nodemap: track the maximum revision tracked in the nodemap

We need a simple way to detect when the on disk data contains less revision
than the index we read from disk. The docket file is meant for this, we just had
to start tracking that data.

We should also try to detect strip operation, but we will deal with this in
later changesets. Right now we are focusing on defining the API for index
supporting persistent nodemap.

Differential Revision: https://phab.mercurial-scm.org/D7888

mercurial/debugcommands.py

@@ -1,4364 +1,4365 b''
 # debugcommands.py - command processing for debug* commands
 #
 # Copyright 2005-2016 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import codecs
 import collections
 import difflib
 import errno
 import operator
 import os
 import platform
 import random
 import re
 import socket
 import ssl
 import stat
 import string
 import subprocess
 import sys
 import time
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullhex,
     nullid,
     nullrev,
     short,
 )
 from .pycompat import (
     getattr,
     open,
 )
 from . import (
     bundle2,
     changegroup,
     cmdutil,
     color,
     context,
     copies,
     dagparser,
     encoding,
     error,
     exchange,
     extensions,
     filemerge,
     filesetlang,
     formatter,
     hg,
     httppeer,
     localrepo,
     lock as lockmod,
     logcmdutil,
     merge as mergemod,
     obsolete,
     obsutil,
     pathutil,
     phases,
     policy,
     pvec,
     pycompat,
     registrar,
     repair,
     revlog,
     revset,
     revsetlang,
     scmutil,
     setdiscovery,
     simplemerge,
     sshpeer,
     sslutil,
     streamclone,
     tags as tagsmod,
     templater,
     treediscovery,
     upgrade,
     url as urlmod,
     util,
     vfs as vfsmod,
     wireprotoframing,
     wireprotoserver,
     wireprotov2peer,
 )
 from .utils import (
     cborutil,
     compression,
     dateutil,
     procutil,
     stringutil,
 )
 
 from .revlogutils import (
     deltas as deltautil,
     nodemap,
 )
 
 release = lockmod.release
 
 command = registrar.command()
 
 
 @command(b'debugancestor', [], _(b'[INDEX] REV1 REV2'), optionalrepo=True)
 def debugancestor(ui, repo, *args):
     """find the ancestor revision of two revisions in a given index"""
     if len(args) == 3:
         index, rev1, rev2 = args
         r = revlog.revlog(vfsmod.vfs(encoding.getcwd(), audit=False), index)
         lookup = r.lookup
     elif len(args) == 2:
         if not repo:
             raise error.Abort(
                 _(b'there is no Mercurial repository here (.hg not found)')
             )
         rev1, rev2 = args
         r = repo.changelog
         lookup = repo.lookup
     else:
         raise error.Abort(_(b'either two or three arguments required'))
     a = r.ancestor(lookup(rev1), lookup(rev2))
     ui.write(b'%d:%s\n' % (r.rev(a), hex(a)))
 
 
 @command(b'debugapplystreamclonebundle', [], b'FILE')
 def debugapplystreamclonebundle(ui, repo, fname):
     """apply a stream clone bundle file"""
     f = hg.openpath(ui, fname)
     gen = exchange.readbundle(ui, f, fname)
     gen.apply(repo)
 
 
 @command(
     b'debugbuilddag',
     [
         (
             b'm',
             b'mergeable-file',
             None,
             _(b'add single file mergeable changes'),
         ),
         (
             b'o',
             b'overwritten-file',
             None,
             _(b'add single file all revs overwrite'),
         ),
         (b'n', b'new-file', None, _(b'add new file at each rev')),
     ],
     _(b'[OPTION]... [TEXT]'),
 )
 def debugbuilddag(
     ui,
     repo,
     text=None,
     mergeable_file=False,
     overwritten_file=False,
     new_file=False,
 ):
     """builds a repo with a given DAG from scratch in the current empty repo
 
     The description of the DAG is read from stdin if not given on the
     command line.
 
     Elements:
 
      - "+n" is a linear run of n nodes based on the current default parent
      - "." is a single node based on the current default parent
      - "$" resets the default parent to null (implied at the start);
            otherwise the default parent is always the last node created
      - "<p" sets the default parent to the backref p
      - "*p" is a fork at parent p, which is a backref
      - "*p1/p2" is a merge of parents p1 and p2, which are backrefs
      - "/p2" is a merge of the preceding node and p2
      - ":tag" defines a local tag for the preceding node
      - "@branch" sets the named branch for subsequent nodes
      - "#...\\n" is a comment up to the end of the line
 
     Whitespace between the above elements is ignored.
 
     A backref is either
 
      - a number n, which references the node curr-n, where curr is the current
        node, or
      - the name of a local tag you placed earlier using ":tag", or
      - empty to denote the default parent.
 
     All string valued-elements are either strictly alphanumeric, or must
     be enclosed in double quotes ("..."), with "\\" as escape character.
     """
 
     if text is None:
         ui.status(_(b"reading DAG from stdin\n"))
         text = ui.fin.read()
 
     cl = repo.changelog
     if len(cl) > 0:
         raise error.Abort(_(b'repository is not empty'))
 
     # determine number of revs in DAG
     total = 0
     for type, data in dagparser.parsedag(text):
         if type == b'n':
             total += 1
 
     if mergeable_file:
         linesperrev = 2
         # make a file with k lines per rev
         initialmergedlines = [
             b'%d' % i for i in pycompat.xrange(0, total * linesperrev)
         ]
         initialmergedlines.append(b"")
 
     tags = []
     progress = ui.makeprogress(
         _(b'building'), unit=_(b'revisions'), total=total
     )
     with progress, repo.wlock(), repo.lock(), repo.transaction(b"builddag"):
         at = -1
         atbranch = b'default'
         nodeids = []
         id = 0
         progress.update(id)
         for type, data in dagparser.parsedag(text):
             if type == b'n':
                 ui.note((b'node %s\n' % pycompat.bytestr(data)))
                 id, ps = data
 
                 files = []
                 filecontent = {}
 
                 p2 = None
                 if mergeable_file:
                     fn = b"mf"
                     p1 = repo[ps[0]]
                     if len(ps) > 1:
                         p2 = repo[ps[1]]
                         pa = p1.ancestor(p2)
                         base, local, other = [
                             x[fn].data() for x in (pa, p1, p2)
                         ]
                         m3 = simplemerge.Merge3Text(base, local, other)
                         ml = [l.strip() for l in m3.merge_lines()]
                         ml.append(b"")
                     elif at > 0:
                         ml = p1[fn].data().split(b"\n")
                     else:
                         ml = initialmergedlines
                     ml[id * linesperrev] += b" r%i" % id
                     mergedtext = b"\n".join(ml)
                     files.append(fn)
                     filecontent[fn] = mergedtext
 
                 if overwritten_file:
                     fn = b"of"
                     files.append(fn)
                     filecontent[fn] = b"r%i\n" % id
 
                 if new_file:
                     fn = b"nf%i" % id
                     files.append(fn)
                     filecontent[fn] = b"r%i\n" % id
                     if len(ps) > 1:
                         if not p2:
                             p2 = repo[ps[1]]
                         for fn in p2:
                             if fn.startswith(b"nf"):
                                 files.append(fn)
                                 filecontent[fn] = p2[fn].data()
 
                 def fctxfn(repo, cx, path):
                     if path in filecontent:
                         return context.memfilectx(
                             repo, cx, path, filecontent[path]
                         )
                     return None
 
                 if len(ps) == 0 or ps[0] < 0:
                     pars = [None, None]
                 elif len(ps) == 1:
                     pars = [nodeids[ps[0]], None]
                 else:
                     pars = [nodeids[p] for p in ps]
                 cx = context.memctx(
                     repo,
                     pars,
                     b"r%i" % id,
                     files,
                     fctxfn,
                     date=(id, 0),
                     user=b"debugbuilddag",
                     extra={b'branch': atbranch},
                 )
                 nodeid = repo.commitctx(cx)
                 nodeids.append(nodeid)
                 at = id
             elif type == b'l':
                 id, name = data
                 ui.note((b'tag %s\n' % name))
                 tags.append(b"%s %s\n" % (hex(repo.changelog.node(id)), name))
             elif type == b'a':
                 ui.note((b'branch %s\n' % data))
                 atbranch = data
             progress.update(id)
 
         if tags:
             repo.vfs.write(b"localtags", b"".join(tags))
 
 
 def _debugchangegroup(ui, gen, all=None, indent=0, **opts):
     indent_string = b' ' * indent
     if all:
         ui.writenoi18n(
             b"%sformat: id, p1, p2, cset, delta base, len(delta)\n"
             % indent_string
         )
 
         def showchunks(named):
             ui.write(b"\n%s%s\n" % (indent_string, named))
             for deltadata in gen.deltaiter():
                 node, p1, p2, cs, deltabase, delta, flags = deltadata
                 ui.write(
                     b"%s%s %s %s %s %s %d\n"
                     % (
                         indent_string,
                         hex(node),
                         hex(p1),
                         hex(p2),
                         hex(cs),
                         hex(deltabase),
                         len(delta),
                     )
                 )
 
         gen.changelogheader()
         showchunks(b"changelog")
         gen.manifestheader()
         showchunks(b"manifest")
         for chunkdata in iter(gen.filelogheader, {}):
             fname = chunkdata[b'filename']
             showchunks(fname)
     else:
         if isinstance(gen, bundle2.unbundle20):
             raise error.Abort(_(b'use debugbundle2 for this file'))
         gen.changelogheader()
         for deltadata in gen.deltaiter():
             node, p1, p2, cs, deltabase, delta, flags = deltadata
             ui.write(b"%s%s\n" % (indent_string, hex(node)))
 
 
 def _debugobsmarkers(ui, part, indent=0, **opts):
     """display version and markers contained in 'data'"""
     opts = pycompat.byteskwargs(opts)
     data = part.read()
     indent_string = b' ' * indent
     try:
         version, markers = obsolete._readmarkers(data)
     except error.UnknownVersion as exc:
         msg = b"%sunsupported version: %s (%d bytes)\n"
         msg %= indent_string, exc.version, len(data)
         ui.write(msg)
     else:
         msg = b"%sversion: %d (%d bytes)\n"
         msg %= indent_string, version, len(data)
         ui.write(msg)
         fm = ui.formatter(b'debugobsolete', opts)
         for rawmarker in sorted(markers):
             m = obsutil.marker(None, rawmarker)
             fm.startitem()
             fm.plain(indent_string)
             cmdutil.showmarker(fm, m)
         fm.end()
 
 
 def _debugphaseheads(ui, data, indent=0):
     """display version and markers contained in 'data'"""
     indent_string = b' ' * indent
     headsbyphase = phases.binarydecode(data)
     for phase in phases.allphases:
         for head in headsbyphase[phase]:
             ui.write(indent_string)
             ui.write(b'%s %s\n' % (hex(head), phases.phasenames[phase]))
 
 
 def _quasirepr(thing):
     if isinstance(thing, (dict, util.sortdict, collections.OrderedDict)):
         return b'{%s}' % (
             b', '.join(b'%s: %s' % (k, thing[k]) for k in sorted(thing))
         )
     return pycompat.bytestr(repr(thing))
 
 
 def _debugbundle2(ui, gen, all=None, **opts):
     """lists the contents of a bundle2"""
     if not isinstance(gen, bundle2.unbundle20):
         raise error.Abort(_(b'not a bundle2 file'))
     ui.write((b'Stream params: %s\n' % _quasirepr(gen.params)))
     parttypes = opts.get('part_type', [])
     for part in gen.iterparts():
         if parttypes and part.type not in parttypes:
             continue
         msg = b'%s -- %s (mandatory: %r)\n'
         ui.write((msg % (part.type, _quasirepr(part.params), part.mandatory)))
         if part.type == b'changegroup':
             version = part.params.get(b'version', b'01')
             cg = changegroup.getunbundler(version, part, b'UN')
             if not ui.quiet:
                 _debugchangegroup(ui, cg, all=all, indent=4, **opts)
         if part.type == b'obsmarkers':
             if not ui.quiet:
                 _debugobsmarkers(ui, part, indent=4, **opts)
         if part.type == b'phase-heads':
             if not ui.quiet:
                 _debugphaseheads(ui, part, indent=4)
 
 
 @command(
     b'debugbundle',
     [
         (b'a', b'all', None, _(b'show all details')),
         (b'', b'part-type', [], _(b'show only the named part type')),
         (b'', b'spec', None, _(b'print the bundlespec of the bundle')),
     ],
     _(b'FILE'),
     norepo=True,
 )
 def debugbundle(ui, bundlepath, all=None, spec=None, **opts):
     """lists the contents of a bundle"""
     with hg.openpath(ui, bundlepath) as f:
         if spec:
             spec = exchange.getbundlespec(ui, f)
             ui.write(b'%s\n' % spec)
             return
 
         gen = exchange.readbundle(ui, f, bundlepath)
         if isinstance(gen, bundle2.unbundle20):
             return _debugbundle2(ui, gen, all=all, **opts)
         _debugchangegroup(ui, gen, all=all, **opts)
 
 
 @command(b'debugcapabilities', [], _(b'PATH'), norepo=True)
 def debugcapabilities(ui, path, **opts):
     """lists the capabilities of a remote peer"""
     opts = pycompat.byteskwargs(opts)
     peer = hg.peer(ui, opts, path)
     caps = peer.capabilities()
     ui.writenoi18n(b'Main capabilities:\n')
     for c in sorted(caps):
         ui.write(b'  %s\n' % c)
     b2caps = bundle2.bundle2caps(peer)
     if b2caps:
         ui.writenoi18n(b'Bundle2 capabilities:\n')
         for key, values in sorted(pycompat.iteritems(b2caps)):
             ui.write(b'  %s\n' % key)
             for v in values:
                 ui.write(b'    %s\n' % v)
 
 
 @command(b'debugcheckstate', [], b'')
 def debugcheckstate(ui, repo):
     """validate the correctness of the current dirstate"""
     parent1, parent2 = repo.dirstate.parents()
     m1 = repo[parent1].manifest()
     m2 = repo[parent2].manifest()
     errors = 0
     for f in repo.dirstate:
         state = repo.dirstate[f]
         if state in b"nr" and f not in m1:
             ui.warn(_(b"%s in state %s, but not in manifest1\n") % (f, state))
             errors += 1
         if state in b"a" and f in m1:
             ui.warn(_(b"%s in state %s, but also in manifest1\n") % (f, state))
             errors += 1
         if state in b"m" and f not in m1 and f not in m2:
             ui.warn(
                 _(b"%s in state %s, but not in either manifest\n") % (f, state)
             )
             errors += 1
     for f in m1:
         state = repo.dirstate[f]
         if state not in b"nrm":
             ui.warn(_(b"%s in manifest1, but listed as state %s") % (f, state))
             errors += 1
     if errors:
         errstr = _(b".hg/dirstate inconsistent with current parent's manifest")
         raise error.Abort(errstr)
 
 
 @command(
     b'debugcolor',
     [(b'', b'style', None, _(b'show all configured styles'))],
     b'hg debugcolor',
 )
 def debugcolor(ui, repo, **opts):
     """show available color, effects or style"""
     ui.writenoi18n(b'color mode: %s\n' % stringutil.pprint(ui._colormode))
     if opts.get('style'):
         return _debugdisplaystyle(ui)
     else:
         return _debugdisplaycolor(ui)
 
 
 def _debugdisplaycolor(ui):
     ui = ui.copy()
     ui._styles.clear()
     for effect in color._activeeffects(ui).keys():
         ui._styles[effect] = effect
     if ui._terminfoparams:
         for k, v in ui.configitems(b'color'):
             if k.startswith(b'color.'):
                 ui._styles[k] = k[6:]
             elif k.startswith(b'terminfo.'):
                 ui._styles[k] = k[9:]
     ui.write(_(b'available colors:\n'))
     # sort label with a '_' after the other to group '_background' entry.
     items = sorted(ui._styles.items(), key=lambda i: (b'_' in i[0], i[0], i[1]))
     for colorname, label in items:
         ui.write(b'%s\n' % colorname, label=label)
 
 
 def _debugdisplaystyle(ui):
     ui.write(_(b'available style:\n'))
     if not ui._styles:
         return
     width = max(len(s) for s in ui._styles)
     for label, effects in sorted(ui._styles.items()):
         ui.write(b'%s' % label, label=label)
         if effects:
             # 50
             ui.write(b': ')
             ui.write(b' ' * (max(0, width - len(label))))
             ui.write(b', '.join(ui.label(e, e) for e in effects.split()))
         ui.write(b'\n')
 
 
 @command(b'debugcreatestreamclonebundle', [], b'FILE')
 def debugcreatestreamclonebundle(ui, repo, fname):
     """create a stream clone bundle file
 
     Stream bundles are special bundles that are essentially archives of
     revlog files. They are commonly used for cloning very quickly.
     """
     # TODO we may want to turn this into an abort when this functionality
     # is moved into `hg bundle`.
     if phases.hassecret(repo):
         ui.warn(
             _(
                 b'(warning: stream clone bundle will contain secret '
                 b'revisions)\n'
             )
         )
 
     requirements, gen = streamclone.generatebundlev1(repo)
     changegroup.writechunks(ui, gen, fname)
 
     ui.write(_(b'bundle requirements: %s\n') % b', '.join(sorted(requirements)))
 
 
 @command(
     b'debugdag',
     [
         (b't', b'tags', None, _(b'use tags as labels')),
         (b'b', b'branches', None, _(b'annotate with branch names')),
         (b'', b'dots', None, _(b'use dots for runs')),
         (b's', b'spaces', None, _(b'separate elements by spaces')),
     ],
     _(b'[OPTION]... [FILE [REV]...]'),
     optionalrepo=True,
 )
 def debugdag(ui, repo, file_=None, *revs, **opts):
     """format the changelog or an index DAG as a concise textual description
 
     If you pass a revlog index, the revlog's DAG is emitted. If you list
     revision numbers, they get labeled in the output as rN.
 
     Otherwise, the changelog DAG of the current repo is emitted.
     """
     spaces = opts.get('spaces')
     dots = opts.get('dots')
     if file_:
         rlog = revlog.revlog(vfsmod.vfs(encoding.getcwd(), audit=False), file_)
         revs = set((int(r) for r in revs))
 
         def events():
             for r in rlog:
                 yield b'n', (r, list(p for p in rlog.parentrevs(r) if p != -1))
                 if r in revs:
                     yield b'l', (r, b"r%i" % r)
 
     elif repo:
         cl = repo.changelog
         tags = opts.get('tags')
         branches = opts.get('branches')
         if tags:
             labels = {}
             for l, n in repo.tags().items():
                 labels.setdefault(cl.rev(n), []).append(l)
 
         def events():
             b = b"default"
             for r in cl:
                 if branches:
                     newb = cl.read(cl.node(r))[5][b'branch']
                     if newb != b:
                         yield b'a', newb
                         b = newb
                 yield b'n', (r, list(p for p in cl.parentrevs(r) if p != -1))
                 if tags:
                     ls = labels.get(r)
                     if ls:
                         for l in ls:
                             yield b'l', (r, l)
 
     else:
         raise error.Abort(_(b'need repo for changelog dag'))
 
     for line in dagparser.dagtextlines(
         events(),
         addspaces=spaces,
         wraplabels=True,
         wrapannotations=True,
         wrapnonlinear=dots,
         usedots=dots,
         maxlinewidth=70,
     ):
         ui.write(line)
         ui.write(b"\n")
 
 
 @command(b'debugdata', cmdutil.debugrevlogopts, _(b'-c|-m|FILE REV'))
 def debugdata(ui, repo, file_, rev=None, **opts):
     """dump the contents of a data file revision"""
     opts = pycompat.byteskwargs(opts)
     if opts.get(b'changelog') or opts.get(b'manifest') or opts.get(b'dir'):
         if rev is not None:
             raise error.CommandError(b'debugdata', _(b'invalid arguments'))
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError(b'debugdata', _(b'invalid arguments'))
     r = cmdutil.openstorage(repo, b'debugdata', file_, opts)
     try:
         ui.write(r.rawdata(r.lookup(rev)))
     except KeyError:
         raise error.Abort(_(b'invalid revision identifier %s') % rev)
 
 
 @command(
     b'debugdate',
     [(b'e', b'extended', None, _(b'try extended date formats'))],
     _(b'[-e] DATE [RANGE]'),
     norepo=True,
     optionalrepo=True,
 )
 def debugdate(ui, date, range=None, **opts):
     """parse and display a date"""
     if opts["extended"]:
         d = dateutil.parsedate(date, dateutil.extendeddateformats)
     else:
         d = dateutil.parsedate(date)
     ui.writenoi18n(b"internal: %d %d\n" % d)
     ui.writenoi18n(b"standard: %s\n" % dateutil.datestr(d))
     if range:
         m = dateutil.matchdate(range)
         ui.writenoi18n(b"match: %s\n" % m(d[0]))
 
 
 @command(
     b'debugdeltachain',
     cmdutil.debugrevlogopts + cmdutil.formatteropts,
     _(b'-c|-m|FILE'),
     optionalrepo=True,
 )
 def debugdeltachain(ui, repo, file_=None, **opts):
     """dump information about delta chains in a revlog
 
     Output can be templatized. Available template keywords are:
 
     :``rev``:       revision number
     :``chainid``:   delta chain identifier (numbered by unique base)
     :``chainlen``:  delta chain length to this revision
     :``prevrev``:   previous revision in delta chain
     :``deltatype``: role of delta / how it was computed
     :``compsize``:  compressed size of revision
     :``uncompsize``: uncompressed size of revision
     :``chainsize``: total size of compressed revisions in chain
     :``chainratio``: total chain size divided by uncompressed revision size
                     (new delta chains typically start at ratio 2.00)
     :``lindist``:   linear distance from base revision in delta chain to end
                     of this revision
     :``extradist``: total size of revisions not part of this delta chain from
                     base of delta chain to end of this revision; a measurement
                     of how much extra data we need to read/seek across to read
                     the delta chain for this revision
     :``extraratio``: extradist divided by chainsize; another representation of
                     how much unrelated data is needed to load this delta chain
 
     If the repository is configured to use the sparse read, additional keywords
     are available:
 
     :``readsize``:     total size of data read from the disk for a revision
                        (sum of the sizes of all the blocks)
     :``largestblock``: size of the largest block of data read from the disk
     :``readdensity``:  density of useful bytes in the data read from the disk
     :``srchunks``:  in how many data hunks the whole revision would be read
 
