merge with stable

mercurial/localrepo.py

@@ -1,2219 +1,2220
 # 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 version 2 or any later version.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup, subrepo, discovery, pushkey
 import changelog, dirstate, filelog, manifest, context, bookmarks, phases
 import lock, transaction, store, encoding
 import scmutil, util, extensions, hook, error, revset
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 from lock import release
 import weakref, errno, os, time, inspect
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
 class localrepository(repo.repository):
     capabilities = set(('lookup', 'changegroupsubset', 'branchmap', 'pushkey',
                         'known', 'getbundle'))
     supportedformats = set(('revlogv1', 'generaldelta'))
     supported = supportedformats | set(('store', 'fncache', 'shared',
                                         'dotencode'))
 
     def __init__(self, baseui, path=None, create=False):
         repo.repository.__init__(self)
         self.root = os.path.realpath(util.expandpath(path))
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.auditor = scmutil.pathauditor(self.root, self._checknested)
         self.opener = scmutil.opener(self.path)
         self.wopener = scmutil.opener(self.root)
         self.baseui = baseui
         self.ui = baseui.copy()
         self._dirtyphases = False
 
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     util.makedirs(path)
                 util.makedir(self.path, notindexed=True)
                 requirements = ["revlogv1"]
                 if self.ui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                         if self.ui.configbool('format', 'dotencode', True):
                             requirements.append('dotencode')
                     # create an invalid changelog
                     self.opener.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'generaldelta', False):
                     requirements.append("generaldelta")
                 requirements = set(requirements)
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 requirements = scmutil.readrequires(self.opener, self.supported)
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = set()
 
         self.sharedpath = self.path
         try:
             s = os.path.realpath(self.opener.read("sharedpath").rstrip('\n'))
             if not os.path.exists(s):
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, scmutil.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
         self._applyrequirements(requirements)
         if create:
             self._writerequirements()
 
 
         self._branchcache = None
         self._branchcachetip = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
     def _applyrequirements(self, requirements):
         self.requirements = requirements
         openerreqs = set(('revlogv1', 'generaldelta'))
         self.sopener.options = dict((r, 1) for r in requirements
                                            if r in openerreqs)
 
     def _writerequirements(self):
         reqfile = self.opener("requires", "w")
         for r in self.requirements:
             reqfile.write("%s\n" % r)
         reqfile.close()
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
+        normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
-            prefix = os.sep.join(parts)
+            prefix = '/'.join(parts)
             if prefix in ctx.substate:
-                if prefix == subpath:
+                if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     @filecache('bookmarks')
     def _bookmarks(self):
         return bookmarks.read(self)
 
     @filecache('bookmarks.current')
     def _bookmarkcurrent(self):
         return bookmarks.readcurrent(self)
 
     def _writebookmarks(self, marks):
       bookmarks.write(self)
 
     @filecache('phaseroots')
     def _phaseroots(self):
         self._dirtyphases = False
         phaseroots = phases.readroots(self)
         phases.filterunknown(self, phaseroots)
         return phaseroots
 
     @propertycache
     def _phaserev(self):
         cache = [0] * len(self)
         for phase in phases.trackedphases:
             roots = map(self.changelog.rev, self._phaseroots[phase])
             if roots:
                 for rev in roots:
                     cache[rev] = phase
                 for rev in self.changelog.descendants(*roots):
                     cache[rev] = phase
         return cache
 
     @filecache('00changelog.i', True)
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         return c
 
     @filecache('00manifest.i', True)
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @filecache('dirstate')
     def dirstate(self):
         warned = [0]
         def validate(node):
             try:
                 self.changelog.rev(node)
                 return node
             except error.LookupError:
                 if not warned[0]:
                     warned[0] = True
                     self.ui.warn(_("warning: ignoring unknown"
                                    " working parent %s!\n") % short(node))
                 return nullid
 
         return dirstate.dirstate(self.opener, self.ui, self.root, validate)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     def revs(self, expr, *args):
         '''Return a list of revisions matching the given revset'''
         expr = revset.formatspec(expr, *args)
         m = revset.match(None, expr)
         return [r for r in m(self, range(len(self)))]
 
     def set(self, expr, *args):
         '''
         Yield a context for each matching revision, after doing arg
         replacement via revset.formatspec
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     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, extra={}):
         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)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         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._tagscache.tagtypes and name in self._tagscache.tagtypes:
                     old = self.tags().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:
                 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
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError, e:
             if e.errno != errno.ENOENT:
                 raise
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         fp.close()
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m)
 
         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'''
 
         if not local:
             for x in self.status()[:5]:
                 if '.hgtags' in x:
                     raise util.Abort(_('working copy of .hgtags is changed '
                                        '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     @propertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         return self._tagscache.tags
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 try:
                     # ignore tags to unknown nodes
                     self.changelog.lookup(node)
                     tags[encoding.tolocal(name)] = node
                 except error.LookupError:
                     pass
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     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
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 r = self.changelog.rev(n)
                 l.append((r, t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self.tags().iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             ctxgen = (self[r] for r in xrange(lrev + 1, tiprev + 1))
             self._updatebranchcache(partial, ctxgen)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def updatebranchcache(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 oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._branchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._branchcache = partial
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         self.updatebranchcache()
         return self._branchcache
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             tip = heads[-1]
             for h in reversed(heads):
                 if 'close' not in self.changelog.read(h)[5]:
                     tip = h
                     break
             bt[bn] = tip
         return bt
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("cache/branchheads")
             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)
                 label = encoding.tolocal(label.strip())
                 partial.setdefault(label, []).append(bin(node))
         except KeyboardInterrupt:
             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("cache/branchheads", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, nodes in branches.iteritems():
                 for node in nodes:
                     f.write("%s %s\n" % (hex(node), encoding.fromlocal(label)))
             f.close()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, ctxgen):
         # collect new branch entries
         newbranches = {}
         for c in ctxgen:
             newbranches.setdefault(c.branch(), []).append(c.node())
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newnodes in newbranches.iteritems():
             bheads = partial.setdefault(branch, [])
             bheads.extend(newnodes)
             if len(bheads) <= 1:
                 continue
             bheads = sorted(bheads, key=lambda x: self[x].rev())
             # starting from tip means fewer passes over reachable
             while newnodes:
                 latest = newnodes.pop()
                 if latest not in bheads:
                     continue
                 minbhrev = self[bheads[0]].node()
                 reachable = self.changelog.reachable(latest, minbhrev)
                 reachable.remove(latest)
                 if reachable:
                     bheads = [b for b in bheads if b not in reachable]
             partial[branch] = bheads
 
     def lookup(self, key):
         if isinstance(key, int):
             return self.changelog.node(key)
         elif key == '.':
             return self.dirstate.p1()
         elif key == 'null':
             return nullid
         elif key == 'tip':
             return self.changelog.tip()
         n = self.changelog._match(key)
         if n:
             return n
         if key in self._bookmarks:
             return self._bookmarks[key]
         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
 
         # can't find key, check if it might have come from damaged dirstate
         if key in self.dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(key))
         try:
             if len(key) == 20:
                 key = hex(key)
         except TypeError:
             pass
         raise error.RepoLookupError(_("unknown revision '%s'") % key)
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def known(self, nodes):
         nm = self.changelog.nodemap
         return [(n in nm) for n in nodes]
 
     def local(self):
         return self
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, 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 _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 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
         return self.filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             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
 
     @propertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @propertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     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.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener.write(filename, data)
             if 'x' in flags:
                 util.setflags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def transaction(self, desc):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise error.RepoError(
                 _("abandoned transaction found - run hg recover"))
 
         journalfiles = self._writejournal(desc)
         renames = [(x, undoname(x)) for x in journalfiles]
 
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def _writejournal(self, desc):
         # save dirstate for rollback
         try:
             ds = self.opener.read("dirstate")
         except IOError:
             ds = ""
         self.opener.write("journal.dirstate", ds)
         self.opener.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.opener.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
 
         bkname = self.join('bookmarks')
         if os.path.exists(bkname):
             util.copyfile(bkname, self.join('journal.bookmarks'))
         else:
             self.opener.write('journal.bookmarks', '')
         phasesname = self.sjoin('phaseroots')
         if os.path.exists(phasesname):
             util.copyfile(phasesname, self.sjoin('journal.phaseroots'))
         else:
             self.sopener.write('journal.phaseroots', '')
 
         return (self.sjoin('journal'), self.join('journal.dirstate'),
                 self.join('journal.branch'), self.join('journal.desc'),
                 self.join('journal.bookmarks'),
                 self.sjoin('journal.phaseroots'))
 
     def recover(self):
         lock = 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.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 return self._rollback(dryrun, force)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     def _rollback(self, dryrun, force):
         ui = self.ui
         try:
             args = self.opener.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise util.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         transaction.rollback(self.sopener, self.sjoin('undo'), ui.warn)
         if os.path.exists(self.join('undo.bookmarks')):
             util.rename(self.join('undo.bookmarks'),
                         self.join('bookmarks'))
         if os.path.exists(self.sjoin('undo.phaseroots')):
             util.rename(self.sjoin('undo.phaseroots'),
                         self.sjoin('phaseroots'))
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             util.rename(self.join('undo.dirstate'), self.join('dirstate'))
             try:
                 branch = self.opener.read('undo.branch')
                 self.dirstate.setbranch(branch)
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             self.dirstate.invalidate()
             parents = tuple([p.rev() for p in self.parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
         self.destroyed()
         return 0
 
     def invalidatecaches(self):
         try:
             delattr(self, '_tagscache')
         except AttributeError:
             pass
 
         self._branchcache = None # in UTF-8
         self._branchcachetip = None
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         try:
             delattr(self, 'dirstate')
         except AttributeError:
             pass
 
     def invalidate(self):
         for k in self._filecache:
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
 
             try:
                 delattr(self, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.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 _afterlock(self, callback):
         """add a callback to the current repository lock.
 
