verify: check for orphaned dirlogs

We already report orphaned filelogs, i.e. revlogs for files that are
not mentioned in any manifest. This change adds checking for orphaned
dirlogs, i.e. revlogs that are not mentioned in any parent-directory
dirlog.

Note that, for fncachestore, only files mentioned in the fncache are
considered, there's not check for files in .hg/store/meta that are not
mentioned in the fncache. This is no different from the current
situation for filelogs.

mercurial/verify.py

@@ -1,408 +1,422
 # verify.py - repository integrity checking for Mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 
 from .i18n import _
 from .node import (
     nullid,
     short,
 )
 
 from . import (
     error,
     revlog,
     util,
 )
 
 def verify(repo):
     with repo.lock():
         return verifier(repo).verify()
 
 def _normpath(f):
     # under hg < 2.4, convert didn't sanitize paths properly, so a
     # converted repo may contain repeated slashes
     while '//' in f:
         f = f.replace('//', '/')
     return f
 
 def _validpath(repo, path):
     """Returns False if a path should NOT be treated as part of a repo.
 
     For all in-core cases, this returns True, as we have no way for a
     path to be mentioned in the history but not actually be
     relevant. For narrow clones, this is important because many
     filelogs will be missing, and changelog entries may mention
     modified files that are outside the narrow scope.
     """
     return True
 
 class verifier(object):
     def __init__(self, repo):
         self.repo = repo.unfiltered()
         self.ui = repo.ui
         self.badrevs = set()
         self.errors = 0
         self.warnings = 0
         self.havecl = len(repo.changelog) > 0
         self.havemf = len(repo.manifest) > 0
         self.revlogv1 = repo.changelog.version != revlog.REVLOGV0
         self.lrugetctx = util.lrucachefunc(repo.changectx)
         self.refersmf = False
         self.fncachewarned = False
 
     def warn(self, msg):
         self.ui.warn(msg + "\n")
         self.warnings += 1
 
     def err(self, linkrev, msg, filename=None):
         if linkrev is not None:
             self.badrevs.add(linkrev)
         else:
             linkrev = '?'
         msg = "%s: %s" % (linkrev, msg)
         if filename:
             msg = "%s@%s" % (filename, msg)
         self.ui.warn(" " + msg + "\n")
         self.errors += 1
 
     def exc(self, linkrev, msg, inst, filename=None):
         if not str(inst):
             inst = repr(inst)
         self.err(linkrev, "%s: %s" % (msg, inst), filename)
 
     def checklog(self, obj, name, linkrev):
         if not len(obj) and (self.havecl or self.havemf):
             self.err(linkrev, _("empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             self.err(None, _("data length off by %d bytes") % d[0], name)
         if d[1]:
             self.err(None, _("index contains %d extra bytes") % d[1], name)
 
         if obj.version != revlog.REVLOGV0:
             if not self.revlogv1:
                 self.warn(_("warning: `%s' uses revlog format 1") % name)
         elif self.revlogv1:
             self.warn(_("warning: `%s' uses revlog format 0") % name)
 
     def checkentry(self, obj, i, node, seen, linkrevs, f):
         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 = _("rev %d points to nonexistent changeset %d")
             else:
                 msg = _("rev %d points to unexpected changeset %d")
             self.err(None, msg % (i, lr), f)
             if linkrevs:
                 if f and len(linkrevs) > 1:
                     try:
                         # attempt to filter down to real linkrevs
                         linkrevs = [l for l in linkrevs
                                     if self.lrugetctx(l)[f].filenode() == node]
                     except Exception:
                         pass
                 self.warn(_(" (expected %s)") % " ".join(map(str, linkrevs)))
             lr = None # can't be trusted
 
         try:
             p1, p2 = obj.parents(node)
             if p1 not in seen and p1 != nullid:
                 self.err(lr, _("unknown parent 1 %s of %s") %
                     (short(p1), short(node)), f)
             if p2 not in seen and p2 != nullid:
                 self.err(lr, _("unknown parent 2 %s of %s") %
                     (short(p2), short(node)), f)
         except Exception as inst:
             self.exc(lr, _("checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             self.err(lr, _("duplicate revision %d (%d)") % (i, seen[node]), f)
         seen[node] = i
         return lr
 
     def verify(self):
         repo = self.repo
 
         ui = repo.ui
 
         if not repo.url().startswith('file:'):
             raise error.Abort(_("cannot verify bundle or remote repos"))
 