     The sparse read can be enabled with experimental.sparse-read = True
     """
     opts = pycompat.byteskwargs(opts)
     r = cmdutil.openrevlog(repo, b'debugdeltachain', file_, opts)
     index = r.index
     start = r.start
     length = r.length
     generaldelta = r.version & revlog.FLAG_GENERALDELTA
     withsparseread = getattr(r, '_withsparseread', False)
 
     def revinfo(rev):
         e = index[rev]
         compsize = e[1]
         uncompsize = e[2]
         chainsize = 0
 
         if generaldelta:
             if e[3] == e[5]:
                 deltatype = b'p1'
             elif e[3] == e[6]:
                 deltatype = b'p2'
             elif e[3] == rev - 1:
                 deltatype = b'prev'
             elif e[3] == rev:
                 deltatype = b'base'
             else:
                 deltatype = b'other'
         else:
             if e[3] == rev:
                 deltatype = b'base'
             else:
                 deltatype = b'prev'
 
         chain = r._deltachain(rev)[0]
         for iterrev in chain:
             e = index[iterrev]
             chainsize += e[1]
 
         return compsize, uncompsize, deltatype, chain, chainsize
 
     fm = ui.formatter(b'debugdeltachain', opts)
 
     fm.plain(
         b'    rev  chain# chainlen     prev   delta       '
         b'size    rawsize  chainsize     ratio   lindist extradist '
         b'extraratio'
     )
     if withsparseread:
         fm.plain(b'   readsize largestblk rddensity srchunks')
     fm.plain(b'\n')
 
     chainbases = {}
     for rev in r:
         comp, uncomp, deltatype, chain, chainsize = revinfo(rev)
         chainbase = chain[0]
         chainid = chainbases.setdefault(chainbase, len(chainbases) + 1)
         basestart = start(chainbase)
         revstart = start(rev)
         lineardist = revstart + comp - basestart
         extradist = lineardist - chainsize
         try:
             prevrev = chain[-2]
         except IndexError:
             prevrev = -1
 
         if uncomp != 0:
             chainratio = float(chainsize) / float(uncomp)
         else:
             chainratio = chainsize
 
         if chainsize != 0:
             extraratio = float(extradist) / float(chainsize)
         else:
             extraratio = extradist
 
         fm.startitem()
         fm.write(
             b'rev chainid chainlen prevrev deltatype compsize '
             b'uncompsize chainsize chainratio lindist extradist '
             b'extraratio',
             b'%7d %7d %8d %8d %7s %10d %10d %10d %9.5f %9d %9d %10.5f',
             rev,
             chainid,
             len(chain),
             prevrev,
             deltatype,
             comp,
             uncomp,
             chainsize,
             chainratio,
             lineardist,
             extradist,
             extraratio,
             rev=rev,
             chainid=chainid,
             chainlen=len(chain),
             prevrev=prevrev,
             deltatype=deltatype,
             compsize=comp,
             uncompsize=uncomp,
             chainsize=chainsize,
             chainratio=chainratio,
             lindist=lineardist,
             extradist=extradist,
             extraratio=extraratio,
         )
         if withsparseread:
             readsize = 0
             largestblock = 0
             srchunks = 0
 
             for revschunk in deltautil.slicechunk(r, chain):
                 srchunks += 1
                 blkend = start(revschunk[-1]) + length(revschunk[-1])
                 blksize = blkend - start(revschunk[0])
 
                 readsize += blksize
                 if largestblock < blksize:
                     largestblock = blksize
 
             if readsize:
                 readdensity = float(chainsize) / float(readsize)
             else:
                 readdensity = 1
 
             fm.write(
                 b'readsize largestblock readdensity srchunks',
                 b' %10d %10d %9.5f %8d',
                 readsize,
                 largestblock,
                 readdensity,
                 srchunks,
                 readsize=readsize,
                 largestblock=largestblock,
                 readdensity=readdensity,
                 srchunks=srchunks,
             )
 
         fm.plain(b'\n')
 
     fm.end()
 
 
 @command(
     b'debugdirstate|debugstate',
     [
         (
             b'',
             b'nodates',
             None,
             _(b'do not display the saved mtime (DEPRECATED)'),
         ),
         (b'', b'dates', True, _(b'display the saved mtime')),
         (b'', b'datesort', None, _(b'sort by saved mtime')),
     ],
     _(b'[OPTION]...'),
 )
 def debugstate(ui, repo, **opts):
     """show the contents of the current dirstate"""
 
     nodates = not opts['dates']
     if opts.get('nodates') is not None:
         nodates = True
     datesort = opts.get('datesort')
 
     if datesort:
         keyfunc = lambda x: (x[1][3], x[0])  # sort by mtime, then by filename
     else:
         keyfunc = None  # sort by filename
     for file_, ent in sorted(pycompat.iteritems(repo.dirstate), key=keyfunc):
         if ent[3] == -1:
             timestr = b'unset               '
         elif nodates:
             timestr = b'set                 '
         else:
             timestr = time.strftime(
                 "%Y-%m-%d %H:%M:%S ", time.localtime(ent[3])
             )
             timestr = encoding.strtolocal(timestr)
         if ent[1] & 0o20000:
             mode = b'lnk'
         else:
             mode = b'%3o' % (ent[1] & 0o777 & ~util.umask)
         ui.write(b"%c %s %10d %s%s\n" % (ent[0], mode, ent[2], timestr, file_))
     for f in repo.dirstate.copies():
         ui.write(_(b"copy: %s -> %s\n") % (repo.dirstate.copied(f), f))
 
 
 @command(
     b'debugdiscovery',
     [
         (b'', b'old', None, _(b'use old-style discovery')),
         (
             b'',
             b'nonheads',
             None,
             _(b'use old-style discovery with non-heads included'),
         ),
         (b'', b'rev', [], b'restrict discovery to this set of revs'),
         (b'', b'seed', b'12323', b'specify the random seed use for discovery'),
     ]
     + cmdutil.remoteopts,
     _(b'[--rev REV] [OTHER]'),
 )
 def debugdiscovery(ui, repo, remoteurl=b"default", **opts):
     """runs the changeset discovery protocol in isolation"""
     opts = pycompat.byteskwargs(opts)
     remoteurl, branches = hg.parseurl(ui.expandpath(remoteurl))
     remote = hg.peer(repo, opts, remoteurl)
     ui.status(_(b'comparing with %s\n') % util.hidepassword(remoteurl))
 
     # make sure tests are repeatable
     random.seed(int(opts[b'seed']))
 
     if opts.get(b'old'):
 
         def doit(pushedrevs, remoteheads, remote=remote):
             if not util.safehasattr(remote, b'branches'):
                 # enable in-client legacy support
                 remote = localrepo.locallegacypeer(remote.local())
             common, _in, hds = treediscovery.findcommonincoming(
                 repo, remote, force=True
             )
             common = set(common)
             if not opts.get(b'nonheads'):
                 ui.writenoi18n(
                     b"unpruned common: %s\n"
                     % b" ".join(sorted(short(n) for n in common))
                 )
 
                 clnode = repo.changelog.node
                 common = repo.revs(b'heads(::%ln)', common)
                 common = {clnode(r) for r in common}
             return common, hds
 
     else:
 
         def doit(pushedrevs, remoteheads, remote=remote):
             nodes = None
             if pushedrevs:
                 revs = scmutil.revrange(repo, pushedrevs)
                 nodes = [repo[r].node() for r in revs]
             common, any, hds = setdiscovery.findcommonheads(
                 ui, repo, remote, ancestorsof=nodes
             )
             return common, hds
 
     remoterevs, _checkout = hg.addbranchrevs(repo, remote, branches, revs=None)
     localrevs = opts[b'rev']
     with util.timedcm('debug-discovery') as t:
         common, hds = doit(localrevs, remoterevs)
 
     # compute all statistics
     common = set(common)
     rheads = set(hds)
     lheads = set(repo.heads())
 
     data = {}
     data[b'elapsed'] = t.elapsed
     data[b'nb-common'] = len(common)
     data[b'nb-common-local'] = len(common & lheads)
     data[b'nb-common-remote'] = len(common & rheads)
     data[b'nb-common-both'] = len(common & rheads & lheads)
     data[b'nb-local'] = len(lheads)
     data[b'nb-local-missing'] = data[b'nb-local'] - data[b'nb-common-local']
     data[b'nb-remote'] = len(rheads)
     data[b'nb-remote-unknown'] = data[b'nb-remote'] - data[b'nb-common-remote']
     data[b'nb-revs'] = len(repo.revs(b'all()'))
     data[b'nb-revs-common'] = len(repo.revs(b'::%ln', common))
     data[b'nb-revs-missing'] = data[b'nb-revs'] - data[b'nb-revs-common']
 
     # display discovery summary
     ui.writenoi18n(b"elapsed time:  %(elapsed)f seconds\n" % data)
     ui.writenoi18n(b"heads summary:\n")
     ui.writenoi18n(b"  total common heads:  %(nb-common)9d\n" % data)
     ui.writenoi18n(b"    also local heads:  %(nb-common-local)9d\n" % data)
     ui.writenoi18n(b"    also remote heads: %(nb-common-remote)9d\n" % data)
     ui.writenoi18n(b"    both:              %(nb-common-both)9d\n" % data)
     ui.writenoi18n(b"  local heads:         %(nb-local)9d\n" % data)
     ui.writenoi18n(b"    common:            %(nb-common-local)9d\n" % data)
     ui.writenoi18n(b"    missing:           %(nb-local-missing)9d\n" % data)
     ui.writenoi18n(b"  remote heads:        %(nb-remote)9d\n" % data)
     ui.writenoi18n(b"    common:            %(nb-common-remote)9d\n" % data)
     ui.writenoi18n(b"    unknown:           %(nb-remote-unknown)9d\n" % data)
     ui.writenoi18n(b"local changesets:      %(nb-revs)9d\n" % data)
     ui.writenoi18n(b"  common:              %(nb-revs-common)9d\n" % data)
     ui.writenoi18n(b"  missing:             %(nb-revs-missing)9d\n" % data)
 
     if ui.verbose:
         ui.writenoi18n(
             b"common heads: %s\n" % b" ".join(sorted(short(n) for n in common))
         )
 
 
 _chunksize = 4 << 10
 
 
 @command(
     b'debugdownload', [(b'o', b'output', b'', _(b'path')),], optionalrepo=True
 )
 def debugdownload(ui, repo, url, output=None, **opts):
     """download a resource using Mercurial logic and config
     """
     fh = urlmod.open(ui, url, output)
 
     dest = ui
     if output:
         dest = open(output, b"wb", _chunksize)
     try:
         data = fh.read(_chunksize)
         while data:
             dest.write(data)
             data = fh.read(_chunksize)
     finally:
         if output:
             dest.close()
 
 
 @command(b'debugextensions', cmdutil.formatteropts, [], optionalrepo=True)
 def debugextensions(ui, repo, **opts):
     '''show information about active extensions'''
     opts = pycompat.byteskwargs(opts)
     exts = extensions.extensions(ui)
     hgver = util.version()
     fm = ui.formatter(b'debugextensions', opts)
     for extname, extmod in sorted(exts, key=operator.itemgetter(0)):
         isinternal = extensions.ismoduleinternal(extmod)
         extsource = None
 
         if util.safehasattr(extmod, '__file__'):
             extsource = pycompat.fsencode(extmod.__file__)
         elif getattr(sys, 'oxidized', False):
             extsource = pycompat.sysexecutable
         if isinternal:
             exttestedwith = []  # never expose magic string to users
         else:
             exttestedwith = getattr(extmod, 'testedwith', b'').split()
         extbuglink = getattr(extmod, 'buglink', None)
 
         fm.startitem()
 
         if ui.quiet or ui.verbose:
             fm.write(b'name', b'%s\n', extname)
         else:
             fm.write(b'name', b'%s', extname)
             if isinternal or hgver in exttestedwith:
                 fm.plain(b'\n')
             elif not exttestedwith:
                 fm.plain(_(b' (untested!)\n'))
             else:
                 lasttestedversion = exttestedwith[-1]
                 fm.plain(b' (%s!)\n' % lasttestedversion)
 
         fm.condwrite(
             ui.verbose and extsource,
             b'source',
             _(b'  location: %s\n'),
             extsource or b"",
         )
 
         if ui.verbose:
             fm.plain(_(b'  bundled: %s\n') % [b'no', b'yes'][isinternal])
         fm.data(bundled=isinternal)
 
         fm.condwrite(
             ui.verbose and exttestedwith,
             b'testedwith',
             _(b'  tested with: %s\n'),
             fm.formatlist(exttestedwith, name=b'ver'),
         )
 
         fm.condwrite(
             ui.verbose and extbuglink,
             b'buglink',
             _(b'  bug reporting: %s\n'),
             extbuglink or b"",
         )
 
     fm.end()
 
 
 @command(
     b'debugfileset',
     [
         (
             b'r',
             b'rev',
             b'',
             _(b'apply the filespec on this revision'),
             _(b'REV'),
         ),
         (
             b'',
             b'all-files',
             False,
             _(b'test files from all revisions and working directory'),
         ),
         (
             b's',
             b'show-matcher',
             None,
             _(b'print internal representation of matcher'),
         ),
         (
             b'p',
             b'show-stage',
             [],
             _(b'print parsed tree at the given stage'),
             _(b'NAME'),
         ),
     ],
     _(b'[-r REV] [--all-files] [OPTION]... FILESPEC'),
 )
 def debugfileset(ui, repo, expr, **opts):
     '''parse and apply a fileset specification'''
     from . import fileset
 
     fileset.symbols  # force import of fileset so we have predicates to optimize
     opts = pycompat.byteskwargs(opts)
     ctx = scmutil.revsingle(repo, opts.get(b'rev'), None)
 
     stages = [
         (b'parsed', pycompat.identity),
         (b'analyzed', filesetlang.analyze),
         (b'optimized', filesetlang.optimize),
     ]
     stagenames = set(n for n, f in stages)
 
     showalways = set()
     if ui.verbose and not opts[b'show_stage']:
         # show parsed tree by --verbose (deprecated)
         showalways.add(b'parsed')
     if opts[b'show_stage'] == [b'all']:
         showalways.update(stagenames)
     else:
         for n in opts[b'show_stage']:
             if n not in stagenames:
                 raise error.Abort(_(b'invalid stage name: %s') % n)
         showalways.update(opts[b'show_stage'])
 
     tree = filesetlang.parse(expr)
     for n, f in stages:
         tree = f(tree)
         if n in showalways:
             if opts[b'show_stage'] or n != b'parsed':
                 ui.write(b"* %s:\n" % n)
             ui.write(filesetlang.prettyformat(tree), b"\n")
 
     files = set()
     if opts[b'all_files']:
         for r in repo:
             c = repo[r]
             files.update(c.files())
             files.update(c.substate)
     if opts[b'all_files'] or ctx.rev() is None:
         wctx = repo[None]
         files.update(
             repo.dirstate.walk(
                 scmutil.matchall(repo),
                 subrepos=list(wctx.substate),
                 unknown=True,
                 ignored=True,
             )
         )
         files.update(wctx.substate)
     else:
         files.update(ctx.files())
         files.update(ctx.substate)
 
     m = ctx.matchfileset(repo.getcwd(), expr)
     if opts[b'show_matcher'] or (opts[b'show_matcher'] is None and ui.verbose):
         ui.writenoi18n(b'* matcher:\n', stringutil.prettyrepr(m), b'\n')
     for f in sorted(files):
         if not m(f):
             continue
         ui.write(b"%s\n" % f)
 
 
 @command(b'debugformat', [] + cmdutil.formatteropts)
 def debugformat(ui, repo, **opts):
     """display format information about the current repository
 
     Use --verbose to get extra information about current config value and
     Mercurial default."""
     opts = pycompat.byteskwargs(opts)
     maxvariantlength = max(len(fv.name) for fv in upgrade.allformatvariant)
     maxvariantlength = max(len(b'format-variant'), maxvariantlength)
 
     def makeformatname(name):
         return b'%s:' + (b' ' * (maxvariantlength - len(name)))
 
     fm = ui.formatter(b'debugformat', opts)
     if fm.isplain():
 
         def formatvalue(value):
             if util.safehasattr(value, b'startswith'):
                 return value
             if value:
                 return b'yes'
             else:
                 return b'no'
 
     else:
         formatvalue = pycompat.identity
 
     fm.plain(b'format-variant')
     fm.plain(b' ' * (maxvariantlength - len(b'format-variant')))
     fm.plain(b' repo')
     if ui.verbose:
         fm.plain(b' config default')
     fm.plain(b'\n')
     for fv in upgrade.allformatvariant:
         fm.startitem()
         repovalue = fv.fromrepo(repo)
         configvalue = fv.fromconfig(repo)
 
         if repovalue != configvalue:
             namelabel = b'formatvariant.name.mismatchconfig'
             repolabel = b'formatvariant.repo.mismatchconfig'
         elif repovalue != fv.default:
             namelabel = b'formatvariant.name.mismatchdefault'
             repolabel = b'formatvariant.repo.mismatchdefault'
         else:
             namelabel = b'formatvariant.name.uptodate'
             repolabel = b'formatvariant.repo.uptodate'
 
         fm.write(b'name', makeformatname(fv.name), fv.name, label=namelabel)
         fm.write(b'repo', b' %3s', formatvalue(repovalue), label=repolabel)
         if fv.default != configvalue:
             configlabel = b'formatvariant.config.special'
         else:
             configlabel = b'formatvariant.config.default'
         fm.condwrite(
             ui.verbose,
             b'config',
             b' %6s',
             formatvalue(configvalue),
             label=configlabel,
         )
         fm.condwrite(
             ui.verbose,
             b'default',
             b' %7s',
             formatvalue(fv.default),
             label=b'formatvariant.default',
         )
         fm.plain(b'\n')
     fm.end()
 
 
 @command(b'debugfsinfo', [], _(b'[PATH]'), norepo=True)
 def debugfsinfo(ui, path=b"."):
     """show information detected about current filesystem"""
     ui.writenoi18n(b'path: %s\n' % path)
     ui.writenoi18n(
         b'mounted on: %s\n' % (util.getfsmountpoint(path) or b'(unknown)')
     )
     ui.writenoi18n(b'exec: %s\n' % (util.checkexec(path) and b'yes' or b'no'))
     ui.writenoi18n(b'fstype: %s\n' % (util.getfstype(path) or b'(unknown)'))
     ui.writenoi18n(
         b'symlink: %s\n' % (util.checklink(path) and b'yes' or b'no')
     )
     ui.writenoi18n(
         b'hardlink: %s\n' % (util.checknlink(path) and b'yes' or b'no')
     )
     casesensitive = b'(unknown)'
     try:
         with pycompat.namedtempfile(prefix=b'.debugfsinfo', dir=path) as f:
             casesensitive = util.fscasesensitive(f.name) and b'yes' or b'no'
     except OSError:
         pass
     ui.writenoi18n(b'case-sensitive: %s\n' % casesensitive)
 
 
 @command(
     b'debuggetbundle',
     [
         (b'H', b'head', [], _(b'id of head node'), _(b'ID')),
         (b'C', b'common', [], _(b'id of common node'), _(b'ID')),
         (
             b't',
             b'type',
             b'bzip2',
             _(b'bundle compression type to use'),
             _(b'TYPE'),
         ),
     ],
     _(b'REPO FILE [-H|-C ID]...'),
     norepo=True,
 )
 def debuggetbundle(ui, repopath, bundlepath, head=None, common=None, **opts):
     """retrieves a bundle from a repo
 
     Every ID must be a full-length hex node id string. Saves the bundle to the
     given file.
     """
     opts = pycompat.byteskwargs(opts)
     repo = hg.peer(ui, opts, repopath)
     if not repo.capable(b'getbundle'):
         raise error.Abort(b"getbundle() not supported by target repository")
     args = {}
     if common:
         args['common'] = [bin(s) for s in common]
     if head:
         args['heads'] = [bin(s) for s in head]
     # TODO: get desired bundlecaps from command line.
     args['bundlecaps'] = None
     bundle = repo.getbundle(b'debug', **args)
 
     bundletype = opts.get(b'type', b'bzip2').lower()
     btypes = {
         b'none': b'HG10UN',
         b'bzip2': b'HG10BZ',
         b'gzip': b'HG10GZ',
         b'bundle2': b'HG20',
     }
     bundletype = btypes.get(bundletype)
     if bundletype not in bundle2.bundletypes:
         raise error.Abort(_(b'unknown bundle type specified with --type'))
     bundle2.writebundle(ui, bundle, bundlepath, bundletype)
 
 
 @command(b'debugignore', [], b'[FILE]')
 def debugignore(ui, repo, *files, **opts):
     """display the combined ignore pattern and information about ignored files
 
     With no argument display the combined ignore pattern.
 
