store: use a StoreEntry object instead of tuple for store files

We want to make the store return more semantic information instead of a stream
of file path. To achieve this, we start with adding a simple object that hold
the same information as the tuple it replace, and do a simple update to the
user code to fetch and use the same information.

From there, we will be able to iteratively upgrade the codebase toward better
objects.

hgext/largefiles/lfutil.py

@@ -1,823 +1,824 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''largefiles utility code: must not import other modules in this package.'''
 
 import contextlib
 import copy
 import os
 import stat
 
 from mercurial.i18n import _
 from mercurial.node import hex
 from mercurial.pycompat import open
 
 from mercurial import (
     dirstate,
     encoding,
     error,
     httpconnection,
     match as matchmod,
     pycompat,
     requirements,
     scmutil,
     sparse,
     util,
     vfs as vfsmod,
 )
 from mercurial.utils import hashutil
 from mercurial.dirstateutils import timestamp
 
 shortname = b'.hglf'
 shortnameslash = shortname + b'/'
 longname = b'largefiles'
 
 # -- Private worker functions ------------------------------------------
 
 
 @contextlib.contextmanager
 def lfstatus(repo, value=True):
     oldvalue = getattr(repo, 'lfstatus', False)
     repo.lfstatus = value
     try:
         yield
     finally:
         repo.lfstatus = oldvalue
 
 
 def getminsize(ui, assumelfiles, opt, default=10):
     lfsize = opt
     if not lfsize and assumelfiles:
         lfsize = ui.config(longname, b'minsize', default=default)
     if lfsize:
         try:
             lfsize = float(lfsize)
         except ValueError:
             raise error.Abort(
                 _(b'largefiles: size must be number (not %s)\n') % lfsize
             )
     if lfsize is None:
         raise error.Abort(_(b'minimum size for largefiles must be specified'))
     return lfsize
 
 
 def link(src, dest):
     """Try to create hardlink - if that fails, efficiently make a copy."""
     util.makedirs(os.path.dirname(dest))
     try:
         util.oslink(src, dest)
     except OSError:
         # if hardlinks fail, fallback on atomic copy
         with open(src, b'rb') as srcf, util.atomictempfile(dest) as dstf:
             for chunk in util.filechunkiter(srcf):
                 dstf.write(chunk)
         os.chmod(dest, os.stat(src).st_mode)
 
 
 def usercachepath(ui, hash):
     """Return the correct location in the "global" largefiles cache for a file
     with the given hash.
     This cache is used for sharing of largefiles across repositories - both
     to preserve download bandwidth and storage space."""
     return os.path.join(_usercachedir(ui), hash)
 
 
 def _usercachedir(ui, name=longname):
     '''Return the location of the "global" largefiles cache.'''
     path = ui.configpath(name, b'usercache')
     if path:
         return path
 
     hint = None
 
     if pycompat.iswindows:
         appdata = encoding.environ.get(
             b'LOCALAPPDATA', encoding.environ.get(b'APPDATA')
         )
         if appdata:
             return os.path.join(appdata, name)
 
         hint = _(b"define %s or %s in the environment, or set %s.usercache") % (
             b"LOCALAPPDATA",
             b"APPDATA",
             name,
         )
     elif pycompat.isdarwin:
         home = encoding.environ.get(b'HOME')
         if home:
             return os.path.join(home, b'Library', b'Caches', name)
 
         hint = _(b"define %s in the environment, or set %s.usercache") % (
             b"HOME",
             name,
         )
     elif pycompat.isposix:
         path = encoding.environ.get(b'XDG_CACHE_HOME')
         if path:
             return os.path.join(path, name)
         home = encoding.environ.get(b'HOME')
         if home:
             return os.path.join(home, b'.cache', name)
 
         hint = _(b"define %s or %s in the environment, or set %s.usercache") % (
             b"XDG_CACHE_HOME",
             b"HOME",
             name,
         )
     else:
         raise error.Abort(
             _(b'unknown operating system: %s\n') % pycompat.osname
         )
 
     raise error.Abort(_(b'unknown %s usercache location') % name, hint=hint)
 
 
 def inusercache(ui, hash):
     path = usercachepath(ui, hash)
     return os.path.exists(path)
 
 
 def findfile(repo, hash):
     """Return store path of the largefile with the specified hash.
     As a side effect, the file might be linked from user cache.
     Return None if the file can't be found locally."""
     path, exists = findstorepath(repo, hash)
     if exists:
         repo.ui.note(_(b'found %s in store\n') % hash)
         return path
     elif inusercache(repo.ui, hash):
         repo.ui.note(_(b'found %s in system cache\n') % hash)
         path = storepath(repo, hash)
         link(usercachepath(repo.ui, hash), path)
         return path
     return None
 
 
 class largefilesdirstate(dirstate.dirstate):
     _large_file_dirstate = True
     _tr_key_suffix = b'-large-files'
 
     def __getitem__(self, key):
         return super(largefilesdirstate, self).__getitem__(unixpath(key))
 
     def set_tracked(self, f):
         return super(largefilesdirstate, self).set_tracked(unixpath(f))
 
     def set_untracked(self, f):
         return super(largefilesdirstate, self).set_untracked(unixpath(f))
 
     def normal(self, f, parentfiledata=None):
         # not sure if we should pass the `parentfiledata` down or throw it
         # away. So throwing it away to stay on the safe side.
         return super(largefilesdirstate, self).normal(unixpath(f))
 
     def remove(self, f):
         return super(largefilesdirstate, self).remove(unixpath(f))
 
     def add(self, f):
         return super(largefilesdirstate, self).add(unixpath(f))
 
     def drop(self, f):
         return super(largefilesdirstate, self).drop(unixpath(f))
 
     def forget(self, f):
         return super(largefilesdirstate, self).forget(unixpath(f))
 
     def normallookup(self, f):
         return super(largefilesdirstate, self).normallookup(unixpath(f))
 
     def _ignore(self, f):
         return False
 
     def write(self, tr):
         # (1) disable PENDING mode always
         #     (lfdirstate isn't yet managed as a part of the transaction)
         # (2) avoid develwarn 'use dirstate.write with ....'
         if tr:
             tr.addbackup(b'largefiles/dirstate', location=b'plain')
         super(largefilesdirstate, self).write(None)
 
 
 def openlfdirstate(ui, repo, create=True):
     """
     Return a dirstate object that tracks largefiles: i.e. its root is
     the repo root, but it is saved in .hg/largefiles/dirstate.
 
     If a dirstate object already exists and is being used for a 'changing_*'
     context, it will be returned.
     """
     sub_dirstate = getattr(repo.dirstate, '_sub_dirstate', None)
     if sub_dirstate is not None:
         return sub_dirstate
     vfs = repo.vfs
     lfstoredir = longname
     opener = vfsmod.vfs(vfs.join(lfstoredir))
     use_dirstate_v2 = requirements.DIRSTATE_V2_REQUIREMENT in repo.requirements
     lfdirstate = largefilesdirstate(
         opener,
         ui,
         repo.root,
         repo.dirstate._validate,
         lambda: sparse.matcher(repo),
         repo.nodeconstants,
         use_dirstate_v2,
     )
 
     # If the largefiles dirstate does not exist, populate and create
     # it. This ensures that we create it on the first meaningful
     # largefiles operation in a new clone.
     if create and not vfs.exists(vfs.join(lfstoredir, b'dirstate')):
         try:
             with repo.wlock(wait=False), lfdirstate.changing_files(repo):
                 matcher = getstandinmatcher(repo)
                 standins = repo.dirstate.walk(
                     matcher, subrepos=[], unknown=False, ignored=False
                 )
 
                 if len(standins) > 0:
                     vfs.makedirs(lfstoredir)
 
                 for standin in standins:
                     lfile = splitstandin(standin)
                     lfdirstate.hacky_extension_update_file(
                         lfile,
                         p1_tracked=True,
                         wc_tracked=True,
                         possibly_dirty=True,
                     )
         except error.LockError:
             # Assume that whatever was holding the lock was important.
             # If we were doing something important, we would already have
             # either the lock or a largefile dirstate.
             pass
     return lfdirstate
 
 
 def lfdirstatestatus(lfdirstate, repo):
     pctx = repo[b'.']
     match = matchmod.always()
     unsure, s, mtime_boundary = lfdirstate.status(
         match, subrepos=[], ignored=False, clean=False, unknown=False
     )
     modified, clean = s.modified, s.clean
     wctx = repo[None]
     for lfile in unsure:
         try:
             fctx = pctx[standin(lfile)]
         except LookupError:
             fctx = None
         if not fctx or readasstandin(fctx) != hashfile(repo.wjoin(lfile)):
             modified.append(lfile)
         else:
             clean.append(lfile)
             st = wctx[lfile].lstat()
             mode = st.st_mode
             size = st.st_size
             mtime = timestamp.reliable_mtime_of(st, mtime_boundary)
             if mtime is not None:
                 cache_data = (mode, size, mtime)
                 lfdirstate.set_clean(lfile, cache_data)
     return s
 
 
 def listlfiles(repo, rev=None, matcher=None):
     """return a list of largefiles in the working copy or the
     specified changeset"""
 
     if matcher is None:
         matcher = getstandinmatcher(repo)
 
     # ignore unknown files in working directory
     return [
         splitstandin(f)
         for f in repo[rev].walk(matcher)
         if rev is not None or repo.dirstate.get_entry(f).any_tracked
     ]
 
 
 def instore(repo, hash, forcelocal=False):
     '''Return true if a largefile with the given hash exists in the store'''
     return os.path.exists(storepath(repo, hash, forcelocal))
 
 
 def storepath(repo, hash, forcelocal=False):
     """Return the correct location in the repository largefiles store for a
     file with the given hash."""
     if not forcelocal and repo.shared():
         return repo.vfs.reljoin(repo.sharedpath, longname, hash)
     return repo.vfs.join(longname, hash)
 
 
 def findstorepath(repo, hash):
     """Search through the local store path(s) to find the file for the given
     hash.  If the file is not found, its path in the primary store is returned.
     The return value is a tuple of (path, exists(path)).
     """
     # For shared repos, the primary store is in the share source.  But for
     # backward compatibility, force a lookup in the local store if it wasn't
     # found in the share source.
     path = storepath(repo, hash, False)
 
     if instore(repo, hash):
         return (path, True)
     elif repo.shared() and instore(repo, hash, True):
         return storepath(repo, hash, True), True
 
     return (path, False)
 
 
 def copyfromcache(repo, hash, filename):
     """Copy the specified largefile from the repo or system cache to
     filename in the repository. Return true on success or false if the
     file was not found in either cache (which should not happened:
     this is meant to be called only after ensuring that the needed
     largefile exists in the cache)."""
     wvfs = repo.wvfs
     path = findfile(repo, hash)
     if path is None:
         return False
     wvfs.makedirs(wvfs.dirname(wvfs.join(filename)))
     # The write may fail before the file is fully written, but we
     # don't use atomic writes in the working copy.
     with open(path, b'rb') as srcfd, wvfs(filename, b'wb') as destfd:
         gothash = copyandhash(util.filechunkiter(srcfd), destfd)
     if gothash != hash:
         repo.ui.warn(
             _(b'%s: data corruption in %s with hash %s\n')
             % (filename, path, gothash)
         )
         wvfs.unlink(filename)
         return False
     return True
 
 
 def copytostore(repo, ctx, file, fstandin):
     wvfs = repo.wvfs
     hash = readasstandin(ctx[fstandin])
     if instore(repo, hash):
         return
     if wvfs.exists(file):
         copytostoreabsolute(repo, wvfs.join(file), hash)
     else:
         repo.ui.warn(
             _(b"%s: largefile %s not available from local store\n")
             % (file, hash)
         )
 
 
 def copyalltostore(repo, node):
     '''Copy all largefiles in a given revision to the store'''
 
     ctx = repo[node]
     for filename in ctx.files():
         realfile = splitstandin(filename)
         if realfile is not None and filename in ctx.manifest():
             copytostore(repo, ctx, realfile, filename)
 
 
 def copytostoreabsolute(repo, file, hash):
     if inusercache(repo.ui, hash):
         link(usercachepath(repo.ui, hash), storepath(repo, hash))
     else:
         util.makedirs(os.path.dirname(storepath(repo, hash)))
         with open(file, b'rb') as srcf:
             with util.atomictempfile(
                 storepath(repo, hash), createmode=repo.store.createmode
             ) as dstf:
                 for chunk in util.filechunkiter(srcf):
                     dstf.write(chunk)
         linktousercache(repo, hash)
 
 
 def linktousercache(repo, hash):
     """Link / copy the largefile with the specified hash from the store
     to the cache."""
     path = usercachepath(repo.ui, hash)
     link(storepath(repo, hash), path)
 
 
 def getstandinmatcher(repo, rmatcher=None):
     '''Return a match object that applies rmatcher to the standin directory'''
     wvfs = repo.wvfs
     standindir = shortname
 
     # no warnings about missing files or directories
     badfn = lambda f, msg: None
 
     if rmatcher and not rmatcher.always():
         pats = [wvfs.join(standindir, pat) for pat in rmatcher.files()]
         if not pats:
             pats = [wvfs.join(standindir)]
         match = scmutil.match(repo[None], pats, badfn=badfn)
     else:
         # no patterns: relative to repo root
         match = scmutil.match(repo[None], [wvfs.join(standindir)], badfn=badfn)
     return match
 
 
 def composestandinmatcher(repo, rmatcher):
     """Return a matcher that accepts standins corresponding to the
     files accepted by rmatcher. Pass the list of files in the matcher
     as the paths specified by the user."""
     smatcher = getstandinmatcher(repo, rmatcher)
     isstandin = smatcher.matchfn
 
     def composedmatchfn(f):
         return isstandin(f) and rmatcher.matchfn(splitstandin(f))
 
     smatcher.matchfn = composedmatchfn
 
     return smatcher
 
 
 def standin(filename):
     """Return the repo-relative path to the standin for the specified big
     file."""
     # Notes:
     # 1) Some callers want an absolute path, but for instance addlargefiles
     #    needs it repo-relative so it can be passed to repo[None].add().  So
     #    leave it up to the caller to use repo.wjoin() to get an absolute path.
     # 2) Join with '/' because that's what dirstate always uses, even on
     #    Windows. Change existing separator to '/' first in case we are
     #    passed filenames from an external source (like the command line).
     return shortnameslash + util.pconvert(filename)
 
 
 def isstandin(filename):
     """Return true if filename is a big file standin. filename must be
     in Mercurial's internal form (slash-separated)."""
     return filename.startswith(shortnameslash)
 
 
 def splitstandin(filename):
     # Split on / because that's what dirstate always uses, even on Windows.
     # Change local separator to / first just in case we are passed filenames
     # from an external source (like the command line).
     bits = util.pconvert(filename).split(b'/', 1)
     if len(bits) == 2 and bits[0] == shortname:
         return bits[1]
     else:
         return None
 
 
 def updatestandin(repo, lfile, standin):
     """Re-calculate hash value of lfile and write it into standin
 
     This assumes that "lfutil.standin(lfile) == standin", for efficiency.
     """
     file = repo.wjoin(lfile)
     if repo.wvfs.exists(lfile):
         hash = hashfile(file)
         executable = getexecutable(file)
         writestandin(repo, standin, hash, executable)
     else:
         raise error.Abort(_(b'%s: file not found!') % lfile)
 
 
 def readasstandin(fctx):
     """read hex hash from given filectx of standin file
 
     This encapsulates how "standin" data is stored into storage layer."""
     return fctx.data().strip()
 
 
 def writestandin(repo, standin, hash, executable):
     '''write hash to <repo.root>/<standin>'''
     repo.wwrite(standin, hash + b'\n', executable and b'x' or b'')
 
 
 def copyandhash(instream, outfile):
     """Read bytes from instream (iterable) and write them to outfile,
     computing the SHA-1 hash of the data along the way. Return the hash."""
     hasher = hashutil.sha1(b'')
     for data in instream:
         hasher.update(data)
         outfile.write(data)
     return hex(hasher.digest())
 
 
 def hashfile(file):
     if not os.path.exists(file):
         return b''
     with open(file, b'rb') as fd:
         return hexsha1(fd)
 
 
 def getexecutable(filename):
     mode = os.stat(filename).st_mode
     return (
         (mode & stat.S_IXUSR)
         and (mode & stat.S_IXGRP)
         and (mode & stat.S_IXOTH)
     )
 
 
 def urljoin(first, second, *arg):
     def join(left, right):
         if not left.endswith(b'/'):
             left += b'/'
         if right.startswith(b'/'):
             right = right[1:]
         return left + right
 
     url = join(first, second)
     for a in arg:
         url = join(url, a)
     return url
 
 
 def hexsha1(fileobj):
     """hexsha1 returns the hex-encoded sha1 sum of the data in the file-like
     object data"""
     h = hashutil.sha1()
     for chunk in util.filechunkiter(fileobj):
         h.update(chunk)
     return hex(h.digest())
 
 
 def httpsendfile(ui, filename):
     return httpconnection.httpsendfile(ui, filename, b'rb')
 
 
 def unixpath(path):
     '''Return a version of path normalized for use with the lfdirstate.'''
     return util.pconvert(os.path.normpath(path))
 
 
 def islfilesrepo(repo):
     '''Return true if the repo is a largefile repo.'''
     if b'largefiles' in repo.requirements and any(
-        shortnameslash in f[1] for f in repo.store.datafiles()
+        shortnameslash in entry.unencoded_path
+        for entry in repo.store.datafiles()
     ):
         return True
 
     return any(openlfdirstate(repo.ui, repo, False))
 
 
 class storeprotonotcapable(Exception):
     def __init__(self, storetypes):
         self.storetypes = storetypes
 
 
 def getstandinsstate(repo):
     standins = []
     matcher = getstandinmatcher(repo)
     wctx = repo[None]
     for standin in repo.dirstate.walk(
         matcher, subrepos=[], unknown=False, ignored=False
     ):
         lfile = splitstandin(standin)
         try:
             hash = readasstandin(wctx[standin])
         except IOError:
             hash = None
         standins.append((lfile, hash))
     return standins
 
 
 def synclfdirstate(repo, lfdirstate, lfile, normallookup):
     lfstandin = standin(lfile)
     if lfstandin not in repo.dirstate:
         lfdirstate.hacky_extension_update_file(
             lfile,
             p1_tracked=False,
             wc_tracked=False,
         )
     else:
         entry = repo.dirstate.get_entry(lfstandin)
         lfdirstate.hacky_extension_update_file(
             lfile,
             wc_tracked=entry.tracked,
             p1_tracked=entry.p1_tracked,
             p2_info=entry.p2_info,
             possibly_dirty=True,
         )
 
 
 def markcommitted(orig, ctx, node):
     repo = ctx.repo()
 
     with repo.dirstate.changing_parents(repo):
         orig(node)
 
         # ATTENTION: "ctx.files()" may differ from "repo[node].files()"
         # because files coming from the 2nd parent are omitted in the latter.
         #
         # The former should be used to get targets of "synclfdirstate",
         # because such files:
         # - are marked as "a" by "patch.patch()" (e.g. via transplant), and
         # - have to be marked as "n" after commit, but
         # - aren't listed in "repo[node].files()"
 
         lfdirstate = openlfdirstate(repo.ui, repo)
         for f in ctx.files():
             lfile = splitstandin(f)
             if lfile is not None:
                 synclfdirstate(repo, lfdirstate, lfile, False)
 
     # As part of committing, copy all of the largefiles into the cache.
     #
     # Using "node" instead of "ctx" implies additional "repo[node]"
     # lookup while copyalltostore(), but can omit redundant check for
     # files comming from the 2nd parent, which should exist in store
     # at merging.
     copyalltostore(repo, node)
 
 
 def getlfilestoupdate(oldstandins, newstandins):
     changedstandins = set(oldstandins).symmetric_difference(set(newstandins))
     filelist = []
     for f in changedstandins:
         if f[0] not in filelist:
             filelist.append(f[0])
     return filelist
 
 
 def getlfilestoupload(repo, missing, addfunc):
     makeprogress = repo.ui.makeprogress
     with makeprogress(
         _(b'finding outgoing largefiles'),
         unit=_(b'revisions'),
         total=len(missing),
     ) as progress:
         for i, n in enumerate(missing):
             progress.update(i)
             parents = [p for p in repo[n].parents() if p != repo.nullid]
 
             with lfstatus(repo, value=False):
                 ctx = repo[n]
 
             files = set(ctx.files())
             if len(parents) == 2:
                 mc = ctx.manifest()
                 mp1 = ctx.p1().manifest()
                 mp2 = ctx.p2().manifest()
                 for f in mp1:
                     if f not in mc:
                         files.add(f)
                 for f in mp2:
                     if f not in mc:
                         files.add(f)
                 for f in mc:
                     if mc[f] != mp1.get(f, None) or mc[f] != mp2.get(f, None):
                         files.add(f)
             for fn in files:
                 if isstandin(fn) and fn in ctx:
                     addfunc(fn, readasstandin(ctx[fn]))
 
 
 def updatestandinsbymatch(repo, match):
     """Update standins in the working directory according to specified match
 
     This returns (possibly modified) ``match`` object to be used for
     subsequent commit process.
     """
 
     ui = repo.ui
 
     # Case 1: user calls commit with no specific files or
     # include/exclude patterns: refresh and commit all files that
     # are "dirty".
     if match is None or match.always():
         # Spend a bit of time here to get a list of files we know
         # are modified so we can compare only against those.
         # It can cost a lot of time (several seconds)
         # otherwise to update all standins if the largefiles are
         # large.
         dirtymatch = matchmod.always()
         with repo.dirstate.running_status(repo):
             lfdirstate = openlfdirstate(ui, repo)
             unsure, s, mtime_boundary = lfdirstate.status(
                 dirtymatch,
                 subrepos=[],
                 ignored=False,
                 clean=False,
                 unknown=False,
             )
         modifiedfiles = unsure + s.modified + s.added + s.removed
         lfiles = listlfiles(repo)
         # this only loops through largefiles that exist (not
         # removed/renamed)
         for lfile in lfiles:
             if lfile in modifiedfiles:
                 fstandin = standin(lfile)
                 if repo.wvfs.exists(fstandin):
                     # this handles the case where a rebase is being
                     # performed and the working copy is not updated
                     # yet.
                     if repo.wvfs.exists(lfile):
                         updatestandin(repo, lfile, fstandin)
 
         return match
 
     lfiles = listlfiles(repo)
     match._files = repo._subdirlfs(match.files(), lfiles)
 
     # Case 2: user calls commit with specified patterns: refresh
     # any matching big files.
     smatcher = composestandinmatcher(repo, match)
     standins = repo.dirstate.walk(
         smatcher, subrepos=[], unknown=False, ignored=False
     )
 
     # No matching big files: get out of the way and pass control to
     # the usual commit() method.
     if not standins:
         return match
 
     # Refresh all matching big files.  It's possible that the
     # commit will end up failing, in which case the big files will
     # stay refreshed.  No harm done: the user modified them and
     # asked to commit them, so sooner or later we're going to
     # refresh the standins.  Might as well leave them refreshed.
     lfdirstate = openlfdirstate(ui, repo)
     for fstandin in standins:
         lfile = splitstandin(fstandin)
         if lfdirstate.get_entry(lfile).tracked:
             updatestandin(repo, lfile, fstandin)
 
     # Cook up a new matcher that only matches regular files or
     # standins corresponding to the big files requested by the
     # user.  Have to modify _files to prevent commit() from
     # complaining "not tracked" for big files.
     match = copy.copy(match)
     origmatchfn = match.matchfn
 
     # Check both the list of largefiles and the list of
     # standins because if a largefile was removed, it
     # won't be in the list of largefiles at this point
     match._files += sorted(standins)
 
     actualfiles = []
     for f in match._files:
         fstandin = standin(f)
 
         # For largefiles, only one of the normal and standin should be
         # committed (except if one of them is a remove).  In the case of a
         # standin removal, drop the normal file if it is unknown to dirstate.
         # Thus, skip plain largefile names but keep the standin.
         if f in lfiles or fstandin in standins:
             if not repo.dirstate.get_entry(fstandin).removed:
                 if not repo.dirstate.get_entry(f).removed:
                     continue
             elif not repo.dirstate.get_entry(f).any_tracked:
                 continue
 
         actualfiles.append(f)
     match._files = actualfiles
 
     def matchfn(f):
         if origmatchfn(f):
             return f not in lfiles
         else:
             return f in standins
 
     match.matchfn = matchfn
 
     return match
 
 
 class automatedcommithook:
     """Stateful hook to update standins at the 1st commit of resuming
 
     For efficiency, updating standins in the working directory should
     be avoided while automated committing (like rebase, transplant and
     so on), because they should be updated before committing.
 
