merge with stable

tests/revlog-formatv0.py

@@ -0,0 +1,60 b''
+#!/usr/bin/env python
+# Copyright 2010 Intevation GmbH
+# Author(s):
+# Thomas Arendsen Hein <[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.
+
+"""Create a Mercurial repository in revlog format 0
+
+changeset:   0:a1ef0b125355
+tag:         tip
+user:        user
+date:        Thu Jan 01 00:00:00 1970 +0000
+files:       empty
+description:
+empty file
+"""
+
+import os, sys
+
+files = [
+    ('formatv0/.hg/00changelog.i',
+     '000000000000004400000000000000000000000000000000000000'
+     '000000000000000000000000000000000000000000000000000000'
+     '0000a1ef0b125355d27765928be600cfe85784284ab3'),
+    ('formatv0/.hg/00changelog.d',
+     '756163613935613961356635353036303562366138343738336237'
+     '61623536363738616436356635380a757365720a3020300a656d70'
+     '74790a0a656d7074792066696c65'),
+    ('formatv0/.hg/00manifest.i',
+     '000000000000003000000000000000000000000000000000000000'
+     '000000000000000000000000000000000000000000000000000000'
+     '0000aca95a9a5f550605b6a84783b7ab56678ad65f58'),
+    ('formatv0/.hg/00manifest.d',
+     '75656d707479006238306465356431333837353835343163356630'
+     '35323635616431343461623966613836643164620a'),
+    ('formatv0/.hg/data/empty.i',
+     '000000000000000000000000000000000000000000000000000000'
+     '000000000000000000000000000000000000000000000000000000'
+     '0000b80de5d138758541c5f05265ad144ab9fa86d1db'),
+    ('formatv0/.hg/data/empty.d',
+     ''),
+]
+
+def makedirs(name):
+    """recursive directory creation"""
+    parent = os.path.dirname(name)
+    if parent:
+        makedirs(parent)
+    os.mkdir(name)
+
+makedirs(os.path.join(*'formatv0/.hg/data'.split('/')))
+
+for name, data in files:
+    f = open(name, 'wb')
+    f.write(data.decode('hex'))
+    f.close()
+
+sys.exit(0)

mercurial/verify.py

@@ -1,301 +1,301 b''
 # 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 node import nullid, short
 from i18n import _
 import os
 import revlog, util, error
 
 def verify(repo):
     lock = repo.lock()
     try:
         return _verify(repo)
     finally:
         lock.release()
 
 def _verify(repo):
     mflinkrevs = {}
     filelinkrevs = {}
     filenodes = {}
     revisions = 0
     badrevs = set()
     errors = [0]
     warnings = [0]
     ui = repo.ui
     cl = repo.changelog
     mf = repo.manifest
     lrugetctx = util.lrucachefunc(repo.changectx)
 
     if not repo.cancopy():
         raise util.Abort(_("cannot verify bundle or remote repos"))
 
     def err(linkrev, msg, filename=None):
         if linkrev != None:
             badrevs.add(linkrev)
         else:
             linkrev = '?'
         msg = "%s: %s" % (linkrev, msg)
         if filename:
             msg = "%s@%s" % (filename, msg)
         ui.warn(" " + msg + "\n")
         errors[0] += 1
 
     def exc(linkrev, msg, inst, filename=None):
         if isinstance(inst, KeyboardInterrupt):
             ui.warn(_("interrupted"))
             raise
         if not str(inst):
             inst = repr(inst)
         err(linkrev, "%s: %s" % (msg, inst), filename)
 
     def warn(msg):
         ui.warn(msg + "\n")
         warnings[0] += 1
 
     def checklog(obj, name, linkrev):
         if not len(obj) and (havecl or havemf):
             err(linkrev, _("empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             err(None, _("data length off by %d bytes") % d[0], name)
         if d[1]:
             err(None, _("index contains %d extra bytes") % d[1], 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)
 