         The callback will be executed on lock release."""
         l = self._lockref and self._lockref()
         if l:
             l.postrelease.append(callback)
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.store.write()
             if self._dirtyphases:
                 phases.writeroots(self)
             for k, ce in self._filecache.items():
                 if k == 'dirstate':
                     continue
                 ce.refresh()
 
         l = self._lock(self.sjoin("lock"), wait, unlock,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         def unlock():
             self.dirstate.write()
             ce = self._filecache.get('dirstate')
             if ce:
                 ce.refresh()
 
         l = self._lock(self.join("wlock"), wait, unlock,
                        self.invalidatedirstate, _('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
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # 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
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self[None].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.dir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             removedsubs = set()
             if '.hgsub' in wctx:
                 # only manage subrepos and .hgsubstate if .hgsub is present
                 for p in wctx.parents():
                     removedsubs.update(s for s in p.substate if match(s))
                 for s in wctx.substate:
                     removedsubs.discard(s)
                     if match(s) and wctx.sub(s).dirty():
                         subs.append(s)
                 if (subs or removedsubs):
                     if (not match('.hgsub') and
                         '.hgsub' in (wctx.modified() + wctx.added())):
                         raise util.Abort(
                             _("can't commit subrepos without .hgsub"))
                     if '.hgsubstate' not in changes[0]:
                         changes[0].insert(0, '.hgsubstate')
                         if '.hgsubstate' in changes[2]:
                             changes[2].remove('.hgsubstate')
             elif '.hgsub' in changes[2]:
                 # clean up .hgsubstate when .hgsub is removed
                 if ('.hgsubstate' in wctx and
                     '.hgsubstate' not in changes[0] + changes[1] + changes[2]):
                     changes[2].insert(0, '.hgsubstate')
 
             if subs and not self.ui.configbool('ui', 'commitsubrepos', False):
                 changedsubs = [s for s in subs if wctx.sub(s).dirty(True)]
                 if changedsubs:
                     raise util.Abort(_("uncommitted changes in subrepo %s")
                                      % changedsubs[0],
                                      hint=_("use --subrepos for recursive commit"))
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             if (not force and not extra.get("close") and not merge
                 and not (changes[0] or changes[1] or changes[2])
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                        "(see hg help resolve)"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs
             if subs or removedsubs:
                 state = wctx.substate.copy()
                 for s in sorted(subs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     state[s] = (state[s][0], sr)
                 subrepo.writestate(self, state)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1, parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except:
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, p1, ret)
             for f in changes[0] + changes[1]:
                 self.dirstate.normal(f)
             for f in changes[2]:
                 self.dirstate.drop(f)
             self.dirstate.setparents(ret)
             ms.reset()
         finally:
             wlock.release()
 
         self.hook("commit", node=hex(ret), parent1=hookp1, parent2=hookp2)
         return ret
 
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = list(ctx.removed())
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.files():
                 m1 = p1.manifest().copy()
                 m2 = p2.manifest()
 
                 # check in files
                 new = {}
                 changed = []
                 linkrev = len(self)
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                                   changed)
                         m1.set(f, fctx.flags())
                     except OSError, inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError, inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                             raise
                         else:
                             removed.append(f)
 
                 # update manifest
                 m1.update(new)
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m1]
                 for f in drop:
                     del m1[f]
                 mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                        p2.manifestnode(), (new, drop))
                 files = changed + removed
             else:
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             # set the new commit is proper phase
             targetphase = self.ui.configint('phases', 'new-commit', 1)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.retractboundary(self, targetphase, [n])
             tr.close()
 
             if self._branchcache:
                 self.updatebranchcache()
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.'''
         # XXX it might be nice if we could take the list of destroyed
         # nodes, but I don't see an easy way for rollback() to do that
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidatecaches()
 
     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,
                listsubrepos=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
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or matchmod.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 if f not in ctx1:
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             subrepos = []
             if '.hgsub' in self.dirstate:
                 subrepos = ctx2.substate.keys()
             s = self.dirstate.status(match, subrepos, 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 sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f])):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     if listclean:
                         clean += fixup
 
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         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 (fn not in deleted and
                         (mf1.flags(fn) != mf2.flags(fn) or
                          (mf1[fn] != mf2[fn] and
                           (mf2[fn] or ctx1[fn].cmp(ctx2[fn]))))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 elif fn not in deleted:
                     added.append(fn)
             removed = mf1.keys()
 
         if working and modified and not self.dirstate._checklink:
             # Symlink placeholders may get non-symlink-like contents
             # via user error or dereferencing by NFS or Samba servers,
             # so we filter out any placeholders that don't look like a
             # symlink
             sane = []
             for f in modified:
                 if ctx2.flags(f) == 'l':
                     d = ctx2[f].data()
                     if len(d) >= 1024 or '\n' in d or util.binary(d):
                         self.ui.debug('ignoring suspect symlink placeholder'
                                       ' "%s"\n' % f)
                         continue
                 sane.append(f)
             modified = sane
 
         r = modified, added, removed, deleted, unknown, ignored, clean
 
         if listsubrepos:
             for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
                 if working:
                     rev2 = None
                 else:
                     rev2 = ctx2.substate[subpath][1]
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self.ui.status(_("skipping missing subrepository: %s\n")
                                    % subpath)
 
         for l in r:
             l.sort()
         return r
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if
                       ('close' not in self.changelog.read(h)[5])]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 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 and n != nullid:
                 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 pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             tmp = discovery.findcommonincoming(self, remote, heads=heads,
                                                force=force)
             common, fetch, rheads = tmp
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 added = []
                 result = 0
             else:
                 if heads is None and list(common) == [nullid]:
                     self.ui.status(_("requesting all changes\n"))
                 elif heads is None and remote.capable('changegroupsubset'):
                     # issue1320, avoid a race if remote changed after discovery
                     heads = rheads
 
                 if remote.capable('getbundle'):
                     cg = remote.getbundle('pull', common=common,
                                           heads=heads or rheads)
                 elif heads is None:
                     cg = remote.changegroup(fetch, 'pull')
                 elif not remote.capable('changegroupsubset'):
                     raise util.Abort(_("partial pull cannot be done because "
                                            "other repository doesn't support "
                                            "changegroupsubset."))
                 else:
                     cg = remote.changegroupsubset(fetch, heads, 'pull')
                 clstart = len(self.changelog)
                 result = self.addchangegroup(cg, 'pull', remote.url())
                 clend = len(self.changelog)
                 added = [self.changelog.node(r) for r in xrange(clstart, clend)]
 
 
             # Get remote phases data from remote
             remotephases = remote.listkeys('phases')
             publishing = bool(remotephases.get('publishing', False))
             if remotephases and not publishing:
                 # remote is new and unpublishing
                 subset = common + added
                 rheads, rroots = phases.analyzeremotephases(self, subset,
                                                             remotephases)
                 for phase, boundary in enumerate(rheads):
                     phases.advanceboundary(self, phase, boundary)
             else:
                 # Remote is old or publishing all common changesets
                 # should be seen as public
                 phases.advanceboundary(self, 0, common + added)
         finally:
             lock.release()
 
         return result
 
     def checkpush(self, force, revs):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
         pass
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         '''Push outgoing changesets (limited by revs) from the current
         repository to remote. Return an integer:
           - 0 means HTTP error *or* nothing to push
           - 1 means we pushed and remote head count is unchanged *or*
             we have outgoing changesets but refused to push
           - other values as described by addchangegroup()
         '''
         # 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).
 