     But the 1st commit of resuming automated committing (e.g. ``rebase
     --continue``) should update them, because largefiles may be
     modified manually.
     """
 
     def __init__(self, resuming):
         self.resuming = resuming
 
     def __call__(self, repo, match):
         if self.resuming:
             self.resuming = False  # avoids updating at subsequent commits
             return updatestandinsbymatch(repo, match)
         else:
             return match
 
 
 def getstatuswriter(ui, repo, forcibly=None):
     """Return the function to write largefiles specific status out
 
     If ``forcibly`` is ``None``, this returns the last element of
     ``repo._lfstatuswriters`` as "default" writer function.
 
     Otherwise, this returns the function to always write out (or
     ignore if ``not forcibly``) status.
     """
     if forcibly is None and util.safehasattr(repo, b'_largefilesenabled'):
         return repo._lfstatuswriters[-1]
     else:
         if forcibly:
             return ui.status  # forcibly WRITE OUT
         else:
             return lambda *msg, **opts: None  # forcibly IGNORE

hgext/largefiles/reposetup.py

@@ -1,469 +1,470 b''
 # Copyright 2009-2010 Gregory P. Ward
 # Copyright 2009-2010 Intelerad Medical Systems Incorporated
 # Copyright 2010-2011 Fog Creek Software
 # Copyright 2010-2011 Unity Technologies
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''setup for largefiles repositories: reposetup'''
 
 import copy
 
 from mercurial.i18n import _
 
 from mercurial import (
     error,
     extensions,
     localrepo,
     match as matchmod,
     scmutil,
     util,
 )
 
 from mercurial.dirstateutils import timestamp
 
 from . import (
     lfcommands,
     lfutil,
 )
 
 
 def reposetup(ui, repo):
     # wire repositories should be given new wireproto functions
     # by "proto.wirereposetup()" via "hg.wirepeersetupfuncs"
     if not repo.local():
         return
 
     class lfilesrepo(repo.__class__):
         # the mark to examine whether "repo" object enables largefiles or not
         _largefilesenabled = True
 
         lfstatus = False
 
         # When lfstatus is set, return a context that gives the names
         # of largefiles instead of their corresponding standins and
         # identifies the largefiles as always binary, regardless of
         # their actual contents.
         def __getitem__(self, changeid):
             ctx = super(lfilesrepo, self).__getitem__(changeid)
             if self.lfstatus:
 
                 def files(orig):
                     filenames = orig()
                     return [lfutil.splitstandin(f) or f for f in filenames]
 
                 extensions.wrapfunction(ctx, 'files', files)
 
                 def manifest(orig):
                     man1 = orig()
 
                     class lfilesmanifest(man1.__class__):
                         def __contains__(self, filename):
                             orig = super(lfilesmanifest, self).__contains__
                             return orig(filename) or orig(
                                 lfutil.standin(filename)
                             )
 
                     man1.__class__ = lfilesmanifest
                     return man1
 
                 extensions.wrapfunction(ctx, 'manifest', manifest)
 
                 def filectx(orig, path, fileid=None, filelog=None):
                     try:
                         if filelog is not None:
                             result = orig(path, fileid, filelog)
                         else:
                             result = orig(path, fileid)
                     except error.LookupError:
                         # Adding a null character will cause Mercurial to
                         # identify this as a binary file.
                         if filelog is not None:
                             result = orig(lfutil.standin(path), fileid, filelog)
                         else:
                             result = orig(lfutil.standin(path), fileid)
                         olddata = result.data
                         result.data = lambda: olddata() + b'\0'
                     return result
 
                 extensions.wrapfunction(ctx, 'filectx', filectx)
 
             return ctx
 
         # Figure out the status of big files and insert them into the
         # appropriate list in the result. Also removes standin files
         # from the listing. Revert to the original status if
         # self.lfstatus is False.
         # XXX large file status is buggy when used on repo proxy.
         # XXX this needs to be investigated.
         @localrepo.unfilteredmethod
         def status(
             self,
             node1=b'.',
             node2=None,
             match=None,
             ignored=False,
             clean=False,
             unknown=False,
             listsubrepos=False,
         ):
             listignored, listclean, listunknown = ignored, clean, unknown
             orig = super(lfilesrepo, self).status
             if not self.lfstatus:
                 return orig(
                     node1,
                     node2,
                     match,
                     listignored,
                     listclean,
                     listunknown,
                     listsubrepos,
                 )
 
             # some calls in this function rely on the old version of status
             self.lfstatus = False
             ctx1 = self[node1]
             ctx2 = self[node2]
             working = ctx2.rev() is None
             parentworking = working and ctx1 == self[b'.']
 
             if match is None:
                 match = matchmod.always()
 
             try:
                 # updating the dirstate is optional
                 # so we don't wait on the lock
                 wlock = self.wlock(False)
                 gotlock = True
             except error.LockError:
                 wlock = util.nullcontextmanager()
                 gotlock = False
             with wlock, self.dirstate.running_status(self):
 
                 # First check if paths or patterns were specified on the
                 # command line.  If there were, and they don't match any
                 # largefiles, we should just bail here and let super
                 # handle it -- thus gaining a big performance boost.
                 lfdirstate = lfutil.openlfdirstate(ui, self)
                 if not match.always():
                     for f in lfdirstate:
                         if match(f):
                             break
                     else:
                         return orig(
                             node1,
                             node2,
                             match,
                             listignored,
                             listclean,
                             listunknown,
                             listsubrepos,
                         )
 
                 # Create a copy of match that matches standins instead
                 # of largefiles.
                 def tostandins(files):
                     if not working:
                         return files
                     newfiles = []
                     dirstate = self.dirstate
                     for f in files:
                         sf = lfutil.standin(f)
                         if sf in dirstate:
                             newfiles.append(sf)
                         elif dirstate.hasdir(sf):
                             # Directory entries could be regular or
                             # standin, check both
                             newfiles.extend((f, sf))
                         else:
                             newfiles.append(f)
                     return newfiles
 
                 m = copy.copy(match)
                 m._files = tostandins(m._files)
 
                 result = orig(
                     node1, node2, m, ignored, clean, unknown, listsubrepos
                 )
                 if working:
 
                     def sfindirstate(f):
                         sf = lfutil.standin(f)
                         dirstate = self.dirstate
                         return sf in dirstate or dirstate.hasdir(sf)
 
                     match._files = [f for f in match._files if sfindirstate(f)]
                     # Don't waste time getting the ignored and unknown
                     # files from lfdirstate
                     unsure, s, mtime_boundary = lfdirstate.status(
                         match,
                         subrepos=[],
                         ignored=False,
                         clean=listclean,
                         unknown=False,
                     )
                     (modified, added, removed, deleted, clean) = (
                         s.modified,
                         s.added,
                         s.removed,
                         s.deleted,
                         s.clean,
                     )
                     if parentworking:
                         wctx = repo[None]
                         for lfile in unsure:
                             standin = lfutil.standin(lfile)
                             if standin not in ctx1:
                                 # from second parent
                                 modified.append(lfile)
                             elif lfutil.readasstandin(
                                 ctx1[standin]
                             ) != lfutil.hashfile(self.wjoin(lfile)):
                                 modified.append(lfile)
                             else:
                                 if listclean:
                                     clean.append(lfile)
                                 s = wctx[lfile].lstat()
                                 mode = s.st_mode
                                 size = s.st_size
                                 mtime = timestamp.reliable_mtime_of(
                                     s, mtime_boundary
                                 )
                                 if mtime is not None:
                                     cache_data = (mode, size, mtime)
                                     lfdirstate.set_clean(lfile, cache_data)
                     else:
                         tocheck = unsure + modified + added + clean
                         modified, added, clean = [], [], []
                         checkexec = self.dirstate._checkexec
 
                         for lfile in tocheck:
                             standin = lfutil.standin(lfile)
                             if standin in ctx1:
                                 abslfile = self.wjoin(lfile)
                                 if (
                                     lfutil.readasstandin(ctx1[standin])
                                     != lfutil.hashfile(abslfile)
                                 ) or (
                                     checkexec
                                     and (b'x' in ctx1.flags(standin))
                                     != bool(lfutil.getexecutable(abslfile))
                                 ):
                                     modified.append(lfile)
                                 elif listclean:
                                     clean.append(lfile)
                             else:
                                 added.append(lfile)
 
                         # at this point, 'removed' contains largefiles
                         # marked as 'R' in the working context.
                         # then, largefiles not managed also in the target
                         # context should be excluded from 'removed'.
                         removed = [
                             lfile
                             for lfile in removed
                             if lfutil.standin(lfile) in ctx1
                         ]
 
                     # Standins no longer found in lfdirstate have been deleted
                     for standin in ctx1.walk(lfutil.getstandinmatcher(self)):
                         lfile = lfutil.splitstandin(standin)
                         if not match(lfile):
                             continue
                         if lfile not in lfdirstate:
                             deleted.append(lfile)
                             # Sync "largefile has been removed" back to the
                             # standin. Removing a file as a side effect of
                             # running status is gross, but the alternatives (if
                             # any) are worse.
                             self.wvfs.unlinkpath(standin, ignoremissing=True)
 
                     # Filter result lists
                     result = list(result)
 
                     # Largefiles are not really removed when they're
                     # still in the normal dirstate. Likewise, normal
                     # files are not really removed if they are still in
                     # lfdirstate. This happens in merges where files
                     # change type.
                     removed = [f for f in removed if f not in self.dirstate]
                     result[2] = [f for f in result[2] if f not in lfdirstate]
 
                     lfiles = set(lfdirstate)
                     # Unknown files
                     result[4] = set(result[4]).difference(lfiles)
                     # Ignored files
                     result[5] = set(result[5]).difference(lfiles)
                     # combine normal files and largefiles
                     normals = [
                         [fn for fn in filelist if not lfutil.isstandin(fn)]
                         for filelist in result
                     ]
                     lfstatus = (
                         modified,
                         added,
                         removed,
                         deleted,
                         [],
                         [],
                         clean,
                     )
                     result = [
                         sorted(list1 + list2)
                         for (list1, list2) in zip(normals, lfstatus)
                     ]
                 else:  # not against working directory
                     result = [
                         [lfutil.splitstandin(f) or f for f in items]
                         for items in result
                     ]
 
                 if gotlock:
                     lfdirstate.write(self.currenttransaction())
                 else:
                     lfdirstate.invalidate()
 
             self.lfstatus = True
             return scmutil.status(*result)
 
         def commitctx(self, ctx, *args, **kwargs):
             node = super(lfilesrepo, self).commitctx(ctx, *args, **kwargs)
 
             class lfilesctx(ctx.__class__):
                 def markcommitted(self, node):
                     orig = super(lfilesctx, self).markcommitted
                     return lfutil.markcommitted(orig, self, node)
 
             ctx.__class__ = lfilesctx
             return node
 
         # Before commit, largefile standins have not had their
         # contents updated to reflect the hash of their largefile.
         # Do that here.
         def commit(
             self,
             text=b"",
             user=None,
             date=None,
             match=None,
             force=False,
             editor=False,
             extra=None,
         ):
             if extra is None:
                 extra = {}
             orig = super(lfilesrepo, self).commit
 
             with self.wlock():
                 lfcommithook = self._lfcommithooks[-1]
                 match = lfcommithook(self, match)
                 result = orig(
                     text=text,
                     user=user,
                     date=date,
                     match=match,
                     force=force,
                     editor=editor,
                     extra=extra,
                 )
                 return result
 
         # TODO: _subdirlfs should be moved into "lfutil.py", because
         # it is referred only from "lfutil.updatestandinsbymatch"
         def _subdirlfs(self, files, lfiles):
             """
             Adjust matched file list
             If we pass a directory to commit whose only committable files
             are largefiles, the core commit code aborts before finding
             the largefiles.
             So we do the following:
             For directories that only have largefiles as matches,
             we explicitly add the largefiles to the match list and remove
             the directory.
             In other cases, we leave the match list unmodified.
             """
             actualfiles = []
             dirs = []
             regulars = []
 
             for f in files:
                 if lfutil.isstandin(f + b'/'):
                     raise error.Abort(
                         _(b'file "%s" is a largefile standin') % f,
                         hint=b'commit the largefile itself instead',
                     )
                 # Scan directories
                 if self.wvfs.isdir(f):
                     dirs.append(f)
                 else:
                     regulars.append(f)
 
             for f in dirs:
                 matcheddir = False
                 d = self.dirstate.normalize(f) + b'/'
                 # Check for matched normal files
                 for mf in regulars:
                     if self.dirstate.normalize(mf).startswith(d):
                         actualfiles.append(f)
                         matcheddir = True
                         break
                 if not matcheddir:
                     # If no normal match, manually append
                     # any matching largefiles
                     for lf in lfiles:
                         if self.dirstate.normalize(lf).startswith(d):
                             actualfiles.append(lf)
                             if not matcheddir:
                                 # There may still be normal files in the dir, so
                                 # add a directory to the list, which
                                 # forces status/dirstate to walk all files and
                                 # call the match function on the matcher, even
                                 # on case sensitive filesystems.
                                 actualfiles.append(b'.')
                                 matcheddir = True
                 # Nothing in dir, so readd it
                 # and let commit reject it
                 if not matcheddir:
                     actualfiles.append(f)
 
             # Always add normal files
             actualfiles += regulars
             return actualfiles
 
     repo.__class__ = lfilesrepo
 
     # stack of hooks being executed before committing.
     # only last element ("_lfcommithooks[-1]") is used for each committing.
     repo._lfcommithooks = [lfutil.updatestandinsbymatch]
 
     # Stack of status writer functions taking "*msg, **opts" arguments
     # like "ui.status()". Only last element ("_lfstatuswriters[-1]")
     # is used to write status out.
     repo._lfstatuswriters = [ui.status]
 
     def prepushoutgoinghook(pushop):
         """Push largefiles for pushop before pushing revisions."""
         lfrevs = pushop.lfrevs
         if lfrevs is None:
             lfrevs = pushop.outgoing.missing
         if lfrevs:
             toupload = set()
             addfunc = lambda fn, lfhash: toupload.add(lfhash)
             lfutil.getlfilestoupload(pushop.repo, lfrevs, addfunc)
             lfcommands.uploadlfiles(ui, pushop.repo, pushop.remote, toupload)
 
     repo.prepushoutgoinghooks.add(b"largefiles", prepushoutgoinghook)
 
     def checkrequireslfiles(ui, repo, **kwargs):
         with repo.lock():
             if b'largefiles' not in repo.requirements and any(
-                lfutil.shortname + b'/' in f[1] for f in repo.store.datafiles()
+                lfutil.shortname + b'/' in entry.unencoded_path
+                for entry in repo.store.datafiles()
             ):
                 repo.requirements.add(b'largefiles')
                 scmutil.writereporequirements(repo)
 
     ui.setconfig(
         b'hooks', b'changegroup.lfiles', checkrequireslfiles, b'largefiles'
     )
     ui.setconfig(b'hooks', b'commit.lfiles', checkrequireslfiles, b'largefiles')

hgext/narrow/narrowcommands.py

@@ -1,695 +1,696 b''
 # narrowcommands.py - command modifications for narrowhg extension
 #
 # Copyright 2017 Google, 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 itertools
 import os
 
 from mercurial.i18n import _
 from mercurial.node import (
     hex,
     short,
 )
 from mercurial import (
     bundle2,
     cmdutil,
     commands,
     discovery,
     encoding,
     error,
     exchange,
     extensions,
     hg,
     narrowspec,
     pathutil,
     pycompat,
     registrar,
     repair,
     repoview,
     requirements,
     sparse,
     util,
     wireprototypes,
 )
 from mercurial.utils import (
     urlutil,
 )
 
 table = {}
 command = registrar.command(table)
 
 
 def setup():
     """Wraps user-facing mercurial commands with narrow-aware versions."""
 
     entry = extensions.wrapcommand(commands.table, b'clone', clonenarrowcmd)
     entry[1].append(
         (b'', b'narrow', None, _(b"create a narrow clone of select files"))
     )
     entry[1].append(
         (
             b'',
             b'depth',
             b'',
             _(b"limit the history fetched by distance from heads"),
         )
     )
     entry[1].append((b'', b'narrowspec', b'', _(b"read narrowspecs from file")))
     # TODO(durin42): unify sparse/narrow --include/--exclude logic a bit
     if b'sparse' not in extensions.enabled():
         entry[1].append(
             (b'', b'include', [], _(b"specifically fetch this file/directory"))
         )
         entry[1].append(
             (
                 b'',
                 b'exclude',
                 [],
                 _(b"do not fetch this file/directory, even if included"),
             )
         )
 
     entry = extensions.wrapcommand(commands.table, b'pull', pullnarrowcmd)
     entry[1].append(
         (
             b'',
             b'depth',
             b'',
             _(b"limit the history fetched by distance from heads"),
         )
     )
 
     extensions.wrapcommand(commands.table, b'archive', archivenarrowcmd)
 
 
 def clonenarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps clone command, so 'hg clone' first wraps localrepo.clone()."""
     opts = pycompat.byteskwargs(opts)
     wrappedextraprepare = util.nullcontextmanager()
     narrowspecfile = opts[b'narrowspec']
 
     if narrowspecfile:
         filepath = os.path.join(encoding.getcwd(), narrowspecfile)
         ui.status(_(b"reading narrowspec from '%s'\n") % filepath)
         try:
             fdata = util.readfile(filepath)
         except IOError as inst:
             raise error.Abort(
                 _(b"cannot read narrowspecs from '%s': %s")
                 % (filepath, encoding.strtolocal(inst.strerror))
             )
 
         includes, excludes, profiles = sparse.parseconfig(ui, fdata, b'narrow')
         if profiles:
             raise error.ConfigError(
                 _(
                     b"cannot specify other files using '%include' in"
                     b" narrowspec"
                 )
             )
 
         narrowspec.validatepatterns(includes)
         narrowspec.validatepatterns(excludes)
 
         # narrowspec is passed so we should assume that user wants narrow clone
         opts[b'narrow'] = True
         opts[b'include'].extend(includes)
         opts[b'exclude'].extend(excludes)
 
     if opts[b'narrow']:
 
         def pullbundle2extraprepare_widen(orig, pullop, kwargs):
             orig(pullop, kwargs)
 
             if opts.get(b'depth'):
                 kwargs[b'depth'] = opts[b'depth']
 
         wrappedextraprepare = extensions.wrappedfunction(
             exchange, b'_pullbundle2extraprepare', pullbundle2extraprepare_widen
         )
 
     with wrappedextraprepare:
         return orig(ui, repo, *args, **pycompat.strkwargs(opts))
 
 
 def pullnarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps pull command to allow modifying narrow spec."""
     wrappedextraprepare = util.nullcontextmanager()
     if requirements.NARROW_REQUIREMENT in repo.requirements:
 
         def pullbundle2extraprepare_widen(orig, pullop, kwargs):
             orig(pullop, kwargs)
             if opts.get('depth'):
                 kwargs[b'depth'] = opts['depth']
 
         wrappedextraprepare = extensions.wrappedfunction(
             exchange, b'_pullbundle2extraprepare', pullbundle2extraprepare_widen
         )
 
     with wrappedextraprepare:
         return orig(ui, repo, *args, **opts)
 
 
 def archivenarrowcmd(orig, ui, repo, *args, **opts):
     """Wraps archive command to narrow the default includes."""
     if requirements.NARROW_REQUIREMENT in repo.requirements:
         repo_includes, repo_excludes = repo.narrowpats
         includes = set(opts.get('include', []))
         excludes = set(opts.get('exclude', []))
         includes, excludes, unused_invalid = narrowspec.restrictpatterns(
             includes, excludes, repo_includes, repo_excludes
         )
         if includes:
             opts['include'] = includes
         if excludes:
             opts['exclude'] = excludes
     return orig(ui, repo, *args, **opts)
 
 
 def pullbundle2extraprepare(orig, pullop, kwargs):
     repo = pullop.repo
     if requirements.NARROW_REQUIREMENT not in repo.requirements:
         return orig(pullop, kwargs)
 
     if wireprototypes.NARROWCAP not in pullop.remote.capabilities():
         raise error.Abort(_(b"server does not support narrow clones"))
     orig(pullop, kwargs)
     kwargs[b'narrow'] = True
     include, exclude = repo.narrowpats
     kwargs[b'oldincludepats'] = include
     kwargs[b'oldexcludepats'] = exclude
     if include:
         kwargs[b'includepats'] = include
     if exclude:
         kwargs[b'excludepats'] = exclude
     # calculate known nodes only in ellipses cases because in non-ellipses cases
     # we have all the nodes
     if wireprototypes.ELLIPSESCAP1 in pullop.remote.capabilities():
         kwargs[b'known'] = [
             hex(ctx.node())
             for ctx in repo.set(b'::%ln', pullop.common)
             if ctx.node() != repo.nullid
         ]
         if not kwargs[b'known']:
             # Mercurial serializes an empty list as '' and deserializes it as
             # [''], so delete it instead to avoid handling the empty string on
             # the server.
             del kwargs[b'known']
 
 
 extensions.wrapfunction(
     exchange, b'_pullbundle2extraprepare', pullbundle2extraprepare
 )
 
 
 def _narrow(
     ui,
     repo,
     remote,
     commoninc,
     oldincludes,
     oldexcludes,
     newincludes,
     newexcludes,
     force,
     backup,
 ):
     oldmatch = narrowspec.match(repo.root, oldincludes, oldexcludes)
     newmatch = narrowspec.match(repo.root, newincludes, newexcludes)
 
     # This is essentially doing "hg outgoing" to find all local-only
     # commits. We will then check that the local-only commits don't
     # have any changes to files that will be untracked.
     unfi = repo.unfiltered()
     outgoing = discovery.findcommonoutgoing(unfi, remote, commoninc=commoninc)
     ui.status(_(b'looking for local changes to affected paths\n'))
     progress = ui.makeprogress(
         topic=_(b'changesets'),
         unit=_(b'changesets'),
         total=len(outgoing.missing) + len(outgoing.excluded),
     )
     localnodes = []
     with progress:
         for n in itertools.chain(outgoing.missing, outgoing.excluded):
             progress.increment()
             if any(oldmatch(f) and not newmatch(f) for f in unfi[n].files()):
                 localnodes.append(n)
     revstostrip = unfi.revs(b'descendants(%ln)', localnodes)
     hiddenrevs = repoview.filterrevs(repo, b'visible')
     visibletostrip = list(
         repo.changelog.node(r) for r in (revstostrip - hiddenrevs)
     )
     if visibletostrip:
         ui.status(
             _(
                 b'The following changeset(s) or their ancestors have '
                 b'local changes not on the remote:\n'
             )
         )
         maxnodes = 10
         if ui.verbose or len(visibletostrip) <= maxnodes:
             for n in visibletostrip:
                 ui.status(b'%s\n' % short(n))
         else:
             for n in visibletostrip[:maxnodes]:
                 ui.status(b'%s\n' % short(n))
             ui.status(
                 _(b'...and %d more, use --verbose to list all\n')
                 % (len(visibletostrip) - maxnodes)
             )
         if not force:
             raise error.StateError(
                 _(b'local changes found'),
                 hint=_(b'use --force-delete-local-changes to ignore'),
             )
 
     with ui.uninterruptible():
         if revstostrip:
             tostrip = [unfi.changelog.node(r) for r in revstostrip]
             if repo[b'.'].node() in tostrip:
                 # stripping working copy, so move to a different commit first
                 urev = max(
                     repo.revs(
                         b'(::%n) - %ln + null',
                         repo[b'.'].node(),
                         visibletostrip,
                     )
                 )
                 hg.clean(repo, urev)
             overrides = {(b'devel', b'strip-obsmarkers'): False}
             if backup:
                 ui.status(_(b'moving unwanted changesets to backup\n'))
             else:
                 ui.status(_(b'deleting unwanted changesets\n'))
             with ui.configoverride(overrides, b'narrow'):
                 repair.strip(ui, unfi, tostrip, topic=b'narrow', backup=backup)
 
         todelete = []
-        for t, f, size in repo.store.datafiles():
+        for entry in repo.store.datafiles():
+            f = entry.unencoded_path
             if f.startswith(b'data/'):
                 file = f[5:-2]
                 if not newmatch(file):
                     todelete.append(f)
             elif f.startswith(b'meta/'):
                 dir = f[5:-13]
                 dirs = sorted(pathutil.dirs({dir})) + [dir]
                 include = True
                 for d in dirs:
                     visit = newmatch.visitdir(d)
                     if not visit:
                         include = False
                         break
                     if visit == b'all':
                         break
                 if not include:
                     todelete.append(f)
 
         repo.destroying()
 
         with repo.transaction(b'narrowing'):
             # Update narrowspec before removing revlogs, so repo won't be
             # corrupt in case of crash
             repo.setnarrowpats(newincludes, newexcludes)
 
             for f in todelete:
                 ui.status(_(b'deleting %s\n') % f)
                 util.unlinkpath(repo.svfs.join(f))
                 repo.store.markremoved(f)
 
             ui.status(_(b'deleting unwanted files from working copy\n'))
             with repo.dirstate.changing_parents(repo):
                 narrowspec.updateworkingcopy(repo, assumeclean=True)
                 narrowspec.copytoworkingcopy(repo)
 
         repo.destroyed()
 
 
 def _widen(
     ui,
     repo,
     remote,
     commoninc,
     oldincludes,
     oldexcludes,
     newincludes,
     newexcludes,
 ):
     # for now we assume that if a server has ellipses enabled, we will be
     # exchanging ellipses nodes. In future we should add ellipses as a client
     # side requirement (maybe) to distinguish a client is shallow or not and
     # then send that information to server whether we want ellipses or not.
     # Theoretically a non-ellipses repo should be able to use narrow
     # functionality from an ellipses enabled server
     remotecap = remote.capabilities()
     ellipsesremote = any(
         cap in remotecap for cap in wireprototypes.SUPPORTED_ELLIPSESCAP
     )
 
