store: change handling of decoding errors

mercurial/localrepo.py

@@ -1,2088 +1,2088 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup
 import changelog, dirstate, filelog, manifest, context, weakref
 import lock, transaction, stat, errno, ui, store
 import os, revlog, time, util, extensions, hook, inspect
 import match as match_
 import merge as merge_
 
 class localrepository(repo.repository):
     capabilities = util.set(('lookup', 'changegroupsubset'))
     supported = ('revlogv1', 'store')
 
     def __init__(self, parentui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(path)
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     os.mkdir(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if parentui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise repo.RepoError(_("repository %s not found") % path)
         elif create:
             raise repo.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             requirements = []
             try:
                 requirements = self.opener("requires").read().splitlines()
                 for r in requirements:
                     if r not in self.supported:
                         raise repo.RepoError(_("requirement '%s' not supported") % r)
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
         self.store = store.store(requirements, self.path, util.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
 
         self.ui = ui.ui(parentui=parentui)
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         self.tagscache = None
         self._tagstypecache = None
         self.branchcache = None
         self._ubranchcache = None  # UTF-8 version of branchcache
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     def __getattr__(self, name):
         if name == 'changelog':
             self.changelog = changelog.changelog(self.sopener)
             self.sopener.defversion = self.changelog.version
             return self.changelog
         if name == 'manifest':
             self.changelog
             self.manifest = manifest.manifest(self.sopener)
             return self.manifest
         if name == 'dirstate':
             self.dirstate = dirstate.dirstate(self.opener, self.ui, self.root)
             return self.dirstate
         else:
             raise AttributeError, name
 
     def __getitem__(self, changeid):
         if changeid == None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, names, node, message, local, user, date, parent=None,
              extra={}):
         use_dirstate = parent is None
 
         if isinstance(names, str):
             allchars = names
             names = (names,)
         else:
             allchars = ''.join(names)
         for c in self.tag_disallowed:
             if c in allchars:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if self._tagstypecache and name in self._tagstypecache:
                     old = self.tagscache.get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError, err:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         if use_dirstate:
             try:
                 fp = self.wfile('.hgtags', 'rb+')
             except IOError, err:
                 fp = self.wfile('.hgtags', 'ab')
             else:
                 prevtags = fp.read()
         else:
             try:
                 prevtags = self.filectx('.hgtags', parent).data()
             except revlog.LookupError:
                 pass
             fp = self.wfile('.hgtags', 'wb')
             if prevtags:
                 fp.write(prevtags)
 
         # committed tags are stored in UTF-8
         writetags(fp, names, util.fromlocal, prevtags)
 
         if use_dirstate and '.hgtags' not in self.dirstate:
             self.add(['.hgtags'])
 
         tagnode = self.commit(['.hgtags'], message, user, date, p1=parent,
                               extra=extra)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
         self._tag(names, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self.tagscache:
             return self.tagscache
 
         globaltags = {}
         tagtypes = {}
 
         def readtags(lines, fn, tagtype):
             filetags = {}
             count = 0
 
             def warn(msg):
                 self.ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
             for l in lines:
                 count += 1
                 if not l:
                     continue
                 s = l.split(" ", 1)
                 if len(s) != 2:
                     warn(_("cannot parse entry"))
                     continue
                 node, key = s
                 key = util.tolocal(key.strip()) # stored in UTF-8
                 try:
                     bin_n = bin(node)
                 except TypeError:
                     warn(_("node '%s' is not well formed") % node)
                     continue
                 if bin_n not in self.changelog.nodemap:
                     warn(_("tag '%s' refers to unknown node") % key)
                     continue
 
                 h = []
                 if key in filetags:
                     n, h = filetags[key]
                     h.append(n)
                 filetags[key] = (bin_n, h)
 
             for k, nh in filetags.items():
                 if k not in globaltags:
                     globaltags[k] = nh
                     tagtypes[k] = tagtype
                     continue
 
                 # we prefer the global tag if:
                 #  it supercedes us OR
                 #  mutual supercedes and it has a higher rank
                 # otherwise we win because we're tip-most
                 an, ah = nh
                 bn, bh = globaltags[k]
                 if (bn != an and an in bh and
                     (bn not in ah or len(bh) > len(ah))):
                     an = bn
                 ah.extend([n for n in bh if n not in ah])
                 globaltags[k] = an, ah
                 tagtypes[k] = tagtype
 
         # read the tags file from each head, ending with the tip
         f = None
         for rev, node, fnode in self._hgtagsnodes():
             f = (f and f.filectx(fnode) or
                  self.filectx('.hgtags', fileid=fnode))
             readtags(f.data().splitlines(), f, "global")
 
         try:
             data = util.fromlocal(self.opener("localtags").read())
             # localtags are stored in the local character set
             # while the internal tag table is stored in UTF-8
             readtags(data.splitlines(), "localtags", "local")
         except IOError:
             pass
 
         self.tagscache = {}
         self._tagstypecache = {}
         for k,nh in globaltags.items():
             n = nh[0]
             if n != nullid:
                 self.tagscache[k] = n
             self._tagstypecache[k] = tagtypes[k]
         self.tagscache['tip'] = self.changelog.tip()
         return self.tagscache
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         self.tags()
 