         self.checkpush(force, revs)
         lock = None
         unbundle = remote.capable('unbundle')
         if not unbundle:
             lock = remote.lock()
         try:
             # get local lock as we might write phase data
             locallock = self.lock()
             try:
                 cg, remote_heads, fut = discovery.prepush(self, remote, force,
                                                            revs, newbranch)
                 ret = remote_heads
                 # create a callback for addchangegroup.
                 # If will be used branch of the conditionnal too.
                 if cg is not None:
                     if unbundle:
                         # 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.
                         if force:
                             remote_heads = ['force']
                         # ssh: return remote's addchangegroup()
                         # http: return remote's addchangegroup() or 0 for error
                         ret = remote.unbundle(cg, remote_heads, 'push')
                     else:
                         # we return an integer indicating remote head count change
                         ret = remote.addchangegroup(cg, 'push', self.url())
 
                 # even when we don't push, exchanging phase data is useful
                 remotephases = remote.listkeys('phases')
                 if not remotephases: # old server or public only repo
                     phases.advanceboundary(self, 0, fut)
                     # don't push any phase data as there is nothing to push
                 else:
                     ana = phases.analyzeremotephases(self, fut, remotephases)
                     rheads, rroots = ana
                     ### Apply remote phase on local
                     if remotephases.get('publishing', False):
                         phases.advanceboundary(self, 0, fut)
                     else: # publish = False
                         for phase, rpheads in enumerate(rheads):
                             phases.advanceboundary(self, phase, rpheads)
                     ### Apply local phase on remote
                     #
                     # XXX If push failed we should use strict common and not
                     # future to avoir pushing phase data on unknown changeset.
                     # This is to done later.
                     futctx = [self[n] for n in fut if n != nullid]
                     for phase in phases.trackedphases[::-1]:
                         prevphase = phase -1
                         # get all candidate for head in previous phase
                         inprev = [ctx for ctx in futctx
                                       if ctx.phase() == prevphase]
                         for newremotehead in  self.set('heads(%ld & (%ln::))',
                                               inprev, rroots[phase]):
                             r = remote.pushkey('phases',
                                                newremotehead.hex(),
                                                str(phase), str(prevphase))
                             if not r:
                                 self.ui.warn(_('updating phase of %s'
                                                'to %s failed!\n')
                                                 % (newremotehead, prevphase))
             finally:
                 locallock.release()
         finally:
             if lock is not None:
                 lock.release()
 
         self.ui.debug("checking for updated bookmarks\n")
         rb = remote.listkeys('bookmarks')
         for k in rb.keys():
             if k in self._bookmarks:
                 nr, nl = rb[k], hex(self._bookmarks[k])
                 if nr in self:
                     cr = self[nr]
                     cl = self[nl]
                     if cl in cr.descendants():
                         r = remote.pushkey('bookmarks', k, nr, nl)
                         if r:
                             self.ui.status(_("updating bookmark %s\n") % k)
                         else:
                             self.ui.warn(_('updating bookmark %s'
                                            ' failed!\n') % k)
 
         return ret
 
     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):
         """Compute a changegroup consisting of all the nodes that are
         descendants of any of the bases and ancestors of any of the heads.
         Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         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.
         """
         cl = self.changelog
         if not bases:
             bases = [nullid]
         csets, bases, heads = cl.nodesbetween(bases, heads)
         # We assume that all ancestors of bases are known
         common = set(cl.ancestors(*[cl.rev(n) for n in bases]))
         return self._changegroupsubset(common, csets, heads, source)
 
     def getbundle(self, source, heads=None, common=None):
         """Like changegroupsubset, but returns the set difference between the
         ancestors of heads and the ancestors common.
 
         If heads is None, use the local heads. If common is None, use [nullid].
 
         The nodes in common might not all be known locally due to the way the
         current discovery protocol works.
         """
         cl = self.changelog
         if common:
             nm = cl.nodemap
             common = [n for n in common if n in nm]
         else:
             common = [nullid]
         if not heads:
             heads = cl.heads()
         common, missing = cl.findcommonmissing(common, heads)
         if not missing:
             return None
         return self._changegroupsubset(common, missing, heads, source)
 
     def _changegroupsubset(self, commonrevs, csets, heads, source):
 
         cl = self.changelog
         mf = self.manifest
         mfs = {} # needed manifests
         fnodes = {} # needed file nodes
         changedfiles = set()
         fstate = ['', {}]
         count = [0]
 
         # can we go through the fast path ?
         heads.sort()
         if heads == sorted(self.heads()):
             return self._changegroup(csets, source)
 
         # slow path
         self.hook('preoutgoing', throw=True, source=source)
         self.changegroupinfo(csets, source)
 
         # filter any nodes that claim to be part of the known set
         def prune(revlog, missing):
             return [n for n in missing
                     if revlog.linkrev(revlog.rev(n)) not in commonrevs]
 
         def lookup(revlog, x):
             if revlog == cl:
                 c = cl.read(x)
                 changedfiles.update(c[3])
                 mfs.setdefault(c[0], x)
                 count[0] += 1
                 self.ui.progress(_('bundling'), count[0],
                                  unit=_('changesets'), total=len(csets))
                 return x
             elif revlog == mf:
                 clnode = mfs[x]
                 mdata = mf.readfast(x)
                 for f in changedfiles:
                     if f in mdata:
                         fnodes.setdefault(f, {}).setdefault(mdata[f], clnode)
                 count[0] += 1
                 self.ui.progress(_('bundling'), count[0],
                                  unit=_('manifests'), total=len(mfs))
                 return mfs[x]
             else:
                 self.ui.progress(
                     _('bundling'), count[0], item=fstate[0],
                     unit=_('files'), total=len(changedfiles))
                 return fstate[1][x]
 
         bundler = changegroup.bundle10(lookup)
         reorder = self.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
 
         def gengroup():
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             for chunk in cl.group(csets, bundler, reorder=reorder):
                 yield chunk
             self.ui.progress(_('bundling'), None)
 
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             count[0] = 0
             for chunk in mf.group(prune(mf, mfs), bundler, reorder=reorder):
                 yield chunk
             self.ui.progress(_('bundling'), None)
 
             mfs.clear()
 
             # Go through all our files in order sorted by name.
             count[0] = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 fstate[0] = fname
                 fstate[1] = fnodes.pop(fname, {})
 
                 nodelist = prune(filerevlog, fstate[1])
                 if nodelist:
                     count[0] += 1
                     yield bundler.fileheader(fname)
                     for chunk in filerevlog.group(nodelist, bundler, reorder):
                         yield chunk
 
             # Signal that no more groups are left.
             yield bundler.close()
             self.ui.progress(_('bundling'), None)
 
             if csets:
                 self.hook('outgoing', node=hex(csets[0]), source=source)
 
         return changegroup.unbundle10(util.chunkbuffer(gengroup()), 'UN')
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     def _changegroup(self, nodes, source):
         """Compute the changegroup of all nodes that we have that a recipient
         doesn't.  Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         nodes is the set of nodes to send"""
 
         cl = self.changelog
         mf = self.manifest
         mfs = {}
         changedfiles = set()
         fstate = ['']
         count = [0]
 
         self.hook('preoutgoing', throw=True, source=source)
         self.changegroupinfo(nodes, source)
 
         revset = set([cl.rev(n) for n in nodes])
 
         def gennodelst(log):
             return [log.node(r) for r in log if log.linkrev(r) in revset]
 
         def lookup(revlog, x):
             if revlog == cl:
                 c = cl.read(x)
                 changedfiles.update(c[3])
                 mfs.setdefault(c[0], x)
                 count[0] += 1
                 self.ui.progress(_('bundling'), count[0],
                                  unit=_('changesets'), total=len(nodes))
                 return x
             elif revlog == mf:
                 count[0] += 1
                 self.ui.progress(_('bundling'), count[0],
                                  unit=_('manifests'), total=len(mfs))
                 return cl.node(revlog.linkrev(revlog.rev(x)))
             else:
                 self.ui.progress(
                     _('bundling'), count[0], item=fstate[0],
                     total=len(changedfiles), unit=_('files'))
                 return cl.node(revlog.linkrev(revlog.rev(x)))
 
         bundler = changegroup.bundle10(lookup)
         reorder = self.ui.config('bundle', 'reorder', 'auto')
         if reorder == 'auto':
             reorder = None
         else:
             reorder = util.parsebool(reorder)
 
         def gengroup():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
 
             for chunk in cl.group(nodes, bundler, reorder=reorder):
                 yield chunk
             self.ui.progress(_('bundling'), None)
 
             count[0] = 0
             for chunk in mf.group(gennodelst(mf), bundler, reorder=reorder):
                 yield chunk
             self.ui.progress(_('bundling'), None)
 