     # check whether we are talking to a server which supports old version of
     # ellipses capabilities
     isoldellipses = (
         ellipsesremote
         and wireprototypes.ELLIPSESCAP1 in remotecap
         and wireprototypes.ELLIPSESCAP not in remotecap
     )
 
     def pullbundle2extraprepare_widen(orig, pullop, kwargs):
         orig(pullop, kwargs)
         # The old{in,ex}cludepats have already been set by orig()
         kwargs[b'includepats'] = newincludes
         kwargs[b'excludepats'] = newexcludes
 
     wrappedextraprepare = extensions.wrappedfunction(
         exchange, b'_pullbundle2extraprepare', pullbundle2extraprepare_widen
     )
 
     # define a function that narrowbundle2 can call after creating the
     # backup bundle, but before applying the bundle from the server
     def setnewnarrowpats():
         repo.setnarrowpats(newincludes, newexcludes)
 
     repo.setnewnarrowpats = setnewnarrowpats
     # silence the devel-warning of applying an empty changegroup
     overrides = {(b'devel', b'all-warnings'): False}
 
     common = commoninc[0]
     with ui.uninterruptible():
         if ellipsesremote:
             ds = repo.dirstate
             p1, p2 = ds.p1(), ds.p2()
             with ds.changing_parents(repo):
                 ds.setparents(repo.nullid, repo.nullid)
         if isoldellipses:
             with wrappedextraprepare:
                 exchange.pull(repo, remote, heads=common)
         else:
             known = []
             if ellipsesremote:
                 known = [
                     ctx.node()
                     for ctx in repo.set(b'::%ln', common)
                     if ctx.node() != repo.nullid
                 ]
             with remote.commandexecutor() as e:
                 bundle = e.callcommand(
                     b'narrow_widen',
                     {
                         b'oldincludes': oldincludes,
                         b'oldexcludes': oldexcludes,
                         b'newincludes': newincludes,
                         b'newexcludes': newexcludes,
                         b'cgversion': b'03',
                         b'commonheads': common,
                         b'known': known,
                         b'ellipses': ellipsesremote,
                     },
                 ).result()
 
             trmanager = exchange.transactionmanager(
                 repo, b'widen', remote.url()
             )
             with trmanager, repo.ui.configoverride(overrides, b'widen'):
                 op = bundle2.bundleoperation(
                     repo, trmanager.transaction, source=b'widen'
                 )
                 # TODO: we should catch error.Abort here
                 bundle2.processbundle(repo, bundle, op=op, remote=remote)
 
         if ellipsesremote:
             with ds.changing_parents(repo):
                 ds.setparents(p1, p2)
 
         with repo.transaction(b'widening'), repo.dirstate.changing_parents(
             repo
         ):
             repo.setnewnarrowpats()
             narrowspec.updateworkingcopy(repo)
             narrowspec.copytoworkingcopy(repo)
 
 
 # TODO(rdamazio): Make new matcher format and update description
 @command(
     b'tracked',
     [
         (b'', b'addinclude', [], _(b'new paths to include')),
         (b'', b'removeinclude', [], _(b'old paths to no longer include')),
         (
             b'',
             b'auto-remove-includes',
             False,
             _(b'automatically choose unused includes to remove'),
         ),
         (b'', b'addexclude', [], _(b'new paths to exclude')),
         (b'', b'import-rules', b'', _(b'import narrowspecs from a file')),
         (b'', b'removeexclude', [], _(b'old paths to no longer exclude')),
         (
             b'',
             b'clear',
             False,
             _(b'whether to replace the existing narrowspec'),
         ),
         (
             b'',
             b'force-delete-local-changes',
             False,
             _(b'forces deletion of local changes when narrowing'),
         ),
         (
             b'',
             b'backup',
             True,
             _(b'back up local changes when narrowing'),
         ),
         (
             b'',
             b'update-working-copy',
             False,
             _(b'update working copy when the store has changed'),
         ),
     ]
     + commands.remoteopts,
     _(b'[OPTIONS]... [REMOTE]'),
     inferrepo=True,
     helpcategory=command.CATEGORY_MAINTENANCE,
 )
 def trackedcmd(ui, repo, remotepath=None, *pats, **opts):
     """show or change the current narrowspec
 
     With no argument, shows the current narrowspec entries, one per line. Each
     line will be prefixed with 'I' or 'X' for included or excluded patterns,
     respectively.
 
     The narrowspec is comprised of expressions to match remote files and/or
     directories that should be pulled into your client.
     The narrowspec has *include* and *exclude* expressions, with excludes always
     trumping includes: that is, if a file matches an exclude expression, it will
     be excluded even if it also matches an include expression.
     Excluding files that were never included has no effect.
 
     Each included or excluded entry is in the format described by
     'hg help patterns'.
 
     The options allow you to add or remove included and excluded expressions.
 
     If --clear is specified, then all previous includes and excludes are DROPPED
     and replaced by the new ones specified to --addinclude and --addexclude.
     If --clear is specified without any further options, the narrowspec will be
     empty and will not match any files.
 
     If --auto-remove-includes is specified, then those includes that don't match
     any files modified by currently visible local commits (those not shared by
     the remote) will be added to the set of explicitly specified includes to
     remove.
 
     --import-rules accepts a path to a file containing rules, allowing you to
     add --addinclude, --addexclude rules in bulk. Like the other include and
     exclude switches, the changes are applied immediately.
     """
     opts = pycompat.byteskwargs(opts)
     if requirements.NARROW_REQUIREMENT not in repo.requirements:
         raise error.InputError(
             _(
                 b'the tracked command is only supported on '
                 b'repositories cloned with --narrow'
             )
         )
 
     # Before supporting, decide whether it "hg tracked --clear" should mean
     # tracking no paths or all paths.
     if opts[b'clear']:
         raise error.InputError(_(b'the --clear option is not yet supported'))
 
     # import rules from a file
     newrules = opts.get(b'import_rules')
     if newrules:
         try:
             filepath = os.path.join(encoding.getcwd(), newrules)
             fdata = util.readfile(filepath)
         except IOError as inst:
             raise error.StorageError(
                 _(b"cannot read narrowspecs from '%s': %s")
                 % (filepath, encoding.strtolocal(inst.strerror))
             )
         includepats, excludepats, profiles = sparse.parseconfig(
             ui, fdata, b'narrow'
         )
         if profiles:
             raise error.InputError(
                 _(
                     b"including other spec files using '%include' "
                     b"is not supported in narrowspec"
                 )
             )
         opts[b'addinclude'].extend(includepats)
         opts[b'addexclude'].extend(excludepats)
 
     addedincludes = narrowspec.parsepatterns(opts[b'addinclude'])
     removedincludes = narrowspec.parsepatterns(opts[b'removeinclude'])
     addedexcludes = narrowspec.parsepatterns(opts[b'addexclude'])
     removedexcludes = narrowspec.parsepatterns(opts[b'removeexclude'])
     autoremoveincludes = opts[b'auto_remove_includes']
 
     update_working_copy = opts[b'update_working_copy']
     only_show = not (
         addedincludes
         or removedincludes
         or addedexcludes
         or removedexcludes
         or newrules
         or autoremoveincludes
         or update_working_copy
     )
 
     # Only print the current narrowspec.
     if only_show:
         oldincludes, oldexcludes = repo.narrowpats
         ui.pager(b'tracked')
         fm = ui.formatter(b'narrow', opts)
         for i in sorted(oldincludes):
             fm.startitem()
             fm.write(b'status', b'%s ', b'I', label=b'narrow.included')
             fm.write(b'pat', b'%s\n', i, label=b'narrow.included')
         for i in sorted(oldexcludes):
             fm.startitem()
             fm.write(b'status', b'%s ', b'X', label=b'narrow.excluded')
             fm.write(b'pat', b'%s\n', i, label=b'narrow.excluded')
         fm.end()
         return 0
 
     with repo.wlock(), repo.lock():
         oldincludes, oldexcludes = repo.narrowpats
 
         # filter the user passed additions and deletions into actual additions and
         # deletions of excludes and includes
         addedincludes -= oldincludes
         removedincludes &= oldincludes
         addedexcludes -= oldexcludes
         removedexcludes &= oldexcludes
 
         widening = addedincludes or removedexcludes
         narrowing = removedincludes or addedexcludes
 
         if update_working_copy:
             with repo.transaction(b'narrow-wc'), repo.dirstate.changing_parents(
                 repo
             ):
                 narrowspec.updateworkingcopy(repo)
                 narrowspec.copytoworkingcopy(repo)
             return 0
 
         if not (widening or narrowing or autoremoveincludes):
             ui.status(_(b"nothing to widen or narrow\n"))
             return 0
 
         cmdutil.bailifchanged(repo)
 
         # Find the revisions we have in common with the remote. These will
         # be used for finding local-only changes for narrowing. They will
         # also define the set of revisions to update for widening.
         path = urlutil.get_unique_pull_path_obj(b'tracked', ui, remotepath)
         ui.status(_(b'comparing with %s\n') % urlutil.hidepassword(path.loc))
         remote = hg.peer(repo, opts, path)
 
         try:
             # check narrow support before doing anything if widening needs to be
             # performed. In future we should also abort if client is ellipses and
             # server does not support ellipses
             if (
                 widening
                 and wireprototypes.NARROWCAP not in remote.capabilities()
             ):
                 raise error.Abort(_(b"server does not support narrow clones"))
 
             commoninc = discovery.findcommonincoming(repo, remote)
 
             if autoremoveincludes:
                 outgoing = discovery.findcommonoutgoing(
                     repo, remote, commoninc=commoninc
                 )
                 ui.status(_(b'looking for unused includes to remove\n'))
                 localfiles = set()
                 for n in itertools.chain(outgoing.missing, outgoing.excluded):
                     localfiles.update(repo[n].files())
                 suggestedremovals = []
                 for include in sorted(oldincludes):
                     match = narrowspec.match(repo.root, [include], oldexcludes)
                     if not any(match(f) for f in localfiles):
                         suggestedremovals.append(include)
                 if suggestedremovals:
                     for s in suggestedremovals:
                         ui.status(b'%s\n' % s)
                     if (
                         ui.promptchoice(
                             _(
                                 b'remove these unused includes (yn)?'
                                 b'$$ &Yes $$ &No'
                             )
                         )
                         == 0
                     ):
                         removedincludes.update(suggestedremovals)
                         narrowing = True
                 else:
                     ui.status(_(b'found no unused includes\n'))
 
             if narrowing:
                 newincludes = oldincludes - removedincludes
                 newexcludes = oldexcludes | addedexcludes
                 _narrow(
                     ui,
                     repo,
                     remote,
                     commoninc,
                     oldincludes,
                     oldexcludes,
                     newincludes,
                     newexcludes,
                     opts[b'force_delete_local_changes'],
                     opts[b'backup'],
                 )
                 # _narrow() updated the narrowspec and _widen() below needs to
                 # use the updated values as its base (otherwise removed includes
                 # and addedexcludes will be lost in the resulting narrowspec)
                 oldincludes = newincludes
                 oldexcludes = newexcludes
 
             if widening:
                 newincludes = oldincludes | addedincludes
                 newexcludes = oldexcludes - removedexcludes
                 _widen(
                     ui,
                     repo,
                     remote,
                     commoninc,
                     oldincludes,
                     oldexcludes,
                     newincludes,
                     newexcludes,
                 )
         finally:
             remote.close()
 
     return 0

hgext/remotefilelog/remotefilelogserver.py

@@ -1,437 +1,446 b''
 # remotefilelogserver.py - server logic for a remotefilelog server
 #
 # 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 stat
 import time
 import zlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex
 from mercurial.pycompat import open
 from mercurial import (
     changegroup,
     changelog,
     context,
     error,
     extensions,
     match,
     scmutil,
     store,
     streamclone,
     util,
     wireprotoserver,
     wireprototypes,
     wireprotov1server,
 )
 from . import (
     constants,
     shallowutil,
 )
 
 _sshv1server = wireprotoserver.sshv1protocolhandler
 
 
 def setupserver(ui, repo):
     """Sets up a normal Mercurial repo so it can serve files to shallow repos."""
     onetimesetup(ui)
 
     # don't send files to shallow clients during pulls
     def generatefiles(
         orig, self, changedfiles, linknodes, commonrevs, source, *args, **kwargs
     ):
         caps = self._bundlecaps or []
         if constants.BUNDLE2_CAPABLITY in caps:
             # only send files that don't match the specified patterns
             includepattern = None
             excludepattern = None
             for cap in self._bundlecaps or []:
                 if cap.startswith(b"includepattern="):
                     includepattern = cap[len(b"includepattern=") :].split(b'\0')
                 elif cap.startswith(b"excludepattern="):
                     excludepattern = cap[len(b"excludepattern=") :].split(b'\0')
 
             m = match.always()
             if includepattern or excludepattern:
                 m = match.match(
                     repo.root, b'', None, includepattern, excludepattern
                 )
 
             changedfiles = list([f for f in changedfiles if not m(f)])
         return orig(
             self, changedfiles, linknodes, commonrevs, source, *args, **kwargs
         )
 
     extensions.wrapfunction(
         changegroup.cgpacker, b'generatefiles', generatefiles
     )
 
 
 onetime = False
 
 
 def onetimesetup(ui):
     """Configures the wireprotocol for both clients and servers."""
     global onetime
     if onetime:
         return
     onetime = True
 
     # support file content requests
     wireprotov1server.wireprotocommand(
         b'x_rfl_getflogheads', b'path', permission=b'pull'
     )(getflogheads)
     wireprotov1server.wireprotocommand(
         b'x_rfl_getfiles', b'', permission=b'pull'
     )(getfiles)
     wireprotov1server.wireprotocommand(
         b'x_rfl_getfile', b'file node', permission=b'pull'
     )(getfile)
 
     class streamstate:
         match = None
         shallowremote = False
         noflatmf = False
 
     state = streamstate()
 
     def stream_out_shallow(repo, proto, other):
         includepattern = None
         excludepattern = None
         raw = other.get(b'includepattern')
         if raw:
             includepattern = raw.split(b'\0')
         raw = other.get(b'excludepattern')
         if raw:
             excludepattern = raw.split(b'\0')
 
         oldshallow = state.shallowremote
         oldmatch = state.match
         oldnoflatmf = state.noflatmf
         try:
             state.shallowremote = True
             state.match = match.always()
             state.noflatmf = other.get(b'noflatmanifest') == b'True'
             if includepattern or excludepattern:
                 state.match = match.match(
                     repo.root, b'', None, includepattern, excludepattern
                 )
             streamres = wireprotov1server.stream(repo, proto)
 
             # Force the first value to execute, so the file list is computed
             # within the try/finally scope
             first = next(streamres.gen)
             second = next(streamres.gen)
 
             def gen():
                 yield first
                 yield second
                 for value in streamres.gen:
                     yield value
 
             return wireprototypes.streamres(gen())
         finally:
             state.shallowremote = oldshallow
             state.match = oldmatch
             state.noflatmf = oldnoflatmf
 
     wireprotov1server.commands[b'stream_out_shallow'] = (
         stream_out_shallow,
         b'*',
     )
 
     # don't clone filelogs to shallow clients
     def _walkstreamfiles(orig, repo, matcher=None):
         if state.shallowremote:
             # if we are shallow ourselves, stream our local commits
             if shallowutil.isenabled(repo):
                 striplen = len(repo.store.path) + 1
                 readdir = repo.store.rawvfs.readdir
                 visit = [os.path.join(repo.store.path, b'data')]
                 while visit:
                     p = visit.pop()
                     for f, kind, st in readdir(p, stat=True):
                         fp = p + b'/' + f
                         if kind == stat.S_IFREG:
                             if not fp.endswith(b'.i') and not fp.endswith(
                                 b'.d'
                             ):
                                 n = util.pconvert(fp[striplen:])
                                 d = store.decodedir(n)
-                                t = store.FILETYPE_OTHER
-                                yield (t, d, st.st_size)
+                                yield store.StoreEntry(
+                                    unencoded_path=d,
+                                    is_revlog=True,
+                                    revlog_type=None,
+                                    is_revlog_main=False,
+                                    is_volatile=False,
+                                    file_size=st.st_size,
+                                )
+
                         if kind == stat.S_IFDIR:
                             visit.append(fp)
 
             if scmutil.istreemanifest(repo):
-                for (t, u, s) in repo.store.datafiles():
+                for entry in repo.store.datafiles():
+                    u = entry.unencoded_path
                     if u.startswith(b'meta/') and (
                         u.endswith(b'.i') or u.endswith(b'.d')
                     ):
-                        yield (t, u, s)
+                        yield entry
 
             # Return .d and .i files that do not match the shallow pattern
             match = state.match
             if match and not match.always():
-                for (t, u, s) in repo.store.datafiles():
+                for entry in repo.store.datafiles():
+                    u = entry.unencoded_path
                     f = u[5:-2]  # trim data/...  and .i/.d
                     if not state.match(f):
-                        yield (t, u, s)
+                        yield entry
 
             for x in repo.store.topfiles():
                 if state.noflatmf and x[1][:11] == b'00manifest.':
                     continue
                 yield x
 
         elif shallowutil.isenabled(repo):
             # don't allow cloning from a shallow repo to a full repo
             # since it would require fetching every version of every
             # file in order to create the revlogs.
             raise error.Abort(
                 _(b"Cannot clone from a shallow repo to a full repo.")
             )
         else:
             for x in orig(repo, matcher):
                 yield x
 
     extensions.wrapfunction(streamclone, b'_walkstreamfiles', _walkstreamfiles)
 
     # expose remotefilelog capabilities
     def _capabilities(orig, repo, proto):
         caps = orig(repo, proto)
         if shallowutil.isenabled(repo) or ui.configbool(
             b'remotefilelog', b'server'
         ):
             if isinstance(proto, _sshv1server):
                 # legacy getfiles method which only works over ssh
                 caps.append(constants.NETWORK_CAP_LEGACY_SSH_GETFILES)
             caps.append(b'x_rfl_getflogheads')
             caps.append(b'x_rfl_getfile')
         return caps
 
     extensions.wrapfunction(wireprotov1server, b'_capabilities', _capabilities)
 
     def _adjustlinkrev(orig, self, *args, **kwargs):
         # When generating file blobs, taking the real path is too slow on large
         # repos, so force it to just return the linkrev directly.
         repo = self._repo
         if util.safehasattr(repo, b'forcelinkrev') and repo.forcelinkrev:
             return self._filelog.linkrev(self._filelog.rev(self._filenode))
         return orig(self, *args, **kwargs)
 
     extensions.wrapfunction(
         context.basefilectx, b'_adjustlinkrev', _adjustlinkrev
     )
 
     def _iscmd(orig, cmd):
         if cmd == b'x_rfl_getfiles':
             return False
         return orig(cmd)
 
     extensions.wrapfunction(wireprotoserver, b'iscmd', _iscmd)
 
 
 def _loadfileblob(repo, cachepath, path, node):
     filecachepath = os.path.join(cachepath, path, hex(node))
     if not os.path.exists(filecachepath) or os.path.getsize(filecachepath) == 0:
         filectx = repo.filectx(path, fileid=node)
         if filectx.node() == repo.nullid:
             repo.changelog = changelog.changelog(repo.svfs)
             filectx = repo.filectx(path, fileid=node)
 
         text = createfileblob(filectx)
         # TODO configurable compression engines
         text = zlib.compress(text)
 
         # everything should be user & group read/writable
         oldumask = os.umask(0o002)
         try:
             dirname = os.path.dirname(filecachepath)
             if not os.path.exists(dirname):
                 try:
                     os.makedirs(dirname)
                 except FileExistsError:
                     pass
 
             f = None
             try:
                 f = util.atomictempfile(filecachepath, b"wb")
                 f.write(text)
             except (IOError, OSError):
                 # Don't abort if the user only has permission to read,
                 # and not write.
                 pass
             finally:
                 if f:
                     f.close()
         finally:
             os.umask(oldumask)
     else:
         with open(filecachepath, b"rb") as f:
             text = f.read()
     return text
 
 
 def getflogheads(repo, proto, path):
     """A server api for requesting a filelog's heads"""
     flog = repo.file(path)
     heads = flog.heads()
     return b'\n'.join((hex(head) for head in heads if head != repo.nullid))
 
 
 def getfile(repo, proto, file, node):
     """A server api for requesting a particular version of a file. Can be used
     in batches to request many files at once. The return protocol is:
     <errorcode>\0<data/errormsg> where <errorcode> is 0 for success or
     non-zero for an error.
 
     data is a compressed blob with revlog flag and ancestors information. See
     createfileblob for its content.
     """
     if shallowutil.isenabled(repo):
         return b'1\0' + _(b'cannot fetch remote files from shallow repo')
     cachepath = repo.ui.config(b"remotefilelog", b"servercachepath")
     if not cachepath:
         cachepath = os.path.join(repo.path, b"remotefilelogcache")
     node = bin(node.strip())
     if node == repo.nullid:
         return b'0\0'
     return b'0\0' + _loadfileblob(repo, cachepath, file, node)
 
 
 def getfiles(repo, proto):
     """A server api for requesting particular versions of particular files."""
     if shallowutil.isenabled(repo):
         raise error.Abort(_(b'cannot fetch remote files from shallow repo'))
     if not isinstance(proto, _sshv1server):
         raise error.Abort(_(b'cannot fetch remote files over non-ssh protocol'))
 
     def streamer():
         fin = proto._fin
 
         cachepath = repo.ui.config(b"remotefilelog", b"servercachepath")
         if not cachepath:
             cachepath = os.path.join(repo.path, b"remotefilelogcache")
 
         while True:
             request = fin.readline()[:-1]
             if not request:
                 break
 
             node = bin(request[:40])
             if node == repo.nullid:
                 yield b'0\n'
                 continue
 
             path = request[40:]
 
             text = _loadfileblob(repo, cachepath, path, node)
 
             yield b'%d\n%s' % (len(text), text)
 
             # it would be better to only flush after processing a whole batch
             # but currently we don't know if there are more requests coming
             proto._fout.flush()
 
     return wireprototypes.streamres(streamer())
 
 
 def createfileblob(filectx):
     """
     format:
         v0:
             str(len(rawtext)) + '\0' + rawtext + ancestortext
         v1:
             'v1' + '\n' + metalist + '\0' + rawtext + ancestortext
             metalist := metalist + '\n' + meta | meta
             meta := sizemeta | flagmeta
             sizemeta := METAKEYSIZE + str(len(rawtext))
             flagmeta := METAKEYFLAG + str(flag)
 
             note: sizemeta must exist. METAKEYFLAG and METAKEYSIZE must have a
             length of 1.
     """
     flog = filectx.filelog()
     frev = filectx.filerev()
     revlogflags = flog._revlog.flags(frev)
     if revlogflags == 0:
         # normal files
         text = filectx.data()
     else:
         # lfs, read raw revision data
         text = flog.rawdata(frev)
 
     repo = filectx._repo
 
     ancestors = [filectx]
 
     try:
         repo.forcelinkrev = True
         ancestors.extend([f for f in filectx.ancestors()])
 
         ancestortext = b""
         for ancestorctx in ancestors:
             parents = ancestorctx.parents()
             p1 = repo.nullid
             p2 = repo.nullid
             if len(parents) > 0:
                 p1 = parents[0].filenode()
             if len(parents) > 1:
                 p2 = parents[1].filenode()
 
             copyname = b""
             rename = ancestorctx.renamed()
             if rename:
                 copyname = rename[0]
             linknode = ancestorctx.node()
             ancestortext += b"%s%s%s%s%s\0" % (
                 ancestorctx.filenode(),
                 p1,
                 p2,
                 linknode,
                 copyname,
             )
     finally:
         repo.forcelinkrev = False
 
     header = shallowutil.buildfileblobheader(len(text), revlogflags)
 
     return b"%s\0%s%s" % (header, text, ancestortext)
 
 
 def gcserver(ui, repo):
     if not repo.ui.configbool(b"remotefilelog", b"server"):
         return
 
     neededfiles = set()
     heads = repo.revs(b"heads(tip~25000:) - null")
 
     cachepath = repo.vfs.join(b"remotefilelogcache")
     for head in heads:
         mf = repo[head].manifest()
         for filename, filenode in mf.items():
             filecachepath = os.path.join(cachepath, filename, hex(filenode))
             neededfiles.add(filecachepath)
 