         if os.path.exists(repo.sjoin("journal")):
             ui.warn(_("abandoned transaction found - run hg recover\n"))
 
         if ui.verbose or not self.revlogv1:
             ui.status(_("repository uses revlog format %d\n") %
                            (self.revlogv1 and 1 or 0))
 
         mflinkrevs, filelinkrevs = self._verifychangelog()
 
         filenodes = self._verifymanifest(mflinkrevs)
         del mflinkrevs
 
         self._crosscheckfiles(filelinkrevs, filenodes)
 
         totalfiles, filerevisions = self._verifyfiles(filenodes, filelinkrevs)
 
         ui.status(_("%d files, %d changesets, %d total revisions\n") %
                        (totalfiles, len(repo.changelog), filerevisions))
         if self.warnings:
             ui.warn(_("%d warnings encountered!\n") % self.warnings)
         if self.fncachewarned:
             ui.warn(_('hint: run "hg debugrebuildfncache" to recover from '
                       'corrupt fncache\n'))
         if self.errors:
             ui.warn(_("%d integrity errors encountered!\n") % self.errors)
             if self.badrevs:
                 ui.warn(_("(first damaged changeset appears to be %d)\n")
                         % min(self.badrevs))
             return 1
 
     def _verifychangelog(self):
         ui = self.ui
         repo = self.repo
         cl = repo.changelog
 
         ui.status(_("checking changesets\n"))
         mflinkrevs = {}
         filelinkrevs = {}
         seen = {}
         self.checklog(cl, "changelog", 0)
         total = len(repo)
         for i in repo:
             ui.progress(_('checking'), i, total=total, unit=_('changesets'))
             n = cl.node(i)
             self.checkentry(cl, i, n, seen, [i], "changelog")
 
             try:
                 changes = cl.read(n)
                 if changes[0] != nullid:
                     mflinkrevs.setdefault(changes[0], []).append(i)
                     self.refersmf = True
                 for f in changes[3]:
                     if _validpath(repo, f):
                         filelinkrevs.setdefault(_normpath(f), []).append(i)
             except Exception as inst:
                 self.refersmf = True
                 self.exc(i, _("unpacking changeset %s") % short(n), inst)
         ui.progress(_('checking'), None)
         return mflinkrevs, filelinkrevs
 
-    def _verifymanifest(self, mflinkrevs, dir=""):
+    def _verifymanifest(self, mflinkrevs, dir="", storefiles=None):
         repo = self.repo
         ui = self.ui
         mf = self.repo.manifest.dirlog(dir)
 
         if not dir:
             self.ui.status(_("checking manifests\n"))
 
         filenodes = {}
         subdirnodes = {}
         seen = {}
         label = "manifest"
         if dir:
             label = dir
+            revlogfiles = mf.files()
+            storefiles.difference_update(revlogfiles)
         if self.refersmf:
             # Do not check manifest if there are only changelog entries with
             # null manifests.
             self.checklog(mf, label, 0)
         total = len(mf)
         for i in mf:
             if not dir:
                 ui.progress(_('checking'), i, total=total, unit=_('manifests'))
             n = mf.node(i)
             lr = self.checkentry(mf, i, n, seen, mflinkrevs.get(n, []), label)
             if n in mflinkrevs:
                 del mflinkrevs[n]
             elif dir:
                 self.err(lr, _("%s not in parent-directory manifest") %
                          short(n), label)
             else:
                 self.err(lr, _("%s not in changesets") % short(n), label)
 
             try:
                 for f, fn, fl in mf.readshallowdelta(n).iterentries():
                     if not f:
                         self.err(lr, _("entry without name in manifest"))
                     elif f == "/dev/null":  # ignore this in very old repos
                         continue
                     fullpath = dir + _normpath(f)
                     if not _validpath(repo, fullpath):
                         continue
                     if fl == 't':
                         subdirnodes.setdefault(fullpath + '/', {}).setdefault(
                             fn, []).append(lr)
                     else:
                         filenodes.setdefault(fullpath, {}).setdefault(fn, lr)
             except Exception as inst:
                 self.exc(lr, _("reading delta %s") % short(n), inst, label)
         if not dir:
             ui.progress(_('checking'), None)
 
         if self.havemf:
             for c, m in sorted([(c, m) for m in mflinkrevs
                         for c in mflinkrevs[m]]):
                 if dir:
                     self.err(c, _("parent-directory manifest refers to unknown "
                                   "revision %s") % short(m), label)
                 else:
                     self.err(c, _("changeset refers to unknown revision %s") %
                              short(m), label)
 