             count[0] = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 fstate[0] = fname
                 nodelist = gennodelst(filerevlog)
                 if nodelist:
                     count[0] += 1
                     yield bundler.fileheader(fname)
                     for chunk in filerevlog.group(nodelist, bundler, reorder):
                         yield chunk
             yield bundler.close()
             self.ui.progress(_('bundling'), None)
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return changegroup.unbundle10(util.chunkbuffer(gengroup()), 'UN')
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer 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
         efiles = set()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = cl.heads()
 
         tr = self.transaction("\n".join([srctype, util.hidepassword(url)]))
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 step = _('changesets')
                 count = 1
                 ui = self.ui
                 total = None
                 def __call__(self):
                     self.ui.progress(self.step, self.count, unit=_('chunks'),
                                      total=self.total)
                     self.count += 1
             pr = prog()
             source.callback = pr
 
             source.changelogheader()
             if (cl.addgroup(source, csmap, trp) is None
                 and not emptyok):
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
             for c in xrange(clstart, clend):
                 efiles.update(self[c].files())
             efiles = len(efiles)
             self.ui.progress(_('changesets'), None)
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             pr.step = _('manifests')
             pr.count = 1
             pr.total = changesets # manifests <= changesets
             # 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
             source.manifestheader()
             self.manifest.addgroup(source, revmap, trp)
             self.ui.progress(_('manifests'), None)
 
             needfiles = {}
             if self.ui.configbool('server', 'validate', default=False):
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfest = self.changelog.read(self.changelog.node(cset))[0]
                     mfest = self.manifest.readdelta(mfest)
                     # store file nodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             pr.step = _('files')
             pr.count = 1
             pr.total = efiles
             source.callback = None
 
             while True:
                 chunkdata = source.filelogheader()
                 if not chunkdata:
                     break
                 f = chunkdata["filename"]
                 self.ui.debug("adding %s revisions\n" % f)
                 pr()
                 fl = self.file(f)
                 o = len(fl)
                 if fl.addgroup(source, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
                 if f in needfiles:
                     needs = needfiles[f]
                     for new in xrange(o, len(fl)):
                         n = fl.node(new)
                         if n in needs:
                             needs.remove(n)
                     if not needs:
                         del needfiles[f]
             self.ui.progress(_('files'), None)
 
             for f, needs in needfiles.iteritems():
                 fl = self.file(f)
                 for n in needs:
                     try:
                         fl.rev(n)
                     except error.LookupError:
                         raise util.Abort(
                             _('missing file data for %s:%s - run hg verify') %
                             (f, hex(n)))
 
             dh = 0
             if oldheads:
                 heads = cl.heads()
                 dh = len(heads) - len(oldheads)
                 for h in heads:
                     if h not in oldheads and 'close' in self[h].extra():
                         dh -= 1
             htext = ""
             if dh:
                 htext = _(" (%+d heads)") % dh
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, htext))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             added = [cl.node(r) for r in xrange(clstart, clend)]
             publishing = self.ui.configbool('phases', 'publish', True)
             if publishing and srctype == 'push':
                 # Old server can not push the boundary themself.
                 # This clause ensure pushed changeset are alway marked as public
                 phases.advanceboundary(self, 0, added)
             elif srctype != 'strip': # strip should not touch boundary at all
                 phases.retractboundary(self, 1, added)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
 
             if changesets > 0:
                 def runhooks():
                     # forcefully update the on-disk branch cache
                     self.ui.debug("updating the branch cache\n")
                     self.updatebranchcache()
                     self.hook("changegroup", node=hex(cl.node(clstart)),
                               source=srctype, url=url)
 
                     for n in added:
                         self.hook("incoming", node=hex(n), source=srctype,
                                   url=url)
                 self._afterlock(runhooks)
 
         finally:
             tr.release()
         # never return 0 here:
         if dh < 0:
             return dh - 1
         else:
             return dh + 1
 
     def stream_in(self, remote, requirements):
         lock = self.lock()
         try:
             fp = remote.stream_out()
             l = fp.readline()
             try:
                 resp = int(l)
             except ValueError:
                 raise error.ResponseError(
                     _('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 error.ResponseError(
                     _('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 error.ResponseError(
                         _('Unexpected response from remote server:'), l)
                 self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
                 # for backwards compat, name was partially encoded
                 ofp = self.sopener(store.decodedir(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)))
 
             # new requirements = old non-format requirements + new format-related
             # requirements from the streamed-in repository
             requirements.update(set(self.requirements) - self.supportedformats)
             self._applyrequirements(requirements)
             self._writerequirements()
 
             self.invalidate()
             return len(self.heads()) + 1
         finally:
             lock.release()
 
     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:
             # 'stream' means remote revlog format is revlogv1 only
             if remote.capable('stream'):
                 return self.stream_in(remote, set(('revlogv1',)))
             # otherwise, 'streamreqs' contains the remote revlog format
             streamreqs = remote.capable('streamreqs')
             if streamreqs:
                 streamreqs = set(streamreqs.split(','))
                 # if we support it, stream in and adjust our requirements
                 if not streamreqs - self.supportedformats:
                     return self.stream_in(remote, streamreqs)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         self.hook('prepushkey', throw=True, namespace=namespace, key=key,
                   old=old, new=new)
         ret = pushkey.push(self, namespace, key, old, new)
         self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                   ret=ret)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
     def savecommitmessage(self, text):
         fp = self.opener('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root)+1:])
 
 # 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 undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True

mercurial/scmutil.py

@@ -1,813 +1,814
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import util, error, osutil, revset, similar, encoding
 import match as matchmod
 import os, errno, re, stat, sys, glob
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise util.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise util.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, existingiter):
         self._ui = ui
         self._abort = abort
         self._map = {}
         for f in existingiter:
             self._map[encoding.lower(f)] = f
 
     def __call__(self, f):
         fl = encoding.lower(f)
         map = self._map
         if fl in map and map[fl] != f:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise util.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         map[fl] = f
 
 class pathauditor(object):
     '''ensure that a filesystem path contains no banned components.
     the following properties of a path are checked:
 
     - ends with a directory separator
     - under top-level .hg
     - starts at the root of a windows drive
     - contains ".."
     - traverses a symlink (e.g. a/symlink_here/b)
     - inside a nested repository (a callback can be used to approve
       some nested repositories, e.g., subrepositories)
     '''
 
     def __init__(self, root, callback=None):
         self.audited = set()
         self.auditeddir = set()
         self.root = root
         self.callback = callback
         if os.path.lexists(root) and not util.checkcase(root):
             self.normcase = util.normcase
         else:
             self.normcase = lambda x: x
 
     def __call__(self, path):
         '''Check the relative path.
         path may contain a pattern (e.g. foodir/**.txt)'''
 
+        path = util.localpath(path)
         normpath = self.normcase(path)
         if normpath in self.audited:
             return
         # AIX ignores "/" at end of path, others raise EISDIR.
         if util.endswithsep(path):
             raise util.Abort(_("path ends in directory separator: %s") % path)
         parts = util.splitpath(path)
         if (os.path.splitdrive(path)[0]
             or parts[0].lower() in ('.hg', '.hg.', '')
             or os.pardir in parts):
             raise util.Abort(_("path contains illegal component: %s") % path)
         if '.hg' in path.lower():
             lparts = [p.lower() for p in parts]
             for p in '.hg', '.hg.':
                 if p in lparts[1:]:
                     pos = lparts.index(p)
                     base = os.path.join(*parts[:pos])
                     raise util.Abort(_("path '%s' is inside nested repo %r")
                                      % (path, base))
 
         normparts = util.splitpath(normpath)
         assert len(parts) == len(normparts)
 
         parts.pop()
         normparts.pop()
         prefixes = []
         while parts:
             prefix = os.sep.join(parts)
             normprefix = os.sep.join(normparts)
             if normprefix in self.auditeddir:
                 break
             curpath = os.path.join(self.root, prefix)
             try:
                 st = os.lstat(curpath)
             except OSError, err:
                 # EINVAL can be raised as invalid path syntax under win32.
                 # They must be ignored for patterns can be checked too.
                 if err.errno not in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
                     raise
             else:
                 if stat.S_ISLNK(st.st_mode):
                     raise util.Abort(
                         _('path %r traverses symbolic link %r')
                         % (path, prefix))
                 elif (stat.S_ISDIR(st.st_mode) and
                       os.path.isdir(os.path.join(curpath, '.hg'))):
                     if not self.callback or not self.callback(curpath):
                         raise util.Abort(_("path '%s' is inside nested repo %r") %
                                          (path, prefix))
             prefixes.append(normprefix)
             parts.pop()
             normparts.pop()
 
