
         nodeconstants,
         opener,
         tree=b'',
         dirlogcache=None,
         indexfile=None,
         treemanifest=False,
     ):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
 
         `treemanifest` - used to indicate this is a tree manifest revlog. Opener
         options can also be used to make this a tree manifest revlog. The opener
         option takes precedence, so if it is set to True, we ignore whatever
         value is passed in to the constructor.
         """
         self.nodeconstants = nodeconstants
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         optiontreemanifest = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get(b'manifestcachesize', cachesize)
             optiontreemanifest = opts.get(b'treemanifest', False)
 
         self._treeondisk = optiontreemanifest or treemanifest
 
         self._fulltextcache = manifestfulltextcache(cachesize)
 
         if tree:
             assert self._treeondisk, b'opts is %r' % opts
 
         if indexfile is None:
             indexfile = b'00manifest.i'
             if tree:
                 indexfile = b"meta/" + tree + indexfile
 
         self.tree = tree
 
         # The dirlogcache is kept on the root manifest log
         if tree:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {b'': self}
 
         self._revlog = revlog.revlog(
             opener,
-            indexfile,
+            target=(revlog_constants.KIND_MANIFESTLOG, self.tree),
+            indexfile=indexfile,
             # only root indexfile is cached
             checkambig=not bool(tree),
             mmaplargeindex=True,
             upperboundcomp=MAXCOMPRESSION,
             persistentnodemap=opener.options.get(b'persistent-nodemap', False),
         )
 
         self.index = self._revlog.index
         self.version = self._revlog.version
         self._generaldelta = self._revlog._generaldelta
         self._revlog.revlog_kind = b'manifest'
 
     def _setupmanifestcachehooks(self, repo):
         """Persist the manifestfulltextcache on lock release"""
         if not util.safehasattr(repo, b'_wlockref'):
             return
 
         self._fulltextcache._opener = repo.wcachevfs
         if repo._currentlock(repo._wlockref) is None:
             return
 
         reporef = weakref.ref(repo)
         manifestrevlogref = weakref.ref(self)
 
         def persistmanifestcache(success):
             # Repo is in an unknown state, do not persist.
             if not success:
                 return
 
             repo = reporef()
             self = manifestrevlogref()
             if repo is None or self is None:
                 return
             if repo.manifestlog.getstorage(b'') is not self:
                 # there's a different manifest in play now, abort
                 return
             self._fulltextcache.write()
 
         repo._afterlock(persistmanifestcache)
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self, clear_persisted_data=False):
         self._revlog.clearcaches()
         self._fulltextcache.clear(clear_persisted_data=clear_persisted_data)
         self._dirlogcache = {self.tree: self}
 
     def dirlog(self, d):
         if d:
             assert self._treeondisk
         if d not in self._dirlogcache:
             mfrevlog = manifestrevlog(
                 self.nodeconstants,
                 self.opener,
                 d,
                 self._dirlogcache,
                 treemanifest=self._treeondisk,
             )
             self._dirlogcache[d] = mfrevlog
         return self._dirlogcache[d]
 
     def add(
         self,
         m,
         transaction,
         link,
         p1,
         p2,
         added,
         removed,
         readtree=None,
         match=None,
     ):
         """add some manifest entry in to the manifest log
 
         input:
 
           m:           the manifest dict we want to store
           transaction: the open transaction
           p1:          manifest-node of p1
           p2:          manifest-node of p2
           added:       file added/changed compared to parent
           removed:     file removed compared to parent
 
         tree manifest input:
 
           readtree:    a function to read a subtree
           match:       a filematcher for the subpart of the tree manifest
         """
         try:
             if p1 not in self.fulltextcache:
                 raise FastdeltaUnavailable()
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge(
                 [(x, False) for x in sorted(added)],
                 [(x, True) for x in sorted(removed)],
             )
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self._revlog.rev(p1), deltatext
             text = util.buffer(arraytext)
             rev = self._revlog.addrevision(
                 text, transaction, link, p1, p2, cachedelta
             )
             n = self._revlog.node(rev)
         except FastdeltaUnavailable:
             # The first parent manifest isn't already loaded or the
             # manifest implementation doesn't support fastdelta, so
             # we'll just encode a fulltext of the manifest and pass
             # that through to the revlog layer, and let it handle the
             # delta process.
             if self._treeondisk:
                 assert readtree, b"readtree must be set for treemanifest writes"
                 assert match, b"match must be specified for treemanifest writes"
                 m1 = readtree(self.tree, p1)
                 m2 = readtree(self.tree, p2)
                 n = self._addtree(
                     m, transaction, link, m1, m2, readtree, match=match
                 )
                 arraytext = None
             else:
                 text = m.text()
                 rev = self._revlog.addrevision(text, transaction, link, p1, p2)
                 n = self._revlog.node(rev)
                 arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree, match):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self.tree != b'' and (
             m.unmodifiedsince(m1) or m.unmodifiedsince(m2)
         ):
             return m.node()
 
         def writesubtree(subm, subp1, subp2, match):
             sublog = self.dirlog(subm.dir())
             sublog.add(
                 subm,
                 transaction,
                 link,
                 subp1,
                 subp2,
                 None,
                 None,
                 readtree=readtree,
                 match=match,
             )
 
         m.writesubtrees(m1, m2, writesubtree, match)
         text = m.dirtext()
         n = None
         if self.tree != b'':
             # Double-check whether contents are unchanged to one parent
             if text == m1.dirtext():
                 n = m1.node()
             elif text == m2.dirtext():
                 n = m2.node()
 
         if not n:
             rev = self._revlog.addrevision(
                 text, transaction, link, m1.node(), m2.node()
             )
             n = self._revlog.node(rev)
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, value):
         return self._revlog.lookup(value)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def checksize(self):
         return self._revlog.checksize()
 
     def revision(self, node, _df=None, raw=False):
         return self._revlog.revision(node, _df=_df, raw=raw)
 
     def rawdata(self, node, _df=None):
         return self._revlog.rawdata(node, _df=_df)
 
     def revdiff(self, rev1, rev2):
         return self._revlog.revdiff(rev1, rev2)
 
     def cmp(self, node, text):
         return self._revlog.cmp(node, text)
 
     def deltaparent(self, rev):
         return self._revlog.deltaparent(rev)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
             sidedata_helpers=sidedata_helpers,
         )
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
     ):
         return self._revlog.addgroup(
             deltas,
             linkmapper,
             transaction,
             alwayscache=alwayscache,
             addrevisioncb=addrevisioncb,
             duplicaterevisioncb=duplicaterevisioncb,
         )
 
     def rawsize(self, rev):
         return self._revlog.rawsize(rev)
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def files(self):
         return self._revlog.files()
 
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, manifestrevlog):
             raise error.ProgrammingError(b'expected manifestrevlog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     @property
     def indexfile(self):
         return self._revlog.indexfile
 
     @indexfile.setter
     def indexfile(self, value):
         self._revlog.indexfile = value
 
     @property
     def opener(self):
         return self._revlog.opener
 
     @opener.setter
     def opener(self, value):
         self._revlog.opener = value
 
 
 @interfaceutil.implementer(repository.imanifestlog)
 class manifestlog(object):
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
 
     def __init__(self, opener, repo, rootstore, narrowmatch):
         self.nodeconstants = repo.nodeconstants
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get(b'treemanifest', usetreemanifest)
             cachesize = opts.get(b'manifestcachesize', cachesize)
 
         self._treemanifests = usetreemanifest
 
         self._rootstore = rootstore
         self._rootstore._setupmanifestcachehooks(repo)
         self._narrowmatch = narrowmatch
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[b''] = util.lrucachedict(cachesize)
 
         self._cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get(b'', node)
 
     def get(self, tree, node, verify=True):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(tree, ()):
             return self._dirmancache[tree][node]
 
         if not self._narrowmatch.always():
             if not self._narrowmatch.visitdir(tree[:-1]):
                 return excludeddirmanifestctx(self.nodeconstants, tree, node)
         if tree:
             if self._rootstore._treeondisk:
                 if verify:
                     # Side-effect is LookupError is raised if node doesn't
                     # exist.
                     self.getstorage(tree).rev(node)
 
                 m = treemanifestctx(self, tree, node)
             else:
                 raise error.Abort(
                     _(
                         b"cannot ask for manifest directory '%s' in a flat "
                         b"manifest"
                     )
                     % tree
                 )
         else:
             if verify:
                 # Side-effect is LookupError is raised if node doesn't exist.
                 self._rootstore.rev(node)
 
             if self._treemanifests:
                 m = treemanifestctx(self, b'', node)
             else:
                 m = manifestctx(self, node)
 
         if node != self.nodeconstants.nullid:
             mancache = self._dirmancache.get(tree)
             if not mancache:
                 mancache = util.lrucachedict(self._cachesize)
                 self._dirmancache[tree] = mancache
             mancache[node] = m
         return m
 
     def getstorage(self, tree):
         return self._rootstore.dirlog(tree)
 
     def clearcaches(self, clear_persisted_data=False):
         self._dirmancache.clear()
         self._rootstore.clearcaches(clear_persisted_data=clear_persisted_data)
 
     def rev(self, node):
         return self._rootstore.rev(node)
 
     def update_caches(self, transaction):
         return self._rootstore._revlog.update_caches(transaction=transaction)
 