         if not dir and subdirnodes:
             self.ui.status(_("checking directory manifests\n"))
+            storefiles = set()
+            revlogv1 = self.revlogv1
+            for f, f2, size in repo.store.datafiles():
+                if not f:
+                    self.err(None, _("cannot decode filename '%s'") % f2)
+                elif (size > 0 or not revlogv1) and f.startswith('meta/'):
+                    storefiles.add(_normpath(f))
+
         for subdir, linkrevs in subdirnodes.iteritems():
-            subdirfilenodes = self._verifymanifest(linkrevs, subdir)
+            subdirfilenodes = self._verifymanifest(linkrevs, subdir, storefiles)
             for f, onefilenodes in subdirfilenodes.iteritems():
                 filenodes.setdefault(f, {}).update(onefilenodes)
 
+        if not dir and subdirnodes:
+            for f in sorted(storefiles):
+                self.warn(_("warning: orphan revlog '%s'") % f)
+
         return filenodes
 
     def _crosscheckfiles(self, filelinkrevs, filenodes):
         repo = self.repo
         ui = self.ui
         ui.status(_("crosschecking files in changesets and manifests\n"))
 
         total = len(filelinkrevs) + len(filenodes)
         count = 0
         if self.havemf:
             for f in sorted(filelinkrevs):
                 count += 1
                 ui.progress(_('crosschecking'), count, total=total)
                 if f not in filenodes:
                     lr = filelinkrevs[f][0]
                     self.err(lr, _("in changeset but not in manifest"), f)
 
         if self.havecl:
             for f in sorted(filenodes):
                 count += 1
                 ui.progress(_('crosschecking'), count, total=total)
                 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, _("in manifest but not in changeset"), f)
 
         ui.progress(_('crosschecking'), None)
 
     def _verifyfiles(self, filenodes, filelinkrevs):
         repo = self.repo
         ui = self.ui
         lrugetctx = self.lrugetctx
         revlogv1 = self.revlogv1
         havemf = self.havemf
         ui.status(_("checking files\n"))
 
         storefiles = set()
         for f, f2, size in repo.store.datafiles():
             if not f:
                 self.err(None, _("cannot decode filename '%s'") % f2)
             elif (size > 0 or not revlogv1) and f.startswith('data/'):
                 storefiles.add(_normpath(f))
 
         files = sorted(set(filenodes) | set(filelinkrevs))
         total = len(files)
         revisions = 0
         for i, f in enumerate(files):
             ui.progress(_('checking'), i, item=f, total=total)
             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.RevlogError as e:
                 self.err(lr, _("broken revlog! (%s)") % e, f)
                 continue
 
             for ff in fl.files():
                 try:
                     storefiles.remove(ff)
                 except KeyError:
                     self.warn(_(" warning: revlog '%s' not in fncache!") % ff)
                     self.fncachewarned = True
 
             self.checklog(fl, f, lr)
             seen = {}
             rp = None
             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, _("%s not in manifests") % (short(n)), f)
                     else:
                         del filenodes[f][n]
 
                 # verify contents
                 try:
                     l = len(fl.read(n))
                     rp = fl.renamed(n)
                     if l != fl.size(i):
                         if len(fl.revision(n)) != fl.size(i):
                             self.err(lr, _("unpacked size is %s, %s expected") %
                                      (l, fl.size(i)), f)
                 except error.CensoredNodeError:
                     # experimental config: censor.policy
                     if ui.config("censor", "policy", "abort") == "abort":
                         self.err(lr, _("censored file data"), f)
                 except Exception as inst:
                     self.exc(lr, _("unpacking %s") % short(n), inst, f)
 
                 # check renames
                 try:
                     if rp:
                         if lr is not None and ui.verbose:
                             ctx = lrugetctx(lr)
                             found = False
                             for pctx in ctx.parents():
                                 if rp[0] in pctx:
                                     found = True
                                     break
                             if not found:
                                 self.warn(_("warning: copy source of '%s' not"
                                             " in parents of %s") % (f, ctx))
                         fl2 = repo.file(rp[0])
                         if not len(fl2):
                             self.err(lr, _("empty or missing copy source "
                                      "revlog %s:%s") % (rp[0], short(rp[1])), f)
                         elif rp[1] == nullid:
                             ui.note(_("warning: %s@%s: copy source"
                                       " revision is nullid %s:%s\n")
                                 % (f, lr, rp[0], short(rp[1])))
                         else:
                             fl2.rev(rp[1])
                 except Exception as inst:
                     self.exc(lr, _("checking rename of %s") % short(n), inst, f)
 