         self.audited.add(normpath)
         # only add prefixes to the cache after checking everything: we don't
         # want to add "foo/bar/baz" before checking if there's a "foo/.hg"
         self.auditeddir.update(prefixes)
 
 class abstractopener(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def read(self, path):
         fp = self(path, 'rb')
         try:
             return fp.read()
         finally:
             fp.close()
 
     def write(self, path, data):
         fp = self(path, 'wb')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def append(self, path, data):
         fp = self(path, 'ab')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
 class opener(abstractopener):
     '''Open files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True):
         self.base = base
         self._audit = audit
         if audit:
             self.auditor = pathauditor(base)
         else:
             self.auditor = util.always
         self.createmode = None
         self._trustnlink = None
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None:
             return
         os.chmod(name, self.createmode & 0666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False):
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise util.Abort("%s: %r" % (r, path))
         self.auditor(path)
         f = os.path.join(self.base, path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         dirname, basename = os.path.split(f)
         # If basename is empty, then the path is malformed because it points
         # to a directory. Let the posixfile() call below raise IOError.
         if basename and mode not in ('r', 'rb'):
             if atomictemp:
                 if not os.path.isdir(dirname):
                     util.makedirs(dirname, self.createmode)
                 return util.atomictempfile(f, mode, self.createmode)
             try:
                 if 'w' in mode:
                     util.unlink(f)
                     nlink = 0
                 else:
                     # nlinks() may behave differently for files on Windows
                     # shares if the file is open.
                     fd = util.posixfile(f)
                     nlink = util.nlinks(f)
                     if nlink < 1:
                         nlink = 2 # force mktempcopy (issue1922)
                     fd.close()
             except (OSError, IOError), e:
                 if e.errno != errno.ENOENT:
                     raise
                 nlink = 0
                 if not os.path.isdir(dirname):
                     util.makedirs(dirname, self.createmode)
             if nlink > 0:
                 if self._trustnlink is None:
                     self._trustnlink = nlink > 1 or util.checknlink(f)
                 if nlink > 1 or not self._trustnlink:
                     util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.auditor(dst)
         linkname = os.path.join(self.base, dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         dirname = os.path.dirname(linkname)
         if not os.path.exists(dirname):
             util.makedirs(dirname, self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError, err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             f = self(dst, "w")
             f.write(src)
             f.close()
             self._fixfilemode(dst)
 
     def audit(self, path):
         self.auditor(path)
 
 class filteropener(abstractopener):
     '''Wrapper opener for filtering filenames with a function.'''
 
     def __init__(self, opener, filter):
         self._filter = filter
         self._orig = opener
 
     def __call__(self, path, *args, **kwargs):
         return self._orig(self._filter(path), *args, **kwargs)
 
 def canonpath(root, cwd, myname, auditor=None):
     '''return the canonical path of myname, given cwd and root'''
     if util.endswithsep(root):
         rootsep = root
     else:
         rootsep = root + os.sep
     name = myname
     if not os.path.isabs(name):
         name = os.path.join(root, cwd, name)
     name = os.path.normpath(name)
     if auditor is None:
         auditor = pathauditor(root)
     if name != rootsep and name.startswith(rootsep):
         name = name[len(rootsep):]
         auditor(name)
         return util.pconvert(name)
     elif name == root:
         return ''
     else:
         # Determine whether `name' is in the hierarchy at or beneath `root',
         # by iterating name=dirname(name) until that causes no change (can't
         # check name == '/', because that doesn't work on windows).  For each
         # `name', compare dev/inode numbers.  If they match, the list `rel'
         # holds the reversed list of components making up the relative file
         # name we want.
         root_st = os.stat(root)
         rel = []
         while True:
             try:
                 name_st = os.stat(name)
             except OSError:
                 break
             if util.samestat(name_st, root_st):
                 if not rel:
                     # name was actually the same as root (maybe a symlink)
                     return ''
                 rel.reverse()
                 name = os.path.join(*rel)
                 auditor(name)
                 return util.pconvert(name)
             dirname, basename = os.path.split(name)
             rel.append(basename)
             if dirname == name:
                 break
             name = dirname
 
         raise util.Abort('%s not under root' % myname)
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, recursively.'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = systemrcpath()
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 if os.name != 'nt':
 
     def rcfiles(path):
         rcs = [os.path.join(path, 'hgrc')]
         rcdir = os.path.join(path, 'hgrc.d')
         try:
             rcs.extend([os.path.join(rcdir, f)
                         for f, kind in osutil.listdir(rcdir)
                         if f.endswith(".rc")])
         except OSError:
             pass
         return rcs
 
     def systemrcpath():
         path = []
         # old mod_python does not set sys.argv
         if len(getattr(sys, 'argv', [])) > 0:
             p = os.path.dirname(os.path.dirname(sys.argv[0]))
             path.extend(rcfiles(os.path.join(p, 'etc/mercurial')))
         path.extend(rcfiles('/etc/mercurial'))
         return path
 
     def userrcpath():
         return [os.path.expanduser('~/.hgrc')]
 
 else:
 
     _HKEY_LOCAL_MACHINE = 0x80000002L
 
     def systemrcpath():
         '''return default os-specific hgrc search path'''
         rcpath = []
         filename = util.executablepath()
         # Use mercurial.ini found in directory with hg.exe
         progrc = os.path.join(os.path.dirname(filename), 'mercurial.ini')
         if os.path.isfile(progrc):
             rcpath.append(progrc)
             return rcpath
         # Use hgrc.d found in directory with hg.exe
         progrcd = os.path.join(os.path.dirname(filename), 'hgrc.d')
         if os.path.isdir(progrcd):
             for f, kind in osutil.listdir(progrcd):
                 if f.endswith('.rc'):
                     rcpath.append(os.path.join(progrcd, f))
             return rcpath
         # else look for a system rcpath in the registry
         value = util.lookupreg('SOFTWARE\\Mercurial', None,
                                _HKEY_LOCAL_MACHINE)
         if not isinstance(value, str) or not value:
             return rcpath
         value = value.replace('/', os.sep)
         for p in value.split(os.pathsep):
             if p.lower().endswith('mercurial.ini'):
                 rcpath.append(p)
             elif os.path.isdir(p):
                 for f, kind in osutil.listdir(p):
                     if f.endswith('.rc'):
                         rcpath.append(os.path.join(p, f))
         return rcpath
 
     def userrcpath():
         '''return os-specific hgrc search path to the user dir'''
         home = os.path.expanduser('~')
         path = [os.path.join(home, 'mercurial.ini'),
                 os.path.join(home, '.hgrc')]
         userprofile = os.environ.get('USERPROFILE')
         if userprofile:
             path.append(os.path.join(userprofile, 'mercurial.ini'))
             path.append(os.path.join(userprofile, '.hgrc'))
         return path
 
 def revsingle(repo, revspec, default='.'):
     if not revspec:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if len(l) < 1:
         raise util.Abort(_('empty revision set'))
     return repo[l[-1]]
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if len(l) == 0:
         return repo.dirstate.p1(), None
 
     if len(l) == 1:
         return repo.lookup(l[0]), None
 
     return repo.lookup(l[0]), repo.lookup(l[-1])
 
 _revrangesep = ':'
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             return defval
         return repo.changelog.rev(repo.lookup(val))
 
     seen, l = set(), []
     for spec in revs:
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         try:
             if isinstance(spec, int):
                 seen.add(spec)
                 l.append(spec)
                 continue
 
             if _revrangesep in spec:
                 start, end = spec.split(_revrangesep, 1)
                 start = revfix(repo, start, 0)
                 end = revfix(repo, end, len(repo) - 1)
                 step = start > end and -1 or 1
                 for rev in xrange(start, end + step, step):
                     if rev in seen:
                         continue
                     seen.add(rev)
                     l.append(rev)
                 continue
             elif spec and spec in repo: # single unquoted rev
                 rev = revfix(repo, spec, None)
                 if rev in seen:
                     continue
                 seen.add(rev)
                 l.append(rev)
                 continue
         except error.RepoLookupError:
             pass
 