     Given space separated file names, shows if the given file is ignored and
     if so, show the ignore rule (file and line number) that matched it.
     """
     ignore = repo.dirstate._ignore
     if not files:
         # Show all the patterns
         ui.write(b"%s\n" % pycompat.byterepr(ignore))
     else:
         m = scmutil.match(repo[None], pats=files)
         uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
         for f in m.files():
             nf = util.normpath(f)
             ignored = None
             ignoredata = None
             if nf != b'.':
                 if ignore(nf):
                     ignored = nf
                     ignoredata = repo.dirstate._ignorefileandline(nf)
                 else:
                     for p in pathutil.finddirs(nf):
                         if ignore(p):
                             ignored = p
                             ignoredata = repo.dirstate._ignorefileandline(p)
                             break
             if ignored:
                 if ignored == nf:
                     ui.write(_(b"%s is ignored\n") % uipathfn(f))
                 else:
                     ui.write(
                         _(
                             b"%s is ignored because of "
                             b"containing directory %s\n"
                         )
                         % (uipathfn(f), ignored)
                     )
                 ignorefile, lineno, line = ignoredata
                 ui.write(
                     _(b"(ignore rule in %s, line %d: '%s')\n")
                     % (ignorefile, lineno, line)
                 )
             else:
                 ui.write(_(b"%s is not ignored\n") % uipathfn(f))
 
 
 @command(
     b'debugindex',
     cmdutil.debugrevlogopts + cmdutil.formatteropts,
     _(b'-c|-m|FILE'),
 )
 def debugindex(ui, repo, file_=None, **opts):
     """dump index data for a storage primitive"""
     opts = pycompat.byteskwargs(opts)
     store = cmdutil.openstorage(repo, b'debugindex', file_, opts)
 
     if ui.debugflag:
         shortfn = hex
     else:
         shortfn = short
 
     idlen = 12
     for i in store:
         idlen = len(shortfn(store.node(i)))
         break
 
     fm = ui.formatter(b'debugindex', opts)
     fm.plain(
         b'   rev linkrev %s %s p2\n'
         % (b'nodeid'.ljust(idlen), b'p1'.ljust(idlen))
     )
 
     for rev in store:
         node = store.node(rev)
         parents = store.parents(node)
 
         fm.startitem()
         fm.write(b'rev', b'%6d ', rev)
         fm.write(b'linkrev', b'%7d ', store.linkrev(rev))
         fm.write(b'node', b'%s ', shortfn(node))
         fm.write(b'p1', b'%s ', shortfn(parents[0]))
         fm.write(b'p2', b'%s', shortfn(parents[1]))
         fm.plain(b'\n')
 
     fm.end()
 
 
 @command(
     b'debugindexdot',
     cmdutil.debugrevlogopts,
     _(b'-c|-m|FILE'),
     optionalrepo=True,
 )
 def debugindexdot(ui, repo, file_=None, **opts):
     """dump an index DAG as a graphviz dot file"""
     opts = pycompat.byteskwargs(opts)
     r = cmdutil.openstorage(repo, b'debugindexdot', file_, opts)
     ui.writenoi18n(b"digraph G {\n")
     for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write(b"\t%d -> %d\n" % (r.rev(pp[0]), i))
         if pp[1] != nullid:
             ui.write(b"\t%d -> %d\n" % (r.rev(pp[1]), i))
     ui.write(b"}\n")
 
 
 @command(b'debugindexstats', [])
 def debugindexstats(ui, repo):
     """show stats related to the changelog index"""
     repo.changelog.shortest(nullid, 1)
     index = repo.changelog.index
     if not util.safehasattr(index, b'stats'):
         raise error.Abort(_(b'debugindexstats only works with native code'))
     for k, v in sorted(index.stats().items()):
         ui.write(b'%s: %d\n' % (k, v))
 
 
 @command(b'debuginstall', [] + cmdutil.formatteropts, b'', norepo=True)
 def debuginstall(ui, **opts):
     '''test Mercurial installation
 
     Returns 0 on success.
     '''
     opts = pycompat.byteskwargs(opts)
 
     problems = 0
 
     fm = ui.formatter(b'debuginstall', opts)
     fm.startitem()
 
     # encoding
     fm.write(b'encoding', _(b"checking encoding (%s)...\n"), encoding.encoding)
     err = None
     try:
         codecs.lookup(pycompat.sysstr(encoding.encoding))
     except LookupError as inst:
         err = stringutil.forcebytestr(inst)
         problems += 1
     fm.condwrite(
         err,
         b'encodingerror',
         _(b" %s\n (check that your locale is properly set)\n"),
         err,
     )
 
     # Python
     pythonlib = None
     if util.safehasattr(os, '__file__'):
         pythonlib = os.path.dirname(pycompat.fsencode(os.__file__))
     elif getattr(sys, 'oxidized', False):
         pythonlib = pycompat.sysexecutable
 
     fm.write(
         b'pythonexe',
         _(b"checking Python executable (%s)\n"),
         pycompat.sysexecutable or _(b"unknown"),
     )
     fm.write(
         b'pythonimplementation',
         _(b"checking Python implementation (%s)\n"),
         pycompat.sysbytes(platform.python_implementation()),
     )
     fm.write(
         b'pythonver',
         _(b"checking Python version (%s)\n"),
         (b"%d.%d.%d" % sys.version_info[:3]),
     )
     fm.write(
         b'pythonlib',
         _(b"checking Python lib (%s)...\n"),
         pythonlib or _(b"unknown"),
     )
 
     security = set(sslutil.supportedprotocols)
     if sslutil.hassni:
         security.add(b'sni')
 
     fm.write(
         b'pythonsecurity',
         _(b"checking Python security support (%s)\n"),
         fm.formatlist(sorted(security), name=b'protocol', fmt=b'%s', sep=b','),
     )
 
     # These are warnings, not errors. So don't increment problem count. This
     # may change in the future.
     if b'tls1.2' not in security:
         fm.plain(
             _(
                 b'  TLS 1.2 not supported by Python install; '
                 b'network connections lack modern security\n'
             )
         )
     if b'sni' not in security:
         fm.plain(
             _(
                 b'  SNI not supported by Python install; may have '
                 b'connectivity issues with some servers\n'
             )
         )
 
     # TODO print CA cert info
 
     # hg version
     hgver = util.version()
     fm.write(
         b'hgver', _(b"checking Mercurial version (%s)\n"), hgver.split(b'+')[0]
     )
     fm.write(
         b'hgverextra',
         _(b"checking Mercurial custom build (%s)\n"),
         b'+'.join(hgver.split(b'+')[1:]),
     )
 
     # compiled modules
     hgmodules = None
     if util.safehasattr(sys.modules[__name__], '__file__'):
         hgmodules = os.path.dirname(pycompat.fsencode(__file__))
     elif getattr(sys, 'oxidized', False):
         hgmodules = pycompat.sysexecutable
 
     fm.write(
         b'hgmodulepolicy', _(b"checking module policy (%s)\n"), policy.policy
     )
     fm.write(
         b'hgmodules',
         _(b"checking installed modules (%s)...\n"),
         hgmodules or _(b"unknown"),
     )
 
     rustandc = policy.policy in (b'rust+c', b'rust+c-allow')
     rustext = rustandc  # for now, that's the only case
     cext = policy.policy in (b'c', b'allow') or rustandc
     nopure = cext or rustext
     if nopure:
         err = None
         try:
             if cext:
                 from .cext import (  # pytype: disable=import-error
                     base85,
                     bdiff,
                     mpatch,
                     osutil,
                 )
 
                 # quiet pyflakes
                 dir(bdiff), dir(mpatch), dir(base85), dir(osutil)
             if rustext:
                 from .rustext import (  # pytype: disable=import-error
                     ancestor,
                     dirstate,
                 )
 
                 dir(ancestor), dir(dirstate)  # quiet pyflakes
         except Exception as inst:
             err = stringutil.forcebytestr(inst)
             problems += 1
         fm.condwrite(err, b'extensionserror', b" %s\n", err)
 
     compengines = util.compengines._engines.values()
     fm.write(
         b'compengines',
         _(b'checking registered compression engines (%s)\n'),
         fm.formatlist(
             sorted(e.name() for e in compengines),
             name=b'compengine',
             fmt=b'%s',
             sep=b', ',
         ),
     )
     fm.write(
         b'compenginesavail',
         _(b'checking available compression engines (%s)\n'),
         fm.formatlist(
             sorted(e.name() for e in compengines if e.available()),
             name=b'compengine',
             fmt=b'%s',
             sep=b', ',
         ),
     )
     wirecompengines = compression.compengines.supportedwireengines(
         compression.SERVERROLE
     )
     fm.write(
         b'compenginesserver',
         _(
             b'checking available compression engines '
             b'for wire protocol (%s)\n'
         ),
         fm.formatlist(
             [e.name() for e in wirecompengines if e.wireprotosupport()],
             name=b'compengine',
             fmt=b'%s',
             sep=b', ',
         ),
     )
     re2 = b'missing'
     if util._re2:
         re2 = b'available'
     fm.plain(_(b'checking "re2" regexp engine (%s)\n') % re2)
     fm.data(re2=bool(util._re2))
 
     # templates
     p = templater.templatepaths()
     fm.write(b'templatedirs', b'checking templates (%s)...\n', b' '.join(p))
     fm.condwrite(not p, b'', _(b" no template directories found\n"))
     if p:
         m = templater.templatepath(b"map-cmdline.default")
         if m:
             # template found, check if it is working
             err = None
             try:
                 templater.templater.frommapfile(m)
             except Exception as inst:
                 err = stringutil.forcebytestr(inst)
                 p = None
             fm.condwrite(err, b'defaulttemplateerror', b" %s\n", err)
         else:
             p = None
         fm.condwrite(
             p, b'defaulttemplate', _(b"checking default template (%s)\n"), m
         )
         fm.condwrite(
             not m,
             b'defaulttemplatenotfound',
             _(b" template '%s' not found\n"),
             b"default",
         )
     if not p:
         problems += 1
     fm.condwrite(
         not p, b'', _(b" (templates seem to have been installed incorrectly)\n")
     )
 
     # editor
     editor = ui.geteditor()
     editor = util.expandpath(editor)
     editorbin = procutil.shellsplit(editor)[0]
     fm.write(b'editor', _(b"checking commit editor... (%s)\n"), editorbin)
     cmdpath = procutil.findexe(editorbin)
     fm.condwrite(
         not cmdpath and editor == b'vi',
         b'vinotfound',
         _(
             b" No commit editor set and can't find %s in PATH\n"
             b" (specify a commit editor in your configuration"
             b" file)\n"
         ),
         not cmdpath and editor == b'vi' and editorbin,
     )
     fm.condwrite(
         not cmdpath and editor != b'vi',
         b'editornotfound',
         _(
             b" Can't find editor '%s' in PATH\n"
             b" (specify a commit editor in your configuration"
             b" file)\n"
         ),
         not cmdpath and editorbin,
     )
     if not cmdpath and editor != b'vi':
         problems += 1
 
     # check username
     username = None
     err = None
     try:
         username = ui.username()
     except error.Abort as e:
         err = stringutil.forcebytestr(e)
         problems += 1
 
     fm.condwrite(
         username, b'username', _(b"checking username (%s)\n"), username
     )
     fm.condwrite(
         err,
         b'usernameerror',
         _(
             b"checking username...\n %s\n"
             b" (specify a username in your configuration file)\n"
         ),
         err,
     )
 
     for name, mod in extensions.extensions():
         handler = getattr(mod, 'debuginstall', None)
         if handler is not None:
             problems += handler(ui, fm)
 
     fm.condwrite(not problems, b'', _(b"no problems detected\n"))
     if not problems:
         fm.data(problems=problems)
     fm.condwrite(
         problems,
         b'problems',
         _(b"%d problems detected, please check your install!\n"),
         problems,
     )
     fm.end()
 
     return problems
 
 
 @command(b'debugknown', [], _(b'REPO ID...'), norepo=True)
 def debugknown(ui, repopath, *ids, **opts):
     """test whether node ids are known to a repo
 
     Every ID must be a full-length hex node id string. Returns a list of 0s
     and 1s indicating unknown/known.
     """
     opts = pycompat.byteskwargs(opts)
     repo = hg.peer(ui, opts, repopath)
     if not repo.capable(b'known'):
         raise error.Abort(b"known() not supported by target repository")
     flags = repo.known([bin(s) for s in ids])
     ui.write(b"%s\n" % (b"".join([f and b"1" or b"0" for f in flags])))
 
 
 @command(b'debuglabelcomplete', [], _(b'LABEL...'))
 def debuglabelcomplete(ui, repo, *args):
     '''backwards compatibility with old bash completion scripts (DEPRECATED)'''
     debugnamecomplete(ui, repo, *args)
 
 
 @command(
     b'debuglocks',
     [
         (b'L', b'force-lock', None, _(b'free the store lock (DANGEROUS)')),
         (
             b'W',
             b'force-wlock',
             None,
             _(b'free the working state lock (DANGEROUS)'),
         ),
         (b's', b'set-lock', None, _(b'set the store lock until stopped')),
         (
             b'S',
             b'set-wlock',
             None,
             _(b'set the working state lock until stopped'),
         ),
     ],
     _(b'[OPTION]...'),
 )
 def debuglocks(ui, repo, **opts):
     """show or modify state of locks
 
     By default, this command will show which locks are held. This
     includes the user and process holding the lock, the amount of time
     the lock has been held, and the machine name where the process is
     running if it's not local.
 
     Locks protect the integrity of Mercurial's data, so should be
     treated with care. System crashes or other interruptions may cause
     locks to not be properly released, though Mercurial will usually
     detect and remove such stale locks automatically.
 
     However, detecting stale locks may not always be possible (for
     instance, on a shared filesystem). Removing locks may also be
     blocked by filesystem permissions.
 
     Setting a lock will prevent other commands from changing the data.
     The command will wait until an interruption (SIGINT, SIGTERM, ...) occurs.
     The set locks are removed when the command exits.
 
     Returns 0 if no locks are held.
 
     """
 
     if opts.get('force_lock'):
         repo.svfs.unlink(b'lock')
     if opts.get('force_wlock'):
         repo.vfs.unlink(b'wlock')
     if opts.get('force_lock') or opts.get('force_wlock'):
         return 0
 
     locks = []
     try:
         if opts.get('set_wlock'):
             try:
                 locks.append(repo.wlock(False))
             except error.LockHeld:
                 raise error.Abort(_(b'wlock is already held'))
         if opts.get('set_lock'):
             try:
                 locks.append(repo.lock(False))
             except error.LockHeld:
                 raise error.Abort(_(b'lock is already held'))
         if len(locks):
             ui.promptchoice(_(b"ready to release the lock (y)? $$ &Yes"))
             return 0
     finally:
         release(*locks)
 
     now = time.time()
     held = 0
 
     def report(vfs, name, method):
         # this causes stale locks to get reaped for more accurate reporting
         try:
             l = method(False)
         except error.LockHeld:
             l = None
 
         if l:
             l.release()
         else:
             try:
                 st = vfs.lstat(name)
                 age = now - st[stat.ST_MTIME]
                 user = util.username(st.st_uid)
                 locker = vfs.readlock(name)
                 if b":" in locker:
                     host, pid = locker.split(b':')
                     if host == socket.gethostname():
                         locker = b'user %s, process %s' % (user or b'None', pid)
                     else:
                         locker = b'user %s, process %s, host %s' % (
                             user or b'None',
                             pid,
                             host,
                         )
                 ui.writenoi18n(b"%-6s %s (%ds)\n" % (name + b":", locker, age))
                 return 1
             except OSError as e:
                 if e.errno != errno.ENOENT:
                     raise
 
         ui.writenoi18n(b"%-6s free\n" % (name + b":"))
         return 0
 
     held += report(repo.svfs, b"lock", repo.lock)
     held += report(repo.vfs, b"wlock", repo.wlock)
 
     return held
 
 
 @command(
     b'debugmanifestfulltextcache',
     [
         (b'', b'clear', False, _(b'clear the cache')),
         (
             b'a',
             b'add',
             [],
             _(b'add the given manifest nodes to the cache'),
             _(b'NODE'),
         ),
     ],
     b'',
 )
 def debugmanifestfulltextcache(ui, repo, add=(), **opts):
     """show, clear or amend the contents of the manifest fulltext cache"""
 
     def getcache():
         r = repo.manifestlog.getstorage(b'')
         try:
             return r._fulltextcache
         except AttributeError:
             msg = _(
                 b"Current revlog implementation doesn't appear to have a "
                 b"manifest fulltext cache\n"
             )
             raise error.Abort(msg)
 
     if opts.get('clear'):
         with repo.wlock():
             cache = getcache()
             cache.clear(clear_persisted_data=True)
             return
 
     if add:
         with repo.wlock():
             m = repo.manifestlog
             store = m.getstorage(b'')
             for n in add:
                 try:
                     manifest = m[store.lookup(n)]
                 except error.LookupError as e:
                     raise error.Abort(e, hint=b"Check your manifest node id")
                 manifest.read()  # stores revisision in cache too
             return
 
     cache = getcache()
     if not len(cache):
         ui.write(_(b'cache empty\n'))
     else:
         ui.write(
             _(
                 b'cache contains %d manifest entries, in order of most to '
                 b'least recent:\n'
             )
             % (len(cache),)
         )
         totalsize = 0
         for nodeid in cache:
             # Use cache.get to not update the LRU order
             data = cache.peek(nodeid)
             size = len(data)
             totalsize += size + 24  # 20 bytes nodeid, 4 bytes size
             ui.write(
                 _(b'id: %s, size %s\n') % (hex(nodeid), util.bytecount(size))
             )
         ondisk = cache._opener.stat(b'manifestfulltextcache').st_size
         ui.write(
             _(b'total cache data size %s, on-disk %s\n')
             % (util.bytecount(totalsize), util.bytecount(ondisk))
         )
 
 
 @command(b'debugmergestate', [], b'')
 def debugmergestate(ui, repo, *args):
     """print merge state
 
     Use --verbose to print out information about whether v1 or v2 merge state
     was chosen."""
 
     def _hashornull(h):
         if h == nullhex:
             return b'null'
         else:
             return h
 
     def printrecords(version):
         ui.writenoi18n(b'* version %d records\n' % version)
         if version == 1:
             records = v1records
         else:
             records = v2records
 
         for rtype, record in records:
             # pretty print some record types
             if rtype == b'L':
                 ui.writenoi18n(b'local: %s\n' % record)
             elif rtype == b'O':
                 ui.writenoi18n(b'other: %s\n' % record)
             elif rtype == b'm':
                 driver, mdstate = record.split(b'\0', 1)
                 ui.writenoi18n(
                     b'merge driver: %s (state "%s")\n' % (driver, mdstate)
                 )
             elif rtype in b'FDC':
                 r = record.split(b'\0')
                 f, state, hash, lfile, afile, anode, ofile = r[0:7]
                 if version == 1:
                     onode = b'not stored in v1 format'
                     flags = r[7]
                 else:
                     onode, flags = r[7:9]
                 ui.writenoi18n(
                     b'file: %s (record type "%s", state "%s", hash %s)\n'
                     % (f, rtype, state, _hashornull(hash))
                 )
                 ui.writenoi18n(
                     b'  local path: %s (flags "%s")\n' % (lfile, flags)
                 )
                 ui.writenoi18n(
                     b'  ancestor path: %s (node %s)\n'
                     % (afile, _hashornull(anode))
                 )
                 ui.writenoi18n(
                     b'  other path: %s (node %s)\n'
                     % (ofile, _hashornull(onode))
                 )
             elif rtype == b'f':
                 filename, rawextras = record.split(b'\0', 1)
                 extras = rawextras.split(b'\0')
                 i = 0
                 extrastrings = []
                 while i < len(extras):
                     extrastrings.append(b'%s = %s' % (extras[i], extras[i + 1]))
                     i += 2
 
                 ui.writenoi18n(
                     b'file extras: %s (%s)\n'
                     % (filename, b', '.join(extrastrings))
                 )
             elif rtype == b'l':
                 labels = record.split(b'\0', 2)
                 labels = [l for l in labels if len(l) > 0]
                 ui.writenoi18n(b'labels:\n')
                 ui.write((b'  local: %s\n' % labels[0]))
                 ui.write((b'  other: %s\n' % labels[1]))
                 if len(labels) > 2:
                     ui.write((b'  base:  %s\n' % labels[2]))
             else:
                 ui.writenoi18n(
                     b'unrecognized entry: %s\t%s\n'
                     % (rtype, record.replace(b'\0', b'\t'))
                 )
 
     # Avoid mergestate.read() since it may raise an exception for unsupported
     # merge state records. We shouldn't be doing this, but this is OK since this
     # command is pretty low-level.
     ms = mergemod.mergestate(repo)
 
     # sort so that reasonable information is on top
     v1records = ms._readrecordsv1()
     v2records = ms._readrecordsv2()
     order = b'LOml'
 
     def key(r):
         idx = order.find(r[0])
         if idx == -1:
             return (1, r[1])
         else:
             return (0, idx)
 
     v1records.sort(key=key)
     v2records.sort(key=key)
 
     if not v1records and not v2records:
         ui.writenoi18n(b'no merge state found\n')
     elif not v2records:
         ui.notenoi18n(b'no version 2 merge state\n')
         printrecords(1)
     elif ms._v1v2match(v1records, v2records):
         ui.notenoi18n(b'v1 and v2 states match: using v2\n')
         printrecords(2)
     else:
         ui.notenoi18n(b'v1 and v2 states mismatch: using v1\n')
         printrecords(1)
         if ui.verbose:
             printrecords(2)
 
 
 @command(b'debugnamecomplete', [], _(b'NAME...'))
 def debugnamecomplete(ui, repo, *args):
     '''complete "names" - tags, open branch names, bookmark names'''
 
     names = set()
     # since we previously only listed open branches, we will handle that
     # specially (after this for loop)
     for name, ns in pycompat.iteritems(repo.names):
         if name != b'branches':
             names.update(ns.listnames(repo))
     names.update(
         tag
         for (tag, heads, tip, closed) in repo.branchmap().iterbranches()
         if not closed
     )
     completions = set()
     if not args:
         args = [b'']
     for a in args:
         completions.update(n for n in names if n.startswith(a))
     ui.write(b'\n'.join(sorted(completions)))
     ui.write(b'\n')
 
 
 @command(
     b'debugnodemap',
     [
         (
             b'',
             b'dump-new',
             False,
             _(b'write a (new) persistent binary nodemap on stdin'),
         ),
         (b'', b'dump-disk', False, _(b'dump on-disk data on stdin')),
         (
             b'',
             b'check',
             False,
             _(b'check that the data on disk data are correct.'),
         ),
         (
             b'',
             b'metadata',
             False,
             _(b'display the on disk meta data for the nodemap'),
         ),
     ],
 )
 def debugnodemap(ui, repo, **opts):
     """write and inspect on disk nodemap
     """
     if opts['dump_new']:
         unfi = repo.unfiltered()
         cl = unfi.changelog
         data = nodemap.persistent_data(cl.index)
         ui.write(data)
     elif opts['dump_disk']:
         unfi = repo.unfiltered()
         cl = unfi.changelog
         nm_data = nodemap.persisted_data(cl)
         if nm_data is not None:
             docket, data = nm_data
             ui.write(data)
     elif opts['check']:
         unfi = repo.unfiltered()
         cl = unfi.changelog
         nm_data = nodemap.persisted_data(cl)
         if nm_data is not None:
             docket, data = nm_data
             return nodemap.check_data(ui, cl.index, data)
     elif opts['metadata']:
         unfi = repo.unfiltered()
         cl = unfi.changelog
         nm_data = nodemap.persisted_data(cl)
         if nm_data is not None:
             docket, data = nm_data
             ui.write((b"uid: %s\n") % docket.uid)
+            ui.write((b"tip-rev: %d\n") % docket.tip_rev)
 