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memmanifestctx(object):
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict(manifestlog.nodeconstants.nodelen)
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self):
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         return self._storage().add(
             self._manifestdict,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             match=match,
         )
 
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class manifestctx(object):
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
 
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def node(self):
         return self._node
 
     def copy(self):
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def read(self):
         if self._data is None:
             nc = self._manifestlog.nodeconstants
             if self._node == nc.nullid:
                 self._data = manifestdict(nc.nodelen)
             else:
                 store = self._storage()
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = manifestdict(nc.nodelen, text)
         return self._data
 
     def readfast(self, shallow=False):
         """Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         """
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow=False):
         """Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         """
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(store.nodeconstants.nodelen, d)
 
     def find(self, key):
         return self.read().find(key)
 
 
 @interfaceutil.implementer(repository.imanifestrevisionwritable)
 class memtreemanifestctx(object):
     def __init__(self, manifestlog, dir=b''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest(manifestlog.nodeconstants)
 
     def _storage(self):
         return self._manifestlog.getstorage(b'')
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self):
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
 
         return self._storage().add(
             self._treemanifest,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             readtree=readtree,
             match=match,
         )
 
 
 @interfaceutil.implementer(repository.imanifestrevisionstored)
 class treemanifestctx(object):
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self):
         narrowmatch = self._manifestlog._narrowmatch
         if not narrowmatch.always():
             if not narrowmatch.visitdir(self._dir[:-1]):
                 return excludedmanifestrevlog(
                     self._manifestlog.nodeconstants, self._dir
                 )
         return self._manifestlog.getstorage(self._dir)
 
     def read(self):
         if self._data is None:
             store = self._storage()
             if self._node == self._manifestlog.nodeconstants.nullid:
                 self._data = treemanifest(self._manifestlog.nodeconstants)
             # TODO accessing non-public API
             elif store._treeondisk:
                 m = treemanifest(self._manifestlog.nodeconstants, dir=self._dir)
 
                 def gettext():
                     return store.revision(self._node)
 
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
 
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(
                     self._manifestlog.nodeconstants, dir=self._dir, text=text
                 )
 
         return self._data
 
     def node(self):
         return self._node
 
     def copy(self):
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self):
         return self._storage().parents(self._node)
 
     def readdelta(self, shallow=False):
         """Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         If `shallow` is True, this will read the delta for this directory,
         without recursively reading subdirectory manifests. Instead, any
         subdirectory entry will be reported as it appears in the manifest, i.e.
         the subdirectory will be reported among files and distinguished only by
         its 't' flag.
         """
         store = self._storage()
         if shallow:
             r = store.rev(self._node)
             d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
             return manifestdict(store.nodeconstants.nodelen, d)
         else:
             # Need to perform a slow delta
             r0 = store.deltaparent(store.rev(self._node))
             m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
             m1 = self.read()
             md = treemanifest(self._manifestlog.nodeconstants, dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in pycompat.iteritems(m0.diff(m1)):
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def readfast(self, shallow=False):
         """Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         """
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(
                 store.nodeconstants.nodelen, store.revision(self._node)
             )
         else:
             return self.read()
 
     def find(self, key):
         return self.read().find(key)
 
 
 class excludeddir(treemanifest):
     """Stand-in for a directory that is excluded from the repository.
 
     With narrowing active on a repository that uses treemanifests,
     some of the directory revlogs will be excluded from the resulting
     clone. This is a huge storage win for clients, but means we need
     some sort of pseudo-manifest to surface to internals so we can
     detect a merge conflict outside the narrowspec. That's what this
     class is: it stands in for a directory whose node is known, but
     whose contents are unknown.
     """
 
     def __init__(self, nodeconstants, dir, node):
         super(excludeddir, self).__init__(nodeconstants, dir)
         self._node = node
         # Add an empty file, which will be included by iterators and such,
         # appearing as the directory itself (i.e. something like "dir/")
         self._files[b''] = node
         self._flags[b''] = b't'
 
     # Manifests outside the narrowspec should never be modified, so avoid
     # copying. This makes a noticeable difference when there are very many
     # directories outside the narrowspec. Also, it makes sense for the copy to
     # be of the same type as the original, which would not happen with the
     # super type's copy().
     def copy(self):
         return self
 
 
 class excludeddirmanifestctx(treemanifestctx):
     """context wrapper for excludeddir - see that docstring for rationale"""
 
     def __init__(self, nodeconstants, dir, node):
         self.nodeconstants = nodeconstants
         self._dir = dir
         self._node = node
 
     def read(self):
         return excludeddir(self.nodeconstants, self._dir, self._node)
 
     def readfast(self, shallow=False):
         # special version of readfast since we don't have underlying storage
         return self.read()
 
     def write(self, *args):
         raise error.ProgrammingError(
             b'attempt to write manifest from excluded dir %s' % self._dir
         )
 
 
 class excludedmanifestrevlog(manifestrevlog):
     """Stand-in for excluded treemanifest revlogs.
 
     When narrowing is active on a treemanifest repository, we'll have
     references to directories we can't see due to the revlog being
     skipped. This class exists to conform to the manifestrevlog
     interface for those directories and proactively prevent writes to
     outside the narrowspec.
     """
 
     def __init__(self, nodeconstants, dir):
         self.nodeconstants = nodeconstants
         self._dir = dir
 
     def __len__(self):
         raise error.ProgrammingError(
             b'attempt to get length of excluded dir %s' % self._dir
         )
 
     def rev(self, node):
         raise error.ProgrammingError(
             b'attempt to get rev from excluded dir %s' % self._dir
         )
 
     def linkrev(self, node):
         raise error.ProgrammingError(
             b'attempt to get linkrev from excluded dir %s' % self._dir
         )
 
     def node(self, rev):
         raise error.ProgrammingError(
             b'attempt to get node from excluded dir %s' % self._dir
         )
 
     def add(self, *args, **kwargs):
         # We should never write entries in dirlogs outside the narrow clone.
         # However, the method still gets called from writesubtree() in
         # _addtree(), so we need to handle it. We should possibly make that
         # avoid calling add() with a clean manifest (_dirty is always False
         # in excludeddir instances).
         pass

mercurial/revlog.py

@@ -1,3121 +1,3138 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import binascii
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
     wdirrev,
 )
 from .i18n import _
 from .pycompat import getattr
 from .revlogutils.constants import (
+    ALL_KINDS,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_HASCOPIESINFO,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
     REVIDX_SIDEDATA,
 )
 from .thirdparty import attr
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     templatefilters,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     flagutil,
     nodemap as nodemaputil,
     revlogv0,
     sidedata as sidedatautil,
 )
 from .utils import (
     storageutil,
     stringutil,
 )
 
 # blanked usage of all the name to prevent pyflakes constraints
 # We need these name available in the module for extensions.
 REVLOGV0
 REVLOGV1
 REVLOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_SIDEDATA
 REVIDX_HASCOPIESINFO
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod('parsers')
 rustancestor = policy.importrust('ancestor')
 rustdagop = policy.importrust('dagop')
 rustrevlog = policy.importrust('revlog')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 
 def offset_type(offset, type):
     if (type & ~flagutil.REVIDX_KNOWN_FLAGS) != 0:
         raise ValueError(b'unknown revlog index flags')
     return int(int(offset) << 16 | type)
 
 
 def _verify_revision(rl, skipflags, state, node):
     """Verify the integrity of the given revlog ``node`` while providing a hook
     point for extensions to influence the operation."""
     if skipflags:
         state[b'skipread'].add(node)
     else:
         # Side-effect: read content and verify hash.
         rl.revision(node)
 
 
 # True if a fast implementation for persistent-nodemap is available
 #
 # We also consider we have a "fast" implementation in "pure" python because
 # people using pure don't really have performance consideration (and a
 # wheelbarrow of other slowness source)
 HAS_FAST_PERSISTENT_NODEMAP = rustrevlog is not None or util.safehasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @attr.s(slots=True, frozen=True)
 class _revisioninfo(object):
     """Information about a revision that allows building its fulltext
     node:       expected hash of the revision
     p1, p2:     parent revs of the revision
     btext:      built text cache consisting of a one-element list
     cachedelta: (baserev, uncompressed_delta) or None
     flags:      flags associated to the revision storage
 
