verify: allow the storage to signal when renames can be tested on `skipread`

This applies the new marker in the lfs handler to show it in action, and adds
the test mentioned at the beginning of the series to show that fulltext isn't
necessary in the LFS case.

The existing `skipread` isn't enough, because it is also set if an error occurs
reading the revlog data, or the data is censored.  It could probably be cleared,
but then it technically violates the interface contract.  That wouldn't matter
for the existing verify algorithm, but it isn't clear how that will change as
alternate storage support is added.

The flag is probably pretty revlog specific, given the comments in verify.py.
But there's already filelog specific stuff in there and I'm not sure what future
storage will bring, so I don't want to over-engineer this.  Likewise, I'm not
sure that we want the verify method for each storage type to completely drive
the bus when it comes to detecting renames, so I don't want to go down the
rabbithole of having verifyintegrity() return metadata hints at this point.

Differential Revision: https://phab.mercurial-scm.org/D7713

hgext/lfs/wrapper.py

@@ -1,542 +1,546 b''
 # wrapper.py - methods wrapping core mercurial logic
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid, short
 from mercurial.pycompat import (
     getattr,
     setattr,
 )
 
 from mercurial import (
     bundle2,
     changegroup,
     cmdutil,
     context,
     error,
     exchange,
     exthelper,
     localrepo,
     pycompat,
     revlog,
     scmutil,
     upgrade,
     util,
     vfs as vfsmod,
     wireprotov1server,
 )
 
 from mercurial.interfaces import repository
 
 from mercurial.utils import (
     storageutil,
     stringutil,
 )
 
 from ..largefiles import lfutil
 
 from . import (
     blobstore,
     pointer,
 )
 
 eh = exthelper.exthelper()
 
 
 @eh.wrapfunction(localrepo, b'makefilestorage')
 def localrepomakefilestorage(orig, requirements, features, **kwargs):
     if b'lfs' in requirements:
         features.add(repository.REPO_FEATURE_LFS)
 
     return orig(requirements=requirements, features=features, **kwargs)
 
 
 @eh.wrapfunction(changegroup, b'allsupportedversions')
 def allsupportedversions(orig, ui):
     versions = orig(ui)
     versions.add(b'03')
     return versions
 
 
 @eh.wrapfunction(wireprotov1server, b'_capabilities')
 def _capabilities(orig, repo, proto):
     '''Wrap server command to announce lfs server capability'''
     caps = orig(repo, proto)
     if util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         # Advertise a slightly different capability when lfs is *required*, so
         # that the client knows it MUST load the extension.  If lfs is not
         # required on the server, there's no reason to autoload the extension
         # on the client.
         if b'lfs' in repo.requirements:
             caps.append(b'lfs-serve')
 
         caps.append(b'lfs')
     return caps
 
 
 def bypasscheckhash(self, text):
     return False
 
 
 def readfromstore(self, text):
     """Read filelog content from local blobstore transform for flagprocessor.
 
     Default tranform for flagprocessor, returning contents from blobstore.
     Returns a 2-typle (text, validatehash) where validatehash is True as the
     contents of the blobstore should be checked using checkhash.
     """
     p = pointer.deserialize(text)
     oid = p.oid()
     store = self.opener.lfslocalblobstore
     if not store.has(oid):
         p.filename = self.filename
         self.opener.lfsremoteblobstore.readbatch([p], store)
 
     # The caller will validate the content
     text = store.read(oid, verify=False)
 
     # pack hg filelog metadata
     hgmeta = {}
     for k in p.keys():
         if k.startswith(b'x-hg-'):
             name = k[len(b'x-hg-') :]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith(b'\1\n'):
         text = storageutil.packmeta(hgmeta, text)
 
     return (text, True, {})
 
 
 def writetostore(self, text, sidedata):
     # hg filelog metadata (includes rename, etc)
     hgmeta, offset = storageutil.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
 
     # git-lfs only supports sha256
     oid = hex(hashlib.sha256(text).digest())
     self.opener.lfslocalblobstore.write(oid, text)
 
     # replace contents with metadata
     longoid = b'sha256:%s' % oid
     metadata = pointer.gitlfspointer(oid=longoid, size=b'%d' % len(text))
 
     # by default, we expect the content to be binary. however, LFS could also
     # be used for non-binary content. add a special entry for non-binary data.
     # this will be used by filectx.isbinary().
     if not stringutil.binary(text):
         # not hg filelog metadata (affecting commit hash), no "x-hg-" prefix
         metadata[b'x-is-binary'] = b'0'
 
     # translate hg filelog metadata to lfs metadata with "x-hg-" prefix
     if hgmeta is not None:
         for k, v in pycompat.iteritems(hgmeta):
             metadata[b'x-hg-%s' % k] = v
 
     rawtext = metadata.serialize()
     return (rawtext, False)
 
 
 def _islfs(rlog, node=None, rev=None):
     if rev is None:
         if node is None:
             # both None - likely working copy content where node is not ready
             return False
         rev = rlog.rev(node)
     else:
         node = rlog.node(rev)
     if node == nullid:
         return False
     flags = rlog.flags(rev)
     return bool(flags & revlog.REVIDX_EXTSTORED)
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogaddrevision(
     orig,
     self,
     text,
     transaction,
     link,
     p1,
     p2,
     cachedelta=None,
     node=None,
     flags=revlog.REVIDX_DEFAULT_FLAGS,
     **kwds
 ):
     # The matcher isn't available if reposetup() wasn't called.
     lfstrack = self._revlog.opener.options.get(b'lfstrack')
 
     if lfstrack:
         textlen = len(text)
         # exclude hg rename meta from file size
         meta, offset = storageutil.parsemeta(text)
         if offset:
             textlen -= offset
 
         if lfstrack(self._revlog.filename, textlen):
             flags |= revlog.REVIDX_EXTSTORED
 
     return orig(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=cachedelta,
         node=node,
         flags=flags,
         **kwds
     )
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogrenamed(orig, self, node):
     if _islfs(self._revlog, node):
         rawtext = self._revlog.rawdata(node)
         if not rawtext:
             return False
         metadata = pointer.deserialize(rawtext)
         if b'x-hg-copy' in metadata and b'x-hg-copyrev' in metadata:
             return metadata[b'x-hg-copy'], bin(metadata[b'x-hg-copyrev'])
         else:
             return False
     return orig(self, node)
 
 
 # Wrapping may also be applied by remotefilelog
 def filelogsize(orig, self, rev):
     if _islfs(self._revlog, rev=rev):
         # fast path: use lfs metadata to answer size
         rawtext = self._revlog.rawdata(rev)
         metadata = pointer.deserialize(rawtext)
         return int(metadata[b'size'])
     return orig(self, rev)
 
 
 @eh.wrapfunction(revlog, b'_verify_revision')
 def _verify_revision(orig, rl, skipflags, state, node):
     if _islfs(rl, node=node):
         rawtext = rl.rawdata(node)
         metadata = pointer.deserialize(rawtext)
 
         # Don't skip blobs that are stored locally, as local verification is
         # relatively cheap and there's no other way to verify the raw data in
         # the revlog.
         if rl.opener.lfslocalblobstore.has(metadata.oid()):
             skipflags &= ~revlog.REVIDX_EXTSTORED
+        elif skipflags & revlog.REVIDX_EXTSTORED:
+            # The wrapped method will set `skipread`, but there's enough local
+            # info to check renames.
+            state[b'safe_renamed'].add(node)
 
     orig(rl, skipflags, state, node)
 
 
 @eh.wrapfunction(context.basefilectx, b'cmp')
 def filectxcmp(orig, self, fctx):
     """returns True if text is different than fctx"""
     # some fctx (ex. hg-git) is not based on basefilectx and do not have islfs
     if self.islfs() and getattr(fctx, 'islfs', lambda: False)():
         # fast path: check LFS oid
         p1 = pointer.deserialize(self.rawdata())
         p2 = pointer.deserialize(fctx.rawdata())
         return p1.oid() != p2.oid()
     return orig(self, fctx)
 
 
 @eh.wrapfunction(context.basefilectx, b'isbinary')
 def filectxisbinary(orig, self):
     if self.islfs():
         # fast path: use lfs metadata to answer isbinary
         metadata = pointer.deserialize(self.rawdata())
         # if lfs metadata says nothing, assume it's binary by default
         return bool(int(metadata.get(b'x-is-binary', 1)))
     return orig(self)
 
 
 def filectxislfs(self):
     return _islfs(self.filelog()._revlog, self.filenode())
 
 
 @eh.wrapfunction(cmdutil, b'_updatecatformatter')
 def _updatecatformatter(orig, fm, ctx, matcher, path, decode):
     orig(fm, ctx, matcher, path, decode)
     fm.data(rawdata=ctx[path].rawdata())
 
 
 @eh.wrapfunction(scmutil, b'wrapconvertsink')
 def convertsink(orig, sink):
     sink = orig(sink)
     if sink.repotype == b'hg':
 
         class lfssink(sink.__class__):
             def putcommit(
                 self,
                 files,
                 copies,
                 parents,
                 commit,
                 source,
                 revmap,
                 full,
                 cleanp2,
             ):
                 pc = super(lfssink, self).putcommit
                 node = pc(
                     files,
                     copies,
                     parents,
                     commit,
                     source,
                     revmap,
                     full,
                     cleanp2,
                 )
 
                 if b'lfs' not in self.repo.requirements:
                     ctx = self.repo[node]
 
                     # The file list may contain removed files, so check for
                     # membership before assuming it is in the context.
                     if any(f in ctx and ctx[f].islfs() for f, n in files):
                         self.repo.requirements.add(b'lfs')
                         self.repo._writerequirements()
 
                 return node
 
         sink.__class__ = lfssink
 
     return sink
 
 
 # bundlerepo uses "vfsmod.readonlyvfs(othervfs)", we need to make sure lfs
 # options and blob stores are passed from othervfs to the new readonlyvfs.
 @eh.wrapfunction(vfsmod.readonlyvfs, b'__init__')
 def vfsinit(orig, self, othervfs):
     orig(self, othervfs)
     # copy lfs related options
     for k, v in othervfs.options.items():
         if k.startswith(b'lfs'):
             self.options[k] = v
     # also copy lfs blobstores. note: this can run before reposetup, so lfs
     # blobstore attributes are not always ready at this time.
     for name in [b'lfslocalblobstore', b'lfsremoteblobstore']:
         if util.safehasattr(othervfs, name):
             setattr(self, name, getattr(othervfs, name))
 
 
 def _prefetchfiles(repo, revs, match):
     """Ensure that required LFS blobs are present, fetching them as a group if
     needed."""
     if not util.safehasattr(repo.svfs, b'lfslocalblobstore'):
         return
 
     pointers = []
     oids = set()
     localstore = repo.svfs.lfslocalblobstore
 
     for rev in revs:
         ctx = repo[rev]
         for f in ctx.walk(match):
             p = pointerfromctx(ctx, f)
             if p and p.oid() not in oids and not localstore.has(p.oid()):
                 p.filename = f
                 pointers.append(p)
                 oids.add(p.oid())
 
     if pointers:
         # Recalculating the repo store here allows 'paths.default' that is set
         # on the repo by a clone command to be used for the update.
         blobstore.remote(repo).readbatch(pointers, localstore)
 
 
 def _canskipupload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, b'lfsremoteblobstore'):
         return True
 
     # if remotestore is a null store, upload is a no-op and can be skipped
     return isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 
 def candownload(repo):
     # Skip if this hasn't been passed to reposetup()
     if not util.safehasattr(repo.svfs, b'lfsremoteblobstore'):
         return False
 
     # if remotestore is a null store, downloads will lead to nothing
     return not isinstance(repo.svfs.lfsremoteblobstore, blobstore._nullremote)
 
 
 def uploadblobsfromrevs(repo, revs):
     '''upload lfs blobs introduced by revs
 
     Note: also used by other extensions e. g. infinitepush. avoid renaming.
     '''
     if _canskipupload(repo):
         return
     pointers = extractpointers(repo, revs)
     uploadblobs(repo, pointers)
 
 
 def prepush(pushop):
     """Prepush hook.
 
     Read through the revisions to push, looking for filelog entries that can be
     deserialized into metadata so that we can block the push on their upload to
     the remote blobstore.
     """
     return uploadblobsfromrevs(pushop.repo, pushop.outgoing.missing)
 
 
 @eh.wrapfunction(exchange, b'push')
 def push(orig, repo, remote, *args, **kwargs):
     """bail on push if the extension isn't enabled on remote when needed, and
     update the remote store based on the destination path."""
     if b'lfs' in repo.requirements:
         # If the remote peer is for a local repo, the requirement tests in the
         # base class method enforce lfs support.  Otherwise, some revisions in
         # this repo use lfs, and the remote repo needs the extension loaded.
         if not remote.local() and not remote.capable(b'lfs'):
             # This is a copy of the message in exchange.push() when requirements
             # are missing between local repos.
             m = _(b"required features are not supported in the destination: %s")
             raise error.Abort(
                 m % b'lfs', hint=_(b'enable the lfs extension on the server')
             )
 
         # Repositories where this extension is disabled won't have the field.
         # But if there's a requirement, then the extension must be loaded AND
         # there may be blobs to push.
         remotestore = repo.svfs.lfsremoteblobstore
         try:
             repo.svfs.lfsremoteblobstore = blobstore.remote(repo, remote.url())
             return orig(repo, remote, *args, **kwargs)
         finally:
             repo.svfs.lfsremoteblobstore = remotestore
     else:
         return orig(repo, remote, *args, **kwargs)
 
 
 # when writing a bundle via "hg bundle" command, upload related LFS blobs
 @eh.wrapfunction(bundle2, b'writenewbundle')
 def writenewbundle(
     orig, ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
 ):
     """upload LFS blobs added by outgoing revisions on 'hg bundle'"""
     uploadblobsfromrevs(repo, outgoing.missing)
     return orig(
         ui, repo, source, filename, bundletype, outgoing, *args, **kwargs
     )
 
 
 def extractpointers(repo, revs):
     """return a list of lfs pointers added by given revs"""
     repo.ui.debug(b'lfs: computing set of blobs to upload\n')
     pointers = {}
 
     makeprogress = repo.ui.makeprogress
     with makeprogress(
         _(b'lfs search'), _(b'changesets'), len(revs)
     ) as progress:
         for r in revs:
             ctx = repo[r]
             for p in pointersfromctx(ctx).values():
                 pointers[p.oid()] = p
             progress.increment()
         return sorted(pointers.values(), key=lambda p: p.oid())
 
 
 def pointerfromctx(ctx, f, removed=False):
     """return a pointer for the named file from the given changectx, or None if
     the file isn't LFS.
 
     Optionally, the pointer for a file deleted from the context can be returned.
     Since no such pointer is actually stored, and to distinguish from a non LFS
     file, this pointer is represented by an empty dict.
     """
     _ctx = ctx
     if f not in ctx:
         if not removed:
             return None
         if f in ctx.p1():
             _ctx = ctx.p1()
         elif f in ctx.p2():
             _ctx = ctx.p2()
         else:
             return None
     fctx = _ctx[f]
     if not _islfs(fctx.filelog()._revlog, fctx.filenode()):
         return None
     try:
         p = pointer.deserialize(fctx.rawdata())
         if ctx == _ctx:
             return p
         return {}
     except pointer.InvalidPointer as ex:
         raise error.Abort(
             _(b'lfs: corrupted pointer (%s@%s): %s\n')
             % (f, short(_ctx.node()), ex)
         )
 
 
 def pointersfromctx(ctx, removed=False):
     """return a dict {path: pointer} for given single changectx.
 