 
 @command(
     b'debugobsolete',
     [
         (b'', b'flags', 0, _(b'markers flag')),
         (
             b'',
             b'record-parents',
             False,
             _(b'record parent information for the precursor'),
         ),
         (b'r', b'rev', [], _(b'display markers relevant to REV')),
         (
             b'',
             b'exclusive',
             False,
             _(b'restrict display to markers only relevant to REV'),
         ),
         (b'', b'index', False, _(b'display index of the marker')),
         (b'', b'delete', [], _(b'delete markers specified by indices')),
     ]
     + cmdutil.commitopts2
     + cmdutil.formatteropts,
     _(b'[OBSOLETED [REPLACEMENT ...]]'),
 )
 def debugobsolete(ui, repo, precursor=None, *successors, **opts):
     """create arbitrary obsolete marker
 
     With no arguments, displays the list of obsolescence markers."""
 
     opts = pycompat.byteskwargs(opts)
 
     def parsenodeid(s):
         try:
             # We do not use revsingle/revrange functions here to accept
             # arbitrary node identifiers, possibly not present in the
             # local repository.
             n = bin(s)
             if len(n) != len(nullid):
                 raise TypeError()
             return n
         except TypeError:
             raise error.Abort(
                 b'changeset references must be full hexadecimal '
                 b'node identifiers'
             )
 
     if opts.get(b'delete'):
         indices = []
         for v in opts.get(b'delete'):
             try:
                 indices.append(int(v))
             except ValueError:
                 raise error.Abort(
                     _(b'invalid index value: %r') % v,
                     hint=_(b'use integers for indices'),
                 )
 
         if repo.currenttransaction():
             raise error.Abort(
                 _(b'cannot delete obsmarkers in the middle of transaction.')
             )
 
         with repo.lock():
             n = repair.deleteobsmarkers(repo.obsstore, indices)
             ui.write(_(b'deleted %i obsolescence markers\n') % n)
 
         return
 
     if precursor is not None:
         if opts[b'rev']:
             raise error.Abort(b'cannot select revision when creating marker')
         metadata = {}
         metadata[b'user'] = encoding.fromlocal(opts[b'user'] or ui.username())
         succs = tuple(parsenodeid(succ) for succ in successors)
         l = repo.lock()
         try:
             tr = repo.transaction(b'debugobsolete')
             try:
                 date = opts.get(b'date')
                 if date:
                     date = dateutil.parsedate(date)
                 else:
                     date = None
                 prec = parsenodeid(precursor)
                 parents = None
                 if opts[b'record_parents']:
                     if prec not in repo.unfiltered():
                         raise error.Abort(
                             b'cannot used --record-parents on '
                             b'unknown changesets'
                         )
                     parents = repo.unfiltered()[prec].parents()
                     parents = tuple(p.node() for p in parents)
                 repo.obsstore.create(
                     tr,
                     prec,
                     succs,
                     opts[b'flags'],
                     parents=parents,
                     date=date,
                     metadata=metadata,
                     ui=ui,
                 )
                 tr.close()
             except ValueError as exc:
                 raise error.Abort(
                     _(b'bad obsmarker input: %s') % pycompat.bytestr(exc)
                 )
             finally:
                 tr.release()
         finally:
             l.release()
     else:
         if opts[b'rev']:
             revs = scmutil.revrange(repo, opts[b'rev'])
             nodes = [repo[r].node() for r in revs]
             markers = list(
                 obsutil.getmarkers(
                     repo, nodes=nodes, exclusive=opts[b'exclusive']
                 )
             )
             markers.sort(key=lambda x: x._data)
         else:
             markers = obsutil.getmarkers(repo)
 
         markerstoiter = markers
         isrelevant = lambda m: True
         if opts.get(b'rev') and opts.get(b'index'):
             markerstoiter = obsutil.getmarkers(repo)
             markerset = set(markers)
             isrelevant = lambda m: m in markerset
 
         fm = ui.formatter(b'debugobsolete', opts)
         for i, m in enumerate(markerstoiter):
             if not isrelevant(m):
                 # marker can be irrelevant when we're iterating over a set
                 # of markers (markerstoiter) which is bigger than the set
                 # of markers we want to display (markers)
                 # this can happen if both --index and --rev options are
                 # provided and thus we need to iterate over all of the markers
                 # to get the correct indices, but only display the ones that
                 # are relevant to --rev value
                 continue
             fm.startitem()
             ind = i if opts.get(b'index') else None
             cmdutil.showmarker(fm, m, index=ind)
         fm.end()
 
 
 @command(
     b'debugp1copies',
     [(b'r', b'rev', b'', _(b'revision to debug'), _(b'REV'))],
     _(b'[-r REV]'),
 )
 def debugp1copies(ui, repo, **opts):
     """dump copy information compared to p1"""
 
     opts = pycompat.byteskwargs(opts)
     ctx = scmutil.revsingle(repo, opts.get(b'rev'), default=None)
     for dst, src in ctx.p1copies().items():
         ui.write(b'%s -> %s\n' % (src, dst))
 
 
 @command(
     b'debugp2copies',
     [(b'r', b'rev', b'', _(b'revision to debug'), _(b'REV'))],
     _(b'[-r REV]'),
 )
 def debugp1copies(ui, repo, **opts):
     """dump copy information compared to p2"""
 
     opts = pycompat.byteskwargs(opts)
     ctx = scmutil.revsingle(repo, opts.get(b'rev'), default=None)
     for dst, src in ctx.p2copies().items():
         ui.write(b'%s -> %s\n' % (src, dst))
 
 
 @command(
     b'debugpathcomplete',
     [
         (b'f', b'full', None, _(b'complete an entire path')),
         (b'n', b'normal', None, _(b'show only normal files')),
         (b'a', b'added', None, _(b'show only added files')),
         (b'r', b'removed', None, _(b'show only removed files')),
     ],
     _(b'FILESPEC...'),
 )
 def debugpathcomplete(ui, repo, *specs, **opts):
     '''complete part or all of a tracked path
 
     This command supports shells that offer path name completion. It
     currently completes only files already known to the dirstate.
 
     Completion extends only to the next path segment unless
     --full is specified, in which case entire paths are used.'''
 
     def complete(path, acceptable):
         dirstate = repo.dirstate
         spec = os.path.normpath(os.path.join(encoding.getcwd(), path))
         rootdir = repo.root + pycompat.ossep
         if spec != repo.root and not spec.startswith(rootdir):
             return [], []
         if os.path.isdir(spec):
             spec += b'/'
         spec = spec[len(rootdir) :]
         fixpaths = pycompat.ossep != b'/'
         if fixpaths:
             spec = spec.replace(pycompat.ossep, b'/')
         speclen = len(spec)
         fullpaths = opts['full']
         files, dirs = set(), set()
         adddir, addfile = dirs.add, files.add
         for f, st in pycompat.iteritems(dirstate):
             if f.startswith(spec) and st[0] in acceptable:
                 if fixpaths:
                     f = f.replace(b'/', pycompat.ossep)
                 if fullpaths:
                     addfile(f)
                     continue
                 s = f.find(pycompat.ossep, speclen)
                 if s >= 0:
                     adddir(f[:s])
                 else:
                     addfile(f)
         return files, dirs
 
     acceptable = b''
     if opts['normal']:
         acceptable += b'nm'
     if opts['added']:
         acceptable += b'a'
     if opts['removed']:
         acceptable += b'r'
     cwd = repo.getcwd()
     if not specs:
         specs = [b'.']
 
     files, dirs = set(), set()
     for spec in specs:
         f, d = complete(spec, acceptable or b'nmar')
         files.update(f)
         dirs.update(d)
     files.update(dirs)
     ui.write(b'\n'.join(repo.pathto(p, cwd) for p in sorted(files)))
     ui.write(b'\n')
 
 
 @command(
     b'debugpathcopies',
     cmdutil.walkopts,
     b'hg debugpathcopies REV1 REV2 [FILE]',
     inferrepo=True,
 )
 def debugpathcopies(ui, repo, rev1, rev2, *pats, **opts):
     """show copies between two revisions"""
     ctx1 = scmutil.revsingle(repo, rev1)
     ctx2 = scmutil.revsingle(repo, rev2)
     m = scmutil.match(ctx1, pats, opts)
     for dst, src in sorted(copies.pathcopies(ctx1, ctx2, m).items()):
         ui.write(b'%s -> %s\n' % (src, dst))
 
 
 @command(b'debugpeer', [], _(b'PATH'), norepo=True)
 def debugpeer(ui, path):
     """establish a connection to a peer repository"""
     # Always enable peer request logging. Requires --debug to display
     # though.
     overrides = {
         (b'devel', b'debug.peer-request'): True,
     }
 
     with ui.configoverride(overrides):
         peer = hg.peer(ui, {}, path)
 
         local = peer.local() is not None
         canpush = peer.canpush()
 
         ui.write(_(b'url: %s\n') % peer.url())
         ui.write(_(b'local: %s\n') % (_(b'yes') if local else _(b'no')))
         ui.write(_(b'pushable: %s\n') % (_(b'yes') if canpush else _(b'no')))
 
 
 @command(
     b'debugpickmergetool',
     [
         (b'r', b'rev', b'', _(b'check for files in this revision'), _(b'REV')),
         (b'', b'changedelete', None, _(b'emulate merging change and delete')),
     ]
     + cmdutil.walkopts
     + cmdutil.mergetoolopts,
     _(b'[PATTERN]...'),
     inferrepo=True,
 )
 def debugpickmergetool(ui, repo, *pats, **opts):
     """examine which merge tool is chosen for specified file
 
     As described in :hg:`help merge-tools`, Mercurial examines
     configurations below in this order to decide which merge tool is
     chosen for specified file.
 
     1. ``--tool`` option
     2. ``HGMERGE`` environment variable
     3. configurations in ``merge-patterns`` section
     4. configuration of ``ui.merge``
     5. configurations in ``merge-tools`` section
     6. ``hgmerge`` tool (for historical reason only)
     7. default tool for fallback (``:merge`` or ``:prompt``)
 
     This command writes out examination result in the style below::
 
         FILE = MERGETOOL
 
     By default, all files known in the first parent context of the
     working directory are examined. Use file patterns and/or -I/-X
     options to limit target files. -r/--rev is also useful to examine
     files in another context without actual updating to it.
 
     With --debug, this command shows warning messages while matching
     against ``merge-patterns`` and so on, too. It is recommended to
     use this option with explicit file patterns and/or -I/-X options,
     because this option increases amount of output per file according
     to configurations in hgrc.
 
     With -v/--verbose, this command shows configurations below at
     first (only if specified).
 
     - ``--tool`` option
     - ``HGMERGE`` environment variable
     - configuration of ``ui.merge``
 
     If merge tool is chosen before matching against
     ``merge-patterns``, this command can't show any helpful
     information, even with --debug. In such case, information above is
     useful to know why a merge tool is chosen.
     """
     opts = pycompat.byteskwargs(opts)
     overrides = {}
     if opts[b'tool']:
         overrides[(b'ui', b'forcemerge')] = opts[b'tool']
         ui.notenoi18n(b'with --tool %r\n' % (pycompat.bytestr(opts[b'tool'])))
 
     with ui.configoverride(overrides, b'debugmergepatterns'):
         hgmerge = encoding.environ.get(b"HGMERGE")
         if hgmerge is not None:
             ui.notenoi18n(b'with HGMERGE=%r\n' % (pycompat.bytestr(hgmerge)))
         uimerge = ui.config(b"ui", b"merge")
         if uimerge:
             ui.notenoi18n(b'with ui.merge=%r\n' % (pycompat.bytestr(uimerge)))
 
         ctx = scmutil.revsingle(repo, opts.get(b'rev'))
         m = scmutil.match(ctx, pats, opts)
         changedelete = opts[b'changedelete']
         for path in ctx.walk(m):
             fctx = ctx[path]
             try:
                 if not ui.debugflag:
                     ui.pushbuffer(error=True)
                 tool, toolpath = filemerge._picktool(
                     repo,
                     ui,
                     path,
                     fctx.isbinary(),
                     b'l' in fctx.flags(),
                     changedelete,
                 )
             finally:
                 if not ui.debugflag:
                     ui.popbuffer()
             ui.write(b'%s = %s\n' % (path, tool))
 
 
 @command(b'debugpushkey', [], _(b'REPO NAMESPACE [KEY OLD NEW]'), norepo=True)
 def debugpushkey(ui, repopath, namespace, *keyinfo, **opts):
     '''access the pushkey key/value protocol
 
     With two args, list the keys in the given namespace.
 
     With five args, set a key to new if it currently is set to old.
     Reports success or failure.
     '''
 
     target = hg.peer(ui, {}, repopath)
     if keyinfo:
         key, old, new = keyinfo
         with target.commandexecutor() as e:
             r = e.callcommand(
                 b'pushkey',
                 {
                     b'namespace': namespace,
                     b'key': key,
                     b'old': old,
                     b'new': new,
                 },
             ).result()
 
         ui.status(pycompat.bytestr(r) + b'\n')
         return not r
     else:
         for k, v in sorted(pycompat.iteritems(target.listkeys(namespace))):
             ui.write(
                 b"%s\t%s\n" % (stringutil.escapestr(k), stringutil.escapestr(v))
             )
 
 
 @command(b'debugpvec', [], _(b'A B'))
 def debugpvec(ui, repo, a, b=None):
     ca = scmutil.revsingle(repo, a)
     cb = scmutil.revsingle(repo, b)
     pa = pvec.ctxpvec(ca)
     pb = pvec.ctxpvec(cb)
     if pa == pb:
         rel = b"="
     elif pa > pb:
         rel = b">"
     elif pa < pb:
         rel = b"<"
     elif pa | pb:
         rel = b"|"
     ui.write(_(b"a: %s\n") % pa)
     ui.write(_(b"b: %s\n") % pb)
     ui.write(_(b"depth(a): %d depth(b): %d\n") % (pa._depth, pb._depth))
     ui.write(
         _(b"delta: %d hdist: %d distance: %d relation: %s\n")
         % (
             abs(pa._depth - pb._depth),
             pvec._hamming(pa._vec, pb._vec),
             pa.distance(pb),
             rel,
         )
     )
 
 
 @command(
     b'debugrebuilddirstate|debugrebuildstate',
     [
         (b'r', b'rev', b'', _(b'revision to rebuild to'), _(b'REV')),
         (
             b'',
             b'minimal',
             None,
             _(
                 b'only rebuild files that are inconsistent with '
                 b'the working copy parent'
             ),
         ),
     ],
     _(b'[-r REV]'),
 )
 def debugrebuilddirstate(ui, repo, rev, **opts):
     """rebuild the dirstate as it would look like for the given revision
 
     If no revision is specified the first current parent will be used.
 
     The dirstate will be set to the files of the given revision.
     The actual working directory content or existing dirstate
     information such as adds or removes is not considered.
 
     ``minimal`` will only rebuild the dirstate status for files that claim to be
     tracked but are not in the parent manifest, or that exist in the parent
     manifest but are not in the dirstate. It will not change adds, removes, or
     modified files that are in the working copy parent.
 
     One use of this command is to make the next :hg:`status` invocation
     check the actual file content.
     """
     ctx = scmutil.revsingle(repo, rev)
     with repo.wlock():
         dirstate = repo.dirstate
         changedfiles = None
         # See command doc for what minimal does.
         if opts.get('minimal'):
             manifestfiles = set(ctx.manifest().keys())
             dirstatefiles = set(dirstate)
             manifestonly = manifestfiles - dirstatefiles
             dsonly = dirstatefiles - manifestfiles
             dsnotadded = set(f for f in dsonly if dirstate[f] != b'a')
             changedfiles = manifestonly | dsnotadded
 
         dirstate.rebuild(ctx.node(), ctx.manifest(), changedfiles)
 
 
 @command(b'debugrebuildfncache', [], b'')
 def debugrebuildfncache(ui, repo):
     """rebuild the fncache file"""
     repair.rebuildfncache(ui, repo)
 
 
 @command(
     b'debugrename',
     [(b'r', b'rev', b'', _(b'revision to debug'), _(b'REV'))],
     _(b'[-r REV] [FILE]...'),
 )
 def debugrename(ui, repo, *pats, **opts):
     """dump rename information"""
 
     opts = pycompat.byteskwargs(opts)
     ctx = scmutil.revsingle(repo, opts.get(b'rev'))
     m = scmutil.match(ctx, pats, opts)
     for abs in ctx.walk(m):
         fctx = ctx[abs]
         o = fctx.filelog().renamed(fctx.filenode())
         rel = repo.pathto(abs)
         if o:
             ui.write(_(b"%s renamed from %s:%s\n") % (rel, o[0], hex(o[1])))
         else:
             ui.write(_(b"%s not renamed\n") % rel)
 
 
 @command(
     b'debugrevlog',
     cmdutil.debugrevlogopts + [(b'd', b'dump', False, _(b'dump index data'))],
     _(b'-c|-m|FILE'),
     optionalrepo=True,
 )
 def debugrevlog(ui, repo, file_=None, **opts):
     """show data and statistics about a revlog"""
     opts = pycompat.byteskwargs(opts)
     r = cmdutil.openrevlog(repo, b'debugrevlog', file_, opts)
 
     if opts.get(b"dump"):
         numrevs = len(r)
         ui.write(
             (
                 b"# rev p1rev p2rev start   end deltastart base   p1   p2"
                 b" rawsize totalsize compression heads chainlen\n"
             )
         )
         ts = 0
         heads = set()
 
         for rev in pycompat.xrange(numrevs):
             dbase = r.deltaparent(rev)
             if dbase == -1:
                 dbase = rev
             cbase = r.chainbase(rev)
             clen = r.chainlen(rev)
             p1, p2 = r.parentrevs(rev)
             rs = r.rawsize(rev)
             ts = ts + rs
             heads -= set(r.parentrevs(rev))
             heads.add(rev)
             try:
                 compression = ts / r.end(rev)
             except ZeroDivisionError:
                 compression = 0
             ui.write(
                 b"%5d %5d %5d %5d %5d %10d %4d %4d %4d %7d %9d "
                 b"%11d %5d %8d\n"
                 % (
                     rev,
                     p1,
                     p2,
                     r.start(rev),
                     r.end(rev),
                     r.start(dbase),
                     r.start(cbase),
                     r.start(p1),
                     r.start(p2),
                     rs,
                     ts,
                     compression,
                     len(heads),
                     clen,
                 )
             )
         return 0
 
     v = r.version
     format = v & 0xFFFF
     flags = []
     gdelta = False
     if v & revlog.FLAG_INLINE_DATA:
         flags.append(b'inline')
     if v & revlog.FLAG_GENERALDELTA:
         gdelta = True
         flags.append(b'generaldelta')
     if not flags:
         flags = [b'(none)']
 
     ### tracks merge vs single parent
     nummerges = 0
 
     ### tracks ways the "delta" are build
     # nodelta
     numempty = 0
     numemptytext = 0
     numemptydelta = 0
     # full file content
     numfull = 0
     # intermediate snapshot against a prior snapshot
     numsemi = 0
     # snapshot count per depth
     numsnapdepth = collections.defaultdict(lambda: 0)
     # delta against previous revision
     numprev = 0
     # delta against first or second parent (not prev)
     nump1 = 0
     nump2 = 0
     # delta against neither prev nor parents
     numother = 0
     # delta against prev that are also first or second parent
     # (details of `numprev`)
     nump1prev = 0
     nump2prev = 0
 
     # data about delta chain of each revs
     chainlengths = []
     chainbases = []
     chainspans = []
 
     # data about each revision
     datasize = [None, 0, 0]
     fullsize = [None, 0, 0]
     semisize = [None, 0, 0]
     # snapshot count per depth
     snapsizedepth = collections.defaultdict(lambda: [None, 0, 0])
     deltasize = [None, 0, 0]
     chunktypecounts = {}
     chunktypesizes = {}
 
     def addsize(size, l):
         if l[0] is None or size < l[0]:
             l[0] = size
         if size > l[1]:
             l[1] = size
         l[2] += size
 
     numrevs = len(r)
     for rev in pycompat.xrange(numrevs):
         p1, p2 = r.parentrevs(rev)
         delta = r.deltaparent(rev)
         if format > 0:
             addsize(r.rawsize(rev), datasize)
         if p2 != nullrev:
             nummerges += 1
         size = r.length(rev)
         if delta == nullrev:
             chainlengths.append(0)
             chainbases.append(r.start(rev))
             chainspans.append(size)
             if size == 0:
                 numempty += 1
                 numemptytext += 1
             else:
                 numfull += 1
                 numsnapdepth[0] += 1
                 addsize(size, fullsize)
                 addsize(size, snapsizedepth[0])
         else:
             chainlengths.append(chainlengths[delta] + 1)
             baseaddr = chainbases[delta]
             revaddr = r.start(rev)
             chainbases.append(baseaddr)
             chainspans.append((revaddr - baseaddr) + size)
             if size == 0:
                 numempty += 1
                 numemptydelta += 1
             elif r.issnapshot(rev):
                 addsize(size, semisize)
                 numsemi += 1
                 depth = r.snapshotdepth(rev)
                 numsnapdepth[depth] += 1
                 addsize(size, snapsizedepth[depth])
             else:
                 addsize(size, deltasize)
                 if delta == rev - 1:
                     numprev += 1
                     if delta == p1:
                         nump1prev += 1
                     elif delta == p2:
                         nump2prev += 1
                 elif delta == p1:
                     nump1 += 1
                 elif delta == p2:
                     nump2 += 1
                 elif delta != nullrev:
                     numother += 1
 
