typing: lock in new pytype gains from making revlog related classes typeable

These were pretty clean changes in the pyi files from earlier in this series, so
add them to the code to make it more understandable.

There's one more trivial hint that can be added to the return of
`mercurial.revlogutils.rewrite._filelog_from_filename()`, however it needs to be
imported from '..' under the conditional of `typing.TYPE_CHECKING`, and that
seems to confuse the import checker- possibly because there's already an import
block from that level.  (I would have expected a message about multiple import
statements in this case, but got one about higher level imports should come
first, no matter where I put the import statement.)

hgext/remotefilelog/debugcommands.py

@@ -1,480 +1,480 b''
 # debugcommands.py - debug logic for remotefilelog
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os
 import zlib
 
 from mercurial.node import (
     bin,
     hex,
     sha1nodeconstants,
     short,
 )
 from mercurial.i18n import _
 from mercurial.pycompat import open
 from mercurial import (
     error,
     filelog,
     lock as lockmod,
     pycompat,
     revlog,
 )
 from mercurial.utils import hashutil
 from . import (
     constants,
     datapack,
     fileserverclient,
     historypack,
     repack,
     shallowutil,
 )
 
 
 def debugremotefilelog(ui, path, **opts) -> None:
     decompress = opts.get('decompress')
 
     size, firstnode, mapping = parsefileblob(path, decompress)
 
     ui.status(_(b"size: %d bytes\n") % size)
     ui.status(_(b"path: %s \n") % path)
     ui.status(_(b"key: %s \n") % (short(firstnode)))
     ui.status(_(b"\n"))
     ui.status(
         _(b"%12s => %12s %13s %13s %12s\n")
         % (b"node", b"p1", b"p2", b"linknode", b"copyfrom")
     )
 
     queue = [firstnode]
     while queue:
         node = queue.pop(0)
         p1, p2, linknode, copyfrom = mapping[node]
         ui.status(
             _(b"%s => %s  %s  %s  %s\n")
             % (short(node), short(p1), short(p2), short(linknode), copyfrom)
         )
         if p1 != sha1nodeconstants.nullid:
             queue.append(p1)
         if p2 != sha1nodeconstants.nullid:
             queue.append(p2)
 
 
-def buildtemprevlog(repo, file):
+def buildtemprevlog(repo, file) -> filelog.FileLog:
     # get filename key
     filekey = hex(hashutil.sha1(file).digest())
     filedir = os.path.join(repo.path, b'store/data', filekey)
 
     # sort all entries based on linkrev
     fctxs = []
     for filenode in os.listdir(filedir):
         if b'_old' not in filenode:
             fctxs.append(repo.filectx(file, fileid=bin(filenode)))
 
     fctxs = sorted(fctxs, key=lambda x: x.linkrev())
 
     # add to revlog
     temppath = repo.sjoin(b'data/temprevlog.i')
     if os.path.exists(temppath):
         os.remove(temppath)
     r = filelog.filelog(repo.svfs, b'temprevlog')
 
     class faket:
         def add(self, a, b, c):
             pass
 
     t = faket()
     for fctx in fctxs:
         if fctx.node() not in repo:
             continue
 
         p = fctx.filelog().parents(fctx.filenode())
         meta = {}
         if fctx.renamed():
             meta[b'copy'] = fctx.renamed()[0]
             meta[b'copyrev'] = hex(fctx.renamed()[1])
 
         r.add(fctx.data(), meta, t, fctx.linkrev(), p[0], p[1])
 
     return r
 
 
 def debugindex(orig, ui, repo, file_=None, **opts):
     """dump the contents of an index file"""
     if (
         opts.get('changelog')
         or opts.get('manifest')
         or opts.get('dir')
         or not shallowutil.isenabled(repo)
         or not repo.shallowmatch(file_)
     ):
         return orig(ui, repo, file_, **opts)
 
     r = buildtemprevlog(repo, file_)
 
     # debugindex like normal
     format = opts.get('format', 0)
     if format not in (0, 1):
         raise error.Abort(_(b"unknown format %d") % format)
 
     generaldelta = r.get_revlog()._format_flags & revlog.FLAG_GENERALDELTA
     if generaldelta:
         basehdr = b' delta'
     else:
         basehdr = b'  base'
 
     if format == 0:
         ui.write(
             (
                 b"   rev    offset  length " + basehdr + b" linkrev"
                 b" nodeid       p1           p2\n"
             )
         )
     elif format == 1:
         ui.write(
             (
                 b"   rev flag   offset   length"
                 b"     size " + basehdr + b"   link     p1     p2"
                 b"       nodeid\n"
             )
         )
 
     for i in r:
         node = r.node(i)
         if generaldelta:
             base = r.get_revlog().deltaparent(i)
         else:
             base = r.get_revlog().chainbase(i)
         if format == 0:
             try:
                 pp = r.parents(node)
             except Exception:
                 pp = [repo.nullid, repo.nullid]
             ui.write(
                 b"% 6d % 9d % 7d % 6d % 7d %s %s %s\n"
                 % (
                     i,
                     r.get_revlog().start(i),
                     r.get_revlog().length(i),
                     base,
                     r.linkrev(i),
                     short(node),
                     short(pp[0]),
                     short(pp[1]),
                 )
             )
         elif format == 1:
             pr = r.parentrevs(i)
             ui.write(
                 b"% 6d %04x % 8d % 8d % 8d % 6d % 6d % 6d % 6d %s\n"
                 % (
                     i,
                     r.get_revlog().flags(i),
                     r.get_revlog().start(i),
                     r.get_revlog().length(i),
                     r.get_revlog().rawsize(i),
                     base,
                     r.linkrev(i),
                     pr[0],
                     pr[1],
                     short(node),
                 )
             )
 
 
 def debugindexdot(orig, ui, repo, file_):
     """dump an index DAG as a graphviz dot file"""
     if not shallowutil.isenabled(repo):
         return orig(ui, repo, file_)
 
     r = buildtemprevlog(repo, os.path.basename(file_)[:-2])
 
     ui.writenoi18n(b"digraph G {\n")
     for i in r:
         node = r.node(i)
         pp = r.parents(node)
         ui.write(b"\t%d -> %d\n" % (r.rev(pp[0]), i))
         if pp[1] != repo.nullid:
             ui.write(b"\t%d -> %d\n" % (r.rev(pp[1]), i))
     ui.write(b"}\n")
 
 
 def verifyremotefilelog(ui, path, **opts):
     decompress = opts.get('decompress')
 
     for root, dirs, files in os.walk(path):
         for file in files:
             if file == b"repos":
                 continue
             filepath = os.path.join(root, file)
             size, firstnode, mapping = parsefileblob(filepath, decompress)
             for p1, p2, linknode, copyfrom in mapping.values():
                 if linknode == sha1nodeconstants.nullid:
                     actualpath = os.path.relpath(root, path)
                     key = fileserverclient.getcachekey(
                         b"reponame", actualpath, file
                     )
                     ui.status(
                         b"%s %s\n" % (key, os.path.relpath(filepath, path))
                     )
 
 
 def _decompressblob(raw):
     return zlib.decompress(raw)
 
 
 def parsefileblob(path, decompress):
     f = open(path, b"rb")
     try:
         raw = f.read()
     finally:
         f.close()
 
     if decompress:
         raw = _decompressblob(raw)
 
     offset, size, flags = shallowutil.parsesizeflags(raw)
     start = offset + size
 
     firstnode = None
 
     mapping = {}
     while start < len(raw):
         divider = raw.index(b'\0', start + 80)
 
         currentnode = raw[start : (start + 20)]
         if not firstnode:
             firstnode = currentnode
 
         p1 = raw[(start + 20) : (start + 40)]
         p2 = raw[(start + 40) : (start + 60)]
         linknode = raw[(start + 60) : (start + 80)]
         copyfrom = raw[(start + 80) : divider]
 
         mapping[currentnode] = (p1, p2, linknode, copyfrom)
         start = divider + 1
 
     return size, firstnode, mapping
 
 
 def debugdatapack(ui, *paths, **opts):
     for path in paths:
         if b'.data' in path:
             path = path[: path.index(b'.data')]
         ui.write(b"%s:\n" % path)
         dpack = datapack.datapack(path)
         node = opts.get('node')
         if node:
             deltachain = dpack.getdeltachain(b'', bin(node))
             dumpdeltachain(ui, deltachain, **opts)
             return
 
         if opts.get('long'):
             hashformatter = hex
             hashlen = 42
         else:
             hashformatter = short
             hashlen = 14
 
         lastfilename = None
         totaldeltasize = 0
         totalblobsize = 0
 
         def printtotals():
             if lastfilename is not None:
                 ui.write(b"\n")
             if not totaldeltasize or not totalblobsize:
                 return
             difference = totalblobsize - totaldeltasize
             deltastr = b"%0.1f%% %s" % (
                 (100.0 * abs(difference) / totalblobsize),
                 (b"smaller" if difference > 0 else b"bigger"),
             )
 
             ui.writenoi18n(
                 b"Total:%s%s  %s (%s)\n"
                 % (
                     b"".ljust(2 * hashlen - len(b"Total:")),
                     (b'%d' % totaldeltasize).ljust(12),
                     (b'%d' % totalblobsize).ljust(9),
                     deltastr,
                 )
             )
 
         bases = {}
         nodes = set()
         failures = 0
         for filename, node, deltabase, deltalen in dpack.iterentries():
             bases[node] = deltabase
             if node in nodes:
                 ui.write((b"Bad entry: %s appears twice\n" % short(node)))
                 failures += 1
             nodes.add(node)
             if filename != lastfilename:
                 printtotals()
                 name = b'(empty name)' if filename == b'' else filename
                 ui.write(b"%s:\n" % name)
                 ui.write(
                     b"%s%s%s%s\n"
                     % (
                         b"Node".ljust(hashlen),
                         b"Delta Base".ljust(hashlen),
                         b"Delta Length".ljust(14),
                         b"Blob Size".ljust(9),
                     )
                 )
                 lastfilename = filename
                 totalblobsize = 0
                 totaldeltasize = 0
 
             # Metadata could be missing, in which case it will be an empty dict.
             meta = dpack.getmeta(filename, node)
             if constants.METAKEYSIZE in meta:
                 blobsize = meta[constants.METAKEYSIZE]
                 totaldeltasize += deltalen
                 totalblobsize += blobsize
             else:
                 blobsize = b"(missing)"
             ui.write(
                 b"%s  %s  %s%s\n"
                 % (
                     hashformatter(node),
                     hashformatter(deltabase),
                     (b'%d' % deltalen).ljust(14),
                     pycompat.bytestr(blobsize),
                 )
             )
 
         if filename is not None:
             printtotals()
 
         failures += _sanitycheck(ui, set(nodes), bases)
         if failures > 1:
             ui.warn((b"%d failures\n" % failures))
             return 1
 
 
 def _sanitycheck(ui, nodes, bases):
     """
     Does some basic sanity checking on a packfiles with ``nodes`` ``bases`` (a
     mapping of node->base):
 
     - Each deltabase must itself be a node elsewhere in the pack
     - There must be no cycles
     """
     failures = 0
     for node in nodes:
         seen = set()
         current = node
         deltabase = bases[current]
 
         while deltabase != sha1nodeconstants.nullid:
             if deltabase not in nodes:
                 ui.warn(
                     (
                         b"Bad entry: %s has an unknown deltabase (%s)\n"
                         % (short(node), short(deltabase))
                     )
                 )
                 failures += 1
                 break
 
             if deltabase in seen:
                 ui.warn(
                     (
                         b"Bad entry: %s has a cycle (at %s)\n"
                         % (short(node), short(deltabase))
                     )
                 )
                 failures += 1
                 break
 
             current = deltabase
             seen.add(current)
             deltabase = bases[current]
         # Since ``node`` begins a valid chain, reset/memoize its base to nullid
         # so we don't traverse it again.
         bases[node] = sha1nodeconstants.nullid
     return failures
 
 
 def dumpdeltachain(ui, deltachain, **opts):
     hashformatter = hex
     hashlen = 40
 
     lastfilename = None
     for filename, node, filename, deltabasenode, delta in deltachain:
         if filename != lastfilename:
             ui.write(b"\n%s\n" % filename)
             lastfilename = filename
         ui.write(
             b"%s  %s  %s  %s\n"
             % (
                 b"Node".ljust(hashlen),
                 b"Delta Base".ljust(hashlen),
                 b"Delta SHA1".ljust(hashlen),
                 b"Delta Length".ljust(6),
             )
         )
 
         ui.write(
             b"%s  %s  %s  %d\n"
             % (
                 hashformatter(node),
                 hashformatter(deltabasenode),
                 hex(hashutil.sha1(delta).digest()),
                 len(delta),
             )
         )
 
 
 def debughistorypack(ui, path):
     if b'.hist' in path:
         path = path[: path.index(b'.hist')]
     hpack = historypack.historypack(path)
 
     lastfilename = None
     for entry in hpack.iterentries():
         filename, node, p1node, p2node, linknode, copyfrom = entry
         if filename != lastfilename:
             ui.write(b"\n%s\n" % filename)
             ui.write(
                 b"%s%s%s%s%s\n"
                 % (
                     b"Node".ljust(14),
                     b"P1 Node".ljust(14),
                     b"P2 Node".ljust(14),
                     b"Link Node".ljust(14),
                     b"Copy From",
                 )
             )
             lastfilename = filename
         ui.write(
             b"%s  %s  %s  %s  %s\n"
             % (
                 short(node),
                 short(p1node),
                 short(p2node),
                 short(linknode),
                 copyfrom,
             )
         )
 
 
 def debugwaitonrepack(repo):
     with lockmod.lock(repack.repacklockvfs(repo), b"repacklock", timeout=-1):
         return
 
 
 def debugwaitonprefetch(repo):
     with repo._lock(
         repo.svfs,
         b"prefetchlock",
         True,
         None,
         None,
         _(b'prefetching in %s') % repo.origroot,
     ):
         pass

hgext/remotefilelog/remotefilelog.py

@@ -1,472 +1,476 b''
 # remotefilelog.py - filelog implementation where filelog history is stored
 #                    remotely
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import collections
 
+from typing import (
+    Iterator,
+)
+
 from mercurial.node import bin
 from mercurial.i18n import _
 from mercurial import (
     ancestor,
     error,
     mdiff,
     revlog,
 )
 from mercurial.utils import storageutil
 from mercurial.revlogutils import flagutil
 
 from . import (
     constants,
     shallowutil,
 )
 
 
 class remotefilelognodemap:
     def __init__(self, filename, store):
         self._filename = filename
         self._store = store
 
     def __contains__(self, node):
         missing = self._store.getmissing([(self._filename, node)])
         return not bool(missing)
 
     def __get__(self, node):
         if node not in self:
             raise KeyError(node)
         return node
 
 
 class remotefilelog:
     _flagserrorclass = error.RevlogError
 
     def __init__(self, opener, path, repo):
         self.opener = opener
         self.filename = path
         self.repo = repo
         self.nodemap = remotefilelognodemap(self.filename, repo.contentstore)
 
         self.version = 1
 
         self._flagprocessors = dict(flagutil.flagprocessors)
 
     def read(self, node):
         """returns the file contents at this node"""
         t = self.revision(node)
         if not t.startswith(b'\1\n'):
             return t
         s = t.index(b'\1\n', 2)
         return t[s + 2 :]
 
     def add(self, text, meta, transaction, linknode, p1=None, p2=None):
         # hash with the metadata, like in vanilla filelogs
         hashtext = shallowutil.createrevlogtext(
             text, meta.get(b'copy'), meta.get(b'copyrev')
         )
         node = storageutil.hashrevisionsha1(hashtext, p1, p2)
         return self.addrevision(
             hashtext, transaction, linknode, p1, p2, node=node
         )
 
     def _createfileblob(self, text, meta, flags, p1, p2, node, linknode):
         # text passed to "_createfileblob" does not include filelog metadata
         header = shallowutil.buildfileblobheader(len(text), flags)
         data = b"%s\0%s" % (header, text)
 
         realp1 = p1
         copyfrom = b""
         if meta and b'copy' in meta:
             copyfrom = meta[b'copy']
             realp1 = bin(meta[b'copyrev'])
 
         data += b"%s%s%s%s%s\0" % (node, realp1, p2, linknode, copyfrom)
 
         visited = set()
 
         pancestors = {}
         queue = []
         if realp1 != self.repo.nullid:
             p1flog = self
             if copyfrom:
                 p1flog = remotefilelog(self.opener, copyfrom, self.repo)
 
             pancestors.update(p1flog.ancestormap(realp1))
             queue.append(realp1)
             visited.add(realp1)
         if p2 != self.repo.nullid:
             pancestors.update(self.ancestormap(p2))
             queue.append(p2)
             visited.add(p2)
 
         ancestortext = b""
 
         # add the ancestors in topological order
         while queue:
             c = queue.pop(0)
             pa1, pa2, ancestorlinknode, pacopyfrom = pancestors[c]
 
             pacopyfrom = pacopyfrom or b''
             ancestortext += b"%s%s%s%s%s\0" % (
                 c,
                 pa1,
                 pa2,
                 ancestorlinknode,
                 pacopyfrom,
             )
 
             if pa1 != self.repo.nullid and pa1 not in visited:
                 queue.append(pa1)
                 visited.add(pa1)
             if pa2 != self.repo.nullid and pa2 not in visited:
                 queue.append(pa2)
                 visited.add(pa2)
 
         data += ancestortext
 
         return data
 
     def addrevision(
         self,
         text,
         transaction,
         linknode,
         p1,
         p2,
         cachedelta=None,
         node=None,
         flags=revlog.REVIDX_DEFAULT_FLAGS,
         sidedata=None,
     ):
         # text passed to "addrevision" includes hg filelog metadata header
         if node is None:
             node = storageutil.hashrevisionsha1(text, p1, p2)
 
         meta, metaoffset = storageutil.parsemeta(text)
         rawtext, validatehash = flagutil.processflagswrite(
             self,
             text,
             flags,
         )
         return self.addrawrevision(
             rawtext,
             transaction,
             linknode,
             p1,
             p2,
             node,
             flags,
             cachedelta,
             _metatuple=(meta, metaoffset),
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         linknode,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         _metatuple=None,
     ):
         if _metatuple:
             # _metatuple: used by "addrevision" internally by remotefilelog
             # meta was parsed confidently
             meta, metaoffset = _metatuple
         else:
             # not from self.addrevision, but something else (repo._filecommit)
             # calls addrawrevision directly. remotefilelog needs to get and
             # strip filelog metadata.
             # we don't have confidence about whether rawtext contains filelog
             # metadata or not (flag processor could replace it), so we just
             # parse it as best-effort.
             # in LFS (flags != 0)'s case, the best way is to call LFS code to
             # get the meta information, instead of storageutil.parsemeta.
             meta, metaoffset = storageutil.parsemeta(rawtext)
         if flags != 0:
             # when flags != 0, be conservative and do not mangle rawtext, since
             # a read flag processor expects the text not being mangled at all.
             metaoffset = 0
         if metaoffset:
             # remotefilelog fileblob stores copy metadata in its ancestortext,
             # not its main blob. so we need to remove filelog metadata
             # (containing copy information) from text.
             blobtext = rawtext[metaoffset:]
         else:
             blobtext = rawtext
         data = self._createfileblob(
             blobtext, meta, flags, p1, p2, node, linknode
         )
         self.repo.contentstore.addremotefilelognode(self.filename, node, data)
 
         return node
 
     def renamed(self, node):
         ancestors = self.repo.metadatastore.getancestors(self.filename, node)
         p1, p2, linknode, copyfrom = ancestors[node]
         if copyfrom:
             return (copyfrom, p1)
 
         return False
 
     def size(self, node):
         """return the size of a given revision"""
         return len(self.read(node))
 
     rawsize = size
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
 
         if node == self.repo.nullid:
             return True
 
         nodetext = self.read(node)
         return nodetext != text
 
     def __nonzero__(self):
         return True
 
     __bool__ = __nonzero__
 
     def __len__(self):
         if self.filename in (b'.hgtags', b'.hgsub', b'.hgsubstate'):
             # Global tag and subrepository support require access to the
             # file history for various performance sensitive operations.
             # excludepattern should be used for repositories depending on
             # those features to fallback to regular filelog.
             return 0
 
         raise RuntimeError(b"len not supported")
 
     def heads(self):
         # Fake heads of the filelog to satisfy hgweb.
         return []
 
     def empty(self):
         return False
 
     def flags(self, node):
         if isinstance(node, int):
             raise error.ProgrammingError(
                 b'remotefilelog does not accept integer rev for flags'
             )
         store = self.repo.contentstore
         return store.getmeta(self.filename, node).get(constants.METAKEYFLAG, 0)
 
     def parents(self, node):
         if node == self.repo.nullid:
             return self.repo.nullid, self.repo.nullid
 
         ancestormap = self.repo.metadatastore.getancestors(self.filename, node)
         p1, p2, linknode, copyfrom = ancestormap[node]
         if copyfrom:
             p1 = self.repo.nullid
 
         return p1, p2
 
     def parentrevs(self, rev):
         # TODO(augie): this is a node and should be a rev, but for now
         # nothing in core seems to actually break.
         return self.parents(rev)
 
     def linknode(self, node):
         ancestormap = self.repo.metadatastore.getancestors(self.filename, node)
         p1, p2, linknode, copyfrom = ancestormap[node]
         return linknode
 
     def linkrev(self, node):
         return self.repo.unfiltered().changelog.rev(self.linknode(node))
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltaprevious=False,
         deltamode=None,
         sidedata_helpers=None,
         debug_info=None,
-    ):
+    ) -> Iterator[revlog.RevLogRevisionDelta]:
         # we don't use any of these parameters here
         del nodesorder, revisiondata, assumehaveparentrevisions, deltaprevious
         del deltamode
         prevnode = None
         for node in nodes:
             p1, p2 = self.parents(node)
             if prevnode is None:
                 basenode = prevnode = p1
             if basenode == node:
                 basenode = self.repo.nullid
             if basenode != self.repo.nullid:
                 revision = None
                 delta = self.revdiff(basenode, node)
             else:
                 revision = self.rawdata(node)
                 delta = None
             yield revlog.revlogrevisiondelta(
                 node=node,
                 p1node=p1,
                 p2node=p2,
                 linknode=self.linknode(node),
                 basenode=basenode,
                 flags=self.flags(node),
                 baserevisionsize=None,
                 revision=revision,
                 delta=delta,
                 # Sidedata is not supported yet
                 sidedata=None,
                 # Protocol flags are not used yet
                 protocol_flags=0,
             )
 
     def revdiff(self, node1, node2):
         return mdiff.textdiff(self.rawdata(node1), self.rawdata(node2))
 
     def lookup(self, node):
         if len(node) == 40:
             node = bin(node)
         if len(node) != 20:
             raise error.LookupError(
                 node, self.filename, _(b'invalid lookup input')
             )
 
         return node
 
     def rev(self, node):
         # This is a hack to make TortoiseHG work.
         return node
 
     def node(self, rev):
         # This is a hack.
         if isinstance(rev, int):
             raise error.ProgrammingError(
                 b'remotefilelog does not convert integer rev to node'
             )
         return rev
 
     def revision(self, node, raw=False):
         """returns the revlog contents at this node.
         this includes the meta data traditionally included in file revlogs.
         this is generally only used for bundling and communicating with vanilla
         hg clients.
         """
         if node == self.repo.nullid:
             return b""
         if len(node) != 20:
             raise error.LookupError(
                 node, self.filename, _(b'invalid revision input')
             )
         if (
             node == self.repo.nodeconstants.wdirid
             or node in self.repo.nodeconstants.wdirfilenodeids
         ):
             raise error.WdirUnsupported
 
         store = self.repo.contentstore
         rawtext = store.get(self.filename, node)
         if raw:
             return rawtext
         flags = store.getmeta(self.filename, node).get(constants.METAKEYFLAG, 0)
         if flags == 0:
             return rawtext
         return flagutil.processflagsread(self, rawtext, flags)[0]
 
     def rawdata(self, node):
         return self.revision(node, raw=False)
 
     def ancestormap(self, node):
         return self.repo.metadatastore.getancestors(self.filename, node)
 
     def ancestor(self, a, b):
         if a == self.repo.nullid or b == self.repo.nullid:
             return self.repo.nullid
 
         revmap, parentfunc = self._buildrevgraph(a, b)
         nodemap = {v: k for (k, v) in revmap.items()}
 
         ancs = ancestor.ancestors(parentfunc, revmap[a], revmap[b])
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(nodemap.__getitem__, ancs))
         return self.repo.nullid
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
 
         if a == self.repo.nullid or b == self.repo.nullid:
             return self.repo.nullid
 
         revmap, parentfunc = self._buildrevgraph(a, b)
         nodemap = {v: k for (k, v) in revmap.items()}
 
         ancs = ancestor.commonancestorsheads(parentfunc, revmap[a], revmap[b])
         return map(nodemap.__getitem__, ancs)
 
     def _buildrevgraph(self, a, b):
         """Builds a numeric revision graph for the given two nodes.
         Returns a node->rev map and a rev->[revs] parent function.
         """
         amap = self.ancestormap(a)
         bmap = self.ancestormap(b)
 
         # Union the two maps
         parentsmap = collections.defaultdict(list)
         allparents = set()
         for mapping in (amap, bmap):
             for node, pdata in mapping.items():
                 parents = parentsmap[node]
                 p1, p2, linknode, copyfrom = pdata
                 # Don't follow renames (copyfrom).
                 # remotefilectx.ancestor does that.
                 if p1 != self.repo.nullid and not copyfrom:
                     parents.append(p1)
                     allparents.add(p1)
                 if p2 != self.repo.nullid:
                     parents.append(p2)
                     allparents.add(p2)
 
         # Breadth first traversal to build linkrev graph
         parentrevs = collections.defaultdict(list)
         revmap = {}
         queue = collections.deque(
             ((None, n) for n in parentsmap if n not in allparents)
         )
         while queue:
             prevrev, current = queue.pop()
             if current in revmap:
                 if prevrev:
                     parentrevs[prevrev].append(revmap[current])
                 continue
 
             # Assign linkrevs in reverse order, so start at
             # len(parentsmap) and work backwards.
             currentrev = len(parentsmap) - len(revmap) - 1
             revmap[current] = currentrev
 
             if prevrev:
                 parentrevs[prevrev].append(currentrev)
 
             for parent in parentsmap.get(current):
                 queue.appendleft((currentrev, parent))
 
         return revmap, parentrevs.__getitem__
 
     def strip(self, minlink, transaction):
         pass
 
     # misc unused things
     def files(self):
         return []
 
     def checksize(self):
         return 0, 0

mercurial/filelog.py

@@ -1,319 +1,328 b''
 # filelog.py - file history class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import typing
 
+from typing import (
+    Iterable,
+    Iterator,
+)
+
 from .i18n import _
 from .node import nullrev
 from . import (
     error,
     revlog,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .utils import storageutil
 from .revlogutils import (
     constants as revlog_constants,
     rewrite,
 )
 
 
 class FileLog:
+    _revlog: revlog.revlog
+    nullid: bytes
+    _fix_issue6528: bool
+
     def __init__(self, opener, path, try_split=False):
         self._revlog = revlog.revlog(
             opener,
             # XXX should use the unencoded path
             target=(revlog_constants.KIND_FILELOG, path),
             radix=b'/'.join((b'data', path)),
             censorable=True,
             canonical_parent_order=False,  # see comment in revlog.py
             try_split=try_split,
         )
         # Full name of the user visible file, relative to the repository root.
         # Used by LFS.
         self._revlog.filename = path
         self.nullid = self._revlog.nullid
         opts = opener.options
         self._fix_issue6528 = opts.get(b'issue6528.fix-incoming', True)
 
-    def get_revlog(self):
+    def get_revlog(self) -> revlog.revlog:
         """return an actual revlog instance if any
 
         This exist because a lot of code leverage the fact the underlying
         storage is a revlog for optimization, so giving simple way to access
         the revlog instance helps such code.
         """
         return self._revlog
 
-    def __len__(self):
+    def __len__(self) -> int:
         return len(self._revlog)
 
-    def __iter__(self):
+    def __iter__(self) -> Iterator[int]:
         return self._revlog.__iter__()
 
     def hasnode(self, node):
         if node in (self.nullid, nullrev):
             return False
 
         try:
             self._revlog.rev(node)
             return True
         except (TypeError, ValueError, IndexError, error.LookupError):
             return False
 
     def revs(self, start=0, stop=None):
         return self._revlog.revs(start=start, stop=stop)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, node):
         return storageutil.fileidlookup(
             self._revlog, node, self._revlog.display_id
         )
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def commonancestorsheads(self, node1, node2):
         return self._revlog.commonancestorsheads(node1, node2)
 
     # Used by dagop.blockdescendants().
     def descendants(self, revs):
         return self._revlog.descendants(revs)
 
     def heads(self, start=None, stop=None):
         return self._revlog.heads(start, stop)
 
     # Used by hgweb, children extension.
     def children(self, node):
         return self._revlog.children(node)
 
     def iscensored(self, rev):
         return self._revlog.iscensored(rev)
 
     def revision(self, node):
         return self._revlog.revision(node)
 
     def rawdata(self, node):
         return self._revlog.rawdata(node)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
         debug_info=None,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
             sidedata_helpers=sidedata_helpers,
             debug_info=debug_info,
         )
 
     def addrevision(
         self,
         revisiondata,
         transaction,
         linkrev,
         p1,
         p2,
         node=None,
         flags=revlog.REVIDX_DEFAULT_FLAGS,
         cachedelta=None,
     ):
         return self._revlog.addrevision(
             revisiondata,
             transaction,
             linkrev,
             p1,
             p2,
             node=node,
             flags=flags,
             cachedelta=cachedelta,
         )
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         maybemissingparents=False,
         debug_info=None,
         delta_base_reuse_policy=None,
     ):
         if maybemissingparents:
             raise error.Abort(
                 _(
                     b'revlog storage does not support missing '
                     b'parents write mode'
                 )
             )
 
         with self._revlog._writing(transaction):
             if self._fix_issue6528:
                 deltas = rewrite.filter_delta_issue6528(self._revlog, deltas)
 
             return self._revlog.addgroup(
                 deltas,
                 linkmapper,
                 transaction,
                 addrevisioncb=addrevisioncb,
                 duplicaterevisioncb=duplicaterevisioncb,
                 debug_info=debug_info,
                 delta_base_reuse_policy=delta_base_reuse_policy,
             )
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def censorrevision(self, tr, node, tombstone=b''):
         return self._revlog.censorrevision(tr, node, tombstone=tombstone)
 
     def files(self):
         return self._revlog.files()
 
     def read(self, node):
         return storageutil.filtermetadata(self.revision(node))
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith(b'\1\n'):
             text = storageutil.packmeta(meta, text)
         rev = self.addrevision(text, transaction, link, p1, p2)
         return self.node(rev)
 
     def renamed(self, node):
         return storageutil.filerevisioncopied(self, node)
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.iscensored(rev):
             return 0
         if self.renamed(node):
             return len(self.read(node))
 
         # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
         # XXX See also basefilectx.cmp.
         return self._revlog.size(rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         return not storageutil.filedataequivalent(self, node, text)
 
-    def verifyintegrity(self, state):
+    def verifyintegrity(self, state) -> Iterable[revlog.RevLogProblem]:
         return self._revlog.verifyintegrity(state)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     # Used by repo upgrade.
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, filelog):
             msg = b'expected filelog to clone(), not %r'
             msg %= destrevlog
             raise error.ProgrammingError(msg)
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
 
 filelog = interfaceutil.implementer(repository.ifilestorage)(FileLog)
 
 if typing.TYPE_CHECKING:
     filelog = FileLog
 
 
 class narrowfilelog(filelog):
     """Filelog variation to be used with narrow stores."""
 
     def __init__(self, opener, path, narrowmatch, try_split=False):
         super(narrowfilelog, self).__init__(opener, path, try_split=try_split)
         self._narrowmatch = narrowmatch
 
     def renamed(self, node):
         res = super(narrowfilelog, self).renamed(node)
 
         # Renames that come from outside the narrowspec are problematic
         # because we may lack the base text for the rename. This can result
         # in code attempting to walk the ancestry or compute a diff
         # encountering a missing revision. We address this by silently
         # removing rename metadata if the source file is outside the
         # narrow spec.
         #
         # A better solution would be to see if the base revision is available,
         # rather than assuming it isn't.
         #
         # An even better solution would be to teach all consumers of rename
         # metadata that the base revision may not be available.
         #
         # TODO consider better ways of doing this.
         if res and not self._narrowmatch(res[0]):
             return None
 
         return res
 
     def size(self, rev):
         # Because we have a custom renamed() that may lie, we need to call
         # the base renamed() to report accurate results.
         node = self.node(rev)
         if super(narrowfilelog, self).renamed(node):
             return len(self.read(node))
         else:
             return super(narrowfilelog, self).size(rev)
 
     def cmp(self, node, text):
         # We don't call `super` because narrow parents can be buggy in case of a
         # ambiguous dirstate. Always take the slow path until there is a better
         # fix, see issue6150.
 