     One of btext[0] or cachedelta must be set.
     """
 
     node = attr.ib()
     p1 = attr.ib()
     p2 = attr.ib()
     btext = attr.ib()
     textlen = attr.ib()
     cachedelta = attr.ib()
     flags = attr.ib()
 
 
 @interfaceutil.implementer(repository.irevisiondelta)
 @attr.s(slots=True)
 class revlogrevisiondelta(object):
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     sidedata = attr.ib()
     linknode = attr.ib(default=None)
 
 
 @interfaceutil.implementer(repository.iverifyproblem)
 @attr.s(frozen=True)
 class revlogproblem(object):
     warning = attr.ib(default=None)
     error = attr.ib(default=None)
     node = attr.ib(default=None)
 
 
 def parse_index_v1(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline)
     return index, cache
 
 
 def parse_index_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, revlogv2=True)
     return index, cache
 
 
 if util.safehasattr(parsers, 'parse_index_devel_nodemap'):
 
     def parse_index_v1_nodemap(data, inline):
         index, cache = parsers.parse_index_devel_nodemap(data, inline)
         return index, cache
 
 
 else:
     parse_index_v1_nodemap = None
 
 
 def parse_index_v1_mixed(data, inline):
     index, cache = parse_index_v1(data, inline)
     return rustrevlog.MixedIndex(index), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
 
     `concurrencychecker` is an optional function that receives 3 arguments: a
     file handle, a filename, and an expected position. It should check whether
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
     """
 
     _flagserrorclass = error.RevlogError
 
     def __init__(
         self,
         opener,
-        indexfile,
+        target,
+        indexfile=None,
         datafile=None,
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
     ):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
 
+        `target`: a (KIND, ID) tuple that identify the content stored in
+        this revlog. It help the rest of the code to understand what the revlog
+        is about without having to resort to heuristic and index filename
+        analysis. Note: that this must be reliably be set by normal code, but
+        that test, debug, or performance measurement code might not set this to
+        accurate value.
         """
         self.upperboundcomp = upperboundcomp
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + b".d")
         self.nodemap_file = None
         if persistentnodemap:
             self.nodemap_file = nodemaputil.get_nodemap_file(
                 opener, self.indexfile
             )
 
         self.opener = opener
+        assert target[0] in ALL_KINDS
+        assert len(target) == 2
+        self.target = target
         #  When True, indexfile is opened with checkambig=True at writing, to
         #  avoid file stat ambiguity.
         self._checkambig = checkambig
         self._mmaplargeindex = mmaplargeindex
         self._censorable = censorable
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
         # 2-tuple of (offset, data) of raw data from the revlog at an offset.
         self._chunkcache = (0, b'')
         # How much data to read and cache into the raw revlog data cache.
         self._chunkcachesize = 65536
         self._maxchainlen = None
         self._deltabothparents = True
         self.index = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
         # Mapping of revision integer to full node.
         self._compengine = b'zlib'
         self._compengineopts = {}
         self._maxdeltachainspan = -1
         self._withsparseread = False
         self._sparserevlog = False
         self._srdensitythreshold = 0.50
         self._srmingapsize = 262144
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
 
         # 2-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._loadindex()
 
         self._concurrencychecker = concurrencychecker
 
     def _loadindex(self):
         mmapindexthreshold = None
         opts = self.opener.options
 
         if b'revlogv2' in opts:
             newversionflags = REVLOGV2 | FLAG_INLINE_DATA
         elif b'revlogv1' in opts:
             newversionflags = REVLOGV1 | FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 newversionflags |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             newversionflags = REVLOGV0
         else:
             newversionflags = REVLOG_DEFAULT_VERSION
 
         if b'chunkcachesize' in opts:
             self._chunkcachesize = opts[b'chunkcachesize']
         if b'maxchainlen' in opts:
             self._maxchainlen = opts[b'maxchainlen']
         if b'deltabothparents' in opts:
             self._deltabothparents = opts[b'deltabothparents']
         self._lazydelta = bool(opts.get(b'lazydelta', True))
         self._lazydeltabase = False
         if self._lazydelta:
             self._lazydeltabase = bool(opts.get(b'lazydeltabase', False))
         if b'compengine' in opts:
             self._compengine = opts[b'compengine']
         if b'zlib.level' in opts:
             self._compengineopts[b'zlib.level'] = opts[b'zlib.level']
         if b'zstd.level' in opts:
             self._compengineopts[b'zstd.level'] = opts[b'zstd.level']
         if b'maxdeltachainspan' in opts:
             self._maxdeltachainspan = opts[b'maxdeltachainspan']
         if self._mmaplargeindex and b'mmapindexthreshold' in opts:
             mmapindexthreshold = opts[b'mmapindexthreshold']
         self.hassidedata = bool(opts.get(b'side-data', False))
         self._sparserevlog = bool(opts.get(b'sparse-revlog', False))
         withsparseread = bool(opts.get(b'with-sparse-read', False))
         # sparse-revlog forces sparse-read
         self._withsparseread = self._sparserevlog or withsparseread
         if b'sparse-read-density-threshold' in opts:
             self._srdensitythreshold = opts[b'sparse-read-density-threshold']
         if b'sparse-read-min-gap-size' in opts:
             self._srmingapsize = opts[b'sparse-read-min-gap-size']
         if opts.get(b'enableellipsis'):
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in pycompat.iteritems(
             opts.get(b'flagprocessors', {})
         ):
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         if self._chunkcachesize <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % self._chunkcachesize
             )
         elif self._chunkcachesize & (self._chunkcachesize - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % self._chunkcachesize
             )
 
         indexdata = b''
         self._initempty = True
         try:
             with self._indexfp() as f:
                 if (
                     mmapindexthreshold is not None
                     and self.opener.fstat(f).st_size >= mmapindexthreshold
                 ):
                     # TODO: should .close() to release resources without
                     # relying on Python GC
                     indexdata = util.buffer(util.mmapread(f))
                 else:
                     indexdata = f.read()
             if len(indexdata) > 0:
                 versionflags = INDEX_HEADER.unpack(indexdata[:4])[0]
                 self._initempty = False
             else:
                 versionflags = newversionflags
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
             versionflags = newversionflags
 
         self.version = versionflags
 
         flags = versionflags & ~0xFFFF
         fmt = versionflags & 0xFFFF
 
         if fmt == REVLOGV0:
             if flags:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             self._inline = False
             self._generaldelta = False
 
         elif fmt == REVLOGV1:
             if flags & ~REVLOGV1_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             self._inline = versionflags & FLAG_INLINE_DATA
             self._generaldelta = versionflags & FLAG_GENERALDELTA
 
         elif fmt == REVLOGV2:
             if flags & ~REVLOGV2_FLAGS:
                 raise error.RevlogError(
                     _(b'unknown flags (%#04x) in version %d revlog %s')
                     % (flags >> 16, fmt, self.indexfile)
                 )
 
             # There is a bug in the transaction handling when going from an
             # inline revlog to a separate index and data file. Turn it off until
             # it's fixed, since v2 revlogs sometimes get rewritten on exchange.
             # See issue6485
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(
                 _(b'unknown version (%d) in revlog %s') % (fmt, self.indexfile)
             )
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self._generaldelta:
             self._sparserevlog = False
 
         self._storedeltachains = True
 
         devel_nodemap = (
             self.nodemap_file
             and opts.get(b'devel-force-nodemap', False)
             and parse_index_v1_nodemap is not None
         )
 
         use_rust_index = False
         if rustrevlog is not None:
             if self.nodemap_file is not None:
                 use_rust_index = True
             else:
                 use_rust_index = self.opener.options.get(b'rust.index')
 
         self._parse_index = parse_index_v1
         if self.version == REVLOGV0:
             self._parse_index = revlogv0.parse_index_v0
         elif fmt == REVLOGV2:
             self._parse_index = parse_index_v2
         elif devel_nodemap:
             self._parse_index = parse_index_v1_nodemap
         elif use_rust_index:
             self._parse_index = parse_index_v1_mixed
         try:
             d = self._parse_index(indexdata, self._inline)
             index, _chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self.nodemap_file is not None
                 and util.safehasattr(index, 'update_nodemap_data')
             )
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
                     docket = nodemap_data[0]
                     if (
                         len(d[0]) > docket.tip_rev
                         and d[0][docket.tip_rev][7] == docket.tip_node
                     ):
                         # no changelog tampering
                         self._nodemap_docket = docket
                         index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
                 _(b"index %s is corrupted") % self.indexfile
             )
         self.index, self._chunkcache = d
         if not self._chunkcache:
             self._chunkclear()
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
         # revlog header -> revlog compressor
         self._decompressors = {}
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self._compengine]
         return engine.revlogcompressor(self._compengineopts)
 
     def _indexfp(self, mode=b'r'):
         """file object for the revlog's index file"""
         args = {'mode': mode}
         if mode != b'r':
             args['checkambig'] = self._checkambig
         if mode == b'w':
             args['atomictemp'] = True
         return self.opener(self.indexfile, **args)
 
     def _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self.datafile, mode=mode)
 