     # delete unneeded older files
     days = repo.ui.configint(b"remotefilelog", b"serverexpiration")
     expiration = time.time() - (days * 24 * 60 * 60)
 
     progress = ui.makeprogress(_(b"removing old server cache"), unit=b"files")
     progress.update(0)
     for root, dirs, files in os.walk(cachepath):
         for file in files:
             filepath = os.path.join(root, file)
             progress.increment()
             if filepath in neededfiles:
                 continue
 
             stat = os.stat(filepath)
             if stat.st_mtime < expiration:
                 os.remove(filepath)
 
     progress.complete()

mercurial/repair.py

@@ -1,574 +1,576 b''
 # repair.py - functions for repository repair for mercurial
 #
 # Copyright 2005, 2006 Chris Mason <[e-mail]>
 # Copyright 2007 Olivia Mackall
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 from .i18n import _
 from .node import (
     hex,
     short,
 )
 from . import (
     bundle2,
     changegroup,
     discovery,
     error,
     exchange,
     obsolete,
     obsutil,
     pathutil,
     phases,
     requirements,
     scmutil,
     transaction,
     util,
 )
 from .utils import (
     hashutil,
     urlutil,
 )
 
 
 def backupbundle(
     repo,
     bases,
     heads,
     node,
     suffix,
     compress=True,
     obsolescence=True,
     tmp_backup=False,
 ):
     """create a bundle with the specified revisions as a backup"""
 
     backupdir = b"strip-backup"
     vfs = repo.vfs
     if not vfs.isdir(backupdir):
         vfs.mkdir(backupdir)
 
     # Include a hash of all the nodes in the filename for uniqueness
     allcommits = repo.set(b'%ln::%ln', bases, heads)
     allhashes = sorted(c.hex() for c in allcommits)
     totalhash = hashutil.sha1(b''.join(allhashes)).digest()
     name = b"%s/%s-%s-%s.hg" % (
         backupdir,
         short(node),
         hex(totalhash[:4]),
         suffix,
     )
 
     cgversion = changegroup.localversion(repo)
     comp = None
     if cgversion != b'01':
         bundletype = b"HG20"
         if compress:
             comp = b'BZ'
     elif compress:
         bundletype = b"HG10BZ"
     else:
         bundletype = b"HG10UN"
 
     outgoing = discovery.outgoing(repo, missingroots=bases, ancestorsof=heads)
     contentopts = {
         b'cg.version': cgversion,
         b'obsolescence': obsolescence,
         b'phases': True,
     }
     return bundle2.writenewbundle(
         repo.ui,
         repo,
         b'strip',
         name,
         bundletype,
         outgoing,
         contentopts,
         vfs,
         compression=comp,
         allow_internal=tmp_backup,
     )
 
 
 def _collectfiles(repo, striprev):
     """find out the filelogs affected by the strip"""
     files = set()
 
     for x in range(striprev, len(repo)):
         files.update(repo[x].files())
 
     return sorted(files)
 
 
 def _collectrevlog(revlog, striprev):
     _, brokenset = revlog.getstrippoint(striprev)
     return [revlog.linkrev(r) for r in brokenset]
 
 
 def _collectbrokencsets(repo, files, striprev):
     """return the changesets which will be broken by the truncation"""
     s = set()
 
     for revlog in manifestrevlogs(repo):
         s.update(_collectrevlog(revlog, striprev))
     for fname in files:
         s.update(_collectrevlog(repo.file(fname), striprev))
 
     return s
 
 
 def strip(ui, repo, nodelist, backup=True, topic=b'backup'):
     # This function requires the caller to lock the repo, but it operates
     # within a transaction of its own, and thus requires there to be no current
     # transaction when it is called.
     if repo.currenttransaction() is not None:
         raise error.ProgrammingError(b'cannot strip from inside a transaction')
 
     # Simple way to maintain backwards compatibility for this
     # argument.
     if backup in [b'none', b'strip']:
         backup = False
 
     repo = repo.unfiltered()
     repo.destroying()
     vfs = repo.vfs
     # load bookmark before changelog to avoid side effect from outdated
     # changelog (see repo._refreshchangelog)
     repo._bookmarks
     cl = repo.changelog
 
     # TODO handle undo of merge sets
     if isinstance(nodelist, bytes):
         nodelist = [nodelist]
     striplist = [cl.rev(node) for node in nodelist]
     striprev = min(striplist)
 
     files = _collectfiles(repo, striprev)
     saverevs = _collectbrokencsets(repo, files, striprev)
 
     # Some revisions with rev > striprev may not be descendants of striprev.
     # We have to find these revisions and put them in a bundle, so that
     # we can restore them after the truncations.
     # To create the bundle we use repo.changegroupsubset which requires
     # the list of heads and bases of the set of interesting revisions.
     # (head = revision in the set that has no descendant in the set;
     #  base = revision in the set that has no ancestor in the set)
     tostrip = set(striplist)
     saveheads = set(saverevs)
     for r in cl.revs(start=striprev + 1):
         if any(p in tostrip for p in cl.parentrevs(r)):
             tostrip.add(r)
 
         if r not in tostrip:
             saverevs.add(r)
             saveheads.difference_update(cl.parentrevs(r))
             saveheads.add(r)
     saveheads = [cl.node(r) for r in saveheads]
 
     # compute base nodes
     if saverevs:
         descendants = set(cl.descendants(saverevs))
         saverevs.difference_update(descendants)
     savebases = [cl.node(r) for r in saverevs]
     stripbases = [cl.node(r) for r in tostrip]
 
     stripobsidx = obsmarkers = ()
     if repo.ui.configbool(b'devel', b'strip-obsmarkers'):
         obsmarkers = obsutil.exclusivemarkers(repo, stripbases)
     if obsmarkers:
         stripobsidx = [
             i for i, m in enumerate(repo.obsstore) if m in obsmarkers
         ]
 
     newbmtarget, updatebm = _bookmarkmovements(repo, tostrip)
 
     backupfile = None
     node = nodelist[-1]
     if backup:
         backupfile = _createstripbackup(repo, stripbases, node, topic)
     # create a changegroup for all the branches we need to keep
     tmpbundlefile = None
     if saveheads:
         # do not compress temporary bundle if we remove it from disk later
         #
         # We do not include obsolescence, it might re-introduce prune markers
         # we are trying to strip.  This is harmless since the stripped markers
         # are already backed up and we did not touched the markers for the
         # saved changesets.
         tmpbundlefile = backupbundle(
             repo,
             savebases,
             saveheads,
             node,
             b'temp',
             compress=False,
             obsolescence=False,
             tmp_backup=True,
         )
 
     with ui.uninterruptible():
         try:
             with repo.transaction(b"strip") as tr:
                 # TODO this code violates the interface abstraction of the
                 # transaction and makes assumptions that file storage is
                 # using append-only files. We'll need some kind of storage
                 # API to handle stripping for us.
                 oldfiles = set(tr._offsetmap.keys())
                 oldfiles.update(tr._newfiles)
 
                 tr.startgroup()
                 cl.strip(striprev, tr)
                 stripmanifest(repo, striprev, tr, files)
 
                 for fn in files:
                     repo.file(fn).strip(striprev, tr)
                 tr.endgroup()
 
                 entries = tr.readjournal()
 
                 for file, troffset in entries:
                     if file in oldfiles:
                         continue
                     with repo.svfs(file, b'a', checkambig=True) as fp:
                         fp.truncate(troffset)
                     if troffset == 0:
                         repo.store.markremoved(file)
 
                 deleteobsmarkers(repo.obsstore, stripobsidx)
                 del repo.obsstore
                 repo.invalidatevolatilesets()
                 repo._phasecache.filterunknown(repo)
 
             if tmpbundlefile:
                 ui.note(_(b"adding branch\n"))
                 f = vfs.open(tmpbundlefile, b"rb")
                 gen = exchange.readbundle(ui, f, tmpbundlefile, vfs)
                 # silence internal shuffling chatter
                 maybe_silent = (
                     repo.ui.silent()
                     if not repo.ui.verbose
                     else util.nullcontextmanager()
                 )
                 with maybe_silent:
                     tmpbundleurl = b'bundle:' + vfs.join(tmpbundlefile)
                     txnname = b'strip'
                     if not isinstance(gen, bundle2.unbundle20):
                         txnname = b"strip\n%s" % urlutil.hidepassword(
                             tmpbundleurl
                         )
                     with repo.transaction(txnname) as tr:
                         bundle2.applybundle(
                             repo, gen, tr, source=b'strip', url=tmpbundleurl
                         )
                 f.close()
 
             with repo.transaction(b'repair') as tr:
                 bmchanges = [(m, repo[newbmtarget].node()) for m in updatebm]
                 repo._bookmarks.applychanges(repo, tr, bmchanges)
 
             transaction.cleanup_undo_files(repo.ui.warn, repo.vfs_map)
 
         except:  # re-raises
             if backupfile:
                 ui.warn(
                     _(b"strip failed, backup bundle stored in '%s'\n")
                     % vfs.join(backupfile)
                 )
             if tmpbundlefile:
                 ui.warn(
                     _(b"strip failed, unrecovered changes stored in '%s'\n")
                     % vfs.join(tmpbundlefile)
                 )
                 ui.warn(
                     _(
                         b"(fix the problem, then recover the changesets with "
                         b"\"hg unbundle '%s'\")\n"
                     )
                     % vfs.join(tmpbundlefile)
                 )
             raise
         else:
             if tmpbundlefile:
                 # Remove temporary bundle only if there were no exceptions
                 vfs.unlink(tmpbundlefile)
 
     repo.destroyed()
     # return the backup file path (or None if 'backup' was False) so
     # extensions can use it
     return backupfile
 
 
 def softstrip(ui, repo, nodelist, backup=True, topic=b'backup'):
     """perform a "soft" strip using the archived phase"""
     tostrip = [c.node() for c in repo.set(b'sort(%ln::)', nodelist)]
     if not tostrip:
         return None
 
     backupfile = None
     if backup:
         node = tostrip[0]
         backupfile = _createstripbackup(repo, tostrip, node, topic)
 
     newbmtarget, updatebm = _bookmarkmovements(repo, tostrip)
     with repo.transaction(b'strip') as tr:
         phases.retractboundary(repo, tr, phases.archived, tostrip)
         bmchanges = [(m, repo[newbmtarget].node()) for m in updatebm]
         repo._bookmarks.applychanges(repo, tr, bmchanges)
     return backupfile
 
 
 def _bookmarkmovements(repo, tostrip):
     # compute necessary bookmark movement
     bm = repo._bookmarks
     updatebm = []
     for m in bm:
         rev = repo[bm[m]].rev()
         if rev in tostrip:
             updatebm.append(m)
     newbmtarget = None
     # If we need to move bookmarks, compute bookmark
     # targets. Otherwise we can skip doing this logic.
     if updatebm:
         # For a set s, max(parents(s) - s) is the same as max(heads(::s - s)),
         # but is much faster
         newbmtarget = repo.revs(b'max(parents(%ld) - (%ld))', tostrip, tostrip)
         if newbmtarget:
             newbmtarget = repo[newbmtarget.first()].node()
         else:
             newbmtarget = b'.'
     return newbmtarget, updatebm
 
 
 def _createstripbackup(repo, stripbases, node, topic):
     # backup the changeset we are about to strip
     vfs = repo.vfs
     unfi = repo.unfiltered()
     to_node = unfi.changelog.node
     # internal changeset are internal implementation details that should not
     # leave the repository and not be exposed to the users. In addition feature
     # using them requires to be resistant to strip. See test case for more
     # details.
     all_backup = unfi.revs(
         b"(%ln)::(%ld) and not _internal()",
         stripbases,
         unfi.changelog.headrevs(),
     )
     if not all_backup:
         return None
 
     def to_nodes(revs):
         return [to_node(r) for r in revs]
 
     bases = to_nodes(unfi.revs("roots(%ld)", all_backup))
     heads = to_nodes(unfi.revs("heads(%ld)", all_backup))
     backupfile = backupbundle(repo, bases, heads, node, topic)
     repo.ui.status(_(b"saved backup bundle to %s\n") % vfs.join(backupfile))
     repo.ui.log(
         b"backupbundle", b"saved backup bundle to %s\n", vfs.join(backupfile)
     )
     return backupfile
 
 
 def safestriproots(ui, repo, nodes):
     """return list of roots of nodes where descendants are covered by nodes"""
     torev = repo.unfiltered().changelog.rev
     revs = {torev(n) for n in nodes}
     # tostrip = wanted - unsafe = wanted - ancestors(orphaned)
     # orphaned = affected - wanted
     # affected = descendants(roots(wanted))
     # wanted = revs
     revset = b'%ld - ( ::( (roots(%ld):: and not _phase(%s)) -%ld) )'
     tostrip = set(repo.revs(revset, revs, revs, phases.internal, revs))
     notstrip = revs - tostrip
     if notstrip:
         nodestr = b', '.join(sorted(short(repo[n].node()) for n in notstrip))
         ui.warn(
             _(b'warning: orphaned descendants detected, not stripping %s\n')
             % nodestr
         )
     return [c.node() for c in repo.set(b'roots(%ld)', tostrip)]
 
 
 class stripcallback:
     """used as a transaction postclose callback"""
 
     def __init__(self, ui, repo, backup, topic):
         self.ui = ui
         self.repo = repo
         self.backup = backup
         self.topic = topic or b'backup'
         self.nodelist = []
 
     def addnodes(self, nodes):
         self.nodelist.extend(nodes)
 
     def __call__(self, tr):
         roots = safestriproots(self.ui, self.repo, self.nodelist)
         if roots:
             strip(self.ui, self.repo, roots, self.backup, self.topic)
 
 
 def delayedstrip(ui, repo, nodelist, topic=None, backup=True):
     """like strip, but works inside transaction and won't strip irreverent revs
 
     nodelist must explicitly contain all descendants. Otherwise a warning will
     be printed that some nodes are not stripped.
 
     Will do a backup if `backup` is True. The last non-None "topic" will be
     used as the backup topic name. The default backup topic name is "backup".
     """
     tr = repo.currenttransaction()
     if not tr:
         nodes = safestriproots(ui, repo, nodelist)
         return strip(ui, repo, nodes, backup=backup, topic=topic)
     # transaction postclose callbacks are called in alphabet order.
     # use '\xff' as prefix so we are likely to be called last.
     callback = tr.getpostclose(b'\xffstrip')
     if callback is None:
         callback = stripcallback(ui, repo, backup=backup, topic=topic)
         tr.addpostclose(b'\xffstrip', callback)
     if topic:
         callback.topic = topic
     callback.addnodes(nodelist)
 
 
 def stripmanifest(repo, striprev, tr, files):
     for revlog in manifestrevlogs(repo):
         revlog.strip(striprev, tr)
 
 
 def manifestrevlogs(repo):
     yield repo.manifestlog.getstorage(b'')
     if scmutil.istreemanifest(repo):
         # This logic is safe if treemanifest isn't enabled, but also
         # pointless, so we skip it if treemanifest isn't enabled.
-        for t, unencoded, size in repo.store.datafiles():
+        for entry in repo.store.datafiles():
+            unencoded = entry.unencoded_path
+            # XXX use the entry.revlog_type instead
             if unencoded.startswith(b'meta/') and unencoded.endswith(
                 b'00manifest.i'
             ):
                 dir = unencoded[5:-12]
                 yield repo.manifestlog.getstorage(dir)
 
 
 def rebuildfncache(ui, repo, only_data=False):
     """Rebuilds the fncache file from repo history.
 
     Missing entries will be added. Extra entries will be removed.
     """
     repo = repo.unfiltered()
 
     if requirements.FNCACHE_REQUIREMENT not in repo.requirements:
         ui.warn(
             _(
                 b'(not rebuilding fncache because repository does not '
                 b'support fncache)\n'
             )
         )
         return
 
     with repo.lock():
         fnc = repo.store.fncache
         fnc.ensureloaded(warn=ui.warn)
 
         oldentries = set(fnc.entries)
         newentries = set()
         seenfiles = set()
 
         if only_data:
             # Trust the listing of .i from the fncache, but not the .d. This is
             # much faster, because we only need to stat every possible .d files,
             # instead of reading the full changelog
             for f in fnc:
                 if f[:5] == b'data/' and f[-2:] == b'.i':
                     seenfiles.add(f[5:-2])
                     newentries.add(f)
                     dataf = f[:-2] + b'.d'
                     if repo.store._exists(dataf):
                         newentries.add(dataf)
         else:
             progress = ui.makeprogress(
                 _(b'rebuilding'), unit=_(b'changesets'), total=len(repo)
             )
             for rev in repo:
                 progress.update(rev)
 
                 ctx = repo[rev]
                 for f in ctx.files():
                     # This is to minimize I/O.
                     if f in seenfiles:
                         continue
                     seenfiles.add(f)
 
                     i = b'data/%s.i' % f
                     d = b'data/%s.d' % f
 
                     if repo.store._exists(i):
                         newentries.add(i)
                     if repo.store._exists(d):
                         newentries.add(d)
 
             progress.complete()
 
         if requirements.TREEMANIFEST_REQUIREMENT in repo.requirements:
             # This logic is safe if treemanifest isn't enabled, but also
             # pointless, so we skip it if treemanifest isn't enabled.
             for dir in pathutil.dirs(seenfiles):
                 i = b'meta/%s/00manifest.i' % dir
                 d = b'meta/%s/00manifest.d' % dir
 
                 if repo.store._exists(i):
                     newentries.add(i)
                 if repo.store._exists(d):
                     newentries.add(d)
 
         addcount = len(newentries - oldentries)
         removecount = len(oldentries - newentries)
         for p in sorted(oldentries - newentries):
             ui.write(_(b'removing %s\n') % p)
         for p in sorted(newentries - oldentries):
             ui.write(_(b'adding %s\n') % p)
 
         if addcount or removecount:
             ui.write(
                 _(b'%d items added, %d removed from fncache\n')
                 % (addcount, removecount)
             )
             fnc.entries = newentries
             fnc._dirty = True
 
             with repo.transaction(b'fncache') as tr:
                 fnc.write(tr)
         else:
             ui.write(_(b'fncache already up to date\n'))
 
 
 def deleteobsmarkers(obsstore, indices):
     """Delete some obsmarkers from obsstore and return how many were deleted
 
     'indices' is a list of ints which are the indices
     of the markers to be deleted.
 
     Every invocation of this function completely rewrites the obsstore file,
     skipping the markers we want to be removed. The new temporary file is
     created, remaining markers are written there and on .close() this file
     gets atomically renamed to obsstore, thus guaranteeing consistency."""
     if not indices:
         # we don't want to rewrite the obsstore with the same content
         return
 
     left = []
     current = obsstore._all
     n = 0
     for i, m in enumerate(current):
         if i in indices:
             n += 1
             continue
         left.append(m)
 
     newobsstorefile = obsstore.svfs(b'obsstore', b'w', atomictemp=True)
     for bytes in obsolete.encodemarkers(left, True, obsstore._version):
         newobsstorefile.write(bytes)
     newobsstorefile.close()
     return n

mercurial/revlogutils/rewrite.py

@@ -1,883 +1,888 b''
 # censor code related to censoring revision
 # coding: utf8
 #
 # Copyright 2021 Pierre-Yves David <[e-mail]>
 # Copyright 2015 Google, Inc <[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 binascii
 import contextlib
 import os
 import struct
 
 from ..node import (
     nullrev,
 )
 from .constants import (
     COMP_MODE_PLAIN,
     ENTRY_DATA_COMPRESSED_LENGTH,
     ENTRY_DATA_COMPRESSION_MODE,
     ENTRY_DATA_OFFSET,
     ENTRY_DATA_UNCOMPRESSED_LENGTH,
     ENTRY_DELTA_BASE,
     ENTRY_LINK_REV,
     ENTRY_NODE_ID,
     ENTRY_PARENT_1,
     ENTRY_PARENT_2,
     ENTRY_SIDEDATA_COMPRESSED_LENGTH,
     ENTRY_SIDEDATA_COMPRESSION_MODE,
     ENTRY_SIDEDATA_OFFSET,
     REVIDX_ISCENSORED,
     REVLOGV0,
     REVLOGV1,
 )
 from ..i18n import _
 
 from .. import (
     error,
     mdiff,
     pycompat,
     revlogutils,
     util,
 )
 from ..utils import (
     storageutil,
 )
 from . import (
     constants,
     deltas,
 )
 
 
 def v1_censor(rl, tr, censornode, tombstone=b''):
     """censors a revision in a "version 1" revlog"""
     assert rl._format_version == constants.REVLOGV1, rl._format_version
 
     # avoid cycle
     from .. import revlog
 
     censorrev = rl.rev(censornode)
     tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
     # Rewriting the revlog in place is hard. Our strategy for censoring is
     # to create a new revlog, copy all revisions to it, then replace the
     # revlogs on transaction close.
     #
     # This is a bit dangerous. We could easily have a mismatch of state.
     newrl = revlog.revlog(
         rl.opener,
         target=rl.target,
         radix=rl.radix,
         postfix=b'tmpcensored',
         censorable=True,
     )
     newrl._format_version = rl._format_version
     newrl._format_flags = rl._format_flags
     newrl._generaldelta = rl._generaldelta
     newrl._parse_index = rl._parse_index
 
     for rev in rl.revs():
         node = rl.node(rev)
         p1, p2 = rl.parents(node)
 
         if rev == censorrev:
             newrl.addrawrevision(
                 tombstone,
                 tr,
                 rl.linkrev(censorrev),
                 p1,
                 p2,
                 censornode,
                 constants.REVIDX_ISCENSORED,
             )
 
             if newrl.deltaparent(rev) != nullrev:
                 m = _(b'censored revision stored as delta; cannot censor')
                 h = _(
                     b'censoring of revlogs is not fully implemented;'
                     b' please report this bug'
                 )
                 raise error.Abort(m, hint=h)
             continue
 
         if rl.iscensored(rev):
             if rl.deltaparent(rev) != nullrev:
                 m = _(
                     b'cannot censor due to censored '
                     b'revision having delta stored'
                 )
                 raise error.Abort(m)
             rawtext = rl._chunk(rev)
         else:
             rawtext = rl.rawdata(rev)
 
         newrl.addrawrevision(
             rawtext, tr, rl.linkrev(rev), p1, p2, node, rl.flags(rev)
         )
 
     tr.addbackup(rl._indexfile, location=b'store')
     if not rl._inline:
         tr.addbackup(rl._datafile, location=b'store')
 
     rl.opener.rename(newrl._indexfile, rl._indexfile)
     if not rl._inline:
         rl.opener.rename(newrl._datafile, rl._datafile)
 
     rl.clearcaches()
     rl._loadindex()
 
 
 def v2_censor(revlog, tr, censornode, tombstone=b''):
     """censors a revision in a "version 2" revlog"""
     assert revlog._format_version != REVLOGV0, revlog._format_version
     assert revlog._format_version != REVLOGV1, revlog._format_version
 
     censor_revs = {revlog.rev(censornode)}
     _rewrite_v2(revlog, tr, censor_revs, tombstone)
 
 
 def _rewrite_v2(revlog, tr, censor_revs, tombstone=b''):
     """rewrite a revlog to censor some of its content
 
     General principle
 
     We create new revlog files (index/data/sidedata) to copy the content of
     the existing data without the censored data.
 
     We need to recompute new delta for any revision that used the censored
     revision as delta base. As the cumulative size of the new delta may be
     large, we store them in a temporary file until they are stored in their
     final destination.
 
     All data before the censored data can be blindly copied. The rest needs
     to be copied as we go and the associated index entry needs adjustement.
     """
     assert revlog._format_version != REVLOGV0, revlog._format_version
     assert revlog._format_version != REVLOGV1, revlog._format_version
 
     old_index = revlog.index
     docket = revlog._docket
 
     tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
     first_excl_rev = min(censor_revs)
 
     first_excl_entry = revlog.index[first_excl_rev]
     index_cutoff = revlog.index.entry_size * first_excl_rev
     data_cutoff = first_excl_entry[ENTRY_DATA_OFFSET] >> 16
     sidedata_cutoff = revlog.sidedata_cut_off(first_excl_rev)
 
     with pycompat.unnamedtempfile(mode=b"w+b") as tmp_storage:
         # rev → (new_base, data_start, data_end, compression_mode)
         rewritten_entries = _precompute_rewritten_delta(
             revlog,
             old_index,
             censor_revs,
             tmp_storage,
         )
 
         all_files = _setup_new_files(
             revlog,
             index_cutoff,
             data_cutoff,
             sidedata_cutoff,
         )
 
         # we dont need to open the old index file since its content already
         # exist in a usable form in `old_index`.
         with all_files() as open_files:
             (
                 old_data_file,
                 old_sidedata_file,
                 new_index_file,
                 new_data_file,
                 new_sidedata_file,
             ) = open_files
 
             # writing the censored revision
 
             # Writing all subsequent revisions
             for rev in range(first_excl_rev, len(old_index)):
                 if rev in censor_revs:
                     _rewrite_censor(
                         revlog,
                         old_index,
                         open_files,
                         rev,
                         tombstone,
                     )
                 else:
                     _rewrite_simple(
                         revlog,
                         old_index,
                         open_files,
                         rev,
                         rewritten_entries,
                         tmp_storage,
                     )
     docket.write(transaction=None, stripping=True)
 
 
 def _precompute_rewritten_delta(
     revlog,
     old_index,
     excluded_revs,
     tmp_storage,
 ):
     """Compute new delta for revisions whose delta is based on revision that
     will not survive as is.
 