     def checkentry(obj, i, node, seen, linkrevs, f):
         lr = obj.linkrev(obj.rev(node))
         if lr < 0 or (havecl and lr not in linkrevs):
             if lr < 0 or lr >= len(cl):
                 msg = _("rev %d points to nonexistent changeset %d")
             else:
                 msg = _("rev %d points to unexpected changeset %d")
             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 lrugetctx(l)[f].filenode() == node]
                     except:
                         pass
                 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:
                 err(lr, _("unknown parent 1 %s of %s") %
                     (short(p1), short(n)), f)
             if p2 not in seen and p2 != nullid:
                 err(lr, _("unknown parent 2 %s of %s") %
                     (short(p2), short(p1)), f)
         except Exception, inst:
             exc(lr, _("checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             err(lr, _("duplicate revision %d (%d)") % (i, seen[n]), f)
         seen[n] = i
         return lr
 
     if os.path.exists(repo.sjoin("journal")):
         ui.warn(_("abandoned transaction found - run hg recover\n"))
 
     revlogv1 = cl.version != revlog.REVLOGV0
     if ui.verbose or not revlogv1:
         ui.status(_("repository uses revlog format %d\n") %
                        (revlogv1 and 1 or 0))
 
     havecl = len(cl) > 0
     havemf = len(mf) > 0
 
     ui.status(_("checking changesets\n"))
     seen = {}
     checklog(cl, "changelog", 0)
     total = len(repo)
     for i in repo:
         ui.progress(_('changesets'), i, total=total)
         n = cl.node(i)
         checkentry(cl, i, n, seen, [i], "changelog")
 
         try:
             changes = cl.read(n)
             mflinkrevs.setdefault(changes[0], []).append(i)
             for f in changes[3]:
                 filelinkrevs.setdefault(f, []).append(i)
         except Exception, inst:
             exc(i, _("unpacking changeset %s") % short(n), inst)
     ui.progress(_('changesets'), None)
 
     ui.status(_("checking manifests\n"))
     seen = {}
     checklog(mf, "manifest", 0)
     total = len(mf)
     for i in mf:
         ui.progress(_('manifests'), i, total=total)
         n = mf.node(i)
         lr = checkentry(mf, i, n, seen, mflinkrevs.get(n, []), "manifest")
         if n in mflinkrevs:
             del mflinkrevs[n]
         else:
             err(lr, _("%s not in changesets") % short(n), "manifest")
 
         try:
             for f, fn in mf.readdelta(n).iteritems():
                 if not f:
                     err(lr, _("file without name in manifest"))
                 elif f != "/dev/null":
                     filenodes.setdefault(f, {}).setdefault(fn, lr)
         except Exception, inst:
             exc(lr, _("reading manifest delta %s") % short(n), inst)
     ui.progress(_('manifests'), None)
 
     ui.status(_("crosschecking files in changesets and manifests\n"))
 
     total = len(mflinkrevs) + len(filelinkrevs) + len(filenodes)
     count = 0
     if havemf:
         for c, m in sorted([(c, m) for m in mflinkrevs
                             for c in mflinkrevs[m]]):
             count += 1
             ui.progress(_('crosschecking'), count, total=total)
             err(c, _("changeset refers to unknown manifest %s") % short(m))
         mflinkrevs = None # del is bad here due to scope issues
 
         for f in sorted(filelinkrevs):
             count += 1
             ui.progress(_('crosschecking'), count, total=total)
             if f not in filenodes:
                 lr = filelinkrevs[f][0]
                 err(lr, _("in changeset but not in manifest"), f)
 
     if 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:
                     lr = None
                 err(lr, _("in manifest but not in changeset"), f)
 
     ui.progress(_('crosschecking'), None)
 
     ui.status(_("checking files\n"))
 
     storefiles = set()
     for f, f2, size in repo.store.datafiles():
         if not f:
             err(None, _("cannot decode filename '%s'") % f2)
-        elif size > 0:
+        elif size > 0 or not revlogv1:
             storefiles.add(f)
 
     files = sorted(set(filenodes) | set(filelinkrevs))
     total = len(files)
     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, e:
             err(lr, _("broken revlog! (%s)") % e, f)
             continue
 
