Mercurial > hg
view mercurial/logexchange.py @ 42377:0546ead39a7e stable
manifest: avoid corruption by dropping removed files with pure (issue5801)
Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`. But no effort was made to
ignore them when compacting the dictionary into text form. This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible. As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry. This typically resulted in
a ValueError complaining about unsorted manifest entries.
Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot. A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.
In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes. However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.
[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Thu, 23 May 2019 21:54:24 -0400 |
parents | 876494fd967d |
children | 2372284d9457 |
line wrap: on
line source
# logexchange.py # # Copyright 2017 Augie Fackler <raf@durin42.com> # Copyright 2017 Sean Farley <sean@farley.io> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. from __future__ import absolute_import from .node import hex from . import ( util, vfs as vfsmod, ) # directory name in .hg/ in which remotenames files will be present remotenamedir = 'logexchange' def readremotenamefile(repo, filename): """ reads a file from .hg/logexchange/ directory and yields it's content filename: the file to be read yield a tuple (node, remotepath, name) """ vfs = vfsmod.vfs(repo.vfs.join(remotenamedir)) if not vfs.exists(filename): return f = vfs(filename) lineno = 0 for line in f: line = line.strip() if not line: continue # contains the version number if lineno == 0: lineno += 1 try: node, remote, rname = line.split('\0') yield node, remote, rname except ValueError: pass f.close() def readremotenames(repo): """ read the details about the remotenames stored in .hg/logexchange/ and yields a tuple (node, remotepath, name). It does not yields information about whether an entry yielded is branch or bookmark. To get that information, call the respective functions. """ for bmentry in readremotenamefile(repo, 'bookmarks'): yield bmentry for branchentry in readremotenamefile(repo, 'branches'): yield branchentry def writeremotenamefile(repo, remotepath, names, nametype): vfs = vfsmod.vfs(repo.vfs.join(remotenamedir)) f = vfs(nametype, 'w', atomictemp=True) # write the storage version info on top of file # version '0' represents the very initial version of the storage format f.write('0\n\n') olddata = set(readremotenamefile(repo, nametype)) # re-save the data from a different remote than this one. for node, oldpath, rname in sorted(olddata): if oldpath != remotepath: f.write('%s\0%s\0%s\n' % (node, oldpath, rname)) for name, node in sorted(names.iteritems()): if nametype == "branches": for n in node: f.write('%s\0%s\0%s\n' % (n, remotepath, name)) elif nametype == "bookmarks": if node: f.write('%s\0%s\0%s\n' % (node, remotepath, name)) f.close() def saveremotenames(repo, remotepath, branches=None, bookmarks=None): """ save remotenames i.e. remotebookmarks and remotebranches in their respective files under ".hg/logexchange/" directory. """ wlock = repo.wlock() try: if bookmarks: writeremotenamefile(repo, remotepath, bookmarks, 'bookmarks') if branches: writeremotenamefile(repo, remotepath, branches, 'branches') finally: wlock.release() def activepath(repo, remote): """returns remote path""" # is the remote a local peer local = remote.local() # determine the remote path from the repo, if possible; else just # use the string given to us rpath = remote if local: rpath = util.pconvert(remote._repo.root) elif not isinstance(remote, bytes): rpath = remote._url # represent the remotepath with user defined path name if exists for path, url in repo.ui.configitems('paths'): # remove auth info from user defined url noauthurl = util.removeauth(url) # Standardize on unix style paths, otherwise some {remotenames} end up # being an absolute path on Windows. url = util.pconvert(bytes(url)) noauthurl = util.pconvert(noauthurl) if url == rpath or noauthurl == rpath: rpath = path break return rpath def pullremotenames(localrepo, remoterepo): """ pulls bookmarks and branches information of the remote repo during a pull or clone operation. localrepo is our local repository remoterepo is the peer instance """ remotepath = activepath(localrepo, remoterepo) with remoterepo.commandexecutor() as e: bookmarks = e.callcommand('listkeys', { 'namespace': 'bookmarks', }).result() # on a push, we don't want to keep obsolete heads since # they won't show up as heads on the next pull, so we # remove them here otherwise we would require the user # to issue a pull to refresh the storage bmap = {} repo = localrepo.unfiltered() with remoterepo.commandexecutor() as e: branchmap = e.callcommand('branchmap', {}).result() for branch, nodes in branchmap.iteritems(): bmap[branch] = [] for node in nodes: if node in repo and not repo[node].obsolete(): bmap[branch].append(hex(node)) saveremotenames(localrepo, remotepath, bmap, bookmarks)