     If ``removed`` == True and the LFS file was removed from ``ctx``, the value
     stored for the path is an empty dict.
     """
     result = {}
     m = ctx.repo().narrowmatch()
 
     # TODO: consider manifest.fastread() instead
     for f in ctx.files():
         if not m(f):
             continue
         p = pointerfromctx(ctx, f, removed=removed)
         if p is not None:
             result[f] = p
     return result
 
 
 def uploadblobs(repo, pointers):
     """upload given pointers from local blobstore"""
     if not pointers:
         return
 
     remoteblob = repo.svfs.lfsremoteblobstore
     remoteblob.writebatch(pointers, repo.svfs.lfslocalblobstore)
 
 
 @eh.wrapfunction(upgrade, b'_finishdatamigration')
 def upgradefinishdatamigration(orig, ui, srcrepo, dstrepo, requirements):
     orig(ui, srcrepo, dstrepo, requirements)
 
     # Skip if this hasn't been passed to reposetup()
     if util.safehasattr(
         srcrepo.svfs, b'lfslocalblobstore'
     ) and util.safehasattr(dstrepo.svfs, b'lfslocalblobstore'):
         srclfsvfs = srcrepo.svfs.lfslocalblobstore.vfs
         dstlfsvfs = dstrepo.svfs.lfslocalblobstore.vfs
 
         for dirpath, dirs, files in srclfsvfs.walk():
             for oid in files:
                 ui.write(_(b'copying lfs blob %s\n') % oid)
                 lfutil.link(srclfsvfs.join(oid), dstlfsvfs.join(oid))
 
 
 @eh.wrapfunction(upgrade, b'preservedrequirements')
 @eh.wrapfunction(upgrade, b'supporteddestrequirements')
 def upgraderequirements(orig, repo):
     reqs = orig(repo)
     if b'lfs' in repo.requirements:
         reqs.add(b'lfs')
     return reqs

mercurial/interfaces/repository.py

@@ -1,1984 +1,1986 b''
 # repository.py - Interfaces and base classes for repositories and peers.
 #
 # Copyright 2017 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from ..i18n import _
 from .. import error
 from . import util as interfaceutil
 
 # When narrowing is finalized and no longer subject to format changes,
 # we should move this to just "narrow" or similar.
 NARROW_REQUIREMENT = b'narrowhg-experimental'
 
 # Local repository feature string.
 
 # Revlogs are being used for file storage.
 REPO_FEATURE_REVLOG_FILE_STORAGE = b'revlogfilestorage'
 # The storage part of the repository is shared from an external source.
 REPO_FEATURE_SHARED_STORAGE = b'sharedstore'
 # LFS supported for backing file storage.
 REPO_FEATURE_LFS = b'lfs'
 # Repository supports being stream cloned.
 REPO_FEATURE_STREAM_CLONE = b'streamclone'
 # Files storage may lack data for all ancestors.
 REPO_FEATURE_SHALLOW_FILE_STORAGE = b'shallowfilestorage'
 
 REVISION_FLAG_CENSORED = 1 << 15
 REVISION_FLAG_ELLIPSIS = 1 << 14
 REVISION_FLAG_EXTSTORED = 1 << 13
 REVISION_FLAG_SIDEDATA = 1 << 12
 
 REVISION_FLAGS_KNOWN = (
     REVISION_FLAG_CENSORED
     | REVISION_FLAG_ELLIPSIS
     | REVISION_FLAG_EXTSTORED
     | REVISION_FLAG_SIDEDATA
 )
 
 CG_DELTAMODE_STD = b'default'
 CG_DELTAMODE_PREV = b'previous'
 CG_DELTAMODE_FULL = b'fulltext'
 CG_DELTAMODE_P1 = b'p1'
 
 
 class ipeerconnection(interfaceutil.Interface):
     """Represents a "connection" to a repository.
 
     This is the base interface for representing a connection to a repository.
     It holds basic properties and methods applicable to all peer types.
 
     This is not a complete interface definition and should not be used
     outside of this module.
     """
 
     ui = interfaceutil.Attribute("""ui.ui instance""")
 
     def url():
         """Returns a URL string representing this peer.
 
         Currently, implementations expose the raw URL used to construct the
         instance. It may contain credentials as part of the URL. The
         expectations of the value aren't well-defined and this could lead to
         data leakage.
 
         TODO audit/clean consumers and more clearly define the contents of this
         value.
         """
 
     def local():
         """Returns a local repository instance.
 
         If the peer represents a local repository, returns an object that
         can be used to interface with it. Otherwise returns ``None``.
         """
 
     def peer():
         """Returns an object conforming to this interface.
 
         Most implementations will ``return self``.
         """
 
     def canpush():
         """Returns a boolean indicating if this peer can be pushed to."""
 
     def close():
         """Close the connection to this peer.
 
         This is called when the peer will no longer be used. Resources
         associated with the peer should be cleaned up.
         """
 
 
 class ipeercapabilities(interfaceutil.Interface):
     """Peer sub-interface related to capabilities."""
 
     def capable(name):
         """Determine support for a named capability.
 
         Returns ``False`` if capability not supported.
 
         Returns ``True`` if boolean capability is supported. Returns a string
         if capability support is non-boolean.
 
         Capability strings may or may not map to wire protocol capabilities.
         """
 
     def requirecap(name, purpose):
         """Require a capability to be present.
 
         Raises a ``CapabilityError`` if the capability isn't present.
         """
 
 
 class ipeercommands(interfaceutil.Interface):
     """Client-side interface for communicating over the wire protocol.
 
     This interface is used as a gateway to the Mercurial wire protocol.
     methods commonly call wire protocol commands of the same name.
     """
 
     def branchmap():
         """Obtain heads in named branches.
 
         Returns a dict mapping branch name to an iterable of nodes that are
         heads on that branch.
         """
 
     def capabilities():
         """Obtain capabilities of the peer.
 
         Returns a set of string capabilities.
         """
 
     def clonebundles():
         """Obtains the clone bundles manifest for the repo.
 
         Returns the manifest as unparsed bytes.
         """
 
     def debugwireargs(one, two, three=None, four=None, five=None):
         """Used to facilitate debugging of arguments passed over the wire."""
 
     def getbundle(source, **kwargs):
         """Obtain remote repository data as a bundle.
 
         This command is how the bulk of repository data is transferred from
         the peer to the local repository
 
         Returns a generator of bundle data.
         """
 
     def heads():
         """Determine all known head revisions in the peer.
 
         Returns an iterable of binary nodes.
         """
 
     def known(nodes):
         """Determine whether multiple nodes are known.
 
         Accepts an iterable of nodes whose presence to check for.
 
         Returns an iterable of booleans indicating of the corresponding node
         at that index is known to the peer.
         """
 
     def listkeys(namespace):
         """Obtain all keys in a pushkey namespace.
 
         Returns an iterable of key names.
         """
 
     def lookup(key):
         """Resolve a value to a known revision.
 
         Returns a binary node of the resolved revision on success.
         """
 
     def pushkey(namespace, key, old, new):
         """Set a value using the ``pushkey`` protocol.
 
         Arguments correspond to the pushkey namespace and key to operate on and
         the old and new values for that key.
 
         Returns a string with the peer result. The value inside varies by the
         namespace.
         """
 
     def stream_out():
         """Obtain streaming clone data.
 
         Successful result should be a generator of data chunks.
         """
 
     def unbundle(bundle, heads, url):
         """Transfer repository data to the peer.
 
         This is how the bulk of data during a push is transferred.
 
         Returns the integer number of heads added to the peer.
         """
 
 
 class ipeerlegacycommands(interfaceutil.Interface):
     """Interface for implementing support for legacy wire protocol commands.
 
     Wire protocol commands transition to legacy status when they are no longer
     used by modern clients. To facilitate identifying which commands are
     legacy, the interfaces are split.
     """
 
     def between(pairs):
         """Obtain nodes between pairs of nodes.
 
         ``pairs`` is an iterable of node pairs.
 
         Returns an iterable of iterables of nodes corresponding to each
         requested pair.
         """
 
     def branches(nodes):
         """Obtain ancestor changesets of specific nodes back to a branch point.
 
         For each requested node, the peer finds the first ancestor node that is
         a DAG root or is a merge.
 
         Returns an iterable of iterables with the resolved values for each node.
         """
 
     def changegroup(nodes, source):
         """Obtain a changegroup with data for descendants of specified nodes."""
 
     def changegroupsubset(bases, heads, source):
         pass
 
 
 class ipeercommandexecutor(interfaceutil.Interface):
     """Represents a mechanism to execute remote commands.
 
     This is the primary interface for requesting that wire protocol commands
     be executed. Instances of this interface are active in a context manager
     and have a well-defined lifetime. When the context manager exits, all
     outstanding requests are waited on.
     """
 
     def callcommand(name, args):
         """Request that a named command be executed.
 
         Receives the command name and a dictionary of command arguments.
 
         Returns a ``concurrent.futures.Future`` that will resolve to the
         result of that command request. That exact value is left up to
         the implementation and possibly varies by command.
 
         Not all commands can coexist with other commands in an executor
         instance: it depends on the underlying wire protocol transport being
         used and the command itself.
 
         Implementations MAY call ``sendcommands()`` automatically if the
         requested command can not coexist with other commands in this executor.
 
         Implementations MAY call ``sendcommands()`` automatically when the
         future's ``result()`` is called. So, consumers using multiple
         commands with an executor MUST ensure that ``result()`` is not called
         until all command requests have been issued.
         """
 
     def sendcommands():
         """Trigger submission of queued command requests.
 
         Not all transports submit commands as soon as they are requested to
         run. When called, this method forces queued command requests to be
         issued. It will no-op if all commands have already been sent.
 
         When called, no more new commands may be issued with this executor.
         """
 
     def close():
         """Signal that this command request is finished.
 
         When called, no more new commands may be issued. All outstanding
         commands that have previously been issued are waited on before
         returning. This not only includes waiting for the futures to resolve,
         but also waiting for all response data to arrive. In other words,
         calling this waits for all on-wire state for issued command requests
         to finish.
 
         When used as a context manager, this method is called when exiting the
         context manager.
 
         This method may call ``sendcommands()`` if there are buffered commands.
         """
 
 
 class ipeerrequests(interfaceutil.Interface):
     """Interface for executing commands on a peer."""
 
     limitedarguments = interfaceutil.Attribute(
         """True if the peer cannot receive large argument value for commands."""
     )
 
     def commandexecutor():
         """A context manager that resolves to an ipeercommandexecutor.
 
         The object this resolves to can be used to issue command requests
         to the peer.
 
         Callers should call its ``callcommand`` method to issue command
         requests.
 
         A new executor should be obtained for each distinct set of commands
         (possibly just a single command) that the consumer wants to execute
         as part of a single operation or round trip. This is because some
         peers are half-duplex and/or don't support persistent connections.
         e.g. in the case of HTTP peers, commands sent to an executor represent
         a single HTTP request. While some peers may support multiple command
         sends over the wire per executor, consumers need to code to the least
         capable peer. So it should be assumed that command executors buffer
         called commands until they are told to send them and that each
         command executor could result in a new connection or wire-level request
         being issued.
         """
 
 
 class ipeerbase(ipeerconnection, ipeercapabilities, ipeerrequests):
     """Unified interface for peer repositories.
 
     All peer instances must conform to this interface.
     """
 
 
 class ipeerv2(ipeerconnection, ipeercapabilities, ipeerrequests):
     """Unified peer interface for wire protocol version 2 peers."""
 
     apidescriptor = interfaceutil.Attribute(
         """Data structure holding description of server API."""
     )
 
 
 @interfaceutil.implementer(ipeerbase)
 class peer(object):
     """Base class for peer repositories."""
 
     limitedarguments = False
 
     def capable(self, name):
         caps = self.capabilities()
         if name in caps:
             return True
 
         name = b'%s=' % name
         for cap in caps:
             if cap.startswith(name):
                 return cap[len(name) :]
 
         return False
 
     def requirecap(self, name, purpose):
         if self.capable(name):
             return
 
         raise error.CapabilityError(
             _(
                 b'cannot %s; remote repository does not support the '
                 b'\'%s\' capability'
             )
             % (purpose, name)
         )
 
 
 class iverifyproblem(interfaceutil.Interface):
     """Represents a problem with the integrity of the repository.
 
     Instances of this interface are emitted to describe an integrity issue
     with a repository (e.g. corrupt storage, missing data, etc).
 
     Instances are essentially messages associated with severity.
     """
 
     warning = interfaceutil.Attribute(
         """Message indicating a non-fatal problem."""
     )
 
     error = interfaceutil.Attribute("""Message indicating a fatal problem.""")
 
     node = interfaceutil.Attribute(
         """Revision encountering the problem.
 
         ``None`` means the problem doesn't apply to a single revision.
         """
     )
 
 
 class irevisiondelta(interfaceutil.Interface):
     """Represents a delta between one revision and another.
 
     Instances convey enough information to allow a revision to be exchanged
     with another repository.
 
     Instances represent the fulltext revision data or a delta against
     another revision. Therefore the ``revision`` and ``delta`` attributes
     are mutually exclusive.
 
     Typically used for changegroup generation.
     """
 
     node = interfaceutil.Attribute("""20 byte node of this revision.""")
 
     p1node = interfaceutil.Attribute(
         """20 byte node of 1st parent of this revision."""
     )
 
     p2node = interfaceutil.Attribute(
         """20 byte node of 2nd parent of this revision."""
     )
 
     linknode = interfaceutil.Attribute(
         """20 byte node of the changelog revision this node is linked to."""
     )
 
     flags = interfaceutil.Attribute(
         """2 bytes of integer flags that apply to this revision.
 
         This is a bitwise composition of the ``REVISION_FLAG_*`` constants.
         """
     )
 
     basenode = interfaceutil.Attribute(
         """20 byte node of the revision this data is a delta against.
 
         ``nullid`` indicates that the revision is a full revision and not
         a delta.
         """
     )
 
     baserevisionsize = interfaceutil.Attribute(
         """Size of base revision this delta is against.
 
         May be ``None`` if ``basenode`` is ``nullid``.
         """
     )
 
     revision = interfaceutil.Attribute(
         """Raw fulltext of revision data for this node."""
     )
 
     delta = interfaceutil.Attribute(
         """Delta between ``basenode`` and ``node``.
 
         Stored in the bdiff delta format.
         """
     )
 
 
 class ifilerevisionssequence(interfaceutil.Interface):
     """Contains index data for all revisions of a file.
 
     Types implementing this behave like lists of tuples. The index
     in the list corresponds to the revision number. The values contain
     index metadata.
 
     The *null* revision (revision number -1) is always the last item
     in the index.
     """
 
     def __len__():
         """The total number of revisions."""
 
     def __getitem__(rev):
         """Returns the object having a specific revision number.
 
         Returns an 8-tuple with the following fields:
 
         offset+flags
            Contains the offset and flags for the revision. 64-bit unsigned
            integer where first 6 bytes are the offset and the next 2 bytes
            are flags. The offset can be 0 if it is not used by the store.
         compressed size
             Size of the revision data in the store. It can be 0 if it isn't
             needed by the store.
         uncompressed size
             Fulltext size. It can be 0 if it isn't needed by the store.
         base revision
             Revision number of revision the delta for storage is encoded
             against. -1 indicates not encoded against a base revision.
         link revision
             Revision number of changelog revision this entry is related to.
         p1 revision
             Revision number of 1st parent. -1 if no 1st parent.
         p2 revision
             Revision number of 2nd parent. -1 if no 1st parent.
         node
             Binary node value for this revision number.
 