         # Censored files compare against the empty file.
         if self.iscensored(self.rev(node)):
             return text != b''
 
         return self.read(node) != text

mercurial/manifest.py

@@ -1,2780 +1,2797 b''
 # manifest.py - manifest revision class for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import heapq
 import itertools
 import struct
 import typing
 import weakref
 
 from typing import (
     ByteString,
     Callable,
     Collection,
     Dict,
     Iterable,
     Iterator,
     List,
     Optional,
     Set,
     Tuple,
     Union,
     cast,
 )
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullrev,
 )
 from . import (
     encoding,
     error,
     match as matchmod,
     mdiff,
     pathutil,
     policy,
     pycompat,
     revlog,
     util,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     constants as revlog_constants,
 )
 
 parsers = policy.importmod('parsers')
 propertycache = util.propertycache
 
 # Allow tests to more easily test the alternate path in manifestdict.fastdelta()
 FASTDELTA_TEXTDIFF_THRESHOLD = 1000
 
 
 def _parse(nodelen, data: bytes):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
     # class exactly matches its C counterpart to try and help
     # prevent surprise breakage for anyone that develops against
     # the pure version.
     if data and data[-1:] != b'\n':
         raise ValueError(b'Manifest did not end in a newline.')
     prev = None
     for l in data.splitlines():
         if prev is not None and prev > l:
             raise ValueError(b'Manifest lines not in sorted order.')
         prev = l
         f, n = l.split(b'\0')
         nl = len(n)
         flags = n[-1:]
         if flags in _manifestflags:
             n = n[:-1]
             nl -= 1
         else:
             flags = b''
         if nl != 2 * nodelen:
             raise ValueError(b'Invalid manifest line')
 
         yield f, bin(n), flags
 
 
 def _text(it):
     files = []
     lines = []
     for f, n, fl in it:
         files.append(f)
         # if this is changed to support newlines in filenames,
         # be sure to check the templates/ dir again (especially *-raw.tmpl)
         lines.append(b"%s\0%s%s\n" % (f, hex(n), fl))
 
     _checkforbidden(files)
     return b''.join(lines)
 
 
 class lazymanifestiter:
     def __init__(self, lm: '_LazyManifest') -> None:
         self.pos = 0
         self.lm = lm
 
     def __iter__(self) -> 'lazymanifestiter':
         return self
 
     def next(self) -> bytes:
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             assert isinstance(data, tuple)
             self.pos += 1
             return data[0]
         assert isinstance(data, bytes)
         self.pos += 1
         zeropos = data.find(b'\x00', pos)
         return data[pos:zeropos]
 
     __next__ = next
 
 
 class lazymanifestiterentries:
     def __init__(self, lm: '_LazyManifest') -> None:
         self.lm = lm
         self.pos = 0
 
     def __iter__(self) -> 'lazymanifestiterentries':
         return self
 
     def next(self) -> Tuple[bytes, bytes, bytes]:
         try:
             data, pos = self.lm._get(self.pos)
         except IndexError:
             raise StopIteration
         if pos == -1:
             assert isinstance(data, tuple)
             self.pos += 1
             return data
         assert isinstance(data, bytes)
         zeropos = data.find(b'\x00', pos)
         nlpos = data.find(b'\n', pos)
         if zeropos == -1 or nlpos == -1 or nlpos < zeropos:
             raise error.StorageError(b'Invalid manifest line')
         flags = data[nlpos - 1 : nlpos]
         if flags in _manifestflags:
             hlen = nlpos - zeropos - 2
         else:
             hlen = nlpos - zeropos - 1
             flags = b''
         if hlen != 2 * self.lm._nodelen:
             raise error.StorageError(b'Invalid manifest line')
         hashval = unhexlify(
             data, self.lm.extrainfo[self.pos], zeropos + 1, hlen
         )
         self.pos += 1
         return (data[pos:zeropos], hashval, flags)
 
     __next__ = next
 
 
 def unhexlify(data: bytes, extra: int, pos, length: int):
     s = bin(data[pos : pos + length])
     if extra:
         s += bytes([extra & 0xFF])
     return s
 
 
 def _cmp(a, b):
     return (a > b) - (a < b)
 
 
 _manifestflags = {b'', b'l', b't', b'x'}
 
 
 class _LazyManifest:
     """A pure python manifest backed by a byte string.  It is supplimented with
     internal lists as it is modified, until it is compacted back to a pure byte
     string.
 
     ``data`` is the initial manifest data.
 
     ``positions`` is a list of offsets, one per manifest entry.  Positive
     values are offsets into ``data``, negative values are offsets into the
     ``extradata`` list.  When an entry is removed, its entry is dropped from
     ``positions``.  The values are encoded such that when walking the list and
     indexing into ``data`` or ``extradata`` as appropriate, the entries are
     sorted by filename.
 
     ``extradata`` is a list of (key, hash, flags) for entries that were added or
     modified since the manifest was created or compacted.
     """
 
     def __init__(
         self,
         nodelen: int,
         data: bytes,
         positions=None,
         extrainfo=None,
         extradata=None,
         hasremovals: bool = False,
     ):
         self._nodelen = nodelen
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
             self.hasremovals = False
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
             self.hasremovals = hasremovals
 
     def findlines(self, data: bytes) -> List[int]:
         if not data:
             return []
         pos = data.find(b"\n")
         if pos == -1 or data[-1:] != b'\n':
             raise ValueError(b"Manifest did not end in a newline.")
         positions = [0]
         prev = data[: data.find(b'\x00')]
         while pos < len(data) - 1 and pos != -1:
             positions.append(pos + 1)
             nexts = data[pos + 1 : data.find(b'\x00', pos + 1)]
             if nexts < prev:
                 raise ValueError(b"Manifest lines not in sorted order.")
             prev = nexts
             pos = data.find(b"\n", pos + 1)
         return positions
 
     def _get(
         self, index: int
     ) -> Tuple[Union[bytes, Tuple[bytes, bytes, bytes]], int]:
         # get the position encoded in pos:
         #   positive number is an index in 'data'
         #   negative number is in extrapieces
         pos = self.positions[index]
         if pos >= 0:
             return self.data, pos
         return self.extradata[-pos - 1], -1
 
     def _getkey(self, pos) -> bytes:
         if pos >= 0:
             return self.data[pos : self.data.find(b'\x00', pos + 1)]
         return self.extradata[-pos - 1][0]
 
     def bsearch(self, key: bytes) -> int:
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return midpoint
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return -1
 
     def bsearch2(self, key: bytes) -> Tuple[int, bool]:
         # same as the above, but will always return the position
         # done for performance reasons
         first = 0
         last = len(self.positions) - 1
 
         while first <= last:
             midpoint = (first + last) // 2
             nextpos = self.positions[midpoint]
             candidate = self._getkey(nextpos)
             r = _cmp(key, candidate)
             if r == 0:
                 return (midpoint, True)
             else:
                 if r < 0:
                     last = midpoint - 1
                 else:
                     first = midpoint + 1
         return (first, False)
 
     def __contains__(self, key: bytes) -> bool:
         return self.bsearch(key) != -1
 
     def __getitem__(self, key: bytes) -> Tuple[bytes, bytes]:
         if not isinstance(key, bytes):
             raise TypeError(b"getitem: manifest keys must be a bytes.")
         needle = self.bsearch(key)
         if needle == -1:
             raise KeyError
         data, pos = self._get(needle)
         if pos == -1:
             assert isinstance(data, tuple)
             return (data[1], data[2])
 
         assert isinstance(data, bytes)
         zeropos = data.find(b'\x00', pos)
         nlpos = data.find(b'\n', zeropos)
         assert 0 <= needle <= len(self.positions)
         assert len(self.extrainfo) == len(self.positions)
         if zeropos == -1 or nlpos == -1 or nlpos < zeropos:
             raise error.StorageError(b'Invalid manifest line')
         hlen = nlpos - zeropos - 1
         flags = data[nlpos - 1 : nlpos]
         if flags in _manifestflags:
             hlen -= 1
         else:
             flags = b''
         if hlen != 2 * self._nodelen:
             raise error.StorageError(b'Invalid manifest line')
         hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, hlen)
         return (hashval, flags)
 
     def __delitem__(self, key: bytes) -> None:
         needle, found = self.bsearch2(key)
         if not found:
             raise KeyError
         cur = self.positions[needle]
         self.positions = self.positions[:needle] + self.positions[needle + 1 :]
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1 :]
         if cur >= 0:
             # This does NOT unsort the list as far as the search functions are
             # concerned, as they only examine lines mapped by self.positions.
             self.data = self.data[:cur] + b'\x00' + self.data[cur + 1 :]
             self.hasremovals = True
 
     def __setitem__(self, key: bytes, value: Tuple[bytes, bytes]):
         if not isinstance(key, bytes):
             raise TypeError(b"setitem: manifest keys must be a byte string.")
         if not isinstance(value, tuple) or len(value) != 2:
             raise TypeError(
                 b"Manifest values must be a tuple of (node, flags)."
             )
         hashval = value[0]
         if not isinstance(hashval, bytes) or len(hashval) not in (20, 32):
             raise TypeError(b"node must be a 20-byte or 32-byte byte string")
         flags = value[1]
         if not isinstance(flags, bytes) or len(flags) > 1:
             raise TypeError(b"flags must a 0 or 1 byte string, got %r", flags)
         needle, found = self.bsearch2(key)
         if found:
             # put the item
             pos = self.positions[needle]
             if pos < 0:
                 self.extradata[-pos - 1] = (key, hashval, value[1])
             else:
                 # just don't bother
                 self.extradata.append((key, hashval, value[1]))
                 self.positions[needle] = -len(self.extradata)
         else:
             # not found, put it in with extra positions
             self.extradata.append((key, hashval, value[1]))
             self.positions = (
                 self.positions[:needle]
                 + [-len(self.extradata)]
                 + self.positions[needle:]
             )
             self.extrainfo = (
                 self.extrainfo[:needle] + [0] + self.extrainfo[needle:]
             )
 
     def copy(self) -> '_LazyManifest':
         # XXX call _compact like in C?
         return _lazymanifest(
             self._nodelen,
             self.data,
             self.positions,
             self.extrainfo,
             self.extradata,
             self.hasremovals,
         )
 
     def _compact(self) -> None:
         # hopefully not called TOO often
         if len(self.extradata) == 0 and not self.hasremovals:
             return
         l = []
         i = 0
         offset = 0
         self.extrainfo = [0] * len(self.positions)
         while i < len(self.positions):
             if self.positions[i] >= 0:
                 cur = self.positions[i]
                 last_cut = cur
 
                 # Collect all contiguous entries in the buffer at the current
                 # offset, breaking out only for added/modified items held in
                 # extradata, or a deleted line prior to the next position.
                 while True:
                     self.positions[i] = offset
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
 
                     # A removed file has no positions[] entry, but does have an
                     # overwritten first byte.  Break out and find the end of the
                     # current good entry/entries if there is a removed file
                     # before the next position.
                     if (
                         self.hasremovals
                         and self.data.find(b'\n\x00', cur, self.positions[i])
                         != -1
                     ):
                         break
 
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find(b'\n', cur)
                 if end_cut != -1:
                     end_cut += 1
                 offset += end_cut - cur
                 l.append(self.data[last_cut:end_cut])
             else:
                 while i < len(self.positions) and self.positions[i] < 0:
                     cur = self.positions[i]
                     t = self.extradata[-cur - 1]
                     l.append(self._pack(t))
                     self.positions[i] = offset
                     # Hashes are either 20 bytes (old sha1s) or 32
                     # bytes (new non-sha1).
                     hlen = 20
                     if len(t[1]) > 25:
                         hlen = 32
                     if len(t[1]) > hlen:
                         self.extrainfo[i] = ord(t[1][hlen + 1])
                     offset += len(l[-1])
                     i += 1
         self.data = b''.join(l)
         self.hasremovals = False
         self.extradata = []
 
     def _pack(self, d: Tuple[bytes, bytes, bytes]) -> bytes:
         n = d[1]
         assert len(n) in (20, 32)
         return d[0] + b'\x00' + hex(n) + d[2] + b'\n'
 
     def text(self) -> ByteString:
         self._compact()
         return self.data
 
     def diff(
         self, m2: '_LazyManifest', clean: bool = False
     ) -> Dict[
         bytes,
         Optional[
             Tuple[Tuple[Optional[bytes], bytes], Tuple[Optional[bytes], bytes]]
         ],
     ]:
         '''Finds changes between the current manifest and m2.'''
         # XXX think whether efficiency matters here
         diff = {}
 
         for fn, e1, flags in self.iterentries():
             if fn not in m2:
                 diff[fn] = (e1, flags), (None, b'')
             else:
                 e2 = m2[fn]
                 if (e1, flags) != e2:
                     diff[fn] = (e1, flags), e2
                 elif clean:
                     diff[fn] = None
 
         for fn, e2, flags in m2.iterentries():
             if fn not in self:
                 diff[fn] = (None, b''), (e2, flags)
 
         return diff
 
     def iterentries(self) -> lazymanifestiterentries:
         return lazymanifestiterentries(self)
 
     def iterkeys(self) -> lazymanifestiter:
         return lazymanifestiter(self)
 
     def __iter__(self) -> lazymanifestiter:
         return lazymanifestiter(self)
 
     def __len__(self) -> int:
         return len(self.positions)
 
     def filtercopy(self, filterfn: Callable[[bytes], bool]) -> '_LazyManifest':
         # XXX should be optimized
         c = _lazymanifest(self._nodelen, b'')
         for f, n, fl in self.iterentries():
             if filterfn(f):
                 c[f] = n, fl
         return c
 
 
 try:
     _lazymanifest = parsers.lazymanifest
 except AttributeError:
     _lazymanifest = _LazyManifest
 
 
 class ManifestDict:
     def __init__(self, nodelen: int, data: ByteString = b''):
         self._nodelen = nodelen
         self._lm = _lazymanifest(nodelen, data)
 
     def __getitem__(self, key: bytes) -> bytes:
         return self._lm[key][0]
 
     def find(self, key: bytes) -> Tuple[bytes, bytes]:
         return self._lm[key]
 
     def __len__(self) -> int:
         return len(self._lm)
 
     def __nonzero__(self) -> bool:
         # nonzero is covered by the __len__ function, but implementing it here
         # makes it easier for extensions to override.
         return len(self._lm) != 0
 
     __bool__ = __nonzero__
 
     def set(self, key: bytes, node: bytes, flags: bytes) -> None:
         self._lm[key] = node, flags
 
     def __setitem__(self, key: bytes, node: bytes) -> None:
         self._lm[key] = node, self.flags(key)
 
     def __contains__(self, key: bytes) -> bool:
         if key is None:
             return False
         return key in self._lm
 
     def __delitem__(self, key: bytes) -> None:
         del self._lm[key]
 
     def __iter__(self) -> Iterator[bytes]:
         return self._lm.__iter__()
 
     def iterkeys(self) -> Iterator[bytes]:
         return self._lm.iterkeys()
 
     def keys(self) -> List[bytes]:
         return list(self.iterkeys())
 
     def filesnotin(self, m2, match=None) -> Set[bytes]:
         '''Set of files in this manifest that are not in the other'''
         if match is not None:
             match = matchmod.badmatch(match, lambda path, msg: None)
             sm2 = set(m2.walk(match))
             return {f for f in self.walk(match) if f not in sm2}
         return {f for f in self if f not in m2}
 
     @propertycache
     def _dirs(self) -> pathutil.dirs:
         return pathutil.dirs(self)
 
     def dirs(self) -> pathutil.dirs:
         return self._dirs
 
     def hasdir(self, dir: bytes) -> bool:
         return dir in self._dirs
 
     def _filesfastpath(self, match: matchmod.basematcher) -> bool:
         """Checks whether we can correctly and quickly iterate over matcher
         files instead of over manifest files."""
         files = match.files()
         return len(files) < 100 and (
             match.isexact()
             or (match.prefix() and all(fn in self for fn in files))
         )
 
     def walk(self, match: matchmod.basematcher) -> Iterator[bytes]:
         """Generates matching file names.
 
         Equivalent to manifest.matches(match).iterkeys(), but without creating
         an entirely new manifest.
 
         It also reports nonexistent files by marking them bad with match.bad().
         """
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         # avoid the entire walk if we're only looking for specific files
         if self._filesfastpath(match):
             for fn in sorted(fset):
                 if fn in self:
                     yield fn
             return
 
         for fn in self:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _matches(self, match: matchmod.basematcher) -> 'ManifestDict':
         '''generate a new manifest filtered by the match argument'''
         if match.always():
             return self.copy()
 
         if self._filesfastpath(match):
             m = manifestdict(self._nodelen)
             lm = self._lm
             for fn in match.files():
                 if fn in lm:
                     m._lm[fn] = lm[fn]
             return m
 
         m = manifestdict(self._nodelen)
         m._lm = self._lm.filtercopy(match)
         return m
 
     def diff(
         self,
         m2: 'ManifestDict',
         match: Optional[matchmod.basematcher] = None,
         clean: bool = False,
     ) -> Dict[
         bytes,
         Optional[
             Tuple[Tuple[Optional[bytes], bytes], Tuple[Optional[bytes], bytes]]
         ],
     ]:
         """Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         """
         if match:
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.diff(m2, clean=clean)
         return self._lm.diff(m2._lm, clean)
 
     def setflag(self, key: bytes, flag: bytes) -> None:
         if flag not in _manifestflags:
             raise TypeError(b"Invalid manifest flag set.")
         self._lm[key] = self[key], flag
 
     def get(self, key: bytes, default=None) -> Optional[bytes]:
         try:
             return self._lm[key][0]
         except KeyError:
             return default
 
     def flags(self, key: bytes) -> bytes:
         try:
             return self._lm[key][1]
         except KeyError:
             return b''
 
     def copy(self) -> 'ManifestDict':
         c = manifestdict(self._nodelen)
         c._lm = self._lm.copy()
         return c
 
     def items(self) -> Iterator[Tuple[bytes, bytes]]:
         return (x[:2] for x in self._lm.iterentries())
 
     def iteritems(self) -> Iterator[Tuple[bytes, bytes]]:
         return (x[:2] for x in self._lm.iterentries())
 
     def iterentries(self) -> Iterator[Tuple[bytes, bytes, bytes]]:
         return self._lm.iterentries()
 
     def text(self) -> ByteString:
         # most likely uses native version
         return self._lm.text()
 
     def fastdelta(
         self, base: ByteString, changes: Iterable[Tuple[bytes, bool]]
     ) -> Tuple[ByteString, ByteString]:
         """Given a base manifest text as a bytearray and a list of changes
         relative to that text, compute a delta that can be used by revlog.
         """
         delta = []
         dstart = None
         dend = None
         dline = [b""]
         start = 0
         # zero copy representation of base as a buffer
         addbuf = util.buffer(base)
 
         changes = list(changes)
         if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
                 # bs will either be the index of the item or the insert point
                 start, end = _msearch(addbuf, f, start)
                 if not todelete:
                     h, fl = self._lm[f]
                     l = b"%s\0%s%s\n" % (f, hex(h), fl)
                 else:
                     if start == end:
                         # item we want to delete was not found, error out
                         raise AssertionError(
                             _(b"failed to remove %s from manifest") % f
                         )
                     l = b""
                 if dstart is not None and dstart <= start and dend >= start:
                     if dend < end:
                         dend = end
                     if l:
                         dline.append(l)
                 else:
                     if dstart is not None:
                         delta.append((dstart, dend, b"".join(dline)))
                     dstart = start
                     dend = end
                     dline = [l]
 
             if dstart is not None:
                 delta.append((dstart, dend, b"".join(dline)))
             # apply the delta to the base, and get a delta for addrevision
             deltatext, arraytext = _addlistdelta(base, delta)
         else:
             # For large changes, it's much cheaper to just build the text and
             # diff it.
             arraytext = bytearray(self.text())
             deltatext = mdiff.textdiff(
                 util.buffer(base), util.buffer(arraytext)
             )
 
         return arraytext, deltatext
 
 
 manifestdict = interfaceutil.implementer(repository.imanifestdict)(ManifestDict)
 
 if typing.TYPE_CHECKING:
     manifestdict = ManifestDict
 
 
 def _msearch(
     m: ByteString, s: bytes, lo: int = 0, hi: Optional[int] = None
 ) -> Tuple[int, int]:
     """return a tuple (start, end) that says where to find s within m.
 
     If the string is found m[start:end] are the line containing
     that string.  If start == end the string was not found and
     they indicate the proper sorted insertion point.
     """
 
     def advance(i: int, c: bytes):
         while i < lenm and m[i : i + 1] != c:
             i += 1
         return i
 
     if not s:
         return (lo, lo)
     lenm = len(m)
     if not hi:
         hi = lenm
     while lo < hi:
         mid = (lo + hi) // 2
         start = mid
         while start > 0 and m[start - 1 : start] != b'\n':
             start -= 1
         end = advance(start, b'\0')
         if bytes(m[start:end]) < s:
             # we know that after the null there are 40 bytes of sha1
             # this translates to the bisect lo = mid + 1
             lo = advance(end + 40, b'\n') + 1
         else:
             # this translates to the bisect hi = mid
             hi = start
     end = advance(lo, b'\0')
     found = m[lo:end]
     if s == found:
         # we know that after the null there are 40 bytes of sha1
         end = advance(end + 40, b'\n')
         return (lo, end + 1)
     else:
         return (lo, lo)
 
 
 def _checkforbidden(l: Iterable[bytes]) -> None:
     """Check filenames for illegal characters."""
     for f in l:
         if b'\n' in f or b'\r' in f:
             raise error.StorageError(
                 _(b"'\\n' and '\\r' disallowed in filenames: %r")
                 % pycompat.bytestr(f)
             )
 
 
 # apply the changes collected during the bisect loop to our addlist
 # return a delta suitable for addrevision
 def _addlistdelta(
     addlist: ByteString,
     x: Iterable[Tuple[int, int, bytes]],
 ) -> Tuple[bytes, ByteString]:
     # for large addlist arrays, building a new array is cheaper
     # than repeatedly modifying the existing one
     currentposition = 0
     newaddlist = bytearray()
 
     for start, end, content in x:
         newaddlist += addlist[currentposition:start]
         if content:
             newaddlist += bytearray(content)
 
         currentposition = end
 
     newaddlist += addlist[currentposition:]
 
     deltatext = b"".join(
         struct.pack(b">lll", start, end, len(content)) + content
         for start, end, content in x
     )
     return deltatext, newaddlist
 
 
 def _splittopdir(f: bytes) -> Tuple[bytes, bytes]:
     if b'/' in f:
         dir, subpath = f.split(b'/', 1)
         return dir + b'/', subpath
     else:
         return b'', f
 
 
 _noop = lambda s: None
 
 
 class TreeManifest:
+    _dir: bytes
+    _dirs: Dict[bytes, 'TreeManifest']
+    _dirty: bool
+    _files: Dict[bytes, bytes]
+    _flags: Dict[bytes, bytes]
+
     def __init__(self, nodeconstants, dir: bytes = b'', text: bytes = b''):
         self._dir = dir
         self.nodeconstants = nodeconstants
         self._node = self.nodeconstants.nullid
         self._nodelen = self.nodeconstants.nodelen
         self._loadfunc = _noop
         self._copyfunc = _noop
         self._dirty = False
-        self._dirs: Dict[bytes, 'TreeManifest'] = {}
+        self._dirs = {}
         self._lazydirs: Dict[
             bytes,
             Tuple[bytes, Callable[[bytes, bytes], 'TreeManifest'], bool],
         ] = {}
         # Using _lazymanifest here is a little slower than plain old dicts
-        self._files: Dict[bytes, bytes] = {}
+        self._files = {}
         self._flags = {}
         if text:
 
             def readsubtree(subdir, subm):
                 raise AssertionError(
                     b'treemanifest constructor only accepts flat manifests'
                 )
 
             self.parse(text, readsubtree)
             self._dirty = True  # Mark flat manifest dirty after parsing
 
     def _subpath(self, path: bytes) -> bytes:
         return self._dir + path
 
     def _loadalllazy(self) -> None:
         selfdirs = self._dirs
         subpath = self._subpath
         for d, (node, readsubtree, docopy) in self._lazydirs.items():
             if docopy:
                 selfdirs[d] = readsubtree(subpath(d), node).copy()
             else:
                 selfdirs[d] = readsubtree(subpath(d), node)
         self._lazydirs.clear()
 
     def _loadlazy(self, d: bytes) -> None:
         v = self._lazydirs.get(d)
         if v is not None:
             node, readsubtree, docopy = v
             if docopy:
                 self._dirs[d] = readsubtree(self._subpath(d), node).copy()
             else:
                 self._dirs[d] = readsubtree(self._subpath(d), node)
             del self._lazydirs[d]
 
     def _loadchildrensetlazy(
         self, visit: Union[Set[bytes], bytes]
     ) -> Optional[Set[bytes]]:
         if not visit:
             return None
         if visit == b'all' or visit == b'this':
             self._loadalllazy()
             return None
 
         visit = cast(Set[bytes], visit)
 
         loadlazy = self._loadlazy
         for k in visit:
             loadlazy(k + b'/')
         return visit
 
     def _loaddifflazy(self, t1: 'TreeManifest', t2: 'TreeManifest'):
         """load items in t1 and t2 if they're needed for diffing.
 
         The criteria currently is:
         - if it's not present in _lazydirs in either t1 or t2, load it in the
           other (it may already be loaded or it may not exist, doesn't matter)
         - if it's present in _lazydirs in both, compare the nodeid; if it
           differs, load it in both
         """
         toloadlazy = []
         for d, v1 in t1._lazydirs.items():
             v2 = t2._lazydirs.get(d)
             if v2 is None or v2[0] != v1[0]:
                 toloadlazy.append(d)
         for d, v1 in t2._lazydirs.items():
             if d not in t1._lazydirs:
                 toloadlazy.append(d)
 
         for d in toloadlazy:
             t1._loadlazy(d)
             t2._loadlazy(d)
 
     def __len__(self) -> int:
         self._load()
         size = len(self._files)
         self._loadalllazy()
         for m in self._dirs.values():
             size += m.__len__()
         return size
 
     def __nonzero__(self) -> bool:
         # Faster than "__len__() != 0" since it avoids loading sub-manifests
         return not self._isempty()
 
     __bool__ = __nonzero__
 
     def _isempty(self) -> bool:
         self._load()  # for consistency; already loaded by all callers
         # See if we can skip loading everything.
         if self._files or (
             self._dirs and any(not m._isempty() for m in self._dirs.values())
         ):
             return False
         self._loadalllazy()
         return not self._dirs or all(m._isempty() for m in self._dirs.values())
 
     @encoding.strmethod
     def __repr__(self) -> bytes:
         return (
             b'<treemanifest dir=%s, node=%s, loaded=%r, dirty=%r at 0x%x>'
             % (
                 self._dir,
                 hex(self._node),
                 bool(self._loadfunc is _noop),
                 self._dirty,
                 id(self),
             )
         )
 
     def dir(self) -> bytes:
         """The directory that this tree manifest represents, including a
         trailing '/'. Empty string for the repo root directory."""
         return self._dir
 
     def node(self) -> bytes:
         """This node of this instance. nullid for unsaved instances. Should
         be updated when the instance is read or written from a revlog.
         """
         assert not self._dirty
         return self._node
 
     def setnode(self, node: bytes) -> None:
         self._node = node
         self._dirty = False
 
     def iterentries(
         self,
     ) -> Iterator[Tuple[bytes, Union[bytes, 'TreeManifest'], bytes]]:
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n, self._flags.get(p, b'')
             else:
                 for x in n.iterentries():
                     yield x
 
     def items(self) -> Iterator[Tuple[bytes, Union[bytes, 'TreeManifest']]]:
         self._load()
         self._loadalllazy()
         for p, n in sorted(
             itertools.chain(self._dirs.items(), self._files.items())
         ):
             if p in self._files:
                 yield self._subpath(p), n
             else:
                 for f, sn in n.items():
                     yield f, sn
 
     iteritems = items
 
     def iterkeys(self) -> Iterator[bytes]:
         self._load()
         self._loadalllazy()
         for p in sorted(itertools.chain(self._dirs, self._files)):
             if p in self._files:
                 yield self._subpath(p)
             else:
                 for f in self._dirs[p]:
                     yield f
 
     def keys(self) -> List[bytes]:
         return list(self.iterkeys())
 
     def __iter__(self) -> Iterator[bytes]:
         return self.iterkeys()
 
     def __contains__(self, f: bytes) -> bool:
         if f is None:
             return False
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return False
 
             return self._dirs[dir].__contains__(subpath)
         else:
             return f in self._files
 
     def get(self, f: bytes, default: Optional[bytes] = None) -> Optional[bytes]:
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return default
             return self._dirs[dir].get(subpath, default)
         else:
             return self._files.get(f, default)
 
     def __getitem__(self, f: bytes) -> bytes:
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].__getitem__(subpath)
         else:
             return self._files[f]
 
     def flags(self, f: bytes) -> bytes:
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             if dir not in self._dirs:
                 return b''
             return self._dirs[dir].flags(subpath)
         else:
             if f in self._lazydirs or f in self._dirs:
                 return b''
             return self._flags.get(f, b'')
 
     def find(self, f: bytes) -> Tuple[bytes, bytes]:
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             return self._dirs[dir].find(subpath)
         else:
             return self._files[f], self._flags.get(f, b'')
 
     def __delitem__(self, f: bytes) -> None:
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
 
             self._dirs[dir].__delitem__(subpath)
             # If the directory is now empty, remove it
             if self._dirs[dir]._isempty():
                 del self._dirs[dir]
         else:
             del self._files[f]
             if f in self._flags:
                 del self._flags[f]
         self._dirty = True
 
     def set(self, f: bytes, node: bytes, flags: bytes) -> None:
         """Set both the node and the flags for path f."""
         assert node is not None
         if flags not in _manifestflags:
             raise TypeError(b"Invalid manifest flag set.")
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(
                     self.nodeconstants, self._subpath(dir)
                 )
             self._dirs[dir].set(subpath, node, flags)
         else:
             assert len(node) in (20, 32)
             self._files[f] = node
             self._flags[f] = flags
         self._dirty = True
 
     def __setitem__(self, f: bytes, n: bytes) -> None:
         assert n is not None
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(
                     self.nodeconstants, self._subpath(dir)
                 )
             self._dirs[dir].__setitem__(subpath, n)
         else:
             # manifest nodes are either 20 bytes or 32 bytes,
             # depending on the hash in use. Assert this as historically
             # sometimes extra bytes were added.
             assert len(n) in (20, 32)
             self._files[f] = n
         self._dirty = True
 
     def _load(self) -> None:
         if self._loadfunc is not _noop:
             lf, self._loadfunc = self._loadfunc, _noop
             lf(self)
         elif self._copyfunc is not _noop:
             cf, self._copyfunc = self._copyfunc, _noop
             cf(self)
 
     def setflag(self, f: bytes, flags: bytes) -> None:
         """Set the flags (symlink, executable) for path f."""
         if flags not in _manifestflags:
             raise TypeError(b"Invalid manifest flag set.")
         self._load()
         dir, subpath = _splittopdir(f)
         if dir:
             self._loadlazy(dir)
             if dir not in self._dirs:
                 self._dirs[dir] = treemanifest(
                     self.nodeconstants, self._subpath(dir)
                 )
             self._dirs[dir].setflag(subpath, flags)
         else:
             self._flags[f] = flags
         self._dirty = True
 
     def copy(self) -> 'TreeManifest':
         copy = treemanifest(self.nodeconstants, self._dir)
         copy._node = self._node
         copy._dirty = self._dirty
         if self._copyfunc is _noop:
 
             def _copyfunc(s):
                 self._load()
                 s._lazydirs = {
                     d: (n, r, True) for d, (n, r, c) in self._lazydirs.items()
                 }
                 sdirs = s._dirs
                 for d, v in self._dirs.items():
                     sdirs[d] = v.copy()
                 s._files = dict.copy(self._files)
                 s._flags = dict.copy(self._flags)
 
             if self._loadfunc is _noop:
                 _copyfunc(copy)
             else:
                 copy._copyfunc = _copyfunc
         else:
             copy._copyfunc = self._copyfunc
         return copy
 
     def filesnotin(
         self, m2: 'TreeManifest', match: Optional[matchmod.basematcher] = None
     ) -> Set[bytes]:
         '''Set of files in this manifest that are not in the other'''
         if match and not match.always():
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.filesnotin(m2)
 
         files = set()
 
         def _filesnotin(t1, t2):
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
             for d, m1 in t1._dirs.items():
                 if d in t2._dirs:
                     m2 = t2._dirs[d]
                     _filesnotin(m1, m2)
                 else:
                     files.update(m1.iterkeys())
 
             for fn in t1._files:
                 if fn not in t2._files:
                     files.add(t1._subpath(fn))
 
         _filesnotin(self, m2)
         return files
 
     @propertycache
     def _alldirs(self) -> pathutil.dirs:
         return pathutil.dirs(self)
 
     def dirs(self) -> pathutil.dirs:
         return self._alldirs
 
     def hasdir(self, dir: bytes) -> bool:
         self._load()
         topdir, subdir = _splittopdir(dir)
         if topdir:
             self._loadlazy(topdir)
             if topdir in self._dirs:
                 return self._dirs[topdir].hasdir(subdir)
             return False
         dirslash = dir + b'/'
         return dirslash in self._dirs or dirslash in self._lazydirs
 
     def walk(self, match: matchmod.basematcher) -> Iterator[bytes]:
         """Generates matching file names.
 