     @contextlib.contextmanager
     def _datareadfp(self, existingfp=None):
         """file object suitable to read data"""
         # Use explicit file handle, if given.
         if existingfp is not None:
             yield existingfp
 
         # Use a file handle being actively used for writes, if available.
         # There is some danger to doing this because reads will seek the
         # file. However, _writeentry() performs a SEEK_END before all writes,
         # so we should be safe.
         elif self._writinghandles:
             if self._inline:
                 yield self._writinghandles[0]
             else:
                 yield self._writinghandles[1]
 
         # Otherwise open a new file handle.
         else:
             if self._inline:
                 func = self._indexfp
             else:
                 func = self._datafp
             with func() as fp:
                 yield fp
 
     def tiprev(self):
         return len(self.index) - 1
 
     def tip(self):
         return self.node(self.tiprev())
 
     def __contains__(self, rev):
         return 0 <= rev < len(self)
 
     def __len__(self):
         return len(self.index)
 
     def __iter__(self):
         return iter(pycompat.xrange(len(self)))
 
     def revs(self, start=0, stop=None):
         """iterate over all rev in this revlog (from start to stop)"""
         return storageutil.iterrevs(len(self), start=start, stop=stop)
 
     @property
     def nodemap(self):
         msg = (
             b"revlog.nodemap is deprecated, "
             b"use revlog.index.[has_node|rev|get_rev]"
         )
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     @property
     def _nodecache(self):
         msg = b"revlog._nodecache is deprecated, use revlog.index.nodemap"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self.index.nodemap
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if (self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS) or (
             self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS
         ):
             return False
         return True
 
     def update_caches(self, transaction):
         if self.nodemap_file is not None:
             if transaction is None:
                 nodemaputil.update_persistent_nodemap(self)
             else:
                 nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, b'')
         self._pcache = {}
         self._nodemap_docket = None
         self.index.clearcaches()
         # The python code is the one responsible for validating the docket, we
         # end up having to refresh it here.
         use_nodemap = (
             not self._inline
             and self.nodemap_file is not None
             and util.safehasattr(self.index, 'update_nodemap_data')
         )
         if use_nodemap:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
                 self.index.update_nodemap_data(*nodemap_data)
 
     def rev(self, node):
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if (
                 node == self.nodeconstants.wdirid
                 or node in self.nodeconstants.wdirfilenodeids
             ):
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.indexfile, _(b'no node'))
 
     # Accessors for index entries.
 
     # First tuple entry is 8 bytes. First 6 bytes are offset. Last 2 bytes
     # are flags.
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def sidedata_length(self, rev):
         if self.version & 0xFFFF != REVLOGV2:
             return 0
         return self.index[rev][9]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.rawdata(rev)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (flagutil.REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev, raw=False))
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
         if entry[5] == nullrev:
             return entry[6], entry[5]
         else:
             return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         # inline node() to avoid function call overhead
         if d[5] == self.nullid:
             return i[d[6]][7], i[d[5]][7]
         else:
             return i[d[5]][7], i[d[6]][7]
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse revision order.
         Does not generate revs lower than stoprev.
 
         See the documentation for ancestor.lazyancestors for more details."""
 
         # first, make sure start revisions aren't filtered
         revs = list(revs)
         checkrev = self.node
         for r in revs:
             checkrev(r)
         # and we're sure ancestors aren't filtered as well
 
         if rustancestor is not None:
             lazyancestors = rustancestor.LazyAncestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset(object):
             def __init__(self, lazyvalues):
                 self.addedvalues = set()
                 self.lazyvalues = lazyvalues
 
             def __contains__(self, value):
                 return value in self.addedvalues or value in self.lazyvalues
 
             def __iter__(self):
                 added = self.addedvalues
                 for r in added:
                     yield r
                 for r in self.lazyvalues:
                     if not r in added:
                         yield r
 
             def add(self, value):
                 self.addedvalues.add(value)
 
             def update(self, values):
                 self.addedvalues.update(values)
 
         has = lazyset(self.ancestors(common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = collections.deque(r for r in heads if r not in has)
         while visit:
             r = visit.popleft()
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(miss) for miss in missing]
 
     def incrementalmissingrevs(self, common=None):
         """Return an object that can be used to incrementally compute the
         revision numbers of the ancestors of arbitrary sets that are not
         ancestors of common. This is an ancestor.incrementalmissingancestors
         object.
 
         'common' is a list of revision numbers. If common is not supplied, uses
         nullrev.
         """
         if common is None:
             common = [nullrev]
 
         if rustancestor is not None:
             return rustancestor.MissingAncestors(self.index, common)
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [self.nullid]  # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return (
                 [self.node(r) for r in self],
                 [self.nullid],
                 list(self.heads()),
             )
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == self.nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n)  # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update(
                             [p for p in self.parents(n) if p != self.nullid]
                         )
                     elif n in heads:  # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [self.nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in pycompat.iteritems(heads) if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self, revs=None):
         if revs is None:
             try:
                 return self.index.headrevs()
             except AttributeError:
                 return self._headrevs()
         if rustdagop is not None:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     def computephases(self, roots):
         return self.index.computephasesmapsets(roots)
 
     def _headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         # we won't iter over filtered rev so nobody is a head at start
         ishead = [0] * (count + 1)
         index = self.index
         for r in self:
             ishead[r] = 1  # I may be an head
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0  # my parent are not
         return [r for r, val in enumerate(ishead) if val]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [self.nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = {self.rev(n) for n in stop or []}
 
         revs = dagop.headrevssubset(
             self.revs, self.parentrevs, startrev=start, stoprevs=stoprevs
         )
 
         return [self.node(rev) for rev in revs]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError):  # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::(<roots> and <roots>::<heads>)))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(
                 minroot, heads, roots, includepath
             )
         except AttributeError:
             return dagop._reachablerootspure(
                 self.parentrevs, minroot, roots, heads, includepath
             )
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return self.nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == self.nodeconstants.nodelen:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node)  # quick search the index
                 return node
             except error.LookupError:
                 pass  # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if b"%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 2 * self.nodeconstants.nodelen:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = self.nodeconstants.wdirhex.startswith(id)
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     raise error.RevlogError
                 return partial
             if maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             return None
         except error.RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             # fast path: for unfiltered changelog, radix tree is accurate
             if not getattr(self, 'filteredrevs', None):
                 raise error.AmbiguousPrefixLookupError(
                     id, self.indexfile, _(b'ambiguous identifier')
                 )
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[: l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [
                     n for n in nl if hex(n).startswith(id) and self.hasnode(n)
                 ]
                 if self.nodeconstants.nullhex.startswith(id):
                     nl.append(self.nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.indexfile, _(b'ambiguous identifier')
                     )
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
         - revision number or str(revision number)
         - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise error.LookupError(id, self.indexfile, _(b'no match found'))
 
     def shortest(self, node, minlength=1):
         """Find the shortest unambiguous prefix that matches node."""
 
         def isvalid(prefix):
             try:
                 matchednode = self._partialmatch(prefix)
             except error.AmbiguousPrefixLookupError:
                 return False
             except error.WdirUnsupported:
                 # single 'ff...' match
                 return True
             if matchednode is None:
                 raise error.LookupError(node, self.indexfile, _(b'no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == b'f' for c in pycompat.iterbytestr(prefix))
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != self.nodeconstants.wdirid:
                     raise error.LookupError(node, self.indexfile, _(b'no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == self.nodeconstants.wdirid:
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, len(hexnode) + 1):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def _cachesegment(self, offset, data):
         """Add a segment to the revlog cache.
 
         Accepts an absolute offset and the data that is at that location.
         """
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _readsegment(self, offset, length, df=None):
         """Load a segment of raw data from the revlog.
 
         Accepts an absolute offset, length to read, and an optional existing
         file handle to read from.
 
         If an existing file handle is passed, it will be seeked and the
         original seek position will NOT be restored.
 
         Returns a str or buffer of raw byte data.
 