         return self._tagstypecache.get(tagname)
 
     def _hgtagsnodes(self):
         heads = self.heads()
         heads.reverse()
         last = {}
         ret = []
         for node in heads:
             c = self[node]
             rev = c.rev()
             try:
                 fnode = c.filenode('.hgtags')
             except revlog.LookupError:
                 continue
             ret.append((rev, node, fnode))
             if fnode in last:
                 ret[last[fnode]] = None
             last[fnode] = len(ret) - 1
         return [item for item in ret if item]
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().items():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in util.sort(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().items():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         tiprev = len(self) - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchtags(self):
         tip = self.changelog.tip()
         if self.branchcache is not None and self._branchcachetip == tip:
             return self.branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if self.branchcache is None:
             self.branchcache = {} # avoid recursion in changectx
         else:
             self.branchcache.clear() # keep using the same dict
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._ubranchcache
 
         self._branchtags(partial, lrev)
 
         # the branch cache is stored on disk as UTF-8, but in the local
         # charset internally
         for k, v in partial.items():
             self.branchcache[util.tolocal(k)] = v
         self._ubranchcache = partial
         return self.branchcache
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branch.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
                 if not l: continue
                 node, label = l.split(" ", 1)
                 partial[label.strip()] = bin(node)
         except (KeyboardInterrupt, util.SignalInterrupt):
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branch.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, node in branches.iteritems():
                 f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, start, end):
         for r in xrange(start, end):
             c = self[r]
             b = c.branch()
             partial[b] = c.node()
 
     def lookup(self, key):
         if key == '.':
             return self.dirstate.parents()[0]
         elif key == 'null':
             return nullid
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
         try:
             if len(key) == 20:
                 key = hex(key)
         except:
             pass
         raise repo.RepoError(_("unknown revision '%s'") % key)
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 mf = util.matcher(self.root, "", [pat], [], [])[1]
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug(_("filtering %s through %s\n") % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         if self._transref and self._transref():
             return self._transref().nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise repo.RepoError(_("journal already exists - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         l = self.lock()
         try:
             if os.path.exists(self.sjoin("journal")):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"))
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             del l
 
     def rollback(self):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 self.ui.status(_("rolling back last transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("undo"))
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 try:
                     branch = self.opener("undo.branch").read()
                     self.dirstate.setbranch(branch)
                 except IOError:
                     self.ui.warn(_("Named branch could not be reset, "
                                    "current branch still is: %s\n")
                                  % util.tolocal(self.dirstate.branch()))
                 self.invalidate()
                 self.dirstate.invalidate()
             else:
                 self.ui.warn(_("no rollback information available\n"))
         finally:
             del lock, wlock
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if a in self.__dict__:
                 delattr(self, a)
         self.tagscache = None
         self._tagstypecache = None
         self.nodetagscache = None
         self.branchcache = None
         self._ubranchcache = None
         self._branchcachetip = None
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except lock.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def lock(self, wait=True):
         if self._lockref and self._lockref():
             return self._lockref()
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         if self._wlockref and self._wlockref():
             return self._wlockref()
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fn = fctx.path()
         t = fctx.data()
         fl = self.file(fn)
         fp1 = manifest1.get(fn, nullid)
         fp2 = manifest2.get(fn, nullid)
 
         meta = {}
         cp = fctx.renamed()
         if cp and cp[0] != fn:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cf = cp[0]
             cr = manifest1.get(cf)
             nfp = fp2
 
             if manifest2: # branch merge
                 if fp2 == nullid: # copied on remote side
                     if fp1 != nullid or cf in manifest2:
                         cr = manifest2[cf]
                         nfp = fp1
 
             # find source in nearest ancestor if we've lost track
             if not cr:
                 self.ui.debug(_(" %s: searching for copy revision for %s\n") %
                               (fn, cf))
 		for a in self['.'].ancestors():
                     if cf in a:
                         cr = a[cf].filenode()
                         break
 
             self.ui.debug(_(" %s: copy %s:%s\n") % (fn, cf, hex(cr)))
             meta["copy"] = cf
             meta["copyrev"] = hex(cr)
             fp1, fp2 = nullid, nfp
         elif fp2 != nullid:
             # is one parent an ancestor of the other?
             fpa = fl.ancestor(fp1, fp2)
             if fpa == fp1:
                 fp1, fp2 = fp2, nullid
             elif fpa == fp2:
                 fp2 = nullid
 