         It also reports nonexistent files by marking them bad with match.bad().
         """
         if match.always():
             for f in iter(self):
                 yield f
             return
 
         fset = set(match.files())
 
         for fn in self._walk(match):
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             yield fn
 
         # for dirstate.walk, files=[''] means "walk the whole tree".
         # follow that here, too
         fset.discard(b'')
 
         for fn in sorted(fset):
             if not self.hasdir(fn):
                 match.bad(fn, None)
 
     def _walk(self, match: matchmod.basematcher) -> Iterator[bytes]:
         '''Recursively generates matching file names for walk().'''
         visit = match.visitchildrenset(self._dir[:-1])
         if not visit:
             return
 
         # yield this dir's files and walk its submanifests
         self._load()
         visit = self._loadchildrensetlazy(visit)
         for p in sorted(list(self._dirs) + list(self._files)):
             if p in self._files:
                 fullp = self._subpath(p)
                 if match(fullp):
                     yield fullp
             else:
                 if not visit or p[:-1] in visit:
                     for f in self._dirs[p]._walk(match):
                         yield f
 
     def _matches(self, match: matchmod.basematcher) -> 'TreeManifest':
         """recursively generate a new manifest filtered by the match argument."""
         if match.always():
             return self.copy()
         return self._matches_inner(match)
 
     def _matches_inner(self, match: matchmod.basematcher) -> 'TreeManifest':
         if match.always():
             return self.copy()
 
         visit = match.visitchildrenset(self._dir[:-1])
         if visit == b'all':
             return self.copy()
         ret = treemanifest(self.nodeconstants, self._dir)
         if not visit:
             return ret
 
         self._load()
         for fn in self._files:
             # While visitchildrenset *usually* lists only subdirs, this is
             # actually up to the matcher and may have some files in the set().
             # If visit == 'this', we should obviously look at the files in this
             # directory; if visit is a set, and fn is in it, we should inspect
             # fn (but no need to inspect things not in the set).
             if visit != b'this' and fn not in visit:
                 continue
             fullp = self._subpath(fn)
             # visitchildrenset isn't perfect, we still need to call the regular
             # matcher code to further filter results.
             if not match(fullp):
                 continue
             ret._files[fn] = self._files[fn]
             if fn in self._flags:
                 ret._flags[fn] = self._flags[fn]
 
         visit = self._loadchildrensetlazy(visit)
         for dir, subm in self._dirs.items():
             if visit and dir[:-1] not in visit:
                 continue
             m = subm._matches_inner(match)
             if not m._isempty():
                 ret._dirs[dir] = m
 
         if not ret._isempty():
             ret._dirty = True
         return ret
 
     def fastdelta(
         self, base: ByteString, changes: Iterable[Tuple[bytes, bool]]
     ) -> ByteString:
         raise FastdeltaUnavailable()
 
     def diff(
         self,
         m2: 'TreeManifest',
         match: Optional[matchmod.basematcher] = None,
         clean: bool = False,
     ) -> Dict[
         bytes,
         Optional[
             Tuple[Tuple[Optional[bytes], bytes], Tuple[Optional[bytes], bytes]]
         ],
     ]:
         """Finds changes between the current manifest and m2.
 
         Args:
           m2: the manifest to which this manifest should be compared.
           clean: if true, include files unchanged between these manifests
                  with a None value in the returned dictionary.
 
         The result is returned as a dict with filename as key and
         values of the form ((n1,fl1),(n2,fl2)), where n1/n2 is the
         nodeid in the current/other manifest and fl1/fl2 is the flag
         in the current/other manifest. Where the file does not exist,
         the nodeid will be None and the flags will be the empty
         string.
         """
         if match and not match.always():
             m1 = self._matches(match)
             m2 = m2._matches(match)
             return m1.diff(m2, clean=clean)
         result = {}
         emptytree = treemanifest(self.nodeconstants)
 
         def _iterativediff(t1, t2, stack):
             """compares two tree manifests and append new tree-manifests which
             needs to be compared to stack"""
             if t1._node == t2._node and not t1._dirty and not t2._dirty:
                 return
             t1._load()
             t2._load()
             self._loaddifflazy(t1, t2)
 
             for d, m1 in t1._dirs.items():
                 m2 = t2._dirs.get(d, emptytree)
                 stack.append((m1, m2))
 
             for d, m2 in t2._dirs.items():
                 if d not in t1._dirs:
                     stack.append((emptytree, m2))
 
             for fn, n1 in t1._files.items():
                 fl1 = t1._flags.get(fn, b'')
                 n2 = t2._files.get(fn, None)
                 fl2 = t2._flags.get(fn, b'')
                 if n1 != n2 or fl1 != fl2:
                     result[t1._subpath(fn)] = ((n1, fl1), (n2, fl2))
                 elif clean:
                     result[t1._subpath(fn)] = None
 
             for fn, n2 in t2._files.items():
                 if fn not in t1._files:
                     fl2 = t2._flags.get(fn, b'')
                     result[t2._subpath(fn)] = ((None, b''), (n2, fl2))
 
         stackls = []
         _iterativediff(self, m2, stackls)
         while stackls:
             t1, t2 = stackls.pop()
             # stackls is populated in the function call
             _iterativediff(t1, t2, stackls)
         return result
 
     def unmodifiedsince(self, m2: 'TreeManifest') -> bool:
         return not self._dirty and not m2._dirty and self._node == m2._node
 
     def parse(
         self,
         text: bytes,
         readsubtree: Callable[[bytes, bytes], 'TreeManifest'],
     ) -> None:
         selflazy = self._lazydirs
         for f, n, fl in _parse(self._nodelen, text):
             if fl == b't':
                 f = f + b'/'
                 # False below means "doesn't need to be copied" and can use the
                 # cached value from readsubtree directly.
                 selflazy[f] = (n, readsubtree, False)
             elif b'/' in f:
                 # This is a flat manifest, so use __setitem__ and setflag rather
                 # than assigning directly to _files and _flags, so we can
                 # assign a path in a subdirectory, and to mark dirty (compared
                 # to nullid).
                 self[f] = n
                 if fl:
                     self.setflag(f, fl)
             else:
                 # Assigning to _files and _flags avoids marking as dirty,
                 # and should be a little faster.
                 self._files[f] = n
                 if fl:
                     self._flags[f] = fl
 
     def text(self) -> ByteString:
         """Get the full data of this manifest as a bytestring."""
         self._load()
         return _text(self.iterentries())
 
     def dirtext(self) -> ByteString:
         """Get the full data of this directory as a bytestring. Make sure that
         any submanifests have been written first, so their nodeids are correct.
         """
         self._load()
         flags = self.flags
         lazydirs = [(d[:-1], v[0], b't') for d, v in self._lazydirs.items()]
         dirs = [(d[:-1], self._dirs[d]._node, b't') for d in self._dirs]
         files = [(f, self._files[f], flags(f)) for f in self._files]
         return _text(sorted(dirs + files + lazydirs))
 
     def read(
         self,
         gettext: Callable[[], ByteString],
         readsubtree: Callable[[bytes, bytes], 'TreeManifest'],
     ) -> None:
         def _load_for_read(s):
             s.parse(gettext(), readsubtree)
             s._dirty = False
 
         self._loadfunc = _load_for_read
 
     def writesubtrees(
         self,
         m1: 'TreeManifest',
         m2: 'TreeManifest',
         writesubtree: Callable[
             [
                 Callable[['TreeManifest'], None],
                 bytes,
                 bytes,
                 matchmod.basematcher,
             ],
             None,
         ],
         match: matchmod.basematcher,
     ) -> None:
         self._load()  # for consistency; should never have any effect here
         m1._load()
         m2._load()
         emptytree = treemanifest(self.nodeconstants)
 
         def getnode(m, d):
             ld = m._lazydirs.get(d)
             if ld:
                 return ld[0]
             tree = m._dirs.get(d, emptytree)
             assert tree is not None  # helps pytype
             return tree._node
 
         # let's skip investigating things that `match` says we do not need.
         visit = match.visitchildrenset(self._dir[:-1])
         visit = self._loadchildrensetlazy(visit)
         if visit == b'this' or visit == b'all':
             visit = None
         for d, subm in self._dirs.items():
             if visit and d[:-1] not in visit:
                 continue
             subp1 = getnode(m1, d)
             subp2 = getnode(m2, d)
             if subp1 == self.nodeconstants.nullid:
                 subp1, subp2 = subp2, subp1
             writesubtree(subm, subp1, subp2, match)
 
     def walksubtrees(
         self, matcher: Optional[matchmod.basematcher] = None
     ) -> Iterator['TreeManifest']:
         """Returns an iterator of the subtrees of this manifest, including this
         manifest itself.
 
         If `matcher` is provided, it only returns subtrees that match.
         """
         if matcher and not matcher.visitdir(self._dir[:-1]):
             return
         if not matcher or matcher(self._dir[:-1]):
             yield self
 
         self._load()
         # OPT: use visitchildrenset to avoid loading everything.
         self._loadalllazy()
         for d, subm in self._dirs.items():
             for subtree in subm.walksubtrees(matcher=matcher):
                 yield subtree
 
 
 treemanifest = interfaceutil.implementer(repository.imanifestdict)(TreeManifest)
 
 if typing.TYPE_CHECKING:
     treemanifest = TreeManifest
 
 
 class manifestfulltextcache(util.lrucachedict):
     """File-backed LRU cache for the manifest cache
 
     File consists of entries, up to EOF:
 
     - 20 bytes node, 4 bytes length, <length> manifest data
 
     These are written in reverse cache order (oldest to newest).
 
     """
 
     _file = b'manifestfulltextcache'
 
     def __init__(self, max):
         super(manifestfulltextcache, self).__init__(max)
         self._dirty = False
         self._read = False
         self._opener = None
 
     def read(self):
         if self._read or self._opener is None:
             return
 
         try:
             with self._opener(self._file) as fp:
                 set = super(manifestfulltextcache, self).__setitem__
                 # ignore trailing data, this is a cache, corruption is skipped
                 while True:
                     # TODO do we need to do work here for sha1 portability?
                     node = fp.read(20)
                     if len(node) < 20:
                         break
                     try:
                         size = struct.unpack(b'>L', fp.read(4))[0]
                     except struct.error:
                         break
                     value = bytearray(fp.read(size))
                     if len(value) != size:
                         break
                     set(node, value)
         except IOError:
             # the file is allowed to be missing
             pass
 
         self._read = True
         self._dirty = False
 
     def write(self):
         if not self._dirty or self._opener is None:
             return
         # rotate backwards to the first used node
         try:
             with self._opener(
                 self._file, b'w', atomictemp=True, checkambig=True
             ) as fp:
                 node = self._head.prev
                 while True:
                     if node.key in self._cache:
                         fp.write(node.key)
                         fp.write(struct.pack(b'>L', len(node.value)))
                         fp.write(node.value)
                     if node is self._head:
                         break
                     node = node.prev
         except IOError:
             # We could not write the cache (eg: permission error)
             # the content can be missing.
             #
             # We could try harder and see if we could recreate a wcache
             # directory were we coudl write too.
             #
             # XXX the error pass silently, having some way to issue an error
             # log `ui.log` would be nice.
             pass
 
     def __len__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__len__()
 
     def __contains__(self, k):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__contains__(k)
 
     def __iter__(self):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).__iter__()
 
     def __getitem__(self, k):
         if not self._read:
             self.read()
         # the cache lru order can change on read
         setdirty = self._cache.get(k) is not self._head
         value = super(manifestfulltextcache, self).__getitem__(k)
         if setdirty:
             self._dirty = True
         return value
 
     def __setitem__(self, k, v):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__setitem__(k, v)
         self._dirty = True
 
     def __delitem__(self, k):
         if not self._read:
             self.read()
         super(manifestfulltextcache, self).__delitem__(k)
         self._dirty = True
 
     def get(self, k, default=None):
         if not self._read:
             self.read()
         return super(manifestfulltextcache, self).get(k, default=default)
 
     def clear(self, clear_persisted_data=False):
         super(manifestfulltextcache, self).clear()
         if clear_persisted_data:
             self._dirty = True
             self.write()
         self._read = False
 
 
 # and upper bound of what we expect from compression
 # (real live value seems to be "3")
 MAXCOMPRESSION = 3
 
 
 class FastdeltaUnavailable(Exception):
     """Exception raised when fastdelta isn't usable on a manifest."""
 
 
 class ManifestRevlog:
     """A revlog that stores manifest texts. This is responsible for caching the
     full-text manifest contents.
     """
 
     def __init__(
         self,
         nodeconstants,
         opener,
         tree=b'',
         dirlogcache=None,
         treemanifest=False,
     ):
         """Constructs a new manifest revlog
 
         `indexfile` - used by extensions to have two manifests at once, like
         when transitioning between flatmanifeset and treemanifests.
 
         `treemanifest` - used to indicate this is a tree manifest revlog. Opener
         options can also be used to make this a tree manifest revlog. The opener
         option takes precedence, so if it is set to True, we ignore whatever
         value is passed in to the constructor.
         """
         self.nodeconstants = nodeconstants
         # During normal operations, we expect to deal with not more than four
         # revs at a time (such as during commit --amend). When rebasing large
         # stacks of commits, the number can go up, hence the config knob below.
         cachesize = 4
         optiontreemanifest = False
         persistentnodemap = False
         opts = getattr(opener, 'options', None)
         if opts is not None:
             cachesize = opts.get(b'manifestcachesize', cachesize)
             optiontreemanifest = opts.get(b'treemanifest', False)
             persistentnodemap = opts.get(b'persistent-nodemap', False)
 
         self._treeondisk = optiontreemanifest or treemanifest
 
         self._fulltextcache = manifestfulltextcache(cachesize)
 
         if tree:
             assert self._treeondisk, (tree, b'opts is %r' % opts)
 
         radix = b'00manifest'
         if tree:
             radix = b"meta/" + tree + radix
 
         self.tree = tree
 
         # The dirlogcache is kept on the root manifest log
         if tree:
             self._dirlogcache = dirlogcache
         else:
             self._dirlogcache = {b'': self}
 
         self._revlog = revlog.revlog(
             opener,
             target=(revlog_constants.KIND_MANIFESTLOG, self.tree),
             radix=radix,
             # only root indexfile is cached
             checkambig=not bool(tree),
             mmaplargeindex=True,
             upperboundcomp=MAXCOMPRESSION,
             persistentnodemap=persistentnodemap,
         )
 
         self.index = self._revlog.index
 
     def get_revlog(self):
         """return an actual revlog instance if any
 
         This exist because a lot of code leverage the fact the underlying
         storage is a revlog for optimization, so giving simple way to access
         the revlog instance helps such code.
         """
         return self._revlog
 
     def _setupmanifestcachehooks(self, repo):
         """Persist the manifestfulltextcache on lock release"""
         if not hasattr(repo, '_wlockref'):
             return
 
         self._fulltextcache._opener = repo.wcachevfs
         if repo._currentlock(repo._wlockref) is None:
             return
 
         reporef = weakref.ref(repo)
         manifestrevlogref = weakref.ref(self)
 
         def persistmanifestcache(success):
             # Repo is in an unknown state, do not persist.
             if not success:
                 return
 
             repo = reporef()
             self = manifestrevlogref()
             if repo is None or self is None:
                 return
             if repo.manifestlog.getstorage(b'') is not self:
                 # there's a different manifest in play now, abort
                 return
             self._fulltextcache.write()
 
         repo._afterlock(persistmanifestcache)
 
     @property
     def fulltextcache(self):
         return self._fulltextcache
 
     def clearcaches(self, clear_persisted_data=False):
         self._revlog.clearcaches()
         self._fulltextcache.clear(clear_persisted_data=clear_persisted_data)
         self._dirlogcache = {self.tree: self}
 
     def dirlog(self, d):
         if d:
             assert self._treeondisk
         if d not in self._dirlogcache:
             mfrevlog = manifestrevlog(
                 self.nodeconstants,
                 self.opener,
                 d,
                 self._dirlogcache,
                 treemanifest=self._treeondisk,
             )
             self._dirlogcache[d] = mfrevlog
         return self._dirlogcache[d]
 
     def add(
         self,
         m,
         transaction,
         link,
         p1,
         p2,
         added: Iterable[bytes],
         removed: Iterable[bytes],
         readtree=None,
         match=None,
     ):
         """add some manifest entry in to the manifest log
 
         input:
 
           m:           the manifest dict we want to store
           transaction: the open transaction
           p1:          manifest-node of p1
           p2:          manifest-node of p2
           added:       file added/changed compared to parent
           removed:     file removed compared to parent
 
         tree manifest input:
 
           readtree:    a function to read a subtree
           match:       a filematcher for the subpart of the tree manifest
         """
         try:
             if p1 not in self.fulltextcache:
                 raise FastdeltaUnavailable()
             # If our first parent is in the manifest cache, we can
             # compute a delta here using properties we know about the
             # manifest up-front, which may save time later for the
             # revlog layer.
 
             _checkforbidden(added)
             # combine the changed lists into one sorted iterator
             work = heapq.merge(
                 [(x, False) for x in sorted(added)],
                 [(x, True) for x in sorted(removed)],
             )
 
             arraytext, deltatext = m.fastdelta(self.fulltextcache[p1], work)
             cachedelta = self._revlog.rev(p1), deltatext
             text = util.buffer(arraytext)
             rev = self._revlog.addrevision(
                 text, transaction, link, p1, p2, cachedelta
             )
             n = self._revlog.node(rev)
         except FastdeltaUnavailable:
             # The first parent manifest isn't already loaded or the
             # manifest implementation doesn't support fastdelta, so
             # we'll just encode a fulltext of the manifest and pass
             # that through to the revlog layer, and let it handle the
             # delta process.
             if self._treeondisk:
                 assert readtree, b"readtree must be set for treemanifest writes"
                 assert match, b"match must be specified for treemanifest writes"
                 m1 = readtree(self.tree, p1)
                 m2 = readtree(self.tree, p2)
                 n = self._addtree(
                     m, transaction, link, m1, m2, readtree, match=match
                 )
                 arraytext = None
             else:
                 text = m.text()
                 rev = self._revlog.addrevision(text, transaction, link, p1, p2)
                 n = self._revlog.node(rev)
                 arraytext = bytearray(text)
 
         if arraytext is not None:
             self.fulltextcache[n] = arraytext
 
         return n
 
     def _addtree(self, m, transaction, link, m1, m2, readtree, match):
         # If the manifest is unchanged compared to one parent,
         # don't write a new revision
         if self.tree != b'' and (
             m.unmodifiedsince(m1) or m.unmodifiedsince(m2)
         ):
             return m.node()
 
         def writesubtree(subm, subp1, subp2, match):
             sublog = self.dirlog(subm.dir())
             sublog.add(
                 subm,
                 transaction,
                 link,
                 subp1,
                 subp2,
                 None,
                 None,
                 readtree=readtree,
                 match=match,
             )
 
         m.writesubtrees(m1, m2, writesubtree, match)
         text = m.dirtext()
         n = None
         if self.tree != b'':
             # Double-check whether contents are unchanged to one parent
             if text == m1.dirtext():
                 n = m1.node()
             elif text == m2.dirtext():
                 n = m2.node()
 
         if not n:
             rev = self._revlog.addrevision(
                 text, transaction, link, m1.node(), m2.node()
             )
             n = self._revlog.node(rev)
 
         # Save nodeid so parent manifest can calculate its nodeid
         m.setnode(n)
         return n
 
     def __len__(self):
         return len(self._revlog)
 
     def __iter__(self):
         return self._revlog.__iter__()
 
     def rev(self, node):
         return self._revlog.rev(node)
 
     def node(self, rev):
         return self._revlog.node(rev)
 
     def lookup(self, value):
         return self._revlog.lookup(value)
 
     def parentrevs(self, rev):
         return self._revlog.parentrevs(rev)
 
     def parents(self, node):
         return self._revlog.parents(node)
 
     def linkrev(self, rev):
         return self._revlog.linkrev(rev)
 
     def checksize(self):
         return self._revlog.checksize()
 
     def revision(self, node):
         return self._revlog.revision(node)
 
     def rawdata(self, node):
         return self._revlog.rawdata(node)
 
     def revdiff(self, rev1, rev2):
         return self._revlog.revdiff(rev1, rev2)
 
     def cmp(self, node, text):
         return self._revlog.cmp(node, text)
 
     def deltaparent(self, rev):
         return self._revlog.deltaparent(rev)
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
         debug_info=None,
     ):
         return self._revlog.emitrevisions(
             nodes,
             nodesorder=nodesorder,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             deltamode=deltamode,
             sidedata_helpers=sidedata_helpers,
             debug_info=debug_info,
         )
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         debug_info=None,
         delta_base_reuse_policy=None,
     ):
         return self._revlog.addgroup(
             deltas,
             linkmapper,
             transaction,
             alwayscache=alwayscache,
             addrevisioncb=addrevisioncb,
             duplicaterevisioncb=duplicaterevisioncb,
             debug_info=debug_info,
             delta_base_reuse_policy=delta_base_reuse_policy,
         )
 
     def rawsize(self, rev):
         return self._revlog.rawsize(rev)
 
     def getstrippoint(self, minlink):
         return self._revlog.getstrippoint(minlink)
 
     def strip(self, minlink, transaction):
         return self._revlog.strip(minlink, transaction)
 
     def files(self):
         return self._revlog.files()
 
     def clone(self, tr, destrevlog, **kwargs):
         if not isinstance(destrevlog, manifestrevlog):
             raise error.ProgrammingError(b'expected manifestrevlog to clone()')
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         return self._revlog.storageinfo(
             exclusivefiles=exclusivefiles,
             sharedfiles=sharedfiles,
             revisionscount=revisionscount,
             trackedsize=trackedsize,
             storedsize=storedsize,
         )
 
     @property
     def opener(self):
         return self._revlog.opener
 
     @opener.setter
     def opener(self, value):
         self._revlog.opener = value
 
 
 manifestrevlog = interfaceutil.implementer(repository.imanifeststorage)(
     ManifestRevlog
 )
 
 if typing.TYPE_CHECKING:
     manifestrevlog = ManifestRevlog
 
 AnyManifestCtx = Union['ManifestCtx', 'TreeManifestCtx']
 AnyManifestDict = Union[ManifestDict, TreeManifest]
 
 
 class ManifestLog:
     """A collection class representing the collection of manifest snapshots
     referenced by commits in the repository.
 
     In this situation, 'manifest' refers to the abstract concept of a snapshot
     of the list of files in the given commit. Consumers of the output of this
     class do not care about the implementation details of the actual manifests
     they receive (i.e. tree or flat or lazily loaded, etc)."""
 
     def __init__(self, opener, repo, rootstore, narrowmatch):
         self.nodeconstants = repo.nodeconstants
         usetreemanifest = False
         cachesize = 4
 
         opts = getattr(opener, 'options', None)
         if opts is not None:
             usetreemanifest = opts.get(b'treemanifest', usetreemanifest)
             cachesize = opts.get(b'manifestcachesize', cachesize)
 
         self._treemanifests = usetreemanifest
 
         self._rootstore = rootstore
         self._rootstore._setupmanifestcachehooks(repo)
         self._narrowmatch = narrowmatch
 
         # A cache of the manifestctx or treemanifestctx for each directory
         self._dirmancache = {}
         self._dirmancache[b''] = util.lrucachedict(cachesize)
 
         self._cachesize = cachesize
 
     def __getitem__(self, node):
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
         """
         return self.get(b'', node)
 
     @property
     def narrowed(self):
         return not (self._narrowmatch is None or self._narrowmatch.always())
 
     def get(
         self, tree: bytes, node: bytes, verify: bool = True
     ) -> AnyManifestCtx:
         """Retrieves the manifest instance for the given node. Throws a
         LookupError if not found.
 
         `verify` - if True an exception will be thrown if the node is not in
                    the revlog
         """
         if node in self._dirmancache.get(tree, ()):
             return self._dirmancache[tree][node]
 
         if not self._narrowmatch.always():
             if not self._narrowmatch.visitdir(tree[:-1]):
                 return excludeddirmanifestctx(self.nodeconstants, tree, node)
         if tree:
             if self._rootstore._treeondisk:
                 if verify:
                     # Side-effect is LookupError is raised if node doesn't
                     # exist.
                     self.getstorage(tree).rev(node)
 
                 m = treemanifestctx(self, tree, node)
             else:
                 raise error.Abort(
                     _(
                         b"cannot ask for manifest directory '%s' in a flat "
                         b"manifest"
                     )
                     % tree
                 )
         else:
             if verify:
                 # Side-effect is LookupError is raised if node doesn't exist.
                 self._rootstore.rev(node)
 
             if self._treemanifests:
                 m = treemanifestctx(self, b'', node)
             else:
                 m = manifestctx(self, node)
 
         if node != self.nodeconstants.nullid:
             mancache = self._dirmancache.get(tree)
             if not mancache:
                 mancache = util.lrucachedict(self._cachesize)
                 self._dirmancache[tree] = mancache
             mancache[node] = m
         return m
 
     def getstorage(self, tree):
         return self._rootstore.dirlog(tree)
 
     def clearcaches(self, clear_persisted_data: bool = False) -> None:
         self._dirmancache.clear()
         self._rootstore.clearcaches(clear_persisted_data=clear_persisted_data)
 
     def rev(self, node) -> int:
         return self._rootstore.rev(node)
 
     def update_caches(self, transaction) -> None:
         return self._rootstore._revlog.update_caches(transaction=transaction)
 
 
 manifestlog = interfaceutil.implementer(repository.imanifestlog)(ManifestLog)
 
 if typing.TYPE_CHECKING:
     manifestlog = ManifestLog
 
 
 class MemManifestCtx:
+    _manifestdict: ManifestDict
+
     def __init__(self, manifestlog):
         self._manifestlog = manifestlog
         self._manifestdict = manifestdict(manifestlog.nodeconstants.nodelen)
 
     def _storage(self) -> ManifestRevlog:
         return self._manifestlog.getstorage(b'')
 
     def copy(self) -> 'MemManifestCtx':
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     def read(self) -> 'ManifestDict':
         return self._manifestdict
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         return self._storage().add(
             self._manifestdict,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             match=match,
         )
 
 
 memmanifestctx = interfaceutil.implementer(
     repository.imanifestrevisionwritable
 )(MemManifestCtx)
 
 if typing.TYPE_CHECKING:
     memmanifestctx = MemManifestCtx
 
 
 class ManifestCtx:
     """A class representing a single revision of a manifest, including its
     contents, its parent revs, and its linkrev.
     """
 
+    _data: Optional[ManifestDict]
+
     def __init__(self, manifestlog, node):
         self._manifestlog = manifestlog
         self._data = None
 
         self._node = node
 
         # TODO: We eventually want p1, p2, and linkrev exposed on this class,
         # but let's add it later when something needs it and we can load it
         # lazily.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self) -> 'ManifestRevlog':
         return self._manifestlog.getstorage(b'')
 
     def node(self) -> bytes:
         return self._node
 
     def copy(self) -> MemManifestCtx:
         memmf = memmanifestctx(self._manifestlog)
         memmf._manifestdict = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self) -> Tuple[bytes, bytes]:
         return self._storage().parents(self._node)
 
     def read(self) -> 'ManifestDict':
         if self._data is None:
             nc = self._manifestlog.nodeconstants
             if self._node == nc.nullid:
                 self._data = manifestdict(nc.nodelen)
             else:
                 store = self._storage()
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = manifestdict(nc.nodelen, text)
         return self._data
 
     def readfast(self, shallow: bool = False) -> 'ManifestDict':
         """Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, nothing changes since this is a flat manifest.
         """
         util.nouideprecwarn(
             b'"readfast" is deprecated use "read_any_fast_delta" or "read_delta_parents"',
             b"6.9",
             stacklevel=2,
         )
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta()
         return self.read()
 
     def readdelta(self, shallow: bool = False) -> 'ManifestDict':
         """Returns a manifest containing just the entries that are present
         in this manifest, but not in its p1 manifest. This is efficient to read
         if the revlog delta is already p1.
 