         Raises if the requested number of bytes could not be read.
         """
         # Cache data both forward and backward around the requested
         # data, in a fixed size window. This helps speed up operations
         # involving reading the revlog backwards.
         cachesize = self._chunkcachesize
         realoffset = offset & ~(cachesize - 1)
         reallength = (
             (offset + length + cachesize) & ~(cachesize - 1)
         ) - realoffset
         with self._datareadfp(df) as df:
             df.seek(realoffset)
             d = df.read(reallength)
 
         self._cachesegment(realoffset, d)
         if offset != realoffset or reallength != length:
             startoffset = offset - realoffset
             if len(d) - startoffset < length:
                 raise error.RevlogError(
                     _(
                         b'partial read of revlog %s; expected %d bytes from '
                         b'offset %d, got %d'
                     )
                     % (
                         self.indexfile if self._inline else self.datafile,
                         length,
                         realoffset,
                         len(d) - startoffset,
                     )
                 )
 
             return util.buffer(d, startoffset, length)
 
         if len(d) < length:
             raise error.RevlogError(
                 _(
                     b'partial read of revlog %s; expected %d bytes from offset '
                     b'%d, got %d'
                 )
                 % (
                     self.indexfile if self._inline else self.datafile,
                     length,
                     offset,
                     len(d),
                 )
             )
 
         return d
 
     def _getsegment(self, offset, length, df=None):
         """Obtain a segment of raw data from the revlog.
 
         Accepts an absolute offset, length of bytes to obtain, and an
         optional file handle to the already-opened revlog. If the file
         handle is used, it's original seek position will not be preserved.
 
         Requests for data may be returned from a cache.
 
         Returns a str or a buffer instance of raw byte data.
         """
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d  # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._readsegment(offset, length, df=df)
 
     def _getsegmentforrevs(self, startrev, endrev, df=None):
         """Obtain a segment of raw data corresponding to a range of revisions.
 
         Accepts the start and end revisions and an optional already-open
         file handle to be used for reading. If the file handle is read, its
         seek position will not be preserved.
 
         Requests for data may be satisfied by a cache.
 
         Returns a 2-tuple of (offset, data) for the requested range of
         revisions. Offset is the integer offset from the beginning of the
         revlog and data is a str or buffer of the raw byte data.
 
         Callers will need to call ``self.start(rev)`` and ``self.length(rev)``
         to determine where each revision's data begins and ends.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self._inline:
             start += (startrev + 1) * self.index.entry_size
             end += (endrev + 1) * self.index.entry_size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self.index.entry_size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = deltautil.slicechunk(
                 self, revs, targetsize=targetsize
             )
 
         for revschunk in slicedchunks:
             firstrev = revschunk[0]
             # Skip trailing revisions with empty diff
             for lastrev in revschunk[::-1]:
                 if length(lastrev) != 0:
                     break
 
             try:
                 offset, data = self._getsegmentforrevs(firstrev, lastrev, df=df)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 return [self._chunk(rev, df=df) for rev in revschunk]
 
             decomp = self.decompress
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 ladd(decomp(buffer(data, chunkstart - offset, chunklength)))
 
         return l
 
     def _chunkclear(self):
         """Clear the raw chunk cache."""
         self._chunkcache = (0, b'')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot"""
         if not self._sparserevlog:
             return self.deltaparent(rev) == nullrev
         elif util.safehasattr(self.index, b'issnapshot'):
             # directly assign the method to cache the testing and access
             self.issnapshot = self.index.issnapshot
             return self.issnapshot(rev)
         if rev == nullrev:
             return True
         entry = self.index[rev]
         base = entry[3]
         if base == rev:
             return True
         if base == nullrev:
             return True
         p1 = entry[5]
         p2 = entry[6]
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     def snapshotdepth(self, rev):
         """number of snapshot in the chain before this one"""
         if not self.issnapshot(rev):
             raise error.ProgrammingError(b'revision %d not a snapshot')
         return len(self._deltachain(rev)[0]) - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions
 
         The delta calculated is in binary form and is intended to be written to
         revlog data directly. So this function needs raw revision data.
         """
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return bytes(self._chunk(rev2))
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def _processflags(self, text, flags, operation, raw=False):
         """deprecated entry point to access flag processors"""
         msg = b'_processflag(...) use the specialized variant'
         util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         if raw:
             return text, flagutil.processflagsraw(self, text, flags)
         elif operation == b'read':
             return flagutil.processflagsread(self, text, flags)
         else:  # write operation
             return flagutil.processflagswrite(self, text, flags)
 
     def revision(self, nodeorrev, _df=None, raw=False):
         """return an uncompressed revision of a given node or revision
         number.
 
         _df - an existing file handle to read from. (internal-only)
         raw - an optional argument specifying if the revision data is to be
         treated as raw data when applying flag transforms. 'raw' should be set
         to True when generating changegroups or in debug commands.
         """
         if raw:
             msg = (
                 b'revlog.revision(..., raw=True) is deprecated, '
                 b'use revlog.rawdata(...)'
             )
             util.nouideprecwarn(msg, b'5.2', stacklevel=2)
         return self._revisiondata(nodeorrev, _df, raw=raw)[0]
 
     def sidedata(self, nodeorrev, _df=None):
         """a map of extra data related to the changeset but not part of the hash
 
         This function currently return a dictionary. However, more advanced
         mapping object will likely be used in the future for a more
         efficient/lazy code.
         """
         return self._revisiondata(nodeorrev, _df)[1]
 
     def _revisiondata(self, nodeorrev, _df=None, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == self.nullid:
             return b"", {}
 
         # ``rawtext`` is the text as stored inside the revlog. Might be the
         # revision or might need to be processed to retrieve the revision.
         rev, rawtext, validated = self._rawtext(node, rev, _df=_df)
 
         if self.version & 0xFFFF == REVLOGV2:
             if rev is None:
                 rev = self.rev(node)
             sidedata = self._sidedata(rev)
         else:
             sidedata = {}
 
         if raw and validated:
             # if we don't want to process the raw text and that raw
             # text is cached, we can exit early.
             return rawtext, sidedata
         if rev is None:
             rev = self.rev(node)
         # the revlog's flag for this revision
         # (usually alter its state or content)
         flags = self.flags(rev)
 
         if validated and flags == REVIDX_DEFAULT_FLAGS:
             # no extra flags set, no flag processor runs, text = rawtext
             return rawtext, sidedata
 
         if raw:
             validatehash = flagutil.processflagsraw(self, rawtext, flags)
             text = rawtext
         else:
             r = flagutil.processflagsread(self, rawtext, flags)
             text, validatehash = r
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._revisioncache = (node, rev, rawtext)
 
         return text, sidedata
 
     def _rawtext(self, node, rev, _df=None):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
 
         # revision in the cache (could be useful to apply delta)
         cachedrev = None
         # An intermediate text to apply deltas to
         basetext = None
 
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._revisioncache:
             if self._revisioncache[0] == node:
                 return (rev, self._revisioncache[2], True)
             cachedrev = self._revisioncache[1]
 
         if rev is None:
             rev = self.rev(node)
 
         chain, stopped = self._deltachain(rev, stoprev=cachedrev)
         if stopped:
             basetext = self._revisioncache[2]
 
         # drop cache to save memory, the caller is expected to
         # update self._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         bins = self._chunks(chain, df=_df, targetsize=targetsize)
         if basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext  # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         index_entry = self.index[rev]
         sidedata_offset = index_entry[8]
         sidedata_size = index_entry[9]
 
         if self._inline:
             sidedata_offset += self.index.entry_size * (1 + rev)
         if sidedata_size == 0:
             return {}
 
         segment = self._getsegment(sidedata_offset, sidedata_size)
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def rawdata(self, nodeorrev, _df=None):
         """return an uncompressed raw data of a given node or revision number.
 
         _df - an existing file handle to read from. (internal-only)
         """
         return self._revisiondata(nodeorrev, _df, raw=True)[0]
 
     def hash(self, text, p1, p2):
         """Compute a node hash.
 
         Available as a function so that subclasses can replace the hash
         as needed.
         """
         return storageutil.hashrevisionsha1(text, p1, p2)
 
     def checkhash(self, text, node, p1=None, p2=None, rev=None):
         """Check node hash integrity.
 
         Available as a function so that subclasses can extend hash mismatch
         behaviors as needed.
         """
         try:
             if p1 is None and p2 is None:
                 p1, p2 = self.parents(node)
             if node != self.hash(text, p1, p2):
                 # Clear the revision cache on hash failure. The revision cache
                 # only stores the raw revision and clearing the cache does have
                 # the side-effect that we won't have a cache hit when the raw
                 # revision data is accessed. But this case should be rare and
                 # it is extra work to teach the cache about the hash
                 # verification state.
                 if self._revisioncache and self._revisioncache[0] == node:
                     self._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(
                     _(b"integrity check failed on %s:%s")
                     % (self.indexfile, pycompat.bytestr(revornode))
                 )
         except error.RevlogError:
             if self._censorable and storageutil.iscensoredtext(text):
                 raise error.CensoredNodeError(self.indexfile, node, text)
             raise
 
     def _enforceinlinesize(self, tr, fp=None):
         """Check if the revlog is too big for inline and convert if so.
 