         # is the file unmodified from the parent? report existing entry
         if fp2 == nullid and not fl.cmp(fp1, t) and not meta:
             return fp1
 
         changelist.append(fn)
         return fl.add(t, meta, tr, linkrev, fp1, fp2)
 
     def rawcommit(self, files, text, user, date, p1=None, p2=None, extra={}):
         if p1 is None:
             p1, p2 = self.dirstate.parents()
         return self.commit(files=files, text=text, user=user, date=date,
                            p1=p1, p2=p2, extra=extra, empty_ok=True)
 
     def commit(self, files=None, text="", user=None, date=None,
                match=None, force=False, force_editor=False,
                p1=None, p2=None, extra={}, empty_ok=False):
         wlock = lock = None
         if files:
             files = util.unique(files)
         try:
             wlock = self.wlock()
             lock = self.lock()
             use_dirstate = (p1 is None) # not rawcommit
 
             if use_dirstate:
                 p1, p2 = self.dirstate.parents()
                 update_dirstate = True
 
                 if (not force and p2 != nullid and
                     (match and (match.files() or match.anypats()))):
                     raise util.Abort(_('cannot partially commit a merge '
                                        '(do not specify files or patterns)'))
 
                 if files:
                     modified, removed = [], []
                     for f in files:
                         s = self.dirstate[f]
                         if s in 'nma':
                             modified.append(f)
                         elif s == 'r':
                             removed.append(f)
                         else:
                             self.ui.warn(_("%s not tracked!\n") % f)
                     changes = [modified, [], removed, [], []]
                 else:
                     changes = self.status(match=match)
             else:
                 p1, p2 = p1, p2 or nullid
                 update_dirstate = (self.dirstate.parents()[0] == p1)
                 changes = [files, [], [], [], []]
 
             ms = merge_.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
             wctx = context.workingctx(self, (p1, p2), text, user, date,
                                       extra, changes)
             return self._commitctx(wctx, force, force_editor, empty_ok,
                                    use_dirstate, update_dirstate)
         finally:
             del lock, wlock
 
     def commitctx(self, ctx):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             return self._commitctx(ctx, force=True, force_editor=False,
                                    empty_ok=True, use_dirstate=False,
                                    update_dirstate=False)
         finally:
             del lock, wlock
 
     def _commitctx(self, wctx, force=False, force_editor=False, empty_ok=False,
                   use_dirstate=True, update_dirstate=True):
         tr = None
         valid = 0 # don't save the dirstate if this isn't set
         try:
             commit = util.sort(wctx.modified() + wctx.added())
             remove = wctx.removed()
             extra = wctx.extra().copy()
             branchname = extra['branch']
             user = wctx.user()
             text = wctx.description()
 
             p1, p2 = [p.node() for p in wctx.parents()]
             c1 = self.changelog.read(p1)
             c2 = self.changelog.read(p2)
             m1 = self.manifest.read(c1[0]).copy()
             m2 = self.manifest.read(c2[0])
 
             if use_dirstate:
                 oldname = c1[5].get("branch") # stored in UTF-8
                 if (not commit and not remove and not force and p2 == nullid
                     and branchname == oldname):
                     self.ui.status(_("nothing changed\n"))
                     return None
 
             xp1 = hex(p1)
             if p2 == nullid: xp2 = ''
             else: xp2 = hex(p2)
 
             self.hook("precommit", throw=True, parent1=xp1, parent2=xp2)
 
             tr = self.transaction()
             trp = weakref.proxy(tr)
 
             # check in files
             new = {}
             changed = []
             linkrev = len(self)
             for f in commit:
                 self.ui.note(f + "\n")
                 try:
                     fctx = wctx.filectx(f)
                     newflags = fctx.flags()
                     new[f] = self.filecommit(fctx, m1, m2, linkrev, trp, changed)
                     if ((not changed or changed[-1] != f) and
                         m2.get(f) != new[f]):
                         # mention the file in the changelog if some
                         # flag changed, even if there was no content
                         # change.
                         if m1.flags(f) != newflags:
                             changed.append(f)
                     m1.set(f, newflags)
                     if use_dirstate:
                         self.dirstate.normal(f)
 
                 except (OSError, IOError):
                     if use_dirstate:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     else:
                         remove.append(f)
 
             # update manifest
             m1.update(new)
             removed = []
 
             for f in util.sort(remove):
                 if f in m1:
                     del m1[f]
                     removed.append(f)
                 elif f in m2:
                     removed.append(f)
             mn = self.manifest.add(m1, trp, linkrev, c1[0], c2[0],
                                    (new, removed))
 
             # add changeset
             if (not empty_ok and not text) or force_editor:
                 edittext = []
                 if text:
                     edittext.append(text)
                 edittext.append("")
                 edittext.append(_("HG: Enter commit message."
                                   "  Lines beginning with 'HG:' are removed."))
                 edittext.append("HG: --")
                 edittext.append("HG: user: %s" % user)
                 if p2 != nullid:
                     edittext.append("HG: branch merge")
                 if branchname:
                     edittext.append("HG: branch '%s'" % util.tolocal(branchname))
                 edittext.extend(["HG: changed %s" % f for f in changed])
                 edittext.extend(["HG: removed %s" % f for f in removed])
                 if not changed and not remove:
                     edittext.append("HG: no files changed")
                 edittext.append("")
                 # run editor in the repository root
                 olddir = os.getcwd()
                 os.chdir(self.root)
                 text = self.ui.edit("\n".join(edittext), user)
                 os.chdir(olddir)
 
             lines = [line.rstrip() for line in text.rstrip().splitlines()]
             while lines and not lines[0]:
                 del lines[0]
             if not lines and use_dirstate:
                 raise util.Abort(_("empty commit message"))
             text = '\n'.join(lines)
 
             n = self.changelog.add(mn, changed + removed, text, trp, p1, p2,
                                    user, wctx.date(), extra)
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             tr.close()
 