             # cross-check
             if f in filenodes:
                 fns = [(lr, n) for n, lr in filenodes[f].iteritems()]
                 for lr, node in sorted(fns):
                     self.err(lr, _("manifest refers to unknown revision %s") %
                              short(node), f)
         ui.progress(_('checking'), None)
 
-        for f in storefiles:
+        for f in sorted(storefiles):
             self.warn(_("warning: orphan revlog '%s'") % f)
 
         return len(files), revisions

tests/test-treemanifest.t

@@ -1,724 +1,731
 #require killdaemons
 
   $ cat << EOF >> $HGRCPATH
   > [format]
   > usegeneraldelta=yes
   > [ui]
   > ssh=python "$TESTDIR/dummyssh"
   > EOF
 
 Set up repo
 
   $ hg --config experimental.treemanifest=True init repo
   $ cd repo
 
 Requirements get set on init
 
   $ grep treemanifest .hg/requires
   treemanifest
 
 Without directories, looks like any other repo
 
   $ echo 0 > a
   $ echo 0 > b
   $ hg ci -Aqm initial
   $ hg debugdata -m 0
   a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
 
 Submanifest is stored in separate revlog
 
   $ mkdir dir1
   $ echo 1 > dir1/a
   $ echo 1 > dir1/b
   $ echo 1 > e
   $ hg ci -Aqm 'add dir1'
   $ hg debugdata -m 1
   a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
   dir1\x008b3ffd73f901e83304c83d33132c8e774ceac44et (esc)
   e\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   $ hg debugdata --dir dir1 0
   a\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
   b\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
 
 Can add nested directories
 
   $ mkdir dir1/dir1
   $ echo 2 > dir1/dir1/a
   $ echo 2 > dir1/dir1/b
   $ mkdir dir1/dir2
   $ echo 2 > dir1/dir2/a
   $ echo 2 > dir1/dir2/b
   $ hg ci -Aqm 'add dir1/dir1'
   $ hg files -r .
   a
   b
   dir1/a (glob)
   dir1/b (glob)
   dir1/dir1/a (glob)
   dir1/dir1/b (glob)
   dir1/dir2/a (glob)
   dir1/dir2/b (glob)
   e
 
 Revision is not created for unchanged directory
 
   $ mkdir dir2
   $ echo 3 > dir2/a
   $ hg add dir2
   adding dir2/a (glob)
   $ hg debugindex --dir dir1 > before
   $ hg ci -qm 'add dir2'
   $ hg debugindex --dir dir1 > after
   $ diff before after
   $ rm before after
 
 Removing directory does not create an revlog entry
 
   $ hg rm dir1/dir1
   removing dir1/dir1/a (glob)
   removing dir1/dir1/b (glob)
   $ hg debugindex --dir dir1/dir1 > before
   $ hg ci -qm 'remove dir1/dir1'
   $ hg debugindex --dir dir1/dir1 > after
   $ diff before after
   $ rm before after
 
 Check that hg files (calls treemanifest.walk()) works
 without loading all directory revlogs
 
   $ hg co 'desc("add dir2")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ mv .hg/store/meta/dir2 .hg/store/meta/dir2-backup
   $ hg files -r . dir1
   dir1/a (glob)
   dir1/b (glob)
   dir1/dir1/a (glob)
   dir1/dir1/b (glob)
   dir1/dir2/a (glob)
   dir1/dir2/b (glob)
 
 Check that status between revisions works (calls treemanifest.matches())
 without loading all directory revlogs
 
   $ hg status --rev 'desc("add dir1")' --rev . dir1
   A dir1/dir1/a
   A dir1/dir1/b
   A dir1/dir2/a
   A dir1/dir2/b
   $ mv .hg/store/meta/dir2-backup .hg/store/meta/dir2
 