         # Obtain data on the raw chunks in the revlog.
         if util.safehasattr(r, b'_getsegmentforrevs'):
             segment = r._getsegmentforrevs(rev, rev)[1]
         else:
             segment = r._revlog._getsegmentforrevs(rev, rev)[1]
         if segment:
             chunktype = bytes(segment[0:1])
         else:
             chunktype = b'empty'
 
         if chunktype not in chunktypecounts:
             chunktypecounts[chunktype] = 0
             chunktypesizes[chunktype] = 0
 
         chunktypecounts[chunktype] += 1
         chunktypesizes[chunktype] += size
 
     # Adjust size min value for empty cases
     for size in (datasize, fullsize, semisize, deltasize):
         if size[0] is None:
             size[0] = 0
 
     numdeltas = numrevs - numfull - numempty - numsemi
     numoprev = numprev - nump1prev - nump2prev
     totalrawsize = datasize[2]
     datasize[2] /= numrevs
     fulltotal = fullsize[2]
     if numfull == 0:
         fullsize[2] = 0
     else:
         fullsize[2] /= numfull
     semitotal = semisize[2]
     snaptotal = {}
     if numsemi > 0:
         semisize[2] /= numsemi
     for depth in snapsizedepth:
         snaptotal[depth] = snapsizedepth[depth][2]
         snapsizedepth[depth][2] /= numsnapdepth[depth]
 
     deltatotal = deltasize[2]
     if numdeltas > 0:
         deltasize[2] /= numdeltas
     totalsize = fulltotal + semitotal + deltatotal
     avgchainlen = sum(chainlengths) / numrevs
     maxchainlen = max(chainlengths)
     maxchainspan = max(chainspans)
     compratio = 1
     if totalsize:
         compratio = totalrawsize / totalsize
 
     basedfmtstr = b'%%%dd\n'
     basepcfmtstr = b'%%%dd %s(%%5.2f%%%%)\n'
 
     def dfmtstr(max):
         return basedfmtstr % len(str(max))
 
     def pcfmtstr(max, padding=0):
         return basepcfmtstr % (len(str(max)), b' ' * padding)
 
     def pcfmt(value, total):
         if total:
             return (value, 100 * float(value) / total)
         else:
             return value, 100.0
 
     ui.writenoi18n(b'format : %d\n' % format)
     ui.writenoi18n(b'flags  : %s\n' % b', '.join(flags))
 
     ui.write(b'\n')
     fmt = pcfmtstr(totalsize)
     fmt2 = dfmtstr(totalsize)
     ui.writenoi18n(b'revisions     : ' + fmt2 % numrevs)
     ui.writenoi18n(b'    merges    : ' + fmt % pcfmt(nummerges, numrevs))
     ui.writenoi18n(
         b'    normal    : ' + fmt % pcfmt(numrevs - nummerges, numrevs)
     )
     ui.writenoi18n(b'revisions     : ' + fmt2 % numrevs)
     ui.writenoi18n(b'    empty     : ' + fmt % pcfmt(numempty, numrevs))
     ui.writenoi18n(
         b'                   text  : '
         + fmt % pcfmt(numemptytext, numemptytext + numemptydelta)
     )
     ui.writenoi18n(
         b'                   delta : '
         + fmt % pcfmt(numemptydelta, numemptytext + numemptydelta)
     )
     ui.writenoi18n(
         b'    snapshot  : ' + fmt % pcfmt(numfull + numsemi, numrevs)
     )
     for depth in sorted(numsnapdepth):
         ui.write(
             (b'      lvl-%-3d :       ' % depth)
             + fmt % pcfmt(numsnapdepth[depth], numrevs)
         )
     ui.writenoi18n(b'    deltas    : ' + fmt % pcfmt(numdeltas, numrevs))
     ui.writenoi18n(b'revision size : ' + fmt2 % totalsize)
     ui.writenoi18n(
         b'    snapshot  : ' + fmt % pcfmt(fulltotal + semitotal, totalsize)
     )
     for depth in sorted(numsnapdepth):
         ui.write(
             (b'      lvl-%-3d :       ' % depth)
             + fmt % pcfmt(snaptotal[depth], totalsize)
         )
     ui.writenoi18n(b'    deltas    : ' + fmt % pcfmt(deltatotal, totalsize))
 
     def fmtchunktype(chunktype):
         if chunktype == b'empty':
             return b'    %s     : ' % chunktype
         elif chunktype in pycompat.bytestr(string.ascii_letters):
             return b'    0x%s (%s)  : ' % (hex(chunktype), chunktype)
         else:
             return b'    0x%s      : ' % hex(chunktype)
 
     ui.write(b'\n')
     ui.writenoi18n(b'chunks        : ' + fmt2 % numrevs)
     for chunktype in sorted(chunktypecounts):
         ui.write(fmtchunktype(chunktype))
         ui.write(fmt % pcfmt(chunktypecounts[chunktype], numrevs))
     ui.writenoi18n(b'chunks size   : ' + fmt2 % totalsize)
     for chunktype in sorted(chunktypecounts):
         ui.write(fmtchunktype(chunktype))
         ui.write(fmt % pcfmt(chunktypesizes[chunktype], totalsize))
 
     ui.write(b'\n')
     fmt = dfmtstr(max(avgchainlen, maxchainlen, maxchainspan, compratio))
     ui.writenoi18n(b'avg chain length  : ' + fmt % avgchainlen)
     ui.writenoi18n(b'max chain length  : ' + fmt % maxchainlen)
     ui.writenoi18n(b'max chain reach   : ' + fmt % maxchainspan)
     ui.writenoi18n(b'compression ratio : ' + fmt % compratio)
 
     if format > 0:
         ui.write(b'\n')
         ui.writenoi18n(
             b'uncompressed data size (min/max/avg) : %d / %d / %d\n'
             % tuple(datasize)
         )
     ui.writenoi18n(
         b'full revision size (min/max/avg)     : %d / %d / %d\n'
         % tuple(fullsize)
     )
     ui.writenoi18n(
         b'inter-snapshot size (min/max/avg)    : %d / %d / %d\n'
         % tuple(semisize)
     )
     for depth in sorted(snapsizedepth):
         if depth == 0:
             continue
         ui.writenoi18n(
             b'    level-%-3d (min/max/avg)          : %d / %d / %d\n'
             % ((depth,) + tuple(snapsizedepth[depth]))
         )
     ui.writenoi18n(
         b'delta size (min/max/avg)             : %d / %d / %d\n'
         % tuple(deltasize)
     )
 
     if numdeltas > 0:
         ui.write(b'\n')
         fmt = pcfmtstr(numdeltas)
         fmt2 = pcfmtstr(numdeltas, 4)
         ui.writenoi18n(
             b'deltas against prev  : ' + fmt % pcfmt(numprev, numdeltas)
         )
         if numprev > 0:
             ui.writenoi18n(
                 b'    where prev = p1  : ' + fmt2 % pcfmt(nump1prev, numprev)
             )
             ui.writenoi18n(
                 b'    where prev = p2  : ' + fmt2 % pcfmt(nump2prev, numprev)
             )
             ui.writenoi18n(
                 b'    other            : ' + fmt2 % pcfmt(numoprev, numprev)
             )
         if gdelta:
             ui.writenoi18n(
                 b'deltas against p1    : ' + fmt % pcfmt(nump1, numdeltas)
             )
             ui.writenoi18n(
                 b'deltas against p2    : ' + fmt % pcfmt(nump2, numdeltas)
             )
             ui.writenoi18n(
                 b'deltas against other : ' + fmt % pcfmt(numother, numdeltas)
             )
 
 
 @command(
     b'debugrevlogindex',
     cmdutil.debugrevlogopts
     + [(b'f', b'format', 0, _(b'revlog format'), _(b'FORMAT'))],
     _(b'[-f FORMAT] -c|-m|FILE'),
     optionalrepo=True,
 )
 def debugrevlogindex(ui, repo, file_=None, **opts):
     """dump the contents of a revlog index"""
     opts = pycompat.byteskwargs(opts)
     r = cmdutil.openrevlog(repo, b'debugrevlogindex', file_, opts)
     format = opts.get(b'format', 0)
     if format not in (0, 1):
         raise error.Abort(_(b"unknown format %d") % format)
 
     if ui.debugflag:
         shortfn = hex
     else:
         shortfn = short
 
     # There might not be anything in r, so have a sane default
     idlen = 12
     for i in r:
         idlen = len(shortfn(r.node(i)))
         break
 
     if format == 0:
         if ui.verbose:
             ui.writenoi18n(
                 b"   rev    offset  length linkrev %s %s p2\n"
                 % (b"nodeid".ljust(idlen), b"p1".ljust(idlen))
             )
         else:
             ui.writenoi18n(
                 b"   rev linkrev %s %s p2\n"
                 % (b"nodeid".ljust(idlen), b"p1".ljust(idlen))
             )
     elif format == 1:
         if ui.verbose:
             ui.writenoi18n(
                 (
                     b"   rev flag   offset   length     size   link     p1"
                     b"     p2 %s\n"
                 )
                 % b"nodeid".rjust(idlen)
             )
         else:
             ui.writenoi18n(
                 b"   rev flag     size   link     p1     p2 %s\n"
                 % b"nodeid".rjust(idlen)
             )
 
     for i in r:
         node = r.node(i)
         if format == 0:
             try:
                 pp = r.parents(node)
             except Exception:
                 pp = [nullid, nullid]
             if ui.verbose:
                 ui.write(
                     b"% 6d % 9d % 7d % 7d %s %s %s\n"
                     % (
                         i,
                         r.start(i),
                         r.length(i),
                         r.linkrev(i),
                         shortfn(node),
                         shortfn(pp[0]),
                         shortfn(pp[1]),
                     )
                 )
             else:
                 ui.write(
                     b"% 6d % 7d %s %s %s\n"
                     % (
                         i,
                         r.linkrev(i),
                         shortfn(node),
                         shortfn(pp[0]),
                         shortfn(pp[1]),
                     )
                 )
         elif format == 1:
             pr = r.parentrevs(i)
             if ui.verbose:
                 ui.write(
                     b"% 6d %04x % 8d % 8d % 8d % 6d % 6d % 6d %s\n"
                     % (
                         i,
                         r.flags(i),
                         r.start(i),
                         r.length(i),
                         r.rawsize(i),
                         r.linkrev(i),
                         pr[0],
                         pr[1],
                         shortfn(node),
                     )
                 )
             else:
                 ui.write(
                     b"% 6d %04x % 8d % 6d % 6d % 6d %s\n"
                     % (
                         i,
                         r.flags(i),
                         r.rawsize(i),
                         r.linkrev(i),
                         pr[0],
                         pr[1],
                         shortfn(node),
                     )
                 )
 
 
 @command(
     b'debugrevspec',
     [
         (
             b'',
             b'optimize',
             None,
             _(b'print parsed tree after optimizing (DEPRECATED)'),
         ),
         (
             b'',
             b'show-revs',
             True,
             _(b'print list of result revisions (default)'),
         ),
         (
             b's',
             b'show-set',
             None,
             _(b'print internal representation of result set'),
         ),
         (
             b'p',
             b'show-stage',
             [],
             _(b'print parsed tree at the given stage'),
             _(b'NAME'),
         ),
         (b'', b'no-optimized', False, _(b'evaluate tree without optimization')),
         (b'', b'verify-optimized', False, _(b'verify optimized result')),
     ],
     b'REVSPEC',
 )
 def debugrevspec(ui, repo, expr, **opts):
     """parse and apply a revision specification
 
     Use -p/--show-stage option to print the parsed tree at the given stages.
     Use -p all to print tree at every stage.
 
     Use --no-show-revs option with -s or -p to print only the set
     representation or the parsed tree respectively.
 
     Use --verify-optimized to compare the optimized result with the unoptimized
     one. Returns 1 if the optimized result differs.
     """
     opts = pycompat.byteskwargs(opts)
     aliases = ui.configitems(b'revsetalias')
     stages = [
         (b'parsed', lambda tree: tree),
         (
             b'expanded',
             lambda tree: revsetlang.expandaliases(tree, aliases, ui.warn),
         ),
         (b'concatenated', revsetlang.foldconcat),
         (b'analyzed', revsetlang.analyze),
         (b'optimized', revsetlang.optimize),
     ]
     if opts[b'no_optimized']:
         stages = stages[:-1]
     if opts[b'verify_optimized'] and opts[b'no_optimized']:
         raise error.Abort(
             _(b'cannot use --verify-optimized with --no-optimized')
         )
     stagenames = set(n for n, f in stages)
 
     showalways = set()
     showchanged = set()
     if ui.verbose and not opts[b'show_stage']:
         # show parsed tree by --verbose (deprecated)
         showalways.add(b'parsed')
         showchanged.update([b'expanded', b'concatenated'])
         if opts[b'optimize']:
             showalways.add(b'optimized')
     if opts[b'show_stage'] and opts[b'optimize']:
         raise error.Abort(_(b'cannot use --optimize with --show-stage'))
     if opts[b'show_stage'] == [b'all']:
         showalways.update(stagenames)
     else:
         for n in opts[b'show_stage']:
             if n not in stagenames:
                 raise error.Abort(_(b'invalid stage name: %s') % n)
         showalways.update(opts[b'show_stage'])
 
     treebystage = {}
     printedtree = None
     tree = revsetlang.parse(expr, lookup=revset.lookupfn(repo))
     for n, f in stages:
         treebystage[n] = tree = f(tree)
         if n in showalways or (n in showchanged and tree != printedtree):
             if opts[b'show_stage'] or n != b'parsed':
                 ui.write(b"* %s:\n" % n)
             ui.write(revsetlang.prettyformat(tree), b"\n")
             printedtree = tree
 
     if opts[b'verify_optimized']:
         arevs = revset.makematcher(treebystage[b'analyzed'])(repo)
         brevs = revset.makematcher(treebystage[b'optimized'])(repo)
         if opts[b'show_set'] or (opts[b'show_set'] is None and ui.verbose):
             ui.writenoi18n(
                 b"* analyzed set:\n", stringutil.prettyrepr(arevs), b"\n"
             )
             ui.writenoi18n(
                 b"* optimized set:\n", stringutil.prettyrepr(brevs), b"\n"
             )
         arevs = list(arevs)
         brevs = list(brevs)
         if arevs == brevs:
             return 0
         ui.writenoi18n(b'--- analyzed\n', label=b'diff.file_a')
         ui.writenoi18n(b'+++ optimized\n', label=b'diff.file_b')
         sm = difflib.SequenceMatcher(None, arevs, brevs)
         for tag, alo, ahi, blo, bhi in sm.get_opcodes():
             if tag in ('delete', 'replace'):
                 for c in arevs[alo:ahi]:
                     ui.write(b'-%d\n' % c, label=b'diff.deleted')
             if tag in ('insert', 'replace'):
                 for c in brevs[blo:bhi]:
                     ui.write(b'+%d\n' % c, label=b'diff.inserted')
             if tag == 'equal':
                 for c in arevs[alo:ahi]:
                     ui.write(b' %d\n' % c)
         return 1
 
     func = revset.makematcher(tree)
     revs = func(repo)
     if opts[b'show_set'] or (opts[b'show_set'] is None and ui.verbose):
         ui.writenoi18n(b"* set:\n", stringutil.prettyrepr(revs), b"\n")
     if not opts[b'show_revs']:
         return
     for c in revs:
         ui.write(b"%d\n" % c)
 
 
 @command(
     b'debugserve',
     [
         (
             b'',
             b'sshstdio',
             False,
             _(b'run an SSH server bound to process handles'),
         ),
         (b'', b'logiofd', b'', _(b'file descriptor to log server I/O to')),
         (b'', b'logiofile', b'', _(b'file to log server I/O to')),
     ],
     b'',
 )
 def debugserve(ui, repo, **opts):
     """run a server with advanced settings
 
     This command is similar to :hg:`serve`. It exists partially as a
     workaround to the fact that ``hg serve --stdio`` must have specific
     arguments for security reasons.
     """
     opts = pycompat.byteskwargs(opts)
 
     if not opts[b'sshstdio']:
         raise error.Abort(_(b'only --sshstdio is currently supported'))
 
     logfh = None
 
     if opts[b'logiofd'] and opts[b'logiofile']:
         raise error.Abort(_(b'cannot use both --logiofd and --logiofile'))
 
     if opts[b'logiofd']:
         # Ideally we would be line buffered. But line buffering in binary
         # mode isn't supported and emits a warning in Python 3.8+. Disabling
         # buffering could have performance impacts. But since this isn't
         # performance critical code, it should be fine.
         try:
             logfh = os.fdopen(int(opts[b'logiofd']), 'ab', 0)
         except OSError as e:
             if e.errno != errno.ESPIPE:
                 raise
             # can't seek a pipe, so `ab` mode fails on py3
             logfh = os.fdopen(int(opts[b'logiofd']), 'wb', 0)
     elif opts[b'logiofile']:
         logfh = open(opts[b'logiofile'], b'ab', 0)
 
     s = wireprotoserver.sshserver(ui, repo, logfh=logfh)
     s.serve_forever()
 
 
 @command(b'debugsetparents', [], _(b'REV1 [REV2]'))
 def debugsetparents(ui, repo, rev1, rev2=None):
     """manually set the parents of the current working directory
 
     This is useful for writing repository conversion tools, but should
     be used with care. For example, neither the working directory nor the
     dirstate is updated, so file status may be incorrect after running this
     command.
 
     Returns 0 on success.
     """
 
     node1 = scmutil.revsingle(repo, rev1).node()
     node2 = scmutil.revsingle(repo, rev2, b'null').node()
 
     with repo.wlock():
         repo.setparents(node1, node2)
 
 
 @command(b'debugsidedata', cmdutil.debugrevlogopts, _(b'-c|-m|FILE REV'))
 def debugsidedata(ui, repo, file_, rev=None, **opts):
     """dump the side data for a cl/manifest/file revision
 
     Use --verbose to dump the sidedata content."""
     opts = pycompat.byteskwargs(opts)
     if opts.get(b'changelog') or opts.get(b'manifest') or opts.get(b'dir'):
         if rev is not None:
             raise error.CommandError(b'debugdata', _(b'invalid arguments'))
         file_, rev = None, file_
     elif rev is None:
         raise error.CommandError(b'debugdata', _(b'invalid arguments'))
     r = cmdutil.openstorage(repo, b'debugdata', file_, opts)
     r = getattr(r, '_revlog', r)
     try:
         sidedata = r.sidedata(r.lookup(rev))
     except KeyError:
         raise error.Abort(_(b'invalid revision identifier %s') % rev)
     if sidedata:
         sidedata = list(sidedata.items())
         sidedata.sort()
         ui.writenoi18n(b'%d sidedata entries\n' % len(sidedata))
         for key, value in sidedata:
             ui.writenoi18n(b' entry-%04o size %d\n' % (key, len(value)))
             if ui.verbose:
                 ui.writenoi18n(b'  %s\n' % stringutil.pprint(value))
 
 
 @command(b'debugssl', [], b'[SOURCE]', optionalrepo=True)
 def debugssl(ui, repo, source=None, **opts):
     '''test a secure connection to a server
 
     This builds the certificate chain for the server on Windows, installing the
     missing intermediates and trusted root via Windows Update if necessary.  It
     does nothing on other platforms.
 
     If SOURCE is omitted, the 'default' path will be used.  If a URL is given,
     that server is used. See :hg:`help urls` for more information.
 
     If the update succeeds, retry the original operation.  Otherwise, the cause
     of the SSL error is likely another issue.
     '''
     if not pycompat.iswindows:
         raise error.Abort(
             _(b'certificate chain building is only possible on Windows')
         )
 
     if not source:
         if not repo:
             raise error.Abort(
                 _(
                     b"there is no Mercurial repository here, and no "
                     b"server specified"
                 )
             )
         source = b"default"
 
     source, branches = hg.parseurl(ui.expandpath(source))
     url = util.url(source)
 
     defaultport = {b'https': 443, b'ssh': 22}
     if url.scheme in defaultport:
         try:
             addr = (url.host, int(url.port or defaultport[url.scheme]))
         except ValueError:
             raise error.Abort(_(b"malformed port number in URL"))
     else:
         raise error.Abort(_(b"only https and ssh connections are supported"))
 
     from . import win32
 
     s = ssl.wrap_socket(
         socket.socket(),
         ssl_version=ssl.PROTOCOL_TLS,
         cert_reqs=ssl.CERT_NONE,
         ca_certs=None,
     )
 
     try:
         s.connect(addr)
         cert = s.getpeercert(True)
 
         ui.status(_(b'checking the certificate chain for %s\n') % url.host)
 
         complete = win32.checkcertificatechain(cert, build=False)
 
         if not complete:
             ui.status(_(b'certificate chain is incomplete, updating... '))
 
             if not win32.checkcertificatechain(cert):
                 ui.status(_(b'failed.\n'))
             else:
                 ui.status(_(b'done.\n'))
         else:
             ui.status(_(b'full certificate chain is available\n'))
     finally:
         s.close()
 
 
 @command(
     b'debugsub',
     [(b'r', b'rev', b'', _(b'revision to check'), _(b'REV'))],
     _(b'[-r REV] [REV]'),
 )
 def debugsub(ui, repo, rev=None):
     ctx = scmutil.revsingle(repo, rev, None)
     for k, v in sorted(ctx.substate.items()):
         ui.writenoi18n(b'path %s\n' % k)
         ui.writenoi18n(b' source   %s\n' % v[0])
         ui.writenoi18n(b' revision %s\n' % v[1])
 
 
 @command(
     b'debugsuccessorssets',
     [(b'', b'closest', False, _(b'return closest successors sets only'))],
     _(b'[REV]'),
 )
 def debugsuccessorssets(ui, repo, *revs, **opts):
     """show set of successors for revision
 
     A successors set of changeset A is a consistent group of revisions that
     succeed A. It contains non-obsolete changesets only unless closests
     successors set is set.
 
     In most cases a changeset A has a single successors set containing a single
     successor (changeset A replaced by A').
 
     A changeset that is made obsolete with no successors are called "pruned".
     Such changesets have no successors sets at all.
 
     A changeset that has been "split" will have a successors set containing
     more than one successor.
 
     A changeset that has been rewritten in multiple different ways is called
     "divergent". Such changesets have multiple successor sets (each of which
     may also be split, i.e. have multiple successors).
 