         Changing the value of `shallow` has no effect on flat manifests.
         """
         util.nouideprecwarn(
             b'"readfast" is deprecated use "read_any_fast_delta" or "read_delta_new_entries"',
             b"6.9",
             stacklevel=2,
         )
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(store.nodeconstants.nodelen, d)
 
     def read_any_fast_delta(
         self,
         valid_bases: Optional[Collection[int]] = None,
         *,
         shallow: bool = False,
     ) -> Tuple[Optional[int], ManifestDict]:
         """see `imanifestrevisionstored` documentation"""
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if valid_bases is None:
             # make sure the next check is True
             valid_bases = (deltaparent,)
         if deltaparent != nullrev and deltaparent in valid_bases:
             d = mdiff.patchtext(store.revdiff(deltaparent, r))
             return (
                 deltaparent,
                 manifestdict(store.nodeconstants.nodelen, d),
             )
         return (None, self.read())
 
     def read_delta_parents(
         self,
         *,
         shallow: bool = False,
         exact: bool = True,
     ) -> ManifestDict:
         """see `interface.imanifestrevisionbase` documentations"""
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         parents = [p for p in store.parentrevs(r) if p is not nullrev]
         if not exact and deltaparent in parents:
             d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
             return manifestdict(store.nodeconstants.nodelen, d)
         elif not exact or len(parents) == 0:
             return self.read()
         elif len(parents) == 1:
             p = parents[0]
             d = mdiff.patchtext(store.revdiff(p, r))
             return manifestdict(store.nodeconstants.nodelen, d)
         else:
             p1, p2 = parents
             d1 = mdiff.patchtext(store.revdiff(p1, r))
             d2 = mdiff.patchtext(store.revdiff(p2, r))
             d1 = manifestdict(store.nodeconstants.nodelen, d1)
             d2 = manifestdict(store.nodeconstants.nodelen, d2)
             md = manifestdict(store.nodeconstants.nodelen)
             for f, new_node, new_flag in d1.iterentries():
                 if f not in d2:
                     continue
                 if new_node is not None:
                     md.set(f, new_node, new_flag)
             return md
 
     def read_delta_new_entries(self, *, shallow=False) -> ManifestDict:
         """see `interface.imanifestrevisionbase` documentations"""
         # If we are using narrow, returning a delta against an arbitrary
         # changeset might return file outside the narrowspec. This can create
         # issue when running validation server side with strict security as
         # push from low priviledge usage might be seen as adding new revision
         # for files they cannot touch. So we are strict if narrow is involved.
         if self._manifestlog.narrowed:
             return self.read_delta_parents(shallow=shallow, exact=True)
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(store.nodeconstants.nodelen, d)
 
     def find(self, key: bytes) -> Tuple[bytes, bytes]:
         return self.read().find(key)
 
 
 manifestctx = interfaceutil.implementer(repository.imanifestrevisionstored)(
     ManifestCtx
 )
 
 if typing.TYPE_CHECKING:
     manifestctx = ManifestCtx
 
 
 class MemTreeManifestCtx:
+    _treemanifest: TreeManifest
+
     def __init__(self, manifestlog, dir=b''):
         self._manifestlog = manifestlog
         self._dir = dir
         self._treemanifest = treemanifest(manifestlog.nodeconstants)
 
     def _storage(self) -> ManifestRevlog:
         return self._manifestlog.getstorage(b'')
 
     def copy(self) -> 'MemTreeManifestCtx':
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self._treemanifest.copy()
         return memmf
 
     def read(self) -> 'TreeManifest':
         return self._treemanifest
 
     def write(self, transaction, link, p1, p2, added, removed, match=None):
         def readtree(dir, node):
             return self._manifestlog.get(dir, node).read()
 
         return self._storage().add(
             self._treemanifest,
             transaction,
             link,
             p1,
             p2,
             added,
             removed,
             readtree=readtree,
             match=match,
         )
 
 
 memtreemanifestctx = interfaceutil.implementer(
     repository.imanifestrevisionwritable
 )(MemTreeManifestCtx)
 
 if typing.TYPE_CHECKING:
     memtreemanifestctx = MemTreeManifestCtx
 
 
 class TreeManifestCtx:
+    _data: Optional[TreeManifest]
+
     def __init__(self, manifestlog, dir, node):
         self._manifestlog = manifestlog
         self._dir = dir
         self._data = None
 
         self._node = node
 
         # TODO: Load p1/p2/linkrev lazily. They need to be lazily loaded so that
         # we can instantiate treemanifestctx objects for directories we don't
         # have on disk.
         # self.p1, self.p2 = store.parents(node)
         # rev = store.rev(node)
         # self.linkrev = store.linkrev(rev)
 
     def _storage(self) -> ManifestRevlog:
         narrowmatch = self._manifestlog._narrowmatch
         if not narrowmatch.always():
             if not narrowmatch.visitdir(self._dir[:-1]):
                 return excludedmanifestrevlog(
                     self._manifestlog.nodeconstants, self._dir
                 )
         return self._manifestlog.getstorage(self._dir)
 
     def read(self) -> 'TreeManifest':
         if self._data is None:
             store = self._storage()
             if self._node == self._manifestlog.nodeconstants.nullid:
                 self._data = treemanifest(self._manifestlog.nodeconstants)
             # TODO accessing non-public API
             elif store._treeondisk:
                 m = treemanifest(self._manifestlog.nodeconstants, dir=self._dir)
 
                 def gettext():
                     return store.revision(self._node)
 
                 def readsubtree(dir, subm):
                     # Set verify to False since we need to be able to create
                     # subtrees for trees that don't exist on disk.
                     return self._manifestlog.get(dir, subm, verify=False).read()
 
                 m.read(gettext, readsubtree)
                 m.setnode(self._node)
                 self._data = m
             else:
                 if self._node in store.fulltextcache:
                     text = pycompat.bytestr(store.fulltextcache[self._node])
                 else:
                     text = store.revision(self._node)
                     arraytext = bytearray(text)
                     store.fulltextcache[self._node] = arraytext
                 self._data = treemanifest(
                     self._manifestlog.nodeconstants, dir=self._dir, text=text
                 )
 
         return self._data
 
     def node(self) -> bytes:
         return self._node
 
     def copy(self) -> 'MemTreeManifestCtx':
         memmf = memtreemanifestctx(self._manifestlog, dir=self._dir)
         memmf._treemanifest = self.read().copy()
         return memmf
 
     @propertycache
     def parents(self) -> Tuple[bytes, bytes]:
         return self._storage().parents(self._node)
 
     def readdelta(self, shallow: bool = False) -> AnyManifestDict:
         """see `imanifestrevisionstored` documentation"""
         util.nouideprecwarn(
             b'"readdelta" is deprecated use "read_any_fast_delta" or "read_delta_new_entries"',
             b"6.9",
             stacklevel=2,
         )
         store = self._storage()
         if shallow:
             r = store.rev(self._node)
             d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
             return manifestdict(store.nodeconstants.nodelen, d)
         else:
             # Need to perform a slow delta
             r0 = store.deltaparent(store.rev(self._node))
             m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
             m1 = self.read()
             md = treemanifest(self._manifestlog.nodeconstants, dir=self._dir)
             for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).items():
                 if n1:
                     md[f] = n1
                     if fl1:
                         md.setflag(f, fl1)
             return md
 
     def read_any_fast_delta(
         self,
         valid_bases: Optional[Collection[int]] = None,
         *,
         shallow: bool = False,
     ) -> Tuple[Optional[int], AnyManifestDict]:
         """see `imanifestrevisionstored` documentation"""
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
 
         if valid_bases is None:
             # make sure the next check is True
             valid_bases = (deltaparent,)
         can_use_delta = deltaparent != nullrev and deltaparent in valid_bases
 
         if shallow:
             if can_use_delta:
                 return (deltaparent, self._read_storage_delta_shallow())
             else:
                 d = store.revision(self._node)
                 return (None, manifestdict(store.nodeconstants.nodelen, d))
         else:
             # note: This use "slow_delta" here is cargo culted from the previous
             # implementation. I am not sure it make sense since the goal here is to
             # be fast, so why are we computing a delta? On the other hand, tree
             # manifest delta as fairly "cheap" and allow for skipping whole part of
             # the tree that a full read would access. So it might be a good idea.
             #
             # If we realize we don't need delta here, we should simply use:
             #
             #     return (None, self.read())
             if can_use_delta:
                 return (None, self._read_storage_slow_delta(base=deltaparent))
             else:
                 parents = [
                     p
                     for p in store.parentrevs(r)
                     if p is not nullrev and p in valid_bases
                 ]
                 if parents:
                     best_base = max(parents)
                 else:
                     best_base = max(valid_bases)
                 return (None, self._read_storage_slow_delta(base=best_base))
 
     def _read_storage_delta_shallow(self) -> ManifestDict:
         store = self._storage()
         r = store.rev(self._node)
         d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
         return manifestdict(store.nodeconstants.nodelen, d)
 
     def _read_storage_slow_delta(self, base) -> 'TreeManifest':
         store = self._storage()
         if base is None:
             base = store.deltaparent(store.rev(self._node))
         m0 = self._manifestlog.get(self._dir, store.node(base)).read()
         m1 = self.read()
         md = treemanifest(self._manifestlog.nodeconstants, dir=self._dir)
         for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).items():
             if n1:
                 md[f] = n1
                 if fl1:
                     md.setflag(f, fl1)
         return md
 
     def read_delta_parents(
         self,
         *,
         shallow: bool = False,
         exact: bool = True,
     ) -> AnyManifestDict:
         """see `interface.imanifestrevisionbase` documentations"""
         store = self._storage()
         r = store.rev(self._node)
         parents = [p for p in store.parentrevs(r) if p is not nullrev]
         if not exact:
             return self.read_any_fast_delta(parents, shallow=shallow)[1]
         elif len(parents) == 0:
             if shallow:
                 d = store.revision(self._node)
                 return manifestdict(store.nodeconstants.nodelen, d)
             else:
                 return self.read()
         elif len(parents) == 1:
             p = parents[0]
             if shallow:
                 d = mdiff.patchtext(store.revdiff(p, r))
                 return manifestdict(store.nodeconstants.nodelen, d)
             else:
                 return self._read_storage_slow_delta(base=p)
         else:
             p1, p2 = parents
             if shallow:
                 d1 = mdiff.patchtext(store.revdiff(p1, r))
                 d2 = mdiff.patchtext(store.revdiff(p2, r))
                 d1 = manifestdict(store.nodeconstants.nodelen, d1)
                 d2 = manifestdict(store.nodeconstants.nodelen, d2)
                 md = manifestdict(store.nodeconstants.nodelen)
                 for f, new_node, new_flag in d1.iterentries():
                     if f not in d2:
                         continue
                     if new_node is not None:
                         md.set(f, new_node, new_flag)
                 return md
             else:
                 m1 = self._manifestlog.get(self._dir, store.node(p1)).read()
                 m2 = self._manifestlog.get(self._dir, store.node(p2)).read()
                 mc = self.read()
                 d1 = m1.diff(mc)
                 d2 = m2.diff(mc)
                 md = treemanifest(
                     self._manifestlog.nodeconstants,
                     dir=self._dir,
                 )
                 for f, new_node, new_flag in d1.iterentries():
                     if f not in d2:
                         continue
                     if new_node is not None:
                         md.set(f, new_node, new_flag)
                 return md
 
     def read_delta_new_entries(
         self, *, shallow: bool = False
     ) -> AnyManifestDict:
         """see `interface.imanifestrevisionbase` documentations"""
         # If we are using narrow, returning a delta against an arbitrary
         # changeset might return file outside the narrowspec. This can create
         # issue when running validation server side with strict security as
         # push from low priviledge usage might be seen as adding new revision
         # for files they cannot touch. So we are strict if narrow is involved.
         if self._manifestlog.narrowed:
             return self.read_delta_parents(shallow=shallow, exact=True)
         # delegate to existing another existing method for simplicity
         store = self._storage()
         r = store.rev(self._node)
         bases = (store.deltaparent(r),)
         return self.read_any_fast_delta(bases, shallow=shallow)[1]
 
     def readfast(self, shallow=False) -> AnyManifestDict:
         """Calls either readdelta or read, based on which would be less work.
         readdelta is called if the delta is against the p1, and therefore can be
         read quickly.
 
         If `shallow` is True, it only returns the entries from this manifest,
         and not any submanifests.
         """
         util.nouideprecwarn(
             b'"readdelta" is deprecated use "read_any_fast_delta" or "read_delta_parents"',
             b"6.9",
             stacklevel=2,
         )
         store = self._storage()
         r = store.rev(self._node)
         deltaparent = store.deltaparent(r)
         if deltaparent != nullrev and deltaparent in store.parentrevs(r):
             return self.readdelta(shallow=shallow)
 
         if shallow:
             return manifestdict(
                 store.nodeconstants.nodelen, store.revision(self._node)
             )
         else:
             return self.read()
 
     def find(self, key: bytes) -> Tuple[bytes, bytes]:
         return self.read().find(key)
 
 
 treemanifestctx = interfaceutil.implementer(repository.imanifestrevisionstored)(
     TreeManifestCtx
 )
 
 if typing.TYPE_CHECKING:
     treemanifestctx = TreeManifestCtx
 
 
 class excludeddir(treemanifest):
     """Stand-in for a directory that is excluded from the repository.
 
     With narrowing active on a repository that uses treemanifests,
     some of the directory revlogs will be excluded from the resulting
     clone. This is a huge storage win for clients, but means we need
     some sort of pseudo-manifest to surface to internals so we can
     detect a merge conflict outside the narrowspec. That's what this
     class is: it stands in for a directory whose node is known, but
     whose contents are unknown.
     """
 
+    _files: Dict[bytes, bytes]
+    _flags: Dict[bytes, bytes]
+
     def __init__(self, nodeconstants, dir, node):
         super(excludeddir, self).__init__(nodeconstants, dir)
         self._node = node
         # Add an empty file, which will be included by iterators and such,
         # appearing as the directory itself (i.e. something like "dir/")
         self._files[b''] = node
         self._flags[b''] = b't'
 
     # Manifests outside the narrowspec should never be modified, so avoid
     # copying. This makes a noticeable difference when there are very many
     # directories outside the narrowspec. Also, it makes sense for the copy to
     # be of the same type as the original, which would not happen with the
     # super type's copy().
     def copy(self):
         return self
 
 
 class excludeddirmanifestctx(treemanifestctx):
     """context wrapper for excludeddir - see that docstring for rationale"""
 
     def __init__(self, nodeconstants, dir, node):
         self.nodeconstants = nodeconstants
         self._dir = dir
         self._node = node
 
     def read(self):
         return excludeddir(self.nodeconstants, self._dir, self._node)
 
     def readfast(self, shallow=False):
         # special version of readfast since we don't have underlying storage
         return self.read()
 
     def write(self, *args):
         raise error.ProgrammingError(
             b'attempt to write manifest from excluded dir %s' % self._dir
         )
 
 
 class excludedmanifestrevlog(manifestrevlog):
     """Stand-in for excluded treemanifest revlogs.
 
     When narrowing is active on a treemanifest repository, we'll have
     references to directories we can't see due to the revlog being
     skipped. This class exists to conform to the manifestrevlog
     interface for those directories and proactively prevent writes to
     outside the narrowspec.
     """
 
     def __init__(self, nodeconstants, dir):
         self.nodeconstants = nodeconstants
         self._dir = dir
 
     def __len__(self):
         raise error.ProgrammingError(
             b'attempt to get length of excluded dir %s' % self._dir
         )
 
     def rev(self, node):
         raise error.ProgrammingError(
             b'attempt to get rev from excluded dir %s' % self._dir
         )
 
     def linkrev(self, node):
         raise error.ProgrammingError(
             b'attempt to get linkrev from excluded dir %s' % self._dir
         )
 
     def node(self, rev):
         raise error.ProgrammingError(
             b'attempt to get node from excluded dir %s' % self._dir
         )
 
     def add(self, *args, **kwargs):
         # We should never write entries in dirlogs outside the narrow clone.
         # However, the method still gets called from writesubtree() in
         # _addtree(), so we need to handle it. We should possibly make that
         # avoid calling add() with a clean manifest (_dirty is always False
         # in excludeddir instances).
         pass

mercurial/revlog.py

@@ -1,4123 +1,4125 b''
 # revlog.py - storage back-end for mercurial
 # coding: utf8
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 
 import binascii
 import collections
 import contextlib
 import functools
 import io
 import os
 import struct
 import typing
 import weakref
 import zlib
 
 from typing import (
+    Iterable,
+    Iterator,
     Optional,
     Tuple,
 )
 
 # import stuff from node for others to import from revlog
 from .node import (
     bin,
     hex,
     nullrev,
     sha1nodeconstants,
     short,
     wdirrev,
 )
 from .i18n import _
 from .revlogutils.constants import (
     ALL_KINDS,
     CHANGELOGV2,
     COMP_MODE_DEFAULT,
     COMP_MODE_INLINE,
     COMP_MODE_PLAIN,
     DELTA_BASE_REUSE_NO,
     DELTA_BASE_REUSE_TRY,
     ENTRY_RANK,
     FEATURES_BY_VERSION,
     FLAG_GENERALDELTA,
     FLAG_INLINE_DATA,
     INDEX_HEADER,
     KIND_CHANGELOG,
     KIND_FILELOG,
     RANK_UNKNOWN,
     REVLOGV0,
     REVLOGV1,
     REVLOGV1_FLAGS,
     REVLOGV2,
     REVLOGV2_FLAGS,
     REVLOG_DEFAULT_FLAGS,
     REVLOG_DEFAULT_FORMAT,
     REVLOG_DEFAULT_VERSION,
     SUPPORTED_FLAGS,
 )
 from .revlogutils.flagutil import (
     REVIDX_DEFAULT_FLAGS,
     REVIDX_ELLIPSIS,
     REVIDX_EXTSTORED,
     REVIDX_FLAGS_ORDER,
     REVIDX_HASCOPIESINFO,
     REVIDX_ISCENSORED,
     REVIDX_RAWTEXT_CHANGING_FLAGS,
 )
 from .thirdparty import attr
 
 # Force pytype to use the non-vendored package
 if typing.TYPE_CHECKING:
     # noinspection PyPackageRequirements
     import attr
 
 from . import (
     ancestor,
     dagop,
     error,
     mdiff,
     policy,
     pycompat,
     revlogutils,
     templatefilters,
     util,
     vfs as vfsmod,
 )
 from .interfaces import (
     repository,
     util as interfaceutil,
 )
 from .revlogutils import (
     deltas as deltautil,
     docket as docketutil,
     flagutil,
     nodemap as nodemaputil,
     randomaccessfile,
     revlogv0,
     rewrite,
     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
 CHANGELOGV2
 FLAG_INLINE_DATA
 FLAG_GENERALDELTA
 REVLOG_DEFAULT_FLAGS
 REVLOG_DEFAULT_FORMAT
 REVLOG_DEFAULT_VERSION
 REVLOGV1_FLAGS
 REVLOGV2_FLAGS
 REVIDX_ISCENSORED
 REVIDX_ELLIPSIS
 REVIDX_HASCOPIESINFO
 REVIDX_EXTSTORED
 REVIDX_DEFAULT_FLAGS
 REVIDX_FLAGS_ORDER
 REVIDX_RAWTEXT_CHANGING_FLAGS
 
 parsers = policy.importmod('parsers')
 rustancestor = policy.importrust('ancestor')
 rustdagop = policy.importrust('dagop')
 rustrevlog = policy.importrust('revlog')
 
 # Aliased for performance.
 _zlibdecompress = zlib.decompress
 
 # max size of inline data embedded into a revlog
 _maxinline = 131072
 
 
 # Flag processors for REVIDX_ELLIPSIS.
 def ellipsisreadprocessor(rl, text):
     return text, False
 
 
 def ellipsiswriteprocessor(rl, text):
     return text, False
 
 
 def ellipsisrawprocessor(rl, text):
     return False
 
 
 ellipsisprocessor = (
     ellipsisreadprocessor,
     ellipsiswriteprocessor,
     ellipsisrawprocessor,
 )
 
 
 def _verify_revision(rl, skipflags, state, node):
     """Verify the integrity of the given revlog ``node`` while providing a hook
     point for extensions to influence the operation."""
     if skipflags:
         state[b'skipread'].add(node)
     else:
         # Side-effect: read content and verify hash.
         rl.revision(node)
 
 
 # True if a fast implementation for persistent-nodemap is available
 #
 # We also consider we have a "fast" implementation in "pure" python because
 # people using pure don't really have performance consideration (and a
 # wheelbarrow of other slowness source)
 HAS_FAST_PERSISTENT_NODEMAP = rustrevlog is not None or hasattr(
     parsers, 'BaseIndexObject'
 )
 
 
 @attr.s(slots=True)
 class RevLogRevisionDelta:
     node = attr.ib()
     p1node = attr.ib()
     p2node = attr.ib()
     basenode = attr.ib()
     flags = attr.ib()
     baserevisionsize = attr.ib()
     revision = attr.ib()
     delta = attr.ib()
     sidedata = attr.ib()
     protocol_flags = attr.ib()
     linknode = attr.ib(default=None)
 
 
 revlogrevisiondelta = interfaceutil.implementer(repository.irevisiondelta)(
     RevLogRevisionDelta
 )
 
 if typing.TYPE_CHECKING:
     revlogrevisiondelta = RevLogRevisionDelta
 
 
 @attr.s(frozen=True)
 class RevLogProblem:
     warning = attr.ib(default=None, type=Optional[bytes])
     error = attr.ib(default=None, type=Optional[bytes])
     node = attr.ib(default=None, type=Optional[bytes])
 
 
 revlogproblem = interfaceutil.implementer(repository.iverifyproblem)(
     RevLogProblem
 )
 
 if typing.TYPE_CHECKING:
     revlogproblem = RevLogProblem
 
 
 def parse_index_v1(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline)
     return index, cache
 
 
 def parse_index_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, format=REVLOGV2)
     return index, cache
 
 
 def parse_index_cl_v2(data, inline):
     # call the C implementation to parse the index data
     index, cache = parsers.parse_index2(data, inline, format=CHANGELOGV2)
     return index, cache
 
 
 if hasattr(parsers, 'parse_index_devel_nodemap'):
 
     def parse_index_v1_nodemap(data, inline):
         index, cache = parsers.parse_index_devel_nodemap(data, inline)
         return index, cache
 
 else:
     parse_index_v1_nodemap = None
 
 
 def parse_index_v1_rust(data, inline, default_header):
     cache = (0, data) if inline else None
     return rustrevlog.Index(data, default_header), cache
 
 
 # corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
 # signed integer)
 _maxentrysize = 0x7FFFFFFF
 
 FILE_TOO_SHORT_MSG = _(
     b'cannot read from revlog %s;'
     b'  expected %d bytes from offset %d, data size is %d'
 )
 
 hexdigits = b'0123456789abcdefABCDEF'
 
 
 class _Config:
     def copy(self):
         return self.__class__(**self.__dict__)
 
 
 @attr.s()
 class FeatureConfig(_Config):
     """Hold configuration values about the available revlog features"""
 
     # the default compression engine
     compression_engine = attr.ib(default=b'zlib')
     # compression engines options
     compression_engine_options = attr.ib(default=attr.Factory(dict))
 
     # can we use censor on this revlog
     censorable = attr.ib(default=False)
     # does this revlog use the "side data" feature
     has_side_data = attr.ib(default=False)
     # might remove rank configuration once the computation has no impact
     compute_rank = attr.ib(default=False)
     # parent order is supposed to be semantically irrelevant, so we
     # normally resort parents to ensure that the first parent is non-null,
     # if there is a non-null parent at all.
     # filelog abuses the parent order as flag to mark some instances of
     # meta-encoded files, so allow it to disable this behavior.
     canonical_parent_order = attr.ib(default=False)
     # can ellipsis commit be used
     enable_ellipsis = attr.ib(default=False)
 
     def copy(self):
         new = super().copy()
         new.compression_engine_options = self.compression_engine_options.copy()
         return new
 
 
 @attr.s()
 class DataConfig(_Config):
     """Hold configuration value about how the revlog data are read"""
 
     # should we try to open the "pending" version of the revlog
     try_pending = attr.ib(default=False)
     # should we try to open the "splitted" version of the revlog
     try_split = attr.ib(default=False)
     #  When True, indexfile should be opened with checkambig=True at writing,
     #  to avoid file stat ambiguity.
     check_ambig = attr.ib(default=False)
 
     # If true, use mmap instead of reading to deal with large index
     mmap_large_index = attr.ib(default=False)
     # how much data is large
     mmap_index_threshold = attr.ib(default=None)
     # How much data to read and cache into the raw revlog data cache.
     chunk_cache_size = attr.ib(default=65536)
 
     # The size of the uncompressed cache compared to the largest revision seen.
     uncompressed_cache_factor = attr.ib(default=None)
 
     # The number of chunk cached
     uncompressed_cache_count = attr.ib(default=None)
 
     # Allow sparse reading of the revlog data
     with_sparse_read = attr.ib(default=False)
     # minimal density of a sparse read chunk
     sr_density_threshold = attr.ib(default=0.50)
     # minimal size of data we skip when performing sparse read
     sr_min_gap_size = attr.ib(default=262144)
 
     # are delta encoded against arbitrary bases.
     generaldelta = attr.ib(default=False)
 
 
 @attr.s()
 class DeltaConfig(_Config):
     """Hold configuration value about how new delta are computed
 
     Some attributes are duplicated from DataConfig to help havign each object
     self contained.
     """
 
     # can delta be encoded against arbitrary bases.
     general_delta = attr.ib(default=False)
     # Allow sparse writing of the revlog data
     sparse_revlog = attr.ib(default=False)
     # maximum length of a delta chain
     max_chain_len = attr.ib(default=None)
     # Maximum distance between delta chain base start and end
     max_deltachain_span = attr.ib(default=-1)
     # If `upper_bound_comp` is not None, this is the expected maximal gain from
     # compression for the data content.
     upper_bound_comp = attr.ib(default=None)
     # Should we try a delta against both parent
     delta_both_parents = attr.ib(default=True)
     # Test delta base candidate group by chunk of this maximal size.
     candidate_group_chunk_size = attr.ib(default=0)
     # Should we display debug information about delta computation
     debug_delta = attr.ib(default=False)
     # trust incoming delta by default
     lazy_delta = attr.ib(default=True)
     # trust the base of incoming delta by default
     lazy_delta_base = attr.ib(default=False)
 
 
 class _InnerRevlog:
     """An inner layer of the revlog object
 
     That layer exist to be able to delegate some operation to Rust, its
     boundaries are arbitrary and based on what we can delegate to Rust.
     """
 
     opener: vfsmod.vfs
 
     def __init__(
         self,
         opener: vfsmod.vfs,
         index,
         index_file,
         data_file,
         sidedata_file,
         inline,
         data_config,
         delta_config,
         feature_config,
         chunk_cache,
         default_compression_header,
     ):
         self.opener = opener
         self.index = index
 
         self.index_file = index_file
         self.data_file = data_file
         self.sidedata_file = sidedata_file
         self.inline = inline
         self.data_config = data_config
         self.delta_config = delta_config
         self.feature_config = feature_config
 
         # used during diverted write.
         self._orig_index_file = None
 
         self._default_compression_header = default_compression_header
 
         # index
 
         # 3-tuple of file handles being used for active writing.
         self._writinghandles = None
 
         self._segmentfile = randomaccessfile.randomaccessfile(
             self.opener,
             (self.index_file if self.inline else self.data_file),
             self.data_config.chunk_cache_size,
             chunk_cache,
         )
         self._segmentfile_sidedata = randomaccessfile.randomaccessfile(
             self.opener,
             self.sidedata_file,
             self.data_config.chunk_cache_size,
         )
 
         # revlog header -> revlog compressor
         self._decompressors = {}
         # 3-tuple of (node, rev, text) for a raw revision.
         self._revisioncache = None
 
         # cache some uncompressed chunks
         # rev → uncompressed_chunk
         #
         # the max cost is dynamically updated to be proportionnal to the
         # size of revision we actually encounter.
         self._uncompressed_chunk_cache = None
         if self.data_config.uncompressed_cache_factor is not None:
             self._uncompressed_chunk_cache = util.lrucachedict(
                 self.data_config.uncompressed_cache_count,
                 maxcost=65536,  # some arbitrary initial value
             )
 
         self._delay_buffer = None
 
     def __len__(self):
         return len(self.index)
 
     def clear_cache(self):
         assert not self.is_delaying
         self._revisioncache = None
         if self._uncompressed_chunk_cache is not None:
             self._uncompressed_chunk_cache.clear()
         self._segmentfile.clear_cache()
         self._segmentfile_sidedata.clear_cache()
 
     @property
     def canonical_index_file(self):
         if self._orig_index_file is not None:
             return self._orig_index_file
         return self.index_file
 
     @property
     def is_delaying(self):
         """is the revlog is currently delaying the visibility of written data?
 
         The delaying mechanism can be either in-memory or written on disk in a
         side-file."""
         return (self._delay_buffer is not None) or (
             self._orig_index_file is not None
         )
 
     # Derived from index values.
 
     def start(self, rev):
         """the offset of the data chunk for this revision"""
         return int(self.index[rev][0] >> 16)
 
     def length(self, rev):
         """the length of the data chunk for this revision"""
         return self.index[rev][1]
 
     def end(self, rev):
         """the end of the data chunk for this revision"""
         return self.start(rev) + self.length(rev)
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self.delta_config.general_delta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot"""
         if not self.delta_config.sparse_revlog:
             return self.deltaparent(rev) == nullrev
         elif hasattr(self.index, '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]
         while self.length(p1) == 0:
             b = self.deltaparent(p1)
             if b == p1:
                 break
             p1 = b
         p2 = entry[6]
         while self.length(p2) == 0:
             b = self.deltaparent(p2)
             if b == p2:
                 break
             p2 = b
         if base == p1 or base == p2:
             return False
         return self.issnapshot(base)
 
     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.
         """
         generaldelta = self.delta_config.general_delta
         # Try C implementation.
         try:
             return self.index.deltachain(rev, stoprev, generaldelta)
         except AttributeError:
             pass
 
         chain = []
 
         # Alias to prevent attribute lookup in tight loop.
         index = self.index
 
         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
 
     @util.propertycache
     def _compressor(self):
         engine = util.compengines[self.feature_config.compression_engine]
         return engine.revlogcompressor(
             self.feature_config.compression_engine_options
         )
 
     @util.propertycache
     def _decompressor(self):
         """the default decompressor"""
         if self._default_compression_header is None:
             return None
         t = self._default_compression_header
         c = self._get_decompressor(t)
         return c.decompress
 
     def _get_decompressor(self, t: bytes):
         try:
             compressor = self._decompressors[t]
         except KeyError:
             try:
                 engine = util.compengines.forrevlogheader(t)
                 compressor = engine.revlogcompressor(
                     self.feature_config.compression_engine_options
                 )
                 self._decompressors[t] = compressor
             except KeyError:
                 raise error.RevlogError(
                     _(b'unknown compression type %s') % binascii.hexlify(t)
                 )
         return compressor
 
     def compress(self, data: bytes) -> Tuple[bytes, bytes]:
         """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: bytes):
         """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)
 
         compressor = self._get_decompressor(t)
 
         return compressor.decompress(data)
 
     @contextlib.contextmanager
     def reading(self):
         """Context manager that keeps data and sidedata files open for reading"""
         if len(self.index) == 0:
             yield  # nothing to be read
         elif self._delay_buffer is not None and self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         else:
             with self._segmentfile.reading():
                 with self._segmentfile_sidedata.reading():
                     yield
 
     @property
     def is_writing(self):
         """True is a writing context is open"""
         return self._writinghandles is not None
 
     @property
     def is_open(self):
         """True if any file handle is being held
 
         Used for assert and debug in the python code"""
         return self._segmentfile.is_open or self._segmentfile_sidedata.is_open
 
     @contextlib.contextmanager
     def writing(self, transaction, data_end=None, sidedata_end=None):
         """Open the revlog files for writing
 
         Add content to a revlog should be done within such context.
         """
         if self.is_writing:
             yield
         else:
             ifh = dfh = sdfh = None
             try:
                 r = len(self.index)
                 # opening the data file.
                 dsize = 0
                 if r:
                     dsize = self.end(r - 1)
                 dfh = None
                 if not self.inline:
                     try:
                         dfh = self.opener(self.data_file, mode=b"r+")
                         if data_end is None:
                             dfh.seek(0, os.SEEK_END)
                         else:
                             dfh.seek(data_end, os.SEEK_SET)
                     except FileNotFoundError:
                         dfh = self.opener(self.data_file, mode=b"w+")
                     transaction.add(self.data_file, dsize)
                 if self.sidedata_file is not None:
                     assert sidedata_end is not None
                     # revlog-v2 does not inline, help Pytype
                     assert dfh is not None
                     try:
                         sdfh = self.opener(self.sidedata_file, mode=b"r+")
                         dfh.seek(sidedata_end, os.SEEK_SET)
                     except FileNotFoundError:
                         sdfh = self.opener(self.sidedata_file, mode=b"w+")
                     transaction.add(self.sidedata_file, sidedata_end)
 
                 # opening the index file.
                 isize = r * self.index.entry_size
                 ifh = self.__index_write_fp()
                 if self.inline:
                     transaction.add(self.index_file, dsize + isize)
                 else:
                     transaction.add(self.index_file, isize)
                 # exposing all file handle for writing.
                 self._writinghandles = (ifh, dfh, sdfh)
                 self._segmentfile.writing_handle = ifh if self.inline else dfh
                 self._segmentfile_sidedata.writing_handle = sdfh
                 yield
             finally:
                 self._writinghandles = None
                 self._segmentfile.writing_handle = None
                 self._segmentfile_sidedata.writing_handle = None
                 if dfh is not None:
                     dfh.close()
                 if sdfh is not None:
                     sdfh.close()
                 # closing the index file last to avoid exposing referent to
                 # potential unflushed data content.
                 if ifh is not None:
                     ifh.close()
 
     def __index_write_fp(self, index_end=None):
         """internal method to open the index file for writing
 
         You should not use this directly and use `_writing` instead
         """
         try:
             if self._delay_buffer is None:
                 f = self.opener(
                     self.index_file,
                     mode=b"r+",
                     checkambig=self.data_config.check_ambig,
                 )
             else:
                 # check_ambig affect we way we open file for writing, however
                 # here, we do not actually open a file for writting as write
                 # will appened to a delay_buffer. So check_ambig is not
                 # meaningful and unneeded here.
                 f = randomaccessfile.appender(
                     self.opener, self.index_file, b"r+", self._delay_buffer
                 )
             if index_end is None:
                 f.seek(0, os.SEEK_END)
             else:
                 f.seek(index_end, os.SEEK_SET)
             return f
         except FileNotFoundError:
             if self._delay_buffer is None:
                 return self.opener(
                     self.index_file,
                     mode=b"w+",
                     checkambig=self.data_config.check_ambig,
                 )
             else:
                 return randomaccessfile.appender(
                     self.opener, self.index_file, b"w+", self._delay_buffer
                 )
 
     def __index_new_fp(self):
         """internal method to create a new index file for writing
 
         You should not use this unless you are upgrading from inline revlog
         """
         return self.opener(
             self.index_file,
             mode=b"w",
             checkambig=self.data_config.check_ambig,
         )
 
     def split_inline(self, tr, header, new_index_file_path=None):
         """split the data of an inline revlog into an index and a data file"""
         assert self._delay_buffer is None
         existing_handles = False
         if self._writinghandles is not None:
             existing_handles = True
             fp = self._writinghandles[0]
             fp.flush()
             fp.close()
             # We can't use the cached file handle after close(). So prevent
             # its usage.
             self._writinghandles = None
             self._segmentfile.writing_handle = None
             # No need to deal with sidedata writing handle as it is only
             # relevant with revlog-v2 which is never inline, not reaching
             # this code
 
         new_dfh = self.opener(self.data_file, mode=b"w+")
         new_dfh.truncate(0)  # drop any potentially existing data
         try:
             with self.reading():
                 for r in range(len(self.index)):
                     new_dfh.write(self.get_segment_for_revs(r, r)[1])
                 new_dfh.flush()
 
             if new_index_file_path is not None:
                 self.index_file = new_index_file_path
             with self.__index_new_fp() as fp:
                 self.inline = False
                 for i in range(len(self.index)):
                     e = self.index.entry_binary(i)
                     if i == 0:
                         packed_header = self.index.pack_header(header)
                         e = packed_header + e
                     fp.write(e)
 
                 # If we don't use side-write, the temp file replace the real
                 # index when we exit the context manager
 
             self._segmentfile = randomaccessfile.randomaccessfile(
                 self.opener,
                 self.data_file,
                 self.data_config.chunk_cache_size,
             )
 
             if existing_handles:
                 # switched from inline to conventional reopen the index
                 ifh = self.__index_write_fp()
                 self._writinghandles = (ifh, new_dfh, None)
                 self._segmentfile.writing_handle = new_dfh
                 new_dfh = None
                 # No need to deal with sidedata writing handle as it is only
                 # relevant with revlog-v2 which is never inline, not reaching
                 # this code
         finally:
             if new_dfh is not None:
                 new_dfh.close()
         return self.index_file
 
     def get_segment_for_revs(self, startrev, endrev):
         """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.
 