             if self.branchcache:
                 self.branchtags()
 
             if use_dirstate or update_dirstate:
                 self.dirstate.setparents(n)
                 if use_dirstate:
                     for f in removed:
                         self.dirstate.forget(f)
             valid = 1 # our dirstate updates are complete
 
             self.hook("commit", node=hex(n), parent1=xp1, parent2=xp2)
             return n
         finally:
             if not valid: # don't save our updated dirstate
                 self.dirstate.invalidate()
             del tr
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         ctx1 = self[node1]
         ctx2 = self[node2]
         working = ctx2 == self[None]
         parentworking = working and ctx1 == self['.']
         match = match or match_.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         if working: # we need to scan the working dir
             s = self.dirstate.status(match, listignored, listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in cmp:
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f].data())):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 if listclean:
                     clean += fixup
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     wlock = None
                     try:
                         try:
                             wlock = self.wlock(False)
                             for f in fixup:
                                 self.dirstate.normal(f)
                         except lock.LockException:
                             pass
                     finally:
                         del wlock
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn].data())))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
         [l.sort() for l in r]
         return r
 
     def add(self, list):
         wlock = self.wlock()
         try:
             rejected = []
             for f in list:
                 p = self.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     self.ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     self.ui.warn(_("%s: files over 10MB may cause memory and"
                                    " performance problems\n"
                                    "(use 'hg revert %s' to unadd the file)\n")
                                    % (f, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     self.ui.warn(_("%s not added: only files and symlinks "
                                    "supported currently\n") % f)
                     rejected.append(p)
                 elif self.dirstate[f] in 'amn':
                     self.ui.warn(_("%s already tracked!\n") % f)
                 elif self.dirstate[f] == 'r':
                     self.dirstate.normallookup(f)
                 else:
                     self.dirstate.add(f)
             return rejected
         finally:
             del wlock
 
     def forget(self, list):
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'a':
                     self.ui.warn(_("%s not added!\n") % f)
                 else:
                     self.dirstate.forget(f)
         finally:
             del wlock
 
     def remove(self, list, unlink=False):
         wlock = None
         try:
             if unlink:
                 for f in list:
                     try:
                         util.unlink(self.wjoin(f))
                     except OSError, inst:
                         if inst.errno != errno.ENOENT:
                             raise
             wlock = self.wlock()
             for f in list:
                 if unlink and os.path.exists(self.wjoin(f)):
                     self.ui.warn(_("%s still exists!\n") % f)
                 elif self.dirstate[f] == 'a':
                     self.dirstate.forget(f)
                 elif f not in self.dirstate:
                     self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self.dirstate.remove(f)
         finally:
             del wlock
 
     def undelete(self, list):
         wlock = None
         try:
             manifests = [self.manifest.read(self.changelog.read(p)[0])
                          for p in self.dirstate.parents() if p != nullid]
             wlock = self.wlock()
             for f in list:
                 if self.dirstate[f] != 'r':
                     self.ui.warn("%s not removed!\n" % f)
                 else:
                     m = f in manifests[0] and manifests[0] or manifests[1]
                     t = self.file(f).read(m[f])
                     self.wwrite(f, t, m.flags(f))
                     self.dirstate.normal(f)
         finally:
             del wlock
 
     def copy(self, source, dest):
         wlock = None
         try:
             p = self.wjoin(dest)
             if not (os.path.exists(p) or os.path.islink(p)):
                 self.ui.warn(_("%s does not exist!\n") % dest)
             elif not (os.path.isfile(p) or os.path.islink(p)):
                 self.ui.warn(_("copy failed: %s is not a file or a "
                                "symbolic link\n") % dest)
             else:
                 wlock = self.wlock()
                 if dest not in self.dirstate:
                     self.dirstate.add(dest)
                 self.dirstate.copy(source, dest)
         finally:
             del wlock
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         return [n for (r, n) in util.sort(heads)]
 
     def branchheads(self, branch=None, start=None):
         if branch is None:
             branch = self[None].branch()
         branches = self.branchtags()
         if branch not in branches:
             return []
         # The basic algorithm is this:
         #
         # Start from the branch tip since there are no later revisions that can
         # possibly be in this branch, and the tip is a guaranteed head.
         #
         # Remember the tip's parents as the first ancestors, since these by
         # definition are not heads.
         #
         # Step backwards from the brach tip through all the revisions. We are
         # guaranteed by the rules of Mercurial that we will now be visiting the
         # nodes in reverse topological order (children before parents).
         #
         # If a revision is one of the ancestors of a head then we can toss it
         # out of the ancestors set (we've already found it and won't be
         # visiting it again) and put its parents in the ancestors set.
         #
         # Otherwise, if a revision is in the branch it's another head, since it
         # wasn't in the ancestor list of an existing head.  So add it to the
         # head list, and add its parents to the ancestor list.
         #
         # If it is not in the branch ignore it.
         #
         # Once we have a list of heads, use nodesbetween to filter out all the
         # heads that cannot be reached from startrev.  There may be a more
         # efficient way to do this as part of the previous algorithm.
 