     Results are displayed as follows::
 
         <rev1>
             <successors-1A>
         <rev2>
             <successors-2A>
             <successors-2B1> <successors-2B2> <successors-2B3>
 
     Here rev2 has two possible (i.e. divergent) successors sets. The first
     holds one element, whereas the second holds three (i.e. the changeset has
     been split).
     """
     # passed to successorssets caching computation from one call to another
     cache = {}
     ctx2str = bytes
     node2str = short
     for rev in scmutil.revrange(repo, revs):
         ctx = repo[rev]
         ui.write(b'%s\n' % ctx2str(ctx))
         for succsset in obsutil.successorssets(
             repo, ctx.node(), closest=opts['closest'], cache=cache
         ):
             if succsset:
                 ui.write(b'    ')
                 ui.write(node2str(succsset[0]))
                 for node in succsset[1:]:
                     ui.write(b' ')
                     ui.write(node2str(node))
             ui.write(b'\n')
 
 
 @command(b'debugtagscache', [])
 def debugtagscache(ui, repo):
     """display the contents of .hg/cache/hgtagsfnodes1"""
     cache = tagsmod.hgtagsfnodescache(repo.unfiltered())
     for r in repo:
         node = repo[r].node()
         tagsnode = cache.getfnode(node, computemissing=False)
         tagsnodedisplay = hex(tagsnode) if tagsnode else 'missing/invalid'
         ui.write(b'%s %s %s\n' % (r, hex(node), tagsnodedisplay))
 
 
 @command(
     b'debugtemplate',
     [
         (b'r', b'rev', [], _(b'apply template on changesets'), _(b'REV')),
         (b'D', b'define', [], _(b'define template keyword'), _(b'KEY=VALUE')),
     ],
     _(b'[-r REV]... [-D KEY=VALUE]... TEMPLATE'),
     optionalrepo=True,
 )
 def debugtemplate(ui, repo, tmpl, **opts):
     """parse and apply a template
 
     If -r/--rev is given, the template is processed as a log template and
     applied to the given changesets. Otherwise, it is processed as a generic
     template.
 
     Use --verbose to print the parsed tree.
     """
     revs = None
     if opts['rev']:
         if repo is None:
             raise error.RepoError(
                 _(b'there is no Mercurial repository here (.hg not found)')
             )
         revs = scmutil.revrange(repo, opts['rev'])
 
     props = {}
     for d in opts['define']:
         try:
             k, v = (e.strip() for e in d.split(b'=', 1))
             if not k or k == b'ui':
                 raise ValueError
             props[k] = v
         except ValueError:
             raise error.Abort(_(b'malformed keyword definition: %s') % d)
 
     if ui.verbose:
         aliases = ui.configitems(b'templatealias')
         tree = templater.parse(tmpl)
         ui.note(templater.prettyformat(tree), b'\n')
         newtree = templater.expandaliases(tree, aliases)
         if newtree != tree:
             ui.notenoi18n(
                 b"* expanded:\n", templater.prettyformat(newtree), b'\n'
             )
 
     if revs is None:
         tres = formatter.templateresources(ui, repo)
         t = formatter.maketemplater(ui, tmpl, resources=tres)
         if ui.verbose:
             kwds, funcs = t.symbolsuseddefault()
             ui.writenoi18n(b"* keywords: %s\n" % b', '.join(sorted(kwds)))
             ui.writenoi18n(b"* functions: %s\n" % b', '.join(sorted(funcs)))
         ui.write(t.renderdefault(props))
     else:
         displayer = logcmdutil.maketemplater(ui, repo, tmpl)
         if ui.verbose:
             kwds, funcs = displayer.t.symbolsuseddefault()
             ui.writenoi18n(b"* keywords: %s\n" % b', '.join(sorted(kwds)))
             ui.writenoi18n(b"* functions: %s\n" % b', '.join(sorted(funcs)))
         for r in revs:
             displayer.show(repo[r], **pycompat.strkwargs(props))
         displayer.close()
 
 
 @command(
     b'debuguigetpass',
     [(b'p', b'prompt', b'', _(b'prompt text'), _(b'TEXT')),],
     _(b'[-p TEXT]'),
     norepo=True,
 )
 def debuguigetpass(ui, prompt=b''):
     """show prompt to type password"""
     r = ui.getpass(prompt)
     ui.writenoi18n(b'respose: %s\n' % r)
 
 
 @command(
     b'debuguiprompt',
     [(b'p', b'prompt', b'', _(b'prompt text'), _(b'TEXT')),],
     _(b'[-p TEXT]'),
     norepo=True,
 )
 def debuguiprompt(ui, prompt=b''):
     """show plain prompt"""
     r = ui.prompt(prompt)
     ui.writenoi18n(b'response: %s\n' % r)
 
 
 @command(b'debugupdatecaches', [])
 def debugupdatecaches(ui, repo, *pats, **opts):
     """warm all known caches in the repository"""
     with repo.wlock(), repo.lock():
         repo.updatecaches(full=True)
 
 
 @command(
     b'debugupgraderepo',
     [
         (
             b'o',
             b'optimize',
             [],
             _(b'extra optimization to perform'),
             _(b'NAME'),
         ),
         (b'', b'run', False, _(b'performs an upgrade')),
         (b'', b'backup', True, _(b'keep the old repository content around')),
         (b'', b'changelog', None, _(b'select the changelog for upgrade')),
         (b'', b'manifest', None, _(b'select the manifest for upgrade')),
     ],
 )
 def debugupgraderepo(ui, repo, run=False, optimize=None, backup=True, **opts):
     """upgrade a repository to use different features
 
     If no arguments are specified, the repository is evaluated for upgrade
     and a list of problems and potential optimizations is printed.
 
     With ``--run``, a repository upgrade is performed. Behavior of the upgrade
     can be influenced via additional arguments. More details will be provided
     by the command output when run without ``--run``.
 
     During the upgrade, the repository will be locked and no writes will be
     allowed.
 
     At the end of the upgrade, the repository may not be readable while new
     repository data is swapped in. This window will be as long as it takes to
     rename some directories inside the ``.hg`` directory. On most machines, this
     should complete almost instantaneously and the chances of a consumer being
     unable to access the repository should be low.
 
     By default, all revlog will be upgraded. You can restrict this using flag
     such as `--manifest`:
 
       * `--manifest`: only optimize the manifest
       * `--no-manifest`: optimize all revlog but the manifest
       * `--changelog`: optimize the changelog only
       * `--no-changelog --no-manifest`: optimize filelogs only
     """
     return upgrade.upgraderepo(
         ui, repo, run=run, optimize=optimize, backup=backup, **opts
     )
 
 
 @command(
     b'debugwalk', cmdutil.walkopts, _(b'[OPTION]... [FILE]...'), inferrepo=True
 )
 def debugwalk(ui, repo, *pats, **opts):
     """show how files match on given patterns"""
     opts = pycompat.byteskwargs(opts)
     m = scmutil.match(repo[None], pats, opts)
     if ui.verbose:
         ui.writenoi18n(b'* matcher:\n', stringutil.prettyrepr(m), b'\n')
     items = list(repo[None].walk(m))
     if not items:
         return
     f = lambda fn: fn
     if ui.configbool(b'ui', b'slash') and pycompat.ossep != b'/':
         f = lambda fn: util.normpath(fn)
     fmt = b'f  %%-%ds  %%-%ds  %%s' % (
         max([len(abs) for abs in items]),
         max([len(repo.pathto(abs)) for abs in items]),
     )
     for abs in items:
         line = fmt % (
             abs,
             f(repo.pathto(abs)),
             m.exact(abs) and b'exact' or b'',
         )
         ui.write(b"%s\n" % line.rstrip())
 
 
 @command(b'debugwhyunstable', [], _(b'REV'))
 def debugwhyunstable(ui, repo, rev):
     """explain instabilities of a changeset"""
     for entry in obsutil.whyunstable(repo, scmutil.revsingle(repo, rev)):
         dnodes = b''
         if entry.get(b'divergentnodes'):
             dnodes = (
                 b' '.join(
                     b'%s (%s)' % (ctx.hex(), ctx.phasestr())
                     for ctx in entry[b'divergentnodes']
                 )
                 + b' '
             )
         ui.write(
             b'%s: %s%s %s\n'
             % (entry[b'instability'], dnodes, entry[b'reason'], entry[b'node'])
         )
 
 
 @command(
     b'debugwireargs',
     [
         (b'', b'three', b'', b'three'),
         (b'', b'four', b'', b'four'),
         (b'', b'five', b'', b'five'),
     ]
     + cmdutil.remoteopts,
     _(b'REPO [OPTIONS]... [ONE [TWO]]'),
     norepo=True,
 )
 def debugwireargs(ui, repopath, *vals, **opts):
     opts = pycompat.byteskwargs(opts)
     repo = hg.peer(ui, opts, repopath)
     for opt in cmdutil.remoteopts:
         del opts[opt[1]]
     args = {}
     for k, v in pycompat.iteritems(opts):
         if v:
             args[k] = v
     args = pycompat.strkwargs(args)
     # run twice to check that we don't mess up the stream for the next command
     res1 = repo.debugwireargs(*vals, **args)
     res2 = repo.debugwireargs(*vals, **args)
     ui.write(b"%s\n" % res1)
     if res1 != res2:
         ui.warn(b"%s\n" % res2)
 
 
 def _parsewirelangblocks(fh):
     activeaction = None
     blocklines = []
     lastindent = 0
 
     for line in fh:
         line = line.rstrip()
         if not line:
             continue
 
         if line.startswith(b'#'):
             continue
 
         if not line.startswith(b' '):
             # New block. Flush previous one.
             if activeaction:
                 yield activeaction, blocklines
 
             activeaction = line
             blocklines = []
             lastindent = 0
             continue
 
         # Else we start with an indent.
 
         if not activeaction:
             raise error.Abort(_(b'indented line outside of block'))
 
         indent = len(line) - len(line.lstrip())
 
         # If this line is indented more than the last line, concatenate it.
         if indent > lastindent and blocklines:
             blocklines[-1] += line.lstrip()
         else:
             blocklines.append(line)
             lastindent = indent
 
     # Flush last block.
     if activeaction:
         yield activeaction, blocklines
 
 
 @command(
     b'debugwireproto',
     [
         (b'', b'localssh', False, _(b'start an SSH server for this repo')),
         (b'', b'peer', b'', _(b'construct a specific version of the peer')),
         (
             b'',
             b'noreadstderr',
             False,
             _(b'do not read from stderr of the remote'),
         ),
         (
             b'',
             b'nologhandshake',
             False,
             _(b'do not log I/O related to the peer handshake'),
         ),
     ]
     + cmdutil.remoteopts,
     _(b'[PATH]'),
     optionalrepo=True,
 )
 def debugwireproto(ui, repo, path=None, **opts):
     """send wire protocol commands to a server
 
     This command can be used to issue wire protocol commands to remote
     peers and to debug the raw data being exchanged.
 
     ``--localssh`` will start an SSH server against the current repository
     and connect to that. By default, the connection will perform a handshake
     and establish an appropriate peer instance.
 
     ``--peer`` can be used to bypass the handshake protocol and construct a
     peer instance using the specified class type. Valid values are ``raw``,
     ``http2``, ``ssh1``, and ``ssh2``. ``raw`` instances only allow sending
     raw data payloads and don't support higher-level command actions.
 
     ``--noreadstderr`` can be used to disable automatic reading from stderr
     of the peer (for SSH connections only). Disabling automatic reading of
     stderr is useful for making output more deterministic.
 
     Commands are issued via a mini language which is specified via stdin.
     The language consists of individual actions to perform. An action is
     defined by a block. A block is defined as a line with no leading
     space followed by 0 or more lines with leading space. Blocks are
     effectively a high-level command with additional metadata.
 
     Lines beginning with ``#`` are ignored.
 
     The following sections denote available actions.
 
     raw
     ---
 
     Send raw data to the server.
 
     The block payload contains the raw data to send as one atomic send
     operation. The data may not actually be delivered in a single system
     call: it depends on the abilities of the transport being used.
 
     Each line in the block is de-indented and concatenated. Then, that
     value is evaluated as a Python b'' literal. This allows the use of
     backslash escaping, etc.
 
     raw+
     ----
 
     Behaves like ``raw`` except flushes output afterwards.
 
     command <X>
     -----------
 
     Send a request to run a named command, whose name follows the ``command``
     string.
 
     Arguments to the command are defined as lines in this block. The format of
     each line is ``<key> <value>``. e.g.::
 
        command listkeys
            namespace bookmarks
 
     If the value begins with ``eval:``, it will be interpreted as a Python
     literal expression. Otherwise values are interpreted as Python b'' literals.
     This allows sending complex types and encoding special byte sequences via
     backslash escaping.
 
     The following arguments have special meaning:
 
     ``PUSHFILE``
         When defined, the *push* mechanism of the peer will be used instead
         of the static request-response mechanism and the content of the
         file specified in the value of this argument will be sent as the
         command payload.
 
         This can be used to submit a local bundle file to the remote.
 
     batchbegin
     ----------
 
     Instruct the peer to begin a batched send.
 
     All ``command`` blocks are queued for execution until the next
     ``batchsubmit`` block.
 
     batchsubmit
     -----------
 
     Submit previously queued ``command`` blocks as a batch request.
 
     This action MUST be paired with a ``batchbegin`` action.
 
     httprequest <method> <path>
     ---------------------------
 
     (HTTP peer only)
 
     Send an HTTP request to the peer.
 
     The HTTP request line follows the ``httprequest`` action. e.g. ``GET /foo``.
 
     Arguments of the form ``<key>: <value>`` are interpreted as HTTP request
     headers to add to the request. e.g. ``Accept: foo``.
 
     The following arguments are special:
 
     ``BODYFILE``
         The content of the file defined as the value to this argument will be
         transferred verbatim as the HTTP request body.
 
     ``frame <type> <flags> <payload>``
         Send a unified protocol frame as part of the request body.
 
         All frames will be collected and sent as the body to the HTTP
         request.
 
     close
     -----
 
     Close the connection to the server.
 
     flush
     -----
 
     Flush data written to the server.
 
     readavailable
     -------------
 
     Close the write end of the connection and read all available data from
     the server.
 
     If the connection to the server encompasses multiple pipes, we poll both
     pipes and read available data.
 
     readline
     --------
 
     Read a line of output from the server. If there are multiple output
     pipes, reads only the main pipe.
 
     ereadline
     ---------
 
     Like ``readline``, but read from the stderr pipe, if available.
 
     read <X>
     --------
 
     ``read()`` N bytes from the server's main output pipe.
 
     eread <X>
     ---------
 
     ``read()`` N bytes from the server's stderr pipe, if available.
 
     Specifying Unified Frame-Based Protocol Frames
     ----------------------------------------------
 
     It is possible to emit a *Unified Frame-Based Protocol* by using special
     syntax.
 
     A frame is composed as a type, flags, and payload. These can be parsed
     from a string of the form:
 
        <request-id> <stream-id> <stream-flags> <type> <flags> <payload>
 
     ``request-id`` and ``stream-id`` are integers defining the request and
     stream identifiers.
 
     ``type`` can be an integer value for the frame type or the string name
     of the type. The strings are defined in ``wireprotoframing.py``. e.g.
     ``command-name``.
 
     ``stream-flags`` and ``flags`` are a ``|`` delimited list of flag
     components. Each component (and there can be just one) can be an integer
     or a flag name for stream flags or frame flags, respectively. Values are
     resolved to integers and then bitwise OR'd together.
 
     ``payload`` represents the raw frame payload. If it begins with
     ``cbor:``, the following string is evaluated as Python code and the
     resulting object is fed into a CBOR encoder. Otherwise it is interpreted
     as a Python byte string literal.
     """
     opts = pycompat.byteskwargs(opts)
 
     if opts[b'localssh'] and not repo:
         raise error.Abort(_(b'--localssh requires a repository'))
 
     if opts[b'peer'] and opts[b'peer'] not in (
         b'raw',
         b'http2',
         b'ssh1',
         b'ssh2',
     ):
         raise error.Abort(
             _(b'invalid value for --peer'),
             hint=_(b'valid values are "raw", "ssh1", and "ssh2"'),
         )
 
     if path and opts[b'localssh']:
         raise error.Abort(_(b'cannot specify --localssh with an explicit path'))
 
     if ui.interactive():
         ui.write(_(b'(waiting for commands on stdin)\n'))
 
     blocks = list(_parsewirelangblocks(ui.fin))
 
     proc = None
     stdin = None
     stdout = None
     stderr = None
     opener = None
 
     if opts[b'localssh']:
         # We start the SSH server in its own process so there is process
         # separation. This prevents a whole class of potential bugs around
         # shared state from interfering with server operation.
         args = procutil.hgcmd() + [
             b'-R',
             repo.root,
             b'debugserve',
             b'--sshstdio',
         ]
         proc = subprocess.Popen(
             pycompat.rapply(procutil.tonativestr, args),
             stdin=subprocess.PIPE,
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
             bufsize=0,
         )
 
         stdin = proc.stdin
         stdout = proc.stdout
         stderr = proc.stderr
 
         # We turn the pipes into observers so we can log I/O.
         if ui.verbose or opts[b'peer'] == b'raw':
             stdin = util.makeloggingfileobject(
                 ui, proc.stdin, b'i', logdata=True
             )
             stdout = util.makeloggingfileobject(
                 ui, proc.stdout, b'o', logdata=True
             )
             stderr = util.makeloggingfileobject(
                 ui, proc.stderr, b'e', logdata=True
             )
 
         # --localssh also implies the peer connection settings.
 
         url = b'ssh://localserver'
         autoreadstderr = not opts[b'noreadstderr']
 
         if opts[b'peer'] == b'ssh1':
             ui.write(_(b'creating ssh peer for wire protocol version 1\n'))
             peer = sshpeer.sshv1peer(
                 ui,
                 url,
                 proc,
                 stdin,
                 stdout,
                 stderr,
                 None,
                 autoreadstderr=autoreadstderr,
             )
         elif opts[b'peer'] == b'ssh2':
             ui.write(_(b'creating ssh peer for wire protocol version 2\n'))
             peer = sshpeer.sshv2peer(
                 ui,
                 url,
                 proc,
                 stdin,
                 stdout,
                 stderr,
                 None,
                 autoreadstderr=autoreadstderr,
             )
         elif opts[b'peer'] == b'raw':
             ui.write(_(b'using raw connection to peer\n'))
             peer = None
         else:
             ui.write(_(b'creating ssh peer from handshake results\n'))
             peer = sshpeer.makepeer(
                 ui,
                 url,
                 proc,
                 stdin,
                 stdout,
                 stderr,
                 autoreadstderr=autoreadstderr,
             )
 
     elif path:
         # We bypass hg.peer() so we can proxy the sockets.
         # TODO consider not doing this because we skip
         # ``hg.wirepeersetupfuncs`` and potentially other useful functionality.
         u = util.url(path)
         if u.scheme != b'http':
             raise error.Abort(_(b'only http:// paths are currently supported'))
 
         url, authinfo = u.authinfo()
         openerargs = {
             'useragent': b'Mercurial debugwireproto',
         }
 
         # Turn pipes/sockets into observers so we can log I/O.
         if ui.verbose:
             openerargs.update(
                 {
                     'loggingfh': ui,
                     'loggingname': b's',
                     'loggingopts': {'logdata': True, 'logdataapis': False,},
                 }
             )
 
         if ui.debugflag:
             openerargs['loggingopts']['logdataapis'] = True
 
         # Don't send default headers when in raw mode. This allows us to
         # bypass most of the behavior of our URL handling code so we can
         # have near complete control over what's sent on the wire.
         if opts[b'peer'] == b'raw':
             openerargs['sendaccept'] = False
 
         opener = urlmod.opener(ui, authinfo, **openerargs)
 
         if opts[b'peer'] == b'http2':
             ui.write(_(b'creating http peer for wire protocol version 2\n'))
             # We go through makepeer() because we need an API descriptor for
             # the peer instance to be useful.
             with ui.configoverride(
                 {(b'experimental', b'httppeer.advertise-v2'): True}
             ):
                 if opts[b'nologhandshake']:
                     ui.pushbuffer()
 
                 peer = httppeer.makepeer(ui, path, opener=opener)
 
                 if opts[b'nologhandshake']:
                     ui.popbuffer()
 
             if not isinstance(peer, httppeer.httpv2peer):
                 raise error.Abort(
                     _(
                         b'could not instantiate HTTP peer for '
                         b'wire protocol version 2'
                     ),
                     hint=_(
                         b'the server may not have the feature '
                         b'enabled or is not allowing this '
                         b'client version'
                     ),
                 )
 
         elif opts[b'peer'] == b'raw':
             ui.write(_(b'using raw connection to peer\n'))
             peer = None
         elif opts[b'peer']:
             raise error.Abort(
                 _(b'--peer %s not supported with HTTP peers') % opts[b'peer']
             )
         else:
             peer = httppeer.makepeer(ui, path, opener=opener)
 
         # We /could/ populate stdin/stdout with sock.makefile()...
     else:
         raise error.Abort(_(b'unsupported connection configuration'))
 
     batchedcommands = None
 
     # Now perform actions based on the parsed wire language instructions.
     for action, lines in blocks:
         if action in (b'raw', b'raw+'):
             if not stdin:
                 raise error.Abort(_(b'cannot call raw/raw+ on this peer'))
 