         Negative values should index off the end of the sequence. ``-1``
         should return the null revision. ``-2`` should return the most
         recent revision.
         """
 
     def __contains__(rev):
         """Whether a revision number exists."""
 
     def insert(self, i, entry):
         """Add an item to the index at specific revision."""
 
 
 class ifileindex(interfaceutil.Interface):
     """Storage interface for index data of a single file.
 
     File storage data is divided into index metadata and data storage.
     This interface defines the index portion of the interface.
 
     The index logically consists of:
 
     * A mapping between revision numbers and nodes.
     * DAG data (storing and querying the relationship between nodes).
     * Metadata to facilitate storage.
     """
 
     def __len__():
         """Obtain the number of revisions stored for this file."""
 
     def __iter__():
         """Iterate over revision numbers for this file."""
 
     def hasnode(node):
         """Returns a bool indicating if a node is known to this store.
 
         Implementations must only return True for full, binary node values:
         hex nodes, revision numbers, and partial node matches must be
         rejected.
 
         The null node is never present.
         """
 
     def revs(start=0, stop=None):
         """Iterate over revision numbers for this file, with control."""
 
     def parents(node):
         """Returns a 2-tuple of parent nodes for a revision.
 
         Values will be ``nullid`` if the parent is empty.
         """
 
     def parentrevs(rev):
         """Like parents() but operates on revision numbers."""
 
     def rev(node):
         """Obtain the revision number given a node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
     def node(rev):
         """Obtain the node value given a revision number.
 
         Raises ``IndexError`` if the node is not known.
         """
 
     def lookup(node):
         """Attempt to resolve a value to a node.
 
         Value can be a binary node, hex node, revision number, or a string
         that can be converted to an integer.
 
         Raises ``error.LookupError`` if a node could not be resolved.
         """
 
     def linkrev(rev):
         """Obtain the changeset revision number a revision is linked to."""
 
     def iscensored(rev):
         """Return whether a revision's content has been censored."""
 
     def commonancestorsheads(node1, node2):
         """Obtain an iterable of nodes containing heads of common ancestors.
 
         See ``ancestor.commonancestorsheads()``.
         """
 
     def descendants(revs):
         """Obtain descendant revision numbers for a set of revision numbers.
 
         If ``nullrev`` is in the set, this is equivalent to ``revs()``.
         """
 
     def heads(start=None, stop=None):
         """Obtain a list of nodes that are DAG heads, with control.
 
         The set of revisions examined can be limited by specifying
         ``start`` and ``stop``. ``start`` is a node. ``stop`` is an
         iterable of nodes. DAG traversal starts at earlier revision
         ``start`` and iterates forward until any node in ``stop`` is
         encountered.
         """
 
     def children(node):
         """Obtain nodes that are children of a node.
 
         Returns a list of nodes.
         """
 
 
 class ifiledata(interfaceutil.Interface):
     """Storage interface for data storage of a specific file.
 
     This complements ``ifileindex`` and provides an interface for accessing
     data for a tracked file.
     """
 
     def size(rev):
         """Obtain the fulltext size of file data.
 
         Any metadata is excluded from size measurements.
         """
 
     def revision(node, raw=False):
         """"Obtain fulltext data for a node.
 
         By default, any storage transformations are applied before the data
         is returned. If ``raw`` is True, non-raw storage transformations
         are not applied.
 
         The fulltext data may contain a header containing metadata. Most
         consumers should use ``read()`` to obtain the actual file data.
         """
 
     def rawdata(node):
         """Obtain raw data for a node.
         """
 
     def read(node):
         """Resolve file fulltext data.
 
         This is similar to ``revision()`` except any metadata in the data
         headers is stripped.
         """
 
     def renamed(node):
         """Obtain copy metadata for a node.
 
         Returns ``False`` if no copy metadata is stored or a 2-tuple of
         (path, node) from which this revision was copied.
         """
 
     def cmp(node, fulltext):
         """Compare fulltext to another revision.
 
         Returns True if the fulltext is different from what is stored.
 
         This takes copy metadata into account.
 
         TODO better document the copy metadata and censoring logic.
         """
 
     def emitrevisions(
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=CG_DELTAMODE_STD,
     ):
         """Produce ``irevisiondelta`` for revisions.
 
         Given an iterable of nodes, emits objects conforming to the
         ``irevisiondelta`` interface that describe revisions in storage.
 
         This method is a generator.
 
         The input nodes may be unordered. Implementations must ensure that a
         node's parents are emitted before the node itself. Transitively, this
         means that a node may only be emitted once all its ancestors in
         ``nodes`` have also been emitted.
 
         By default, emits "index" data (the ``node``, ``p1node``, and
         ``p2node`` attributes). If ``revisiondata`` is set, revision data
         will also be present on the emitted objects.
 
         With default argument values, implementations can choose to emit
         either fulltext revision data or a delta. When emitting deltas,
         implementations must consider whether the delta's base revision
         fulltext is available to the receiver.
 
         The base revision fulltext is guaranteed to be available if any of
         the following are met:
 
         * Its fulltext revision was emitted by this method call.
         * A delta for that revision was emitted by this method call.
         * ``assumehaveparentrevisions`` is True and the base revision is a
           parent of the node.
 
         ``nodesorder`` can be used to control the order that revisions are
         emitted. By default, revisions can be reordered as long as they are
         in DAG topological order (see above). If the value is ``nodes``,
         the iteration order from ``nodes`` should be used. If the value is
         ``storage``, then the native order from the backing storage layer
         is used. (Not all storage layers will have strong ordering and behavior
         of this mode is storage-dependent.) ``nodes`` ordering can force
         revisions to be emitted before their ancestors, so consumers should
         use it with care.
 
         The ``linknode`` attribute on the returned ``irevisiondelta`` may not
         be set and it is the caller's responsibility to resolve it, if needed.
 
         If ``deltamode`` is CG_DELTAMODE_PREV and revision data is requested,
         all revision data should be emitted as deltas against the revision
         emitted just prior. The initial revision should be a delta against its
         1st parent.
         """
 
 
 class ifilemutation(interfaceutil.Interface):
     """Storage interface for mutation events of a tracked file."""
 
     def add(filedata, meta, transaction, linkrev, p1, p2):
         """Add a new revision to the store.
 
         Takes file data, dictionary of metadata, a transaction, linkrev,
         and parent nodes.
 
         Returns the node that was added.
 
         May no-op if a revision matching the supplied data is already stored.
         """
 
     def addrevision(
         revisiondata,
         transaction,
         linkrev,
         p1,
         p2,
         node=None,
         flags=0,
         cachedelta=None,
     ):
         """Add a new revision to the store.
 
         This is similar to ``add()`` except it operates at a lower level.
 
         The data passed in already contains a metadata header, if any.
 
         ``node`` and ``flags`` can be used to define the expected node and
         the flags to use with storage. ``flags`` is a bitwise value composed
         of the various ``REVISION_FLAG_*`` constants.
 
         ``add()`` is usually called when adding files from e.g. the working
         directory. ``addrevision()`` is often called by ``add()`` and for
         scenarios where revision data has already been computed, such as when
         applying raw data from a peer repo.
         """
 
     def addgroup(
         deltas,
         linkmapper,
         transaction,
         addrevisioncb=None,
         maybemissingparents=False,
     ):
         """Process a series of deltas for storage.
 
         ``deltas`` is an iterable of 7-tuples of
         (node, p1, p2, linknode, deltabase, delta, flags) defining revisions
         to add.
 
         The ``delta`` field contains ``mpatch`` data to apply to a base
         revision, identified by ``deltabase``. The base node can be
         ``nullid``, in which case the header from the delta can be ignored
         and the delta used as the fulltext.
 
         ``addrevisioncb`` should be called for each node as it is committed.
 
         ``maybemissingparents`` is a bool indicating whether the incoming
         data may reference parents/ancestor revisions that aren't present.
         This flag is set when receiving data into a "shallow" store that
         doesn't hold all history.
 
         Returns a list of nodes that were processed. A node will be in the list
         even if it existed in the store previously.
         """
 
     def censorrevision(tr, node, tombstone=b''):
         """Remove the content of a single revision.
 
         The specified ``node`` will have its content purged from storage.
         Future attempts to access the revision data for this node will
         result in failure.
 
         A ``tombstone`` message can optionally be stored. This message may be
         displayed to users when they attempt to access the missing revision
         data.
 
         Storage backends may have stored deltas against the previous content
         in this revision. As part of censoring a revision, these storage
         backends are expected to rewrite any internally stored deltas such
         that they no longer reference the deleted content.
         """
 
     def getstrippoint(minlink):
         """Find the minimum revision that must be stripped to strip a linkrev.
 
         Returns a 2-tuple containing the minimum revision number and a set
         of all revisions numbers that would be broken by this strip.
 
         TODO this is highly revlog centric and should be abstracted into
         a higher-level deletion API. ``repair.strip()`` relies on this.
         """
 
     def strip(minlink, transaction):
         """Remove storage of items starting at a linkrev.
 
         This uses ``getstrippoint()`` to determine the first node to remove.
         Then it effectively truncates storage for all revisions after that.
 
         TODO this is highly revlog centric and should be abstracted into a
         higher-level deletion API.
         """
 
 
 class ifilestorage(ifileindex, ifiledata, ifilemutation):
     """Complete storage interface for a single tracked file."""
 
     def files():
         """Obtain paths that are backing storage for this file.
 
         TODO this is used heavily by verify code and there should probably
         be a better API for that.
         """
 
     def storageinfo(
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         """Obtain information about storage for this file's data.
 
         Returns a dict describing storage for this tracked path. The keys
         in the dict map to arguments of the same. The arguments are bools
         indicating whether to calculate and obtain that data.
 
         exclusivefiles
            Iterable of (vfs, path) describing files that are exclusively
            used to back storage for this tracked path.
 
         sharedfiles
            Iterable of (vfs, path) describing files that are used to back
            storage for this tracked path. Those files may also provide storage
            for other stored entities.
 
         revisionscount
            Number of revisions available for retrieval.
 
         trackedsize
            Total size in bytes of all tracked revisions. This is a sum of the
            length of the fulltext of all revisions.
 
         storedsize
            Total size in bytes used to store data for all tracked revisions.
            This is commonly less than ``trackedsize`` due to internal usage
            of deltas rather than fulltext revisions.
 
         Not all storage backends may support all queries are have a reasonable
         value to use. In that case, the value should be set to ``None`` and
         callers are expected to handle this special value.
         """
 
     def verifyintegrity(state):
         """Verifies the integrity of file storage.
 
         ``state`` is a dict holding state of the verifier process. It can be
         used to communicate data between invocations of multiple storage
         primitives.
 
         If individual revisions cannot have their revision content resolved,
         the method is expected to set the ``skipread`` key to a set of nodes
-        that encountered problems.
+        that encountered problems.  If set, the method can also add the node(s)
+        to ``safe_renamed`` in order to indicate nodes that may perform the
+        rename checks with currently accessible data.
 
         The method yields objects conforming to the ``iverifyproblem``
         interface.
         """
 
 
 class idirs(interfaceutil.Interface):
     """Interface representing a collection of directories from paths.
 
     This interface is essentially a derived data structure representing
     directories from a collection of paths.
     """
 
     def addpath(path):
         """Add a path to the collection.
 
         All directories in the path will be added to the collection.
         """
 
     def delpath(path):
         """Remove a path from the collection.
 
         If the removal was the last path in a particular directory, the
         directory is removed from the collection.
         """
 
     def __iter__():
         """Iterate over the directories in this collection of paths."""
 
     def __contains__(path):
         """Whether a specific directory is in this collection."""
 
 
 class imanifestdict(interfaceutil.Interface):
     """Interface representing a manifest data structure.
 
     A manifest is effectively a dict mapping paths to entries. Each entry
     consists of a binary node and extra flags affecting that entry.
     """
 
     def __getitem__(path):
         """Returns the binary node value for a path in the manifest.
 
         Raises ``KeyError`` if the path does not exist in the manifest.
 
         Equivalent to ``self.find(path)[0]``.
         """
 
     def find(path):
         """Returns the entry for a path in the manifest.
 
         Returns a 2-tuple of (node, flags).
 
         Raises ``KeyError`` if the path does not exist in the manifest.
         """
 
     def __len__():
         """Return the number of entries in the manifest."""
 
     def __nonzero__():
         """Returns True if the manifest has entries, False otherwise."""
 
     __bool__ = __nonzero__
 
     def __setitem__(path, node):
         """Define the node value for a path in the manifest.
 
         If the path is already in the manifest, its flags will be copied to
         the new entry.
         """
 
     def __contains__(path):
         """Whether a path exists in the manifest."""
 
     def __delitem__(path):
         """Remove a path from the manifest.
 
         Raises ``KeyError`` if the path is not in the manifest.
         """
 
     def __iter__():
         """Iterate over paths in the manifest."""
 
     def iterkeys():
         """Iterate over paths in the manifest."""
 
     def keys():
         """Obtain a list of paths in the manifest."""
 
     def filesnotin(other, match=None):
         """Obtain the set of paths in this manifest but not in another.
 
         ``match`` is an optional matcher function to be applied to both
         manifests.
 
         Returns a set of paths.
         """
 
     def dirs():
         """Returns an object implementing the ``idirs`` interface."""
 
     def hasdir(dir):
         """Returns a bool indicating if a directory is in this manifest."""
 
     def matches(match):
         """Generate a new manifest filtered through a matcher.
 
         Returns an object conforming to the ``imanifestdict`` interface.
         """
 
     def walk(match):
         """Generator of paths in manifest satisfying a matcher.
 
         This is equivalent to ``self.matches(match).iterkeys()`` except a new
         manifest object is not created.
 
         If the matcher has explicit files listed and they don't exist in
         the manifest, ``match.bad()`` is called for each missing file.
         """
 
     def diff(other, match=None, clean=False):
         """Find differences between this manifest and another.
 
         This manifest is compared to ``other``.
 
         If ``match`` is provided, the two manifests are filtered against this
         matcher and only entries satisfying the matcher are compared.
 
         If ``clean`` is True, unchanged files are included in the returned
         object.
 
         Returns a dict with paths as keys and values of 2-tuples of 2-tuples of
         the form ``((node1, flag1), (node2, flag2))`` where ``(node1, flag1)``
         represents the node and flags for this manifest and ``(node2, flag2)``
         are the same for the other manifest.
         """
 
     def setflag(path, flag):
         """Set the flag value for a given path.
 
         Raises ``KeyError`` if the path is not already in the manifest.
         """
 
     def get(path, default=None):
         """Obtain the node value for a path or a default value if missing."""
 
     def flags(path, default=b''):
         """Return the flags value for a path or a default value if missing."""
 
     def copy():
         """Return a copy of this manifest."""
 
     def items():
         """Returns an iterable of (path, node) for items in this manifest."""
 
     def iteritems():
         """Identical to items()."""
 
     def iterentries():
         """Returns an iterable of (path, node, flags) for this manifest.
 
         Similar to ``iteritems()`` except items are a 3-tuple and include
         flags.
         """
 
     def text():
         """Obtain the raw data representation for this manifest.
 
         Result is used to create a manifest revision.
         """
 
     def fastdelta(base, changes):
         """Obtain a delta between this manifest and another given changes.
 
         ``base`` in the raw data representation for another manifest.
 
         ``changes`` is an iterable of ``(path, to_delete)``.
 
         Returns a 2-tuple containing ``bytearray(self.text())`` and the
         delta between ``base`` and this manifest.
         """
 
 
 class imanifestrevisionbase(interfaceutil.Interface):
     """Base interface representing a single revision of a manifest.
 
     Should not be used as a primary interface: should always be inherited
     as part of a larger interface.
     """
 
     def new():
         """Obtain a new manifest instance.
 