     Return a mapping: {rev → (new_base, data_start, data_end, compression_mode)}
     """
     dc = deltas.deltacomputer(revlog)
     rewritten_entries = {}
     first_excl_rev = min(excluded_revs)
     with revlog._segmentfile._open_read() as dfh:
         for rev in range(first_excl_rev, len(old_index)):
             if rev in excluded_revs:
                 # this revision will be preserved as is, so we don't need to
                 # consider recomputing a delta.
                 continue
             entry = old_index[rev]
             if entry[ENTRY_DELTA_BASE] not in excluded_revs:
                 continue
             # This is a revision that use the censored revision as the base
             # for its delta. We need a need new deltas
             if entry[ENTRY_DATA_UNCOMPRESSED_LENGTH] == 0:
                 # this revision is empty, we can delta against nullrev
                 rewritten_entries[rev] = (nullrev, 0, 0, COMP_MODE_PLAIN)
             else:
 
                 text = revlog.rawdata(rev, _df=dfh)
                 info = revlogutils.revisioninfo(
                     node=entry[ENTRY_NODE_ID],
                     p1=revlog.node(entry[ENTRY_PARENT_1]),
                     p2=revlog.node(entry[ENTRY_PARENT_2]),
                     btext=[text],
                     textlen=len(text),
                     cachedelta=None,
                     flags=entry[ENTRY_DATA_OFFSET] & 0xFFFF,
                 )
                 d = dc.finddeltainfo(
                     info, dfh, excluded_bases=excluded_revs, target_rev=rev
                 )
                 default_comp = revlog._docket.default_compression_header
                 comp_mode, d = deltas.delta_compression(default_comp, d)
                 # using `tell` is a bit lazy, but we are not here for speed
                 start = tmp_storage.tell()
                 tmp_storage.write(d.data[1])
                 end = tmp_storage.tell()
                 rewritten_entries[rev] = (d.base, start, end, comp_mode)
     return rewritten_entries
 
 
 def _setup_new_files(
     revlog,
     index_cutoff,
     data_cutoff,
     sidedata_cutoff,
 ):
     """
 
     return a context manager to open all the relevant files:
     - old_data_file,
     - old_sidedata_file,
     - new_index_file,
     - new_data_file,
     - new_sidedata_file,
 
     The old_index_file is not here because it is accessed through the
     `old_index` object if the caller function.
     """
     docket = revlog._docket
     old_index_filepath = revlog.opener.join(docket.index_filepath())
     old_data_filepath = revlog.opener.join(docket.data_filepath())
     old_sidedata_filepath = revlog.opener.join(docket.sidedata_filepath())
 
     new_index_filepath = revlog.opener.join(docket.new_index_file())
     new_data_filepath = revlog.opener.join(docket.new_data_file())
     new_sidedata_filepath = revlog.opener.join(docket.new_sidedata_file())
 
     util.copyfile(old_index_filepath, new_index_filepath, nb_bytes=index_cutoff)
     util.copyfile(old_data_filepath, new_data_filepath, nb_bytes=data_cutoff)
     util.copyfile(
         old_sidedata_filepath,
         new_sidedata_filepath,
         nb_bytes=sidedata_cutoff,
     )
     revlog.opener.register_file(docket.index_filepath())
     revlog.opener.register_file(docket.data_filepath())
     revlog.opener.register_file(docket.sidedata_filepath())
 
     docket.index_end = index_cutoff
     docket.data_end = data_cutoff
     docket.sidedata_end = sidedata_cutoff
 
     # reload the revlog internal information
     revlog.clearcaches()
     revlog._loadindex(docket=docket)
 
     @contextlib.contextmanager
     def all_files_opener():
         # hide opening in an helper function to please check-code, black
         # and various python version at the same time
         with open(old_data_filepath, 'rb') as old_data_file:
             with open(old_sidedata_filepath, 'rb') as old_sidedata_file:
                 with open(new_index_filepath, 'r+b') as new_index_file:
                     with open(new_data_filepath, 'r+b') as new_data_file:
                         with open(
                             new_sidedata_filepath, 'r+b'
                         ) as new_sidedata_file:
                             new_index_file.seek(0, os.SEEK_END)
                             assert new_index_file.tell() == index_cutoff
                             new_data_file.seek(0, os.SEEK_END)
                             assert new_data_file.tell() == data_cutoff
                             new_sidedata_file.seek(0, os.SEEK_END)
                             assert new_sidedata_file.tell() == sidedata_cutoff
                             yield (
                                 old_data_file,
                                 old_sidedata_file,
                                 new_index_file,
                                 new_data_file,
                                 new_sidedata_file,
                             )
 
     return all_files_opener
 
 
 def _rewrite_simple(
     revlog,
     old_index,
     all_files,
     rev,
     rewritten_entries,
     tmp_storage,
 ):
     """append a normal revision to the index after the rewritten one(s)"""
     (
         old_data_file,
         old_sidedata_file,
         new_index_file,
         new_data_file,
         new_sidedata_file,
     ) = all_files
     entry = old_index[rev]
     flags = entry[ENTRY_DATA_OFFSET] & 0xFFFF
     old_data_offset = entry[ENTRY_DATA_OFFSET] >> 16
 
     if rev not in rewritten_entries:
         old_data_file.seek(old_data_offset)
         new_data_size = entry[ENTRY_DATA_COMPRESSED_LENGTH]
         new_data = old_data_file.read(new_data_size)
         data_delta_base = entry[ENTRY_DELTA_BASE]
         d_comp_mode = entry[ENTRY_DATA_COMPRESSION_MODE]
     else:
         (
             data_delta_base,
             start,
             end,
             d_comp_mode,
         ) = rewritten_entries[rev]
         new_data_size = end - start
         tmp_storage.seek(start)
         new_data = tmp_storage.read(new_data_size)
 
     # It might be faster to group continuous read/write operation,
     # however, this is censor, an operation that is not focussed
     # around stellar performance. So I have not written this
     # optimisation yet.
     new_data_offset = new_data_file.tell()
     new_data_file.write(new_data)
 
     sidedata_size = entry[ENTRY_SIDEDATA_COMPRESSED_LENGTH]
     new_sidedata_offset = new_sidedata_file.tell()
     if 0 < sidedata_size:
         old_sidedata_offset = entry[ENTRY_SIDEDATA_OFFSET]
         old_sidedata_file.seek(old_sidedata_offset)
         new_sidedata = old_sidedata_file.read(sidedata_size)
         new_sidedata_file.write(new_sidedata)
 
     data_uncompressed_length = entry[ENTRY_DATA_UNCOMPRESSED_LENGTH]
     sd_com_mode = entry[ENTRY_SIDEDATA_COMPRESSION_MODE]
     assert data_delta_base <= rev, (data_delta_base, rev)
 
     new_entry = revlogutils.entry(
         flags=flags,
         data_offset=new_data_offset,
         data_compressed_length=new_data_size,
         data_uncompressed_length=data_uncompressed_length,
         data_delta_base=data_delta_base,
         link_rev=entry[ENTRY_LINK_REV],
         parent_rev_1=entry[ENTRY_PARENT_1],
         parent_rev_2=entry[ENTRY_PARENT_2],
         node_id=entry[ENTRY_NODE_ID],
         sidedata_offset=new_sidedata_offset,
         sidedata_compressed_length=sidedata_size,
         data_compression_mode=d_comp_mode,
         sidedata_compression_mode=sd_com_mode,
     )
     revlog.index.append(new_entry)
     entry_bin = revlog.index.entry_binary(rev)
     new_index_file.write(entry_bin)
 
     revlog._docket.index_end = new_index_file.tell()
     revlog._docket.data_end = new_data_file.tell()
     revlog._docket.sidedata_end = new_sidedata_file.tell()
 
 
 def _rewrite_censor(
     revlog,
     old_index,
     all_files,
     rev,
     tombstone,
 ):
     """rewrite and append a censored revision"""
     (
         old_data_file,
         old_sidedata_file,
         new_index_file,
         new_data_file,
         new_sidedata_file,
     ) = all_files
     entry = old_index[rev]
 
     # XXX consider trying the default compression too
     new_data_size = len(tombstone)
     new_data_offset = new_data_file.tell()
     new_data_file.write(tombstone)
 
     # we are not adding any sidedata as they might leak info about the censored version
 
     link_rev = entry[ENTRY_LINK_REV]
 
     p1 = entry[ENTRY_PARENT_1]
     p2 = entry[ENTRY_PARENT_2]
 
     new_entry = revlogutils.entry(
         flags=constants.REVIDX_ISCENSORED,
         data_offset=new_data_offset,
         data_compressed_length=new_data_size,
         data_uncompressed_length=new_data_size,
         data_delta_base=rev,
         link_rev=link_rev,
         parent_rev_1=p1,
         parent_rev_2=p2,
         node_id=entry[ENTRY_NODE_ID],
         sidedata_offset=0,
         sidedata_compressed_length=0,
         data_compression_mode=COMP_MODE_PLAIN,
         sidedata_compression_mode=COMP_MODE_PLAIN,
     )
     revlog.index.append(new_entry)
     entry_bin = revlog.index.entry_binary(rev)
     new_index_file.write(entry_bin)
     revlog._docket.index_end = new_index_file.tell()
     revlog._docket.data_end = new_data_file.tell()
 
 
 def _get_filename_from_filelog_index(path):
     # Drop the extension and the `data/` prefix
     path_part = path.rsplit(b'.', 1)[0].split(b'/', 1)
     if len(path_part) < 2:
         msg = _(b"cannot recognize filelog from filename: '%s'")
         msg %= path
         raise error.Abort(msg)
 
     return path_part[1]
 
 
 def _filelog_from_filename(repo, path):
     """Returns the filelog for the given `path`. Stolen from `engine.py`"""
 
     from .. import filelog  # avoid cycle
 
     fl = filelog.filelog(repo.svfs, path)
     return fl
 
 
 def _write_swapped_parents(repo, rl, rev, offset, fp):
     """Swaps p1 and p2 and overwrites the revlog entry for `rev` in `fp`"""
     from ..pure import parsers  # avoid cycle
 
     if repo._currentlock(repo._lockref) is None:
         # Let's be paranoid about it
         msg = "repo needs to be locked to rewrite parents"
         raise error.ProgrammingError(msg)
 
     index_format = parsers.IndexObject.index_format
     entry = rl.index[rev]
     new_entry = list(entry)
     new_entry[5], new_entry[6] = entry[6], entry[5]
     packed = index_format.pack(*new_entry[:8])
     fp.seek(offset)
     fp.write(packed)
 
 
 def _reorder_filelog_parents(repo, fl, to_fix):
     """
     Swaps p1 and p2 for all `to_fix` revisions of filelog `fl` and writes the
     new version to disk, overwriting the old one with a rename.
     """
     from ..pure import parsers  # avoid cycle
 
     ui = repo.ui
     assert len(to_fix) > 0
     rl = fl._revlog
     if rl._format_version != constants.REVLOGV1:
         msg = "expected version 1 revlog, got version '%d'" % rl._format_version
         raise error.ProgrammingError(msg)
 
     index_file = rl._indexfile
     new_file_path = index_file + b'.tmp-parents-fix'
     repaired_msg = _(b"repaired revision %d of 'filelog %s'\n")
 
     with ui.uninterruptible():
         try:
             util.copyfile(
                 rl.opener.join(index_file),
                 rl.opener.join(new_file_path),
                 checkambig=rl._checkambig,
             )
 
             with rl.opener(new_file_path, mode=b"r+") as fp:
                 if rl._inline:
                     index = parsers.InlinedIndexObject(fp.read())
                     for rev in fl.revs():
                         if rev in to_fix:
                             offset = index._calculate_index(rev)
                             _write_swapped_parents(repo, rl, rev, offset, fp)
                             ui.write(repaired_msg % (rev, index_file))
                 else:
                     index_format = parsers.IndexObject.index_format
                     for rev in to_fix:
                         offset = rev * index_format.size
                         _write_swapped_parents(repo, rl, rev, offset, fp)
                         ui.write(repaired_msg % (rev, index_file))
 
             rl.opener.rename(new_file_path, index_file)
             rl.clearcaches()
             rl._loadindex()
         finally:
             util.tryunlink(new_file_path)
 
 
 def _is_revision_affected(fl, filerev, metadata_cache=None):
     full_text = lambda: fl._revlog.rawdata(filerev)
     parent_revs = lambda: fl._revlog.parentrevs(filerev)
     return _is_revision_affected_inner(
         full_text, parent_revs, filerev, metadata_cache
     )
 
 
 def _is_revision_affected_inner(
     full_text,
     parents_revs,
     filerev,
     metadata_cache=None,
 ):
     """Mercurial currently (5.9rc0) uses `p1 == nullrev and p2 != nullrev` as a
     special meaning compared to the reverse in the context of filelog-based
     copytracing. issue6528 exists because new code assumed that parent ordering
     didn't matter, so this detects if the revision contains metadata (since
     it's only used for filelog-based copytracing) and its parents are in the
     "wrong" order."""
     try:
         raw_text = full_text()
     except error.CensoredNodeError:
         # We don't care about censored nodes as they never carry metadata
         return False
 
     # raw text can be a `memoryview`, which doesn't implement `startswith`
     has_meta = bytes(raw_text[:2]) == b'\x01\n'
     if metadata_cache is not None:
         metadata_cache[filerev] = has_meta
     if has_meta:
         (p1, p2) = parents_revs()
         if p1 != nullrev and p2 == nullrev:
             return True
     return False
 
 
 def _is_revision_affected_fast(repo, fl, filerev, metadata_cache):
     rl = fl._revlog
     is_censored = lambda: rl.iscensored(filerev)
     delta_base = lambda: rl.deltaparent(filerev)
     delta = lambda: rl._chunk(filerev)
     full_text = lambda: rl.rawdata(filerev)
     parent_revs = lambda: rl.parentrevs(filerev)
     return _is_revision_affected_fast_inner(
         is_censored,
         delta_base,
         delta,
         full_text,
         parent_revs,
         filerev,
         metadata_cache,
     )
 
 
 def _is_revision_affected_fast_inner(
     is_censored,
     delta_base,
     delta,
     full_text,
     parent_revs,
     filerev,
     metadata_cache,
 ):
     """Optimization fast-path for `_is_revision_affected`.
 
     `metadata_cache` is a dict of `{rev: has_metadata}` which allows any
     revision to check if its base has metadata, saving computation of the full
     text, instead looking at the current delta.
 
     This optimization only works if the revisions are looked at in order."""
 
     if is_censored():
         # Censored revisions don't contain metadata, so they cannot be affected
         metadata_cache[filerev] = False
         return False
 
     p1, p2 = parent_revs()
     if p1 == nullrev or p2 != nullrev:
         return False
 
     delta_parent = delta_base()
     parent_has_metadata = metadata_cache.get(delta_parent)
     if parent_has_metadata is None:
         return _is_revision_affected_inner(
             full_text,
             parent_revs,
             filerev,
             metadata_cache,
         )
 
     chunk = delta()
     if not len(chunk):
         # No diff for this revision
         return parent_has_metadata
 
     header_length = 12
     if len(chunk) < header_length:
         raise error.Abort(_(b"patch cannot be decoded"))
 
     start, _end, _length = struct.unpack(b">lll", chunk[:header_length])
 
     if start < 2:  # len(b'\x01\n') == 2
         # This delta does *something* to the metadata marker (if any).
         # Check it the slow way
         is_affected = _is_revision_affected_inner(
             full_text,
             parent_revs,
             filerev,
             metadata_cache,
         )
         return is_affected
 
     # The diff did not remove or add the metadata header, it's then in the same
     # situation as its parent
     metadata_cache[filerev] = parent_has_metadata
     return parent_has_metadata
 
 
 def _from_report(ui, repo, context, from_report, dry_run):
     """
     Fix the revisions given in the `from_report` file, but still checks if the
     revisions are indeed affected to prevent an unfortunate cyclic situation
     where we'd swap well-ordered parents again.
 
     See the doc for `debug_fix_issue6528` for the format documentation.
     """
     ui.write(_(b"loading report file '%s'\n") % from_report)
 
     with context(), open(from_report, mode='rb') as f:
         for line in f.read().split(b'\n'):
             if not line:
                 continue
             filenodes, filename = line.split(b' ', 1)
             fl = _filelog_from_filename(repo, filename)
             to_fix = set(
                 fl.rev(binascii.unhexlify(n)) for n in filenodes.split(b',')
             )
             excluded = set()
 
             for filerev in to_fix:
                 if _is_revision_affected(fl, filerev):
                     msg = b"found affected revision %d for filelog '%s'\n"
                     ui.warn(msg % (filerev, filename))
                 else:
                     msg = _(b"revision %s of file '%s' is not affected\n")
                     msg %= (binascii.hexlify(fl.node(filerev)), filename)
                     ui.warn(msg)
                     excluded.add(filerev)
 
             to_fix = to_fix - excluded
             if not to_fix:
                 msg = _(b"no affected revisions were found for '%s'\n")
                 ui.write(msg % filename)
                 continue
             if not dry_run:
                 _reorder_filelog_parents(repo, fl, sorted(to_fix))
 
 
 def filter_delta_issue6528(revlog, deltas_iter):
     """filter incomind deltas to repaire issue 6528 on the fly"""
     metadata_cache = {}
 
     deltacomputer = deltas.deltacomputer(revlog)
 
     for rev, d in enumerate(deltas_iter, len(revlog)):
         (
             node,
             p1_node,
             p2_node,
             linknode,
             deltabase,
             delta,
             flags,
             sidedata,
         ) = d
 
         if not revlog.index.has_node(deltabase):
             raise error.LookupError(
                 deltabase, revlog.radix, _(b'unknown parent')
             )
         base_rev = revlog.rev(deltabase)
         if not revlog.index.has_node(p1_node):
             raise error.LookupError(p1_node, revlog.radix, _(b'unknown parent'))
         p1_rev = revlog.rev(p1_node)
         if not revlog.index.has_node(p2_node):
             raise error.LookupError(p2_node, revlog.radix, _(b'unknown parent'))
         p2_rev = revlog.rev(p2_node)
 
         is_censored = lambda: bool(flags & REVIDX_ISCENSORED)
         delta_base = lambda: revlog.rev(delta_base)
         delta_base = lambda: base_rev
         parent_revs = lambda: (p1_rev, p2_rev)
 
         def full_text():
             # note: being able to reuse the full text computation in the
             # underlying addrevision would be useful however this is a bit too
             # intrusive the for the "quick" issue6528 we are writing before the
             # 5.8 release
             textlen = mdiff.patchedsize(revlog.size(base_rev), delta)
 
             revinfo = revlogutils.revisioninfo(
                 node,
                 p1_node,
                 p2_node,
                 [None],
                 textlen,
                 (base_rev, delta),
                 flags,
             )
             # cached by the global "writing" context
             assert revlog._writinghandles is not None
             if revlog._inline:
                 fh = revlog._writinghandles[0]
             else:
                 fh = revlog._writinghandles[1]
             return deltacomputer.buildtext(revinfo, fh)
 
         is_affected = _is_revision_affected_fast_inner(
             is_censored,
             delta_base,
             lambda: delta,
             full_text,
             parent_revs,
             rev,
             metadata_cache,
         )
         if is_affected:
             d = (
                 node,
                 p2_node,
                 p1_node,
                 linknode,
                 deltabase,
                 delta,
                 flags,
                 sidedata,
             )
         yield d
 
 
 def repair_issue6528(
     ui, repo, dry_run=False, to_report=None, from_report=None, paranoid=False
 ):
     from .. import store  # avoid cycle
 
     @contextlib.contextmanager
     def context():
         if dry_run or to_report:  # No need for locking
             yield
         else:
             with repo.wlock(), repo.lock():
                 yield
 
     if from_report:
         return _from_report(ui, repo, context, from_report, dry_run)
 
     report_entries = []
 
     with context():
         files = list(
-            (file_type, path)
-            for (file_type, path, _s) in repo.store.datafiles()
-            if path.endswith(b'.i') and file_type & store.FILEFLAGS_FILELOG
+            entry
+            for entry in repo.store.datafiles()
+            if (
+                entry.unencoded_path.endswith(b'.i')
+                and entry.is_revlog
+                and entry.revlog_type == store.FILEFLAGS_FILELOG
+            )
         )
 
         progress = ui.makeprogress(
             _(b"looking for affected revisions"),
             unit=_(b"filelogs"),
             total=len(files),
         )
         found_nothing = True
 
-        for file_type, path in files:
+        for entry in files:
+            path = entry.unencoded_path
             progress.increment()
             filename = _get_filename_from_filelog_index(path)
             fl = _filelog_from_filename(repo, filename)
 
             # Set of filerevs (or hex filenodes if `to_report`) that need fixing
             to_fix = set()
             metadata_cache = {}
             for filerev in fl.revs():
                 affected = _is_revision_affected_fast(
                     repo, fl, filerev, metadata_cache
                 )
                 if paranoid:
                     slow = _is_revision_affected(fl, filerev)
                     if slow != affected:
                         msg = _(b"paranoid check failed for '%s' at node %s")
                         node = binascii.hexlify(fl.node(filerev))
                         raise error.Abort(msg % (filename, node))
                 if affected:
                     msg = b"found affected revision %d for filelog '%s'\n"
                     ui.warn(msg % (filerev, path))
                     found_nothing = False
                     if not dry_run:
                         if to_report:
                             to_fix.add(binascii.hexlify(fl.node(filerev)))
                         else:
                             to_fix.add(filerev)
 
             if to_fix:
                 to_fix = sorted(to_fix)
                 if to_report:
                     report_entries.append((filename, to_fix))
                 else:
                     _reorder_filelog_parents(repo, fl, to_fix)
 
         if found_nothing:
             ui.write(_(b"no affected revisions were found\n"))
 
         if to_report and report_entries:
             with open(to_report, mode="wb") as f:
                 for path, to_fix in report_entries:
                     f.write(b"%s %s\n" % (b",".join(to_fix), path))
 
         progress.complete()

mercurial/store.py

@@ -1,855 +1,901 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 functools
 import os
 import re
 import stat
+from typing import Generator
 
 from .i18n import _
 from .pycompat import getattr
+from .thirdparty import attr
 from .node import hex
 from . import (
     changelog,
     error,
     manifest,
     policy,
     pycompat,
     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 _matchtrackedpath(path, 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
     path = decodedir(path)
     if path.startswith(b'data/'):
         return matcher(path[len(b'data/') : -len(b'.i')])
     elif path.startswith(b'meta/'):
         return matcher.visitdir(path[len(b'meta/') : -len(b'/00manifest.i')])
 
     raise error.ProgrammingError(b"cannot decode path %s" % path)
 
 
 # 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_MAIN_EXT = (b'.i',)
 REVLOG_FILES_OTHER_EXT = (
     b'.idx',
     b'.d',
     b'.dat',
     b'.n',
     b'.nd',
     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 None
     return revlog_type(f)
 
 
 def revlog_type(f):
     # XXX we need to filter `undo.` created by the transaction here, however
     # being naive about it also filter revlog for `undo.*` files, leading to
     # issue6542. So we no longer use EXCLUDED.
     if f.endswith(REVLOG_FILES_MAIN_EXT):
         return FILEFLAGS_REVLOG_MAIN
     elif f.endswith(REVLOG_FILES_OTHER_EXT):
         t = FILETYPE_FILELOG_OTHER
         if f.endswith(REVLOG_FILES_VOLATILE_EXT):
             t |= FILEFLAGS_VOLATILE
         return t
     return None
 
 
 # the file is part of changelog data
 FILEFLAGS_CHANGELOG = 1 << 13
 # the file is part of manifest data
 FILEFLAGS_MANIFESTLOG = 1 << 12
 # the file is part of filelog data
 FILEFLAGS_FILELOG = 1 << 11
 # file that are not directly part of a revlog
 FILEFLAGS_OTHER = 1 << 10
 
 # the main entry point for a revlog
 FILEFLAGS_REVLOG_MAIN = 1 << 1
 # a secondary file for a revlog
 FILEFLAGS_REVLOG_OTHER = 1 << 0
 
 # files that are "volatile" and might change between listing and streaming
 FILEFLAGS_VOLATILE = 1 << 20
 
 FILETYPE_CHANGELOG_MAIN = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_CHANGELOG_OTHER = FILEFLAGS_CHANGELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_MANIFESTLOG_MAIN = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_MANIFESTLOG_OTHER = FILEFLAGS_MANIFESTLOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_FILELOG_MAIN = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_MAIN
 FILETYPE_FILELOG_OTHER = FILEFLAGS_FILELOG | FILEFLAGS_REVLOG_OTHER
 FILETYPE_OTHER = FILEFLAGS_OTHER
 