             # Concatenate the data together.
             data = b''.join(l.lstrip() for l in lines)
             data = stringutil.unescapestr(data)
             stdin.write(data)
 
             if action == b'raw+':
                 stdin.flush()
         elif action == b'flush':
             if not stdin:
                 raise error.Abort(_(b'cannot call flush on this peer'))
             stdin.flush()
         elif action.startswith(b'command'):
             if not peer:
                 raise error.Abort(
                     _(
                         b'cannot send commands unless peer instance '
                         b'is available'
                     )
                 )
 
             command = action.split(b' ', 1)[1]
 
             args = {}
             for line in lines:
                 # We need to allow empty values.
                 fields = line.lstrip().split(b' ', 1)
                 if len(fields) == 1:
                     key = fields[0]
                     value = b''
                 else:
                     key, value = fields
 
                 if value.startswith(b'eval:'):
                     value = stringutil.evalpythonliteral(value[5:])
                 else:
                     value = stringutil.unescapestr(value)
 
                 args[key] = value
 
             if batchedcommands is not None:
                 batchedcommands.append((command, args))
                 continue
 
             ui.status(_(b'sending %s command\n') % command)
 
             if b'PUSHFILE' in args:
                 with open(args[b'PUSHFILE'], 'rb') as fh:
                     del args[b'PUSHFILE']
                     res, output = peer._callpush(
                         command, fh, **pycompat.strkwargs(args)
                     )
                     ui.status(_(b'result: %s\n') % stringutil.escapestr(res))
                     ui.status(
                         _(b'remote output: %s\n') % stringutil.escapestr(output)
                     )
             else:
                 with peer.commandexecutor() as e:
                     res = e.callcommand(command, args).result()
 
                 if isinstance(res, wireprotov2peer.commandresponse):
                     val = res.objects()
                     ui.status(
                         _(b'response: %s\n')
                         % stringutil.pprint(val, bprefix=True, indent=2)
                     )
                 else:
                     ui.status(
                         _(b'response: %s\n')
                         % stringutil.pprint(res, bprefix=True, indent=2)
                     )
 
         elif action == b'batchbegin':
             if batchedcommands is not None:
                 raise error.Abort(_(b'nested batchbegin not allowed'))
 
             batchedcommands = []
         elif action == b'batchsubmit':
             # There is a batching API we could go through. But it would be
             # difficult to normalize requests into function calls. It is easier
             # to bypass this layer and normalize to commands + args.
             ui.status(
                 _(b'sending batch with %d sub-commands\n')
                 % len(batchedcommands)
             )
             assert peer is not None
             for i, chunk in enumerate(peer._submitbatch(batchedcommands)):
                 ui.status(
                     _(b'response #%d: %s\n') % (i, stringutil.escapestr(chunk))
                 )
 
             batchedcommands = None
 
         elif action.startswith(b'httprequest '):
             if not opener:
                 raise error.Abort(
                     _(b'cannot use httprequest without an HTTP peer')
                 )
 
             request = action.split(b' ', 2)
             if len(request) != 3:
                 raise error.Abort(
                     _(
                         b'invalid httprequest: expected format is '
                         b'"httprequest <method> <path>'
                     )
                 )
 
             method, httppath = request[1:]
             headers = {}
             body = None
             frames = []
             for line in lines:
                 line = line.lstrip()
                 m = re.match(b'^([a-zA-Z0-9_-]+): (.*)$', line)
                 if m:
                     # Headers need to use native strings.
                     key = pycompat.strurl(m.group(1))
                     value = pycompat.strurl(m.group(2))
                     headers[key] = value
                     continue
 
                 if line.startswith(b'BODYFILE '):
                     with open(line.split(b' ', 1), b'rb') as fh:
                         body = fh.read()
                 elif line.startswith(b'frame '):
                     frame = wireprotoframing.makeframefromhumanstring(
                         line[len(b'frame ') :]
                     )
 
                     frames.append(frame)
                 else:
                     raise error.Abort(
                         _(b'unknown argument to httprequest: %s') % line
                     )
 
             url = path + httppath
 
             if frames:
                 body = b''.join(bytes(f) for f in frames)
 
             req = urlmod.urlreq.request(pycompat.strurl(url), body, headers)
 
             # urllib.Request insists on using has_data() as a proxy for
             # determining the request method. Override that to use our
             # explicitly requested method.
             req.get_method = lambda: pycompat.sysstr(method)
 
             try:
                 res = opener.open(req)
                 body = res.read()
             except util.urlerr.urlerror as e:
                 # read() method must be called, but only exists in Python 2
                 getattr(e, 'read', lambda: None)()
                 continue
 
             ct = res.headers.get('Content-Type')
             if ct == 'application/mercurial-cbor':
                 ui.write(
                     _(b'cbor> %s\n')
                     % stringutil.pprint(
                         cborutil.decodeall(body), bprefix=True, indent=2
                     )
                 )
 
         elif action == b'close':
             assert peer is not None
             peer.close()
         elif action == b'readavailable':
             if not stdout or not stderr:
                 raise error.Abort(
                     _(b'readavailable not available on this peer')
                 )
 
             stdin.close()
             stdout.read()
             stderr.read()
 
         elif action == b'readline':
             if not stdout:
                 raise error.Abort(_(b'readline not available on this peer'))
             stdout.readline()
         elif action == b'ereadline':
             if not stderr:
                 raise error.Abort(_(b'ereadline not available on this peer'))
             stderr.readline()
         elif action.startswith(b'read '):
             count = int(action.split(b' ', 1)[1])
             if not stdout:
                 raise error.Abort(_(b'read not available on this peer'))
             stdout.read(count)
         elif action.startswith(b'eread '):
             count = int(action.split(b' ', 1)[1])
             if not stderr:
                 raise error.Abort(_(b'eread not available on this peer'))
             stderr.read(count)
         else:
             raise error.Abort(_(b'unknown action: %s') % action)
 
     if batchedcommands is not None:
         raise error.Abort(_(b'unclosed "batchbegin" request'))
 
     if peer:
         peer.close()
 
     if proc:
         proc.kill()

mercurial/pure/parsers.py

@@ -1,284 +1,284 b''
 # parsers.py - Python implementation of parsers.c
 #
 # Copyright 2009 Matt Mackall <[e-mail]> and others
 #
 # 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 struct
 import zlib
 
 from ..node import nullid, nullrev
 from .. import (
     pycompat,
     util,
 )
 
 from ..revlogutils import nodemap as nodemaputil
 
 stringio = pycompat.bytesio
 
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 
 # Some code below makes tuples directly because it's more convenient. However,
 # code outside this module should always use dirstatetuple.
 def dirstatetuple(*x):
     # x is a tuple
     return x
 
 
 indexformatng = b">Qiiiiii20s12x"
 indexfirst = struct.calcsize(b'Q')
 sizeint = struct.calcsize(b'i')
 indexsize = struct.calcsize(indexformatng)
 
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 
 def offset_type(offset, type):
     return int(int(offset) << 16 | type)
 
 
 class BaseIndexObject(object):
     @property
     def nodemap(self):
         msg = b"index.nodemap is deprecated, use index.[has_node|rev|get_rev]"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self._nodemap
 
     @util.propertycache
     def _nodemap(self):
         nodemap = nodemaputil.NodeMap({nullid: nullrev})
         for r in range(0, len(self)):
             n = self[r][7]
             nodemap[n] = r
         return nodemap
 
     def has_node(self, node):
         """return True if the node exist in the index"""
         return node in self._nodemap
 
     def rev(self, node):
         """return a revision for a node
 
         If the node is unknown, raise a RevlogError"""
         return self._nodemap[node]
 
     def get_rev(self, node):
         """return a revision for a node
 
         If the node is unknown, return None"""
         return self._nodemap.get(node)
 
     def _stripnodes(self, start):
         if '_nodemap' in vars(self):
             for r in range(start, len(self)):
                 n = self[r][7]
                 del self._nodemap[n]
 
     def clearcaches(self):
         self.__dict__.pop('_nodemap', None)
 
     def __len__(self):
         return self._lgt + len(self._extra)
 
     def append(self, tup):
         if '_nodemap' in vars(self):
             self._nodemap[tup[7]] = len(self)
         self._extra.append(tup)
 
     def _check_index(self, i):
         if not isinstance(i, int):
             raise TypeError(b"expecting int indexes")
         if i < 0 or i >= len(self):
             raise IndexError
 
     def __getitem__(self, i):
         if i == -1:
             return (0, 0, 0, -1, -1, -1, -1, nullid)
         self._check_index(i)
         if i >= self._lgt:
             return self._extra[i - self._lgt]
         index = self._calculate_index(i)
         r = struct.unpack(indexformatng, self._data[index : index + indexsize])
         if i == 0:
             e = list(r)
             type = gettype(e[0])
             e[0] = offset_type(0, type)
             return tuple(e)
         return r
 
 
 class IndexObject(BaseIndexObject):
     def __init__(self, data):
         assert len(data) % indexsize == 0
         self._data = data
         self._lgt = len(data) // indexsize
         self._extra = []
 
     def _calculate_index(self, i):
         return i * indexsize
 
     def __delitem__(self, i):
         if not isinstance(i, slice) or not i.stop == -1 or i.step is not None:
             raise ValueError(b"deleting slices only supports a:-1 with step 1")
         i = i.start
         self._check_index(i)
         self._stripnodes(i)
         if i < self._lgt:
             self._data = self._data[: i * indexsize]
             self._lgt = i
             self._extra = []
         else:
             self._extra = self._extra[: i - self._lgt]
 
 
 class PersistentNodeMapIndexObject(IndexObject):
     """a Debug oriented class to test persistent nodemap
 
     We need a simple python object to test API and higher level behavior. See
     the Rust implementation for  more serious usage. This should be used only
     through the dedicated `devel.persistent-nodemap` config.
     """
 
     def nodemap_data_all(self):
         """Return bytes containing a full serialization of a nodemap
 
         The nodemap should be valid for the full set of revisions in the
         index."""
         return nodemaputil.persistent_data(self)
 
     def nodemap_data_incremental(self):
         """Return bytes containing a incremental update to persistent nodemap
 
         This containst the data for an append-only update of the data provided
         in the last call to `update_nodemap_data`.
         """
         if self._nm_root is None:
             return None
         data = nodemaputil.update_persistent_data(
             self, self._nm_root, self._nm_max_idx, self._nm_rev
         )
         self._nm_root = self._nm_max_idx = self._nm_rev = None
         return data
 
-    def update_nodemap_data(self, nm_data):
-        """provide full blokc of persisted binary data for a nodemap
+    def update_nodemap_data(self, docket, nm_data):
+        """provide full block of persisted binary data for a nodemap
 
         The data are expected to come from disk. See `nodemap_data_all` for a
         produceur of such data."""
         if nm_data is not None:
             self._nm_root, self._nm_max_idx = nodemaputil.parse_data(nm_data)
             if self._nm_root:
-                self._nm_rev = len(self) - 1
+                self._nm_rev = docket.tip_rev
             else:
                 self._nm_root = self._nm_max_idx = self._nm_rev = None
 
 
 class InlinedIndexObject(BaseIndexObject):
     def __init__(self, data, inline=0):
         self._data = data
         self._lgt = self._inline_scan(None)
         self._inline_scan(self._lgt)
         self._extra = []
 
     def _inline_scan(self, lgt):
         off = 0
         if lgt is not None:
             self._offsets = [0] * lgt
         count = 0
         while off <= len(self._data) - indexsize:
             (s,) = struct.unpack(
                 b'>i', self._data[off + indexfirst : off + sizeint + indexfirst]
             )
             if lgt is not None:
                 self._offsets[count] = off
             count += 1
             off += indexsize + s
         if off != len(self._data):
             raise ValueError(b"corrupted data")
         return count
 
     def __delitem__(self, i):
         if not isinstance(i, slice) or not i.stop == -1 or i.step is not None:
             raise ValueError(b"deleting slices only supports a:-1 with step 1")
         i = i.start
         self._check_index(i)
         self._stripnodes(i)
         if i < self._lgt:
             self._offsets = self._offsets[:i]
             self._lgt = i
             self._extra = []
         else:
             self._extra = self._extra[: i - self._lgt]
 
     def _calculate_index(self, i):
         return self._offsets[i]
 
 
 def parse_index2(data, inline):
     if not inline:
         return IndexObject(data), None
     return InlinedIndexObject(data, inline), (0, data)
 
 
 def parse_index_devel_nodemap(data, inline):
     """like parse_index2, but alway return a PersistentNodeMapIndexObject
     """
     return PersistentNodeMapIndexObject(data), None
 
 
 def parse_dirstate(dmap, copymap, st):
     parents = [st[:20], st[20:40]]
     # dereference fields so they will be local in loop
     format = b">cllll"
     e_size = struct.calcsize(format)
     pos1 = 40
     l = len(st)
 
     # the inner loop
     while pos1 < l:
         pos2 = pos1 + e_size
         e = _unpack(b">cllll", st[pos1:pos2])  # a literal here is faster
         pos1 = pos2 + e[4]
         f = st[pos2:pos1]
         if b'\0' in f:
             f, c = f.split(b'\0')
             copymap[f] = c
         dmap[f] = e[:4]
     return parents
 
 
 def pack_dirstate(dmap, copymap, pl, now):
     now = int(now)
     cs = stringio()
     write = cs.write
     write(b"".join(pl))
     for f, e in pycompat.iteritems(dmap):
         if e[0] == b'n' and e[3] == now:
             # The file was last modified "simultaneously" with the current
             # write to dirstate (i.e. within the same second for file-
             # systems with a granularity of 1 sec). This commonly happens
             # for at least a couple of files on 'update'.
             # The user could change the file without changing its size
             # within the same second. Invalidate the file's mtime in
             # dirstate, forcing future 'status' calls to compare the
             # contents of the file if the size is the same. This prevents
             # mistakenly treating such files as clean.
             e = dirstatetuple(e[0], e[1], e[2], -1)
             dmap[f] = e
 
         if f in copymap:
             f = b"%s\0%s" % (f, copymap[f])
         e = _pack(b">cllll", e[0], e[1], e[2], e[3], len(f))
         write(e)
         write(f)
     return cs.getvalue()

mercurial/revlog.py

@@ -1,3033 +1,3033 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import io
 import os
 import struct
 import zlib
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullhex,
     nullid,
     nullrev,
     short,
     wdirfilenodeids,
     wdirhex,
     wdirid,
     wdirrev,
 )
 from .i18n import _
 from .pycompat import getattr
 from .revlogutils.constants import (
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     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_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,
     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_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, sidedata):
     return text, False
 
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 
 def getoffset(q):
     return int(q >> 16)
 
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 
 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)
 
 
 @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()
     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)
 
 
 # index v0:
 #  4 bytes: offset
 #  4 bytes: compressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 # 20 bytes: parent 1 nodeid
 # 20 bytes: parent 2 nodeid
 # 20 bytes: nodeid
 indexformatv0 = struct.Struct(b">4l20s20s20s")
 indexformatv0_pack = indexformatv0.pack
 indexformatv0_unpack = indexformatv0.unpack
 
 
 class revlogoldindex(list):
     @property
     def nodemap(self):
         msg = b"index.nodemap is deprecated, use index.[has_node|rev|get_rev]"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self._nodemap
 
     @util.propertycache
     def _nodemap(self):
         nodemap = nodemaputil.NodeMap({nullid: nullrev})
         for r in range(0, len(self)):
             n = self[r][7]
             nodemap[n] = r
         return nodemap
 
     def has_node(self, node):
         """return True if the node exist in the index"""
         return node in self._nodemap
 
     def rev(self, node):
         """return a revision for a node
 
         If the node is unknown, raise a RevlogError"""
         return self._nodemap[node]
 
     def get_rev(self, node):
         """return a revision for a node
 
         If the node is unknown, return None"""
         return self._nodemap.get(node)
 
     def append(self, tup):
         self._nodemap[tup[7]] = len(self)
         super(revlogoldindex, self).append(tup)
 
     def __delitem__(self, i):
         if not isinstance(i, slice) or not i.stop == -1 or i.step is not None:
             raise ValueError(b"deleting slices only supports a:-1 with step 1")
         for r in pycompat.xrange(i.start, len(self)):
             del self._nodemap[self[r][7]]
         super(revlogoldindex, self).__delitem__(i)
 
     def clearcaches(self):
         self.__dict__.pop('_nodemap', None)
 
     def __getitem__(self, i):
         if i == -1:
             return (0, 0, 0, -1, -1, -1, -1, nullid)
         return list.__getitem__(self, i)
 
 
 class revlogoldio(object):
     def __init__(self):
         self.size = indexformatv0.size
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap = nodemaputil.NodeMap({nullid: nullrev})
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off : off + s]
             off += s
             e = indexformatv0_unpack(cur)
             # transform to revlogv1 format
             e2 = (
                 offset_type(e[0], 0),
                 e[1],
                 -1,
                 e[2],
                 e[3],
                 nodemap.get(e[4], nullrev),
                 nodemap.get(e[5], nullrev),
                 e[6],
             )
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         index = revlogoldindex(index)
         return index, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise error.RevlogError(
                 _(b'index entry flags need revlog version 1')
             )
         e2 = (
             getoffset(entry[0]),
             entry[1],
             entry[3],
             entry[4],
             node(entry[5]),
             node(entry[6]),
             entry[7],
         )
         return indexformatv0_pack(*e2)
 
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = struct.Struct(b">Qiiiiii20s12x")
 indexformatng_pack = indexformatng.pack
 versionformat = struct.Struct(b">I")
 versionformat_pack = versionformat.pack
 versionformat_unpack = versionformat.unpack
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 
 class revlogio(object):
     def __init__(self):
         self.size = indexformatng.size
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, cache
 
     def packentry(self, entry, node, version, rev):
         p = indexformatng_pack(*entry)
         if rev == 0:
             p = versionformat_pack(version) + p[4:]
         return p
 
 
 NodemapRevlogIO = None
 
 if util.safehasattr(parsers, 'parse_index_devel_nodemap'):
 
     class NodemapRevlogIO(revlogio):
         """A debug oriented IO class that return a PersistentNodeMapIndexObject
 
         The PersistentNodeMapIndexObject object is meant to test the persistent nodemap feature.
         """
 
         def parseindex(self, data, inline):
             index, cache = parsers.parse_index_devel_nodemap(data, inline)
             return index, cache
 
 
 class rustrevlogio(revlogio):
     def parseindex(self, data, inline):
         index, cache = super(rustrevlogio, self).parseindex(data, inline)
         return rustrevlog.MixedIndex(index), cache
 
 
 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.
     """
 
     _flagserrorclass = error.RevlogError
 
     def __init__(
         self,
         opener,
         indexfile,
         datafile=None,
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
     ):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
 
         """
         self.upperboundcomp = upperboundcomp
         self.indexfile = indexfile
         self.datafile = datafile or (indexfile[:-2] + b".d")
         self.nodemap_file = None
         if persistentnodemap:
             self.nodemap_file = indexfile[:-2] + b".n"
 
         self.opener = opener
         #  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()
 
     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))
         if self.hassidedata:
             self._flagprocessors[REVIDX_SIDEDATA] = sidedatautil.processors
         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:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
             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 = versionformat_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)
                 )
 
             self._inline = versionflags & FLAG_INLINE_DATA
             # generaldelta implied by version 2 revlogs.
             self._generaldelta = True
 
         else:
             raise error.RevlogError(
                 _(b'unknown version (%d) in revlog %s') % (fmt, self.indexfile)
             )
         # 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 NodemapRevlogIO is not None
         )
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         elif devel_nodemap:
             self._io = NodemapRevlogIO()
         elif rustrevlog is not None and self.opener.options.get(b'rust.index'):
             self._io = rustrevlogio()
         try:
             d = self._io.parseindex(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:
-                    index.update_nodemap_data(nodemap_data[1])
+                    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 = {}
         # 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 clearcaches(self):
         self._revisioncache = None
         self._chainbasecache.clear()
         self._chunkcache = (0, b'')
         self._pcache = {}
         self.index.clearcaches()
 
     def rev(self, node):
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if node == wdirid or node in 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 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
 
         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)]
         return i[d[5]][7], i[d[6]][7]  # map revisions to nodes inline
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         clen = 0
         compresseddeltalen = 0
         while iterrev != e[3]:
             clen += 1
             compresseddeltalen += e[1]
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             if iterrev in chaininfocache:
                 t = chaininfocache[iterrev]
                 clen += t[0]
                 compresseddeltalen += t[1]
                 break
             e = index[iterrev]
         else:
             # Add text length of base since decompressing that also takes
             # work. For cache hits the length is already included.
             compresseddeltalen += e[1]
         r = (clen, compresseddeltalen)
         chaininfocache[rev] = r
         return r
 
     def _deltachain(self, rev, stoprev=None):
         """Obtain the delta chain for a revision.
 
         ``stoprev`` specifies a revision to stop at. If not specified, we
         stop at the base of the chain.
 
         Returns a 2-tuple of (chain, stopped) where ``chain`` is a list of
         revs in ascending order and ``stopped`` is a bool indicating whether
         ``stoprev`` was hit.
         """
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, self._generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
         generaldelta = self._generaldelta
 
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != stoprev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
 
         if iterrev == stoprev:
             stopped = True
         else:
             chain.append(iterrev)
             stopped = False
 
         chain.reverse()
         return chain, stopped
 
     def ancestors(self, revs, stoprev=0, inclusive=False):
         """Generate the ancestors of 'revs' in reverse 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
         elif util.safehasattr(parsers, b'rustlazyancestors'):
             lazyancestors = ancestor.rustlazyancestors
             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 = [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 = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid]  # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n)  # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update(
                             [p for p in self.parents(n) if p != nullid]
                         )
                     elif n in heads:  # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in 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 [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = set(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 nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node)  # quick search the index
                 return node
             except 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) == 40:
             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 = 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 nullhex.startswith(id):
                     nl.append(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, 41):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != wdirid:
                     raise error.LookupError(node, self.indexfile, _(b'no node'))
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == wdirid:
             for length in range(minlength, 41):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, 41):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return 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._io.size
             end += (endrev + 1) * self._io.size
         length = end - start
 
         return start, self._getsegment(start, length, df=df)
 
     def _chunk(self, rev, df=None):
         """Obtain a single decompressed chunk for a revision.
 
         Accepts an integer revision and an optional already-open file handle
         to be used for reading. If used, the seek position of the file will not
         be preserved.
 
