Mercurial > hg > mercurial-crew-with-dirclash
view mercurial/verify.py @ 5192:33015dac5df5
convert: fix mercurial_sink.putcommit
Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a
revision that touches no files, but this can break regular conversions
from some repositories:
- conceptually, since we're converting a repo, we should try to make
the new hg repo as similar as possible to the original repo - we
should create a new changeset, even if the original revision didn't
touch any files (maybe the commit message had some important bit);
- even if a "regular" revision that doesn't touch any file may seem
weird (and maybe even broken), it's completely legitimate for a merge
revision to not touch any file, and, if we just skip it, the
converted repo will end up with wrong history and possibly an extra
head.
As an example, say the crew and main hg repos are sync'ed. Somebody
sends an important patch to the mailing list. Matt quickly applies
and pushes it. But at the same time somebody also applies it to crew
and pushes it. Suppose the commit message ended up being a bit
different (say, there was a typo and somebody didn't fix it) or that
the date ended up being different (because of different patch-applying
scripts): the changeset hashes will be different, but the manifests
will be the same.
Since both changesets were pushed to public repos, it's hard to recall
them. If both are merged, the manifest from the resulting merge
revision will have the exact same contents as its parents - i.e. the
merge revision really doesn't touch any file at all.
To keep the file filtering stuff "working", the generic code was changed
to skip empty revisions if we're filtering the repo, fixing a bug in the
process (we want parents[0] instead of tip).
author | Alexis S. L. Carvalho <alexis@cecm.usp.br> |
---|---|
date | Fri, 17 Aug 2007 20:18:05 -0300 |
parents | 2da57dc04aa8 |
children | 29be4228303b |
line wrap: on
line source
# verify.py - repository integrity checking for Mercurial # # Copyright 2006, 2007 Matt Mackall <mpm@selenic.com> # # This software may be used and distributed according to the terms # of the GNU General Public License, incorporated herein by reference. from node import * from i18n import _ import revlog def verify(repo): lock = repo.lock() try: return _verify(repo) finally: del lock def _verify(repo): filelinkrevs = {} filenodes = {} changesets = revisions = files = 0 errors = [0] warnings = [0] neededmanifests = {} def err(msg): repo.ui.warn(msg + "\n") errors[0] += 1 def warn(msg): repo.ui.warn(msg + "\n") warnings[0] += 1 def checksize(obj, name): d = obj.checksize() if d[0]: err(_("%s data length off by %d bytes") % (name, d[0])) if d[1]: err(_("%s index contains %d extra bytes") % (name, d[1])) def checkversion(obj, name): if obj.version != revlog.REVLOGV0: if not revlogv1: warn(_("warning: `%s' uses revlog format 1") % name) elif revlogv1: warn(_("warning: `%s' uses revlog format 0") % name) revlogv1 = repo.changelog.version != revlog.REVLOGV0 if repo.ui.verbose or not revlogv1: repo.ui.status(_("repository uses revlog format %d\n") % (revlogv1 and 1 or 0)) seen = {} repo.ui.status(_("checking changesets\n")) checksize(repo.changelog, "changelog") for i in xrange(repo.changelog.count()): changesets += 1 n = repo.changelog.node(i) l = repo.changelog.linkrev(n) if l != i: err(_("incorrect link (%d) for changeset revision %d") %(l, i)) if n in seen: err(_("duplicate changeset at revision %d") % i) seen[n] = 1 for p in repo.changelog.parents(n): if p not in repo.changelog.nodemap: err(_("changeset %s has unknown parent %s") % (short(n), short(p))) try: changes = repo.changelog.read(n) except KeyboardInterrupt: repo.ui.warn(_("interrupted")) raise except Exception, inst: err(_("unpacking changeset %s: %s") % (short(n), inst)) continue neededmanifests[changes[0]] = n for f in changes[3]: filelinkrevs.setdefault(f, []).append(i) seen = {} repo.ui.status(_("checking manifests\n")) checkversion(repo.manifest, "manifest") checksize(repo.manifest, "manifest") for i in xrange(repo.manifest.count()): n = repo.manifest.node(i) l = repo.manifest.linkrev(n) if l < 0 or l >= repo.changelog.count(): err(_("bad manifest link (%d) at revision %d") % (l, i)) if n in neededmanifests: del neededmanifests[n] if n in seen: err(_("duplicate manifest at revision %d") % i) seen[n] = 1 for p in repo.manifest.parents(n): if p not in repo.manifest.nodemap: err(_("manifest %s has unknown parent %s") % (short(n), short(p))) try: for f, fn in repo.manifest.readdelta(n).iteritems(): filenodes.setdefault(f, {})[fn] = 1 except KeyboardInterrupt: repo.ui.warn(_("interrupted")) raise except Exception, inst: err(_("reading delta for manifest %s: %s") % (short(n), inst)) continue repo.ui.status(_("crosschecking files in changesets and manifests\n")) for m, c in neededmanifests.items(): err(_("Changeset %s refers to unknown manifest %s") % (short(m), short(c))) del neededmanifests for f in filenodes: if f not in filelinkrevs: err(_("file %s in manifest but not in changesets") % f) for f in filelinkrevs: if f not in filenodes: err(_("file %s in changeset but not in manifest") % f) repo.ui.status(_("checking files\n")) ff = filenodes.keys() ff.sort() for f in ff: if f == "/dev/null": continue files += 1 if not f: err(_("file without name in manifest %s") % short(n)) continue fl = repo.file(f) checkversion(fl, f) checksize(fl, f) nodes = {nullid: 1} seen = {} for i in xrange(fl.count()): revisions += 1 n = fl.node(i) if n in seen: err(_("%s: duplicate revision %d") % (f, i)) if n not in filenodes[f]: err(_("%s: %d:%s not in manifests") % (f, i, short(n))) else: del filenodes[f][n] flr = fl.linkrev(n) if flr not in filelinkrevs.get(f, []): err(_("%s:%s points to unexpected changeset %d") % (f, short(n), flr)) err(_("expecting one of %s" % filelinkrevs.get(f, []))) else: filelinkrevs[f].remove(flr) # verify contents try: t = fl.read(n) except KeyboardInterrupt: repo.ui.warn(_("interrupted")) raise except Exception, inst: err(_("unpacking file %s %s: %s") % (f, short(n), inst)) # verify parents (p1, p2) = fl.parents(n) if p1 not in nodes: err(_("file %s:%s unknown parent 1 %s") % (f, short(n), short(p1))) if p2 not in nodes: err(_("file %s:%s unknown parent 2 %s") % (f, short(n), short(p1))) nodes[n] = 1 # check renames try: rp = fl.renamed(n) if rp: fl2 = repo.file(rp[0]) rev = fl2.rev(rp[1]) except KeyboardInterrupt: repo.ui.warn(_("interrupted")) raise except Exception, inst: err(_("checking rename on file %s %s: %s") % (f, short(n), inst)) # cross-check for node in filenodes[f]: err(_("node %s in manifests not in %s") % (hex(node), f)) repo.ui.status(_("%d files, %d changesets, %d total revisions\n") % (files, changesets, revisions)) if warnings[0]: repo.ui.warn(_("%d warnings encountered!\n") % warnings[0]) if errors[0]: repo.ui.warn(_("%d integrity errors encountered!\n") % errors[0]) return 1