         for ff in fl.files():
             try:
                 storefiles.remove(ff)
             except KeyError:
                 err(lr, _("missing revlog!"), ff)
 
         checklog(fl, f, lr)
         seen = {}
         rp = None
         for i in fl:
             revisions += 1
             n = fl.node(i)
             lr = checkentry(fl, i, n, seen, linkrevs, f)
             if f in filenodes:
                 if havemf and n not in filenodes[f]:
                     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):
                         err(lr, _("unpacked size is %s, %s expected") %
                             (l, fl.size(i)), f)
             except Exception, inst:
                 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:
                             warn(_("warning: copy source of '%s' not"
                                    " in parents of %s") % (f, ctx))
                     fl2 = repo.file(rp[0])
                     if not len(fl2):
                         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, inst:
                 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):
                 err(lr, _("%s in manifests not found") % short(node), f)
     ui.progress(_('checking'), None)
 
     for f in storefiles:
         warn(_("warning: orphan revlog '%s'") % f)
 
     ui.status(_("%d files, %d changesets, %d total revisions\n") %
                    (len(files), len(cl), revisions))
     if warnings[0]:
         ui.warn(_("%d warnings encountered!\n") % warnings[0])
     if errors[0]:
         ui.warn(_("%d integrity errors encountered!\n") % errors[0])
         if badrevs:
             ui.warn(_("(first damaged changeset appears to be %d)\n")
                     % min(badrevs))
         return 1

tests/test-verify.t

@@ -1,87 +1,101 b''
 prepare repo
 
   $ hg init a
   $ cd a
   $ echo "some text" > FOO.txt
   $ echo "another text" > bar.txt
   $ echo "more text" > QUICK.txt
   $ hg add
   adding FOO.txt
   adding QUICK.txt
   adding bar.txt
   $ hg ci -mtest1
 
 verify
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   3 files, 1 changesets, 3 total revisions
 
 verify with journal
 
   $ touch .hg/store/journal
   $ hg verify
   abandoned transaction found - run hg recover
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
   3 files, 1 changesets, 3 total revisions
   $ rm .hg/store/journal
 
 introduce some bugs in repo
 
   $ cd .hg/store/data
   $ mv _f_o_o.txt.i X_f_o_o.txt.i
   $ mv bar.txt.i xbar.txt.i
   $ rm _q_u_i_c_k.txt.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    data/FOO.txt.i@0: missing revlog!
    0: empty or missing FOO.txt
    FOO.txt@0: f62022d3d590 in manifests not found
    data/QUICK.txt.i@0: missing revlog!
    0: empty or missing QUICK.txt
    QUICK.txt@0: 88b857db8eba in manifests not found
    data/bar.txt.i@0: missing revlog!
    0: empty or missing bar.txt
    bar.txt@0: 256559129457 in manifests not found
   3 files, 1 changesets, 0 total revisions
   9 integrity errors encountered!
   (first damaged changeset appears to be 0)
 
   $ cd ..
 
 test revlog corruption
 
   $ hg init b
   $ cd b
 
   $ touch a
   $ hg add a
   $ hg ci -m a
 
   $ echo 'corrupted' > b
   $ dd if=.hg/store/data/a.i of=start bs=1 count=20 2>/dev/null
   $ cat start b > .hg/store/data/a.i
 
   $ hg verify
   checking changesets
   checking manifests
   crosschecking files in changesets and manifests
   checking files
    a@0: broken revlog! (index data/a.i is corrupted)
   warning: orphan revlog 'data/a.i'
   1 files, 1 changesets, 0 total revisions
   1 warnings encountered!
   1 integrity errors encountered!
   (first damaged changeset appears to be 0)
 
+  $ cd ..
+
+test revlog format 0
+
+  $ "$TESTDIR/revlog-formatv0.py"
+  $ cd formatv0
+  $ hg verify
+  repository uses revlog format 0
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+  1 files, 1 changesets, 1 total revisions
+
   $ exit 0