         This should be called after revisions are added to the revlog. If the
         revlog has grown too large to be an inline revlog, it will convert it
         to use multiple index and data files.
         """
         tiprev = len(self) - 1
         if (
             not self._inline
             or (self.start(tiprev) + self.length(tiprev)) < _maxinline
         ):
             return
 
         troffset = tr.findoffset(self.indexfile)
         if troffset is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self.indexfile
             )
         trindex = 0
         tr.add(self.datafile, 0)
 
         if fp:
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
 
         with self._indexfp(b'r') as ifh, self._datafp(b'w') as dfh:
             for r in self:
                 dfh.write(self._getsegmentforrevs(r, r, df=ifh)[1])
                 if troffset <= self.start(r):
                     trindex = r
 
         with self._indexfp(b'w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             for i in self:
                 e = self.index.entry_binary(i)
                 if i == 0:
                     header = self.index.pack_header(self.version)
                     e = header + e
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self.index.entry_size)
         nodemaputil.setup_persistent_nodemap(tr, self)
         self._chunkclear()
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     def addrevision(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=None,
         node=None,
         flags=REVIDX_DEFAULT_FLAGS,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         node - nodeid of revision; typically node is not specified, and it is
             computed by default as hash(text, p1, p2), however subclasses might
             use different hashing method (and override checkhash() in such case)
         flags - the known flags to set on the revision
         deltacomputer - an optional deltacomputer instance shared between
             multiple calls
         """
         if link == nullrev:
             raise error.RevlogError(
                 _(b"attempted to add linkrev -1 to %s") % self.indexfile
             )
 
         if sidedata is None:
             sidedata = {}
         elif not self.hassidedata:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _(
                     b"%s: size of %d bytes exceeds maximum revlog storage of 2GiB"
                 )
                 % (self.indexfile, len(rawtext))
             )
 
         node = node or self.hash(rawtext, p1, p2)
         rev = self.index.get_rev(node)
         if rev is not None:
             return rev
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
             sidedata=sidedata,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp(b"a+")
         ifh = self._indexfp(b"a+")
         try:
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 ifh,
                 dfh,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return b'', data
 
         compressed = self._compressor.compress(data)
 
         if compressed:
             # The revlog compressor added the header in the returned data.
             return b'', compressed
 
         if data[0:1] == b'\0':
             return b'', data
         return b'u', data
 
     def decompress(self, data):
         """Decompress a revlog chunk.
 
         The chunk is expected to begin with a header identifying the
         format type so it can be routed to an appropriate decompressor.
         """
         if not data:
             return data
 
         # Revlogs are read much more frequently than they are written and many
         # chunks only take microseconds to decompress, so performance is
         # important here.
         #
         # We can make a few assumptions about revlogs:
         #
         # 1) the majority of chunks will be compressed (as opposed to inline
         #    raw data).
         # 2) decompressing *any* data will likely by at least 10x slower than
         #    returning raw inline data.
         # 3) we want to prioritize common and officially supported compression
         #    engines
         #
         # It follows that we want to optimize for "decompress compressed data
         # when encoded with common and officially supported compression engines"
         # case over "raw data" and "data encoded by less common or non-official
         # compression engines." That is why we have the inline lookup first
         # followed by the compengines lookup.
         #
         # According to `hg perfrevlogchunks`, this is ~0.5% faster for zlib
         # compressed chunks. And this matters for changelog and manifest reads.
         t = data[0:1]
 
         if t == b'x':
             try:
                 return _zlibdecompress(data)
             except zlib.error as e:
                 raise error.RevlogError(
                     _(b'revlog decompress error: %s')
                     % stringutil.forcebytestr(e)
                 )
         # '\0' is more common than 'u' so it goes first.
         elif t == b'\0':
             return data
         elif t == b'u':
             return util.buffer(data, 1)
 
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(self._compengineopts)
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         ifh,
         dfh,
         alwayscache=False,
         deltacomputer=None,
         sidedata=None,
     ):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == self.nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self.indexfile
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%s: attempt to add wdir revision") % self.indexfile
             )
 
         if self._inline:
             fh = ifh
         else:
             fh = dfh
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
 
         offset = self._get_data_offset(prev)
 
         if self._concurrencychecker:
             if self._inline:
                 # offset is "as if" it were in the .d file, so we need to add on
                 # the size of the entry metadata.
                 self._concurrencychecker(
                     ifh, self.indexfile, offset + curr * self.index.entry_size
                 )
             else:
                 # Entries in the .i are a consistent size.
                 self._concurrencychecker(
                     ifh, self.indexfile, curr * self.index.entry_size
                 )
                 self._concurrencychecker(dfh, self.datafile, offset)
 
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(
                 revlog.size(self, cachedelta[0]), cachedelta[1]
             )
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         if sidedata:
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = offset + deltainfo.deltalen
         else:
             serialized_sidedata = b""
             # Don't store the offset if the sidedata is empty, that way
             # we can easily detect empty sidedata and they will be no different
             # than ones we manually add.
             sidedata_offset = 0
 
         e = (
             offset_type(offset, flags),
             deltainfo.deltalen,
             textlen,
             deltainfo.base,
             link,
             p1r,
             p2r,
             node,
             sidedata_offset,
             len(serialized_sidedata),
         )
 
         if self.version & 0xFFFF != REVLOGV2:
             e = e[:8]
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0:
             header = self.index.pack_header(self.version)
             entry = header + entry
         self._writeentry(
             transaction,
             ifh,
             dfh,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
         )
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo, fh)
 
         if type(rawtext) == bytes:  # only accept immutable objects
             self._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return curr
 
     def _get_data_offset(self, prev):
         """Returns the current offset in the (in-transaction) data file.
         Versions < 2 of the revlog can get this 0(1), revlog v2 needs a docket
         file to store that information: since sidedata can be rewritten to the
         end of the data file within a transaction, you can have cases where, for
         example, rev `n` does not have sidedata while rev `n - 1` does, leading
         to `n - 1`'s sidedata being written after `n`'s data.
 
         TODO cache this in a docket file before getting out of experimental."""
         if self.version & 0xFFFF != REVLOGV2:
             return self.end(prev)
 
         offset = 0
         for rev, entry in enumerate(self.index):
             sidedata_end = entry[8] + entry[9]
             # Sidedata for a previous rev has potentially been written after
             # this rev's end, so take the max.
             offset = max(self.end(rev), offset, sidedata_end)
         return offset
 
     def _writeentry(
         self, transaction, ifh, dfh, entry, data, link, offset, sidedata
     ):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. However, because
         # the file handle is reused for reads and may be seeked there, we need
         # to be careful before changing this.
         ifh.seek(0, os.SEEK_END)
         if dfh:
             dfh.seek(0, os.SEEK_END)
 
         curr = len(self) - 1
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 dfh.write(sidedata)
             ifh.write(entry)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self.indexfile, offset)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             if sidedata:
                 ifh.write(sidedata)
             self._enforceinlinesize(transaction, ifh)
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
     ):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         if self._writinghandles:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp(b"a+")
         isize = r * self.index.entry_size
         if self._inline:
             transaction.add(self.indexfile, end + isize)
             dfh = None
         else:
             transaction.add(self.indexfile, isize)
             transaction.add(self.datafile, end)
             dfh = self._datafp(b"a+")
 
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
         empty = True
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags, sidedata = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 rev = self.index.get_rev(node)
                 if rev is not None:
                     # this can happen if two branches make the same change
                     self._nodeduplicatecallback(transaction, rev)
                     if duplicaterevisioncb:
                         duplicaterevisioncb(self, rev)
                     empty = False
                     continue
 
                 for p in (p1, p2):
                     if not self.index.has_node(p):
                         raise error.LookupError(
                             p, self.indexfile, _(b'unknown parent')
                         )
 
                 if not self.index.has_node(deltabase):
                     raise error.LookupError(
                         deltabase, self.indexfile, _(b'unknown delta base')
                     )
 
                 baserev = self.rev(deltabase)
 
                 if baserev != nullrev and self.iscensored(baserev):
                     # if base is censored, delta must be full replacement in a
                     # single patch operation
                     hlen = struct.calcsize(b">lll")
                     oldlen = self.rawsize(baserev)
                     newlen = len(delta) - hlen
                     if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
                         raise error.CensoredBaseError(
                             self.indexfile, self.node(baserev)
                         )
 
                 if not flags and self._peek_iscensored(baserev, delta, flush):
                     flags |= REVIDX_ISCENSORED
 
                 # We assume consumers of addrevisioncb will want to retrieve
                 # the added revision, which will require a call to
                 # revision(). revision() will fast path if there is a cache
                 # hit. So, we tell _addrevision() to always cache in this case.
                 # We're only using addgroup() in the context of changegroup
                 # generation so the revision data can always be handled as raw
                 # by the flagprocessor.
                 rev = self._addrevision(
                     node,
                     None,
                     transaction,
                     link,
                     p1,
                     p2,
                     flags,
                     (baserev, delta),
                     ifh,
                     dfh,
                     alwayscache=alwayscache,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
 
                 if addrevisioncb:
                     addrevisioncb(self, rev)
                 empty = False
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp(b"a+")
                     ifh = self._indexfp(b"a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
         return not empty
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         return storageutil.deltaiscensored(delta, baserev, self.rawsize)
 