         Returns an object conforming to the ``imanifestrevisionwritable``
         interface. The instance will be associated with the same
         ``imanifestlog`` collection as this instance.
         """
 
     def copy():
         """Obtain a copy of this manifest instance.
 
         Returns an object conforming to the ``imanifestrevisionwritable``
         interface. The instance will be associated with the same
         ``imanifestlog`` collection as this instance.
         """
 
     def read():
         """Obtain the parsed manifest data structure.
 
         The returned object conforms to the ``imanifestdict`` interface.
         """
 
 
 class imanifestrevisionstored(imanifestrevisionbase):
     """Interface representing a manifest revision committed to storage."""
 
     def node():
         """The binary node for this manifest."""
 
     parents = interfaceutil.Attribute(
         """List of binary nodes that are parents for this manifest revision."""
     )
 
     def readdelta(shallow=False):
         """Obtain the manifest data structure representing changes from parent.
 
         This manifest is compared to its 1st parent. A new manifest representing
         those differences is constructed.
 
         The returned object conforms to the ``imanifestdict`` interface.
         """
 
     def readfast(shallow=False):
         """Calls either ``read()`` or ``readdelta()``.
 
         The faster of the two options is called.
         """
 
     def find(key):
         """Calls self.read().find(key)``.
 
         Returns a 2-tuple of ``(node, flags)`` or raises ``KeyError``.
         """
 
 
 class imanifestrevisionwritable(imanifestrevisionbase):
     """Interface representing a manifest revision that can be committed."""
 
     def write(transaction, linkrev, p1node, p2node, added, removed, match=None):
         """Add this revision to storage.
 
         Takes a transaction object, the changeset revision number it will
         be associated with, its parent nodes, and lists of added and
         removed paths.
 
         If match is provided, storage can choose not to inspect or write out
         items that do not match. Storage is still required to be able to provide
         the full manifest in the future for any directories written (these
         manifests should not be "narrowed on disk").
 
         Returns the binary node of the created revision.
         """
 
 
 class imanifeststorage(interfaceutil.Interface):
     """Storage interface for manifest data."""
 
     tree = interfaceutil.Attribute(
         """The path to the directory this manifest tracks.
 
         The empty bytestring represents the root manifest.
         """
     )
 
     index = interfaceutil.Attribute(
         """An ``ifilerevisionssequence`` instance."""
     )
 
     indexfile = interfaceutil.Attribute(
         """Path of revlog index file.
 
         TODO this is revlog specific and should not be exposed.
         """
     )
 
     opener = interfaceutil.Attribute(
         """VFS opener to use to access underlying files used for storage.
 
         TODO this is revlog specific and should not be exposed.
         """
     )
 
     version = interfaceutil.Attribute(
         """Revlog version number.
 
         TODO this is revlog specific and should not be exposed.
         """
     )
 
     _generaldelta = interfaceutil.Attribute(
         """Whether generaldelta storage is being used.
 
         TODO this is revlog specific and should not be exposed.
         """
     )
 
     fulltextcache = interfaceutil.Attribute(
         """Dict with cache of fulltexts.
 
         TODO this doesn't feel appropriate for the storage interface.
         """
     )
 
     def __len__():
         """Obtain the number of revisions stored for this manifest."""
 
     def __iter__():
         """Iterate over revision numbers for this manifest."""
 
     def rev(node):
         """Obtain the revision number given a binary node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
     def node(rev):
         """Obtain the node value given a revision number.
 
         Raises ``error.LookupError`` if the revision is not known.
         """
 
     def lookup(value):
         """Attempt to resolve a value to a node.
 
         Value can be a binary node, hex node, revision number, or a bytes
         that can be converted to an integer.
 
         Raises ``error.LookupError`` if a ndoe could not be resolved.
         """
 
     def parents(node):
         """Returns a 2-tuple of parent nodes for a node.
 
         Values will be ``nullid`` if the parent is empty.
         """
 
     def parentrevs(rev):
         """Like parents() but operates on revision numbers."""
 
     def linkrev(rev):
         """Obtain the changeset revision number a revision is linked to."""
 
     def revision(node, _df=None, raw=False):
         """Obtain fulltext data for a node."""
 
     def rawdata(node, _df=None):
         """Obtain raw data for a node."""
 
     def revdiff(rev1, rev2):
         """Obtain a delta between two revision numbers.
 
         The returned data is the result of ``bdiff.bdiff()`` on the raw
         revision data.
         """
 
     def cmp(node, fulltext):
         """Compare fulltext to another revision.
 
         Returns True if the fulltext is different from what is stored.
         """
 
     def emitrevisions(
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
     ):
         """Produce ``irevisiondelta`` describing revisions.
 
         See the documentation for ``ifiledata`` for more.
         """
 
     def addgroup(deltas, linkmapper, transaction, addrevisioncb=None):
         """Process a series of deltas for storage.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def rawsize(rev):
         """Obtain the size of tracked data.
 
         Is equivalent to ``len(m.rawdata(node))``.
 
         TODO this method is only used by upgrade code and may be removed.
         """
 
     def getstrippoint(minlink):
         """Find minimum revision that must be stripped to strip a linkrev.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def strip(minlink, transaction):
         """Remove storage of items starting at a linkrev.
 
         See the documentation in ``ifilemutation`` for more.
         """
 
     def checksize():
         """Obtain the expected sizes of backing files.
 
         TODO this is used by verify and it should not be part of the interface.
         """
 
     def files():
         """Obtain paths that are backing storage for this manifest.
 
         TODO this is used by verify and there should probably be a better API
         for this functionality.
         """
 
     def deltaparent(rev):
         """Obtain the revision that a revision is delta'd against.
 
         TODO delta encoding is an implementation detail of storage and should
         not be exposed to the storage interface.
         """
 
     def clone(tr, dest, **kwargs):
         """Clone this instance to another."""
 
     def clearcaches(clear_persisted_data=False):
         """Clear any caches associated with this instance."""
 
     def dirlog(d):
         """Obtain a manifest storage instance for a tree."""
 
     def add(
         m, transaction, link, p1, p2, added, removed, readtree=None, match=None
     ):
         """Add a revision to storage.
 
         ``m`` is an object conforming to ``imanifestdict``.
 
         ``link`` is the linkrev revision number.
 
         ``p1`` and ``p2`` are the parent revision numbers.
 
         ``added`` and ``removed`` are iterables of added and removed paths,
         respectively.
 
         ``readtree`` is a function that can be used to read the child tree(s)
         when recursively writing the full tree structure when using
         treemanifets.
 
         ``match`` is a matcher that can be used to hint to storage that not all
         paths must be inspected; this is an optimization and can be safely
         ignored. Note that the storage must still be able to reproduce a full
         manifest including files that did not match.
         """
 
     def storageinfo(
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         """Obtain information about storage for this manifest's data.
 
         See ``ifilestorage.storageinfo()`` for a description of this method.
         This one behaves the same way, except for manifest data.
         """
 
 
 class imanifestlog(interfaceutil.Interface):
     """Interface representing a collection of manifest snapshots.
 
     Represents the root manifest in a repository.
 
     Also serves as a means to access nested tree manifests and to cache
     tree manifests.
     """
 
     def __getitem__(node):
         """Obtain a manifest instance for a given binary node.
 
         Equivalent to calling ``self.get('', node)``.
 
         The returned object conforms to the ``imanifestrevisionstored``
         interface.
         """
 
     def get(tree, node, verify=True):
         """Retrieve the manifest instance for a given directory and binary node.
 
         ``node`` always refers to the node of the root manifest (which will be
         the only manifest if flat manifests are being used).
 
         If ``tree`` is the empty string, the root manifest is returned.
         Otherwise the manifest for the specified directory will be returned
         (requires tree manifests).
 
         If ``verify`` is True, ``LookupError`` is raised if the node is not
         known.
 
         The returned object conforms to the ``imanifestrevisionstored``
         interface.
         """
 
     def getstorage(tree):
         """Retrieve an interface to storage for a particular tree.
 
         If ``tree`` is the empty bytestring, storage for the root manifest will
         be returned. Otherwise storage for a tree manifest is returned.
 
         TODO formalize interface for returned object.
         """
 
     def clearcaches():
         """Clear caches associated with this collection."""
 
     def rev(node):
         """Obtain the revision number for a binary node.
 
         Raises ``error.LookupError`` if the node is not known.
         """
 
 
 class ilocalrepositoryfilestorage(interfaceutil.Interface):
     """Local repository sub-interface providing access to tracked file storage.
 
     This interface defines how a repository accesses storage for a single
     tracked file path.
     """
 
     def file(f):
         """Obtain a filelog for a tracked path.
 
         The returned type conforms to the ``ifilestorage`` interface.
         """
 
 
 class ilocalrepositorymain(interfaceutil.Interface):
     """Main interface for local repositories.
 
     This currently captures the reality of things - not how things should be.
     """
 
     supportedformats = interfaceutil.Attribute(
         """Set of requirements that apply to stream clone.
 
         This is actually a class attribute and is shared among all instances.
         """
     )
 
     supported = interfaceutil.Attribute(
         """Set of requirements that this repo is capable of opening."""
     )
 
     requirements = interfaceutil.Attribute(
         """Set of requirements this repo uses."""
     )
 
     features = interfaceutil.Attribute(
         """Set of "features" this repository supports.
 
         A "feature" is a loosely-defined term. It can refer to a feature
         in the classical sense or can describe an implementation detail
         of the repository. For example, a ``readonly`` feature may denote
         the repository as read-only. Or a ``revlogfilestore`` feature may
         denote that the repository is using revlogs for file storage.
 
         The intent of features is to provide a machine-queryable mechanism
         for repo consumers to test for various repository characteristics.
 
         Features are similar to ``requirements``. The main difference is that
         requirements are stored on-disk and represent requirements to open the
         repository. Features are more run-time capabilities of the repository
         and more granular capabilities (which may be derived from requirements).
         """
     )
 
     filtername = interfaceutil.Attribute(
         """Name of the repoview that is active on this repo."""
     )
 
     wvfs = interfaceutil.Attribute(
         """VFS used to access the working directory."""
     )
 
     vfs = interfaceutil.Attribute(
         """VFS rooted at the .hg directory.
 
         Used to access repository data not in the store.
         """
     )
 
     svfs = interfaceutil.Attribute(
         """VFS rooted at the store.
 
         Used to access repository data in the store. Typically .hg/store.
         But can point elsewhere if the store is shared.
         """
     )
 
     root = interfaceutil.Attribute(
         """Path to the root of the working directory."""
     )
 
     path = interfaceutil.Attribute("""Path to the .hg directory.""")
 
     origroot = interfaceutil.Attribute(
         """The filesystem path that was used to construct the repo."""
     )
 
     auditor = interfaceutil.Attribute(
         """A pathauditor for the working directory.
 
         This checks if a path refers to a nested repository.
 
         Operates on the filesystem.
         """
     )
 
     nofsauditor = interfaceutil.Attribute(
         """A pathauditor for the working directory.
 
         This is like ``auditor`` except it doesn't do filesystem checks.
         """
     )
 
     baseui = interfaceutil.Attribute(
         """Original ui instance passed into constructor."""
     )
 
     ui = interfaceutil.Attribute("""Main ui instance for this instance.""")
 
     sharedpath = interfaceutil.Attribute(
         """Path to the .hg directory of the repo this repo was shared from."""
     )
 
     store = interfaceutil.Attribute("""A store instance.""")
 
     spath = interfaceutil.Attribute("""Path to the store.""")
 
     sjoin = interfaceutil.Attribute("""Alias to self.store.join.""")
 
     cachevfs = interfaceutil.Attribute(
         """A VFS used to access the cache directory.
 
         Typically .hg/cache.
         """
     )
 
     wcachevfs = interfaceutil.Attribute(
         """A VFS used to access the cache directory dedicated to working copy
 
         Typically .hg/wcache.
         """
     )
 
     filteredrevcache = interfaceutil.Attribute(
         """Holds sets of revisions to be filtered."""
     )
 
     names = interfaceutil.Attribute("""A ``namespaces`` instance.""")
 
     filecopiesmode = interfaceutil.Attribute(
         """The way files copies should be dealt with in this repo."""
     )
 
     def close():
         """Close the handle on this repository."""
 
     def peer():
         """Obtain an object conforming to the ``peer`` interface."""
 
     def unfiltered():
         """Obtain an unfiltered/raw view of this repo."""
 
     def filtered(name, visibilityexceptions=None):
         """Obtain a named view of this repository."""
 
     obsstore = interfaceutil.Attribute("""A store of obsolescence data.""")
 
     changelog = interfaceutil.Attribute("""A handle on the changelog revlog.""")
 
     manifestlog = interfaceutil.Attribute(
         """An instance conforming to the ``imanifestlog`` interface.
 
         Provides access to manifests for the repository.
         """
     )
 
     dirstate = interfaceutil.Attribute("""Working directory state.""")
 
     narrowpats = interfaceutil.Attribute(
         """Matcher patterns for this repository's narrowspec."""
     )
 
     def narrowmatch(match=None, includeexact=False):
         """Obtain a matcher for the narrowspec."""
 
     def setnarrowpats(newincludes, newexcludes):
         """Define the narrowspec for this repository."""
 
     def __getitem__(changeid):
         """Try to resolve a changectx."""
 
     def __contains__(changeid):
         """Whether a changeset exists."""
 
     def __nonzero__():
         """Always returns True."""
         return True
 
     __bool__ = __nonzero__
 
     def __len__():
         """Returns the number of changesets in the repo."""
 
     def __iter__():
         """Iterate over revisions in the changelog."""
 
     def revs(expr, *args):
         """Evaluate a revset.
 
         Emits revisions.
         """
 
     def set(expr, *args):
         """Evaluate a revset.
 
         Emits changectx instances.
         """
 
     def anyrevs(specs, user=False, localalias=None):
         """Find revisions matching one of the given revsets."""
 
     def url():
         """Returns a string representing the location of this repo."""
 
     def hook(name, throw=False, **args):
         """Call a hook."""
 
     def tags():
         """Return a mapping of tag to node."""
 
     def tagtype(tagname):
         """Return the type of a given tag."""
 
     def tagslist():
         """Return a list of tags ordered by revision."""
 
     def nodetags(node):
         """Return the tags associated with a node."""
 
     def nodebookmarks(node):
         """Return the list of bookmarks pointing to the specified node."""
 
     def branchmap():
         """Return a mapping of branch to heads in that branch."""
 
     def revbranchcache():
         pass
 
     def branchtip(branchtip, ignoremissing=False):
         """Return the tip node for a given branch."""
 
     def lookup(key):
         """Resolve the node for a revision."""
 
     def lookupbranch(key):
         """Look up the branch name of the given revision or branch name."""
 
     def known(nodes):
         """Determine whether a series of nodes is known.
 
         Returns a list of bools.
         """
 
     def local():
         """Whether the repository is local."""
         return True
 
     def publishing():
         """Whether the repository is a publishing repository."""
 
     def cancopy():
         pass
 
     def shared():
         """The type of shared repository or None."""
 
     def wjoin(f, *insidef):
         """Calls self.vfs.reljoin(self.root, f, *insidef)"""
 
     def setparents(p1, p2):
         """Set the parent nodes of the working directory."""
 
     def filectx(path, changeid=None, fileid=None):
         """Obtain a filectx for the given file revision."""
 
     def getcwd():
         """Obtain the current working directory from the dirstate."""
 
     def pathto(f, cwd=None):
         """Obtain the relative path to a file."""
 
     def adddatafilter(name, fltr):
         pass
 
     def wread(filename):
         """Read a file from wvfs, using data filters."""
 
     def wwrite(filename, data, flags, backgroundclose=False, **kwargs):
         """Write data to a file in the wvfs, using data filters."""
 
     def wwritedata(filename, data):
         """Resolve data for writing to the wvfs, using data filters."""
 
     def currenttransaction():
         """Obtain the current transaction instance or None."""
 
     def transaction(desc, report=None):
         """Open a new transaction to write to the repository."""
 
     def undofiles():
         """Returns a list of (vfs, path) for files to undo transactions."""
 
     def recover():
         """Roll back an interrupted transaction."""
 
     def rollback(dryrun=False, force=False):
         """Undo the last transaction.
 