 
+@attr.s(slots=True)
+class StoreEntry:
+    """An entry in the store
+
+    This is returned by `store.walk` and represent some data in the store."""
+
+    unencoded_path = attr.ib()
+    is_revlog = attr.ib(default=False)
+    revlog_type = attr.ib(default=None)
+    is_revlog_main = attr.ib(default=None)
+    is_volatile = attr.ib(default=False)
+    file_size = attr.ib(default=None)
+
+
 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):
         '''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
                     rl_type = is_revlog(f, kind, st)
                     if rl_type is not None:
                         n = util.pconvert(fp[striplen:])
                         l.append((rl_type, 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):
         rootstore = manifest.manifestrevlog(repo.nodeconstants, self.vfs)
         return manifest.manifestlog(self.vfs, repo, rootstore, storenarrowmatch)
 
-    def datafiles(self, matcher=None, undecodable=None):
+    def datafiles(
+        self, matcher=None, undecodable=None
+    ) -> Generator[StoreEntry, 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."""
         files = self._walk(b'data', True) + self._walk(b'meta', True)
         for (t, u, s) in files:
             if t is not None:
-                yield (FILEFLAGS_FILELOG | t, u, s)
+                yield StoreEntry(
+                    unencoded_path=u,
+                    is_revlog=True,
+                    revlog_type=FILEFLAGS_FILELOG,
+                    is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
+                    is_volatile=bool(t & FILEFLAGS_VOLATILE),
+                    file_size=s,
+                )
 
-    def topfiles(self):
+    def topfiles(self) -> Generator[StoreEntry, None, None]:
         # yield manifest before changelog
         files = reversed(self._walk(b'', False))
         for (t, u, s) in files:
             if u.startswith(b'00changelog'):
-                yield (FILEFLAGS_CHANGELOG | t, u, s)
+                revlog_type = FILEFLAGS_CHANGELOG
             elif u.startswith(b'00manifest'):
-                yield (FILEFLAGS_MANIFESTLOG | t, u, s)
+                revlog_type = FILEFLAGS_MANIFESTLOG
             else:
-                yield (FILETYPE_OTHER | t, u, s)
+                revlog_type = None
+            yield StoreEntry(
+                unencoded_path=u,
+                is_revlog=revlog_type is not None,
+                revlog_type=revlog_type,
+                is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
+                is_volatile=bool(t & FILEFLAGS_VOLATILE),
+                file_size=s,
+            )
 
-    def walk(self, matcher=None):
+    def walk(self, matcher=None) -> Generator[StoreEntry, None, None]:
         """return files related to data storage (ie: revlogs)
 
         yields (file_type, unencoded, size)
 
         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.datafiles(matcher):
             yield x
         for x in self.topfiles():
             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
 
     # note: topfiles would also need a decode phase. It is just that in
     # practice we do not have any file outside of `data/` that needs encoding.
     # However that might change so we should probably add a test and encoding
     # decoding for it too. see issue6548
 
-    def datafiles(self, matcher=None, undecodable=None):
-        for t, f1, size in super(encodedstore, self).datafiles():
+    def datafiles(
+        self, matcher=None, undecodable=None
+    ) -> Generator[StoreEntry, None, None]:
+        for entry in super(encodedstore, self).datafiles():
             try:
+                f1 = entry.unencoded_path
                 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
             if not _matchtrackedpath(f2, matcher):
                 continue
-            yield t, f2, size
+            entry.unencoded_path = f2
+            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 revlog_type(path) is not None
         ):
             # do not trigger a fncache load when adding a file that already is
             # known to exist.
             notload = self.fncache.entries is None and self.vfs.exists(encoded)
             if notload and b'r+' in mode and not self.vfs.stat(encoded).st_size:
                 # when appending to an existing file, 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.
                 notload = False
             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 datafiles(self, matcher=None, undecodable=None):
+    def datafiles(
+        self, matcher=None, undecodable=None
+    ) -> Generator[StoreEntry, None, None]:
         for f in sorted(self.fncache):
             if not _matchtrackedpath(f, matcher):
                 continue
             ef = self.encode(f)
             t = revlog_type(f)
             if t is None:
                 # Note: this should not be in the fncache then…
                 #
                 # However the fncache might contains such file added by
                 # previous version of Mercurial.
                 continue
             t |= FILEFLAGS_FILELOG
             try:
-                yield t, f, self.getsize(ef)
+                yield StoreEntry(
+                    unencoded_path=f,
+                    is_revlog=True,
+                    revlog_type=FILEFLAGS_FILELOG,
+                    is_revlog_main=bool(t & FILEFLAGS_REVLOG_MAIN),
+                    is_volatile=bool(t & FILEFLAGS_VOLATILE),
+                    file_size=self.getsize(ef),
+                )
             except FileNotFoundError:
                 pass
 
     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/streamclone.py

@@ -1,935 +1,937 b''
 # streamclone.py - producing and consuming streaming repository data
 #
 # Copyright 2015 Gregory Szorc <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import contextlib
 import os
 import struct
 
 from .i18n import _
 from .pycompat import open
 from .interfaces import repository
 from . import (
     bookmarks,
     cacheutil,
     error,
     narrowspec,
     phases,
     pycompat,
     requirements as requirementsmod,
     scmutil,
     store,
     transaction,
     util,
 )
 from .revlogutils import (
     nodemap,
 )
 
 
 def new_stream_clone_requirements(default_requirements, streamed_requirements):
     """determine the final set of requirement for a new stream clone
 
     this method combine the "default" requirements that a new repository would
     use with the constaint we get from the stream clone content. We keep local
     configuration choice when possible.
     """
     requirements = set(default_requirements)
     requirements -= requirementsmod.STREAM_FIXED_REQUIREMENTS
     requirements.update(streamed_requirements)
     return requirements
 
 
 def streamed_requirements(repo):
     """the set of requirement the new clone will have to support
 
     This is used for advertising the stream options and to generate the actual
     stream content."""
     requiredformats = (
         repo.requirements & requirementsmod.STREAM_FIXED_REQUIREMENTS
     )
     return requiredformats
 
 
 def canperformstreamclone(pullop, bundle2=False):
     """Whether it is possible to perform a streaming clone as part of pull.
 
     ``bundle2`` will cause the function to consider stream clone through
     bundle2 and only through bundle2.
 
     Returns a tuple of (supported, requirements). ``supported`` is True if
     streaming clone is supported and False otherwise. ``requirements`` is
     a set of repo requirements from the remote, or ``None`` if stream clone
     isn't supported.
     """
     repo = pullop.repo
     remote = pullop.remote
 
     bundle2supported = False
     if pullop.canusebundle2:
         if b'v2' in pullop.remotebundle2caps.get(b'stream', []):
             bundle2supported = True
         # else
         # Server doesn't support bundle2 stream clone or doesn't support
         # the versions we support. Fall back and possibly allow legacy.
 
     # Ensures legacy code path uses available bundle2.
     if bundle2supported and not bundle2:
         return False, None
     # Ensures bundle2 doesn't try to do a stream clone if it isn't supported.
     elif bundle2 and not bundle2supported:
         return False, None
 
     # Streaming clone only works on empty repositories.
     if len(repo):
         return False, None
 
     # Streaming clone only works if all data is being requested.
     if pullop.heads:
         return False, None
 
     streamrequested = pullop.streamclonerequested
 
     # If we don't have a preference, let the server decide for us. This
     # likely only comes into play in LANs.
     if streamrequested is None:
         # The server can advertise whether to prefer streaming clone.
         streamrequested = remote.capable(b'stream-preferred')
 
     if not streamrequested:
         return False, None
 
     # In order for stream clone to work, the client has to support all the
     # requirements advertised by the server.
     #
     # The server advertises its requirements via the "stream" and "streamreqs"
     # capability. "stream" (a value-less capability) is advertised if and only
     # if the only requirement is "revlogv1." Else, the "streamreqs" capability
     # is advertised and contains a comma-delimited list of requirements.
     requirements = set()
     if remote.capable(b'stream'):
         requirements.add(requirementsmod.REVLOGV1_REQUIREMENT)
     else:
         streamreqs = remote.capable(b'streamreqs')
         # This is weird and shouldn't happen with modern servers.
         if not streamreqs:
             pullop.repo.ui.warn(
                 _(
                     b'warning: stream clone requested but server has them '
                     b'disabled\n'
                 )
             )
             return False, None
 
         streamreqs = set(streamreqs.split(b','))
         # Server requires something we don't support. Bail.
         missingreqs = streamreqs - repo.supported
         if missingreqs:
             pullop.repo.ui.warn(
                 _(
                     b'warning: stream clone requested but client is missing '
                     b'requirements: %s\n'
                 )
                 % b', '.join(sorted(missingreqs))
             )
             pullop.repo.ui.warn(
                 _(
                     b'(see https://www.mercurial-scm.org/wiki/MissingRequirement '
                     b'for more information)\n'
                 )
             )
             return False, None
         requirements = streamreqs
 
     return True, requirements
 
 
 def maybeperformlegacystreamclone(pullop):
     """Possibly perform a legacy stream clone operation.
 
     Legacy stream clones are performed as part of pull but before all other
     operations.
 
     A legacy stream clone will not be performed if a bundle2 stream clone is
     supported.
     """
     from . import localrepo
 
     supported, requirements = canperformstreamclone(pullop)
 
     if not supported:
         return
 
     repo = pullop.repo
     remote = pullop.remote
 
     # Save remote branchmap. We will use it later to speed up branchcache
     # creation.
     rbranchmap = None
     if remote.capable(b'branchmap'):
         with remote.commandexecutor() as e:
             rbranchmap = e.callcommand(b'branchmap', {}).result()
 
     repo.ui.status(_(b'streaming all changes\n'))
 
     with remote.commandexecutor() as e:
         fp = e.callcommand(b'stream_out', {}).result()
 
     # TODO strictly speaking, this code should all be inside the context
     # manager because the context manager is supposed to ensure all wire state
     # is flushed when exiting. But the legacy peers don't do this, so it
     # doesn't matter.
     l = fp.readline()
     try:
         resp = int(l)
     except ValueError:
         raise error.ResponseError(
             _(b'unexpected response from remote server:'), l
         )
     if resp == 1:
         raise error.Abort(_(b'operation forbidden by server'))
     elif resp == 2:
         raise error.Abort(_(b'locking the remote repository failed'))
     elif resp != 0:
         raise error.Abort(_(b'the server sent an unknown error code'))
 
     l = fp.readline()
     try:
         filecount, bytecount = map(int, l.split(b' ', 1))
     except (ValueError, TypeError):
         raise error.ResponseError(
             _(b'unexpected response from remote server:'), l
         )
 
     with repo.lock():
         consumev1(repo, fp, filecount, bytecount)
         repo.requirements = new_stream_clone_requirements(
             repo.requirements,
             requirements,
         )
         repo.svfs.options = localrepo.resolvestorevfsoptions(
             repo.ui, repo.requirements, repo.features
         )
         scmutil.writereporequirements(repo)
         nodemap.post_stream_cleanup(repo)
 
         if rbranchmap:
             repo._branchcaches.replace(repo, rbranchmap)
 
         repo.invalidate()
 
 
 def allowservergeneration(repo):
     """Whether streaming clones are allowed from the server."""
     if repository.REPO_FEATURE_STREAM_CLONE not in repo.features:
         return False
 
     if not repo.ui.configbool(b'server', b'uncompressed', untrusted=True):
         return False
 
     # The way stream clone works makes it impossible to hide secret changesets.
     # So don't allow this by default.
     secret = phases.hassecret(repo)
     if secret:
         return repo.ui.configbool(b'server', b'uncompressedallowsecret')
 
     return True
 
 
 # This is it's own function so extensions can override it.
 def _walkstreamfiles(repo, matcher=None):
     return repo.store.walk(matcher)
 
 
 def generatev1(repo):
     """Emit content for version 1 of a streaming clone.
 
     This returns a 3-tuple of (file count, byte size, data iterator).
 
     The data iterator consists of N entries for each file being transferred.
     Each file entry starts as a line with the file name and integer size
     delimited by a null byte.
 
     The raw file data follows. Following the raw file data is the next file
     entry, or EOF.
 
     When used on the wire protocol, an additional line indicating protocol
     success will be prepended to the stream. This function is not responsible
     for adding it.
 
     This function will obtain a repository lock to ensure a consistent view of
     the store is captured. It therefore may raise LockError.
     """
     entries = []
     total_bytes = 0
     # Get consistent snapshot of repo, lock during scan.
     with repo.lock():
         repo.ui.debug(b'scanning\n')
-        for file_type, name, size in _walkstreamfiles(repo):
-            if size:
-                entries.append((name, size))
-                total_bytes += size
+        for entry in _walkstreamfiles(repo):
+            if entry.file_size:
+                entries.append((entry.unencoded_path, entry.file_size))
+                total_bytes += entry.file_size
         _test_sync_point_walk_1(repo)
     _test_sync_point_walk_2(repo)
 
     repo.ui.debug(
         b'%d files, %d bytes to transfer\n' % (len(entries), total_bytes)
     )
 
     svfs = repo.svfs
     debugflag = repo.ui.debugflag
 
     def emitrevlogdata():
         for name, size in entries:
             if debugflag:
                 repo.ui.debug(b'sending %s (%d bytes)\n' % (name, size))
             # partially encode name over the wire for backwards compat
             yield b'%s\0%d\n' % (store.encodedir(name), size)
             # auditing at this stage is both pointless (paths are already
             # trusted by the local repo) and expensive
             with svfs(name, b'rb', auditpath=False) as fp:
                 if size <= 65536:
                     yield fp.read(size)
                 else:
                     for chunk in util.filechunkiter(fp, limit=size):
                         yield chunk
 
     return len(entries), total_bytes, emitrevlogdata()
 
 
 def generatev1wireproto(repo):
     """Emit content for version 1 of streaming clone suitable for the wire.
 
     This is the data output from ``generatev1()`` with 2 header lines. The
     first line indicates overall success. The 2nd contains the file count and
     byte size of payload.
 
     The success line contains "0" for success, "1" for stream generation not
     allowed, and "2" for error locking the repository (possibly indicating
     a permissions error for the server process).
     """
     if not allowservergeneration(repo):
         yield b'1\n'
         return
 
     try:
         filecount, bytecount, it = generatev1(repo)
     except error.LockError:
         yield b'2\n'
         return
 
     # Indicates successful response.
     yield b'0\n'
     yield b'%d %d\n' % (filecount, bytecount)
     for chunk in it:
         yield chunk
 
 
 def generatebundlev1(repo, compression=b'UN'):
     """Emit content for version 1 of a stream clone bundle.
 
     The first 4 bytes of the output ("HGS1") denote this as stream clone
     bundle version 1.
 
     The next 2 bytes indicate the compression type. Only "UN" is currently
     supported.
 
     The next 16 bytes are two 64-bit big endian unsigned integers indicating
     file count and byte count, respectively.
 
     The next 2 bytes is a 16-bit big endian unsigned short declaring the length
     of the requirements string, including a trailing \0. The following N bytes
     are the requirements string, which is ASCII containing a comma-delimited
     list of repo requirements that are needed to support the data.
 
     The remaining content is the output of ``generatev1()`` (which may be
     compressed in the future).
 
     Returns a tuple of (requirements, data generator).
     """
     if compression != b'UN':
         raise ValueError(b'we do not support the compression argument yet')
 
     requirements = streamed_requirements(repo)
     requires = b','.join(sorted(requirements))
 
     def gen():
         yield b'HGS1'
         yield compression
 
         filecount, bytecount, it = generatev1(repo)
         repo.ui.status(
             _(b'writing %d bytes for %d files\n') % (bytecount, filecount)
         )
 
         yield struct.pack(b'>QQ', filecount, bytecount)
         yield struct.pack(b'>H', len(requires) + 1)
         yield requires + b'\0'
 
         # This is where we'll add compression in the future.
         assert compression == b'UN'
 
         progress = repo.ui.makeprogress(
             _(b'bundle'), total=bytecount, unit=_(b'bytes')
         )
         progress.update(0)
 
         for chunk in it:
             progress.increment(step=len(chunk))
             yield chunk
 
         progress.complete()
 
     return requirements, gen()
 
 
 def consumev1(repo, fp, filecount, bytecount):
     """Apply the contents from version 1 of a streaming clone file handle.
 
     This takes the output from "stream_out" and applies it to the specified
     repository.
 
     Like "stream_out," the status line added by the wire protocol is not
     handled by this function.
     """
     with repo.lock():
         repo.ui.status(
             _(b'%d files to transfer, %s of data\n')
             % (filecount, util.bytecount(bytecount))
         )
         progress = repo.ui.makeprogress(
             _(b'clone'), total=bytecount, unit=_(b'bytes')
         )
         progress.update(0)
         start = util.timer()
 
         # TODO: get rid of (potential) inconsistency
         #
         # If transaction is started and any @filecache property is
         # changed at this point, it causes inconsistency between
         # in-memory cached property and streamclone-ed file on the
         # disk. Nested transaction prevents transaction scope "clone"
         # below from writing in-memory changes out at the end of it,
         # even though in-memory changes are discarded at the end of it
         # regardless of transaction nesting.
         #
         # But transaction nesting can't be simply prohibited, because
         # nesting occurs also in ordinary case (e.g. enabling
         # clonebundles).
 
         with repo.transaction(b'clone'):
             with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                 for i in range(filecount):
                     # XXX doesn't support '\n' or '\r' in filenames
                     l = fp.readline()
                     try:
                         name, size = l.split(b'\0', 1)
                         size = int(size)
                     except (ValueError, TypeError):
                         raise error.ResponseError(
                             _(b'unexpected response from remote server:'), l
                         )
                     if repo.ui.debugflag:
                         repo.ui.debug(
                             b'adding %s (%s)\n' % (name, util.bytecount(size))
                         )
                     # for backwards compat, name was partially encoded
                     path = store.decodedir(name)
                     with repo.svfs(path, b'w', backgroundclose=True) as ofp:
                         for chunk in util.filechunkiter(fp, limit=size):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         progress.complete()
         repo.ui.status(
             _(b'transferred %s in %.1f seconds (%s/sec)\n')
             % (
                 util.bytecount(bytecount),
                 elapsed,
                 util.bytecount(bytecount / elapsed),
             )
         )
 
 
 def readbundle1header(fp):
     compression = fp.read(2)
     if compression != b'UN':
         raise error.Abort(
             _(
                 b'only uncompressed stream clone bundles are '
                 b'supported; got %s'
             )
             % compression
         )
 
     filecount, bytecount = struct.unpack(b'>QQ', fp.read(16))
     requireslen = struct.unpack(b'>H', fp.read(2))[0]
     requires = fp.read(requireslen)
 
     if not requires.endswith(b'\0'):
         raise error.Abort(
             _(
                 b'malformed stream clone bundle: '
                 b'requirements not properly encoded'
             )
         )
 
     requirements = set(requires.rstrip(b'\0').split(b','))
 
     return filecount, bytecount, requirements
 
 
 def applybundlev1(repo, fp):
     """Apply the content from a stream clone bundle version 1.
 
     We assume the 4 byte header has been read and validated and the file handle
     is at the 2 byte compression identifier.
     """
     if len(repo):
         raise error.Abort(
             _(b'cannot apply stream clone bundle on non-empty repo')
         )
 
     filecount, bytecount, requirements = readbundle1header(fp)
     missingreqs = requirements - repo.supported
     if missingreqs:
         raise error.Abort(
             _(b'unable to apply stream clone: unsupported format: %s')
             % b', '.join(sorted(missingreqs))
         )
 
     consumev1(repo, fp, filecount, bytecount)
     nodemap.post_stream_cleanup(repo)
 
 
 class streamcloneapplier:
     """Class to manage applying streaming clone bundles.
 
     We need to wrap ``applybundlev1()`` in a dedicated type to enable bundle
     readers to perform bundle type-specific functionality.
     """
 
     def __init__(self, fh):
         self._fh = fh
 
     def apply(self, repo):
         return applybundlev1(repo, self._fh)
 
 
 # type of file to stream
 _fileappend = 0  # append only file
 _filefull = 1  # full snapshot file
 
 # Source of the file
 _srcstore = b's'  # store (svfs)
 _srccache = b'c'  # cache (cache)
 
 # This is it's own function so extensions can override it.
 def _walkstreamfullstorefiles(repo):
     """list snapshot file from the store"""
     fnames = []
     if not repo.publishing():
         fnames.append(b'phaseroots')
     return fnames
 
 
 def _filterfull(entry, copy, vfsmap):
     """actually copy the snapshot files"""
     src, name, ftype, data = entry
     if ftype != _filefull:
         return entry
     return (src, name, ftype, copy(vfsmap[src].join(name)))
 
 
 @contextlib.contextmanager
 def maketempcopies():
     """return a function to temporary copy file"""
 
     files = []
     dst_dir = pycompat.mkdtemp(prefix=b'hg-clone-')
     try:
 
         def copy(src):
             fd, dst = pycompat.mkstemp(
                 prefix=os.path.basename(src), dir=dst_dir
             )
             os.close(fd)
             files.append(dst)
             util.copyfiles(src, dst, hardlink=True)
             return dst
 
         yield copy
     finally:
         for tmp in files:
             util.tryunlink(tmp)
         util.tryrmdir(dst_dir)
 
 
 def _makemap(repo):
     """make a (src -> vfs) map for the repo"""
     vfsmap = {
         _srcstore: repo.svfs,
         _srccache: repo.cachevfs,
     }
     # we keep repo.vfs out of the on purpose, ther are too many danger there
     # (eg: .hg/hgrc)
     assert repo.vfs not in vfsmap.values()
 
     return vfsmap
 
 
 def _emit2(repo, entries, totalfilesize):
     """actually emit the stream bundle"""
     vfsmap = _makemap(repo)
     # we keep repo.vfs out of the on purpose, ther are too many danger there
     # (eg: .hg/hgrc),
     #
     # this assert is duplicated (from _makemap) as author might think this is
     # fine, while this is really not fine.
     if repo.vfs in vfsmap.values():
         raise error.ProgrammingError(
             b'repo.vfs must not be added to vfsmap for security reasons'
         )
 
     progress = repo.ui.makeprogress(
         _(b'bundle'), total=totalfilesize, unit=_(b'bytes')
     )
     progress.update(0)
     with maketempcopies() as copy, progress:
         # copy is delayed until we are in the try
         entries = [_filterfull(e, copy, vfsmap) for e in entries]
         yield None  # this release the lock on the repository
         totalbytecount = 0
 
         for src, name, ftype, data in entries:
             vfs = vfsmap[src]
             yield src
             yield util.uvarintencode(len(name))
             if ftype == _fileappend:
                 fp = vfs(name)
                 size = data
             elif ftype == _filefull:
                 fp = open(data, b'rb')
                 size = util.fstat(fp).st_size
             bytecount = 0
             try:
                 yield util.uvarintencode(size)
                 yield name
                 if size <= 65536:
                     chunks = (fp.read(size),)
                 else:
                     chunks = util.filechunkiter(fp, limit=size)
                 for chunk in chunks:
                     bytecount += len(chunk)
                     totalbytecount += len(chunk)
                     progress.update(totalbytecount)
                     yield chunk
                 if bytecount != size:
                     # Would most likely be caused by a race due to `hg strip` or
                     # a revlog split
                     raise error.Abort(
                         _(
                             b'clone could only read %d bytes from %s, but '
                             b'expected %d bytes'
                         )
                         % (bytecount, name, size)
                     )
             finally:
                 fp.close()
 
 
 def _test_sync_point_walk_1(repo):
     """a function for synchronisation during tests"""
 
 
 def _test_sync_point_walk_2(repo):
     """a function for synchronisation during tests"""
 
 
 def _v2_walk(repo, includes, excludes, includeobsmarkers):
     """emit a seris of files information useful to clone a repo
 
     return (entries, totalfilesize)
 
     entries is a list of tuple (vfs-key, file-path, file-type, size)
 
     - `vfs-key`: is a key to the right vfs to write the file (see _makemap)
     - `name`: file path of the file to copy (to be feed to the vfss)
     - `file-type`: do this file need to be copied with the source lock ?
     - `size`: the size of the file (or None)
     """
     assert repo._currentlock(repo._lockref) is not None
     entries = []
     totalfilesize = 0
 
     matcher = None
     if includes or excludes:
         matcher = narrowspec.match(repo.root, includes, excludes)
 
-    for rl_type, name, size in _walkstreamfiles(repo, matcher):
-        if size:
+    for entry in _walkstreamfiles(repo, matcher):
+        if entry.file_size:
             ft = _fileappend
-            if rl_type & store.FILEFLAGS_VOLATILE:
+            if entry.is_volatile:
                 ft = _filefull
-            entries.append((_srcstore, name, ft, size))
-            totalfilesize += size
+            entries.append(
+                (_srcstore, entry.unencoded_path, ft, entry.file_size)
+            )
+            totalfilesize += entry.file_size
     for name in _walkstreamfullstorefiles(repo):
         if repo.svfs.exists(name):
             totalfilesize += repo.svfs.lstat(name).st_size
             entries.append((_srcstore, name, _filefull, None))
     if includeobsmarkers and repo.svfs.exists(b'obsstore'):
         totalfilesize += repo.svfs.lstat(b'obsstore').st_size
         entries.append((_srcstore, b'obsstore', _filefull, None))
     for name in cacheutil.cachetocopy(repo):
         if repo.cachevfs.exists(name):
             totalfilesize += repo.cachevfs.lstat(name).st_size
             entries.append((_srccache, name, _filefull, None))
     return entries, totalfilesize
 
 
 def generatev2(repo, includes, excludes, includeobsmarkers):
     """Emit content for version 2 of a streaming clone.
 
     the data stream consists the following entries:
     1) A char representing the file destination (eg: store or cache)
     2) A varint containing the length of the filename
     3) A varint containing the length of file data
     4) N bytes containing the filename (the internal, store-agnostic form)
     5) N bytes containing the file data
 
     Returns a 3-tuple of (file count, file size, data iterator).
     """
 
     with repo.lock():
 
         repo.ui.debug(b'scanning\n')
 
         entries, totalfilesize = _v2_walk(
             repo,
             includes=includes,
             excludes=excludes,
             includeobsmarkers=includeobsmarkers,
         )
 
         chunks = _emit2(repo, entries, totalfilesize)
         first = next(chunks)
         assert first is None
         _test_sync_point_walk_1(repo)
     _test_sync_point_walk_2(repo)
 
     return len(entries), totalfilesize, chunks
 
 
 @contextlib.contextmanager
 def nested(*ctxs):
     this = ctxs[0]
     rest = ctxs[1:]
     with this:
         if rest:
             with nested(*rest):
                 yield
         else:
             yield
 
 
 def consumev2(repo, fp, filecount, filesize):
     """Apply the contents from a version 2 streaming clone.
 