 Merge creates 2-parent revision of directory revlog
 
   $ echo 5 > dir1/a
   $ hg ci -Aqm 'modify dir1/a'
   $ hg co '.^'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 6 > dir1/b
   $ hg ci -Aqm 'modify dir1/b'
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'conflict-free merge involving dir1/'
   $ cat dir1/a
   5
   $ cat dir1/b
   6
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      54     -1       1 8b3ffd73f901 000000000000 000000000000
        1        54      68      0       2 68e9d057c5a8 8b3ffd73f901 000000000000
        2       122      12      1       4 4698198d2624 68e9d057c5a8 000000000000
        3       134      55      1       5 44844058ccce 68e9d057c5a8 000000000000
        4       189      55      1       6 bf3d9b744927 68e9d057c5a8 000000000000
        5       244      55      4       7 dde7c0af2a03 bf3d9b744927 44844058ccce
 
 Merge keeping directory from parent 1 does not create revlog entry. (Note that
 dir1's manifest does change, but only because dir1/a's filelog changes.)
 
   $ hg co 'desc("add dir2")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 8 > dir2/a
   $ hg ci -m 'modify dir2/a'
   created new head
 
   $ hg debugindex --dir dir2 > before
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg revert -r 'desc("modify dir2/a")' .
   reverting dir1/a (glob)
   $ hg ci -m 'merge, keeping parent 1'
   $ hg debugindex --dir dir2 > after
   $ diff before after
   $ rm before after
 
 Merge keeping directory from parent 2 does not create revlog entry. (Note that
 dir2's manifest does change, but only because dir2/a's filelog changes.)
 
   $ hg co 'desc("modify dir2/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg debugindex --dir dir1 > before
   $ hg merge 'desc("modify dir1/a")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg revert -r 'desc("modify dir1/a")' .
   reverting dir2/a (glob)
   $ hg ci -m 'merge, keeping parent 2'
   created new head
   $ hg debugindex --dir dir1 > after
   $ diff before after
   $ rm before after
 
 Create flat source repo for tests with mixed flat/tree manifests
 
   $ cd ..
   $ hg init repo-flat
   $ cd repo-flat
 
 Create a few commits with flat manifest
 
   $ echo 0 > a
   $ echo 0 > b
   $ echo 0 > e
   $ for d in dir1 dir1/dir1 dir1/dir2 dir2
   > do
   >   mkdir $d
   >   echo 0 > $d/a
   >   echo 0 > $d/b
   > done
   $ hg ci -Aqm initial
 
   $ echo 1 > a
   $ echo 1 > dir1/a
   $ echo 1 > dir1/dir1/a
   $ hg ci -Aqm 'modify on branch 1'
 
   $ hg co 0
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 2 > b
   $ echo 2 > dir1/b
   $ echo 2 > dir1/dir1/b
   $ hg ci -Aqm 'modify on branch 2'
 
   $ hg merge 1
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'merge of flat manifests to new flat manifest'
 
   $ hg serve -p $HGPORT -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
 
 Create clone with tree manifests enabled
 
   $ cd ..
   $ hg clone --config experimental.treemanifest=1 \
   >   http://localhost:$HGPORT repo-mixed -r 1
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 14 changes to 11 files
   updating to branch default
   11 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd repo-mixed
   $ test -d .hg/store/meta
   [1]
   $ grep treemanifest .hg/requires
   treemanifest
 
 Should be possible to push updates from flat to tree manifest repo
 
   $ hg -R ../repo-flat push ssh://user@dummy/repo-mixed
   pushing to ssh://user@dummy/repo-mixed
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 2 changesets with 3 changes to 3 files
 
 Commit should store revlog per directory
 
   $ hg co 1
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo 3 > a
   $ echo 3 > dir1/a
   $ echo 3 > dir1/dir1/a
   $ hg ci -m 'first tree'
   created new head
   $ find .hg/store/meta | sort
   .hg/store/meta
   .hg/store/meta/dir1
   .hg/store/meta/dir1/00manifest.i
   .hg/store/meta/dir1/dir1
   .hg/store/meta/dir1/dir1/00manifest.i
   .hg/store/meta/dir1/dir2
   .hg/store/meta/dir1/dir2/00manifest.i
   .hg/store/meta/dir2
   .hg/store/meta/dir2/00manifest.i
 
 Merge of two trees
 
   $ hg co 2
   6 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 1
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'merge of flat manifests to new tree manifest'
   created new head
   $ hg diff -r 3
 