         API: we should consider making this a private part of the InnerRevlog
         at some point.
         """
         # Inlined self.start(startrev) & self.end(endrev) for perf reasons
         # (functions are expensive).
         index = self.index
         istart = index[startrev]
         start = int(istart[0] >> 16)
         if startrev == endrev:
             end = start + istart[1]
         else:
             iend = index[endrev]
             end = int(iend[0] >> 16) + iend[1]
 
         if self.inline:
             start += (startrev + 1) * self.index.entry_size
             end += (endrev + 1) * self.index.entry_size
         length = end - start
 
         return start, self._segmentfile.read_chunk(start, length)
 
     def _chunk(self, rev):
         """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.
         """
         if self._uncompressed_chunk_cache is not None:
             uncomp = self._uncompressed_chunk_cache.get(rev)
             if uncomp is not None:
                 return uncomp
 
         compression_mode = self.index[rev][10]
         data = self.get_segment_for_revs(rev, rev)[1]
         if compression_mode == COMP_MODE_PLAIN:
             uncomp = data
         elif compression_mode == COMP_MODE_DEFAULT:
             uncomp = self._decompressor(data)
         elif compression_mode == COMP_MODE_INLINE:
             uncomp = self.decompress(data)
         else:
             msg = b'unknown compression mode %d'
             msg %= compression_mode
             raise error.RevlogError(msg)
         if self._uncompressed_chunk_cache is not None:
             self._uncompressed_chunk_cache.insert(rev, uncomp, cost=len(uncomp))
         return uncomp
 
     def _chunks(self, revs, targetsize=None):
         """Obtain decompressed chunks for the specified revisions.
 
         Accepts an iterable of numeric revisions that are assumed to be in
         ascending order. Also accepts an optional already-open file handle
         to be used for reading. If used, the seek position of the file will
         not be preserved.
 
         This function is similar to calling ``self._chunk()`` multiple times,
         but is faster.
 
         Returns a list with decompressed data for each requested revision.
         """
         if not revs:
             return []
         start = self.start
         length = self.length
         inline = self.inline
         iosize = self.index.entry_size
         buffer = util.buffer
 
         fetched_revs = []
         fadd = fetched_revs.append
 
         chunks = []
         ladd = chunks.append
 
         if self._uncompressed_chunk_cache is None:
             fetched_revs = revs
         else:
             for rev in revs:
                 cached_value = self._uncompressed_chunk_cache.get(rev)
                 if cached_value is None:
                     fadd(rev)
                 else:
                     ladd((rev, cached_value))
 
         if not fetched_revs:
             slicedchunks = ()
         elif not self.data_config.with_sparse_read:
             slicedchunks = (fetched_revs,)
         else:
             slicedchunks = deltautil.slicechunk(
                 self,
                 fetched_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.get_segment_for_revs(firstrev, lastrev)
             except OverflowError:
                 # issue4215 - we can't cache a run of chunks greater than
                 # 2G on Windows
                 for rev in revschunk:
                     ladd((rev, self._chunk(rev)))
 
             decomp = self.decompress
             # self._decompressor might be None, but will not be used in that case
             def_decomp = self._decompressor
             for rev in revschunk:
                 chunkstart = start(rev)
                 if inline:
                     chunkstart += (rev + 1) * iosize
                 chunklength = length(rev)
                 comp_mode = self.index[rev][10]
                 c = buffer(data, chunkstart - offset, chunklength)
                 if comp_mode == COMP_MODE_PLAIN:
                     c = c
                 elif comp_mode == COMP_MODE_INLINE:
                     c = decomp(c)
                 elif comp_mode == COMP_MODE_DEFAULT:
                     c = def_decomp(c)
                 else:
                     msg = b'unknown compression mode %d'
                     msg %= comp_mode
                     raise error.RevlogError(msg)
                 ladd((rev, c))
                 if self._uncompressed_chunk_cache is not None:
                     self._uncompressed_chunk_cache.insert(rev, c, len(c))
 
         chunks.sort()
         return [x[1] for x in chunks]
 
     def raw_text(self, node, rev):
         """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:
             cachedrev = self._revisioncache[1]
 
         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._inner._revisioncache after validating the text
         self._revisioncache = None
 
         targetsize = None
         rawsize = self.index[rev][2]
         if 0 <= rawsize:
             targetsize = 4 * rawsize
 
         if self._uncompressed_chunk_cache is not None:
             # dynamically update the uncompressed_chunk_cache size to the
             # largest revision we saw in this revlog.
             factor = self.data_config.uncompressed_cache_factor
             candidate_size = rawsize * factor
             if candidate_size > self._uncompressed_chunk_cache.maxcost:
                 self._uncompressed_chunk_cache.maxcost = candidate_size
 
         bins = self._chunks(chain, targetsize=targetsize)
         if basetext is None:
             basetext = bytes(bins[0])
             bins = bins[1:]
 
         rawtext = mdiff.patches(basetext, bins)
         del basetext  # let us have a chance to free memory early
         return (rev, rawtext, False)
 
     def sidedata(self, rev, sidedata_end):
         """Return the sidedata for a given revision number."""
         index_entry = self.index[rev]
         sidedata_offset = index_entry[8]
         sidedata_size = index_entry[9]
 
         if self.inline:
             sidedata_offset += self.index.entry_size * (1 + rev)
         if sidedata_size == 0:
             return {}
 
         if sidedata_end < sidedata_offset + sidedata_size:
             filename = self.sidedata_file
             end = sidedata_end
             offset = sidedata_offset
             length = sidedata_size
             m = FILE_TOO_SHORT_MSG % (filename, length, offset, end)
             raise error.RevlogError(m)
 
         comp_segment = self._segmentfile_sidedata.read_chunk(
             sidedata_offset, sidedata_size
         )
 
         comp = self.index[rev][11]
         if comp == COMP_MODE_PLAIN:
             segment = comp_segment
         elif comp == COMP_MODE_DEFAULT:
             segment = self._decompressor(comp_segment)
         elif comp == COMP_MODE_INLINE:
             segment = self.decompress(comp_segment)
         else:
             msg = b'unknown compression mode %d'
             msg %= comp
             raise error.RevlogError(msg)
 
         sidedata = sidedatautil.deserialize_sidedata(segment)
         return sidedata
 
     def write_entry(
         self,
         transaction,
         entry,
         data,
         link,
         offset,
         sidedata,
         sidedata_offset,
         index_end,
         data_end,
         sidedata_end,
     ):
         # 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.
         if self._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
         ifh, dfh, sdfh = self._writinghandles
         if index_end is None:
             ifh.seek(0, os.SEEK_END)
         else:
             ifh.seek(index_end, os.SEEK_SET)
         if dfh:
             if data_end is None:
                 dfh.seek(0, os.SEEK_END)
             else:
                 dfh.seek(data_end, os.SEEK_SET)
         if sdfh:
             sdfh.seek(sidedata_end, os.SEEK_SET)
 
         curr = len(self.index) - 1
         if not self.inline:
             transaction.add(self.data_file, offset)
             if self.sidedata_file:
                 transaction.add(self.sidedata_file, sidedata_offset)
             transaction.add(self.canonical_index_file, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             if sidedata:
                 sdfh.write(sidedata)
             if self._delay_buffer is None:
                 ifh.write(entry)
             else:
                 self._delay_buffer.append(entry)
         elif self._delay_buffer is not None:
             msg = b'invalid delayed write on inline revlog'
             raise error.ProgrammingError(msg)
         else:
             offset += curr * self.index.entry_size
             transaction.add(self.canonical_index_file, offset)
             assert not sidedata
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
         return (
             ifh.tell(),
             dfh.tell() if dfh else None,
             sdfh.tell() if sdfh else None,
         )
 
     def _divert_index(self):
         index_file = self.index_file
         # when we encounter a legacy inline-changelog, split it. However it is
         # important to use the expected filename for pending content
         # (<radix>.a) otherwise hooks won't be seeing the content of the
         # pending transaction.
         if index_file.endswith(b'.s'):
             index_file = self.index_file[:-2]
         return index_file + b'.a'
 
     def delay(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         if self._delay_buffer is not None or self._orig_index_file is not None:
             # delay or divert already in place
             return None
         elif len(self.index) == 0:
             self._orig_index_file = self.index_file
             self.index_file = self._divert_index()
             assert self._orig_index_file is not None
             assert self.index_file is not None
             if self.opener.exists(self.index_file):
                 self.opener.unlink(self.index_file)
             return self.index_file
         else:
             self._delay_buffer = []
             return None
 
     def write_pending(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
         if self._orig_index_file is not None:
             return None, True
         any_pending = False
         pending_index_file = self._divert_index()
         if self.opener.exists(pending_index_file):
             self.opener.unlink(pending_index_file)
         util.copyfile(
             self.opener.join(self.index_file),
             self.opener.join(pending_index_file),
         )
         if self._delay_buffer:
             with self.opener(pending_index_file, b'r+') as ifh:
                 ifh.seek(0, os.SEEK_END)
                 ifh.write(b"".join(self._delay_buffer))
             any_pending = True
         self._delay_buffer = None
         self._orig_index_file = self.index_file
         self.index_file = pending_index_file
         return self.index_file, any_pending
 
     def finalize_pending(self):
         assert not self.is_open
         if self.inline:
             msg = "revlog with delayed write should not be inline"
             raise error.ProgrammingError(msg)
 
         delay = self._delay_buffer is not None
         divert = self._orig_index_file is not None
 
         if delay and divert:
             assert False, "unreachable"
         elif delay:
             if self._delay_buffer:
                 with self.opener(self.index_file, b'r+') as ifh:
                     ifh.seek(0, os.SEEK_END)
                     ifh.write(b"".join(self._delay_buffer))
             self._delay_buffer = None
         elif divert:
             if self.opener.exists(self.index_file):
                 self.opener.rename(
                     self.index_file,
                     self._orig_index_file,
                     checkambig=True,
                 )
             self.index_file = self._orig_index_file
             self._orig_index_file = None
         else:
             msg = b"not delay or divert found on this revlog"
             raise error.ProgrammingError(msg)
         return self.canonical_index_file
 
 
 class revlog:
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
 
     If checkambig, indexfile is opened with checkambig=True at
     writing, to avoid file stat ambiguity.
 
     If mmaplargeindex is True, and an mmapindexthreshold is set, the
     index will be mmapped rather than read if it is larger than the
     configured threshold.
 
     If censorable is True, the revlog can have censored revisions.
 
     If `upperboundcomp` is not None, this is the expected maximal gain from
     compression for the data content.
 
     `concurrencychecker` is an optional function that receives 3 arguments: a
     file handle, a filename, and an expected position. It should check whether
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
 
     See mercurial/revlogutils/contants.py for details about the content of an
     index entry.
     """
 
     _flagserrorclass = error.RevlogError
 
     opener: vfsmod.vfs
 
     @staticmethod
     def is_inline_index(header_bytes):
         """Determine if a revlog is inline from the initial bytes of the index"""
         if len(header_bytes) == 0:
             return True
 
         header = INDEX_HEADER.unpack(header_bytes)[0]
 
         _format_flags = header & ~0xFFFF
         _format_version = header & 0xFFFF
 
         features = FEATURES_BY_VERSION[_format_version]
         return features[b'inline'](_format_flags)
 
     _docket_file: Optional[bytes]
 
     def __init__(
         self,
         opener: vfsmod.vfs,
         target,
         radix,
         postfix=None,  # only exist for `tmpcensored` now
         checkambig=False,
         mmaplargeindex=False,
         censorable=False,
         upperboundcomp=None,
         persistentnodemap=False,
         concurrencychecker=None,
         trypending=False,
         try_split=False,
         canonical_parent_order=True,
         data_config=None,
         delta_config=None,
         feature_config=None,
         may_inline=True,  # may inline new revlog
     ):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
 
         `target`: a (KIND, ID) tuple that identify the content stored in
         this revlog. It help the rest of the code to understand what the revlog
         is about without having to resort to heuristic and index filename
         analysis. Note: that this must be reliably be set by normal code, but
         that test, debug, or performance measurement code might not set this to
         accurate value.
         """
 
         self.radix = radix
 
         self._docket_file = None
         self._indexfile = None
         self._datafile = None
         self._sidedatafile = None
         self._nodemap_file = None
         self.postfix = postfix
         self._trypending = trypending
         self._try_split = try_split
         self._may_inline = may_inline
         self.opener = opener
         if persistentnodemap:
             self._nodemap_file = nodemaputil.get_nodemap_file(self)
 
         assert target[0] in ALL_KINDS
         assert len(target) == 2
         self.target = target
         if feature_config is not None:
             self.feature_config = feature_config.copy()
         elif b'feature-config' in self.opener.options:
             self.feature_config = self.opener.options[b'feature-config'].copy()
         else:
             self.feature_config = FeatureConfig()
         self.feature_config.censorable = censorable
         self.feature_config.canonical_parent_order = canonical_parent_order
         if data_config is not None:
             self.data_config = data_config.copy()
         elif b'data-config' in self.opener.options:
             self.data_config = self.opener.options[b'data-config'].copy()
         else:
             self.data_config = DataConfig()
         self.data_config.check_ambig = checkambig
         self.data_config.mmap_large_index = mmaplargeindex
         if delta_config is not None:
             self.delta_config = delta_config.copy()
         elif b'delta-config' in self.opener.options:
             self.delta_config = self.opener.options[b'delta-config'].copy()
         else:
             self.delta_config = DeltaConfig()
         self.delta_config.upper_bound_comp = upperboundcomp
 
         # Maps rev to chain base rev.
         self._chainbasecache = util.lrucachedict(100)
 
         self.index = None
         self._docket = None
         self._nodemap_docket = None
         # Mapping of partial identifiers to full nodes.
         self._pcache = {}
 
         # other optionnals features
 
         # Make copy of flag processors so each revlog instance can support
         # custom flags.
         self._flagprocessors = dict(flagutil.flagprocessors)
         # prevent nesting of addgroup
         self._adding_group = None
 
         chunk_cache = self._loadindex()
         self._load_inner(chunk_cache)
         self._concurrencychecker = concurrencychecker
 
     def _init_opts(self):
         """process options (from above/config) to setup associated default revlog mode
 
         These values might be affected when actually reading on disk information.
 
         The relevant values are returned for use in _loadindex().
 
         * newversionflags:
             version header to use if we need to create a new revlog
 
         * mmapindexthreshold:
             minimal index size for start to use mmap
 
         * force_nodemap:
             force the usage of a "development" version of the nodemap code
         """
         opts = self.opener.options
 
         if b'changelogv2' in opts and self.revlog_kind == KIND_CHANGELOG:
             new_header = CHANGELOGV2
             compute_rank = opts.get(b'changelogv2.compute-rank', True)
             self.feature_config.compute_rank = compute_rank
         elif b'revlogv2' in opts:
             new_header = REVLOGV2
         elif b'revlogv1' in opts:
             new_header = REVLOGV1
             if self._may_inline:
                 new_header |= FLAG_INLINE_DATA
             if b'generaldelta' in opts:
                 new_header |= FLAG_GENERALDELTA
         elif b'revlogv0' in self.opener.options:
             new_header = REVLOGV0
         else:
             new_header = REVLOG_DEFAULT_VERSION
 
         mmapindexthreshold = None
         if self.data_config.mmap_large_index:
             mmapindexthreshold = self.data_config.mmap_index_threshold
         if self.feature_config.enable_ellipsis:
             self._flagprocessors[REVIDX_ELLIPSIS] = ellipsisprocessor
 
         # revlog v0 doesn't have flag processors
         for flag, processor in opts.get(b'flagprocessors', {}).items():
             flagutil.insertflagprocessor(flag, processor, self._flagprocessors)
 
         chunk_cache_size = self.data_config.chunk_cache_size
         if chunk_cache_size <= 0:
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not greater than 0')
                 % chunk_cache_size
             )
         elif chunk_cache_size & (chunk_cache_size - 1):
             raise error.RevlogError(
                 _(b'revlog chunk cache size %r is not a power of 2')
                 % chunk_cache_size
             )
         force_nodemap = opts.get(b'devel-force-nodemap', False)
         return new_header, mmapindexthreshold, force_nodemap
 
     def _get_data(self, filepath, mmap_threshold, size=None):
         """return a file content with or without mmap
 
         If the file is missing return the empty string"""
         try:
             with self.opener(filepath) as fp:
                 if mmap_threshold is not None:
                     file_size = self.opener.fstat(fp).st_size
                     if (
                         file_size >= mmap_threshold
                         and self.opener.is_mmap_safe(filepath)
                     ):
                         if size is not None:
                             # avoid potentiel mmap crash
                             size = min(file_size, size)
                         # TODO: should .close() to release resources without
                         # relying on Python GC
                         if size is None:
                             return util.buffer(util.mmapread(fp))
                         else:
                             return util.buffer(util.mmapread(fp, size))
                 if size is None:
                     return fp.read()
                 else:
                     return fp.read(size)
         except FileNotFoundError:
             return b''
 
     def get_streams(self, max_linkrev, force_inline=False):
         """return a list of streams that represent this revlog
 
         This is used by stream-clone to do bytes to bytes copies of a repository.
 
         This streams data for all revisions that refer to a changelog revision up
         to `max_linkrev`.
 
         If `force_inline` is set, it enforces that the stream will represent an inline revlog.
 
         It returns is a list of three-tuple:
 
             [
                 (filename, bytes_stream, stream_size),
                 …
             ]
         """
         n = len(self)
         index = self.index
         while n > 0:
             linkrev = index[n - 1][4]
             if linkrev < max_linkrev:
                 break
             # note: this loop will rarely go through multiple iterations, since
             # it only traverses commits created during the current streaming
             # pull operation.
             #
             # If this become a problem, using a binary search should cap the
             # runtime of this.
             n = n - 1
         if n == 0:
             # no data to send
             return []
         index_size = n * index.entry_size
         data_size = self.end(n - 1)
 
         # XXX we might have been split (or stripped) since the object
         # initialization, We need to close this race too, but having a way to
         # pre-open the file we feed to the revlog and never closing them before
         # we are done streaming.
 
         if self._inline:
 
             def get_stream():
                 with self.opener(self._indexfile, mode=b"r") as fp:
                     yield None
                     size = index_size + data_size
                     if size <= 65536:
                         yield fp.read(size)
                     else:
                         yield from util.filechunkiter(fp, limit=size)
 
             inline_stream = get_stream()
             next(inline_stream)
             return [
                 (self._indexfile, inline_stream, index_size + data_size),
             ]
         elif force_inline:
 
             def get_stream():
                 with self.reading():
                     yield None
 
                     for rev in range(n):
                         idx = self.index.entry_binary(rev)
                         if rev == 0 and self._docket is None:
                             # re-inject the inline flag
                             header = self._format_flags
                             header |= self._format_version
                             header |= FLAG_INLINE_DATA
                             header = self.index.pack_header(header)
                             idx = header + idx
                         yield idx
                         yield self._inner.get_segment_for_revs(rev, rev)[1]
 
             inline_stream = get_stream()
             next(inline_stream)
             return [
                 (self._indexfile, inline_stream, index_size + data_size),
             ]
         else:
 
             def get_index_stream():
                 with self.opener(self._indexfile, mode=b"r") as fp:
                     yield None
                     if index_size <= 65536:
                         yield fp.read(index_size)
                     else:
                         yield from util.filechunkiter(fp, limit=index_size)
 
             def get_data_stream():
                 with self._datafp() as fp:
                     yield None
                     if data_size <= 65536:
                         yield fp.read(data_size)
                     else:
                         yield from util.filechunkiter(fp, limit=data_size)
 
             index_stream = get_index_stream()
             next(index_stream)
             data_stream = get_data_stream()
             next(data_stream)
             return [
                 (self._datafile, data_stream, data_size),
                 (self._indexfile, index_stream, index_size),
             ]
 
     def _loadindex(self, docket=None):
         new_header, mmapindexthreshold, force_nodemap = self._init_opts()
 
         if self.postfix is not None:
             entry_point = b'%s.i.%s' % (self.radix, self.postfix)
         elif self._trypending and self.opener.exists(b'%s.i.a' % self.radix):
             entry_point = b'%s.i.a' % self.radix
         elif self._try_split and self.opener.exists(self._split_index_file):
             entry_point = self._split_index_file
         else:
             entry_point = b'%s.i' % self.radix
 
         if docket is not None:
             self._docket = docket
             self._docket_file = entry_point
         else:
             self._initempty = True
             entry_data = self._get_data(entry_point, mmapindexthreshold)
             if len(entry_data) > 0:
                 header = INDEX_HEADER.unpack(entry_data[:4])[0]
                 self._initempty = False
             else:
                 header = new_header
 
             self._format_flags = header & ~0xFFFF
             self._format_version = header & 0xFFFF
 
             supported_flags = SUPPORTED_FLAGS.get(self._format_version)
             if supported_flags is None:
                 msg = _(b'unknown version (%d) in revlog %s')
                 msg %= (self._format_version, self.display_id)
                 raise error.RevlogError(msg)
             elif self._format_flags & ~supported_flags:
                 msg = _(b'unknown flags (%#04x) in version %d revlog %s')
                 display_flag = self._format_flags >> 16
                 msg %= (display_flag, self._format_version, self.display_id)
                 raise error.RevlogError(msg)
 
             features = FEATURES_BY_VERSION[self._format_version]
             self._inline = features[b'inline'](self._format_flags)
             self.delta_config.general_delta = features[b'generaldelta'](
                 self._format_flags
             )
             self.feature_config.has_side_data = features[b'sidedata']
 
             if not features[b'docket']:
                 self._indexfile = entry_point
                 index_data = entry_data
             else:
                 self._docket_file = entry_point
                 if self._initempty:
                     self._docket = docketutil.default_docket(self, header)
                 else:
                     self._docket = docketutil.parse_docket(
                         self, entry_data, use_pending=self._trypending
                     )
 
         if self._docket is not None:
             self._indexfile = self._docket.index_filepath()
             index_data = b''
             index_size = self._docket.index_end
             if index_size > 0:
                 index_data = self._get_data(
                     self._indexfile, mmapindexthreshold, size=index_size
                 )
                 if len(index_data) < index_size:
                     msg = _(b'too few index data for %s: got %d, expected %d')
                     msg %= (self.display_id, len(index_data), index_size)
                     raise error.RevlogError(msg)
 
             self._inline = False
             # generaldelta implied by version 2 revlogs.
             self.delta_config.general_delta = True
             # the logic for persistent nodemap will be dealt with within the
             # main docket, so disable it for now.
             self._nodemap_file = None
 
         if self._docket is not None:
             self._datafile = self._docket.data_filepath()
             self._sidedatafile = self._docket.sidedata_filepath()
         elif self.postfix is None:
             self._datafile = b'%s.d' % self.radix
         else:
             self._datafile = b'%s.d.%s' % (self.radix, self.postfix)
 
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # sparse-revlog can't be on without general-delta (issue6056)
         if not self.delta_config.general_delta:
             self.delta_config.sparse_revlog = False
 
         self._storedeltachains = True
 
         devel_nodemap = (
             self._nodemap_file
             and force_nodemap
             and parse_index_v1_nodemap is not None
         )
 
         use_rust_index = False
         if rustrevlog is not None and self._nodemap_file is not None:
             # we would like to use the rust_index in all case, especially
             # because it is necessary for AncestorsIterator and LazyAncestors
             # since the 6.7 cycle.
             #
             # However, the performance impact of inconditionnaly building the
             # nodemap is currently a problem for non-persistent nodemap
             # repository.
             use_rust_index = True
 
         self._parse_index = parse_index_v1
         if self._format_version == REVLOGV0:
             self._parse_index = revlogv0.parse_index_v0
         elif self._format_version == REVLOGV2:
             self._parse_index = parse_index_v2
         elif self._format_version == CHANGELOGV2:
             self._parse_index = parse_index_cl_v2
         elif devel_nodemap:
             self._parse_index = parse_index_v1_nodemap
         elif use_rust_index:
             self._parse_index = functools.partial(
                 parse_index_v1_rust, default_header=new_header
             )
         try:
             d = self._parse_index(index_data, self._inline)
             index, chunkcache = d
             use_nodemap = (
                 not self._inline
                 and self._nodemap_file is not None
                 and hasattr(index, 'update_nodemap_data')
             )
             if use_nodemap:
                 nodemap_data = nodemaputil.persisted_data(self)
                 if nodemap_data is not None:
                     docket = nodemap_data[0]
                     if (
                         len(d[0]) > docket.tip_rev
                         and d[0][docket.tip_rev][7] == docket.tip_node
                     ):
                         # no changelog tampering
                         self._nodemap_docket = docket
                         index.update_nodemap_data(*nodemap_data)
         except (ValueError, IndexError):
             raise error.RevlogError(
                 _(b"index %s is corrupted") % self.display_id
             )
         self.index = index
         # revnum -> (chain-length, sum-delta-length)
         self._chaininfocache = util.lrucachedict(500)
 
         return chunkcache
 
     def _load_inner(self, chunk_cache):
         if self._docket is None:
             default_compression_header = None
         else:
             default_compression_header = self._docket.default_compression_header
 
         self._inner = _InnerRevlog(
             opener=self.opener,
             index=self.index,
             index_file=self._indexfile,
             data_file=self._datafile,
             sidedata_file=self._sidedatafile,
             inline=self._inline,
             data_config=self.data_config,
             delta_config=self.delta_config,
             feature_config=self.feature_config,
             chunk_cache=chunk_cache,
             default_compression_header=default_compression_header,
         )
 
     def get_revlog(self):
         """simple function to mirror API of other not-really-revlog API"""
         return self
 
     @util.propertycache
     def revlog_kind(self):
         return self.target[0]
 
     @util.propertycache
     def display_id(self):
         """The public facing "ID" of the revlog that we use in message"""
         if self.revlog_kind == KIND_FILELOG:
             # Reference the file without the "data/" prefix, so it is familiar
             # to the user.
             return self.target[1]
         else:
             return self.radix
 
     def _datafp(self, mode=b'r'):
         """file object for the revlog's data file"""
         return self.opener(self._datafile, mode=mode)
 
     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):
+    def __iter__(self) -> Iterator[int]:
         return iter(range(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)
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def _candelta(self, baserev, rev):
         """whether two revisions (baserev, rev) can be delta-ed or not"""
         # Disable delta if either rev requires a content-changing flag
         # processor (ex. LFS). This is because such flag processor can alter
         # the rawtext content that the delta will be based on, and two clients
         # could have a same revlog node with different flags (i.e. different
         # rawtext contents) and the delta could be incompatible.
         if (self.flags(baserev) & REVIDX_RAWTEXT_CHANGING_FLAGS) or (
             self.flags(rev) & REVIDX_RAWTEXT_CHANGING_FLAGS
         ):
             return False
         return True
 
     def update_caches(self, transaction):
         """update on disk cache
 
         If a transaction is passed, the update may be delayed to transaction
         commit."""
         if self._nodemap_file is not None:
             if transaction is None:
                 nodemaputil.update_persistent_nodemap(self)
             else:
                 nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def clearcaches(self):
         """Clear in-memory caches"""
         self._chainbasecache.clear()
         self._inner.clear_cache()
         self._pcache = {}
         self._nodemap_docket = None
         self.index.clearcaches()
         # The python code is the one responsible for validating the docket, we
         # end up having to refresh it here.
         use_nodemap = (
             not self._inline
             and self._nodemap_file is not None
             and hasattr(self.index, 'update_nodemap_data')
         )
         if use_nodemap:
             nodemap_data = nodemaputil.persisted_data(self)
             if nodemap_data is not None:
                 self._nodemap_docket = nodemap_data[0]
                 self.index.update_nodemap_data(*nodemap_data)
 
     def rev(self, node):
         """return the revision number associated with a <nodeid>"""
         try:
             return self.index.rev(node)
         except TypeError:
             raise
         except error.RevlogError:
             # parsers.c radix tree lookup failed
             if (
                 node == self.nodeconstants.wdirid
                 or node in self.nodeconstants.wdirfilenodeids
             ):
                 raise error.WdirUnsupported
             raise error.LookupError(node, self.display_id, _(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 sidedata_cut_off(self, rev):
         sd_cut_off = self.index[rev][8]
         if sd_cut_off != 0:
             return sd_cut_off
         # This is some annoying dance, because entries without sidedata
         # currently use 0 as their ofsset. (instead of previous-offset +
         # previous-size)
         #
         # We should reconsider this sidedata → 0 sidata_offset policy.
         # In the meantime, we need this.
         while 0 <= rev:
             e = self.index[rev]
             if e[9] != 0:
                 return e[8] + e[9]
             rev -= 1
         return 0
 
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
 
     def length(self, rev):
         return self.index[rev][1]
 
     def sidedata_length(self, rev):
         if not self.feature_config.has_side_data:
             return 0
         return self.index[rev][9]
 
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.rawdata(rev)
         return len(t)
 
     def size(self, rev):
         """length of non-raw text (processed by a "read" flag processor)"""
         # fast path: if no "read" flag processor could change the content,
         # size is rawsize. note: ELLIPSIS is known to not change the content.
         flags = self.flags(rev)
         if flags & (flagutil.REVIDX_KNOWN_FLAGS ^ REVIDX_ELLIPSIS) == 0:
             return self.rawsize(rev)
 
         return len(self.revision(rev))
 
     def fast_rank(self, rev):
         """Return the rank of a revision if already known, or None otherwise.
 