         # fall through to new-style queries if old-style fails
         m = revset.match(repo.ui, spec)
         for r in m(repo, range(len(repo))):
             if r not in seen:
                 l.append(r)
         seen.update(l)
 
     return l
 
 def expandpats(pats):
     if not util.expandglobs:
         return list(pats)
     ret = []
     for p in pats:
         kind, name = matchmod._patsplit(p, None)
         if kind is None:
             try:
                 globbed = glob.glob(name)
             except re.error:
                 globbed = [name]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(p)
     return ret
 
 def match(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     if pats == ("",):
         pats = []
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                          default)
     def badfn(f, msg):
         ctx._repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
     m.bad = badfn
     return m
 
 def matchall(repo):
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files):
     return matchmod.exact(repo.root, repo.getcwd(), files)
 
 def addremove(repo, pats=[], opts={}, dry_run=None, similarity=None):
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
     # we'd use status here, except handling of symlinks and ignore is tricky
     added, unknown, deleted, removed = [], [], [], []
     audit_path = pathauditor(repo.root)
     m = match(repo[None], pats, opts)
     for abs in repo.walk(m):
         target = repo.wjoin(abs)
         good = True
         try:
             audit_path(abs)
         except (OSError, util.Abort):
             good = False
         rel = m.rel(abs)
         exact = m.exact(abs)
         if good and abs not in repo.dirstate:
             unknown.append(abs)
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('adding %s\n') % ((pats and rel) or abs))
         elif repo.dirstate[abs] != 'r' and (not good or not os.path.lexists(target)
             or (os.path.isdir(target) and not os.path.islink(target))):
             deleted.append(abs)
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('removing %s\n') % ((pats and rel) or abs))
         # for finding renames
         elif repo.dirstate[abs] == 'r':
             removed.append(abs)
         elif repo.dirstate[abs] == 'a':
             added.append(abs)
     copies = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo,
                 added + unknown, removed + deleted, similarity):
             if repo.ui.verbose or not m.exact(old) or not m.exact(new):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (m.rel(old), m.rel(new), score * 100))
             copies[new] = old
 
     if not dry_run:
         wctx = repo[None]
         wlock = repo.wlock()
         try:
             wctx.forget(deleted)
             wctx.add(unknown)
             for new, old in copies.iteritems():
                 wctx.copy(old, new)
         finally:
             wlock.release()
 
 def updatedir(ui, repo, patches, similarity=0):
     '''Update dirstate after patch application according to metadata'''
     if not patches:
         return []
     copies = []
     removes = set()
     cfiles = patches.keys()
     cwd = repo.getcwd()
     if cwd:
         cfiles = [util.pathto(repo.root, cwd, f) for f in patches.keys()]
     for f in patches:
         gp = patches[f]
         if not gp:
             continue
         if gp.op == 'RENAME':
             copies.append((gp.oldpath, gp.path))
             removes.add(gp.oldpath)
         elif gp.op == 'COPY':
             copies.append((gp.oldpath, gp.path))
         elif gp.op == 'DELETE':
             removes.add(gp.path)
 
     wctx = repo[None]
     for src, dst in copies:
         dirstatecopy(ui, repo, wctx, src, dst, cwd=cwd)
     if (not similarity) and removes:
         wctx.remove(sorted(removes), True)
 
     for f in patches:
         gp = patches[f]
         if gp and gp.mode:
             islink, isexec = gp.mode
             dst = repo.wjoin(gp.path)
             # patch won't create empty files
             if gp.op == 'ADD' and not os.path.lexists(dst):
                 flags = (isexec and 'x' or '') + (islink and 'l' or '')
                 repo.wwrite(gp.path, '', flags)
             util.setflags(dst, islink, isexec)
     addremove(repo, cfiles, similarity=similarity)
     files = patches.keys()
     files.extend([r for r in removes if r not in files])
     return sorted(files)
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(_("unknown repository format: "
             "requires features '%s' (upgrade Mercurial)") % "', '".join(missings))
     return requirements
 
 class filecacheentry(object):
     def __init__(self, path):
         self.path = path
         self.cachestat = filecacheentry.stat(self.path)
 
         if self.cachestat:
             self._cacheable = self.cachestat.cacheable()
         else:
             # None means we don't know yet
             self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecacheentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecacheentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecache(object):
     '''A property like decorator that tracks a file under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates
     the object when needed, updating the new stat info in _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behaviour as
     propertycache).'''
     def __init__(self, path, instore=False):
         self.path = path
         self.instore = instore
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             path = self.instore and obj.sjoin(self.path) or obj.join(self.path)
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(path)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         setattr(obj, self.name, entry.obj)
         return entry.obj

mercurial/subrepo.py

@@ -1,1149 +1,1149
 # subrepo.py - sub-repository handling for Mercurial
 #
 # Copyright 2009-2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import errno, os, re, xml.dom.minidom, shutil, posixpath
 import stat, subprocess, tarfile
 from i18n import _
 import config, scmutil, util, node, error, cmdutil, bookmarks
 hg = None
 propertycache = util.propertycache
 
 nullstate = ('', '', 'empty')
 
 def state(ctx, ui):
     """return a state dict, mapping subrepo paths configured in .hgsub
     to tuple: (source from .hgsub, revision from .hgsubstate, kind
     (key in types dict))
     """
     p = config.config()
     def read(f, sections=None, remap=None):
         if f in ctx:
             try:
                 data = ctx[f].data()
             except IOError, err:
                 if err.errno != errno.ENOENT:
                     raise
                 # handle missing subrepo spec files as removed
                 ui.warn(_("warning: subrepo spec file %s not found\n") % f)
                 return
             p.parse(f, data, sections, remap, read)
         else:
             raise util.Abort(_("subrepo spec file %s not found") % f)
 
     if '.hgsub' in ctx:
         read('.hgsub')
 
     for path, src in ui.configitems('subpaths'):
         p.set('subpaths', path, src, ui.configsource('subpaths', path))
 
     rev = {}
     if '.hgsubstate' in ctx:
         try:
             for l in ctx['.hgsubstate'].data().splitlines():
                 revision, path = l.split(" ", 1)
                 rev[path] = revision
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
 
     def remap(src):
         for pattern, repl in p.items('subpaths'):
             # Turn r'C:\foo\bar' into r'C:\\foo\\bar' since re.sub
             # does a string decode.
             repl = repl.encode('string-escape')
             # However, we still want to allow back references to go
             # through unharmed, so we turn r'\\1' into r'\1'. Again,
             # extra escapes are needed because re.sub string decodes.
             repl = re.sub(r'\\\\([0-9]+)', r'\\\1', repl)
             try:
                 src = re.sub(pattern, repl, src, 1)
             except re.error, e:
                 raise util.Abort(_("bad subrepository pattern in %s: %s")
                                  % (p.source('subpaths', pattern), e))
         return src
 
     state = {}
     for path, src in p[''].items():
         kind = 'hg'
         if src.startswith('['):
             if ']' not in src:
                 raise util.Abort(_('missing ] in subrepo source'))
             kind, src = src.split(']', 1)
             kind = kind[1:]
             src = src.lstrip() # strip any extra whitespace after ']'
 
         if not util.url(src).isabs():
             parent = _abssource(ctx._repo, abort=False)
             if parent:
                 parent = util.url(parent)
                 parent.path = posixpath.join(parent.path or '', src)
                 parent.path = posixpath.normpath(parent.path)
                 joined = str(parent)
                 # Remap the full joined path and use it if it changes,
                 # else remap the original source.
                 remapped = remap(joined)
                 if remapped == joined:
                     src = remap(src)
                 else:
                     src = remapped
 
         src = remap(src)
-        state[path] = (src.strip(), rev.get(path, ''), kind)
+        state[util.pconvert(path)] = (src.strip(), rev.get(path, ''), kind)
 
     return state
 
 def writestate(repo, state):
     """rewrite .hgsubstate in (outer) repo with these subrepo states"""
     lines = ['%s %s\n' % (state[s][1], s) for s in sorted(state)]
     repo.wwrite('.hgsubstate', ''.join(lines), '')
 
 def submerge(repo, wctx, mctx, actx, overwrite):
     """delegated from merge.applyupdates: merging of .hgsubstate file
     in working context, merging context and ancestor context"""
     if mctx == actx: # backwards?
         actx = wctx.p1()
     s1 = wctx.substate
     s2 = mctx.substate
     sa = actx.substate
     sm = {}
 
     repo.ui.debug("subrepo merge %s %s %s\n" % (wctx, mctx, actx))
 
     def debug(s, msg, r=""):
         if r:
             r = "%s:%s:%s" % r
         repo.ui.debug("  subrepo %s: %s %s\n" % (s, msg, r))
 
     for s, l in s1.items():
         a = sa.get(s, nullstate)
         ld = l # local state with possible dirty flag for compares
         if wctx.sub(s).dirty():
             ld = (l[0], l[1] + "+")
         if wctx == actx: # overwrite
             a = ld
 