 Parent of tree root manifest should be flat manifest, and two for merge
 
   $ hg debugindex -m
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0      80     -1       0 40536115ed9e 000000000000 000000000000
        1        80      83      0       1 f3376063c255 40536115ed9e 000000000000
        2       163      89      0       2 5d9b9da231a2 40536115ed9e 000000000000
        3       252      83      2       3 d17d663cbd8a 5d9b9da231a2 f3376063c255
        4       335     124      1       4 51e32a8c60ee f3376063c255 000000000000
        5       459     126      2       5 cc5baa78b230 5d9b9da231a2 f3376063c255
 
 
 Status across flat/tree boundary should work
 
   $ hg status --rev '.^' --rev .
   M a
   M dir1/a
   M dir1/dir1/a
 
 
 Turning off treemanifest config has no effect
 
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0     127     -1       4 064927a0648a 000000000000 000000000000
        1       127     111      0       5 25ecb8cb8618 000000000000 000000000000
   $ echo 2 > dir1/a
   $ hg --config experimental.treemanifest=False ci -qm 'modify dir1/a'
   $ hg debugindex --dir dir1
      rev    offset  length  delta linkrev nodeid       p1           p2
        0         0     127     -1       4 064927a0648a 000000000000 000000000000
        1       127     111      0       5 25ecb8cb8618 000000000000 000000000000
        2       238      55      1       6 5b16163a30c6 25ecb8cb8618 000000000000
 
 Stripping and recovering changes should work
 
   $ hg st --change tip
   M dir1/a
   $ hg --config extensions.strip= strip tip
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   saved backup bundle to $TESTTMP/repo-mixed/.hg/strip-backup/51cfd7b1e13b-78a2f3ed-backup.hg (glob)
   $ hg unbundle -q .hg/strip-backup/*
   $ hg st --change tip
   M dir1/a
 
 Shelving and unshelving should work
 
   $ echo foo >> dir1/a
   $ hg --config extensions.shelve= shelve
   shelved as default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg --config extensions.shelve= unshelve
   unshelving change 'default'
   $ hg diff --nodates
   diff -r 708a273da119 dir1/a
   --- a/dir1/a
   +++ b/dir1/a
   @@ -1,1 +1,2 @@
    1
   +foo
 
 Pushing from treemanifest repo to an empty repo makes that a treemanifest repo
 
   $ cd ..
   $ hg init empty-repo
   $ cat << EOF >> empty-repo/.hg/hgrc
   > [experimental]
   > changegroup3=yes
   > EOF
   $ grep treemanifest empty-repo/.hg/requires
   [1]
   $ hg push -R repo -r 0 empty-repo
   pushing to empty-repo
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 2 changes to 2 files
   $ grep treemanifest empty-repo/.hg/requires
   treemanifest
 
 Pushing to an empty repo works
 
   $ hg --config experimental.treemanifest=1 init clone
   $ grep treemanifest clone/.hg/requires
   treemanifest
   $ hg push -R repo clone
   pushing to clone
   searching for changes
   adding changesets
   adding manifests
   adding file changes
   added 11 changesets with 15 changes to 10 files (+3 heads)
   $ grep treemanifest clone/.hg/requires
   treemanifest
 
 Create deeper repo with tree manifests.
 
   $ hg --config experimental.treemanifest=True init deeprepo
   $ cd deeprepo
 
   $ mkdir .A
   $ mkdir b
   $ mkdir b/bar
   $ mkdir b/bar/orange
   $ mkdir b/bar/orange/fly
   $ mkdir b/foo
   $ mkdir b/foo/apple
   $ mkdir b/foo/apple/bees
 
   $ touch .A/one.txt
   $ touch .A/two.txt
   $ touch b/bar/fruits.txt
   $ touch b/bar/orange/fly/gnat.py
   $ touch b/bar/orange/fly/housefly.txt
   $ touch b/foo/apple/bees/flower.py
   $ touch c.txt
   $ touch d.py
 
   $ hg ci -Aqm 'initial'
 
 We'll see that visitdir works by removing some treemanifest revlogs and running
 the files command with various parameters.
 
 Test files from the root.
 
   $ hg files -r .
   .A/one.txt (glob)
   .A/two.txt (glob)
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   b/foo/apple/bees/flower.py (glob)
   c.txt
   d.py
 
 Excludes with a glob should not exclude everything from the glob's root
 
   $ hg files -r . -X 'b/fo?' b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store .hg/store-copy
 
 Test files for a subdirectory.
 