         Returns a str holding uncompressed data for the requested revision.
         """
         return self.decompress(self._getsegmentforrevs(rev, rev, df=df)[1])
 
     def _chunks(self, revs, df=None, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self._inline
         iosize = self._io.size
         buffer = util.buffer
 
         l = []
         ladd = l.append
 
         if not self._withsparseread:
             slicedchunks = (revs,)
         else:
             slicedchunks = 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 == 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 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, {}
         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:
             try:
                 r = flagutil.processflagsread(self, rawtext, flags)
             except error.SidedataHashError as exc:
                 msg = _(b"integrity check failed on %s:%s sidedata key %d")
                 msg %= (self.indexfile, pycompat.bytestr(rev), exc.sidedatakey)
                 raise error.RevlogError(msg)
             text, validatehash, sidedata = 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 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
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self.indexfile
             )
 
         trindex = trinfo[2]
         if trindex is not None:
             dataoff = self.start(trindex)
         else:
             # revlog was stripped at start of transaction, use all leftover data
             trindex = len(self) - 1
             dataoff = self.end(tiprev)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
             # 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])
 
         with self._indexfp(b'w') as fp:
             self.version &= ~FLAG_INLINE_DATA
             self._inline = False
             io = self._io
             for i in self:
                 e = io.packentry(self.index[i], self.node, self.version, i)
                 fp.write(e)
 
             # the temp file replace the real index when we exit the context
             # manager
 
         tr.replace(self.indexfile, trindex * self._io.size)
         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 = {}
             flags = flags & ~REVIDX_SIDEDATA
         elif not self.hassidedata:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
         else:
             flags |= REVIDX_SIDEDATA
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(
             self, text, flags, sidedata=sidedata
         )
 
         # 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)
         if self.index.has_node(node):
             return node
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
     ):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         dfh = None
         if not self._inline:
             dfh = self._datafp(b"a+")
         ifh = self._indexfp(b"a+")
         try:
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 ifh,
                 dfh,
                 deltacomputer=deltacomputer,
             )
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def compress(self, data):
         """Generate a possibly-compressed representation of data."""
         if not data:
             return 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 %r') % t)
 
         return compressor.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         ifh,
         dfh,
         alwayscache=False,
         deltacomputer=None,
     ):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self.indexfile
             )
         if node == wdirid or node in 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.end(prev)
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(
                 revlog.size(self, cachedelta[0]), cachedelta[1]
             )
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             deltacomputer = deltautil.deltacomputer(self)
 
         revinfo = _revisioninfo(node, p1, p2, btext, textlen, cachedelta, flags)
 
         deltainfo = deltacomputer.finddeltainfo(revinfo, fh)
 
         e = (
             offset_type(offset, flags),
             deltainfo.deltalen,
             textlen,
             deltainfo.base,
             link,
             p1r,
             p2r,
             node,
         )
         self.index.append(e)
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         self._writeentry(
             transaction, ifh, dfh, entry, deltainfo.data, link, offset
         )
 
         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 node
 
     def _writeentry(self, transaction, ifh, dfh, entry, data, link, offset):
         # Files opened in a+ mode have inconsistent behavior on various
         # platforms. Windows requires that a file positioning call be made
         # when the file handle transitions between reads and writes. See
         # 3686fa2b8eee and the mixedfilemodewrapper in windows.py. On other
         # platforms, Python or the platform itself can be buggy. Some versions
         # of Solaris have been observed to not append at the end of the file
         # if the file was seeked to before the end. See issue4943 for more.
         #
         # We work around this issue by inserting a seek() before writing.
         # Note: This is likely not necessary on Python 3. 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])
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self._enforceinlinesize(transaction, ifh)
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
 
         If ``addrevisioncb`` is defined, it will be called with arguments of
         this revlog and the node that was added.
         """
 
         if self._writinghandles:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         nodes = []
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self._indexfp(b"a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self._datafp(b"a+")
 
         def flush():
             if dfh:
                 dfh.flush()
             ifh.flush()
 
         self._writinghandles = (ifh, dfh)
 
         try:
             deltacomputer = deltautil.deltacomputer(self)
             # loop through our set of deltas
             for data in deltas:
                 node, p1, p2, linknode, deltabase, delta, flags = data
                 link = linkmapper(linknode)
                 flags = flags or REVIDX_DEFAULT_FLAGS
 
                 nodes.append(node)
 
                 if self.index.has_node(node):
                     self._nodeduplicatecallback(transaction, node)
                     # this can happen if two branches make the same change
                     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.
                 self._addrevision(
                     node,
                     None,
                     transaction,
                     link,
                     p1,
                     p2,
                     flags,
                     (baserev, delta),
                     ifh,
                     dfh,
                     alwayscache=bool(addrevisioncb),
                     deltacomputer=deltacomputer,
                 )
 
                 if addrevisioncb:
                     addrevisioncb(self, node)
 
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self._datafp(b"a+")
                     ifh = self._indexfp(b"a+")
                     self._writinghandles = (ifh, dfh)
         finally:
             self._writinghandles = None
 
             if dfh:
                 dfh.close()
             ifh.close()
 
         return nodes
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self._censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta, flush):
         """Quickly check if a delta produces a censored revision."""
         if not self._censorable:
             return False
 
         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._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._revisioncache = None
         self._chaininfocache = {}
         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._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
     ):
         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,
         )
 
     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 triplet that control changes to sidedata content from the
         old revision to the new clone result:
 
             (dropall, filterout, update)
 
         * 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
         """
         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, [], {})
             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, filterout, update = sidedataactions
                 text, sidedata = self._revisiondata(rev)
                 if dropall:
                     sidedata = {}
                 for key in filterout:
                     sidedata.pop(key, None)
                 sidedata.update(update)
                 if not sidedata:
                     sidedata = None
                 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.version = self.version
         newrl._generaldelta = self._generaldelta
         newrl._io = self._io
 
         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

mercurial/revlogutils/nodemap.py

@@ -1,456 +1,463 b''
 # nodemap.py - nodemap related code and utilities
 #
 # Copyright 2019 Pierre-Yves David <[e-mail]>
 # Copyright 2019 George Racinet <[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 os
 import re
 import struct
 
 from .. import (
     error,
     node as nodemod,
     util,
 )
 
 
 class NodeMap(dict):
     def __missing__(self, x):
         raise error.RevlogError(b'unknown node: %s' % x)
 
 
 def persisted_data(revlog):
     """read the nodemap for a revlog from disk"""
     if revlog.nodemap_file is None:
         return None
     pdata = revlog.opener.tryread(revlog.nodemap_file)
     if not pdata:
         return None
     offset = 0
     (version,) = S_VERSION.unpack(pdata[offset : offset + S_VERSION.size])
     if version != ONDISK_VERSION:
         return None
     offset += S_VERSION.size
-    (uid_size,) = S_HEADER.unpack(pdata[offset : offset + S_HEADER.size])
+    headers = S_HEADER.unpack(pdata[offset : offset + S_HEADER.size])
+    uid_size, tip_rev = headers
     offset += S_HEADER.size
     docket = NodeMapDocket(pdata[offset : offset + uid_size])
+    docket.tip_rev = tip_rev
 
     filename = _rawdata_filepath(revlog, docket)
     return docket, revlog.opener.tryread(filename)
 
 
 def setup_persistent_nodemap(tr, revlog):
     """Install whatever is needed transaction side to persist a nodemap on disk
 
     (only actually persist the nodemap if this is relevant for this revlog)
     """
     if revlog._inline:
         return  # inlined revlog are too small for this to be relevant
     if revlog.nodemap_file is None:
         return  # we do not use persistent_nodemap on this revlog
     callback_id = b"revlog-persistent-nodemap-%s" % revlog.nodemap_file
     if tr.hasfinalize(callback_id):
         return  # no need to register again
     tr.addfinalize(callback_id, lambda tr: _persist_nodemap(tr, revlog))
 
 
 def _persist_nodemap(tr, revlog):
     """Write nodemap data on disk for a given revlog
     """
     if getattr(revlog, 'filteredrevs', ()):
         raise error.ProgrammingError(
             "cannot persist nodemap of a filtered changelog"
         )
     if revlog.nodemap_file is None:
         msg = "calling persist nodemap on a revlog without the feature enableb"
         raise error.ProgrammingError(msg)
 
     can_incremental = util.safehasattr(revlog.index, "nodemap_data_incremental")
     ondisk_docket = revlog._nodemap_docket
 
     # first attemp an incremental update of the data
     if can_incremental and ondisk_docket is not None:
         target_docket = revlog._nodemap_docket.copy()
         data = revlog.index.nodemap_data_incremental()
         datafile = _rawdata_filepath(revlog, target_docket)
         # EXP-TODO: if this is a cache, this should use a cache vfs, not a
         # store vfs
         with revlog.opener(datafile, b'a') as fd:
             fd.write(data)
     else:
         # otherwise fallback to a full new export
         target_docket = NodeMapDocket()
         datafile = _rawdata_filepath(revlog, target_docket)
         if util.safehasattr(revlog.index, "nodemap_data_all"):
             data = revlog.index.nodemap_data_all()
         else:
             data = persistent_data(revlog.index)
         # EXP-TODO: if this is a cache, this should use a cache vfs, not a
         # store vfs
         with revlog.opener(datafile, b'w') as fd:
             fd.write(data)
+    target_docket.tip_rev = revlog.tiprev()
     # EXP-TODO: if this is a cache, this should use a cache vfs, not a
     # store vfs
     with revlog.opener(revlog.nodemap_file, b'w', atomictemp=True) as fp:
         fp.write(target_docket.serialize())
     revlog._nodemap_docket = target_docket
     # EXP-TODO: if the transaction abort, we should remove the new data and
     # reinstall the old one.
 
     # search for old index file in all cases, some older process might have
     # left one behind.
     olds = _other_rawdata_filepath(revlog, target_docket)
     if olds:
         realvfs = getattr(revlog, '_realopener', revlog.opener)
 
         def cleanup(tr):
             for oldfile in olds:
                 realvfs.tryunlink(oldfile)
 
         callback_id = b"revlog-cleanup-nodemap-%s" % revlog.nodemap_file
         tr.addpostclose(callback_id, cleanup)
 
 
 ### Nodemap docket file
 #
 # The nodemap data are stored on disk using 2 files:
 #
 # * a raw data files containing a persistent nodemap
 #   (see `Nodemap Trie` section)
 #
 # * a small "docket" file containing medatadata
 #
 # While the nodemap data can be multiple tens of megabytes, the "docket" is
 # small, it is easy to update it automatically or to duplicated its content
 # during a transaction.
 #
 # Multiple raw data can exist at the same time (The currently valid one and a
 # new one beind used by an in progress transaction). To accomodate this, the
 # filename hosting the raw data has a variable parts. The exact filename is
 # specified inside the "docket" file.
 #
 # The docket file contains information to find, qualify and validate the raw
 # data. Its content is currently very light, but it will expand as the on disk
 # nodemap gains the necessary features to be used in production.
 
 # version 0 is experimental, no BC garantee, do no use outside of tests.
 ONDISK_VERSION = 0
 
 S_VERSION = struct.Struct(">B")
-S_HEADER = struct.Struct(">B")
+S_HEADER = struct.Struct(">BQ")
 
 ID_SIZE = 8
 
 
 def _make_uid():
     """return a new unique identifier.
 
     The identifier is random and composed of ascii characters."""
     return nodemod.hex(os.urandom(ID_SIZE))
 
 
 class NodeMapDocket(object):
     """metadata associated with persistent nodemap data
 
     The persistent data may come from disk or be on their way to disk.
     """
 
     def __init__(self, uid=None):
         if uid is None:
             uid = _make_uid()
         self.uid = uid
+        self.tip_rev = None
 
     def copy(self):
-        return NodeMapDocket(uid=self.uid)
+        new = NodeMapDocket(uid=self.uid)
+        new.tip_rev = self.tip_rev
+        return new
 
     def serialize(self):
         """return serialized bytes for a docket using the passed uid"""
         data = []
         data.append(S_VERSION.pack(ONDISK_VERSION))
-        data.append(S_HEADER.pack(len(self.uid)))
+        headers = (len(self.uid), self.tip_rev)
+        data.append(S_HEADER.pack(*headers))
         data.append(self.uid)
         return b''.join(data)
 
 
 def _rawdata_filepath(revlog, docket):
     """The (vfs relative) nodemap's rawdata file for a given uid"""
     prefix = revlog.nodemap_file[:-2]
     return b"%s-%s.nd" % (prefix, docket.uid)
 
 
 def _other_rawdata_filepath(revlog, docket):
     prefix = revlog.nodemap_file[:-2]
     pattern = re.compile(b"(^|/)%s-[0-9a-f]+\.nd$" % prefix)
     new_file_path = _rawdata_filepath(revlog, docket)
     new_file_name = revlog.opener.basename(new_file_path)
     dirpath = revlog.opener.dirname(new_file_path)
     others = []
     for f in revlog.opener.listdir(dirpath):
         if pattern.match(f) and f != new_file_name:
             others.append(f)
     return others
 
 
 ### Nodemap Trie
 #
 # This is a simple reference implementation to compute and persist a nodemap
 # trie. This reference implementation is write only. The python version of this
 # is not expected to be actually used, since it wont provide performance
 # improvement over existing non-persistent C implementation.
 #
 # The nodemap is persisted as Trie using 4bits-address/16-entries block. each
 # revision can be adressed using its node shortest prefix.
 #
 # The trie is stored as a sequence of block. Each block contains 16 entries
 # (signed 64bit integer, big endian). Each entry can be one of the following:
 #
 #  * value >=  0 -> index of sub-block
 #  * value == -1 -> no value
 #  * value <  -1 -> a revision value: rev = -(value+10)
 #
 # The implementation focus on simplicity, not on performance. A Rust
 # implementation should provide a efficient version of the same binary
 # persistence. This reference python implementation is never meant to be
 # extensively use in production.
 
 
 def persistent_data(index):
     """return the persistent binary form for a nodemap for a given index
     """
     trie = _build_trie(index)
     return _persist_trie(trie)
 
 
 def update_persistent_data(index, root, max_idx, last_rev):
     """return the incremental update for persistent nodemap from a given index
     """
     trie = _update_trie(index, root, last_rev)
     return _persist_trie(trie, existing_idx=max_idx)
 
 
 S_BLOCK = struct.Struct(">" + ("l" * 16))
 
 NO_ENTRY = -1
 # rev 0 need to be -2 because 0 is used by block, -1 is a special value.
 REV_OFFSET = 2
 
 
 def _transform_rev(rev):
     """Return the number used to represent the rev in the tree.
 
     (or retrieve a rev number from such representation)
 
     Note that this is an involution, a function equal to its inverse (i.e.
     which gives the identity when applied to itself).
     """
     return -(rev + REV_OFFSET)
 
 
 def _to_int(hex_digit):
     """turn an hexadecimal digit into a proper integer"""
     return int(hex_digit, 16)
 
 
 class Block(dict):
     """represent a block of the Trie
 
     contains up to 16 entry indexed from 0 to 15"""
 
     def __init__(self):
         super(Block, self).__init__()
         # If this block exist on disk, here is its ID
         self.ondisk_id = None
 
     def __iter__(self):
         return iter(self.get(i) for i in range(16))
 
 
 def _build_trie(index):
     """build a nodemap trie
 
     The nodemap stores revision number for each unique prefix.
 
     Each block is a dictionary with keys in `[0, 15]`. Values are either
     another block or a revision number.
     """
     root = Block()
     for rev in range(len(index)):
         hex = nodemod.hex(index[rev][7])
         _insert_into_block(index, 0, root, rev, hex)
     return root
 
 
 def _update_trie(index, root, last_rev):
     """consume"""
     for rev in range(last_rev + 1, len(index)):
         hex = nodemod.hex(index[rev][7])
         _insert_into_block(index, 0, root, rev, hex)
     return root
 
 
 def _insert_into_block(index, level, block, current_rev, current_hex):
     """insert a new revision in a block
 
     index: the index we are adding revision for
     level: the depth of the current block in the trie
     block: the block currently being considered
     current_rev: the revision number we are adding
     current_hex: the hexadecimal representation of the of that revision
     """
     if block.ondisk_id is not None:
         block.ondisk_id = None
     hex_digit = _to_int(current_hex[level : level + 1])
     entry = block.get(hex_digit)
     if entry is None:
         # no entry, simply store the revision number
         block[hex_digit] = current_rev
     elif isinstance(entry, dict):
         # need to recurse to an underlying block
         _insert_into_block(index, level + 1, entry, current_rev, current_hex)
     else:
         # collision with a previously unique prefix, inserting new
         # vertices to fit both entry.
         other_hex = nodemod.hex(index[entry][7])
         other_rev = entry
         new = Block()
         block[hex_digit] = new
         _insert_into_block(index, level + 1, new, other_rev, other_hex)
         _insert_into_block(index, level + 1, new, current_rev, current_hex)
 
 
 def _persist_trie(root, existing_idx=None):
     """turn a nodemap trie into persistent binary data
 
     See `_build_trie` for nodemap trie structure"""
     block_map = {}
     if existing_idx is not None:
         base_idx = existing_idx + 1
     else:
         base_idx = 0
     chunks = []
     for tn in _walk_trie(root):
         if tn.ondisk_id is not None:
             block_map[id(tn)] = tn.ondisk_id
         else:
             block_map[id(tn)] = len(chunks) + base_idx
             chunks.append(_persist_block(tn, block_map))
     return b''.join(chunks)
 
 
 def _walk_trie(block):
     """yield all the block in a trie
 
     Children blocks are always yield before their parent block.
     """
     for (_, item) in sorted(block.items()):
         if isinstance(item, dict):
             for sub_block in _walk_trie(item):
                 yield sub_block
     yield block
 
 
 def _persist_block(block_node, block_map):
     """produce persistent binary data for a single block
 
     Children block are assumed to be already persisted and present in
     block_map.
     """
     data = tuple(_to_value(v, block_map) for v in block_node)
     return S_BLOCK.pack(*data)
 
 
 def _to_value(item, block_map):
     """persist any value as an integer"""
     if item is None:
         return NO_ENTRY
     elif isinstance(item, dict):
         return block_map[id(item)]
     else:
         return _transform_rev(item)
 
 
 def parse_data(data):
     """parse parse nodemap data into a nodemap Trie"""
     if (len(data) % S_BLOCK.size) != 0:
         msg = "nodemap data size is not a multiple of block size (%d): %d"
         raise error.Abort(msg % (S_BLOCK.size, len(data)))
     if not data:
         return Block(), None
     block_map = {}
     new_blocks = []
     for i in range(0, len(data), S_BLOCK.size):
         block = Block()
         block.ondisk_id = len(block_map)
         block_map[block.ondisk_id] = block
         block_data = data[i : i + S_BLOCK.size]
         values = S_BLOCK.unpack(block_data)
         new_blocks.append((block, values))
     for b, values in new_blocks:
         for idx, v in enumerate(values):
             if v == NO_ENTRY:
                 continue
             elif v >= 0:
                 b[idx] = block_map[v]
             else:
                 b[idx] = _transform_rev(v)
     return block, i // S_BLOCK.size
 
 
 # debug utility
 
 
 def check_data(ui, index, data):
     """verify that the provided nodemap data are valid for the given idex"""
     ret = 0
     ui.status((b"revision in index:   %d\n") % len(index))
     root, __ = parse_data(data)
     all_revs = set(_all_revisions(root))
     ui.status((b"revision in nodemap: %d\n") % len(all_revs))
     for r in range(len(index)):
         if r not in all_revs:
             msg = b"  revision missing from nodemap: %d\n" % r
             ui.write_err(msg)
             ret = 1
         else:
             all_revs.remove(r)
         nm_rev = _find_node(root, nodemod.hex(index[r][7]))
         if nm_rev is None:
             msg = b"  revision node does not match any entries: %d\n" % r
             ui.write_err(msg)
             ret = 1
         elif nm_rev != r:
             msg = (
                 b"  revision node does not match the expected revision: "
                 b"%d != %d\n" % (r, nm_rev)
             )
             ui.write_err(msg)
             ret = 1
 
     if all_revs:
         for r in sorted(all_revs):
             msg = b"  extra revision in  nodemap: %d\n" % r
             ui.write_err(msg)
         ret = 1
     return ret
 
 
 def _all_revisions(root):
     """return all revisions stored in a Trie"""
     for block in _walk_trie(root):
         for v in block:
             if v is None or isinstance(v, Block):
                 continue
             yield v
 
 
 def _find_node(block, node):
     """find the revision associated with a given node"""
     entry = block.get(_to_int(node[0:1]))
     if isinstance(entry, dict):
         return _find_node(entry, node[1:])
     return entry

tests/test-persistent-nodemap.t

@@ -1,71 +1,73 b''
 ===================================
 Test the persistent on-disk nodemap
 ===================================
 
 
   $ hg init test-repo
   $ cd test-repo
   $ cat << EOF >> .hg/hgrc
   > [experimental]
   > exp-persistent-nodemap=yes
   > [devel]
   > persistent-nodemap=yes
   > EOF
   $ hg debugbuilddag .+5000
   $ hg debugnodemap --metadata
   uid: ???????????????? (glob)
+  tip-rev: 5000
   $ f --size .hg/store/00changelog.n
-  .hg/store/00changelog.n: size=18
+  .hg/store/00changelog.n: size=26
   $ f --sha256 .hg/store/00changelog-*.nd
   .hg/store/00changelog-????????????????.nd: sha256=b961925120e1c9bc345c199b2cc442abc477029fdece37ef9d99cbe59c0558b7 (glob)
   $ hg debugnodemap --dump-new | f --sha256 --size
   size=122880, sha256=b961925120e1c9bc345c199b2cc442abc477029fdece37ef9d99cbe59c0558b7
   $ hg debugnodemap --dump-disk | f --sha256 --bytes=256 --hexdump --size
   size=122880, sha256=b961925120e1c9bc345c199b2cc442abc477029fdece37ef9d99cbe59c0558b7
   0000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0010: ff ff ff ff ff ff ff ff ff ff fa c2 ff ff ff ff |................|
   0020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0030: ff ff ff ff ff ff ed b3 ff ff ff ff ff ff ff ff |................|
   0040: ff ff ff ff ff ff ee 34 00 00 00 00 ff ff ff ff |.......4........|
   0050: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0060: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0070: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   0080: ff ff ff ff ff ff f8 50 ff ff ff ff ff ff ff ff |.......P........|
   0090: ff ff ff ff ff ff ff ff ff ff ec c7 ff ff ff ff |................|
   00a0: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   00b0: ff ff ff ff ff ff fa be ff ff f2 fc ff ff ff ff |................|
   00c0: ff ff ff ff ff ff ef ea ff ff ff ff ff ff f9 17 |................|
   00d0: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   00e0: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   00f0: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff |................|
   $ hg debugnodemap --check
   revision in index:   5001
   revision in nodemap: 5001
 
 add a new commit
 
   $ hg up
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo foo > foo
   $ hg add foo
   $ hg ci -m 'foo'
   $ hg debugnodemap --metadata
   uid: ???????????????? (glob)
+  tip-rev: 5001
   $ f --size .hg/store/00changelog.n
-  .hg/store/00changelog.n: size=18
+  .hg/store/00changelog.n: size=26
 
 (The pure code use the debug code that perform incremental update, the C code reencode from scratch)
 
 #if pure
   $ f --sha256 .hg/store/00changelog-*.nd --size
   .hg/store/00changelog-????????????????.nd: size=123072, sha256=136472751566c8198ff09e306a7d2f9bd18bd32298d614752b73da4d6df23340 (glob)
 
 #else
   $ f --sha256 .hg/store/00changelog-*.nd --size
   .hg/store/00changelog-????????????????.nd: size=122880, sha256=bfafebd751c4f6d116a76a37a1dee2a251747affe7efbcc4f4842ccc746d4db9 (glob)
 
 #endif
 
   $ hg debugnodemap --check
   revision in index:   5002
   revision in nodemap: 5002