         if s in s2:
             r = s2[s]
             if ld == r or r == a: # no change or local is newer
                 sm[s] = l
                 continue
             elif ld == a: # other side changed
                 debug(s, "other changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             elif ld[0] != r[0]: # sources differ
                 if repo.ui.promptchoice(
                     _(' subrepository sources for %s differ\n'
                       'use (l)ocal source (%s) or (r)emote source (%s)?')
                       % (s, l[0], r[0]),
                       (_('&Local'), _('&Remote')), 0):
                     debug(s, "prompt changed, get", r)
                     wctx.sub(s).get(r, overwrite)
                     sm[s] = r
             elif ld[1] == a[1]: # local side is unchanged
                 debug(s, "other side changed, get", r)
                 wctx.sub(s).get(r, overwrite)
                 sm[s] = r
             else:
                 debug(s, "both sides changed, merge with", r)
                 wctx.sub(s).merge(r)
                 sm[s] = l
         elif ld == a: # remote removed, local unchanged
             debug(s, "remote removed, remove")
             wctx.sub(s).remove()
         elif a == nullstate: # not present in remote or ancestor
             debug(s, "local added, keep")
             sm[s] = l
             continue
         else:
             if repo.ui.promptchoice(
                 _(' local changed subrepository %s which remote removed\n'
                   'use (c)hanged version or (d)elete?') % s,
                 (_('&Changed'), _('&Delete')), 0):
                 debug(s, "prompt remove")
                 wctx.sub(s).remove()
 
     for s, r in sorted(s2.items()):
         if s in s1:
             continue
         elif s not in sa:
             debug(s, "remote added, get", r)
             mctx.sub(s).get(r)
             sm[s] = r
         elif r != sa[s]:
             if repo.ui.promptchoice(
                 _(' remote changed subrepository %s which local removed\n'
                   'use (c)hanged version or (d)elete?') % s,
                 (_('&Changed'), _('&Delete')), 0) == 0:
                 debug(s, "prompt recreate", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
 
     # record merged .hgsubstate
     writestate(repo, sm)
 
 def _updateprompt(ui, sub, dirty, local, remote):
     if dirty:
         msg = (_(' subrepository sources for %s differ\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n')
                % (subrelpath(sub), local, remote))
     else:
         msg = (_(' subrepository sources for %s differ (in checked out version)\n'
                  'use (l)ocal source (%s) or (r)emote source (%s)?\n')
                % (subrelpath(sub), local, remote))
     return ui.promptchoice(msg, (_('&Local'), _('&Remote')), 0)
 
 def reporelpath(repo):
     """return path to this (sub)repo as seen from outermost repo"""
     parent = repo
     while util.safehasattr(parent, '_subparent'):
         parent = parent._subparent
     p = parent.root.rstrip(os.sep)
     return repo.root[len(p) + 1:]
 
 def subrelpath(sub):
     """return path to this subrepo as seen from outermost repo"""
     if util.safehasattr(sub, '_relpath'):
         return sub._relpath
     if not util.safehasattr(sub, '_repo'):
         return sub._path
     return reporelpath(sub._repo)
 
 def _abssource(repo, push=False, abort=True):
     """return pull/push path of repo - either based on parent repo .hgsub info
     or on the top repo config. Abort or return None if no source found."""
     if util.safehasattr(repo, '_subparent'):
         source = util.url(repo._subsource)
         if source.isabs():
             return str(source)
         source.path = posixpath.normpath(source.path)
         parent = _abssource(repo._subparent, push, abort=False)
         if parent:
             parent = util.url(util.pconvert(parent))
             parent.path = posixpath.join(parent.path or '', source.path)
             parent.path = posixpath.normpath(parent.path)
             return str(parent)
     else: # recursion reached top repo
         if util.safehasattr(repo, '_subtoppath'):
             return repo._subtoppath
         if push and repo.ui.config('paths', 'default-push'):
             return repo.ui.config('paths', 'default-push')
         if repo.ui.config('paths', 'default'):
             return repo.ui.config('paths', 'default')
     if abort:
         raise util.Abort(_("default path for subrepository %s not found") %
             reporelpath(repo))
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
 def subrepo(ctx, path):
     """return instance of the right subrepo class for subrepo in path"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     import hg as h
     hg = h
 
     scmutil.pathauditor(ctx._repo.root)(path)
     state = ctx.substate.get(path, nullstate)
     if state[2] not in types:
         raise util.Abort(_('unknown subrepo type %s') % state[2])
     return types[state[2]](ctx, path, state[:2])
 
 # subrepo classes need to implement the following abstract class:
 
 class abstractsubrepo(object):
 
     def dirty(self, ignoreupdate=False):
         """returns true if the dirstate of the subrepo is dirty or does not
         match current stored state. If ignoreupdate is true, only check
         whether the subrepo has uncommitted changes in its dirstate.
         """
         raise NotImplementedError
 
     def checknested(self, path):
         """check if path is a subrepository within this repository"""
         return False
 
     def commit(self, text, user, date):
         """commit the current changes to the subrepo with the given
         log message. Use given user and date if possible. Return the
         new state of the subrepo.
         """
         raise NotImplementedError
 
     def remove(self):
         """remove the subrepo
 
         (should verify the dirstate is not dirty first)
         """
         raise NotImplementedError
 
     def get(self, state, overwrite=False):
         """run whatever commands are needed to put the subrepo into
         this state
         """
         raise NotImplementedError
 
     def merge(self, state):
         """merge currently-saved state with the new state."""
         raise NotImplementedError
 
     def push(self, opts):
         """perform whatever action is analogous to 'hg push'
 
         This may be a no-op on some systems.
         """
         raise NotImplementedError
 
     def add(self, ui, match, dryrun, prefix):
         return []
 
     def status(self, rev2, **opts):
         return [], [], [], [], [], [], []
 
     def diff(self, diffopts, node2, match, prefix, **opts):
         pass
 
     def outgoing(self, ui, dest, opts):
         return 1
 
     def incoming(self, ui, source, opts):
         return 1
 
     def files(self):
         """return filename iterator"""
         raise NotImplementedError
 
     def filedata(self, name):
         """return file data"""
         raise NotImplementedError
 
     def fileflags(self, name):
         """return file flags"""
         return ''
 
     def archive(self, ui, archiver, prefix):
         files = self.files()
         total = len(files)
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0,
                     unit=_('files'), total=total)
         for i, name in enumerate(files):
             flags = self.fileflags(name)
             mode = 'x' in flags and 0755 or 0644
             symlink = 'l' in flags
             archiver.addfile(os.path.join(prefix, self._path, name),
                              mode, symlink, self.filedata(name))
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'), total=total)
         ui.progress(_('archiving (%s)') % relpath, None)
 
     def walk(self, match):
         '''
         walk recursively through the directory tree, finding all files
         matched by the match function
         '''
         pass
 
     def forget(self, files):
         pass
 
 class hgsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         r = ctx._repo
         root = r.wjoin(path)
         create = False
         if not os.path.exists(os.path.join(root, '.hg')):
             create = True
             util.makedirs(root)
         self._repo = hg.repository(r.ui, root, create=create)
         self._initrepo(r, state[0], create)
 
     def _initrepo(self, parentrepo, source, create):
         self._repo._subparent = parentrepo
         self._repo._subsource = source
 
         if create:
             fp = self._repo.opener("hgrc", "w", text=True)
             fp.write('[paths]\n')
 
             def addpathconfig(key, value):
                 if value:
                     fp.write('%s = %s\n' % (key, value))
                     self._repo.ui.setconfig('paths', key, value)
 
             defpath = _abssource(self._repo, abort=False)
             defpushpath = _abssource(self._repo, True, abort=False)
             addpathconfig('default', defpath)
             if defpath != defpushpath:
                 addpathconfig('default-push', defpushpath)
             fp.close()
 
     def add(self, ui, match, dryrun, prefix):
         return cmdutil.add(ui, self._repo, match, dryrun, True,
                            os.path.join(prefix, self._path))
 
     def status(self, rev2, **opts):
         try:
             rev1 = self._state[1]
             ctx1 = self._repo[rev1]
             ctx2 = self._repo[rev2]
             return self._repo.status(ctx1, ctx2, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
             return [], [], [], [], [], [], []
 
     def diff(self, diffopts, node2, match, prefix, **opts):
         try:
             node1 = node.bin(self._state[1])
             # We currently expect node2 to come from substate and be
             # in hex format
             if node2 is not None:
                 node2 = node.bin(node2)
             cmdutil.diffordiffstat(self._repo.ui, self._repo, diffopts,
                                    node1, node2, match,
                                    prefix=os.path.join(prefix, self._path),
                                    listsubrepos=True, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_('warning: error "%s" in subrepository "%s"\n')
                                % (inst, subrelpath(self)))
 
     def archive(self, ui, archiver, prefix):
         self._get(self._state + ('hg',))
         abstractsubrepo.archive(self, ui, archiver, prefix)
 