   $ rm -r .hg/store/meta/~2e_a
   $ hg files -r . b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   b/foo/apple/bees/flower.py (glob)
   $ cp -r .hg/store-copy/* .hg/store
 
 Test files with just includes and excludes.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/bar/orange/fly
   $ rm -r .hg/store/meta/b/foo/apple/bees
   $ hg files -r . -I path:b/bar -X path:b/bar/orange/fly -I path:b/foo -X path:b/foo/apple/bees
   b/bar/fruits.txt (glob)
   $ cp -r .hg/store-copy/* .hg/store
 
 Test files for a subdirectory, excluding a directory within it.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ hg files -r . -X path:b/foo b
   b/bar/fruits.txt (glob)
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store-copy/* .hg/store
 
 Test files for a sub directory, including only a directory within it, and
 including an unrelated directory.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ hg files -r . -I path:b/bar/orange -I path:a b
   b/bar/orange/fly/gnat.py (glob)
   b/bar/orange/fly/housefly.txt (glob)
   $ cp -r .hg/store-copy/* .hg/store
 
 Test files for a pattern, including a directory, and excluding a directory
 within that.
 
   $ rm -r .hg/store/meta/~2e_a
   $ rm -r .hg/store/meta/b/foo
   $ rm -r .hg/store/meta/b/bar/orange
   $ hg files -r . glob:**.txt -I path:b/bar -X path:b/bar/orange
   b/bar/fruits.txt (glob)
   $ cp -r .hg/store-copy/* .hg/store
 
 Add some more changes to the deep repo
   $ echo narf >> b/bar/fruits.txt
   $ hg ci -m narf
   $ echo troz >> b/bar/orange/fly/gnat.py
   $ hg ci -m troz
 
 Verify works
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Dirlogs are included in fncache
   $ grep meta/.A/00manifest.i .hg/store/fncache
   meta/.A/00manifest.i
 
 Rebuilt fncache includes dirlogs
   $ rm .hg/store/fncache
   $ hg debugrebuildfncache
   adding data/.A/one.txt.i
   adding data/.A/two.txt.i
   adding data/b/bar/fruits.txt.i
   adding data/b/bar/orange/fly/gnat.py.i
   adding data/b/bar/orange/fly/housefly.txt.i
   adding data/b/foo/apple/bees/flower.py.i
   adding data/c.txt.i
   adding data/d.py.i
   adding meta/.A/00manifest.i
   adding meta/b/00manifest.i
   adding meta/b/bar/00manifest.i
   adding meta/b/bar/orange/00manifest.i
   adding meta/b/bar/orange/fly/00manifest.i
   adding meta/b/foo/00manifest.i
   adding meta/b/foo/apple/00manifest.i
   adding meta/b/foo/apple/bees/00manifest.i
   16 items added, 0 removed from fncache
 
 Finish first server
   $ killdaemons.py
 
 Back up the recently added revlogs
   $ cp -r .hg/store .hg/store-newcopy
 
 Verify reports missing dirlog
   $ rm .hg/store/meta/b/00manifest.*
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
    0: empty or missing b/
    b/@0: parent-directory manifest refers to unknown revision 67688a370455
    b/@1: parent-directory manifest refers to unknown revision f38e85d334c5
    b/@2: parent-directory manifest refers to unknown revision 99c9792fd4b0
+  warning: orphan revlog 'meta/b/bar/00manifest.i'
+  warning: orphan revlog 'meta/b/bar/orange/00manifest.i'
+  warning: orphan revlog 'meta/b/bar/orange/fly/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/apple/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/apple/bees/00manifest.i'
   crosschecking files in changesets and manifests
    b/bar/fruits.txt@0: in changeset but not in manifest
    b/bar/orange/fly/gnat.py@0: in changeset but not in manifest
    b/bar/orange/fly/housefly.txt@0: in changeset but not in manifest
    b/foo/apple/bees/flower.py@0: in changeset but not in manifest
   checking files
   8 files, 3 changesets, 10 total revisions
+  6 warnings encountered!
   8 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]
   $ cp -rT .hg/store-newcopy .hg/store
 
 Verify reports missing dirlog entry
   $ mv -f .hg/store-copy/meta/b/00manifest.* .hg/store/meta/b/
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
    b/@1: parent-directory manifest refers to unknown revision f38e85d334c5
    b/@2: parent-directory manifest refers to unknown revision 99c9792fd4b0
    b/bar/@?: rev 1 points to unexpected changeset 1
    b/bar/@?: 5e03c4ee5e4a not in parent-directory manifest
    b/bar/@?: rev 2 points to unexpected changeset 2
    b/bar/@?: 1b16940d66d6 not in parent-directory manifest
    b/bar/orange/@?: rev 1 points to unexpected changeset 2
    (expected None)
    b/bar/orange/fly/@?: rev 1 points to unexpected changeset 2
    (expected None)
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
   2 warnings encountered!
   8 integrity errors encountered!
   (first damaged changeset appears to be 1)
   [1]
   $ cp -rT .hg/store-newcopy .hg/store
 