     Data is read from an object that only needs to provide a ``read(size)``
     method.
     """
     with repo.lock():
         repo.ui.status(
             _(b'%d files to transfer, %s of data\n')
             % (filecount, util.bytecount(filesize))
         )
 
         start = util.timer()
         progress = repo.ui.makeprogress(
             _(b'clone'), total=filesize, unit=_(b'bytes')
         )
         progress.update(0)
 
         vfsmap = _makemap(repo)
         # we keep repo.vfs out of the on purpose, ther are too many danger
         # there (eg: .hg/hgrc),
         #
         # this assert is duplicated (from _makemap) as author might think this
         # is fine, while this is really not fine.
         if repo.vfs in vfsmap.values():
             raise error.ProgrammingError(
                 b'repo.vfs must not be added to vfsmap for security reasons'
             )
 
         with repo.transaction(b'clone'):
             ctxs = (vfs.backgroundclosing(repo.ui) for vfs in vfsmap.values())
             with nested(*ctxs):
                 for i in range(filecount):
                     src = util.readexactly(fp, 1)
                     vfs = vfsmap[src]
                     namelen = util.uvarintdecodestream(fp)
                     datalen = util.uvarintdecodestream(fp)
 
                     name = util.readexactly(fp, namelen)
 
                     if repo.ui.debugflag:
                         repo.ui.debug(
                             b'adding [%s] %s (%s)\n'
                             % (src, name, util.bytecount(datalen))
                         )
 
                     with vfs(name, b'w') as ofp:
                         for chunk in util.filechunkiter(fp, limit=datalen):
                             progress.increment(step=len(chunk))
                             ofp.write(chunk)
 
             # force @filecache properties to be reloaded from
             # streamclone-ed file at next access
             repo.invalidate(clearfilecache=True)
 
         elapsed = util.timer() - start
         if elapsed <= 0:
             elapsed = 0.001
         repo.ui.status(
             _(b'transferred %s in %.1f seconds (%s/sec)\n')
             % (
                 util.bytecount(progress.pos),
                 elapsed,
                 util.bytecount(progress.pos / elapsed),
             )
         )
         progress.complete()
 
 
 def applybundlev2(repo, fp, filecount, filesize, requirements):
     from . import localrepo
 
     missingreqs = [r for r in requirements if r not in repo.supported]
     if missingreqs:
         raise error.Abort(
             _(b'unable to apply stream clone: unsupported format: %s')
             % b', '.join(sorted(missingreqs))
         )
 
     consumev2(repo, fp, filecount, filesize)
 
     repo.requirements = new_stream_clone_requirements(
         repo.requirements,
         requirements,
     )
     repo.svfs.options = localrepo.resolvestorevfsoptions(
         repo.ui, repo.requirements, repo.features
     )
     scmutil.writereporequirements(repo)
     nodemap.post_stream_cleanup(repo)
 
 
 def _copy_files(src_vfs_map, dst_vfs_map, entries, progress):
     hardlink = [True]
 
     def copy_used():
         hardlink[0] = False
         progress.topic = _(b'copying')
 
     for k, path, size in entries:
         src_vfs = src_vfs_map[k]
         dst_vfs = dst_vfs_map[k]
         src_path = src_vfs.join(path)
         dst_path = dst_vfs.join(path)
         # We cannot use dirname and makedirs of dst_vfs here because the store
         # encoding confuses them. See issue 6581 for details.
         dirname = os.path.dirname(dst_path)
         if not os.path.exists(dirname):
             util.makedirs(dirname)
         dst_vfs.register_file(path)
         # XXX we could use the #nb_bytes argument.
         util.copyfile(
             src_path,
             dst_path,
             hardlink=hardlink[0],
             no_hardlink_cb=copy_used,
             check_fs_hardlink=False,
         )
         progress.increment()
     return hardlink[0]
 
 
 def local_copy(src_repo, dest_repo):
     """copy all content from one local repository to another
 
     This is useful for local clone"""
     src_store_requirements = {
         r
         for r in src_repo.requirements
         if r not in requirementsmod.WORKING_DIR_REQUIREMENTS
     }
     dest_store_requirements = {
         r
         for r in dest_repo.requirements
         if r not in requirementsmod.WORKING_DIR_REQUIREMENTS
     }
     assert src_store_requirements == dest_store_requirements
 
     with dest_repo.lock():
         with src_repo.lock():
 
             # bookmark is not integrated to the streaming as it might use the
             # `repo.vfs` and they are too many sentitive data accessible
             # through `repo.vfs` to expose it to streaming clone.
             src_book_vfs = bookmarks.bookmarksvfs(src_repo)
             srcbookmarks = src_book_vfs.join(b'bookmarks')
             bm_count = 0
             if os.path.exists(srcbookmarks):
                 bm_count = 1
 
             entries, totalfilesize = _v2_walk(
                 src_repo,
                 includes=None,
                 excludes=None,
                 includeobsmarkers=True,
             )
             src_vfs_map = _makemap(src_repo)
             dest_vfs_map = _makemap(dest_repo)
             progress = src_repo.ui.makeprogress(
                 topic=_(b'linking'),
                 total=len(entries) + bm_count,
                 unit=_(b'files'),
             )
             # copy  files
             #
             # We could copy the full file while the source repository is locked
             # and the other one without the lock. However, in the linking case,
             # this would also requires checks that nobody is appending any data
             # to the files while we do the clone, so this is not done yet. We
             # could do this blindly when copying files.
             files = ((k, path, size) for k, path, ftype, size in entries)
             hardlink = _copy_files(src_vfs_map, dest_vfs_map, files, progress)
 
             # copy bookmarks over
             if bm_count:
                 dst_book_vfs = bookmarks.bookmarksvfs(dest_repo)
                 dstbookmarks = dst_book_vfs.join(b'bookmarks')
                 util.copyfile(srcbookmarks, dstbookmarks)
         progress.complete()
         if hardlink:
             msg = b'linked %d files\n'
         else:
             msg = b'copied %d files\n'
         src_repo.ui.debug(msg % (len(entries) + bm_count))
 
         with dest_repo.transaction(b"localclone") as tr:
             dest_repo.store.write(tr)
 
         # clean up transaction file as they do not make sense
         transaction.cleanup_undo_files(dest_repo.ui.warn, dest_repo.vfs_map)

mercurial/upgrade_utils/engine.py

@@ -1,689 +1,690 b''
 # upgrade.py - functions for in place upgrade of Mercurial repository
 #
 # Copyright (c) 2016-present, Gregory Szorc
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 
 import stat
 
 from ..i18n import _
 from ..pycompat import getattr
 from .. import (
     changelog,
     error,
     filelog,
     manifest,
     metadata,
     pycompat,
     requirements,
     scmutil,
     store,
     util,
     vfs as vfsmod,
 )
 from ..revlogutils import (
     constants as revlogconst,
     flagutil,
     nodemap,
     sidedata as sidedatamod,
 )
 from . import actions as upgrade_actions
 
 
 def get_sidedata_helpers(srcrepo, dstrepo):
     use_w = srcrepo.ui.configbool(b'experimental', b'worker.repository-upgrade')
     sequential = pycompat.iswindows or not use_w
     if not sequential:
         srcrepo.register_sidedata_computer(
             revlogconst.KIND_CHANGELOG,
             sidedatamod.SD_FILES,
             (sidedatamod.SD_FILES,),
             metadata._get_worker_sidedata_adder(srcrepo, dstrepo),
             flagutil.REVIDX_HASCOPIESINFO,
             replace=True,
         )
     return sidedatamod.get_sidedata_helpers(srcrepo, dstrepo._wanted_sidedata)
 
 
 def _revlogfrompath(repo, rl_type, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if rl_type & store.FILEFLAGS_CHANGELOG:
         return changelog.changelog(repo.svfs)
     elif rl_type & store.FILEFLAGS_MANIFESTLOG:
         mandir = b''
         if b'/' in path:
             mandir = path.rsplit(b'/', 1)[0]
         return manifest.manifestrevlog(
             repo.nodeconstants, repo.svfs, tree=mandir
         )
     else:
         # drop the extension and the `data/` prefix
         path_part = path.rsplit(b'.', 1)[0].split(b'/', 1)
         if len(path_part) < 2:
             msg = _(b'cannot recognize revlog from filename: %s')
             msg %= path
             raise error.Abort(msg)
         path = path_part[1]
         return filelog.filelog(repo.svfs, path)
 
 
 def _copyrevlog(tr, destrepo, oldrl, rl_type, unencodedname):
     """copy all relevant files for `oldrl` into `destrepo` store
 
     Files are copied "as is" without any transformation. The copy is performed
     without extra checks. Callers are responsible for making sure the copied
     content is compatible with format of the destination repository.
     """
     oldrl = getattr(oldrl, '_revlog', oldrl)
     newrl = _revlogfrompath(destrepo, rl_type, unencodedname)
     newrl = getattr(newrl, '_revlog', newrl)
 
     oldvfs = oldrl.opener
     newvfs = newrl.opener
     oldindex = oldvfs.join(oldrl._indexfile)
     newindex = newvfs.join(newrl._indexfile)
     olddata = oldvfs.join(oldrl._datafile)
     newdata = newvfs.join(newrl._datafile)
 
     with newvfs(newrl._indexfile, b'w'):
         pass  # create all the directories
 
     util.copyfile(oldindex, newindex)
     copydata = oldrl.opener.exists(oldrl._datafile)
     if copydata:
         util.copyfile(olddata, newdata)
 
     if rl_type & store.FILEFLAGS_FILELOG:
         destrepo.svfs.fncache.add(unencodedname)
         if copydata:
             destrepo.svfs.fncache.add(unencodedname[:-2] + b'.d')
 
 
 UPGRADE_CHANGELOG = b"changelog"
 UPGRADE_MANIFEST = b"manifest"
 UPGRADE_FILELOGS = b"all-filelogs"
 
 UPGRADE_ALL_REVLOGS = frozenset(
     [UPGRADE_CHANGELOG, UPGRADE_MANIFEST, UPGRADE_FILELOGS]
 )
 
 
 def matchrevlog(revlogfilter, rl_type):
     """check if a revlog is selected for cloning.
 
     In other words, are there any updates which need to be done on revlog
     or it can be blindly copied.
 
     The store entry is checked against the passed filter"""
     if rl_type & store.FILEFLAGS_CHANGELOG:
         return UPGRADE_CHANGELOG in revlogfilter
     elif rl_type & store.FILEFLAGS_MANIFESTLOG:
         return UPGRADE_MANIFEST in revlogfilter
     assert rl_type & store.FILEFLAGS_FILELOG
     return UPGRADE_FILELOGS in revlogfilter
 
 
 def _perform_clone(
     ui,
     dstrepo,
     tr,
     old_revlog,
     rl_type,
     unencoded,
     upgrade_op,
     sidedata_helpers,
     oncopiedrevision,
 ):
     """returns the new revlog object created"""
     newrl = None
     if matchrevlog(upgrade_op.revlogs_to_process, rl_type):
         ui.note(
             _(b'cloning %d revisions from %s\n') % (len(old_revlog), unencoded)
         )
         newrl = _revlogfrompath(dstrepo, rl_type, unencoded)
         old_revlog.clone(
             tr,
             newrl,
             addrevisioncb=oncopiedrevision,
             deltareuse=upgrade_op.delta_reuse_mode,
             forcedeltabothparents=upgrade_op.force_re_delta_both_parents,
             sidedata_helpers=sidedata_helpers,
         )
     else:
         msg = _(b'blindly copying %s containing %i revisions\n')
         ui.note(msg % (unencoded, len(old_revlog)))
         _copyrevlog(tr, dstrepo, old_revlog, rl_type, unencoded)
 
         newrl = _revlogfrompath(dstrepo, rl_type, unencoded)
     return newrl
 
 
 def _clonerevlogs(
     ui,
     srcrepo,
     dstrepo,
     tr,
     upgrade_op,
 ):
     """Copy revlogs between 2 repos."""
     revcount = 0
     srcsize = 0
     srcrawsize = 0
     dstsize = 0
     fcount = 0
     frevcount = 0
     fsrcsize = 0
     frawsize = 0
     fdstsize = 0
     mcount = 0
     mrevcount = 0
     msrcsize = 0
     mrawsize = 0
     mdstsize = 0
     crevcount = 0
     csrcsize = 0
     crawsize = 0
     cdstsize = 0
 
     alldatafiles = list(srcrepo.store.walk())
     # mapping of data files which needs to be cloned
     # key is unencoded filename
     # value is revlog_object_from_srcrepo
     manifests = {}
     changelogs = {}
     filelogs = {}
 
     # Perform a pass to collect metadata. This validates we can open all
     # source files and allows a unified progress bar to be displayed.
-    for rl_type, unencoded, size in alldatafiles:
-        if not rl_type & store.FILEFLAGS_REVLOG_MAIN:
+    for entry in alldatafiles:
+        if not (entry.is_revlog and entry.is_revlog_main):
             continue
+        unencoded = entry.unencoded_path
 
         # the store.walk function will wrongly pickup transaction backup and
         # get confused. As a quick fix for 5.9 release, we ignore those.
         # (this is not a module constants because it seems better to keep the
         # hack together)
         skip_undo = (
             b'undo.backup.00changelog.i',
             b'undo.backup.00manifest.i',
         )
         if unencoded in skip_undo:
             continue
 
-        rl = _revlogfrompath(srcrepo, rl_type, unencoded)
+        rl = _revlogfrompath(srcrepo, entry.revlog_type, unencoded)
 
         info = rl.storageinfo(
             exclusivefiles=True,
             revisionscount=True,
             trackedsize=True,
             storedsize=True,
         )
 
         revcount += info[b'revisionscount'] or 0
         datasize = info[b'storedsize'] or 0
         rawsize = info[b'trackedsize'] or 0
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
-        if rl_type & store.FILEFLAGS_CHANGELOG:
-            changelogs[unencoded] = rl_type
+        if entry.revlog_type & store.FILEFLAGS_CHANGELOG:
+            changelogs[unencoded] = entry.revlog_type
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
-        elif rl_type & store.FILEFLAGS_MANIFESTLOG:
-            manifests[unencoded] = rl_type
+        elif entry.revlog_type & store.FILEFLAGS_MANIFESTLOG:
+            manifests[unencoded] = entry.revlog_type
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
-        elif rl_type & store.FILEFLAGS_FILELOG:
-            filelogs[unencoded] = rl_type
+        elif entry.revlog_type & store.FILEFLAGS_FILELOG:
+            filelogs[unencoded] = entry.revlog_type
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError(b'unknown revlog type')
 
     if not revcount:
         return
 
     ui.status(
         _(
             b'migrating %d total revisions (%d in filelogs, %d in manifests, '
             b'%d in changelog)\n'
         )
         % (revcount, frevcount, mrevcount, crevcount)
     )
     ui.status(
         _(b'migrating %s in store; %s tracked data\n')
         % ((util.bytecount(srcsize), util.bytecount(srcrawsize)))
     )
 
     # Used to keep track of progress.
     progress = None
 
     def oncopiedrevision(rl, rev, node):
         progress.increment()
 
     sidedata_helpers = get_sidedata_helpers(srcrepo, dstrepo)
 
     # Migrating filelogs
     ui.status(
         _(
             b'migrating %d filelogs containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             fcount,
             frevcount,
             util.bytecount(fsrcsize),
             util.bytecount(frawsize),
         )
     )
     progress = srcrepo.ui.makeprogress(_(b'file revisions'), total=frevcount)
     for unencoded, rl_type in sorted(filelogs.items()):
         oldrl = _revlogfrompath(srcrepo, rl_type, unencoded)
 
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
             sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         fdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d filelog revisions across %d '
             b'filelogs; change in size: %s\n'
         )
         % (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
     )
 
     # Migrating manifests
     ui.status(
         _(
             b'migrating %d manifests containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             mcount,
             mrevcount,
             util.bytecount(msrcsize),
             util.bytecount(mrawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'manifest revisions'), total=mrevcount
     )
     for unencoded, rl_type in sorted(manifests.items()):
         oldrl = _revlogfrompath(srcrepo, rl_type, unencoded)
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
             sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         mdstsize += info[b'storedsize'] or 0
     ui.status(
         _(
             b'finished migrating %d manifest revisions across %d '
             b'manifests; change in size: %s\n'
         )
         % (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
     )
 
     # Migrating changelog
     ui.status(
         _(
             b'migrating changelog containing %d revisions '
             b'(%s in store; %s tracked data)\n'
         )
         % (
             crevcount,
             util.bytecount(csrcsize),
             util.bytecount(crawsize),
         )
     )
     if progress:
         progress.complete()
     progress = srcrepo.ui.makeprogress(
         _(b'changelog revisions'), total=crevcount
     )
     for unencoded, rl_type in sorted(changelogs.items()):
         oldrl = _revlogfrompath(srcrepo, rl_type, unencoded)
         newrl = _perform_clone(
             ui,
             dstrepo,
             tr,
             oldrl,
             rl_type,
             unencoded,
             upgrade_op,
             sidedata_helpers,
             oncopiedrevision,
         )
         info = newrl.storageinfo(storedsize=True)
         cdstsize += info[b'storedsize'] or 0
     progress.complete()
     ui.status(
         _(
             b'finished migrating %d changelog revisions; change in size: '
             b'%s\n'
         )
         % (crevcount, util.bytecount(cdstsize - csrcsize))
     )
 
     dstsize = fdstsize + mdstsize + cdstsize
     ui.status(
         _(
             b'finished migrating %d total revisions; total change in store '
             b'size: %s\n'
         )
         % (revcount, util.bytecount(dstsize - srcsize))
     )
 
 
 def _files_to_copy_post_revlog_clone(srcrepo):
     """yields files which should be copied to destination after revlogs
     are cloned"""
     for path, kind, st in sorted(srcrepo.store.vfs.readdir(b'', stat=True)):
         # don't copy revlogs as they are already cloned
         if store.revlog_type(path) is not None:
             continue
         # Skip transaction related files.
         if path.startswith(b'undo'):
             continue
         # Only copy regular files.
         if kind != stat.S_IFREG:
             continue
         # Skip other skipped files.
         if path in (b'lock', b'fncache'):
             continue
         # TODO: should we skip cache too?
 
         yield path
 
 
 def _replacestores(currentrepo, upgradedrepo, backupvfs, upgrade_op):
     """Replace the stores after current repository is upgraded
 
     Creates a backup of current repository store at backup path
     Replaces upgraded store files in current repo from upgraded one
 
     Arguments:
       currentrepo: repo object of current repository
       upgradedrepo: repo object of the upgraded data
       backupvfs: vfs object for the backup path
       upgrade_op: upgrade operation object
                   to be used to decide what all is upgraded
     """
     # TODO: don't blindly rename everything in store
     # There can be upgrades where store is not touched at all
     if upgrade_op.backup_store:
         util.rename(currentrepo.spath, backupvfs.join(b'store'))
     else:
         currentrepo.vfs.rmtree(b'store', forcibly=True)
     util.rename(upgradedrepo.spath, currentrepo.spath)
 
 
 def finishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 
 def upgrade(ui, srcrepo, dstrepo, upgrade_op):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
     backuppath = None
     backupvfs = None
 
     ui.status(
         _(
             b'(it is safe to interrupt this process any time before '
             b'data migration completes)\n'
         )
     )
 
     if upgrade_actions.dirstatev2 in upgrade_op.upgrade_actions:
         ui.status(_(b'upgrading to dirstate-v2 from v1\n'))
         upgrade_dirstate(ui, srcrepo, upgrade_op, b'v1', b'v2')
         upgrade_op.upgrade_actions.remove(upgrade_actions.dirstatev2)
 
     if upgrade_actions.dirstatev2 in upgrade_op.removed_actions:
         ui.status(_(b'downgrading from dirstate-v2 to v1\n'))
         upgrade_dirstate(ui, srcrepo, upgrade_op, b'v2', b'v1')
         upgrade_op.removed_actions.remove(upgrade_actions.dirstatev2)
 
     if upgrade_actions.dirstatetrackedkey in upgrade_op.upgrade_actions:
         ui.status(_(b'create dirstate-tracked-hint file\n'))
         upgrade_tracked_hint(ui, srcrepo, upgrade_op, add=True)
         upgrade_op.upgrade_actions.remove(upgrade_actions.dirstatetrackedkey)
     elif upgrade_actions.dirstatetrackedkey in upgrade_op.removed_actions:
         ui.status(_(b'remove dirstate-tracked-hint file\n'))
         upgrade_tracked_hint(ui, srcrepo, upgrade_op, add=False)
         upgrade_op.removed_actions.remove(upgrade_actions.dirstatetrackedkey)
 
     if not (upgrade_op.upgrade_actions or upgrade_op.removed_actions):
         return
 
     if upgrade_op.requirements_only:
         ui.status(_(b'upgrading repository requirements\n'))
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     # if there is only one action and that is persistent nodemap upgrade
     # directly write the nodemap file and update requirements instead of going
     # through the whole cloning process
     elif (
         len(upgrade_op.upgrade_actions) == 1
         and b'persistent-nodemap' in upgrade_op.upgrade_actions_names
         and not upgrade_op.removed_actions
     ):
         ui.status(
             _(b'upgrading repository to use persistent nodemap feature\n')
         )
         with srcrepo.transaction(b'upgrade') as tr:
             unfi = srcrepo.unfiltered()
             cl = unfi.changelog
             nodemap.persist_nodemap(tr, cl, force=True)
             # we want to directly operate on the underlying revlog to force
             # create a nodemap file. This is fine since this is upgrade code
             # and it heavily relies on repository being revlog based
             # hence accessing private attributes can be justified
             nodemap.persist_nodemap(
                 tr, unfi.manifestlog._rootstore._revlog, force=True
             )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     elif (
         len(upgrade_op.removed_actions) == 1
         and [
             x
             for x in upgrade_op.removed_actions
             if x.name == b'persistent-nodemap'
         ]
         and not upgrade_op.upgrade_actions
     ):
         ui.status(
             _(b'downgrading repository to not use persistent nodemap feature\n')
         )
         with srcrepo.transaction(b'upgrade') as tr:
             unfi = srcrepo.unfiltered()
             cl = unfi.changelog
             nodemap.delete_nodemap(tr, srcrepo, cl)
             # check comment 20 lines above for accessing private attributes
             nodemap.delete_nodemap(
                 tr, srcrepo, unfi.manifestlog._rootstore._revlog
             )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
     else:
         with dstrepo.transaction(b'upgrade') as tr:
             _clonerevlogs(
                 ui,
                 srcrepo,
                 dstrepo,
                 tr,
                 upgrade_op,
             )
 
         # Now copy other files in the store directory.
         for p in _files_to_copy_post_revlog_clone(srcrepo):
             srcrepo.ui.status(_(b'copying %s\n') % p)
             src = srcrepo.store.rawvfs.join(p)
             dst = dstrepo.store.rawvfs.join(p)
             util.copyfile(src, dst, copystat=True)
 
         finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
         ui.status(_(b'data fully upgraded in a temporary repository\n'))
 
         if upgrade_op.backup_store:
             backuppath = pycompat.mkdtemp(
                 prefix=b'upgradebackup.', dir=srcrepo.path
             )
             backupvfs = vfsmod.vfs(backuppath)
 