         The rank of a revision is the size of the sub-graph it defines as a
         head. Equivalently, the rank of a revision `r` is the size of the set
         `ancestors(r)`, `r` included.
 
         This method returns the rank retrieved from the revlog in constant
         time. It makes no attempt at computing unknown values for versions of
         the revlog which do not persist the rank.
         """
         rank = self.index[rev][ENTRY_RANK]
         if self._format_version != CHANGELOGV2 or rank == RANK_UNKNOWN:
             return None
         if rev == nullrev:
             return 0  # convention
         return rank
 
     def chainbase(self, rev):
         base = self._chainbasecache.get(rev)
         if base is not None:
             return base
 
         index = self.index
         iterrev = rev
         base = index[iterrev][3]
         while base != iterrev:
             iterrev = base
             base = index[iterrev][3]
 
         self._chainbasecache[rev] = base
         return base
 
     def linkrev(self, rev):
         return self.index[rev][4]
 
     def parentrevs(self, rev):
         try:
             entry = self.index[rev]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
         if self.feature_config.canonical_parent_order and entry[5] == nullrev:
             return entry[6], entry[5]
         else:
             return entry[5], entry[6]
 
     # fast parentrevs(rev) where rev isn't filtered
     _uncheckedparentrevs = parentrevs
 
     def node(self, rev):
         try:
             return self.index[rev][7]
         except IndexError:
             if rev == wdirrev:
                 raise error.WdirUnsupported
             raise
 
     # Derived from index values.
 
     def end(self, rev):
         return self.start(rev) + self.length(rev)
 
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         # inline node() to avoid function call overhead
         if self.feature_config.canonical_parent_order and d[5] == self.nullid:
             return i[d[6]][7], i[d[5]][7]
         else:
             return i[d[5]][7], i[d[6]][7]
 
     def chainlen(self, rev):
         return self._chaininfo(rev)[0]
 
     def _chaininfo(self, rev):
         chaininfocache = self._chaininfocache
         if rev in chaininfocache:
             return chaininfocache[rev]
         index = self.index
         generaldelta = self.delta_config.general_delta
         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):
         return self._inner._deltachain(rev, stoprev=stoprev)
 
     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 and self.index.rust_ext_compat:
             lazyancestors = rustancestor.LazyAncestors
             arg = self.index
         else:
             lazyancestors = ancestor.lazyancestors
             arg = self._uncheckedparentrevs
         return lazyancestors(arg, revs, stoprev=stoprev, inclusive=inclusive)
 
     def descendants(self, revs):
         return dagop.descendantrevs(revs, self.revs, self.parentrevs)
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         class lazyset:
             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 and self.index.rust_ext_compat:
             return rustancestor.MissingAncestors(self.index, common)
         return ancestor.incrementalmissingancestors(self.parentrevs, common)
 
     def findmissingrevs(self, common=None, heads=None):
         """Return the revision numbers of the ancestors of heads that
         are not ancestors of common.
 
         More specifically, return a list of revision numbers corresponding to
         nodes N such that every N satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of revision numbers.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullrev]
         if heads is None:
             heads = self.headrevs()
 
         inc = self.incrementalmissingrevs(common=common)
         return inc.missingancestors(heads)
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [self.nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         inc = self.incrementalmissingrevs(common=common)
         return [self.node(r) for r in inc.missingancestors(heads)]
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [self.nullid]  # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return (
                 [self.node(r) for r in self],
                 [self.nullid],
                 list(self.heads()),
             )
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == self.nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n)  # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update(
                             [p for p in self.parents(n) if p != self.nullid]
                         )
                     elif n in heads:  # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [root for root in roots if root in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(root) for root in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [self.nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descendants, empty parents will look like
         # they're descendants.
         for r in self.revs(start=max(lowestrev, 0), stop=highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [head for head, flag in heads.items() 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 and self.index.rust_ext_compat:
             return rustdagop.headrevs(self.index, revs)
         return dagop.headrevs(revs, self._uncheckedparentrevs)
 
     def headrevsdiff(self, start, stop):
         try:
             return self.index.headrevsdiff(start, stop)
         except AttributeError:
             return dagop.headrevsdiff(self._uncheckedparentrevs, start, stop)
 
     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 _head_node_ids(self):
         try:
             return self.index.head_node_ids()
         except AttributeError:
             return [self.node(r) for r in self.headrevs()]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [self.nullid]
             return self._head_node_ids()
         if start is None:
             start = nullrev
         else:
             start = self.rev(start)
 
         stoprevs = {self.rev(n) for n in stop or []}
 
         revs = dagop.headrevssubset(
             self.revs, self.parentrevs, startrev=start, stoprevs=stoprevs
         )
 
         return [self.node(rev) for rev in revs]
 
     def diffheads(self, start, stop):
         """return the nodes that make up the difference between
         heads of revs before `start` and heads of revs before `stop`"""
         removed, added = self.headrevsdiff(start, stop)
         return [self.node(r) for r in removed], [self.node(r) for r in added]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in self.revs(start=p + 1):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def commonancestorsheads(self, a, b):
         """calculate all the heads of the common ancestors of nodes a and b"""
         a, b = self.rev(a), self.rev(b)
         ancs = self._commonancestorsheads(a, b)
         return pycompat.maplist(self.node, ancs)
 
     def _commonancestorsheads(self, *revs):
         """calculate all the heads of the common ancestors of revs"""
         try:
             ancs = self.index.commonancestorsheads(*revs)
         except (AttributeError, OverflowError):  # C implementation failed
             ancs = ancestor.commonancestorsheads(self.parentrevs, *revs)
         return ancs
 
     def isancestor(self, a, b):
         """return True if node a is an ancestor of node b
 
         A revision is considered an ancestor of itself."""
         a, b = self.rev(a), self.rev(b)
         return self.isancestorrev(a, b)
 
     def isancestorrev(self, a, b):
         """return True if revision a is an ancestor of revision b
 
         A revision is considered an ancestor of itself.
 
         The implementation of this is trivial but the use of
         reachableroots is not."""
         if a == nullrev:
             return True
         elif a == b:
             return True
         elif a > b:
             return False
         return bool(self.reachableroots(a, [b], [a], includepath=False))
 
     def reachableroots(self, minroot, heads, roots, includepath=False):
         """return (heads(::(<roots> and <roots>::<heads>)))
 
         If includepath is True, return (<roots>::<heads>)."""
         try:
             return self.index.reachableroots2(
                 minroot, heads, roots, includepath
             )
         except AttributeError:
             return dagop._reachablerootspure(
                 self.parentrevs, minroot, roots, heads, includepath
             )
 
     def ancestor(self, a, b):
         """calculate the "best" common ancestor of nodes a and b"""
 
         a, b = self.rev(a), self.rev(b)
         try:
             ancs = self.index.ancestors(a, b)
         except (AttributeError, OverflowError):
             ancs = ancestor.ancestors(self.parentrevs, a, b)
         if ancs:
             # choose a consistent winner when there's a tie
             return min(map(self.node, ancs))
         return self.nullid
 
     def _match(self, id):
         if isinstance(id, int):
             # rev
             return self.node(id)
         if len(id) == self.nodeconstants.nodelen:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node)  # quick search the index
                 return node
             except error.LookupError:
                 pass  # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if b"%d" % rev != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 2 * self.nodeconstants.nodelen:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (binascii.Error, error.LookupError):
                 pass
 
     def _partialmatch(self, id):
         # we don't care wdirfilenodeids as they should be always full hash
         maybewdir = self.nodeconstants.wdirhex.startswith(id)
         ambiguous = False
         try:
             partial = self.index.partialmatch(id)
             if partial and self.hasnode(partial):
                 if maybewdir:
                     # single 'ff...' match in radix tree, ambiguous with wdir
                     ambiguous = True
                 else:
                     return partial
             elif maybewdir:
                 # no 'ff...' match in radix tree, wdir identified
                 raise error.WdirUnsupported
             else:
                 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):
                 ambiguous = True
             # fall through to slow path that filters hidden revisions
         except (AttributeError, ValueError):
             # we are pure python, or key is not hex
             pass
         if ambiguous:
             raise error.AmbiguousPrefixLookupError(
                 id, self.display_id, _(b'ambiguous identifier')
             )
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) <= 40:
             # hex(node)[:...]
             l = len(id) // 2 * 2  # grab an even number of digits
             try:
                 # we're dropping the last digit, so let's check that it's hex,
                 # to avoid the expensive computation below if it's not
                 if len(id) % 2 > 0:
                     if not (id[-1] in hexdigits):
                         return None
                 prefix = bin(id[:l])
             except binascii.Error:
                 pass
             else:
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [
                     n for n in nl if hex(n).startswith(id) and self.hasnode(n)
                 ]
                 if self.nodeconstants.nullhex.startswith(id):
                     nl.append(self.nullid)
                 if len(nl) > 0:
                     if len(nl) == 1 and not maybewdir:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise error.AmbiguousPrefixLookupError(
                         id, self.display_id, _(b'ambiguous identifier')
                     )
                 if maybewdir:
                     raise error.WdirUnsupported
                 return None
 
     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.display_id, _(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.display_id, _(b'no node'))
             return True
 
         def maybewdir(prefix):
             return all(c == b'f' for c in pycompat.iterbytestr(prefix))
 
         hexnode = hex(node)
 
         def disambiguate(hexnode, minlength):
             """Disambiguate against wdirid."""
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if not maybewdir(prefix):
                     return prefix
 
         if not getattr(self, 'filteredrevs', None):
             try:
                 length = max(self.index.shortest(node), minlength)
                 return disambiguate(hexnode, length)
             except error.RevlogError:
                 if node != self.nodeconstants.wdirid:
                     raise error.LookupError(
                         node, self.display_id, _(b'no node')
                     )
             except AttributeError:
                 # Fall through to pure code
                 pass
 
         if node == self.nodeconstants.wdirid:
             for length in range(minlength, len(hexnode) + 1):
                 prefix = hexnode[:length]
                 if isvalid(prefix):
                     return prefix
 
         for length in range(minlength, len(hexnode) + 1):
             prefix = hexnode[:length]
             if isvalid(prefix):
                 return disambiguate(hexnode, length)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return storageutil.hashrevisionsha1(text, p1, p2) != node
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self.delta_config.general_delta:
             return base
         else:
             return rev - 1
 
     def issnapshot(self, rev):
         """tells whether rev is a snapshot"""
         ret = self._inner.issnapshot(rev)
         self.issnapshot = self._inner.issnapshot
         return ret
 
     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._inner._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._inner._chunk(rev2))
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         return self._revisiondata(nodeorrev)
 
     def sidedata(self, nodeorrev):
         """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.
         """
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
         else:
             rev = self.rev(nodeorrev)
         return self._sidedata(rev)
 
     def _rawtext(self, node, rev):
         """return the possibly unvalidated rawtext for a revision
 
         returns (rev, rawtext, validated)
         """
         # Check if we have the entry in cache
         # The cache entry looks like (node, rev, rawtext)
         if self._inner._revisioncache:
             if self._inner._revisioncache[0] == node:
                 return (rev, self._inner._revisioncache[2], True)
 
         if rev is None:
             rev = self.rev(node)
 
         return self._inner.raw_text(node, rev)
 
     def _revisiondata(self, nodeorrev, raw=False):
         # deal with <nodeorrev> argument type
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         # fast path the special `nullid` rev
         if node == self.nullid:
             return b""
 
         # ``rawtext`` is the text as stored inside the revlog. Might be the
         # revision or might need to be processed to retrieve the revision.
         rev, rawtext, validated = self._rawtext(node, rev)
 
         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
 
         if raw:
             validatehash = flagutil.processflagsraw(self, rawtext, flags)
             text = rawtext
         else:
             r = flagutil.processflagsread(self, rawtext, flags)
             text, validatehash = r
         if validatehash:
             self.checkhash(text, node, rev=rev)
         if not validated:
             self._inner._revisioncache = (node, rev, rawtext)
 
         return text
 
     def _sidedata(self, rev):
         """Return the sidedata for a given revision number."""
         sidedata_end = None
         if self._docket is not None:
             sidedata_end = self._docket.sidedata_end
         return self._inner.sidedata(rev, sidedata_end)
 
     def rawdata(self, nodeorrev):
         """return an uncompressed raw data of a given node or revision number."""
         return self._revisiondata(nodeorrev, raw=True)
 
     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._inner._revisioncache
                     and self._inner._revisioncache[0] == node
                 ):
                     self._inner._revisioncache = None
 
                 revornode = rev
                 if revornode is None:
                     revornode = templatefilters.short(hex(node))
                 raise error.RevlogError(
                     _(b"integrity check failed on %s:%s")
                     % (self.display_id, pycompat.bytestr(revornode))
                 )
         except error.RevlogError:
             if self.feature_config.censorable and storageutil.iscensoredtext(
                 text
             ):
                 raise error.CensoredNodeError(self.display_id, node, text)
             raise
 
     @property
     def _split_index_file(self):
         """the path where to expect the index of an ongoing splitting operation
 
         The file will only exist if a splitting operation is in progress, but
         it is always expected at the same location."""
         parts = self.radix.split(b'/')
         if len(parts) > 1:
             # adds a '-s' prefix to the ``data/` or `meta/` base
             head = parts[0] + b'-s'
             mids = parts[1:-1]
             tail = parts[-1] + b'.i'
             pieces = [head] + mids + [tail]
             return b'/'.join(pieces)
         else:
             # the revlog is stored at the root of the store (changelog or
             # manifest), no risk of collision.
             return self.radix + b'.i.s'
 
     def _enforceinlinesize(self, tr):
         """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
         total_size = self.start(tiprev) + self.length(tiprev)
         if not self._inline or (self._may_inline and total_size < _maxinline):
             return
 
         if self._docket is not None:
             msg = b"inline revlog should not have a docket"
             raise error.ProgrammingError(msg)
 
         # In the common case, we enforce inline size because the revlog has
         # been appened too. And in such case, it must have an initial offset
         # recorded in the transaction.
         troffset = tr.findoffset(self._inner.canonical_index_file)
         pre_touched = troffset is not None
         if not pre_touched and self.target[0] != KIND_CHANGELOG:
             raise error.RevlogError(
                 _(b"%s not found in the transaction") % self._indexfile
             )
 
         tr.addbackup(self._inner.canonical_index_file, for_offset=pre_touched)
         tr.add(self._datafile, 0)
 
         new_index_file_path = None
         old_index_file_path = self._indexfile
         new_index_file_path = self._split_index_file
         opener = self.opener
         weak_self = weakref.ref(self)
 
         # the "split" index replace the real index when the transaction is
         # finalized
         def finalize_callback(tr):
             opener.rename(
                 new_index_file_path,
                 old_index_file_path,
                 checkambig=True,
             )
             maybe_self = weak_self()
             if maybe_self is not None:
                 maybe_self._indexfile = old_index_file_path
                 maybe_self._inner.index_file = maybe_self._indexfile
 
         def abort_callback(tr):
             maybe_self = weak_self()
             if maybe_self is not None:
                 maybe_self._indexfile = old_index_file_path
                 maybe_self._inner.inline = True
                 maybe_self._inner.index_file = old_index_file_path
 
         tr.registertmp(new_index_file_path)
         # we use 001 here to make this this happens after the finalisation of
         # pending changelog write (using 000). Otherwise the two finalizer
         # would step over each other and delete the changelog.i file.
         if self.target[1] is not None:
             callback_id = b'001-revlog-split-%d-%s' % self.target
         else:
             callback_id = b'001-revlog-split-%d' % self.target[0]
         tr.addfinalize(callback_id, finalize_callback)
         tr.addabort(callback_id, abort_callback)
 
         self._format_flags &= ~FLAG_INLINE_DATA
         self._inner.split_inline(
             tr,
             self._format_flags | self._format_version,
             new_index_file_path=new_index_file_path,
         )
 
         self._inline = False
         if new_index_file_path is not None:
             self._indexfile = new_index_file_path
 
         nodemaputil.setup_persistent_nodemap(tr, self)
 
     def _nodeduplicatecallback(self, transaction, node):
         """called when trying to add a node already stored."""
 
     @contextlib.contextmanager
     def reading(self):
         with self._inner.reading():
             yield
 
     @contextlib.contextmanager
     def _writing(self, transaction):
         if self._trypending:
             msg = b'try to write in a `trypending` revlog: %s'
             msg %= self.display_id
             raise error.ProgrammingError(msg)
         if self._inner.is_writing:
             yield
         else:
             data_end = None
             sidedata_end = None
             if self._docket is not None:
                 data_end = self._docket.data_end
                 sidedata_end = self._docket.sidedata_end
             with self._inner.writing(
                 transaction,
                 data_end=data_end,
                 sidedata_end=sidedata_end,
             ):
                 yield
                 if self._docket is not None:
                     self._write_docket(transaction)
 
     @property
     def is_delaying(self):
         return self._inner.is_delaying
 
     def _write_docket(self, transaction):
         """write the current docket on disk
 
         Exist as a method to help changelog to implement transaction logic
 
         We could also imagine using the same transaction logic for all revlog
         since docket are cheap."""
         self._docket.write(transaction)
 
     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.display_id
             )
 
         if sidedata is None:
             sidedata = {}
         elif sidedata and not self.feature_config.has_side_data:
             raise error.ProgrammingError(
                 _(b"trying to add sidedata to a revlog who don't support them")
             )
 
         if flags:
             node = node or self.hash(text, p1, p2)
 
         rawtext, validatehash = flagutil.processflagswrite(self, text, flags)
 
         # If the flag processor modifies the revision data, ignore any provided
         # cachedelta.
         if rawtext != text:
             cachedelta = None
 
         if len(rawtext) > _maxentrysize:
             raise error.RevlogError(
                 _(
                     b"%s: size of %d bytes exceeds maximum revlog storage of 2GiB"
                 )
                 % (self.display_id, len(rawtext))
             )
 
         node = node or self.hash(rawtext, p1, p2)
         rev = self.index.get_rev(node)
         if rev is not None:
             return rev
 
         if validatehash:
             self.checkhash(rawtext, node, p1=p1, p2=p2)
 
         return self.addrawrevision(
             rawtext,
             transaction,
             link,
             p1,
             p2,
             node,
             flags,
             cachedelta=cachedelta,
             deltacomputer=deltacomputer,
             sidedata=sidedata,
         )
 
     def addrawrevision(
         self,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         node,
         flags,
         cachedelta=None,
         deltacomputer=None,
         sidedata=None,
     ):
         """add a raw revision with known flags, node and parents
         useful when reusing a revision not stored in this revlog (ex: received
         over wire, or read from an external bundle).
         """
         with self._writing(transaction):
             return self._addrevision(
                 node,
                 rawtext,
                 transaction,
                 link,
                 p1,
                 p2,
                 flags,
                 cachedelta,
                 deltacomputer=deltacomputer,
                 sidedata=sidedata,
             )
 
     def compress(self, data: bytes) -> Tuple[bytes, bytes]:
         return self._inner.compress(data)
 
     def decompress(self, data):
         return self._inner.decompress(data)
 
     def _addrevision(
         self,
         node,
         rawtext,
         transaction,
         link,
         p1,
         p2,
         flags,
         cachedelta,
         alwayscache=False,
         deltacomputer=None,
         sidedata=None,
     ):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
 
         note: "addrevision" takes non-raw text, "_addrevision" takes raw text.
 
         if "deltacomputer" is not provided or None, a defaultdeltacomputer will
         be used.
 
         invariants:
         - rawtext is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to each other.
         """
         if node == self.nullid:
             raise error.RevlogError(
                 _(b"%s: attempt to add null revision") % self.display_id
             )
         if (
             node == self.nodeconstants.wdirid
             or node in self.nodeconstants.wdirfilenodeids
         ):
             raise error.RevlogError(
                 _(b"%s: attempt to add wdir revision") % self.display_id
             )
         if self._inner._writinghandles is None:
             msg = b'adding revision outside `revlog._writing` context'
             raise error.ProgrammingError(msg)
 
         btext = [rawtext]
 
         curr = len(self)
         prev = curr - 1
 
         offset = self._get_data_offset(prev)
 
         if self._concurrencychecker:
             ifh, dfh, sdfh = self._inner._writinghandles
             # XXX no checking for the sidedata file
             if self._inline:
                 # offset is "as if" it were in the .d file, so we need to add on
                 # the size of the entry metadata.
                 self._concurrencychecker(
                     ifh, self._indexfile, offset + curr * self.index.entry_size
                 )
             else:
                 # Entries in the .i are a consistent size.
                 self._concurrencychecker(
                     ifh, self._indexfile, curr * self.index.entry_size
                 )
                 self._concurrencychecker(dfh, self._datafile, offset)
 
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if rawtext is None:
             # need rawtext size, before changed by flag processors, which is
             # the non-raw size. use revlog explicitly to avoid filelog's extra
             # logic that might remove metadata size.
             textlen = mdiff.patchedsize(
                 revlog.size(self, cachedelta[0]), cachedelta[1]
             )
         else:
             textlen = len(rawtext)
 
         if deltacomputer is None:
             write_debug = None
             if self.delta_config.debug_delta:
                 write_debug = transaction._report
             deltacomputer = deltautil.deltacomputer(
                 self, write_debug=write_debug
             )
 
         if cachedelta is not None and len(cachedelta) == 2:
             # If the cached delta has no information about how it should be
             # reused, add the default reuse instruction according to the
             # revlog's configuration.
             if (
                 self.delta_config.general_delta
                 and self.delta_config.lazy_delta_base
             ):
                 delta_base_reuse = DELTA_BASE_REUSE_TRY
             else:
                 delta_base_reuse = DELTA_BASE_REUSE_NO
             cachedelta = (cachedelta[0], cachedelta[1], delta_base_reuse)
 
         revinfo = revlogutils.revisioninfo(
             node,
             p1,
             p2,
             btext,
             textlen,
             cachedelta,
             flags,
         )
 
         deltainfo = deltacomputer.finddeltainfo(revinfo)
 
         compression_mode = COMP_MODE_INLINE
         if self._docket is not None:
             default_comp = self._docket.default_compression_header
             r = deltautil.delta_compression(default_comp, deltainfo)
             compression_mode, deltainfo = r
 
         sidedata_compression_mode = COMP_MODE_INLINE
         if sidedata and self.feature_config.has_side_data:
             sidedata_compression_mode = COMP_MODE_PLAIN
             serialized_sidedata = sidedatautil.serialize_sidedata(sidedata)
             sidedata_offset = self._docket.sidedata_end
             h, comp_sidedata = self._inner.compress(serialized_sidedata)
             if (
                 h != b'u'
                 and comp_sidedata[0:1] != b'\0'
                 and len(comp_sidedata) < len(serialized_sidedata)
             ):
                 assert not h
                 if (
                     comp_sidedata[0:1]
                     == self._docket.default_compression_header
                 ):
                     sidedata_compression_mode = COMP_MODE_DEFAULT
                     serialized_sidedata = comp_sidedata
                 else:
                     sidedata_compression_mode = COMP_MODE_INLINE
                     serialized_sidedata = comp_sidedata
         else:
             serialized_sidedata = b""
             # Don't store the offset if the sidedata is empty, that way
             # we can easily detect empty sidedata and they will be no different
             # than ones we manually add.
             sidedata_offset = 0
 
         rank = RANK_UNKNOWN
         if self.feature_config.compute_rank:
             if (p1r, p2r) == (nullrev, nullrev):
                 rank = 1
             elif p1r != nullrev and p2r == nullrev:
                 rank = 1 + self.fast_rank(p1r)
             elif p1r == nullrev and p2r != nullrev:
                 rank = 1 + self.fast_rank(p2r)
             else:  # merge node
                 if rustdagop is not None and self.index.rust_ext_compat:
                     rank = rustdagop.rank(self.index, p1r, p2r)
                 else:
                     pmin, pmax = sorted((p1r, p2r))
                     rank = 1 + self.fast_rank(pmax)
                     rank += sum(1 for _ in self.findmissingrevs([pmax], [pmin]))
 
         e = revlogutils.entry(
             flags=flags,
             data_offset=offset,
             data_compressed_length=deltainfo.deltalen,
             data_uncompressed_length=textlen,
             data_compression_mode=compression_mode,
             data_delta_base=deltainfo.base,
             link_rev=link,
             parent_rev_1=p1r,
             parent_rev_2=p2r,
             node_id=node,
             sidedata_offset=sidedata_offset,
             sidedata_compressed_length=len(serialized_sidedata),
             sidedata_compression_mode=sidedata_compression_mode,
             rank=rank,
         )
 
         self.index.append(e)
         entry = self.index.entry_binary(curr)
         if curr == 0 and self._docket is None:
             header = self._format_flags | self._format_version
             header = self.index.pack_header(header)
             entry = header + entry
         self._writeentry(
             transaction,
             entry,
             deltainfo.data,
             link,
             offset,
             serialized_sidedata,
             sidedata_offset,
         )
 
         rawtext = btext[0]
 
         if alwayscache and rawtext is None:
             rawtext = deltacomputer.buildtext(revinfo)
 
         if type(rawtext) == bytes:  # only accept immutable objects
             self._inner._revisioncache = (node, curr, rawtext)
         self._chainbasecache[curr] = deltainfo.chainbase
         return curr
 
     def _get_data_offset(self, prev):
         """Returns the current offset in the (in-transaction) data file.
         Versions < 2 of the revlog can get this 0(1), revlog v2 needs a docket
         file to store that information: since sidedata can be rewritten to the
         end of the data file within a transaction, you can have cases where, for
         example, rev `n` does not have sidedata while rev `n - 1` does, leading
         to `n - 1`'s sidedata being written after `n`'s data.
 
         TODO cache this in a docket file before getting out of experimental."""
         if self._docket is None:
             return self.end(prev)
         else:
             return self._docket.data_end
 
     def _writeentry(
         self,
         transaction,
         entry,
         data,
         link,
         offset,
         sidedata,
         sidedata_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.
         index_end = data_end = sidedata_end = None
         if self._docket is not None:
             index_end = self._docket.index_end
             data_end = self._docket.data_end
             sidedata_end = self._docket.sidedata_end
 
         files_end = self._inner.write_entry(
             transaction,
             entry,
             data,
             link,
             offset,
             sidedata,
             sidedata_offset,
             index_end,
             data_end,
             sidedata_end,
         )
         self._enforceinlinesize(transaction)
         if self._docket is not None:
             self._docket.index_end = files_end[0]
             self._docket.data_end = files_end[1]
             self._docket.sidedata_end = files_end[2]
 
         nodemaputil.setup_persistent_nodemap(transaction, self)
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         debug_info=None,
         delta_base_reuse_policy=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._adding_group:
             raise error.ProgrammingError(b'cannot nest addgroup() calls')
 
         # read the default delta-base reuse policy from revlog config if the
         # group did not specify one.
         if delta_base_reuse_policy is None:
             if (
                 self.delta_config.general_delta
                 and self.delta_config.lazy_delta_base
             ):
                 delta_base_reuse_policy = DELTA_BASE_REUSE_TRY
             else:
                 delta_base_reuse_policy = DELTA_BASE_REUSE_NO
 
         self._adding_group = True
         empty = True
         try:
             with self._writing(transaction):
                 write_debug = None
                 if self.delta_config.debug_delta:
                     write_debug = transaction._report
                 deltacomputer = deltautil.deltacomputer(
                     self,
                     write_debug=write_debug,
                     debug_info=debug_info,
                 )
                 # loop through our set of deltas
                 for data in deltas:
                     (
                         node,
                         p1,
                         p2,
                         linknode,
                         deltabase,
                         delta,
                         flags,
                         sidedata,
                     ) = data
                     link = linkmapper(linknode)
                     flags = flags or REVIDX_DEFAULT_FLAGS
 
                     rev = self.index.get_rev(node)
                     if rev is not None:
                         # this can happen if two branches make the same change
                         self._nodeduplicatecallback(transaction, rev)
                         if duplicaterevisioncb:
                             duplicaterevisioncb(self, rev)
                         empty = False
                         continue
 
                     for p in (p1, p2):
                         if not self.index.has_node(p):
                             raise error.LookupError(
                                 p, self.radix, _(b'unknown parent')
                             )
 
                     if not self.index.has_node(deltabase):
                         raise error.LookupError(
                             deltabase, self.display_id, _(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.display_id, self.node(baserev)
                             )
 
                     if not flags and self._peek_iscensored(baserev, delta):
                         flags |= REVIDX_ISCENSORED
 
                     # We assume consumers of addrevisioncb will want to retrieve
                     # the added revision, which will require a call to
                     # revision(). revision() will fast path if there is a cache
                     # hit. So, we tell _addrevision() to always cache in this case.
                     # We're only using addgroup() in the context of changegroup
                     # generation so the revision data can always be handled as raw
                     # by the flagprocessor.
                     rev = self._addrevision(
                         node,
                         None,
                         transaction,
                         link,
                         p1,
                         p2,
                         flags,
                         (baserev, delta, delta_base_reuse_policy),
                         alwayscache=alwayscache,
                         deltacomputer=deltacomputer,
                         sidedata=sidedata,
                     )
 
                     if addrevisioncb:
                         addrevisioncb(self, rev)
                     empty = False
         finally:
             self._adding_group = False
         return not empty
 
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         if not self.feature_config.censorable:
             return False
 
         return self.flags(rev) & REVIDX_ISCENSORED
 
     def _peek_iscensored(self, baserev, delta):
         """Quickly check if a delta produces a censored revision."""
         if not self.feature_config.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
         data_end = self.start(rev)
         if not self._inline:
             transaction.add(self._datafile, data_end)
             end = rev * self.index.entry_size
         else:
             end = data_end + (rev * self.index.entry_size)
 
         if self._sidedatafile:
             sidedata_end = self.sidedata_cut_off(rev)
             transaction.add(self._sidedatafile, sidedata_end)
 
         transaction.add(self._indexfile, end)
         if self._docket is not None:
             # XXX we could, leverage the docket while stripping. However it is
             # not powerfull enough at the time of this comment
             self._docket.index_end = end
             self._docket.data_end = data_end
             self._docket.sidedata_end = sidedata_end
             self._docket.write(transaction, stripping=True)
 
         # then reset internal state in memory to forget those revisions
         self._chaininfocache = util.lrucachedict(500)
         self._inner.clear_cache()
 
         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 FileNotFoundError:
             dd = 0
 
         try:
             f = self.opener(self._indexfile)
             f.seek(0, io.SEEK_END)
             actual = f.tell()
             f.close()
             s = self.index.entry_size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except FileNotFoundError:
             di = 0
 
         return (dd, di)
 
     def files(self):
         """return list of files that compose this revlog"""
         res = [self._indexfile]
         if self._docket_file is None:
             if not self._inline:
                 res.append(self._datafile)
         else:
             res.append(self._docket_file)
             res.extend(self._docket.old_index_filepaths(include_empty=False))
             if self._docket.data_end:
                 res.append(self._datafile)
             res.extend(self._docket.old_data_filepaths(include_empty=False))
             if self._docket.sidedata_end:
                 res.append(self._sidedatafile)
             res.extend(self._docket.old_sidedata_filepaths(include_empty=False))
         return res
 
     def emitrevisions(
         self,
         nodes,
         nodesorder=None,
         revisiondata=False,
         assumehaveparentrevisions=False,
         deltamode=repository.CG_DELTAMODE_STD,
         sidedata_helpers=None,
         debug_info=None,
     ):
         if nodesorder not in (b'nodes', b'storage', b'linear', None):
             raise error.ProgrammingError(
                 b'unhandled value for nodesorder: %s' % nodesorder
             )
 
         if nodesorder is None and not self.delta_config.general_delta:
             nodesorder = b'storage'
 
         if (
             not self._storedeltachains
             and deltamode != repository.CG_DELTAMODE_PREV
         ):
             deltamode = repository.CG_DELTAMODE_FULL
 
         return storageutil.emitrevisions(
             self,
             nodes,
             nodesorder,
             revlogrevisiondelta,
             deltaparentfn=self.deltaparent,
             candeltafn=self._candelta,
             rawsizefn=self.rawsize,
             revdifffn=self.revdiff,
             flagsfn=self.flags,
             deltamode=deltamode,
             revisiondata=revisiondata,
             assumehaveparentrevisions=assumehaveparentrevisions,
             sidedata_helpers=sidedata_helpers,
             debug_info=debug_info,
         )
 
     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,
         sidedata_helpers=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.
 