         DANGEROUS.
         """
 
     def updatecaches(tr=None, full=False):
         """Warm repo caches."""
 
     def invalidatecaches():
         """Invalidate cached data due to the repository mutating."""
 
     def invalidatevolatilesets():
         pass
 
     def invalidatedirstate():
         """Invalidate the dirstate."""
 
     def invalidate(clearfilecache=False):
         pass
 
     def invalidateall():
         pass
 
     def lock(wait=True):
         """Lock the repository store and return a lock instance."""
 
     def wlock(wait=True):
         """Lock the non-store parts of the repository."""
 
     def currentwlock():
         """Return the wlock if it's held or None."""
 
     def checkcommitpatterns(wctx, match, status, fail):
         pass
 
     def commit(
         text=b'',
         user=None,
         date=None,
         match=None,
         force=False,
         editor=False,
         extra=None,
     ):
         """Add a new revision to the repository."""
 
     def commitctx(ctx, error=False, origctx=None):
         """Commit a commitctx instance to the repository."""
 
     def destroying():
         """Inform the repository that nodes are about to be destroyed."""
 
     def destroyed():
         """Inform the repository that nodes have been destroyed."""
 
     def status(
         node1=b'.',
         node2=None,
         match=None,
         ignored=False,
         clean=False,
         unknown=False,
         listsubrepos=False,
     ):
         """Convenience method to call repo[x].status()."""
 
     def addpostdsstatus(ps):
         pass
 
     def postdsstatus():
         pass
 
     def clearpostdsstatus():
         pass
 
     def heads(start=None):
         """Obtain list of nodes that are DAG heads."""
 
     def branchheads(branch=None, start=None, closed=False):
         pass
 
     def branches(nodes):
         pass
 
     def between(pairs):
         pass
 
     def checkpush(pushop):
         pass
 
     prepushoutgoinghooks = interfaceutil.Attribute("""util.hooks instance.""")
 
     def pushkey(namespace, key, old, new):
         pass
 
     def listkeys(namespace):
         pass
 
     def debugwireargs(one, two, three=None, four=None, five=None):
         pass
 
     def savecommitmessage(text):
         pass
 
 
 class completelocalrepository(
     ilocalrepositorymain, ilocalrepositoryfilestorage
 ):
     """Complete interface for a local repository."""
 
 
 class iwireprotocolcommandcacher(interfaceutil.Interface):
     """Represents a caching backend for wire protocol commands.
 
     Wire protocol version 2 supports transparent caching of many commands.
     To leverage this caching, servers can activate objects that cache
     command responses. Objects handle both cache writing and reading.
     This interface defines how that response caching mechanism works.
 
     Wire protocol version 2 commands emit a series of objects that are
     serialized and sent to the client. The caching layer exists between
     the invocation of the command function and the sending of its output
     objects to an output layer.
 
     Instances of this interface represent a binding to a cache that
     can serve a response (in place of calling a command function) and/or
     write responses to a cache for subsequent use.
 
     When a command request arrives, the following happens with regards
     to this interface:
 
     1. The server determines whether the command request is cacheable.
     2. If it is, an instance of this interface is spawned.
     3. The cacher is activated in a context manager (``__enter__`` is called).
     4. A cache *key* for that request is derived. This will call the
        instance's ``adjustcachekeystate()`` method so the derivation
        can be influenced.
     5. The cacher is informed of the derived cache key via a call to
        ``setcachekey()``.
     6. The cacher's ``lookup()`` method is called to test for presence of
        the derived key in the cache.
     7. If ``lookup()`` returns a hit, that cached result is used in place
        of invoking the command function. ``__exit__`` is called and the instance
        is discarded.
     8. The command function is invoked.
     9. ``onobject()`` is called for each object emitted by the command
        function.
     10. After the final object is seen, ``onfinished()`` is called.
     11. ``__exit__`` is called to signal the end of use of the instance.
 
     Cache *key* derivation can be influenced by the instance.
 
     Cache keys are initially derived by a deterministic representation of
     the command request. This includes the command name, arguments, protocol
     version, etc. This initial key derivation is performed by CBOR-encoding a
     data structure and feeding that output into a hasher.
 
     Instances of this interface can influence this initial key derivation
     via ``adjustcachekeystate()``.
 
     The instance is informed of the derived cache key via a call to
     ``setcachekey()``. The instance must store the key locally so it can
     be consulted on subsequent operations that may require it.
 
     When constructed, the instance has access to a callable that can be used
     for encoding response objects. This callable receives as its single
     argument an object emitted by a command function. It returns an iterable
     of bytes chunks representing the encoded object. Unless the cacher is
     caching native Python objects in memory or has a way of reconstructing
     the original Python objects, implementations typically call this function
     to produce bytes from the output objects and then store those bytes in
     the cache. When it comes time to re-emit those bytes, they are wrapped
     in a ``wireprototypes.encodedresponse`` instance to tell the output
     layer that they are pre-encoded.
 
     When receiving the objects emitted by the command function, instances
     can choose what to do with those objects. The simplest thing to do is
     re-emit the original objects. They will be forwarded to the output
     layer and will be processed as if the cacher did not exist.
 
     Implementations could also choose to not emit objects - instead locally
     buffering objects or their encoded representation. They could then emit
     a single "coalesced" object when ``onfinished()`` is called. In
     this way, the implementation would function as a filtering layer of
     sorts.
 
     When caching objects, typically the encoded form of the object will
     be stored. Keep in mind that if the original object is forwarded to
     the output layer, it will need to be encoded there as well. For large
     output, this redundant encoding could add overhead. Implementations
     could wrap the encoded object data in ``wireprototypes.encodedresponse``
     instances to avoid this overhead.
     """
 
     def __enter__():
         """Marks the instance as active.
 
         Should return self.
         """
 
     def __exit__(exctype, excvalue, exctb):
         """Called when cacher is no longer used.
 
         This can be used by implementations to perform cleanup actions (e.g.
         disconnecting network sockets, aborting a partially cached response.
         """
 
     def adjustcachekeystate(state):
         """Influences cache key derivation by adjusting state to derive key.
 
         A dict defining the state used to derive the cache key is passed.
 
         Implementations can modify this dict to record additional state that
         is wanted to influence key derivation.
 
         Implementations are *highly* encouraged to not modify or delete
         existing keys.
         """
 
     def setcachekey(key):
         """Record the derived cache key for this request.
 
         Instances may mutate the key for internal usage, as desired. e.g.
         instances may wish to prepend the repo name, introduce path
         components for filesystem or URL addressing, etc. Behavior is up to
         the cache.
 
         Returns a bool indicating if the request is cacheable by this
         instance.
         """
 
     def lookup():
         """Attempt to resolve an entry in the cache.
 
         The instance is instructed to look for the cache key that it was
         informed about via the call to ``setcachekey()``.
 
         If there's no cache hit or the cacher doesn't wish to use the cached
         entry, ``None`` should be returned.
 
         Else, a dict defining the cached result should be returned. The
         dict may have the following keys:
 
         objs
            An iterable of objects that should be sent to the client. That
            iterable of objects is expected to be what the command function
            would return if invoked or an equivalent representation thereof.
         """
 
     def onobject(obj):
         """Called when a new object is emitted from the command function.
 
         Receives as its argument the object that was emitted from the
         command function.
 
         This method returns an iterator of objects to forward to the output
         layer. The easiest implementation is a generator that just
         ``yield obj``.
         """
 
     def onfinished():
         """Called after all objects have been emitted from the command function.
 
         Implementations should return an iterator of objects to forward to
         the output layer.
 
         This method can be a generator.
         """

mercurial/revlog.py

@@ -1,2988 +1,2989 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
 
 
 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,
     ):
         """
         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.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
         # 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:
             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
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         elif rustrevlog is not None and self.opener.options.get(b'rust.index'):
             self._io = rustrevlogio()
         try:
             d = self._io.parseindex(indexdata, self._inline)
         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)
         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)
 
     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/verify.py

@@ -1,626 +1,628 b''
 # verify.py - repository integrity checking for Mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 
 from .i18n import _
 from .node import (
     nullid,
     short,
 )
 
 from . import (
     error,
     pycompat,
     revlog,
     util,
 )
 
 VERIFY_DEFAULT = 0
 VERIFY_FULL = 1
 
 
 def verify(repo, level=None):
     with repo.lock():
         v = verifier(repo, level)
         return v.verify()
 
 
 def _normpath(f):
     # under hg < 2.4, convert didn't sanitize paths properly, so a
     # converted repo may contain repeated slashes
     while b'//' in f:
         f = f.replace(b'//', b'/')
     return f
 
 
 class verifier(object):
     def __init__(self, repo, level=None):
         self.repo = repo.unfiltered()
         self.ui = repo.ui
         self.match = repo.narrowmatch()
         if level is None:
             level = VERIFY_DEFAULT
         self._level = level
         self.badrevs = set()
         self.errors = 0
         self.warnings = 0
         self.havecl = len(repo.changelog) > 0
         self.havemf = len(repo.manifestlog.getstorage(b'')) > 0
         self.revlogv1 = repo.changelog.version != revlog.REVLOGV0
         self.lrugetctx = util.lrucachefunc(repo.__getitem__)
         self.refersmf = False
         self.fncachewarned = False
         # developer config: verify.skipflags
         self.skipflags = repo.ui.configint(b'verify', b'skipflags')
         self.warnorphanstorefiles = True
 
     def _warn(self, msg):
         """record a "warning" level issue"""
         self.ui.warn(msg + b"\n")
         self.warnings += 1
 
     def _err(self, linkrev, msg, filename=None):
         """record a "error" level issue"""
         if linkrev is not None:
             self.badrevs.add(linkrev)
             linkrev = b"%d" % linkrev
         else:
             linkrev = b'?'
         msg = b"%s: %s" % (linkrev, msg)
         if filename:
             msg = b"%s@%s" % (filename, msg)
         self.ui.warn(b" " + msg + b"\n")
         self.errors += 1
 
     def _exc(self, linkrev, msg, inst, filename=None):
         """record exception raised during the verify process"""
         fmsg = pycompat.bytestr(inst)
         if not fmsg:
             fmsg = pycompat.byterepr(inst)
         self._err(linkrev, b"%s: %s" % (msg, fmsg), filename)
 
     def _checkrevlog(self, obj, name, linkrev):
         """verify high level property of a revlog
 
         - revlog is present,
         - revlog is non-empty,
         - sizes (index and data) are correct,
         - revlog's format version is correct.
         """
         if not len(obj) and (self.havecl or self.havemf):
             self._err(linkrev, _(b"empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             self._err(None, _(b"data length off by %d bytes") % d[0], name)
         if d[1]:
             self._err(None, _(b"index contains %d extra bytes") % d[1], name)
 
         if obj.version != revlog.REVLOGV0:
             if not self.revlogv1:
                 self._warn(_(b"warning: `%s' uses revlog format 1") % name)
         elif self.revlogv1:
             self._warn(_(b"warning: `%s' uses revlog format 0") % name)
 
     def _checkentry(self, obj, i, node, seen, linkrevs, f):
         """verify a single revlog entry
 
         arguments are:
         - obj:      the source revlog
         - i:        the revision number
         - node:        the revision node id
         - seen:     nodes previously seen for this revlog
         - linkrevs: [changelog-revisions] introducing "node"
         - f:        string label ("changelog", "manifest", or filename)
 
         Performs the following checks:
         - linkrev points to an existing changelog revision,
         - linkrev points to a changelog revision that introduces this revision,
         - linkrev points to the lowest of these changesets,
         - both parents exist in the revlog,
         - the revision is not duplicated.
 
         Return the linkrev of the revision (or None for changelog's revisions).
         """
         lr = obj.linkrev(obj.rev(node))
         if lr < 0 or (self.havecl and lr not in linkrevs):
             if lr < 0 or lr >= len(self.repo.changelog):
                 msg = _(b"rev %d points to nonexistent changeset %d")
             else:
                 msg = _(b"rev %d points to unexpected changeset %d")
             self._err(None, msg % (i, lr), f)
             if linkrevs:
                 if f and len(linkrevs) > 1:
                     try:
                         # attempt to filter down to real linkrevs
                         linkrevs = [
                             l
                             for l in linkrevs
                             if self.lrugetctx(l)[f].filenode() == node
                         ]
                     except Exception:
                         pass
                 self._warn(
                     _(b" (expected %s)")
                     % b" ".join(map(pycompat.bytestr, linkrevs))
                 )
             lr = None  # can't be trusted
 
         try:
             p1, p2 = obj.parents(node)
             if p1 not in seen and p1 != nullid:
                 self._err(
                     lr,
                     _(b"unknown parent 1 %s of %s") % (short(p1), short(node)),
                     f,
                 )
             if p2 not in seen and p2 != nullid:
                 self._err(
                     lr,
                     _(b"unknown parent 2 %s of %s") % (short(p2), short(node)),
                     f,
                 )
         except Exception as inst:
             self._exc(lr, _(b"checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             self._err(lr, _(b"duplicate revision %d (%d)") % (i, seen[node]), f)
         seen[node] = i
         return lr
 
     def verify(self):
         """verify the content of the Mercurial repository
 
         This method run all verifications, displaying issues as they are found.
 
         return 1 if any error have been encountered, 0 otherwise."""
         # initial validation and generic report
         repo = self.repo
         ui = repo.ui
         if not repo.url().startswith(b'file:'):
             raise error.Abort(_(b"cannot verify bundle or remote repos"))
 
         if os.path.exists(repo.sjoin(b"journal")):
             ui.warn(_(b"abandoned transaction found - run hg recover\n"))
 
         if ui.verbose or not self.revlogv1:
             ui.status(
                 _(b"repository uses revlog format %d\n")
                 % (self.revlogv1 and 1 or 0)
             )
 
         # data verification
         mflinkrevs, filelinkrevs = self._verifychangelog()
         filenodes = self._verifymanifest(mflinkrevs)
         del mflinkrevs
         self._crosscheckfiles(filelinkrevs, filenodes)
         totalfiles, filerevisions = self._verifyfiles(filenodes, filelinkrevs)
 
         # final report
         ui.status(
             _(b"checked %d changesets with %d changes to %d files\n")
             % (len(repo.changelog), filerevisions, totalfiles)
         )
         if self.warnings:
             ui.warn(_(b"%d warnings encountered!\n") % self.warnings)
         if self.fncachewarned:
             ui.warn(
                 _(
                     b'hint: run "hg debugrebuildfncache" to recover from '
                     b'corrupt fncache\n'
                 )
             )
         if self.errors:
             ui.warn(_(b"%d integrity errors encountered!\n") % self.errors)
             if self.badrevs:
                 ui.warn(
                     _(b"(first damaged changeset appears to be %d)\n")
                     % min(self.badrevs)
                 )
             return 1
         return 0
 
     def _verifychangelog(self):
         """verify the changelog of a repository
 
         The following checks are performed:
         - all of `_checkrevlog` checks,
         - all of `_checkentry` checks (for each revisions),
         - each revision can be read.
 