             # Make a backup of requires file first, as it is the first to be modified.
             util.copyfile(
                 srcrepo.vfs.join(b'requires'), backupvfs.join(b'requires')
             )
 
         # We install an arbitrary requirement that clients must not support
         # as a mechanism to lock out new clients during the data swap. This is
         # better than allowing a client to continue while the repository is in
         # an inconsistent state.
         ui.status(
             _(
                 b'marking source repository as being upgraded; clients will be '
                 b'unable to read from repository\n'
             )
         )
         scmutil.writereporequirements(
             srcrepo, srcrepo.requirements | {b'upgradeinprogress'}
         )
 
         ui.status(_(b'starting in-place swap of repository data\n'))
         if upgrade_op.backup_store:
             ui.status(
                 _(b'replaced files will be backed up at %s\n') % backuppath
             )
 
         # Now swap in the new store directory. Doing it as a rename should make
         # the operation nearly instantaneous and atomic (at least in well-behaved
         # environments).
         ui.status(_(b'replacing store...\n'))
         tstart = util.timer()
         _replacestores(srcrepo, dstrepo, backupvfs, upgrade_op)
         elapsed = util.timer() - tstart
         ui.status(
             _(
                 b'store replacement complete; repository was inconsistent for '
                 b'%0.1fs\n'
             )
             % elapsed
         )
 
         # We first write the requirements file. Any new requirements will lock
         # out legacy clients.
         ui.status(
             _(
                 b'finalizing requirements file and making repository readable '
                 b'again\n'
             )
         )
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
 
         if upgrade_op.backup_store:
             # The lock file from the old store won't be removed because nothing has a
             # reference to its new location. So clean it up manually. Alternatively, we
             # could update srcrepo.svfs and other variables to point to the new
             # location. This is simpler.
             assert backupvfs is not None  # help pytype
             backupvfs.unlink(b'store/lock')
 
     return backuppath
 
 
 def upgrade_dirstate(ui, srcrepo, upgrade_op, old, new):
     if upgrade_op.backup_store:
         backuppath = pycompat.mkdtemp(
             prefix=b'upgradebackup.', dir=srcrepo.path
         )
         ui.status(_(b'replaced files will be backed up at %s\n') % backuppath)
         backupvfs = vfsmod.vfs(backuppath)
         util.copyfile(
             srcrepo.vfs.join(b'requires'), backupvfs.join(b'requires')
         )
         try:
             util.copyfile(
                 srcrepo.vfs.join(b'dirstate'), backupvfs.join(b'dirstate')
             )
         except FileNotFoundError:
             # The dirstate does not exist on an empty repo or a repo with no
             # revision checked out
             pass
 
     assert srcrepo.dirstate._use_dirstate_v2 == (old == b'v2')
     use_v2 = new == b'v2'
     if use_v2:
         # Write the requirements *before* upgrading
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
 
     srcrepo.dirstate._map.preload()
     srcrepo.dirstate._use_dirstate_v2 = use_v2
     srcrepo.dirstate._map._use_dirstate_v2 = use_v2
     srcrepo.dirstate._dirty = True
     try:
         srcrepo.vfs.unlink(b'dirstate')
     except FileNotFoundError:
         # The dirstate does not exist on an empty repo or a repo with no
         # revision checked out
         pass
 
     srcrepo.dirstate.write(None)
     if not use_v2:
         # Remove the v2 requirement *after* downgrading
         scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)
 
 
 def upgrade_tracked_hint(ui, srcrepo, upgrade_op, add):
     if add:
         srcrepo.dirstate._use_tracked_hint = True
         srcrepo.dirstate._dirty = True
         srcrepo.dirstate._dirty_tracked_set = True
         srcrepo.dirstate.write(None)
     if not add:
         srcrepo.dirstate.delete_tracked_hint()
 
     scmutil.writereporequirements(srcrepo, upgrade_op.new_requirements)

mercurial/verify.py

@@ -1,621 +1,625 b''
 # verify.py - repository integrity checking for Mercurial
 #
 # Copyright 2006, 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 os
 
 from .i18n import _
 from .node import short
 from .utils import stringutil
 
 from . import (
     error,
     pycompat,
     requirements,
     revlog,
     util,
 )
 
 VERIFY_DEFAULT = 0
 VERIFY_FULL = 1
 
 
 def verify(repo, level=None):
     with repo.lock():
         v = verifier(repo, level)
         return v.verify()
 
 
 def _normpath(f):
     # under hg < 2.4, convert didn't sanitize paths properly, so a
     # converted repo may contain repeated slashes
     while b'//' in f:
         f = f.replace(b'//', b'/')
     return f
 
 
 HINT_FNCACHE = _(
     b'hint: run "hg debugrebuildfncache" to recover from corrupt fncache\n'
 )
 
 WARN_PARENT_DIR_UNKNOWN_REV = _(
     b"parent-directory manifest refers to unknown revision %s"
 )
 
 WARN_UNKNOWN_COPY_SOURCE = _(
     b"warning: copy source of '%s' not in parents of %s"
 )
 
 WARN_NULLID_COPY_SOURCE = _(
     b"warning: %s@%s: copy source revision is nullid %s:%s\n"
 )
 
 
 class verifier:
     def __init__(self, repo, level=None):
         self.repo = repo.unfiltered()
         self.ui = repo.ui
         self.match = repo.narrowmatch()
         if level is None:
             level = VERIFY_DEFAULT
         self._level = level
         self.badrevs = set()
         self.errors = 0
         self.warnings = 0
         self.havecl = len(repo.changelog) > 0
         self.havemf = len(repo.manifestlog.getstorage(b'')) > 0
         self.revlogv1 = repo.changelog._format_version != revlog.REVLOGV0
         self.lrugetctx = util.lrucachefunc(repo.unfiltered().__getitem__)
         self.refersmf = False
         self.fncachewarned = False
         # developer config: verify.skipflags
         self.skipflags = repo.ui.configint(b'verify', b'skipflags')
         self.warnorphanstorefiles = True
 
     def _warn(self, msg):
         """record a "warning" level issue"""
         self.ui.warn(msg + b"\n")
         self.warnings += 1
 
     def _err(self, linkrev, msg, filename=None):
         """record a "error" level issue"""
         if linkrev is not None:
             self.badrevs.add(linkrev)
             linkrev = b"%d" % linkrev
         else:
             linkrev = b'?'
         msg = b"%s: %s" % (linkrev, msg)
         if filename:
             msg = b"%s@%s" % (filename, msg)
         self.ui.warn(b" " + msg + b"\n")
         self.errors += 1
 
     def _exc(self, linkrev, msg, inst, filename=None):
         """record exception raised during the verify process"""
         fmsg = stringutil.forcebytestr(inst)
         if not fmsg:
             fmsg = pycompat.byterepr(inst)
         self._err(linkrev, b"%s: %s" % (msg, fmsg), filename)
 
     def _checkrevlog(self, obj, name, linkrev):
         """verify high level property of a revlog
 
         - revlog is present,
         - revlog is non-empty,
         - sizes (index and data) are correct,
         - revlog's format version is correct.
         """
         if not len(obj) and (self.havecl or self.havemf):
             self._err(linkrev, _(b"empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             self._err(None, _(b"data length off by %d bytes") % d[0], name)
         if d[1]:
             self._err(None, _(b"index contains %d extra bytes") % d[1], name)
 
         if obj._format_version != revlog.REVLOGV0:
             if not self.revlogv1:
                 self._warn(_(b"warning: `%s' uses revlog format 1") % name)
         elif self.revlogv1:
             self._warn(_(b"warning: `%s' uses revlog format 0") % name)
 
     def _checkentry(self, obj, i, node, seen, linkrevs, f):
         """verify a single revlog entry
 
         arguments are:
         - obj:      the source revlog
         - i:        the revision number
         - node:     the revision node id
         - seen:     nodes previously seen for this revlog
         - linkrevs: [changelog-revisions] introducing "node"
         - f:        string label ("changelog", "manifest", or filename)
 
         Performs the following checks:
         - linkrev points to an existing changelog revision,
         - linkrev points to a changelog revision that introduces this revision,
         - linkrev points to the lowest of these changesets,
         - both parents exist in the revlog,
         - the revision is not duplicated.
 
         Return the linkrev of the revision (or None for changelog's revisions).
         """
         lr = obj.linkrev(obj.rev(node))
         if lr < 0 or (self.havecl and lr not in linkrevs):
             if lr < 0 or lr >= len(self.repo.changelog):
                 msg = _(b"rev %d points to nonexistent changeset %d")
             else:
                 msg = _(b"rev %d points to unexpected changeset %d")
             self._err(None, msg % (i, lr), f)
             if linkrevs:
                 if f and len(linkrevs) > 1:
                     try:
                         # attempt to filter down to real linkrevs
                         linkrevs = []
                         for lr in linkrevs:
                             if self.lrugetctx(lr)[f].filenode() == node:
                                 linkrevs.append(lr)
                     except Exception:
                         pass
                 msg = _(b" (expected %s)")
                 msg %= b" ".join(map(pycompat.bytestr, linkrevs))
                 self._warn(msg)
             lr = None  # can't be trusted
 
         try:
             p1, p2 = obj.parents(node)
             if p1 not in seen and p1 != self.repo.nullid:
                 msg = _(b"unknown parent 1 %s of %s") % (short(p1), short(node))
                 self._err(lr, msg, f)
             if p2 not in seen and p2 != self.repo.nullid:
                 msg = _(b"unknown parent 2 %s of %s") % (short(p2), short(node))
                 self._err(lr, msg, f)
         except Exception as inst:
             self._exc(lr, _(b"checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             self._err(lr, _(b"duplicate revision %d (%d)") % (i, seen[node]), f)
         seen[node] = i
         return lr
 
     def verify(self):
         """verify the content of the Mercurial repository
 
         This method run all verifications, displaying issues as they are found.
 
         return 1 if any error have been encountered, 0 otherwise."""
         # initial validation and generic report
         repo = self.repo
         ui = repo.ui
         if not repo.url().startswith(b'file:'):
             raise error.Abort(_(b"cannot verify bundle or remote repos"))
 
         if os.path.exists(repo.sjoin(b"journal")):
             ui.warn(_(b"abandoned transaction found - run hg recover\n"))
 
         if ui.verbose or not self.revlogv1:
             ui.status(
                 _(b"repository uses revlog format %d\n")
                 % (self.revlogv1 and 1 or 0)
             )
 
         # data verification
         mflinkrevs, filelinkrevs = self._verifychangelog()
         filenodes = self._verifymanifest(mflinkrevs)
         del mflinkrevs
         self._crosscheckfiles(filelinkrevs, filenodes)
         totalfiles, filerevisions = self._verifyfiles(filenodes, filelinkrevs)
 
         if self.errors:
             ui.warn(_(b"not checking dirstate because of previous errors\n"))
             dirstate_errors = 0
         else:
             dirstate_errors = self._verify_dirstate()
 
         # final report
         ui.status(
             _(b"checked %d changesets with %d changes to %d files\n")
             % (len(repo.changelog), filerevisions, totalfiles)
         )
         if self.warnings:
             ui.warn(_(b"%d warnings encountered!\n") % self.warnings)
         if self.fncachewarned:
             ui.warn(HINT_FNCACHE)
         if self.errors:
             ui.warn(_(b"%d integrity errors encountered!\n") % self.errors)
             if self.badrevs:
                 msg = _(b"(first damaged changeset appears to be %d)\n")
                 msg %= min(self.badrevs)
                 ui.warn(msg)
             if dirstate_errors:
                 ui.warn(
                     _(b"dirstate inconsistent with current parent's manifest\n")
                 )
                 ui.warn(_(b"%d dirstate errors\n") % dirstate_errors)
             return 1
         return 0
 
     def _verifychangelog(self):
         """verify the changelog of a repository
 
         The following checks are performed:
         - all of `_checkrevlog` checks,
         - all of `_checkentry` checks (for each revisions),
         - each revision can be read.
 
         The function returns some of the data observed in the changesets as a
         (mflinkrevs, filelinkrevs) tuples:
         - mflinkrevs:   is a { manifest-node -> [changelog-rev] } mapping
         - filelinkrevs: is a { file-path -> [changelog-rev] } mapping
 
         If a matcher was specified, filelinkrevs will only contains matched
         files.
         """
         ui = self.ui
         repo = self.repo
         match = self.match
         cl = repo.changelog
 
         ui.status(_(b"checking changesets\n"))
         mflinkrevs = {}
         filelinkrevs = {}
         seen = {}
         self._checkrevlog(cl, b"changelog", 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'changesets'), total=len(repo)
         )
         for i in repo:
             progress.update(i)
             n = cl.node(i)
             self._checkentry(cl, i, n, seen, [i], b"changelog")
 
             try:
                 changes = cl.read(n)
                 if changes[0] != self.repo.nullid:
                     mflinkrevs.setdefault(changes[0], []).append(i)
                     self.refersmf = True
                 for f in changes[3]:
                     if match(f):
                         filelinkrevs.setdefault(_normpath(f), []).append(i)
             except Exception as inst:
                 self.refersmf = True
                 self._exc(i, _(b"unpacking changeset %s") % short(n), inst)
         progress.complete()
         return mflinkrevs, filelinkrevs
 
     def _verifymanifest(
         self, mflinkrevs, dir=b"", storefiles=None, subdirprogress=None
     ):
         """verify the manifestlog content
 
         Inputs:
         - mflinkrevs:     a {manifest-node -> [changelog-revisions]} mapping
         - dir:            a subdirectory to check (for tree manifest repo)
         - storefiles:     set of currently "orphan" files.
         - subdirprogress: a progress object
 
         This function checks:
         * all of `_checkrevlog` checks (for all manifest related revlogs)
         * all of `_checkentry` checks (for all manifest related revisions)
         * nodes for subdirectory exists in the sub-directory manifest
         * each manifest entries have a file path
         * each manifest node refered in mflinkrevs exist in the manifest log
 
         If tree manifest is in use and a matchers is specified, only the
         sub-directories matching it will be verified.
 
         return a two level mapping:
             {"path" -> { filenode -> changelog-revision}}
 
         This mapping primarily contains entries for every files in the
         repository. In addition, when tree-manifest is used, it also contains
         sub-directory entries.
 
         If a matcher is provided, only matching paths will be included.
         """
         repo = self.repo
         ui = self.ui
         match = self.match
         mfl = self.repo.manifestlog
         mf = mfl.getstorage(dir)
 
         if not dir:
             self.ui.status(_(b"checking manifests\n"))
 
         filenodes = {}
         subdirnodes = {}
         seen = {}
         label = b"manifest"
         if dir:
             label = dir
             revlogfiles = mf.files()
             storefiles.difference_update(revlogfiles)
             if subdirprogress:  # should be true since we're in a subdirectory
                 subdirprogress.increment()
         if self.refersmf:
             # Do not check manifest if there are only changelog entries with
             # null manifests.
             self._checkrevlog(mf._revlog, label, 0)
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'manifests'), total=len(mf)
         )
         for i in mf:
             if not dir:
                 progress.update(i)
             n = mf.node(i)
             lr = self._checkentry(mf, i, n, seen, mflinkrevs.get(n, []), label)
             if n in mflinkrevs:
                 del mflinkrevs[n]
             elif dir:
                 msg = _(b"%s not in parent-directory manifest") % short(n)
                 self._err(lr, msg, label)
             else:
                 self._err(lr, _(b"%s not in changesets") % short(n), label)
 
             try:
                 mfdelta = mfl.get(dir, n).readdelta(shallow=True)
                 for f, fn, fl in mfdelta.iterentries():
                     if not f:
                         self._err(lr, _(b"entry without name in manifest"))
                     elif f == b"/dev/null":  # ignore this in very old repos
                         continue
                     fullpath = dir + _normpath(f)
                     if fl == b't':
                         if not match.visitdir(fullpath):
                             continue
                         sdn = subdirnodes.setdefault(fullpath + b'/', {})
                         sdn.setdefault(fn, []).append(lr)
                     else:
                         if not match(fullpath):
                             continue
                         filenodes.setdefault(fullpath, {}).setdefault(fn, lr)
             except Exception as inst:
                 self._exc(lr, _(b"reading delta %s") % short(n), inst, label)
             if self._level >= VERIFY_FULL:
                 try:
                     # Various issues can affect manifest. So we read each full
                     # text from storage. This triggers the checks from the core
                     # code (eg: hash verification, filename are ordered, etc.)
                     mfdelta = mfl.get(dir, n).read()
                 except Exception as inst:
                     msg = _(b"reading full manifest %s") % short(n)
                     self._exc(lr, msg, inst, label)
 
         if not dir:
             progress.complete()
 
         if self.havemf:
             # since we delete entry in `mflinkrevs` during iteration, any
             # remaining entries are "missing". We need to issue errors for them.
             changesetpairs = [(c, m) for m in mflinkrevs for c in mflinkrevs[m]]
             for c, m in sorted(changesetpairs):
                 if dir:
                     self._err(c, WARN_PARENT_DIR_UNKNOWN_REV % short(m), label)
                 else:
                     msg = _(b"changeset refers to unknown revision %s")
                     msg %= short(m)
                     self._err(c, msg, label)
 
         if not dir and subdirnodes:
             self.ui.status(_(b"checking directory manifests\n"))
             storefiles = set()
             subdirs = set()
             revlogv1 = self.revlogv1
             undecodable = []
-            for t, f, size in repo.store.datafiles(undecodable=undecodable):
+            for entry in repo.store.datafiles(undecodable=undecodable):
+                f = entry.unencoded_path
+                size = entry.file_size
                 if (size > 0 or not revlogv1) and f.startswith(b'meta/'):
                     storefiles.add(_normpath(f))
                     subdirs.add(os.path.dirname(f))
             for f in undecodable:
                 self._err(None, _(b"cannot decode filename '%s'") % f)
             subdirprogress = ui.makeprogress(
                 _(b'checking'), unit=_(b'manifests'), total=len(subdirs)
             )
 
         for subdir, linkrevs in subdirnodes.items():
             subdirfilenodes = self._verifymanifest(
                 linkrevs, subdir, storefiles, subdirprogress
             )
             for f, onefilenodes in subdirfilenodes.items():
                 filenodes.setdefault(f, {}).update(onefilenodes)
 
         if not dir and subdirnodes:
             assert subdirprogress is not None  # help pytype
             subdirprogress.complete()
             if self.warnorphanstorefiles:
                 for f in sorted(storefiles):
                     self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return filenodes
 
     def _crosscheckfiles(self, filelinkrevs, filenodes):
         repo = self.repo
         ui = self.ui
         ui.status(_(b"crosschecking files in changesets and manifests\n"))
 
         total = len(filelinkrevs) + len(filenodes)
         progress = ui.makeprogress(
             _(b'crosschecking'), unit=_(b'files'), total=total
         )
         if self.havemf:
             for f in sorted(filelinkrevs):
                 progress.increment()
                 if f not in filenodes:
                     lr = filelinkrevs[f][0]
                     self._err(lr, _(b"in changeset but not in manifest"), f)
 
         if self.havecl:
             for f in sorted(filenodes):
                 progress.increment()
                 if f not in filelinkrevs:
                     try:
                         fl = repo.file(f)
                         lr = min([fl.linkrev(fl.rev(n)) for n in filenodes[f]])
                     except Exception:
                         lr = None
                     self._err(lr, _(b"in manifest but not in changeset"), f)
 
         progress.complete()
 
     def _verifyfiles(self, filenodes, filelinkrevs):
         repo = self.repo
         ui = self.ui
         lrugetctx = self.lrugetctx
         revlogv1 = self.revlogv1
         havemf = self.havemf
         ui.status(_(b"checking files\n"))
 
         storefiles = set()
         undecodable = []
-        for t, f, size in repo.store.datafiles(undecodable=undecodable):
+        for entry in repo.store.datafiles(undecodable=undecodable):
+            size = entry.file_size
+            f = entry.unencoded_path
             if (size > 0 or not revlogv1) and f.startswith(b'data/'):
                 storefiles.add(_normpath(f))
         for f in undecodable:
             self._err(None, _(b"cannot decode filename '%s'") % f)
 
         state = {
             # TODO this assumes revlog storage for changelog.
             b'expectedversion': self.repo.changelog._format_version,
             b'skipflags': self.skipflags,
             # experimental config: censor.policy
             b'erroroncensored': ui.config(b'censor', b'policy') == b'abort',
         }
 
         files = sorted(set(filenodes) | set(filelinkrevs))
         revisions = 0
         progress = ui.makeprogress(
             _(b'checking'), unit=_(b'files'), total=len(files)
         )
         for i, f in enumerate(files):
             progress.update(i, item=f)
             try:
                 linkrevs = filelinkrevs[f]
             except KeyError:
                 # in manifest but not in changelog
                 linkrevs = []
 
             if linkrevs:
                 lr = linkrevs[0]
             else:
                 lr = None
 
             try:
                 fl = repo.file(f)
             except error.StorageError as e:
                 self._err(lr, _(b"broken revlog! (%s)") % e, f)
                 continue
 
             for ff in fl.files():
                 try:
                     storefiles.remove(ff)
                 except KeyError:
                     if self.warnorphanstorefiles:
                         msg = _(b" warning: revlog '%s' not in fncache!")
                         self._warn(msg % ff)
                         self.fncachewarned = True
 
             if not len(fl) and (self.havecl or self.havemf):
                 self._err(lr, _(b"empty or missing %s") % f)
             else:
                 # Guard against implementations not setting this.
                 state[b'skipread'] = set()
                 state[b'safe_renamed'] = set()
 
                 for problem in fl.verifyintegrity(state):
                     if problem.node is not None:
                         linkrev = fl.linkrev(fl.rev(problem.node))
                     else:
                         linkrev = None
 
                     if problem.warning:
                         self._warn(problem.warning)
                     elif problem.error:
                         linkrev_msg = linkrev if linkrev is not None else lr
                         self._err(linkrev_msg, problem.error, f)
                     else:
                         raise error.ProgrammingError(
                             b'problem instance does not set warning or error '
                             b'attribute: %s' % problem.msg
                         )
 
             seen = {}
             for i in fl:
                 revisions += 1
                 n = fl.node(i)
                 lr = self._checkentry(fl, i, n, seen, linkrevs, f)
                 if f in filenodes:
                     if havemf and n not in filenodes[f]:
                         self._err(lr, _(b"%s not in manifests") % (short(n)), f)
                     else:
                         del filenodes[f][n]
 
                 if n in state[b'skipread'] and n not in state[b'safe_renamed']:
                     continue
 
                 # check renames
                 try:
                     # This requires resolving fulltext (at least on revlogs,
                     # though not with LFS revisions). We may want
                     # ``verifyintegrity()`` to pass a set of nodes with
                     # rename metadata as an optimization.
                     rp = fl.renamed(n)
                     if rp:
                         if lr is not None and ui.verbose:
                             ctx = lrugetctx(lr)
                             if not any(rp[0] in pctx for pctx in ctx.parents()):
                                 self._warn(WARN_UNKNOWN_COPY_SOURCE % (f, ctx))
                         fl2 = repo.file(rp[0])
                         if not len(fl2):
                             m = _(b"empty or missing copy source revlog %s:%s")
                             self._err(lr, m % (rp[0], short(rp[1])), f)
                         elif rp[1] == self.repo.nullid:
                             msg = WARN_NULLID_COPY_SOURCE
                             msg %= (f, lr, rp[0], short(rp[1]))
                             ui.note(msg)
                         else:
                             fl2.rev(rp[1])
                 except Exception as inst:
                     self._exc(
                         lr, _(b"checking rename of %s") % short(n), inst, f
                     )
 
             # cross-check
             if f in filenodes:
                 fns = [(v, k) for k, v in filenodes[f].items()]
                 for lr, node in sorted(fns):
                     msg = _(b"manifest refers to unknown revision %s")
                     self._err(lr, msg % short(node), f)
         progress.complete()
 
         if self.warnorphanstorefiles:
             for f in sorted(storefiles):
                 self._warn(_(b"warning: orphan data file '%s'") % f)
 
         return len(files), revisions
 
     def _verify_dirstate(self):
         """Check that the dirstate is consistent with the parent's manifest"""
         repo = self.repo
         ui = self.ui
         ui.status(_(b"checking dirstate\n"))
 
         parent1, parent2 = repo.dirstate.parents()
         m1 = repo[parent1].manifest()
         m2 = repo[parent2].manifest()
         dirstate_errors = 0
 
         is_narrow = requirements.NARROW_REQUIREMENT in repo.requirements
         narrow_matcher = repo.narrowmatch() if is_narrow else None
 
         for err in repo.dirstate.verify(m1, m2, parent1, narrow_matcher):
             ui.error(err)
             dirstate_errors += 1
 
         if dirstate_errors:
             self.errors += dirstate_errors
         return dirstate_errors