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev
 
         Returns a tuple containing the minimum rev and a set of all revs that
         have linkrevs that will be broken by this strip.
         """
         return storageutil.resolvestripinfo(
             minlink,
             len(self) - 1,
             self.headrevs(),
             self.linkrev,
             self.parentrevs,
         )
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         rev, _ = self.getstrippoint(minlink)
         if rev == len(self):
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self.index.entry_size
         else:
             end += rev * self.index.entry_size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = util.lrucachedict(500)
         self._chunkclear()
 
         del self.index[rev:-1]
 
     def checksize(self):
         """Check size of index and data files
 
         return a (dd, di) tuple.
         - dd: extra bytes for the "data" file
         - di: extra bytes for the "index" file
 
         A healthy revlog will return (0, 0).
         """
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             with self._datafp() as f:
                 f.seek(0, io.SEEK_END)
                 actual = f.tell()
             dd = actual - expected
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self.index.entry_size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
     ):
         if nodesorder not in (b'nodes', b'storage', b'linear', None):
             raise error.ProgrammingError(
                 b'unhandled value for nodesorder: %s' % nodesorder
             )
 
         if nodesorder is None and not self._generaldelta:
             nodesorder = b'storage'
 
         if (
             not self._storedeltachains
             and deltamode != repository.CG_DELTAMODE_PREV
         ):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self,
             nodes,
             nodesorder,
             revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self.candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             sidedata_helpers=sidedata_helpers,
         )
 
     DELTAREUSEALWAYS = b'always'
     DELTAREUSESAMEREVS = b'samerevs'
     DELTAREUSENEVER = b'never'
 
     DELTAREUSEFULLADD = b'fulladd'
 
     DELTAREUSEALL = {b'always', b'samerevs', b'never', b'fulladd'}
 
     def clone(
         self,
         tr,
         destrevlog,
         addrevisioncb=None,
         deltareuse=DELTAREUSESAMEREVS,
         forcedeltabothparents=None,
         sidedatacompanion=None,
     ):
         """Copy this revlog to another, possibly with format changes.
 
         The destination revlog will contain the same revisions and nodes.
         However, it may not be bit-for-bit identical due to e.g. delta encoding
         differences.
 
         The ``deltareuse`` argument control how deltas from the existing revlog
         are preserved in the destination revlog. The argument can have the
         following values:
 
         DELTAREUSEALWAYS
            Deltas will always be reused (if possible), even if the destination
            revlog would not select the same revisions for the delta. This is the
            fastest mode of operation.
         DELTAREUSESAMEREVS
            Deltas will be reused if the destination revlog would pick the same
            revisions for the delta. This mode strikes a balance between speed
            and optimization.
         DELTAREUSENEVER
            Deltas will never be reused. This is the slowest mode of execution.
            This mode can be used to recompute deltas (e.g. if the diff/delta
            algorithm changes).
         DELTAREUSEFULLADD
            Revision will be re-added as if their were new content. This is
            slower than DELTAREUSEALWAYS but allow more mechanism to kicks in.
            eg: large file detection and handling.
 
         Delta computation can be slow, so the choice of delta reuse policy can
         significantly affect run time.
 
         The default policy (``DELTAREUSESAMEREVS``) strikes a balance between
         two extremes. Deltas will be reused if they are appropriate. But if the
         delta could choose a better revision, it will do so. This means if you
         are converting a non-generaldelta revlog to a generaldelta revlog,
         deltas will be recomputed if the delta's parent isn't a parent of the
         revision.
 
         In addition to the delta policy, the ``forcedeltabothparents``
         argument controls whether to force compute deltas against both parents
         for merges. By default, the current default is used.
 
         If not None, the `sidedatacompanion` is callable that accept two
         arguments:
 
             (srcrevlog, rev)
 
         and return a quintet that control changes to sidedata content from the
         old revision to the new clone result:
 
             (dropall, filterout, update, new_flags, dropped_flags)
 
         * if `dropall` is True, all sidedata should be dropped
         * `filterout` is a set of sidedata keys that should be dropped
         * `update` is a mapping of additionnal/new key -> value
         * new_flags is a bitfields of new flags that the revision should get
         * dropped_flags is a bitfields of new flags that the revision shoudl not longer have
         """
         if deltareuse not in self.DELTAREUSEALL:
             raise ValueError(
                 _(b'value for deltareuse invalid: %s') % deltareuse
             )
 
         if len(destrevlog):
             raise ValueError(_(b'destination revlog is not empty'))
 
         if getattr(self, 'filteredrevs', None):
             raise ValueError(_(b'source revlog has filtered revisions'))
         if getattr(destrevlog, 'filteredrevs', None):
             raise ValueError(_(b'destination revlog has filtered revisions'))
 
         # lazydelta and lazydeltabase controls whether to reuse a cached delta,
         # if possible.
         oldlazydelta = destrevlog._lazydelta
         oldlazydeltabase = destrevlog._lazydeltabase
         oldamd = destrevlog._deltabothparents
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog._lazydeltabase = True
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog._lazydeltabase = False
                 destrevlog._lazydelta = False
 
             destrevlog._deltabothparents = forcedeltabothparents or oldamd
 
             self._clone(
                 tr,
                 destrevlog,
                 addrevisioncb,
                 deltareuse,
                 forcedeltabothparents,
                 sidedatacompanion,
             )
 
         finally:
             destrevlog._lazydelta = oldlazydelta
             destrevlog._lazydeltabase = oldlazydeltabase
             destrevlog._deltabothparents = oldamd
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
         sidedatacompanion,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         deltacomputer = deltautil.deltacomputer(destrevlog)
         index = self.index
         for rev in self:
             entry = index[rev]
 
             # Some classes override linkrev to take filtered revs into
             # account. Use raw entry from index.
             flags = entry[0] & 0xFFFF
             linkrev = entry[4]
             p1 = index[entry[5]][7]
             p2 = index[entry[6]][7]
             node = entry[7]
 
             sidedataactions = (False, [], {}, 0, 0)
             if sidedatacompanion is not None:
                 sidedataactions = sidedatacompanion(self, rev)
 
             # (Possibly) reuse the delta from the revlog if allowed and
             # the revlog chunk is a delta.
             cachedelta = None
             rawtext = None
             if any(sidedataactions) or deltareuse == self.DELTAREUSEFULLADD:
                 dropall = sidedataactions[0]
                 filterout = sidedataactions[1]
                 update = sidedataactions[2]
                 new_flags = sidedataactions[3]
                 dropped_flags = sidedataactions[4]
                 text, sidedata = self._revisiondata(rev)
                 if dropall:
                     sidedata = {}
                 for key in filterout:
                     sidedata.pop(key, None)
                 sidedata.update(update)
                 if not sidedata:
                     sidedata = None
 
                 flags |= new_flags
                 flags &= ~dropped_flags
 
                 destrevlog.addrevision(
                     text,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     cachedelta=cachedelta,
                     node=node,
                     flags=flags,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
             else:
                 if destrevlog._lazydelta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._chunk(rev)))
 
                 if not cachedelta:
                     rawtext = self.rawdata(rev)
 
                 ifh = destrevlog.opener(
                     destrevlog.indexfile, b'a+', checkambig=False
                 )
                 dfh = None
                 if not destrevlog._inline:
                     dfh = destrevlog.opener(destrevlog.datafile, b'a+')
                 try:
                     destrevlog._addrevision(
                         node,
                         rawtext,
                         tr,
                         linkrev,
                         p1,
                         p2,
                         flags,
                         cachedelta,
                         ifh,
                         dfh,
                         deltacomputer=deltacomputer,
                     )
                 finally:
                     if dfh:
                         dfh.close()
                     ifh.close()
 
             if addrevisioncb:
                 addrevisioncb(self, rev, node)
 
     def censorrevision(self, tr, censornode, tombstone=b''):
         if (self.version & 0xFFFF) == REVLOGV0:
             raise error.RevlogError(
                 _(b'cannot censor with version %d revlogs') % self.version
             )
 
         censorrev = self.rev(censornode)
         tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(censorrev):
             raise error.Abort(
                 _(b'censor tombstone must be no longer than censored data')
             )
 
         # Rewriting the revlog in place is hard. Our strategy for censoring is
         # to create a new revlog, copy all revisions to it, then replace the
         # revlogs on transaction close.
 
         newindexfile = self.indexfile + b'.tmpcensored'
         newdatafile = self.datafile + b'.tmpcensored'
 