         See `revlogutil.sidedata.get_sidedata_helpers` for the doc on
         `sidedata_helpers`.
         """
         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.
         old_delta_config = destrevlog.delta_config
         destrevlog.delta_config = destrevlog.delta_config.copy()
 
         try:
             if deltareuse == self.DELTAREUSEALWAYS:
                 destrevlog.delta_config.lazy_delta_base = True
                 destrevlog.delta_config.lazy_delta = True
             elif deltareuse == self.DELTAREUSESAMEREVS:
                 destrevlog.delta_config.lazy_delta_base = False
                 destrevlog.delta_config.lazy_delta = True
             elif deltareuse == self.DELTAREUSENEVER:
                 destrevlog.delta_config.lazy_delta_base = False
                 destrevlog.delta_config.lazy_delta = False
 
             delta_both_parents = (
                 forcedeltabothparents or old_delta_config.delta_both_parents
             )
             destrevlog.delta_config.delta_both_parents = delta_both_parents
 
             with self.reading(), destrevlog._writing(tr):
                 self._clone(
                     tr,
                     destrevlog,
                     addrevisioncb,
                     deltareuse,
                     forcedeltabothparents,
                     sidedata_helpers,
                 )
 
         finally:
             destrevlog.delta_config = old_delta_config
 
     def _clone(
         self,
         tr,
         destrevlog,
         addrevisioncb,
         deltareuse,
         forcedeltabothparents,
         sidedata_helpers,
     ):
         """perform the core duty of `revlog.clone` after parameter processing"""
         write_debug = None
         if self.delta_config.debug_delta:
             write_debug = tr._report
         deltacomputer = deltautil.deltacomputer(
             destrevlog,
             write_debug=write_debug,
         )
         index = self.index
         for rev in self:
             entry = index[rev]
 
             # Some classes override linkrev to take filtered revs into
             # account. Use raw entry from index.
             flags = entry[0] & 0xFFFF
             linkrev = entry[4]
             p1 = index[entry[5]][7]
             p2 = index[entry[6]][7]
             node = entry[7]
 
             # (Possibly) reuse the delta from the revlog if allowed and
             # the revlog chunk is a delta.
             cachedelta = None
             rawtext = None
             if deltareuse == self.DELTAREUSEFULLADD:
                 text = self._revisiondata(rev)
                 sidedata = self.sidedata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 destrevlog.addrevision(
                     text,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     cachedelta=cachedelta,
                     node=node,
                     flags=flags,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
             else:
                 if destrevlog.delta_config.lazy_delta:
                     dp = self.deltaparent(rev)
                     if dp != nullrev:
                         cachedelta = (dp, bytes(self._inner._chunk(rev)))
 
                 sidedata = None
                 if not cachedelta:
                     try:
                         rawtext = self._revisiondata(rev)
                     except error.CensoredNodeError as censored:
                         assert flags & REVIDX_ISCENSORED
                         rawtext = censored.tombstone
                     sidedata = self.sidedata(rev)
                 if sidedata is None:
                     sidedata = self.sidedata(rev)
 
                 if sidedata_helpers is not None:
                     (sidedata, new_flags) = sidedatautil.run_sidedata_helpers(
                         self, sidedata_helpers, sidedata, rev
                     )
                     flags = flags | new_flags[0] & ~new_flags[1]
 
                 destrevlog._addrevision(
                     node,
                     rawtext,
                     tr,
                     linkrev,
                     p1,
                     p2,
                     flags,
                     cachedelta,
                     deltacomputer=deltacomputer,
                     sidedata=sidedata,
                 )
 
             if addrevisioncb:
                 addrevisioncb(self, rev, node)
 
     def censorrevision(self, tr, censor_nodes, tombstone=b''):
         if self._format_version == REVLOGV0:
             raise error.RevlogError(
                 _(b'cannot censor with version %d revlogs')
                 % self._format_version
             )
         elif self._format_version == REVLOGV1:
             rewrite.v1_censor(self, tr, censor_nodes, tombstone)
         else:
             rewrite.v2_censor(self, tr, censor_nodes, tombstone)
 
-    def verifyintegrity(self, state):
+    def verifyintegrity(self, state) -> Iterable[RevLogProblem]:
         """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._format_version
 
         # 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.display_id, version, state[b'expectedversion'])
             )
 
         state[b'skipread'] = set()
         state[b'safe_renamed'] = set()
 
         for rev in self:
             node = self.node(rev)
 
             # Verify contents. 4 cases to care about:
             #
             #   common: the most common case
             #   rename: with a rename
             #   meta: file content starts with b'\1\n', the metadata
             #         header defined in filelog.py, but without a rename
             #   ext: content stored externally
             #
             # More formally, their differences are shown below:
             #
             #                       | common | rename | meta  | ext
             #  -------------------------------------------------------
             #   flags()             | 0      | 0      | 0     | not 0
             #   renamed()           | False  | True   | False | ?
             #   rawtext[0:2]=='\1\n'| False  | True   | True  | ?
             #
             # "rawtext" means the raw text stored in revlog data, which
             # could be retrieved by "rawdata(rev)". "text"
             # mentioned below is "revision(rev)".
             #
             # There are 3 different lengths stored physically:
             #  1. L1: rawsize, stored in revlog index
             #  2. L2: len(rawtext), stored in revlog data
             #  3. L3: len(text), stored in revlog data if flags==0, or
             #     possibly somewhere else if flags!=0
             #
             # L1 should be equal to L2. L3 could be different from them.
             # "text" may or may not affect commit hash depending on flag
             # processors (see flagutil.addflagprocessor).
             #
             #              | common  | rename | meta  | ext
             # -------------------------------------------------
             #    rawsize() | L1      | L1     | L1    | L1
             #       size() | L1      | L2-LM  | L1(*) | L1 (?)
             # len(rawtext) | L2      | L2     | L2    | L2
             #    len(text) | L2      | L2     | L2    | L3
             #  len(read()) | L2      | L2-LM  | L2-LM | L3 (?)
             #
             # LM:  length of metadata, depending on rawtext
             # (*): not ideal, see comment in filelog.size
             # (?): could be "- len(meta)" if the resolved content has
             #      rename metadata
             #
             # Checks needed to be done:
             #  1. length check: L1 == L2, in all cases.
             #  2. hash check: depending on flag processor, we may need to
             #     use either "text" (external), or "rawtext" (in revlog).
 
             try:
                 skipflags = state.get(b'skipflags', 0)
                 if skipflags:
                     skipflags &= self.flags(rev)
 
                 _verify_revision(self, skipflags, state, node)
 
                 l1 = self.rawsize(rev)
                 l2 = len(self.rawdata(node))
 
                 if l1 != l2:
                     yield revlogproblem(
                         error=_(b'unpacked size is %d, %d expected') % (l2, l1),
                         node=node,
                     )
 
             except error.CensoredNodeError:
                 if state[b'erroroncensored']:
                     yield revlogproblem(
                         error=_(b'censored file data'), node=node
                     )
                     state[b'skipread'].add(node)
             except Exception as e:
                 yield revlogproblem(
                     error=_(b'unpacking %s: %s')
                     % (short(node), stringutil.forcebytestr(e)),
                     node=node,
                 )
                 state[b'skipread'].add(node)
 
     def storageinfo(
         self,
         exclusivefiles=False,
         sharedfiles=False,
         revisionscount=False,
         trackedsize=False,
         storedsize=False,
     ):
         d = {}
 
         if exclusivefiles:
             d[b'exclusivefiles'] = [(self.opener, self._indexfile)]
             if not self._inline:
                 d[b'exclusivefiles'].append((self.opener, self._datafile))
 
         if sharedfiles:
             d[b'sharedfiles'] = []
 
         if revisionscount:
             d[b'revisionscount'] = len(self)
 
         if trackedsize:
             d[b'trackedsize'] = sum(map(self.rawsize, iter(self)))
 
         if storedsize:
             d[b'storedsize'] = sum(
                 self.opener.stat(path).st_size for path in self.files()
             )
 
         return d
 
     def rewrite_sidedata(self, transaction, helpers, startrev, endrev):
         if not self.feature_config.has_side_data:
             return
         # revlog formats with sidedata support does not support inline
         assert not self._inline
         if not helpers[1] and not helpers[2]:
             # Nothing to generate or remove
             return
 
         new_entries = []
         # append the new sidedata
         with self._writing(transaction):
             ifh, dfh, sdfh = self._inner._writinghandles
             dfh.seek(self._docket.sidedata_end, os.SEEK_SET)
 
             current_offset = sdfh.tell()
             for rev in range(startrev, endrev + 1):
                 entry = self.index[rev]
                 new_sidedata, flags = sidedatautil.run_sidedata_helpers(
                     store=self,
                     sidedata_helpers=helpers,
                     sidedata={},
                     rev=rev,
                 )
 
                 serialized_sidedata = sidedatautil.serialize_sidedata(
                     new_sidedata
                 )
 
                 sidedata_compression_mode = COMP_MODE_INLINE
                 if serialized_sidedata and self.feature_config.has_side_data:
                     sidedata_compression_mode = COMP_MODE_PLAIN
                     h, comp_sidedata = self._inner.compress(serialized_sidedata)
                     if (
                         h != b'u'
                         and comp_sidedata[0] != b'\0'
                         and len(comp_sidedata) < len(serialized_sidedata)
                     ):
                         assert not h
                         if (
                             comp_sidedata[0]
                             == self._docket.default_compression_header
                         ):
                             sidedata_compression_mode = COMP_MODE_DEFAULT
                             serialized_sidedata = comp_sidedata
                         else:
                             sidedata_compression_mode = COMP_MODE_INLINE
                             serialized_sidedata = comp_sidedata
                 if entry[8] != 0 or entry[9] != 0:
                     # rewriting entries that already have sidedata is not
                     # supported yet, because it introduces garbage data in the
                     # revlog.
                     msg = b"rewriting existing sidedata is not supported yet"
                     raise error.Abort(msg)
 
                 # Apply (potential) flags to add and to remove after running
                 # the sidedata helpers
                 new_offset_flags = entry[0] | flags[0] & ~flags[1]
                 entry_update = (
                     current_offset,
                     len(serialized_sidedata),
                     new_offset_flags,
                     sidedata_compression_mode,
                 )
 
                 # the sidedata computation might have move the file cursors around
                 sdfh.seek(current_offset, os.SEEK_SET)
                 sdfh.write(serialized_sidedata)
                 new_entries.append(entry_update)
                 current_offset += len(serialized_sidedata)
                 self._docket.sidedata_end = sdfh.tell()
 
             # rewrite the new index entries
             ifh.seek(startrev * self.index.entry_size)
             for i, e in enumerate(new_entries):
                 rev = startrev + i
                 self.index.replace_sidedata_info(rev, *e)
                 packed = self.index.entry_binary(rev)
                 if rev == 0 and self._docket is None:
                     header = self._format_flags | self._format_version
                     header = self.index.pack_header(header)
                     packed = header + packed
                 ifh.write(packed)

mercurial/statichttprepo.py

@@ -1,271 +1,273 b''
 # statichttprepo.py - simple http repository class for mercurial
 #
 # This provides read-only repo access to repositories exported via static http
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import errno
 
 from .i18n import _
 from .node import sha1nodeconstants
 from . import (
     branchmap,
     changelog,
     error,
     localrepo,
     manifest,
     namespaces,
     pathutil,
     pycompat,
     requirements as requirementsmod,
     url,
     util,
     vfs as vfsmod,
 )
 from .utils import (
     urlutil,
 )
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 
 class httprangereader:
     def __init__(self, url, opener):
         # we assume opener has HTTPRangeHandler
         self.url = url
         self.pos = 0
         self.opener = opener
         self.name = url
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, traceback):
         self.close()
 
     def seek(self, pos):
         self.pos = pos
 
     def read(self, bytes=None):
         req = urlreq.request(pycompat.strurl(self.url))
         end = b''
         if bytes:
             end = self.pos + bytes - 1
         if self.pos or end:
             req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))
 
         try:
             f = self.opener.open(req)
             data = f.read()
             code = f.code
         except urlerr.httperror as inst:
             num = inst.code == 404 and errno.ENOENT or None
             # Explicitly convert the exception to str as Py3 will try
             # convert it to local encoding and with as the HTTPResponse
             # instance doesn't support encode.
             raise IOError(num, str(inst))
         except urlerr.urlerror as inst:
             raise IOError(None, inst.reason)
 
         if code == 200:
             # HTTPRangeHandler does nothing if remote does not support
             # Range headers and returns the full entity. Let's slice it.
             if bytes:
                 data = data[self.pos : self.pos + bytes]
             else:
                 data = data[self.pos :]
         elif bytes:
             data = data[:bytes]
         self.pos += len(data)
         return data
 
     def readlines(self):
         return self.read().splitlines(True)
 
     def __iter__(self):
         return iter(self.readlines())
 
     def close(self):
         pass
 
 
 # _RangeError and _HTTPRangeHandler were originally in byterange.py,
 # which was itself extracted from urlgrabber. See the last version of
 # byterange.py from history if you need more information.
 class _RangeError(IOError):
     """Error raised when an unsatisfiable range is requested."""
 
 
 class _HTTPRangeHandler(urlreq.basehandler):
     """Handler that enables HTTP Range headers.
 
     This was extremely simple. The Range header is a HTTP feature to
     begin with so all this class does is tell urllib2 that the
     "206 Partial Content" response from the HTTP server is what we
     expected.
     """
 
     def http_error_206(self, req, fp, code, msg, hdrs):
         # 206 Partial Content Response
         r = urlreq.addinfourl(fp, hdrs, req.get_full_url())
         r.code = code
         r.msg = msg
         return r
 
     def http_error_416(self, req, fp, code, msg, hdrs):
         # HTTP's Range Not Satisfiable error
         raise _RangeError('Requested Range Not Satisfiable')
 
 
 def build_opener(ui, authinfo):
     # urllib cannot handle URLs with embedded user or passwd
     urlopener = url.opener(ui, authinfo)
     urlopener.add_handler(_HTTPRangeHandler())
 
     class statichttpvfs(vfsmod.abstractvfs):
         def __init__(self, base):
             self.base = base
             self.options = {}
 
         def __call__(self, path, mode=b'r', *args, **kw):
             if mode not in (b'r', b'rb'):
                 raise IOError('Permission denied')
             f = b"/".join((self.base, urlreq.quote(path)))
             return httprangereader(f, urlopener)
 
         def join(self, path, *insidef):
             if path:
                 return pathutil.join(self.base, path, *insidef)
             else:
                 return self.base
 
     return statichttpvfs
 
 
 class statichttppeer(localrepo.localpeer):
     def local(self):
         return None
 
     def canpush(self):
         return False
 
 
 class statichttprepository(
     localrepo.localrepository, localrepo.revlogfilestorage
 ):
     supported = localrepo.localrepository._basesupported
 
+    manifestlog: manifest.ManifestLog
+
     def __init__(self, ui, path):
         self._url = path
         self.ui = ui
 
         self.root = path
         u = urlutil.url(path.rstrip(b'/') + b"/.hg")
         self.path, authinfo = u.authinfo()
 
         vfsclass = build_opener(ui, authinfo)
         self.vfs = vfsclass(self.path)
         self.cachevfs = vfsclass(self.vfs.join(b'cache'))
         self._phasedefaults = []
 
         self.names = namespaces.namespaces()
         self.filtername = None
         self._extrafilterid = None
         self._wanted_sidedata = set()
         self.features = set()
 
         try:
             requirements = set(self.vfs.read(b'requires').splitlines())
         except FileNotFoundError:
             requirements = set()
 
             # check if it is a non-empty old-style repository
             try:
                 fp = self.vfs(b"00changelog.i")
                 fp.read(1)
                 fp.close()
             except FileNotFoundError:
                 # we do not care about empty old-style repositories here
                 msg = _(b"'%s' does not appear to be an hg repository") % path
                 raise error.RepoError(msg)
         if requirementsmod.SHARESAFE_REQUIREMENT in requirements:
             storevfs = vfsclass(self.vfs.join(b'store'))
             requirements |= set(storevfs.read(b'requires').splitlines())
 
         supportedrequirements = localrepo.gathersupportedrequirements(ui)
         localrepo.ensurerequirementsrecognized(
             requirements, supportedrequirements
         )
         localrepo.ensurerequirementscompatible(ui, requirements)
         self.nodeconstants = sha1nodeconstants
         self.nullid = self.nodeconstants.nullid
 
         # setup store
         self.store = localrepo.makestore(requirements, self.path, vfsclass)
         self.spath = self.store.path
         self.svfs = self.store.opener
         self.sjoin = self.store.join
         self._filecache = {}
         self.requirements = requirements
 
         rootmanifest = manifest.manifestrevlog(self.nodeconstants, self.svfs)
         self.manifestlog = manifest.manifestlog(
             self.svfs, self, rootmanifest, self.narrowmatch()
         )
         self.changelog = changelog.changelog(self.svfs)
         self._tags = None
         self.nodetagscache = None
         self._branchcaches = branchmap.BranchMapCache()
         self._revbranchcache = None
         self.encodepats = None
         self.decodepats = None
         self._transref = None
         self._dirstate = None
 
     def _restrictcapabilities(self, caps):
         caps = super(statichttprepository, self)._restrictcapabilities(caps)
         return caps.difference([b"pushkey"])
 
     def url(self):
         return self._url
 
     def local(self):
         return False
 
     def peer(self, path=None, remotehidden=False):
         return statichttppeer(self, path=path, remotehidden=remotehidden)
 
     def wlock(self, wait=True):
         raise error.LockUnavailable(
             0,
             pycompat.sysstr(_(b'lock not available')),
             b'lock',
             _(b'cannot lock static-http repository'),
         )
 
     def lock(self, wait=True):
         raise error.LockUnavailable(
             0,
             pycompat.sysstr(_(b'lock not available')),
             b'lock',
             _(b'cannot lock static-http repository'),
         )
 
     def _writecaches(self):
         pass  # statichttprepository are read only
 
 
 def make_peer(
     ui, path, create, intents=None, createopts=None, remotehidden=False
 ):
     if create:
         raise error.Abort(_(b'cannot create new static-http repository'))
     url = path.loc[7:]
     return statichttprepository(ui, url).peer(
         path=path, remotehidden=remotehidden
     )

mercurial/store.py

@@ -1,1250 +1,1250 b''
 # store.py - repository store handling for Mercurial)
 #
 # Copyright 2008 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import collections
 import functools
 import os
 import re
 import stat
 import typing
 
 from typing import Generator, List
 
 from .i18n import _
 from .thirdparty import attr
 
 # Force pytype to use the non-vendored package
 if typing.TYPE_CHECKING:
     # noinspection PyPackageRequirements
     import attr
 
 from .node import hex
 from .revlogutils.constants import (
     INDEX_HEADER,
     KIND_CHANGELOG,
     KIND_FILELOG,
     KIND_MANIFESTLOG,
 )
 from . import (
     changelog,
     error,
     filelog,
     manifest,
     policy,
     pycompat,
     revlog as revlogmod,
     util,
     vfs as vfsmod,
 )
 from .utils import hashutil
 
 parsers = policy.importmod('parsers')
 # how much bytes should be read from fncache in one read
 # It is done to prevent loading large fncache files into memory
 fncache_chunksize = 10**6
 
 
 def _match_tracked_entry(entry: "BaseStoreEntry", matcher):
     """parses a fncache entry and returns whether the entry is tracking a path
     matched by matcher or not.
 
     If matcher is None, returns True"""
 
     if matcher is None:
         return True
 
     # TODO: make this safe for other entry types.  Currently, the various
     #  store.data_entry generators only yield  RevlogStoreEntry, so the
     #  attributes do exist on `entry`.
     # pytype: disable=attribute-error
     if entry.is_filelog:
         return matcher(entry.target_id)
     elif entry.is_manifestlog:
         return matcher.visitdir(entry.target_id.rstrip(b'/'))
     # pytype: enable=attribute-error
     raise error.ProgrammingError(b"cannot process entry %r" % entry)
 
 
 # This avoids a collision between a file named foo and a dir named
 # foo.i or foo.d
 def _encodedir(path):
     """
     >>> _encodedir(b'data/foo.i')
     'data/foo.i'
     >>> _encodedir(b'data/foo.i/bla.i')
     'data/foo.i.hg/bla.i'
     >>> _encodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i.hg.hg/bla.i'
     >>> _encodedir(b'data/foo.i\\ndata/foo.i/bla.i\\ndata/foo.i.hg/bla.i\\n')
     'data/foo.i\\ndata/foo.i.hg/bla.i\\ndata/foo.i.hg.hg/bla.i\\n'
     """
     return (
         path.replace(b".hg/", b".hg.hg/")
         .replace(b".i/", b".i.hg/")
         .replace(b".d/", b".d.hg/")
     )
 
 
 encodedir = getattr(parsers, 'encodedir', _encodedir)
 
 
 def decodedir(path):
     """
     >>> decodedir(b'data/foo.i')
     'data/foo.i'
     >>> decodedir(b'data/foo.i.hg/bla.i')
     'data/foo.i/bla.i'
     >>> decodedir(b'data/foo.i.hg.hg/bla.i')
     'data/foo.i.hg/bla.i'
     """
     if b".hg/" not in path:
         return path
     return (
         path.replace(b".d.hg/", b".d/")
         .replace(b".i.hg/", b".i/")
         .replace(b".hg.hg/", b".hg/")
     )
 
 
 def _reserved():
     """characters that are problematic for filesystems
 
     * ascii escapes (0..31)
     * ascii hi (126..255)
     * windows specials
 
     these characters will be escaped by encodefunctions
     """
     winreserved = [ord(x) for x in u'\\:*?"<>|']
     for x in range(32):
         yield x
     for x in range(126, 256):
         yield x
     for x in winreserved:
         yield x
 
 
 def _buildencodefun():
     """
     >>> enc, dec = _buildencodefun()
 
     >>> enc(b'nothing/special.txt')
     'nothing/special.txt'
     >>> dec(b'nothing/special.txt')
     'nothing/special.txt'
 
     >>> enc(b'HELLO')
     '_h_e_l_l_o'
     >>> dec(b'_h_e_l_l_o')
     'HELLO'
 
     >>> enc(b'hello:world?')
     'hello~3aworld~3f'
     >>> dec(b'hello~3aworld~3f')
     'hello:world?'
 
     >>> enc(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     >>> dec(b'the~07quick~adshot')
     'the\\x07quick\\xadshot'
     """
     e = b'_'
     xchr = pycompat.bytechr
     asciistr = list(map(xchr, range(127)))
     capitals = list(range(ord(b"A"), ord(b"Z") + 1))
 
     cmap = {x: x for x in asciistr}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in capitals + [ord(e)]:
         cmap[xchr(x)] = e + xchr(x).lower()
 
     dmap = {}
     for k, v in cmap.items():
         dmap[v] = k
 
     def decode(s):
         i = 0
         while i < len(s):
             for l in range(1, 4):
                 try:
                     yield dmap[s[i : i + l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
 
     return (
         lambda s: b''.join([cmap[s[c : c + 1]] for c in range(len(s))]),
         lambda s: b''.join(list(decode(s))),
     )
 
 
 _encodefname, _decodefname = _buildencodefun()
 
 
 def encodefilename(s):
     """
     >>> encodefilename(b'foo.i/bar.d/bla.hg/hi:world?/HELLO')
     'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o'
     """
     return _encodefname(encodedir(s))
 
 
 def decodefilename(s):
     """
     >>> decodefilename(b'foo.i.hg/bar.d.hg/bla.hg.hg/hi~3aworld~3f/_h_e_l_l_o')
     'foo.i/bar.d/bla.hg/hi:world?/HELLO'
     """
     return decodedir(_decodefname(s))
 
 
 def _buildlowerencodefun():
     """
     >>> f = _buildlowerencodefun()
     >>> f(b'nothing/special.txt')
     'nothing/special.txt'
     >>> f(b'HELLO')
     'hello'
     >>> f(b'hello:world?')
     'hello~3aworld~3f'
     >>> f(b'the\\x07quick\\xADshot')
     'the~07quick~adshot'
     """
     xchr = pycompat.bytechr
     cmap = {xchr(x): xchr(x) for x in range(127)}
     for x in _reserved():
         cmap[xchr(x)] = b"~%02x" % x
     for x in range(ord(b"A"), ord(b"Z") + 1):
         cmap[xchr(x)] = xchr(x).lower()
 
     def lowerencode(s):
         return b"".join([cmap[c] for c in pycompat.iterbytestr(s)])
 
     return lowerencode
 
 
 lowerencode = getattr(parsers, 'lowerencode', None) or _buildlowerencodefun()
 
 # Windows reserved names: con, prn, aux, nul, com1..com9, lpt1..lpt9
 _winres3 = (b'aux', b'con', b'prn', b'nul')  # length 3
 _winres4 = (b'com', b'lpt')  # length 4 (with trailing 1..9)
 
 
 def _auxencode(path, dotencode):
     """
     Encodes filenames containing names reserved by Windows or which end in
     period or space. Does not touch other single reserved characters c.
     Specifically, c in '\\:*?"<>|' or ord(c) <= 31 are *not* encoded here.
     Additionally encodes space or period at the beginning, if dotencode is
     True. Parameter path is assumed to be all lowercase.
     A segment only needs encoding if a reserved name appears as a
     basename (e.g. "aux", "aux.foo"). A directory or file named "foo.aux"
     doesn't need encoding.
 
     >>> s = b'.foo/aux.txt/txt.aux/con/prn/nul/foo.'
     >>> _auxencode(s.split(b'/'), True)
     ['~2efoo', 'au~78.txt', 'txt.aux', 'co~6e', 'pr~6e', 'nu~6c', 'foo~2e']
     >>> s = b'.com1com2/lpt9.lpt4.lpt1/conprn/com0/lpt0/foo.'
     >>> _auxencode(s.split(b'/'), False)
     ['.com1com2', 'lp~749.lpt4.lpt1', 'conprn', 'com0', 'lpt0', 'foo~2e']
     >>> _auxencode([b'foo. '], True)
     ['foo.~20']
     >>> _auxencode([b' .foo'], True)
     ['~20.foo']
     """
     for i, n in enumerate(path):
         if not n:
             continue
         if dotencode and n[0] in b'. ':
             n = b"~%02x" % ord(n[0:1]) + n[1:]
             path[i] = n
         else:
             l = n.find(b'.')
             if l == -1:
                 l = len(n)
             if (l == 3 and n[:3] in _winres3) or (
                 l == 4
                 and n[3:4] <= b'9'
                 and n[3:4] >= b'1'
                 and n[:3] in _winres4
             ):
                 # encode third letter ('aux' -> 'au~78')
                 ec = b"~%02x" % ord(n[2:3])
                 n = n[0:2] + ec + n[3:]
                 path[i] = n
         if n[-1] in b'. ':
             # encode last period or space ('foo...' -> 'foo..~2e')
             path[i] = n[:-1] + b"~%02x" % ord(n[-1:])
     return path
 
 
 _maxstorepathlen = 120
 _dirprefixlen = 8
 _maxshortdirslen = 8 * (_dirprefixlen + 1) - 4
 
 
 def _hashencode(path, dotencode):
     digest = hex(hashutil.sha1(path).digest())
     le = lowerencode(path[5:]).split(b'/')  # skips prefix 'data/' or 'meta/'
     parts = _auxencode(le, dotencode)
     basename = parts[-1]
     _root, ext = os.path.splitext(basename)
     sdirs = []
     sdirslen = 0
     for p in parts[:-1]:
         d = p[:_dirprefixlen]
         if d[-1] in b'. ':
             # Windows can't access dirs ending in period or space
             d = d[:-1] + b'_'
         if sdirslen == 0:
             t = len(d)
         else:
             t = sdirslen + 1 + len(d)
             if t > _maxshortdirslen:
                 break
         sdirs.append(d)
         sdirslen = t
     dirs = b'/'.join(sdirs)
     if len(dirs) > 0:
         dirs += b'/'
     res = b'dh/' + dirs + digest + ext
     spaceleft = _maxstorepathlen - len(res)
     if spaceleft > 0:
         filler = basename[:spaceleft]
         res = b'dh/' + dirs + filler + digest + ext
     return res
 
 
 def _hybridencode(path, dotencode):
     """encodes path with a length limit
 
     Encodes all paths that begin with 'data/', according to the following.
 
     Default encoding (reversible):
 
     Encodes all uppercase letters 'X' as '_x'. All reserved or illegal
     characters are encoded as '~xx', where xx is the two digit hex code
     of the character (see encodefilename).
     Relevant path components consisting of Windows reserved filenames are
     masked by encoding the third character ('aux' -> 'au~78', see _auxencode).
 
     Hashed encoding (not reversible):
 
     If the default-encoded path is longer than _maxstorepathlen, a
     non-reversible hybrid hashing of the path is done instead.
     This encoding uses up to _dirprefixlen characters of all directory
     levels of the lowerencoded path, but not more levels than can fit into
     _maxshortdirslen.
     Then follows the filler followed by the sha digest of the full path.
     The filler is the beginning of the basename of the lowerencoded path
     (the basename is everything after the last path separator). The filler
     is as long as possible, filling in characters from the basename until
     the encoded path has _maxstorepathlen characters (or all chars of the
     basename have been taken).
     The extension (e.g. '.i' or '.d') is preserved.
 