         set = util.set
         heads = [self.changelog.rev(branches[branch])]
         # Don't care if ancestors contains nullrev or not.
         ancestors = set(self.changelog.parentrevs(heads[0]))
         for rev in xrange(heads[0] - 1, nullrev, -1):
             if rev in ancestors:
                 ancestors.update(self.changelog.parentrevs(rev))
                 ancestors.remove(rev)
             elif self[rev].branch() == branch:
                 heads.append(rev)
                 ancestors.update(self.changelog.parentrevs(rev))
         heads = [self.changelog.node(rev) for rev in heads]
         if start is not None:
             heads = self.changelog.nodesbetween([start], heads)[2]
         return heads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         m = self.changelog.nodemap
         search = []
         fetch = {}
         seen = {}
         seenbranch = {}
         if base == None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid]
             return []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         if not unknown:
             return []
 
         req = dict.fromkeys(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug(_("examining %s:%s\n")
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug(_("branch already found\n"))
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug(_("found incomplete branch %s:%s\n")
                                   % (short(n[0]), short(n[1])))
                     search.append(n) # schedule branch range for scanning
                     seenbranch[n] = 1
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug(_("found new changeset %s\n") %
                                           short(n[1]))
                             fetch[n[1]] = 1 # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req[p] = 1
                 seen[n[0]] = 1
 
             if r:
                 reqcnt += 1
                 self.ui.debug(_("request %d: %s\n") %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug(_("received %s:%s\n") %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             n = search.pop(0)
             reqcnt += 1
             l = remote.between([(n[0], n[1])])[0]
             l.append(n[1])
             p = n[0]
             f = 1
             for i in l:
                 self.ui.debug(_("narrowing %d:%d %s\n") % (f, len(l), short(i)))
                 if i in m:
                     if f <= 2:
                         self.ui.debug(_("found new branch changeset %s\n") %
                                           short(p))
                         fetch[p] = 1
                         base[i] = 1
                     else:
                         self.ui.debug(_("narrowed branch search to %s:%s\n")
                                       % (short(p), short(i)))
                         search.append((p, i))
                     break
                 p, f = i, f * 2
 
         # sanity check our fetch list
         for f in fetch.keys():
             if f in m:
                 raise repo.RepoError(_("already have changeset ") + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug(_("found new changesets starting at ") +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug(_("%d total queries\n") % reqcnt)
 
         return fetch.keys()
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base == None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug(_("common changesets up to ")
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = dict.fromkeys(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         del remain[nullid]
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 del remain[n]
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = {}
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads[p1] = True
                 if p2 in heads:
                     updated_heads[p2] = True
 
         # this is the set of all roots we have to push
         if heads:
             return subset, updated_heads.keys()
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             fetch = self.findincoming(remote, heads=heads, force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if 'changegroupsubset' not in remote.capabilities:
                     raise util.Abort(_("Partial pull cannot be done because other repository doesn't support changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             del lock
 
     def push(self, remote, force=False, revs=None):
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if remote.capable('unbundle'):
             return self.push_unbundle(remote, force, revs)
         return self.push_addchangegroup(remote, force, revs)
 
     def prepush(self, remote, force, revs):
         base = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, base, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, base, remote_heads)
         if revs is not None:
             msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
         else:
             bases, heads = update, self.changelog.heads()
 
         if not bases:
             self.ui.status(_("no changes found\n"))
             return None, 1
         elif not force:
             # check if we're creating new remote heads
             # to be a remote head after push, node must be either
             # - unknown locally
             # - a local outgoing head descended from update
             # - a remote head that's known locally and not
             #   ancestral to an outgoing head
 
             warn = 0
 
             if remote_heads == [nullid]:
                 warn = 0
             elif not revs and len(heads) > len(remote_heads):
                 warn = 1
             else:
                 newheads = list(heads)
                 for r in remote_heads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.append(r)
                     else:
                         newheads.append(r)
                 if len(newheads) > len(remote_heads):
                     warn = 1
 
             if warn:
                 self.ui.warn(_("abort: push creates new remote heads!\n"))
                 self.ui.status(_("(did you forget to merge?"
                                  " use push -f to force)\n"))
                 return None, 0
             elif inc:
                 self.ui.warn(_("note: unsynced remote changes!\n"))
 
 
         if revs is None:
             cg = self.changegroup(update, 'push')
         else:
             cg = self.changegroupsubset(update, revs, 'push')
         return cg, remote_heads
 
     def push_addchangegroup(self, remote, force, revs):
         lock = remote.lock()
         try:
             ret = self.prepush(remote, force, revs)
             if ret[0] is not None:
                 cg, remote_heads = ret
                 return remote.addchangegroup(cg, 'push', self.url())
             return ret[1]
         finally:
             del lock
 
     def push_unbundle(self, remote, force, revs):
         # local repo finds heads on server, finds out what revs it
         # must push.  once revs transferred, if server finds it has
         # different heads (someone else won commit/push race), server
         # aborts.
 