 Test cloning a treemanifest repo over http.
   $ hg serve -p $HGPORT -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
 We can clone even with the knob turned off and we'll get a treemanifest repo.
   $ hg clone --config experimental.treemanifest=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deepclone
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
 No server errors.
   $ cat deeprepo/errors.log
 requires got updated to include treemanifest
   $ cat deepclone/.hg/requires | grep treemanifest
   treemanifest
 Tree manifest revlogs exist.
   $ find deepclone/.hg/store/meta | sort
   deepclone/.hg/store/meta
   deepclone/.hg/store/meta/b
   deepclone/.hg/store/meta/b/00manifest.i
   deepclone/.hg/store/meta/b/bar
   deepclone/.hg/store/meta/b/bar/00manifest.i
   deepclone/.hg/store/meta/b/bar/orange
   deepclone/.hg/store/meta/b/bar/orange/00manifest.i
   deepclone/.hg/store/meta/b/bar/orange/fly
   deepclone/.hg/store/meta/b/bar/orange/fly/00manifest.i
   deepclone/.hg/store/meta/b/foo
   deepclone/.hg/store/meta/b/foo/00manifest.i
   deepclone/.hg/store/meta/b/foo/apple
   deepclone/.hg/store/meta/b/foo/apple/00manifest.i
   deepclone/.hg/store/meta/b/foo/apple/bees
   deepclone/.hg/store/meta/b/foo/apple/bees/00manifest.i
   deepclone/.hg/store/meta/~2e_a
   deepclone/.hg/store/meta/~2e_a/00manifest.i
 Verify passes.
   $ cd deepclone
   $ hg verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
   $ cd ..
 
 Create clones using old repo formats to use in later tests
   $ hg clone --config format.usestore=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deeprepo-basicstore
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd deeprepo-basicstore
   $ grep store .hg/requires
   [1]
   $ hg serve -p $HGPORT1 -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
   $ hg clone --config format.usefncache=False \
   >   --config experimental.changegroup3=True \
   >   http://localhost:$HGPORT deeprepo-encodedstore
   requesting all changes
   adding changesets
   adding manifests
   adding file changes
   added 3 changesets with 10 changes to 8 files
   updating to branch default
   8 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd deeprepo-encodedstore
   $ grep fncache .hg/requires
   [1]
   $ hg serve -p $HGPORT2 -d --pid-file=hg.pid --errorlog=errors.log
   $ cat hg.pid >> $DAEMON_PIDS
   $ cd ..
 
 Local clone with basicstore
   $ hg clone -U deeprepo-basicstore local-clone-basicstore
   $ hg -R local-clone-basicstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Local clone with encodedstore
   $ hg clone -U deeprepo-encodedstore local-clone-encodedstore
   $ hg -R local-clone-encodedstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Local clone with fncachestore
   $ hg clone -U deeprepo local-clone-fncachestore
   $ hg -R local-clone-fncachestore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with basicstore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT1 stream-clone-basicstore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-basicstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with encodedstore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT2 stream-clone-encodedstore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-encodedstore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Stream clone with fncachestore
   $ hg clone --config experimental.changegroup3=True --uncompressed -U \
   >   http://localhost:$HGPORT stream-clone-fncachestore
   streaming all changes
   18 files to transfer, * of data (glob)
   transferred * in * seconds (*) (glob)
   searching for changes
   no changes found
   $ hg -R stream-clone-fncachestore verify
   checking changesets
   checking manifests
   checking directory manifests
   crosschecking files in changesets and manifests
   checking files
   8 files, 3 changesets, 10 total revisions
 
 Packed bundle
   $ hg -R deeprepo debugcreatestreamclonebundle repo-packed.hg
   writing 3349 bytes for 18 files
   bundle requirements: generaldelta, revlogv1, treemanifest
   $ hg debugbundle --spec repo-packed.hg
   none-packed1;requirements%3Dgeneraldelta%2Crevlogv1%2Ctreemanifest