     The string 'data/' at the beginning is replaced with 'dh/', if the hashed
     encoding was used.
     """
     path = encodedir(path)
     ef = _encodefname(path).split(b'/')
     res = b'/'.join(_auxencode(ef, dotencode))
     if len(res) > _maxstorepathlen:
         res = _hashencode(path, dotencode)
     return res
 
 
 def _pathencode(path):
     de = encodedir(path)
     if len(path) > _maxstorepathlen:
         return _hashencode(de, True)
     ef = _encodefname(de).split(b'/')
     res = b'/'.join(_auxencode(ef, True))
     if len(res) > _maxstorepathlen:
         return _hashencode(de, True)
     return res
 
 
 _pathencode = getattr(parsers, 'pathencode', _pathencode)
 
 
 def _plainhybridencode(f):
     return _hybridencode(f, False)
 
 
 def _calcmode(vfs):
     try:
         # files in .hg/ will be created using this mode
         mode = vfs.stat().st_mode
         # avoid some useless chmods
         if (0o777 & ~util.umask) == (0o777 & mode):
             mode = None
     except OSError:
         mode = None
     return mode
 
 
 _data = [
     b'bookmarks',
     b'narrowspec',
     b'data',
     b'meta',
     b'00manifest.d',
     b'00manifest.i',
     b'00changelog.d',
     b'00changelog.i',
     b'phaseroots',
     b'obsstore',
     b'requires',
 ]
 
 REVLOG_FILES_EXT = (
     b'.i',
     b'.idx',
     b'.d',
     b'.dat',
     b'.n',
     b'.nd',
     b'.sda',
 )
 # file extension that also use a `-SOMELONGIDHASH.ext` form
 REVLOG_FILES_LONG_EXT = (
     b'.nd',
     b'.idx',
     b'.dat',
     b'.sda',
 )
 # files that are "volatile" and might change between listing and streaming
 #
 # note: the ".nd" file are nodemap data and won't "change" but they might be
 # deleted.
 REVLOG_FILES_VOLATILE_EXT = (b'.n', b'.nd')
 
 # some exception to the above matching
 #
 # XXX This is currently not in use because of issue6542
 EXCLUDED = re.compile(br'.*undo\.[^/]+\.(nd?|i)$')
 
 
 def is_revlog(f, kind, st):
     if kind != stat.S_IFREG:
         return False
     if f.endswith(REVLOG_FILES_EXT):
         return True
     return False
 
 
 def is_revlog_file(f):
     if f.endswith(REVLOG_FILES_EXT):
         return True
     return False
 
 
 @attr.s(slots=True)
 class StoreFile:
     """a file matching a store entry"""
 
     unencoded_path = attr.ib()
     _file_size = attr.ib(default=None)
     is_volatile = attr.ib(default=False)
 
     def file_size(self, vfs):
         if self._file_size is None:
             if vfs is None:
                 msg = b"calling vfs-less file_size without prior call: %s"
                 msg %= self.unencoded_path
                 raise error.ProgrammingError(msg)
             try:
                 self._file_size = vfs.stat(self.unencoded_path).st_size
             except FileNotFoundError:
                 self._file_size = 0
         return self._file_size
 
     @property
     def has_size(self):
         return self._file_size is not None
 
     def get_stream(self, vfs, copies):
         """return data "stream" information for this file
 
         (unencoded_file_path, content_iterator, content_size)
         """
         size = self.file_size(None)
 
         def get_stream():
             actual_path = copies[vfs.join(self.unencoded_path)]
             with open(actual_path, 'rb') as fp:
                 yield None  # ready to stream
                 if size <= 65536:
                     yield fp.read(size)
                 else:
                     yield from util.filechunkiter(fp, limit=size)
 
         s = get_stream()
         next(s)
         return (self.unencoded_path, s, size)
 
 
 @attr.s(slots=True, init=False)
 class BaseStoreEntry:
     """An entry in the store
 
     This is returned by `store.walk` and represent some data in the store."""
 
     maybe_volatile = True
 
     def files(self) -> List[StoreFile]:
         raise NotImplementedError
 
     def get_streams(
         self,
         repo=None,
         vfs=None,
         copies=None,
         max_changeset=None,
         preserve_file_count=False,
     ):
         """return a list of data stream associated to files for this entry
 
         return [(unencoded_file_path, content_iterator, content_size), …]
         """
         assert vfs is not None
         return [f.get_stream(vfs, copies) for f in self.files()]
 
 
 @attr.s(slots=True, init=False)
 class SimpleStoreEntry(BaseStoreEntry):
     """A generic entry in the store"""
 
     is_revlog = False
 
     maybe_volatile = attr.ib()
     _entry_path = attr.ib()
     _is_volatile = attr.ib(default=False)
     _file_size = attr.ib(default=None)
     _files = attr.ib(default=None)
 
     def __init__(
         self,
         entry_path,
         is_volatile=False,
         file_size=None,
     ):
         super().__init__()
         self._entry_path = entry_path
         self._is_volatile = is_volatile
         self._file_size = file_size
         self._files = None
         self.maybe_volatile = is_volatile
 
     def files(self) -> List[StoreFile]:
         if self._files is None:
             self._files = [
                 StoreFile(
                     unencoded_path=self._entry_path,
                     file_size=self._file_size,
                     is_volatile=self._is_volatile,
                 )
             ]
         return self._files
 
 
 @attr.s(slots=True, init=False)
 class RevlogStoreEntry(BaseStoreEntry):
     """A revlog entry in the store"""
 
     is_revlog = True
 
     revlog_type = attr.ib(default=None)
     target_id = attr.ib(default=None)
     maybe_volatile = attr.ib(default=True)
     _path_prefix = attr.ib(default=None)
     _details = attr.ib(default=None)
     _files = attr.ib(default=None)
 
     def __init__(
         self,
         revlog_type,
         path_prefix,
         target_id,
         details,
     ):
         super().__init__()
         self.revlog_type = revlog_type
         self.target_id = target_id
         self._path_prefix = path_prefix
         assert b'.i' in details, (path_prefix, details)
         for ext in details:
             if ext.endswith(REVLOG_FILES_VOLATILE_EXT):
                 self.maybe_volatile = True
                 break
         else:
             self.maybe_volatile = False
         self._details = details
         self._files = None
 
     @property
     def is_changelog(self):
         return self.revlog_type == KIND_CHANGELOG
 
     @property
     def is_manifestlog(self):
         return self.revlog_type == KIND_MANIFESTLOG
 
     @property
     def is_filelog(self):
         return self.revlog_type == KIND_FILELOG
 
     def main_file_path(self):
         """unencoded path of the main revlog file"""
         return self._path_prefix + b'.i'
 
     def files(self) -> List[StoreFile]:
         if self._files is None:
             self._files = []
             for ext in sorted(self._details, key=_ext_key):
                 path = self._path_prefix + ext
                 file_size = self._details[ext]
                 # files that are "volatile" and might change between
                 # listing and streaming
                 #
                 # note: the ".nd" file are nodemap data and won't "change"
                 # but they might be deleted.
                 volatile = ext.endswith(REVLOG_FILES_VOLATILE_EXT)
                 f = StoreFile(path, file_size, volatile)
                 self._files.append(f)
         return self._files
 
     def get_streams(
         self,
         repo=None,
         vfs=None,
         copies=None,
         max_changeset=None,
         preserve_file_count=False,
     ):
         pre_sized = all(f.has_size for f in self.files())
         if pre_sized and (
             repo is None
             or max_changeset is None
             # This use revlog-v2, ignore for now
             or any(k.endswith(b'.idx') for k in self._details.keys())
             # This is not inline, no race expected
             or b'.d' in self._details
         ):
             return super().get_streams(
                 repo=repo,
                 vfs=vfs,
                 copies=copies,
                 max_changeset=max_changeset,
                 preserve_file_count=preserve_file_count,
             )
         elif not preserve_file_count:
             stream = [
                 f.get_stream(vfs, copies)
                 for f in self.files()
                 if not f.unencoded_path.endswith((b'.i', b'.d'))
             ]
             rl = self.get_revlog_instance(repo).get_revlog()
             rl_stream = rl.get_streams(max_changeset)
             stream.extend(rl_stream)
             return stream
 
         name_to_size = {}
         for f in self.files():
             name_to_size[f.unencoded_path] = f.file_size(None)
 
         stream = [
             f.get_stream(vfs, copies)
             for f in self.files()
             if not f.unencoded_path.endswith(b'.i')
         ]
 
         index_path = self._path_prefix + b'.i'
 
         index_file = None
         try:
             index_file = vfs(index_path)
             header = index_file.read(INDEX_HEADER.size)
             if revlogmod.revlog.is_inline_index(header):
                 size = name_to_size[index_path]
 
                 # no split underneath, just return the stream
                 def get_stream():
                     fp = index_file
                     try:
                         fp.seek(0)
                         yield None
                         if size <= 65536:
                             yield fp.read(size)
                         else:
                             yield from util.filechunkiter(fp, limit=size)
                     finally:
                         fp.close()
 
                 s = get_stream()
                 next(s)
                 index_file = None
                 stream.append((index_path, s, size))
             else:
                 rl = self.get_revlog_instance(repo).get_revlog()
                 rl_stream = rl.get_streams(max_changeset, force_inline=True)
                 for name, s, size in rl_stream:
                     if name_to_size.get(name, 0) != size:
                         msg = _(b"expected %d bytes but %d provided for %s")
                         msg %= name_to_size.get(name, 0), size, name
                         raise error.Abort(msg)
                 stream.extend(rl_stream)
         finally:
             if index_file is not None:
                 index_file.close()
 
         files = self.files()
         assert len(stream) == len(files), (
             stream,
             files,
             self._path_prefix,
             self.target_id,
         )
         return stream
 
     def get_revlog_instance(self, repo):
         """Obtain a revlog instance from this store entry
 
         An instance of the appropriate class is returned.
         """
         if self.is_changelog:
             return changelog.changelog(repo.svfs)
         elif self.is_manifestlog:
             mandir = self.target_id
             return manifest.manifestrevlog(
                 repo.nodeconstants, repo.svfs, tree=mandir
             )
         else:
             return filelog.filelog(repo.svfs, self.target_id)
 
 
 def _gather_revlog(files_data):
     """group files per revlog prefix
 
     The returns a two level nested dict. The top level key is the revlog prefix
     without extension, the second level is all the file "suffix" that were
     seen for this revlog and arbitrary file data as value.
     """
     revlogs = collections.defaultdict(dict)
     for u, value in files_data:
         name, ext = _split_revlog_ext(u)
         revlogs[name][ext] = value
     return sorted(revlogs.items())
 
 
 def _split_revlog_ext(filename):
     """split the revlog file prefix from the variable extension"""
     if filename.endswith(REVLOG_FILES_LONG_EXT):
         char = b'-'
     else:
         char = b'.'
     idx = filename.rfind(char)
     return filename[:idx], filename[idx:]
 
 
 def _ext_key(ext):
     """a key to order revlog suffix
 
     important to issue .i after other entry."""
     # the only important part of this order is to keep the `.i` last.
     if ext.endswith(b'.n'):
         return (0, ext)
     elif ext.endswith(b'.nd'):
         return (10, ext)
     elif ext.endswith(b'.d'):
         return (20, ext)
     elif ext.endswith(b'.i'):
         return (50, ext)
     else:
         return (40, ext)
 
 
 class basicstore:
     '''base class for local repository stores'''
 
     def __init__(self, path, vfstype):
         vfs = vfstype(path)
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodedir)
         self.opener = self.vfs
 
     def join(self, f):
         return self.path + b'/' + encodedir(f)
 
     def _walk(self, relpath, recurse, undecodable=None):
         '''yields (revlog_type, unencoded, size)'''
         path = self.path
         if relpath:
             path += b'/' + relpath
         striplen = len(self.path) + 1
         l = []
         if self.rawvfs.isdir(path):
             visit = [path]
             readdir = self.rawvfs.readdir
             while visit:
                 p = visit.pop()
                 for f, kind, st in readdir(p, stat=True):
                     fp = p + b'/' + f
                     if is_revlog(f, kind, st):
                         n = util.pconvert(fp[striplen:])
                         l.append((decodedir(n), st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
 
         l.sort()
         return l
 
     def changelog(self, trypending, concurrencychecker=None):
         return changelog.changelog(
             self.vfs,
             trypending=trypending,
             concurrencychecker=concurrencychecker,
         )
 
-    def manifestlog(self, repo, storenarrowmatch):
+    def manifestlog(self, repo, storenarrowmatch) -> manifest.ManifestLog:
         rootstore = manifest.manifestrevlog(repo.nodeconstants, self.vfs)
         return manifest.manifestlog(self.vfs, repo, rootstore, storenarrowmatch)
 
     def data_entries(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         """Like walk, but excluding the changelog and root manifest.
 
         When [undecodable] is None, revlogs names that can't be
         decoded cause an exception. When it is provided, it should
         be a list and the filenames that can't be decoded are added
         to it instead. This is very rarely needed."""
         dirs = [
             (b'data', KIND_FILELOG, False),
             (b'meta', KIND_MANIFESTLOG, True),
         ]
         for base_dir, rl_type, strip_filename in dirs:
             files = self._walk(base_dir, True, undecodable=undecodable)
             for revlog, details in _gather_revlog(files):
                 revlog_target_id = revlog.split(b'/', 1)[1]
                 if strip_filename and b'/' in revlog:
                     revlog_target_id = revlog_target_id.rsplit(b'/', 1)[0]
                     revlog_target_id += b'/'
                 yield RevlogStoreEntry(
                     path_prefix=revlog,
                     revlog_type=rl_type,
                     target_id=revlog_target_id,
                     details=details,
                 )
 
     def top_entries(
         self, phase=False, obsolescence=False
     ) -> Generator[BaseStoreEntry, None, None]:
         if phase and self.vfs.exists(b'phaseroots'):
             yield SimpleStoreEntry(
                 entry_path=b'phaseroots',
                 is_volatile=True,
             )
 
         if obsolescence and self.vfs.exists(b'obsstore'):
             # XXX if we had the file size it could be non-volatile
             yield SimpleStoreEntry(
                 entry_path=b'obsstore',
                 is_volatile=True,
             )
 
         files = reversed(self._walk(b'', False))
 
         changelogs = collections.defaultdict(dict)
         manifestlogs = collections.defaultdict(dict)
 
         for u, s in files:
             if u.startswith(b'00changelog'):
                 name, ext = _split_revlog_ext(u)
                 changelogs[name][ext] = s
             elif u.startswith(b'00manifest'):
                 name, ext = _split_revlog_ext(u)
                 manifestlogs[name][ext] = s
             else:
                 yield SimpleStoreEntry(
                     entry_path=u,
                     is_volatile=False,
                     file_size=s,
                 )
         # yield manifest before changelog
         top_rl = [
             (manifestlogs, KIND_MANIFESTLOG),
             (changelogs, KIND_CHANGELOG),
         ]
         assert len(manifestlogs) <= 1
         assert len(changelogs) <= 1
         for data, revlog_type in top_rl:
             for revlog, details in sorted(data.items()):
                 yield RevlogStoreEntry(
                     path_prefix=revlog,
                     revlog_type=revlog_type,
                     target_id=b'',
                     details=details,
                 )
 
     def walk(
         self, matcher=None, phase=False, obsolescence=False
     ) -> Generator[BaseStoreEntry, None, None]:
         """return files related to data storage (ie: revlogs)
 
         yields instance from BaseStoreEntry subclasses
 
         if a matcher is passed, storage files of only those tracked paths
         are passed with matches the matcher
         """
         # yield data files first
         for x in self.data_entries(matcher):
             yield x
         for x in self.top_entries(phase=phase, obsolescence=obsolescence):
             yield x
 
     def copylist(self):
         return _data
 
     def write(self, tr):
         pass
 
     def invalidatecaches(self):
         pass
 
     def markremoved(self, fn):
         pass
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # file?
         if self.vfs.exists(path + b".i"):
             return True
         # dir?
         if not path.endswith(b"/"):
             path = path + b"/"
         return self.vfs.exists(path)
 
 
 class encodedstore(basicstore):
     def __init__(self, path, vfstype):
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         self.vfs = vfsmod.filtervfs(vfs, encodefilename)
         self.opener = self.vfs
 
     def _walk(self, relpath, recurse, undecodable=None):
         old = super()._walk(relpath, recurse)
         new = []
         for f1, value in old:
             try:
                 f2 = decodefilename(f1)
             except KeyError:
                 if undecodable is None:
                     msg = _(b'undecodable revlog name %s') % f1
                     raise error.StorageError(msg)
                 else:
                     undecodable.append(f1)
                     continue
             new.append((f2, value))
         return new
 
     def data_entries(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         entries = super(encodedstore, self).data_entries(
             undecodable=undecodable
         )
         for entry in entries:
             if _match_tracked_entry(entry, matcher):
                 yield entry
 
     def join(self, f):
         return self.path + b'/' + encodefilename(f)
 
     def copylist(self):
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in _data]
 
 
 class fncache:
     # the filename used to be partially encoded
     # hence the encodedir/decodedir dance
     def __init__(self, vfs):
         self.vfs = vfs
         self._ignores = set()
         self.entries = None
         self._dirty = False
         # set of new additions to fncache
         self.addls = set()
 
     def ensureloaded(self, warn=None):
         """read the fncache file if not already read.
 
         If the file on disk is corrupted, raise. If warn is provided,
         warn and keep going instead."""
         if self.entries is None:
             self._load(warn)
 
     def _load(self, warn=None):
         '''fill the entries from the fncache file'''
         self._dirty = False
         try:
             fp = self.vfs(b'fncache', mode=b'rb')
         except IOError:
             # skip nonexistent file
             self.entries = set()
             return
 
         self.entries = set()
         chunk = b''
         for c in iter(functools.partial(fp.read, fncache_chunksize), b''):
             chunk += c
             try:
                 p = chunk.rindex(b'\n')
                 self.entries.update(decodedir(chunk[: p + 1]).splitlines())
                 chunk = chunk[p + 1 :]
             except ValueError:
                 # substring '\n' not found, maybe the entry is bigger than the
                 # chunksize, so let's keep iterating
                 pass
 
         if chunk:
             msg = _(b"fncache does not ends with a newline")
             if warn:
                 warn(msg + b'\n')
             else:
                 raise error.Abort(
                     msg,
                     hint=_(
                         b"use 'hg debugrebuildfncache' to "
                         b"rebuild the fncache"
                     ),
                 )
         self._checkentries(fp, warn)
         fp.close()
 
     def _checkentries(self, fp, warn):
         """make sure there is no empty string in entries"""
         if b'' in self.entries:
             fp.seek(0)
             for n, line in enumerate(fp):
                 if not line.rstrip(b'\n'):
                     t = _(b'invalid entry in fncache, line %d') % (n + 1)
                     if warn:
                         warn(t + b'\n')
                     else:
                         raise error.Abort(t)
 
     def write(self, tr):
         if self._dirty:
             assert self.entries is not None
             self.entries = self.entries | self.addls
             self.addls = set()
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'wb', atomictemp=True)
             if self.entries:
                 fp.write(encodedir(b'\n'.join(self.entries) + b'\n'))
             fp.close()
             self._dirty = False
         if self.addls:
             # if we have just new entries, let's append them to the fncache
             tr.addbackup(b'fncache')
             fp = self.vfs(b'fncache', mode=b'ab', atomictemp=True)
             if self.addls:
                 fp.write(encodedir(b'\n'.join(self.addls) + b'\n'))
             fp.close()
             self.entries = None
             self.addls = set()
 
     def addignore(self, fn):
         self._ignores.add(fn)
 
     def add(self, fn):
         if fn in self._ignores:
             return
         if self.entries is None:
             self._load()
         if fn not in self.entries:
             self.addls.add(fn)
 
     def remove(self, fn):
         if self.entries is None:
             self._load()
         if fn in self.addls:
             self.addls.remove(fn)
             return
         try:
             self.entries.remove(fn)
             self._dirty = True
         except KeyError:
             pass
 
     def __contains__(self, fn):
         if fn in self.addls:
             return True
         if self.entries is None:
             self._load()
         return fn in self.entries
 
     def __iter__(self):
         if self.entries is None:
             self._load()
         return iter(self.entries | self.addls)
 
 
 class _fncachevfs(vfsmod.proxyvfs):
     def __init__(self, vfs, fnc, encode):
         vfsmod.proxyvfs.__init__(self, vfs)
         self.fncache = fnc
         self.encode = encode
 
     def __call__(self, path, mode=b'r', *args, **kw):
         encoded = self.encode(path)
         if (
             mode not in (b'r', b'rb')
             and (path.startswith(b'data/') or path.startswith(b'meta/'))
             and is_revlog_file(path)
         ):
             # do not trigger a fncache load when adding a file that already is
             # known to exist.
             notload = self.fncache.entries is None and (
                 # if the file has size zero, it should be considered as missing.
                 # Such zero-size files are the result of truncation when a
                 # transaction is aborted.
                 self.vfs.exists(encoded)
                 and self.vfs.stat(encoded).st_size
             )
             if not notload:
                 self.fncache.add(path)
         return self.vfs(encoded, mode, *args, **kw)
 
     def join(self, path):
         if path:
             return self.vfs.join(self.encode(path))
         else:
             return self.vfs.join(path)
 
     def register_file(self, path):
         """generic hook point to lets fncache steer its stew"""
         if path.startswith(b'data/') or path.startswith(b'meta/'):
             self.fncache.add(path)
 
 
 class fncachestore(basicstore):
     def __init__(self, path, vfstype, dotencode):
         if dotencode:
             encode = _pathencode
         else:
             encode = _plainhybridencode
         self.encode = encode
         vfs = vfstype(path + b'/store')
         self.path = vfs.base
         self.pathsep = self.path + b'/'
         self.createmode = _calcmode(vfs)
         vfs.createmode = self.createmode
         self.rawvfs = vfs
         fnc = fncache(vfs)
         self.fncache = fnc
         self.vfs = _fncachevfs(vfs, fnc, encode)
         self.opener = self.vfs
 
     def join(self, f):
         return self.pathsep + self.encode(f)
 
     def getsize(self, path):
         return self.rawvfs.stat(path).st_size
 
     def data_entries(
         self, matcher=None, undecodable=None
     ) -> Generator[BaseStoreEntry, None, None]:
         # Note: all files in fncache should be revlog related, However the
         # fncache might contains such file added by previous version of
         # Mercurial.
         files = ((f, None) for f in self.fncache if is_revlog_file(f))
         by_revlog = _gather_revlog(files)
         for revlog, details in by_revlog:
             if revlog.startswith(b'data/'):
                 rl_type = KIND_FILELOG
                 revlog_target_id = revlog.split(b'/', 1)[1]
             elif revlog.startswith(b'meta/'):
                 rl_type = KIND_MANIFESTLOG
                 # drop the initial directory and the `00manifest` file part
                 tmp = revlog.split(b'/', 1)[1]
                 revlog_target_id = tmp.rsplit(b'/', 1)[0] + b'/'
             else:
                 # unreachable
                 assert False, revlog
             entry = RevlogStoreEntry(
                 path_prefix=revlog,
                 revlog_type=rl_type,
                 target_id=revlog_target_id,
                 details=details,
             )
             if _match_tracked_entry(entry, matcher):
                 yield entry
 
     def copylist(self):
         d = (
             b'bookmarks',
             b'narrowspec',
             b'data',
             b'meta',
             b'dh',
             b'fncache',
             b'phaseroots',
             b'obsstore',
             b'00manifest.d',
             b'00manifest.i',
             b'00changelog.d',
             b'00changelog.i',
             b'requires',
         )
         return [b'requires', b'00changelog.i'] + [b'store/' + f for f in d]
 
     def write(self, tr):
         self.fncache.write(tr)
 
     def invalidatecaches(self):
         self.fncache.entries = None
         self.fncache.addls = set()
 
     def markremoved(self, fn):
         self.fncache.remove(fn)
 
     def _exists(self, f):
         ef = self.encode(f)
         try:
             self.getsize(ef)
             return True
         except FileNotFoundError:
             return False
 
     def __contains__(self, path):
         '''Checks if the store contains path'''
         path = b"/".join((b"data", path))
         # check for files (exact match)
         e = path + b'.i'
         if e in self.fncache and self._exists(e):
             return True
         # now check for directories (prefix match)
         if not path.endswith(b'/'):
             path += b'/'
         for e in self.fncache:
             if e.startswith(path) and self._exists(e):
                 return True
         return False

mercurial/unionrepo.py

@@ -1,344 +1,351 b''
 # unionrepo.py - repository class for viewing union of repository changesets
 #
 # Derived from bundlerepo.py
 # Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
 # Copyright 2013 Unity Technologies, Mads Kiilerich <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Repository class for "in-memory pull" of one local repository to another,
 allowing operations like diff and log with revsets.
 """
 
 import contextlib
 
 
 from .i18n import _
 
 from . import (
     changelog,
     cmdutil,
     encoding,
     error,
     filelog,
     localrepo,
     manifest,
     mdiff,
     pathutil,
     revlog,
     util,
     vfs as vfsmod,
 )
 
 from .revlogutils import (
     constants as revlog_constants,
 )
 
 
 class unionrevlog(revlog.revlog):
     def __init__(self, opener, radix, revlog2, linkmapper):
         # How it works:
         # To retrieve a revision, we just need to know the node id so we can
         # look it up in revlog2.
         #
         # To differentiate a rev in the second revlog from a rev in the revlog,
         # we check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
         target = getattr(revlog2, 'target', None)
         if target is None:
             # a revlog wrapper, eg: the manifestlog that is not an actual revlog
             target = revlog2._revlog.target
         revlog.revlog.__init__(self, opener, target=target, radix=radix)
         self.revlog2 = revlog2
 
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set()  # used by 'bundle()' revset expression
         for rev2 in self.revlog2:
             rev = self.revlog2.index[rev2]
             # rev numbers - in revlog2, very different from self.rev
             (
                 _start,
                 _csize,
                 rsize,
                 base,
                 linkrev,
                 p1rev,
                 p2rev,
                 node,
                 _sdo,
                 _sds,
                 _dcm,
                 _sdcm,
                 rank,
             ) = rev
             flags = _start & 0xFFFF
 
             if linkmapper is None:  # link is to same revlog
                 assert linkrev == rev2  # we never link back
                 link = n
             else:  # rev must be mapped from repo2 cl to unified cl by linkmapper
                 link = linkmapper(linkrev)
 
             if linkmapper is not None:  # link is to same revlog
                 base = linkmapper(base)
 
             this_rev = self.index.get_rev(node)
             if this_rev is not None:
                 # this happens for the common revlog revisions
                 self.bundlerevs.add(this_rev)
                 continue
 
             p1node = self.revlog2.node(p1rev)
             p2node = self.revlog2.node(p2rev)
 
             # TODO: it's probably wrong to set compressed length to -1, but
             # I have no idea if csize is valid in the base revlog context.
             e = (
                 flags,
                 -1,
                 rsize,
                 base,
                 link,
                 self.rev(p1node),
                 self.rev(p2node),
                 node,
                 0,  # sidedata offset
                 0,  # sidedata size
                 revlog_constants.COMP_MODE_INLINE,
                 revlog_constants.COMP_MODE_INLINE,
                 rank,
             )
             self.index.append(e)
             self.bundlerevs.add(n)
             n += 1
 
     @contextlib.contextmanager
     def reading(self):
         if 0 <= len(self.bundlerevs) < len(self.index):
             read_1 = super().reading
         else:
             read_1 = util.nullcontextmanager
         if 0 < len(self.bundlerevs):
             read_2 = self.revlog2.reading
         else:
             read_2 = util.nullcontextmanager
         with read_1(), read_2():
             yield
 
     def _chunk(self, rev):
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         return self.revlog2._chunk(self.node(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             return self.revlog2.revdiff(
                 self.revlog2.rev(self.node(rev1)),
                 self.revlog2.rev(self.node(rev2)),
             )
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return super(unionrevlog, self).revdiff(rev1, rev2)
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def _revisiondata(self, nodeorrev, raw=False):
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if rev > self.repotiprev:
             # work around manifestrevlog NOT being a revlog
             revlog2 = getattr(self.revlog2, '_revlog', self.revlog2)
             func = revlog2._revisiondata
         else:
             func = super(unionrevlog, self)._revisiondata
         return func(node, raw=raw)
 
     def addrevision(
         self,
         text,
         transaction,
         link,
         p1,
         p2,
         cachedelta=None,
         node=None,
         flags=revlog.REVIDX_DEFAULT_FLAGS,
         deltacomputer=None,
         sidedata=None,
     ):
         raise NotImplementedError
 
     def addgroup(
         self,
         deltas,
         linkmapper,
         transaction,
         alwayscache=False,
         addrevisioncb=None,
         duplicaterevisioncb=None,
         debug_info=None,
         delta_base_reuse_policy=None,
     ):
         raise NotImplementedError
 
     def strip(self, minlink, transaction):
         raise NotImplementedError
 
     def checksize(self):
         raise NotImplementedError
 
 
 class unionchangelog(unionrevlog, changelog.changelog):
     def __init__(self, opener, opener2):
         changelog.changelog.__init__(self, opener)
         linkmapper = None
         changelog2 = changelog.changelog(opener2)
         unionrevlog.__init__(self, opener, self.radix, changelog2, linkmapper)
 
 
 class unionmanifest(unionrevlog, manifest.manifestrevlog):
+    repotiprev: int
+    revlog2: manifest.ManifestRevlog
+
     def __init__(self, nodeconstants, opener, opener2, linkmapper):
         # XXX manifestrevlog is not actually a revlog , so mixing it with
         # bundlerevlog is not a good idea.
         manifest.manifestrevlog.__init__(self, nodeconstants, opener)
         manifest2 = manifest.manifestrevlog(nodeconstants, opener2)
         unionrevlog.__init__(
             self, opener, self._revlog.radix, manifest2, linkmapper
         )
 
 
 class unionfilelog(filelog.filelog):
+    _revlog: unionrevlog
+    repotiprev: int
+    revlog2: revlog.revlog
+
     def __init__(self, opener, path, opener2, linkmapper, repo):
         filelog.filelog.__init__(self, opener, path)
         filelog2 = filelog.filelog(opener2, path)
         self._revlog = unionrevlog(
             opener, self._revlog.radix, filelog2._revlog, linkmapper
         )
         self._repo = repo
         self.repotiprev = self._revlog.repotiprev
         self.revlog2 = self._revlog.revlog2
 
     def iscensored(self, rev):
         """Check if a revision is censored."""
         if rev <= self.repotiprev:
             return filelog.filelog.iscensored(self, rev)
         node = self.node(rev)
         return self.revlog2.iscensored(self.revlog2.rev(node))
 
 
 class unionpeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 
 class unionrepository:
     """Represents the union of data in 2 repositories.
 
     Instances are not usable if constructed directly. Use ``instance()``
     or ``makeunionrepository()`` to create a usable instance.
     """
 
     def __init__(self, repo2, url):
         self.repo2 = repo2
         self._url = url
 
         self.ui.setconfig(b'phases', b'publish', False, b'unionrepo')
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         return unionchangelog(self.svfs, self.repo2.svfs)
 
     @localrepo.unfilteredpropertycache
     def manifestlog(self):
         rootstore = unionmanifest(
             self.nodeconstants,
             self.svfs,
             self.repo2.svfs,
             self.unfiltered()._clrev,
         )
         return manifest.manifestlog(
             self.svfs, self, rootstore, self.narrowmatch()
         )
 
     def _clrev(self, rev2):
         """map from repo2 changelog rev to temporary rev in self.changelog"""
         node = self.repo2.changelog.node(rev2)
         return self.changelog.rev(node)
 
     def url(self):
         return self._url
 
     def file(self, f):
         return unionfilelog(
             self.svfs, f, self.repo2.svfs, self.unfiltered()._clrev, self
         )
 
     def close(self):
         self.repo2.close()
 
     def cancopy(self):
         return False
 
     def peer(self, path=None, remotehidden=False):
         return unionpeer(self, path=None, remotehidden=remotehidden)
 
     def getcwd(self):
         return encoding.getcwd()  # always outside the repo
 
 
 def instance(ui, path, create, intents=None, createopts=None):
     if create:
         raise error.Abort(_(b'cannot create new union repository'))
     parentpath = ui.config(b"bundle", b"mainreporoot")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(encoding.getcwd())
         if parentpath is None:
             parentpath = b''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = encoding.getcwd()
         if parentpath == cwd:
             parentpath = b''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd) :]
     if path.startswith(b'union:'):
         s = path.split(b":", 1)[1].split(b"+", 1)
         if len(s) == 1:
             repopath, repopath2 = parentpath, s[0]
         else:
             repopath, repopath2 = s
     else:
         repopath, repopath2 = parentpath, path
 
     return makeunionrepository(ui, repopath, repopath2)
 
 
 def makeunionrepository(ui, repopath1, repopath2):
     """Make a union repository object from 2 local repo paths."""
     repo1 = localrepo.instance(ui, repopath1, create=False)
     repo2 = localrepo.instance(ui, repopath2, create=False)
 
     url = b'union:%s+%s' % (
         util.expandpath(repopath1),
         util.expandpath(repopath2),
     )
 
     class derivedunionrepository(unionrepository, repo1.__class__):
         pass
 
     repo = repo1
     repo.__class__ = derivedunionrepository
     unionrepository.__init__(repo1, repo2, url)
 
     return repo