         The function returns some of the data observed in the changesets as a
         (mflinkrevs, filelinkrevs) tuples:
         - mflinkrevs:   is a { manifest-node -> [changelog-rev] } mapping
         - filelinkrevs: is a { file-path -> [changelog-rev] } mapping
 
         If a matcher was specified, filelinkrevs will only contains matched
         files.
         """
         ui = self.ui
         repo = self.repo
         match = self.match
         cl = repo.changelog
 
         ui.status(_(b"checking changesets\n"))
         mflinkrevs = {}
         filelinkrevs = {}
         seen = {}
         self._checkrevlog(cl, b"changelog", 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'changesets'), total=len(repo)
         )
         for i in repo:
             progress.update(i)
             n = cl.node(i)
             self._checkentry(cl, i, n, seen, [i], b"changelog")
 
             try:
                 changes = cl.read(n)
                 if changes[0] != nullid:
                     mflinkrevs.setdefault(changes[0], []).append(i)
                     self.refersmf = True
                 for f in changes[3]:
                     if match(f):
                         filelinkrevs.setdefault(_normpath(f), []).append(i)
             except Exception as inst:
                 self.refersmf = True
                 self._exc(i, _(b"unpacking changeset %s") % short(n), inst)
         progress.complete()
         return mflinkrevs, filelinkrevs
 
     def _verifymanifest(
         self, mflinkrevs, dir=b"", storefiles=None, subdirprogress=None
     ):
         """verify the manifestlog content
 
         Inputs:
         - mflinkrevs:     a {manifest-node -> [changelog-revisions]} mapping
         - dir:            a subdirectory to check (for tree manifest repo)
         - storefiles:     set of currently "orphan" files.
         - subdirprogress: a progress object
 
         This function checks:
         * all of `_checkrevlog` checks (for all manifest related revlogs)
         * all of `_checkentry` checks (for all manifest related revisions)
         * nodes for subdirectory exists in the sub-directory manifest
         * each manifest entries have a file path
         * each manifest node refered in mflinkrevs exist in the manifest log
 
         If tree manifest is in use and a matchers is specified, only the
         sub-directories matching it will be verified.
 
         return a two level mapping:
             {"path" -> { filenode -> changelog-revision}}
 
         This mapping primarily contains entries for every files in the
         repository. In addition, when tree-manifest is used, it also contains
         sub-directory entries.
 
         If a matcher is provided, only matching paths will be included.
         """
         repo = self.repo
         ui = self.ui
         match = self.match
         mfl = self.repo.manifestlog
         mf = mfl.getstorage(dir)
 
         if not dir:
             self.ui.status(_(b"checking manifests\n"))
 
         filenodes = {}
         subdirnodes = {}
         seen = {}
         label = b"manifest"
         if dir:
             label = dir
             revlogfiles = mf.files()
             storefiles.difference_update(revlogfiles)
             if subdirprogress:  # should be true since we're in a subdirectory
                 subdirprogress.increment()
         if self.refersmf:
             # Do not check manifest if there are only changelog entries with
             # null manifests.
             self._checkrevlog(mf, label, 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'manifests'), total=len(mf)
         )
         for i in mf:
             if not dir:
                 progress.update(i)
             n = mf.node(i)
             lr = self._checkentry(mf, i, n, seen, mflinkrevs.get(n, []), label)
             if n in mflinkrevs:
                 del mflinkrevs[n]
             elif dir:
                 self._err(
                     lr,
                     _(b"%s not in parent-directory manifest") % short(n),
                     label,
                 )
             else:
                 self._err(lr, _(b"%s not in changesets") % short(n), label)
 
             try:
                 mfdelta = mfl.get(dir, n).readdelta(shallow=True)
                 for f, fn, fl in mfdelta.iterentries():
                     if not f:
                         self._err(lr, _(b"entry without name in manifest"))
                     elif f == b"/dev/null":  # ignore this in very old repos
                         continue
                     fullpath = dir + _normpath(f)
                     if fl == b't':
                         if not match.visitdir(fullpath):
                             continue
                         subdirnodes.setdefault(fullpath + b'/', {}).setdefault(
                             fn, []
                         ).append(lr)
                     else:
                         if not match(fullpath):
                             continue
                         filenodes.setdefault(fullpath, {}).setdefault(fn, lr)
             except Exception as inst:
                 self._exc(lr, _(b"reading delta %s") % short(n), inst, label)
             if self._level >= VERIFY_FULL:
                 try:
                     # Various issues can affect manifest. So we read each full
                     # text from storage. This triggers the checks from the core
                     # code (eg: hash verification, filename are ordered, etc.)
                     mfdelta = mfl.get(dir, n).read()
                 except Exception as inst:
                     self._exc(
                         lr,
                         _(b"reading full manifest %s") % short(n),
                         inst,
                         label,
                     )
 
         if not dir:
             progress.complete()
 
         if self.havemf:
             # since we delete entry in `mflinkrevs` during iteration, any
             # remaining entries are "missing". We need to issue errors for them.
             changesetpairs = [(c, m) for m in mflinkrevs for c in mflinkrevs[m]]
             for c, m in sorted(changesetpairs):
                 if dir:
                     self._err(
                         c,
                         _(
                             b"parent-directory manifest refers to unknown"
                             b" revision %s"
                         )
                         % short(m),
                         label,
                     )
                 else:
                     self._err(
                         c,
                         _(b"changeset refers to unknown revision %s")
                         % short(m),
                         label,
                     )
 
         if not dir and subdirnodes:
             self.ui.status(_(b"checking directory manifests\n"))
             storefiles = set()
             subdirs = set()
             revlogv1 = self.revlogv1
             for f, f2, size in repo.store.datafiles():
                 if not f:
                     self._err(None, _(b"cannot decode filename '%s'") % f2)
                 elif (size > 0 or not revlogv1) and f.startswith(b'meta/'):
                     storefiles.add(_normpath(f))
                     subdirs.add(os.path.dirname(f))
             subdirprogress = ui.makeprogress(
                 _(b'checking'), unit=_(b'manifests'), total=len(subdirs)
             )
 
         for subdir, linkrevs in pycompat.iteritems(subdirnodes):
             subdirfilenodes = self._verifymanifest(
                 linkrevs, subdir, storefiles, subdirprogress
             )
             for f, onefilenodes in pycompat.iteritems(subdirfilenodes):
                 filenodes.setdefault(f, {}).update(onefilenodes)
 
         if not dir and subdirnodes:
             subdirprogress.complete()
             if self.warnorphanstorefiles:
                 for f in sorted(storefiles):
                     self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return filenodes
 
     def _crosscheckfiles(self, filelinkrevs, filenodes):
         repo = self.repo
         ui = self.ui
         ui.status(_(b"crosschecking files in changesets and manifests\n"))
 
         total = len(filelinkrevs) + len(filenodes)
         progress = ui.makeprogress(
             _(b'crosschecking'), unit=_(b'files'), total=total
         )
         if self.havemf:
             for f in sorted(filelinkrevs):
                 progress.increment()
                 if f not in filenodes:
                     lr = filelinkrevs[f][0]
                     self._err(lr, _(b"in changeset but not in manifest"), f)
 
         if self.havecl:
             for f in sorted(filenodes):
                 progress.increment()
                 if f not in filelinkrevs:
                     try:
                         fl = repo.file(f)
                         lr = min([fl.linkrev(fl.rev(n)) for n in filenodes[f]])
                     except Exception:
                         lr = None
                     self._err(lr, _(b"in manifest but not in changeset"), f)
 
         progress.complete()
 
     def _verifyfiles(self, filenodes, filelinkrevs):
         repo = self.repo
         ui = self.ui
         lrugetctx = self.lrugetctx
         revlogv1 = self.revlogv1
         havemf = self.havemf
         ui.status(_(b"checking files\n"))
 
         storefiles = set()
         for f, f2, size in repo.store.datafiles():
             if not f:
                 self._err(None, _(b"cannot decode filename '%s'") % f2)
             elif (size > 0 or not revlogv1) and f.startswith(b'data/'):
                 storefiles.add(_normpath(f))
 
         state = {
             # TODO this assumes revlog storage for changelog.
             b'expectedversion': self.repo.changelog.version & 0xFFFF,
             b'skipflags': self.skipflags,
             # experimental config: censor.policy
             b'erroroncensored': ui.config(b'censor', b'policy') == b'abort',
         }
 
         files = sorted(set(filenodes) | set(filelinkrevs))
         revisions = 0
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'files'), total=len(files)
         )
         for i, f in enumerate(files):
             progress.update(i, item=f)
             try:
                 linkrevs = filelinkrevs[f]
             except KeyError:
                 # in manifest but not in changelog
                 linkrevs = []
 
             if linkrevs:
                 lr = linkrevs[0]
             else:
                 lr = None
 
             try:
                 fl = repo.file(f)
             except error.StorageError as e:
                 self._err(lr, _(b"broken revlog! (%s)") % e, f)
                 continue
 
             for ff in fl.files():
                 try:
                     storefiles.remove(ff)
                 except KeyError:
                     if self.warnorphanstorefiles:
                         self._warn(
                             _(b" warning: revlog '%s' not in fncache!") % ff
                         )
                         self.fncachewarned = True
 
             if not len(fl) and (self.havecl or self.havemf):
                 self._err(lr, _(b"empty or missing %s") % f)
             else:
                 # Guard against implementations not setting this.
                 state[b'skipread'] = set()
+                state[b'safe_renamed'] = set()
+
                 for problem in fl.verifyintegrity(state):
                     if problem.node is not None:
                         linkrev = fl.linkrev(fl.rev(problem.node))
                     else:
                         linkrev = None
 
                     if problem.warning:
                         self._warn(problem.warning)
                     elif problem.error:
                         self._err(
                             linkrev if linkrev is not None else lr,
                             problem.error,
                             f,
                         )
                     else:
                         raise error.ProgrammingError(
                             b'problem instance does not set warning or error '
                             b'attribute: %s' % problem.msg
                         )
 
             seen = {}
             for i in fl:
                 revisions += 1
                 n = fl.node(i)
                 lr = self._checkentry(fl, i, n, seen, linkrevs, f)
                 if f in filenodes:
                     if havemf and n not in filenodes[f]:
                         self._err(lr, _(b"%s not in manifests") % (short(n)), f)
                     else:
                         del filenodes[f][n]
 
-                if n in state[b'skipread']:
+                if n in state[b'skipread'] and n not in state[b'safe_renamed']:
                     continue
 
                 # check renames
                 try:
                     # This requires resolving fulltext (at least on revlogs,
                     # though not with LFS revisions). We may want
                     # ``verifyintegrity()`` to pass a set of nodes with
                     # rename metadata as an optimization.
                     rp = fl.renamed(n)
                     if rp:
                         if lr is not None and ui.verbose:
                             ctx = lrugetctx(lr)
                             if not any(rp[0] in pctx for pctx in ctx.parents()):
                                 self._warn(
                                     _(
                                         b"warning: copy source of '%s' not"
                                         b" in parents of %s"
                                     )
                                     % (f, ctx)
                                 )
                         fl2 = repo.file(rp[0])
                         if not len(fl2):
                             self._err(
                                 lr,
                                 _(
                                     b"empty or missing copy source revlog "
                                     b"%s:%s"
                                 )
                                 % (rp[0], short(rp[1])),
                                 f,
                             )
                         elif rp[1] == nullid:
                             ui.note(
                                 _(
                                     b"warning: %s@%s: copy source"
                                     b" revision is nullid %s:%s\n"
                                 )
                                 % (f, lr, rp[0], short(rp[1]))
                             )
                         else:
                             fl2.rev(rp[1])
                 except Exception as inst:
                     self._exc(
                         lr, _(b"checking rename of %s") % short(n), inst, f
                     )
 
             # cross-check
             if f in filenodes:
                 fns = [(v, k) for k, v in pycompat.iteritems(filenodes[f])]
                 for lr, node in sorted(fns):
                     self._err(
                         lr,
                         _(b"manifest refers to unknown revision %s")
                         % short(node),
                         f,
                     )
         progress.complete()
 
         if self.warnorphanstorefiles:
             for f in sorted(storefiles):
                 self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return len(files), revisions

tests/test-lfs.t

@@ -1,1192 +1,1231 b''
 #require no-reposimplestore no-chg
 
   $ hg init requirements
   $ cd requirements
 
 # LFS not loaded by default.
 
   $ hg config extensions
   [1]
 
 # Adding lfs to requires file will auto-load lfs extension.
 
   $ echo lfs >> .hg/requires
   $ hg config extensions
   extensions.lfs=
 
 # But only if there is no config entry for the extension already.
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs=!
   > EOF
 
   $ hg config extensions
   abort: repository requires features unknown to this Mercurial: lfs!
   (see https://mercurial-scm.org/wiki/MissingRequirement for more information)
   [255]
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs=
   > EOF
 
   $ hg config extensions
   extensions.lfs=
 
   $ cat > .hg/hgrc << EOF
   > [extensions]
   > lfs = missing.py
   > EOF
 
   $ hg config extensions
   \*\*\* failed to import extension lfs from missing.py: [Errno *] $ENOENT$: 'missing.py' (glob)
   abort: repository requires features unknown to this Mercurial: lfs!
   (see https://mercurial-scm.org/wiki/MissingRequirement for more information)
   [255]
 
   $ cd ..
 
 # Initial setup
 
   $ cat >> $HGRCPATH << EOF
   > [extensions]
   > lfs=
   > [lfs]
   > # Test deprecated config
   > threshold=1000B
   > EOF
 
   $ LONG=AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Prepare server and enable extension
   $ hg init server
   $ hg clone -q server client
   $ cd client
 
 # Commit small file
   $ echo s > smallfile
   $ echo '**.py = LF' > .hgeol
   $ hg --config lfs.track='"size(\">1000B\")"' commit -Aqm "add small file"
   hg: parse error: unsupported file pattern: size(">1000B")
   (paths must be prefixed with "path:")
   [255]
   $ hg --config lfs.track='size(">1000B")' commit -Aqm "add small file"
 
 # Commit large file
   $ echo $LONG > largefile
   $ grep lfs .hg/requires
   [1]
   $ hg commit --traceback -Aqm "add large file"
   $ grep lfs .hg/requires
   lfs
 
 # Ensure metadata is stored
   $ hg debugdata largefile 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:f11e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
   size 1501
   x-is-binary 0
 
 # Check the blobstore is populated
   $ find .hg/store/lfs/objects | sort
   .hg/store/lfs/objects
   .hg/store/lfs/objects/f1
   .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
 
 # Check the blob stored contains the actual contents of the file
   $ cat .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Push changes to the server
 
   $ hg push
   pushing to $TESTTMP/server
   searching for changes
   abort: lfs.url needs to be configured
   [255]
 
   $ cat >> $HGRCPATH << EOF
   > [lfs]
   > url=file:$TESTTMP/dummy-remote/
   > EOF
 
 Push to a local non-lfs repo with the extension enabled will add the
 lfs requirement
 
   $ grep lfs $TESTTMP/server/.hg/requires
   [1]
   $ hg push -v | egrep -v '^(uncompressed| )'
   pushing to $TESTTMP/server
   searching for changes
   lfs: found f11e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b in the local lfs store
   2 changesets found
   adding changesets
   adding manifests
   adding file changes
   calling hook pretxnchangegroup.lfs: hgext.lfs.checkrequireslfs
   added 2 changesets with 3 changes to 3 files
   $ grep lfs $TESTTMP/server/.hg/requires
   lfs
 
 # Unknown URL scheme
 
   $ hg push --config lfs.url=ftp://foobar
   abort: lfs: unknown url scheme: ftp
   [255]
 
   $ cd ../
 
 # Initialize new client (not cloning) and setup extension
   $ hg init client2
   $ cd client2
   $ cat >> .hg/hgrc <<EOF
   > [paths]
   > default = $TESTTMP/server
   > EOF
 
 # Pull from server
 
 Pulling a local lfs repo into a local non-lfs repo with the extension
 enabled adds the lfs requirement
 
   $ grep lfs .hg/requires $TESTTMP/server/.hg/requires
   $TESTTMP/server/.hg/requires:lfs
   $ hg pull default
   pulling from $TESTTMP/server
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 3 changes to 3 files
   new changesets 0ead593177f7:b88141481348
   (run 'hg update' to get a working copy)
   $ grep lfs .hg/requires $TESTTMP/server/.hg/requires
   .hg/requires:lfs
   $TESTTMP/server/.hg/requires:lfs
 
 # Check the blobstore is not yet populated
   $ [ -d .hg/store/lfs/objects ]
   [1]
 
 # Update to the last revision containing the large file
   $ hg update
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 # Check the blobstore has been populated on update
   $ find .hg/store/lfs/objects | sort
   .hg/store/lfs/objects
   .hg/store/lfs/objects/f1
   .hg/store/lfs/objects/f1/1e77c257047a398492d8d6cb9f6acf3aa7c4384bb23080b43546053e183e4b
 
 # Check the contents of the file are fetched from blobstore when requested
   $ hg cat -r . largefile
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
 # Check the file has been copied in the working copy
   $ cat largefile
   AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
 
   $ cd ..
 