         ret = self.prepush(remote, force, revs)
         if ret[0] is not None:
             cg, remote_heads = ret
             if force: remote_heads = ['force']
             return remote.unbundle(cg, remote_heads, 'push')
         return ret[1]
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug(_("List of changesets:\n"))
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source, extranodes=None):
         """This function generates a changegroup consisting of all the nodes
         that are descendents of any of the bases, and ancestors of any of
         the heads.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         self.hook('preoutgoing', throw=True, source=source)
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # msng is short for missing - compute the list of changesets in this
         # changegroup.
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
         self.changegroupinfo(msng_cl_lst, source)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = {}
         # We assume that all parents of bases are known heads.
         for n in bases:
             for p in cl.parents(n):
                 if p != nullid:
                     knownheads[p] = 1
         knownheads = knownheads.keys()
         if knownheads:
             # Now that we know what heads are known, we can compute which
             # changesets are known.  The recipient must know about all
             # changesets required to reach the known heads from the null
             # changeset.
             has_cl_set, junk, junk = cl.nodesbetween(None, knownheads)
             junk = None
             # Transform the list into an ersatz set.
             has_cl_set = dict.fromkeys(has_cl_set)
         else:
             # If there were no known heads, the recipient cannot be assumed to
             # know about any changesets.
             has_cl_set = {}
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function.  Sets up an environment for the
         # inner function.
         def cmp_by_rev_func(revlog):
             # Compare two nodes by their revision number in the environment's
             # revision history.  Since the revision number both represents the
             # most efficient order to read the nodes in, and represents a
             # topological sorting of the nodes, this function is often useful.
             def cmp_by_rev(a, b):
                 return cmp(revlog.rev(a), revlog.rev(b))
             return cmp_by_rev
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune_parents(revlog, hasset, msngset):
             haslst = hasset.keys()
             haslst.sort(cmp_by_rev_func(revlog))
             for node in haslst:
                 parentlst = [p for p in revlog.parents(node) if p != nullid]
                 while parentlst:
                     n = parentlst.pop()
                     if n not in hasset:
                         hasset[n] = 1
                         p = [p for p in revlog.parents(n) if p != nullid]
                         parentlst.extend(p)
             for n in hasset:
                 msngset.pop(n, None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = {}
             for n in msng_mnfst_set:
                 # If a 'missing' manifest thinks it belongs to a changenode
                 # the recipient is assumed to have, obviously the recipient
                 # must have that manifest.
                 linknode = cl.node(mnfst.linkrev(n))
                 if linknode in has_cl_set:
                     has_mnfst_set[n] = 1
             prune_parents(mnfst, has_mnfst_set, msng_mnfst_set)
 
         # Use the information collected in collect_manifests_and_files to say
         # which changenode any manifestnode belongs to.
         def lookup_manifest_link(mnfstnode):
             return msng_mnfst_set[mnfstnode]
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             next_rev = [0]
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r == next_rev[0]:
                     # If the last rev we looked at was the one just previous,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.items():
                         f = changedfiles.get(f, None)
                         # And if the file is in the list of files we care
                         # about.
                         if f is not None:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
                 # Remember the revision we hope to see next.
                 next_rev[0] = r + 1
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we now the recipient must have.
         def prune_filenodes(f, filerevlog):
             msngset = msng_filenode_set[f]
             hasset = {}
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in msngset:
                 clnode = cl.node(filerevlog.linkrev(n))
                 if clnode in has_cl_set:
                     hasset[n] = 1
             prune_parents(filerevlog, hasset, msngset)
 
         # A function generator function that sets up the a context for the
         # inner function.
         def lookup_filenode_link_func(fname):
             msngset = msng_filenode_set[fname]
             # Lookup the changenode the filenode belongs to.
             def lookup_filenode_link(fnode):
                 return msngset[fnode]
             return lookup_filenode_link
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = {}
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             group = cl.group(msng_cl_lst, identity,
                              manifest_and_file_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # The list of manifests has been collected by the generator
             # calling our functions back.
             prune_manifests()
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(cmp_by_rev_func(mnfst))
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
                                 filenode_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     add_extra_nodes(fname,
                                     msng_filenode_set.setdefault(fname, {}))
                     changedfiles[fname] = 1
             # Go through all our files in order sorted by name.
             for fname in util.sort(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 if fname in msng_filenode_set:
                     prune_filenodes(fname, filerevlog)
                     msng_filenode_lst = msng_filenode_set[fname].keys()
                 else:
                     msng_filenode_lst = []
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if len(msng_filenode_lst) > 0:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision #
                     msng_filenode_lst.sort(cmp_by_rev_func(filerevlog))
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(msng_filenode_lst,
                                              lookup_filenode_link_func(fname))
                     for chnk in group:
                         yield chnk
                 if fname in msng_filenode_set:
                     # Don't need this anymore, toss it to free memory.
                     del msng_filenode_set[fname]
             # Signal that no more groups are left.
             yield changegroup.closechunk()
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         """Generate a changegroup of all nodes that we have that a recipient
         doesn't.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them."""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         nodes = cl.nodesbetween(basenodes, None)[0]
         revset = dict.fromkeys([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(log):
             for r in log:
                 n = log.node(r)
                 if log.linkrev(n) in revset:
                     yield n
 
         def changed_file_collector(changedfileset):
             def collect_changed_files(clnode):
                 c = cl.read(clnode)
                 for fname in c[3]:
                     changedfileset[fname] = 1
             return collect_changed_files
 
         def lookuprevlink_func(revlog):
             def lookuprevlink(n):
                 return cl.node(revlog.linkrev(n))
             return lookuprevlink
 
         def gengroup():
             # construct a list of all changed files
             changedfiles = {}
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in util.sort(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuprevlink_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         yield chnk
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """add changegroup to repo.
 