         # This is a bit dangerous. We could easily have a mismatch of state.
-        newrl = revlog(self.opener, newindexfile, newdatafile, censorable=True)
+        newrl = revlog(
+            self.opener,
+            target=self.target,
+            indexfile=newindexfile,
+            datafile=newdatafile,
+            censorable=True,
+        )
         newrl.version = self.version
         newrl._generaldelta = self._generaldelta
         newrl._parse_index = self._parse_index
 
         for rev in self.revs():
             node = self.node(rev)
             p1, p2 = self.parents(node)
 
             if rev == censorrev:
                 newrl.addrawrevision(
                     tombstone,
                     tr,
                     self.linkrev(censorrev),
                     p1,
                     p2,
                     censornode,
                     REVIDX_ISCENSORED,
                 )
 
                 if newrl.deltaparent(rev) != nullrev:
                     raise error.Abort(
                         _(
                             b'censored revision stored as delta; '
                             b'cannot censor'
                         ),
                         hint=_(
                             b'censoring of revlogs is not '
                             b'fully implemented; please report '
                             b'this bug'
                         ),
                     )
                 continue
 
             if self.iscensored(rev):
                 if self.deltaparent(rev) != nullrev:
                     raise error.Abort(
                         _(
                             b'cannot censor due to censored '
                             b'revision having delta stored'
                         )
                     )
                 rawtext = self._chunk(rev)
             else:
                 rawtext = self.rawdata(rev)
 
             newrl.addrawrevision(
                 rawtext, tr, self.linkrev(rev), p1, p2, node, self.flags(rev)
             )
 
         tr.addbackup(self.indexfile, location=b'store')
         if not self._inline:
             tr.addbackup(self.datafile, location=b'store')
 
         self.opener.rename(newrl.indexfile, self.indexfile)
         if not self._inline:
             self.opener.rename(newrl.datafile, self.datafile)
 
         self.clearcaches()
         self._loadindex()
 
     def verifyintegrity(self, state):
         """Verifies the integrity of the revlog.
 
         Yields ``revlogproblem`` instances describing problems that are
         found.
         """
         dd, di = self.checksize()
         if dd:
             yield revlogproblem(error=_(b'data length off by %d bytes') % dd)
         if di:
             yield revlogproblem(error=_(b'index contains %d extra bytes') % di)
 
         version = self.version & 0xFFFF
 
         # The verifier tells us what version revlog we should be.
         if version != state[b'expectedversion']:
             yield revlogproblem(
                 warning=_(b"warning: '%s' uses revlog format %d; expected %d")
                 % (self.indexfile, version, state[b'expectedversion'])
             )
 
         state[b'skipread'] = set()
         state[b'safe_renamed'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see flagutil.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get(b'skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_(b'unpacked size is %d, %d expected') % (l2, l1),
                         node=node,
                     )
 
             except error.CensoredNodeError:
                 if state[b'erroroncensored']:
                     yield revlogproblem(
                         error=_(b'censored file data'), node=node
                     )
                     state[b'skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_(b'unpacking %s: %s')
                     % (short(node), stringutil.forcebytestr(e)),
                     node=node,
                 )
                 state[b'skipread'].add(node)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         d = {}
 
         if exclusivefiles:
             d[b'exclusivefiles'] = [(self.opener, self.indexfile)]
             if not self._inline:
                 d[b'exclusivefiles'].append((self.opener, self.datafile))
 
         if sharedfiles:
             d[b'sharedfiles'] = []
 
         if revisionscount:
             d[b'revisionscount'] = len(self)
 
         if trackedsize:
             d[b'trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d[b'storedsize'] = sum(
                 self.opener.stat(path).st_size for path in self.files()
             )
 
         return d
 
     def rewrite_sidedata(self, helpers, startrev, endrev):
         if self.version & 0xFFFF != REVLOGV2:
             return
         # inline are not yet supported because they suffer from an issue when
         # rewriting them (since it's not an append-only operation).
         # See issue6485.
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         new_entries = []
         # append the new sidedata
         with self._datafp(b'a+') as fp:
             # Maybe this bug still exists, see revlog._writeentry
             fp.seek(0, os.SEEK_END)
             current_offset = fp.tell()
             for rev in range(startrev, endrev + 1):
                 entry = self.index[rev]
                 new_sidedata = storageutil.run_sidedata_helpers(
                     store=self,
                     sidedata_helpers=helpers,
                     sidedata={},
                     rev=rev,
                 )
 
                 serialized_sidedata = sidedatautil.serialize_sidedata(
                     new_sidedata
                 )
                 if entry[8] != 0 or entry[9] != 0:
                     # rewriting entries that already have sidedata is not
                     # supported yet, because it introduces garbage data in the
                     # revlog.
                     msg = b"Rewriting existing sidedata is not supported yet"
                     raise error.Abort(msg)
                 entry = entry[:8]
                 entry += (current_offset, len(serialized_sidedata))
 
                 fp.write(serialized_sidedata)
                 new_entries.append(entry)
                 current_offset += len(serialized_sidedata)
 
         # rewrite the new index entries
         with self._indexfp(b'w+') as fp:
             fp.seek(startrev * self.index.entry_size)
             for i, entry in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, entry[8], entry[9])
                 packed = self.index.entry_binary(rev)
                 if rev == 0:
                     header = self.index.pack_header(self.version)
                     packed = header + packed
                 fp.write(packed)

mercurial/revlogutils/constants.py

@@ -1,107 +1,121 b''
 # revlogdeltas.py - constant used for revlog logic
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 # Copyright 2018 Octobus <[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.
 """Helper class to compute deltas stored inside revlogs"""
 
 from __future__ import absolute_import
 
 import struct
 
 from ..interfaces import repository
 
+### Internal utily constants
+
+KIND_CHANGELOG = 1001  # over 256 to not be comparable with a bytes
+KIND_MANIFESTLOG = 1002
+KIND_FILELOG = 1003
+KIND_OTHER = 1004
+
+ALL_KINDS = {
+    KIND_CHANGELOG,
+    KIND_MANIFESTLOG,
+    KIND_FILELOG,
+    KIND_OTHER,
+}
+
 ### main revlog header
 
 INDEX_HEADER = struct.Struct(b">I")
 
 ## revlog version
 REVLOGV0 = 0
 REVLOGV1 = 1
 # Dummy value until file format is finalized.
 REVLOGV2 = 0xDEAD
 
 ##  global revlog header flags
 # Shared across v1 and v2.
 FLAG_INLINE_DATA = 1 << 16
 # Only used by v1, implied by v2.
 FLAG_GENERALDELTA = 1 << 17
 REVLOG_DEFAULT_FLAGS = FLAG_INLINE_DATA
 REVLOG_DEFAULT_FORMAT = REVLOGV1
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGV1_FLAGS = FLAG_INLINE_DATA | FLAG_GENERALDELTA
 REVLOGV2_FLAGS = FLAG_INLINE_DATA
 
 ### individual entry
 
 ## index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 INDEX_ENTRY_V0 = struct.Struct(b">4l20s20s20s")
 
 ## index v1
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 INDEX_ENTRY_V1 = struct.Struct(b">Qiiiiii20s12x")
 assert INDEX_ENTRY_V1.size == 32 * 2
 
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 #  8 bytes: sidedata offset
 #  4 bytes: sidedata compressed length
 #  20 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page)
 INDEX_ENTRY_V2 = struct.Struct(b">Qiiiiii20s12xQi20x")
 assert INDEX_ENTRY_V2.size == 32 * 3
 
 # revlog index flags
 
 # For historical reasons, revlog's internal flags were exposed via the
 # wire protocol and are even exposed in parts of the storage APIs.
 
 # revision has censor metadata, must be verified
 REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED
 # revision hash does not match data (narrowhg)
 REVIDX_ELLIPSIS = repository.REVISION_FLAG_ELLIPSIS
 # revision data is stored externally
 REVIDX_EXTSTORED = repository.REVISION_FLAG_EXTSTORED
 # revision data contains extra metadata not part of the official digest
 REVIDX_SIDEDATA = repository.REVISION_FLAG_SIDEDATA
 # revision changes files in a way that could affect copy tracing.
 REVIDX_HASCOPIESINFO = repository.REVISION_FLAG_HASCOPIESINFO
 REVIDX_DEFAULT_FLAGS = 0
 # stable order in which flags need to be processed and their processors applied
 REVIDX_FLAGS_ORDER = [
     REVIDX_ISCENSORED,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_SIDEDATA,
     REVIDX_HASCOPIESINFO,
 ]
 
 # bitmark for flags that could cause rawdata content change
 REVIDX_RAWTEXT_CHANGING_FLAGS = (
     REVIDX_ISCENSORED | REVIDX_EXTSTORED | REVIDX_SIDEDATA
 )
 
 SPARSE_REVLOG_MAX_CHAIN_LENGTH = 1000