 # Check rename, and switch between large and small files
 
   $ hg init repo3
   $ cd repo3
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > EOF
 
   $ echo LONGER-THAN-TEN-BYTES-WILL-TRIGGER-LFS > large
   $ echo SHORTER > small
   $ hg add . -q
   $ hg commit -m 'commit with lfs content'
 
   $ hg files -r . 'set:added()'
   large
   small
   $ hg files -r . 'set:added() & lfs()'
   large
 
   $ hg mv large l
   $ hg mv small s
   $ hg status 'set:removed()'
   R large
   R small
   $ hg status 'set:removed() & lfs()'
   R large
   $ hg commit -m 'renames'
 
+  $ hg cat -r . l -T '{rawdata}\n'
+  version https://git-lfs.github.com/spec/v1
+  oid sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
+  size 39
+  x-hg-copy large
+  x-hg-copyrev 2c531e0992ff3107c511b53cb82a91b6436de8b2
+  x-is-binary 0
+  
+
   $ hg files -r . 'set:copied()'
   l
   s
   $ hg files -r . 'set:copied() & lfs()'
   l
   $ hg status --change . 'set:removed()'
   R large
   R small
   $ hg status --change . 'set:removed() & lfs()'
   R large
 
   $ echo SHORT > l
   $ echo BECOME-LARGER-FROM-SHORTER > s
   $ hg commit -m 'large to small, small to large'
 
   $ echo 1 >> l
   $ echo 2 >> s
   $ hg commit -m 'random modifications'
 
   $ echo RESTORE-TO-BE-LARGE > l
   $ echo SHORTER > s
   $ hg commit -m 'switch large and small again'
 
 # Test lfs_files template
 
   $ hg log -r 'all()' -T '{rev} {join(lfs_files, ", ")}\n'
   0 large
   1 l, large
   2 s
   3 s
   4 l
 
 # Push and pull the above repo
 
   $ hg --cwd .. init repo4
   $ hg push ../repo4
   pushing to ../repo4
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 10 changes to 4 files
 
   $ hg --cwd .. init repo5
   $ hg --cwd ../repo5 pull ../repo3
   pulling from ../repo3
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 5 changesets with 10 changes to 4 files
   new changesets fd47a419c4f7:5adf850972b9
   (run 'hg update' to get a working copy)
 
   $ cd ..
 
 # Test clone
 
   $ hg init repo6
   $ cd repo6
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">30B")
   > EOF
 
   $ echo LARGE-BECAUSE-IT-IS-MORE-THAN-30-BYTES > large
   $ echo SMALL > small
   $ hg commit -Aqm 'create a lfs file' large small
   $ hg debuglfsupload -r 'all()' -v
   lfs: found 8e92251415339ae9b148c8da89ed5ec665905166a1ab11b09dca8fad83344738 in the local lfs store
 
   $ cd ..
 
   $ hg clone repo6 repo7
   updating to branch default
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd repo7
   $ cat large
   LARGE-BECAUSE-IT-IS-MORE-THAN-30-BYTES
   $ cat small
   SMALL
 
   $ cd ..
 
   $ hg --config extensions.share= share repo7 sharedrepo
   updating working directory
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ grep lfs sharedrepo/.hg/requires
   lfs
 
 # Test rename and status
 
   $ hg init repo8
   $ cd repo8
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > EOF
 
   $ echo THIS-IS-LFS-BECAUSE-10-BYTES > a1
   $ echo SMALL > a2
   $ hg commit -m a -A a1 a2
   $ hg status
   $ hg mv a1 b1
   $ hg mv a2 a1
   $ hg mv b1 a2
   $ hg commit -m b
   $ hg status
   >>> with open('a2', 'wb') as f:
   ...     f.write(b'\1\nSTART-WITH-HG-FILELOG-METADATA') and None
   >>> with open('a1', 'wb') as f:
   ...     f.write(b'\1\nMETA\n') and None
   $ hg commit -m meta
   $ hg status
   $ hg log -T '{rev}: {file_copies} | {file_dels} | {file_adds}\n'
   2:  |  | 
   1: a1 (a2)a2 (a1) |  | 
   0:  |  | a1 a2
 
   $ for n in a1 a2; do
   >   for r in 0 1 2; do
   >     printf '\n%s @ %s\n' $n $r
   >     hg debugdata $n $r
   >   done
   > done
   
   a1 @ 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   
   a1 @ 1
   \x01 (esc)
   copy: a2
   copyrev: 50470ad23cf937b1f4b9f80bfe54df38e65b50d9
   \x01 (esc)
   SMALL
   
   a1 @ 2
   \x01 (esc)
   \x01 (esc)
   \x01 (esc)
   META
   
   a2 @ 0
   SMALL
   
   a2 @ 1
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-hg-copy a1
   x-hg-copyrev be23af27908a582af43e5cda209a5a9b319de8d4
   x-is-binary 0
   
   a2 @ 2
   version https://git-lfs.github.com/spec/v1
   oid sha256:876dadc86a8542f9798048f2c47f51dbf8e4359aed883e8ec80c5db825f0d943
   size 32
   x-is-binary 0
 
 # Verify commit hashes include rename metadata
 
   $ hg log -T '{rev}:{node|short} {desc}\n'
   2:0fae949de7fa meta
   1:9cd6bdffdac0 b
   0:7f96794915f7 a
 
   $ cd ..
 
 # Test bundle
 
   $ hg init repo9
   $ cd repo9
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=size(">10B")
   > [diff]
   > git=1
   > EOF
 
   $ for i in 0 single two three 4; do
   >   echo 'THIS-IS-LFS-'$i > a
   >   hg commit -m a-$i -A a
   > done
 
   $ hg update 2 -q
   $ echo 'THIS-IS-LFS-2-CHILD' > a
   $ hg commit -m branching -q
 
   $ hg bundle --base 1 bundle.hg -v
   lfs: found 5ab7a3739a5feec94a562d070a14f36dba7cad17e5484a4a89eea8e5f3166888 in the local lfs store
   lfs: found a9c7d1cd6ce2b9bbdf46ed9a862845228717b921c089d0d42e3bcaed29eb612e in the local lfs store
   lfs: found f693890c49c409ec33673b71e53f297681f76c1166daf33b2ad7ebf8b1d3237e in the local lfs store
   lfs: found fda198fea753eb66a252e9856915e1f5cddbe41723bd4b695ece2604ad3c9f75 in the local lfs store
   4 changesets found
   uncompressed size of bundle content:
        * (changelog) (glob)
        * (manifests) (glob)
       * a (glob)
   $ hg --config extensions.strip= strip -r 2 --no-backup --force -q
   $ hg -R bundle.hg log -p -T '{rev} {desc}\n' a
   5 branching
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-2-CHILD
   
   4 a-4
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-three
   +THIS-IS-LFS-4
   
   3 a-three
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-three
   
   2 a-two
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-single
   +THIS-IS-LFS-two
   
   1 a-single
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-0
   +THIS-IS-LFS-single
   
   0 a-0
   diff --git a/a b/a
   new file mode 100644
   --- /dev/null
   +++ b/a
   @@ -0,0 +1,1 @@
   +THIS-IS-LFS-0
   
   $ hg bundle -R bundle.hg --base 1 bundle-again.hg -q
   $ hg -R bundle-again.hg log -p -T '{rev} {desc}\n' a
   5 branching
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-2-CHILD
   
   4 a-4
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-three
   +THIS-IS-LFS-4
   
   3 a-three
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-two
   +THIS-IS-LFS-three
   
   2 a-two
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-single
   +THIS-IS-LFS-two
   
   1 a-single
   diff --git a/a b/a
   --- a/a
   +++ b/a
   @@ -1,1 +1,1 @@
   -THIS-IS-LFS-0
   +THIS-IS-LFS-single
   
   0 a-0
   diff --git a/a b/a
   new file mode 100644
   --- /dev/null
   +++ b/a
   @@ -0,0 +1,1 @@
   +THIS-IS-LFS-0
   
   $ cd ..
 
 # Test isbinary
 
   $ hg init repo10
   $ cd repo10
   $ cat >> .hg/hgrc << EOF
   > [extensions]
   > lfs=
   > [lfs]
   > track=all()
   > EOF
   $ "$PYTHON" <<'EOF'
   > def write(path, content):
   >     with open(path, 'wb') as f:
   >         f.write(content)
   > write('a', b'\0\0')
   > write('b', b'\1\n')
   > write('c', b'\1\n\0')
   > write('d', b'xx')
   > EOF
   $ hg add a b c d
   $ hg diff --stat
    a |  Bin 
    b |    1 +
    c |  Bin 
    d |    1 +
    4 files changed, 2 insertions(+), 0 deletions(-)
   $ hg commit -m binarytest
   $ cat > $TESTTMP/dumpbinary.py << EOF
   > from mercurial.utils import (
   >     stringutil,
   > )
   > def reposetup(ui, repo):
   >     for n in (b'a', b'b', b'c', b'd'):
   >         ui.write((b'%s: binary=%s\n')
   >                   % (n, stringutil.pprint(repo[b'.'][n].isbinary())))
   > EOF
   $ hg --config extensions.dumpbinary=$TESTTMP/dumpbinary.py id --trace
   a: binary=True
   b: binary=False
   c: binary=True
   d: binary=False
   b55353847f02 tip
 
 Binary blobs don't need to be present to be skipped in filesets.  (And their
 absence doesn't cause an abort.)
 
   $ rm .hg/store/lfs/objects/96/a296d224f285c67bee93c30f8a309157f0daa35dc5b87e410b78630a09cfc7
   $ rm .hg/store/lfs/objects/92/f76135a4baf4faccb8586a60faf830c2bdfce147cefa188aaf4b790bd01b7e
 
   $ hg files --debug -r . 'set:eol("unix")' --config 'experimental.lfs.disableusercache=True'
   lfs: found c04b5bb1a5b2eb3e9cd4805420dba5a9d133da5b7adeeafb5474c4adae9faa80 in the local lfs store
            2   b
   lfs: found 5dde896887f6754c9b15bfe3a441ae4806df2fde94001311e08bf110622e0bbe in the local lfs store
 
   $ hg files --debug -r . 'set:binary()' --config 'experimental.lfs.disableusercache=True'
            2   a
            3   c
 
   $ cd ..
 
 # Test fctx.cmp fastpath - diff without LFS blobs
 
   $ hg init repo12
   $ cd repo12
   $ cat >> .hg/hgrc <<EOF
   > [lfs]
   > threshold=1
   > EOF
   $ cat > ../patch.diff <<EOF
   > # HG changeset patch
   > 2
   > 
   > diff --git a/a b/a
   > old mode 100644
   > new mode 100755
   > EOF
 
   $ for i in 1 2 3; do
   >     cp ../repo10/a a
   >     if [ $i = 3 ]; then
   >         # make a content-only change
   >         hg import -q --bypass ../patch.diff
   >         hg update -q
   >         rm ../patch.diff
   >     else
   >         echo $i >> a
   >         hg commit -m $i -A a
   >     fi
   > done
   $ [ -d .hg/store/lfs/objects ]
 
   $ cd ..
 
   $ hg clone repo12 repo13 --noupdate
   $ cd repo13
   $ hg log --removed -p a -T '{desc}\n' --config diff.nobinary=1 --git
   2
   diff --git a/a b/a
   old mode 100644
   new mode 100755
   
   2
   diff --git a/a b/a
   Binary file a has changed
   
   1
   diff --git a/a b/a
   new file mode 100644
   Binary file a has changed
   
   $ [ -d .hg/store/lfs/objects ]
   [1]
 
   $ cd ..
 
 # Test filter
 
   $ hg init repo11
   $ cd repo11
   $ cat >> .hg/hgrc << EOF
   > [lfs]
   > track=(**.a & size(">5B")) | (**.b & !size(">5B"))
   >      | (**.c & "path:d" & !"path:d/c.c") | size(">10B")
   > EOF
 
   $ mkdir a
   $ echo aaaaaa > a/1.a
   $ echo a > a/2.a
   $ echo aaaaaa > 1.b
   $ echo a > 2.b
   $ echo a > 1.c
   $ mkdir d
   $ echo a > d/c.c
   $ echo a > d/d.c
   $ echo aaaaaaaaaaaa > x
   $ hg add . -q
   $ hg commit -m files
 
   $ for p in a/1.a a/2.a 1.b 2.b 1.c d/c.c d/d.c x; do
   >   if hg debugdata $p 0 2>&1 | grep git-lfs >/dev/null; then
   >     echo "${p}: is lfs"
   >   else
   >     echo "${p}: not lfs"
   >   fi
   > done
   a/1.a: is lfs
   a/2.a: not lfs
   1.b: not lfs
   2.b: is lfs
   1.c: not lfs
   d/c.c: not lfs
   d/d.c: is lfs
   x: is lfs
 
   $ cd ..
 
 # Verify the repos
 
   $ cat > $TESTTMP/dumpflog.py << EOF
   > # print raw revision sizes, flags, and hashes for certain files
   > import hashlib
   > from mercurial.node import short
   > from mercurial import (
   >     pycompat,
   >     revlog,
   > )
   > from mercurial.utils import (
   >     stringutil,
   > )
   > def hash(rawtext):
   >     h = hashlib.sha512()
   >     h.update(rawtext)
   >     return pycompat.sysbytes(h.hexdigest()[:4])
   > def reposetup(ui, repo):
   >     # these 2 files are interesting
   >     for name in [b'l', b's']:
   >         fl = repo.file(name)
   >         if len(fl) == 0:
   >             continue
   >         sizes = [fl._revlog.rawsize(i) for i in fl]
   >         texts = [fl.rawdata(i) for i in fl]
   >         flags = [int(fl._revlog.flags(i)) for i in fl]
   >         hashes = [hash(t) for t in texts]
   >         pycompat.stdout.write(b'  %s: rawsizes=%r flags=%r hashes=%s\n'
   >                               % (name, sizes, flags, stringutil.pprint(hashes)))
   > EOF
 
   $ for i in client client2 server repo3 repo4 repo5 repo6 repo7 repo8 repo9 \
   >          repo10; do
   >   echo 'repo:' $i
   >   hg --cwd $i verify --config extensions.dumpflog=$TESTTMP/dumpflog.py -q
   > done
   repo: client
   repo: client2
   repo: server
   repo: repo3
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo4
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo5
     l: rawsizes=[211, 6, 8, 141] flags=[8192, 0, 0, 8192] hashes=['d2b8', '948c', 'cc88', '724d']
     s: rawsizes=[74, 141, 141, 8] flags=[0, 8192, 8192, 0] hashes=['3c80', 'fce0', '874a', '826b']
   repo: repo6
   repo: repo7
   repo: repo8
   repo: repo9
   repo: repo10
 
 repo13 doesn't have any cached lfs files and its source never pushed its
 files.  Therefore, the files don't exist in the remote store.  Use the files in
 the user cache.
 