         return values:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - less heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug(_("add changeset %s\n") % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction()
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             cor = len(cl) - 1
             chunkiter = changegroup.chunkiter(source)
             if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             cnr = len(cl) - 1
             changesets = cnr - cor
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             chunkiter = changegroup.chunkiter(source)
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             self.manifest.addgroup(chunkiter, revmap, trp)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug(_("adding %s revisions\n") % f)
                 fl = self.file(f)
                 o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
 
             # make changelog see real files again
             cl.finalize(trp)
 
             newheads = len(self.changelog.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(self.changelog.node(cor+1)), source=srctype,
                           url=url)
 
             tr.close()
         finally:
             del tr
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug(_("updating the branch cache\n"))
             self.branchtags()
             self.hook("changegroup", node=hex(self.changelog.node(cor+1)),
                       source=srctype, url=url)
 
             for i in xrange(cor + 1, cnr + 1):
                 self.hook("incoming", node=hex(self.changelog.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise util.UnexpectedOutput(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise util.UnexpectedOutput(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except ValueError, TypeError:
                 raise util.UnexpectedOutput(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             ofp = self.sopener(name, 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
     def storefiles(self):
         '''get all *.i and *.d files in the store
 
         Returns (list of (filename, size), total_bytes)'''
 
         lock = None
         try:
             self.ui.debug('scanning\n')
             entries = []
             total_bytes = 0
             # get consistent snapshot of repo, lock during scan
             lock = self.lock()
-            for name, size in self.store.walk():
+            for name, ename, size in self.store.walk():
                 entries.append((name, size))
                 total_bytes += size
             return entries, total_bytes
         finally:
             del lock
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True

mercurial/store.py

@@ -1,117 +1,116 b''
 # store.py - repository store handling for Mercurial
 #
 # Copyright 2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
-from i18n import _
 import os, stat, osutil, util
 
 def _buildencodefun():
     e = '_'
     win_reserved = [ord(x) for x in '\\:*?"<>|']
     cmap = dict([ (chr(x), chr(x)) for x in xrange(127) ])
     for x in (range(32) + range(126, 256) + win_reserved):
         cmap[chr(x)] = "~%02x" % x
     for x in range(ord("A"), ord("Z")+1) + [ord(e)]:
         cmap[chr(x)] = e + chr(x).lower()
     dmap = {}
     for k, v in cmap.iteritems():
         dmap[v] = k
     def decode(s):
         i = 0
         while i < len(s):
             for l in xrange(1, 4):
                 try:
                     yield dmap[s[i:i+l]]
                     i += l
                     break
                 except KeyError:
                     pass
             else:
                 raise KeyError
     return (lambda s: "".join([cmap[c] for c in s]),
             lambda s: "".join(list(decode(s))))
 
 encodefilename, decodefilename = _buildencodefun()
 
 def _calcmode(path):
     try:
         # files in .hg/ will be created using this mode
         mode = os.stat(path).st_mode
             # avoid some useless chmods
         if (0777 & ~util._umask) == (0777 & mode):
             mode = None
     except OSError:
         mode = None
     return mode
 
 class basicstore:
     '''base class for local repository stores'''
     def __init__(self, path, opener):
         self.path = path
         self.createmode = _calcmode(path)
         self.opener = opener(self.path)
         self.opener.createmode = self.createmode
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def _walk(self, relpath, recurse):
-        '''yields (filename, size)'''
+        '''yields (unencoded, encoded, size)'''
         path = os.path.join(self.path, relpath)
         striplen = len(self.path) + len(os.sep)
         prefix = path[striplen:]
         l = []
         if os.path.isdir(path):
             visit = [path]
             while visit:
                 p = visit.pop()
                 for f, kind, st in osutil.listdir(p, stat=True):
                     fp = os.path.join(p, f)
                     if kind == stat.S_IFREG and f[-2:] in ('.d', '.i'):
-                        l.append((util.pconvert(fp[striplen:]), st.st_size))
+                        n = util.pconvert(fp[striplen:])
+                        l.append((n, n, st.st_size))
                     elif kind == stat.S_IFDIR and recurse:
                         visit.append(fp)
         return util.sort(l)
 
-    def datafiles(self, reporterror=None):
+    def datafiles(self):
         return self._walk('data', True)
 
     def walk(self):
-        '''yields (direncoded filename, size)'''
+        '''yields (unencoded, encoded, size)'''
         # yield data files first
         for x in self.datafiles():
             yield x
         # yield manifest before changelog
         meta = self._walk('', False)
         meta.reverse()
         for x in meta:
             yield x
 
 class encodedstore(basicstore):
     def __init__(self, path, opener):
         self.path = os.path.join(path, 'store')
         self.createmode = _calcmode(self.path)
         self.encodefn = encodefilename
         op = opener(self.path)
         op.createmode = self.createmode
         self.opener = lambda f, *args, **kw: op(self.encodefn(f), *args, **kw)
 