   $ test -d $TESTTMP/repo13/.hg/store/lfs/objects
   [1]
 
   $ hg --config extensions.share= share repo13 repo14
   updating working directory
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R repo14 -q verify
 
   $ hg clone repo13 repo15
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg -R repo15 -q verify
 
 If the source repo doesn't have the blob (maybe it was pulled or cloned with
 --noupdate), the blob is still accessible via the global cache to send to the
 remote store.
 
   $ rm -rf $TESTTMP/repo15/.hg/store/lfs
   $ hg init repo16
   $ hg -R repo15 push repo16
   pushing to repo16
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 2 changes to 1 files
   $ hg -R repo15 -q verify
 
 Test damaged file scenarios.  (This also damages the usercache because of the
 hardlinks.)
 
   $ echo 'damage' >> repo5/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
 
 Repo with damaged lfs objects in any revision will fail verification.
 
   $ hg -R repo5 verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
    large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
 Updates work after cloning a damaged repo, if the damaged lfs objects aren't in
 the update destination.  Those objects won't be added to the new repo's store
 because they aren't accessed.
 
   $ hg clone -v repo5 fromcorrupt
   updating to branch default
   resolving manifests
   getting l
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the usercache
   getting s
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ test -f fromcorrupt/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   [1]
 
-Verify will not try to download lfs blobs, if told not to process lfs content
+Verify will not try to download lfs blobs, if told not to process lfs content.
+The extension makes sure that the filelog.renamed() path is taken on a missing
+blob, and the output shows that it isn't fetched.
 
-  $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v --no-lfs
+  $ cat > $TESTTMP/lfsrename.py <<EOF
+  > from mercurial import (
+  >     exthelper,
+  > )
+  > 
+  > from hgext.lfs import (
+  >     pointer,
+  >     wrapper,
+  > )
+  > 
+  > eh = exthelper.exthelper()
+  > uisetup = eh.finaluisetup
+  > 
+  > @eh.wrapfunction(wrapper, b'filelogrenamed')
+  > def filelogrenamed(orig, orig1, self, node):
+  >     ret = orig(orig1, self, node)
+  >     if wrapper._islfs(self._revlog, node) and ret:
+  >         rawtext = self._revlog.rawdata(node)
+  >         metadata = pointer.deserialize(rawtext)
+  >         print('lfs blob %s renamed %s -> %s'
+  >               % (metadata[b'oid'], ret[0], self._revlog.filename))
+  >     return ret
+  > EOF
+
+  $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v --no-lfs \
+  >                   --config extensions.x=$TESTTMP/lfsrename.py
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
+  lfs blob sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e renamed large -> l
   checked 5 changesets with 10 changes to 4 files
 
 Verify will not try to download lfs blobs, if told not to by the config option
 
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v \
-  >                   --config verify.skipflags=8192
+  >                   --config verify.skipflags=8192 \
+  >                   --config extensions.x=$TESTTMP/lfsrename.py
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
+  lfs blob sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e renamed large -> l
   checked 5 changesets with 10 changes to 4 files
 
 Verify will copy/link all lfs objects into the local store that aren't already
 present.  Bypass the corrupted usercache to show that verify works when fed by
 the (uncorrupted) remote store.
 
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: adding 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e to the usercache
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: adding 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 to the usercache
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: adding b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c to the usercache
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
 
 Verify will not copy/link a corrupted file from the usercache into the local
 store, and poison it.  (The verify with a good remote now works.)
 
   $ rm -r fromcorrupt/.hg/store/lfs/objects/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   $ hg -R fromcorrupt verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
    large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ hg -R fromcorrupt --config lfs.usercache=emptycache verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the usercache
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   lfs: found 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e in the local lfs store
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
 
 Damaging a file required by the update destination fails the update.
 
   $ echo 'damage' >> $TESTTMP/dummy-remote/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ hg --config lfs.usercache=emptycache clone -v repo5 fromcorrupt2
   updating to branch default
   resolving manifests
   abort: corrupt remote lfs object: 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [255]
 
 A corrupted lfs blob is not transferred from a file://remotestore to the
 usercache or local store.
 
   $ test -f emptycache/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [1]
   $ test -f fromcorrupt2/.hg/store/lfs/objects/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   [1]
 
   $ hg -R fromcorrupt2 verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
    large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
 Corrupt local files are not sent upstream.  (The alternate dummy remote
 avoids the corrupt lfs object in the original remote.)
 
   $ mkdir $TESTTMP/dummy-remote2
   $ hg init dest
   $ hg -R fromcorrupt2 --config lfs.url=file:///$TESTTMP/dummy-remote2 push -v dest
   pushing to dest
   searching for changes
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
   abort: detected corrupt lfs object: 66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   (run hg verify)
   [255]
 
   $ hg -R fromcorrupt2 --config lfs.url=file:///$TESTTMP/dummy-remote2 verify -v
   repository uses revlog format 1
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    l@1: unpacking 46a2f24864bc: integrity check failed on data/l.i:0
   lfs: found 22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b in the local lfs store
    large@0: unpacking 2c531e0992ff: integrity check failed on data/large.i:0
   lfs: found 89b6070915a3d573ff3599d1cda305bc5e38549b15c4847ab034169da66e1ca8 in the local lfs store
   lfs: found b1a6ea88da0017a0e77db139a54618986e9a2489bee24af9fe596de9daac498c in the local lfs store
   checked 5 changesets with 10 changes to 4 files
   2 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
 
   $ cat $TESTTMP/dummy-remote2/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b | $TESTDIR/f --sha256
   sha256=22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ cat fromcorrupt2/.hg/store/lfs/objects/22/f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b | $TESTDIR/f --sha256
   sha256=22f66a3fc0b9bf3f012c814303995ec07099b3a9ce02a7af84b5970811074a3b
   $ test -f $TESTTMP/dummy-remote2/66/100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   [1]
 
 Accessing a corrupt file will complain
 
   $ hg --cwd fromcorrupt2 cat -r 0 large
   abort: integrity check failed on data/large.i:0!
   [255]
 
 lfs -> normal -> lfs round trip conversions are possible.  The 'none()'
 predicate on the command line will override whatever is configured globally and
 locally, and ensures everything converts to a regular file.  For lfs -> normal,
 there's no 'lfs' destination repo requirement.  For normal -> lfs, there is.
 
   $ hg --config extensions.convert= --config 'lfs.track=none()' \
   >    convert repo8 convert_normal
   initializing destination convert_normal repository
   scanning source...
   sorting...
   converting...
   2 a
   1 b
   0 meta
   $ grep 'lfs' convert_normal/.hg/requires
   [1]
   $ hg --cwd convert_normal cat a1 -r 0 -T '{rawdata}'
   THIS-IS-LFS-BECAUSE-10-BYTES
 
   $ hg --config extensions.convert= --config lfs.threshold=10B \
   >    convert convert_normal convert_lfs
   initializing destination convert_lfs repository
   scanning source...
   sorting...
   converting...
   2 a
   1 b
   0 meta
 
   $ hg --cwd convert_lfs cat -r 0 a1 -T '{rawdata}'
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   $ hg --cwd convert_lfs debugdata a1 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size 29
   x-is-binary 0
   $ hg --cwd convert_lfs log -r 0 -T "{lfs_files % '{lfspointer % '{key}={value}\n'}'}"
   version=https://git-lfs.github.com/spec/v1
   oid=sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   size=29
   x-is-binary=0
   $ hg --cwd convert_lfs log -r 0 \
   >    -T '{lfs_files % "{get(lfspointer, "oid")}\n"}{lfs_files % "{lfspointer.oid}\n"}'
   sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   $ hg --cwd convert_lfs log -r 0 -T '{lfs_files % "{lfspointer}\n"}'
   version=https://git-lfs.github.com/spec/v1 oid=sha256:5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024 size=29 x-is-binary=0
   $ hg --cwd convert_lfs \
   >     log -r 'all()' -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}'
   0: a1: 5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   1: a2: 5bb8341bee63b3649f222b2215bde37322bea075a30575aa685d8f8d21c77024
   2: a2: 876dadc86a8542f9798048f2c47f51dbf8e4359aed883e8ec80c5db825f0d943
 
   $ grep 'lfs' convert_lfs/.hg/requires
   lfs
 
 The hashes in all stages of the conversion are unchanged.
 
   $ hg -R repo8 log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
   $ hg -R convert_normal log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
   $ hg -R convert_lfs log -T '{node|short}\n'
   0fae949de7fa
   9cd6bdffdac0
   7f96794915f7
 
 This convert is trickier, because it contains deleted files (via `hg mv`)
 
   $ hg --config extensions.convert= --config lfs.threshold=1000M \
   >    convert repo3 convert_normal2
   initializing destination convert_normal2 repository
   scanning source...
   sorting...
   converting...
   4 commit with lfs content
   3 renames
   2 large to small, small to large
   1 random modifications
   0 switch large and small again
   $ grep 'lfs' convert_normal2/.hg/requires
   [1]
   $ hg --cwd convert_normal2 debugdata large 0
   LONGER-THAN-TEN-BYTES-WILL-TRIGGER-LFS
 
   $ hg --config extensions.convert= --config lfs.threshold=10B \
   >    convert convert_normal2 convert_lfs2
   initializing destination convert_lfs2 repository
   scanning source...
   sorting...
   converting...
   4 commit with lfs content
   3 renames
   2 large to small, small to large
   1 random modifications
   0 switch large and small again
   $ grep 'lfs' convert_lfs2/.hg/requires
   lfs
   $ hg --cwd convert_lfs2 debugdata large 0
   version https://git-lfs.github.com/spec/v1
   oid sha256:66100b384bf761271b407d79fc30cdd0554f3b2c5d944836e936d584b88ce88e
   size 39
   x-is-binary 0
 
 Committing deleted files works:
 
   $ hg init $TESTTMP/repo-del
   $ cd $TESTTMP/repo-del
   $ echo 1 > A
   $ hg commit -m 'add A' -A A
   $ hg rm A
   $ hg commit -m 'rm A'
 
 Bad .hglfs files will block the commit with a useful message
 
   $ cat > .hglfs << EOF
   > [track]
   > **.test = size(">5B")
   > bad file ... no commit
   > EOF
 
   $ echo x > file.txt
   $ hg ci -Aqm 'should fail'
   hg: parse error at .hglfs:3: bad file ... no commit
   [255]
 
   $ cat > .hglfs << EOF
   > [track]
   > **.test = size(">5B")
   > ** = nonexistent()
   > EOF
 
   $ hg ci -Aqm 'should fail'
   abort: parse error in .hglfs: unknown identifier: nonexistent
   [255]
 
 '**' works out to mean all files.
 
   $ cat > .hglfs << EOF
   > [track]
   > path:.hglfs = none()
   > **.test = size(">5B")
   > **.exclude = none()
   > ** = size(">10B")
   > EOF
 
 The LFS policy takes effect without tracking the .hglfs file
 
   $ echo 'largefile' > lfs.test
   $ echo '012345678901234567890' > nolfs.exclude
   $ echo '01234567890123456' > lfs.catchall
   $ hg add *
   $ hg ci -qm 'before add .hglfs'
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   2: lfs.catchall: d4ec46c2869ba22eceb42a729377432052d9dd75d82fc40390ebaadecee87ee9
   lfs.test: 5489e6ced8c36a7b267292bde9fd5242a5f80a7482e8f23fa0477393dfaa4d6c
   
 The .hglfs file works when tracked
 
   $ echo 'largefile2' > lfs.test
   $ echo '012345678901234567890a' > nolfs.exclude
   $ echo '01234567890123456a' > lfs.catchall
   $ hg ci -Aqm 'after adding .hglfs'
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   3: lfs.catchall: 31f43b9c62b540126b0ad5884dc013d21a61c9329b77de1fceeae2fc58511573
   lfs.test: 8acd23467967bc7b8cc5a280056589b0ba0b17ff21dbd88a7b6474d6290378a6
   
 The LFS policy stops when the .hglfs is gone
 
   $ mv .hglfs .hglfs_
   $ echo 'largefile3' > lfs.test
   $ echo '012345678901234567890abc' > nolfs.exclude
   $ echo '01234567890123456abc' > lfs.catchall
   $ hg ci -qm 'file test' -X .hglfs
   $ hg log -r . -T '{rev}: {lfs_files % "{file}: {lfsoid}\n"}\n'
   4: 
 
   $ mv .hglfs_ .hglfs
   $ echo '012345678901234567890abc' > lfs.test
   $ hg ci -m 'back to lfs'
   $ hg rm lfs.test
   $ hg ci -qm 'remove lfs'
 
 {lfs_files} will list deleted files too
 
   $ hg log -T "{lfs_files % '{rev} {file}: {lfspointer.oid}\n'}"
   6 lfs.test: 
   5 lfs.test: sha256:43f8f41171b6f62a6b61ba4ce98a8a6c1649240a47ebafd43120aa215ac9e7f6
   3 lfs.catchall: sha256:31f43b9c62b540126b0ad5884dc013d21a61c9329b77de1fceeae2fc58511573
   3 lfs.test: sha256:8acd23467967bc7b8cc5a280056589b0ba0b17ff21dbd88a7b6474d6290378a6
   2 lfs.catchall: sha256:d4ec46c2869ba22eceb42a729377432052d9dd75d82fc40390ebaadecee87ee9
   2 lfs.test: sha256:5489e6ced8c36a7b267292bde9fd5242a5f80a7482e8f23fa0477393dfaa4d6c
 
   $ hg log -r 'file("set:lfs()")' -T '{rev} {join(lfs_files, ", ")}\n'
   2 lfs.catchall, lfs.test
   3 lfs.catchall, lfs.test
   5 lfs.test
   6 lfs.test
 
   $ cd ..
 
 Unbundling adds a requirement to a non-lfs repo, if necessary.
 
   $ hg bundle -R $TESTTMP/repo-del -qr 0 --base null nolfs.hg
   $ hg bundle -R convert_lfs2 -qr tip --base null lfs.hg
   $ hg init unbundle
   $ hg pull -R unbundle -q nolfs.hg
   $ grep lfs unbundle/.hg/requires
   [1]
   $ hg pull -R unbundle -q lfs.hg
   $ grep lfs unbundle/.hg/requires
   lfs
 
   $ hg init no_lfs
   $ cat >> no_lfs/.hg/hgrc <<EOF
   > [experimental]
   > changegroup3 = True
   > [extensions]
   > lfs=!
   > EOF
   $ cp -R no_lfs no_lfs2
 
 Pushing from a local lfs repo to a local repo without an lfs requirement and
 with lfs disabled, fails.
 
   $ hg push -R convert_lfs2 no_lfs
   pushing to no_lfs
   abort: required features are not supported in the destination: lfs
   [255]
   $ grep lfs no_lfs/.hg/requires
   [1]
 
 Pulling from a local lfs repo to a local repo without an lfs requirement and
 with lfs disabled, fails.
 
   $ hg pull -R no_lfs2 convert_lfs2
   pulling from convert_lfs2
   abort: required features are not supported in the destination: lfs
   [255]
   $ grep lfs no_lfs2/.hg/requires
   [1]