-    def datafiles(self, reporterror=None):
-        for f, size in self._walk('data', True):
+    def datafiles(self):
+        for a, b, size in self._walk('data', True):
             try:
-                yield decodefilename(f), size
+                a = decodefilename(a)
             except KeyError:
-                if not reporterror:
-                    raise
-                reporterror(_("cannot decode filename '%s'") % f)
+                a = None
+            yield a, b, size
 
     def join(self, f):
         return os.path.join(self.path, self.encodefn(f))
 
 def store(requirements, path, opener):
     if 'store' in requirements:
         return encodedstore(path, opener)
     return basicstore(path, opener)

mercurial/verify.py

@@ -1,233 +1,235 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, incorporated herein by reference.
 
 from node import nullid, short
 from i18n import _
 import revlog, util
 
 def verify(repo):
     lock = repo.lock()
     try:
         return _verify(repo)
     finally:
         del lock
 
 def _verify(repo):
     mflinkrevs = {}
     filelinkrevs = {}
     filenodes = {}
     revisions = 0
     badrevs = {}
     errors = [0]
     warnings = [0]
     ui = repo.ui
     cl = repo.changelog
     mf = repo.manifest
 
     def err(linkrev, msg, filename=None):
         if linkrev != None:
             badrevs[linkrev] = True
         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
         err(linkrev, "%s: %s" % (msg, inst), filename)
 
     def warn(msg):
         ui.warn(msg + "\n")
         warnings[0] += 1
 
     def checklog(obj, name):
         if not len(obj) and (havecl or havemf):
             err(0, _("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(node)
         if lr < 0 or (havecl and lr not in linkrevs):
             t = "unexpected"
             if lr < 0 or lr >= len(cl):
                 t = "nonexistent"
             err(None, _("rev %d point to %s changeset %d") % (i, t, lr), f)
             if linkrevs:
                 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
 
     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")
     for i in repo:
         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.status(_("checking manifests\n"))
     seen = {}
     checklog(mf, "manifest")
     for i in mf:
         n = mf.node(i)
         lr = checkentry(mf, i, n, seen, mflinkrevs.get(n, []), "manifest")
         if n in mflinkrevs:
             del mflinkrevs[n]
 
         try:
             for f, fn in mf.readdelta(n).iteritems():
                 if not f:
                     err(lr, _("file without name in manifest"))
                 elif f != "/dev/null":
                     fns = filenodes.setdefault(f, {})
                     if fn not in fns:
                         fns[fn] = n
         except Exception, inst:
             exc(lr, _("reading manifest delta %s") % short(n), inst)
 
     ui.status(_("crosschecking files in changesets and manifests\n"))
 
     if havemf:
         for c, m in util.sort([(c, m) for m in mflinkrevs for c in mflinkrevs[m]]):
             err(c, _("changeset refers to unknown manifest %s") % short(m))
         del mflinkrevs
 
         for f in util.sort(filelinkrevs):
             if f not in filenodes:
                 lr = filelinkrevs[f][0]
                 err(lr, _("in changeset but not in manifest"), f)
 
     if havecl:
         for f in util.sort(filenodes):
             if f not in filelinkrevs:
                 try:
                     lr = min([repo.file(f).linkrev(n) for n in filenodes[f]])
                 except:
                     lr = None
                 err(lr, _("in manifest but not in changeset"), f)
 
     ui.status(_("checking files\n"))
 
-    storefiles = {} 
-    for f, size in repo.store.datafiles(lambda m: err(None, m)):
-        if size > 0:
+    storefiles = {}
+    for f, f2, size in repo.store.datafiles():
+        if not f:
+            err(None, _("cannot decode filename '%s'") % f2)
+        elif size > 0:
             storefiles[f] = True
 
     files = util.sort(util.unique(filenodes.keys() + filelinkrevs.keys()))
     for f in files:
         fl = repo.file(f)
 
-        for ff in fl.files():    
+        for ff in fl.files():
             try:
                 del storefiles[ff]
             except KeyError:
                 err(0, _("missing revlog!"), ff)
 
         checklog(fl, f)
         seen = {}
         for i in fl:
             revisions += 1
             n = fl.node(i)
             lr = checkentry(fl, i, n, seen, filelinkrevs.get(f, []), 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:
                 t = fl.read(n)
                 rp = fl.renamed(n)
                 if len(t) != fl.size(i):
                     if not fl._readmeta(n): # ancient copy?
                         err(lr, _("unpacked size is %s, %s expected") %
                             (len(t), fl.size(i)), f)
             except Exception, inst:
                 exc(lr, _("unpacking %s") % short(n), inst, f)
 
             # check renames
             try:
                 if rp:
                     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:
                         warn(lr, _("copy source revision is nullid %s:%s")
                             % (rp[0], short(rp[1])), f)
                     else:
                         rev = fl2.rev(rp[1])
             except Exception, inst:
                 exc(lr, _("checking rename of %s") % short(n), inst, f)
 
         # cross-check
         if f in filenodes:
             fns = [(mf.linkrev(l), n) for n,l in filenodes[f].items()]
             for lr, node in util.sort(fns):
                 err(lr, _("%s in manifests not found") % short(node), f)
 
     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