         rev = self._state[1]
         ctx = self._repo[rev]
         for subpath in ctx.substate:
             s = subrepo(ctx, subpath)
             s.archive(ui, archiver, os.path.join(prefix, self._path))
 
     def dirty(self, ignoreupdate=False):
         r = self._state[1]
         if r == '' and not ignoreupdate: # no state recorded
             return True
         w = self._repo[None]
         if r != w.p1().hex() and not ignoreupdate:
             # different version checked out
             return True
         return w.dirty() # working directory changed
 
     def checknested(self, path):
         return self._repo._checknested(self._repo.wjoin(path))
 
     def commit(self, text, user, date):
         # don't bother committing in the subrepo if it's only been
         # updated
         if not self.dirty(True):
             return self._repo['.'].hex()
         self._repo.ui.debug("committing subrepo %s\n" % subrelpath(self))
         n = self._repo.commit(text, user, date)
         if not n:
             return self._repo['.'].hex() # different version checked out
         return node.hex(n)
 
     def remove(self):
         # we can't fully delete the repository as it may contain
         # local-only history
         self._repo.ui.note(_('removing subrepo %s\n') % subrelpath(self))
         hg.clean(self._repo, node.nullid, False)
 
     def _get(self, state):
         source, revision, kind = state
         if revision not in self._repo:
             self._repo._subsource = source
             srcurl = _abssource(self._repo)
             other = hg.peer(self._repo.ui, {}, srcurl)
             if len(self._repo) == 0:
                 self._repo.ui.status(_('cloning subrepo %s from %s\n')
                                      % (subrelpath(self), srcurl))
                 parentrepo = self._repo._subparent
                 shutil.rmtree(self._repo.path)
                 other, self._repo = hg.clone(self._repo._subparent.ui, {}, other,
                                          self._repo.root, update=False)
                 self._initrepo(parentrepo, source, create=True)
             else:
                 self._repo.ui.status(_('pulling subrepo %s from %s\n')
                                      % (subrelpath(self), srcurl))
                 self._repo.pull(other)
             bookmarks.updatefromremote(self._repo.ui, self._repo, other,
                                        srcurl)
 
     def get(self, state, overwrite=False):
         self._get(state)
         source, revision, kind = state
         self._repo.ui.debug("getting subrepo %s\n" % self._path)
         hg.clean(self._repo, revision, False)
 
     def merge(self, state):
         self._get(state)
         cur = self._repo['.']
         dst = self._repo[state[1]]
         anc = dst.ancestor(cur)
 
         def mergefunc():
             if anc == cur:
                 self._repo.ui.debug("updating subrepo %s\n" % subrelpath(self))
                 hg.update(self._repo, state[1])
             elif anc == dst:
                 self._repo.ui.debug("skipping subrepo %s\n" % subrelpath(self))
             else:
                 self._repo.ui.debug("merging subrepo %s\n" % subrelpath(self))
                 hg.merge(self._repo, state[1], remind=False)
 
         wctx = self._repo[None]
         if self.dirty():
             if anc != dst:
                 if _updateprompt(self._repo.ui, self, wctx.dirty(), cur, dst):
                     mergefunc()
             else:
                 mergefunc()
         else:
             mergefunc()
 
     def push(self, opts):
         force = opts.get('force')
         newbranch = opts.get('new_branch')
         ssh = opts.get('ssh')
 
         # push subrepos depth-first for coherent ordering
         c = self._repo['']
         subs = c.substate # only repos that are committed
         for s in sorted(subs):
             if not c.sub(s).push(opts):
                 return False
 
         dsturl = _abssource(self._repo, True)
         self._repo.ui.status(_('pushing subrepo %s to %s\n') %
             (subrelpath(self), dsturl))
         other = hg.peer(self._repo.ui, {'ssh': ssh}, dsturl)
         return self._repo.push(other, force, newbranch=newbranch)
 
     def outgoing(self, ui, dest, opts):
         return hg.outgoing(ui, self._repo, _abssource(self._repo, True), opts)
 
     def incoming(self, ui, source, opts):
         return hg.incoming(ui, self._repo, _abssource(self._repo, False), opts)
 
     def files(self):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.manifest()
 
     def filedata(self, name):
         rev = self._state[1]
         return self._repo[rev][name].data()
 
     def fileflags(self, name):
         rev = self._state[1]
         ctx = self._repo[rev]
         return ctx.flags(name)
 
     def walk(self, match):
         ctx = self._repo[None]
         return ctx.walk(match)
 
     def forget(self, files):
         ctx = self._repo[None]
         ctx.forget(files)
 
 class svnsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         self._ctx = ctx
         self._ui = ctx._repo.ui
         self._exe = util.findexe('svn')
         if not self._exe:
             raise util.Abort(_("'svn' executable not found for subrepo '%s'")
                              % self._path)
 
     def _svncommand(self, commands, filename='', failok=False):
         cmd = [self._exe]
         extrakw = {}
         if not self._ui.interactive():
             # Making stdin be a pipe should prevent svn from behaving
             # interactively even if we can't pass --non-interactive.
             extrakw['stdin'] = subprocess.PIPE
             # Starting in svn 1.5 --non-interactive is a global flag
             # instead of being per-command, but we need to support 1.4 so
             # we have to be intelligent about what commands take
             # --non-interactive.
             if commands[0] in ('update', 'checkout', 'commit'):
                 cmd.append('--non-interactive')
         cmd.extend(commands)
         if filename is not None:
             path = os.path.join(self._ctx._repo.origroot, self._path, filename)
             cmd.append(path)
         env = dict(os.environ)
         # Avoid localized output, preserve current locale for everything else.
         env['LC_MESSAGES'] = 'C'
         p = subprocess.Popen(cmd, bufsize=-1, close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                               universal_newlines=True, env=env, **extrakw)
         stdout, stderr = p.communicate()
         stderr = stderr.strip()
         if not failok:
             if p.returncode:
                 raise util.Abort(stderr or 'exited with code %d' % p.returncode)
             if stderr:
                 self._ui.warn(stderr + '\n')
         return stdout, stderr
 
     @propertycache
     def _svnversion(self):
         output, err = self._svncommand(['--version'], filename=None)
         m = re.search(r'^svn,\s+version\s+(\d+)\.(\d+)', output)
         if not m:
             raise util.Abort(_('cannot retrieve svn tool version'))
         return (int(m.group(1)), int(m.group(2)))
 
     def _wcrevs(self):
         # Get the working directory revision as well as the last
         # commit revision so we can compare the subrepo state with
         # both. We used to store the working directory one.
         output, err = self._svncommand(['info', '--xml'])
         doc = xml.dom.minidom.parseString(output)
         entries = doc.getElementsByTagName('entry')
         lastrev, rev = '0', '0'
         if entries:
             rev = str(entries[0].getAttribute('revision')) or '0'
             commits = entries[0].getElementsByTagName('commit')
             if commits:
                 lastrev = str(commits[0].getAttribute('revision')) or '0'
         return (lastrev, rev)
 
     def _wcrev(self):
         return self._wcrevs()[0]
 
     def _wcchanged(self):
         """Return (changes, extchanges) where changes is True
         if the working directory was changed, and extchanges is
         True if any of these changes concern an external entry.
         """
         output, err = self._svncommand(['status', '--xml'])
         externals, changes = [], []
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             s = e.getElementsByTagName('wc-status')
             if not s:
                 continue
             item = s[0].getAttribute('item')
             props = s[0].getAttribute('props')
             path = e.getAttribute('path')
             if item == 'external':
                 externals.append(path)
             if (item not in ('', 'normal', 'unversioned', 'external')
                 or props not in ('', 'none', 'normal')):
                 changes.append(path)
         for path in changes:
             for ext in externals:
                 if path == ext or path.startswith(ext + os.sep):
                     return True, True
         return bool(changes), False
 
     def dirty(self, ignoreupdate=False):
         if not self._wcchanged()[0]:
             if self._state[1] in self._wcrevs() or ignoreupdate:
                 return False
         return True
 
     def commit(self, text, user, date):
         # user and date are out of our hands since svn is centralized
         changed, extchanged = self._wcchanged()
         if not changed:
             return self._wcrev()
         if extchanged:
             # Do not try to commit externals
             raise util.Abort(_('cannot commit svn externals'))
         commitinfo, err = self._svncommand(['commit', '-m', text])
         self._ui.status(commitinfo)
         newrev = re.search('Committed revision ([0-9]+).', commitinfo)
         if not newrev:
             raise util.Abort(commitinfo.splitlines()[-1])
         newrev = newrev.groups()[0]
         self._ui.status(self._svncommand(['update', '-r', newrev])[0])
         return newrev
 
     def remove(self):
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n' % self._path))
             return
         self._ui.note(_('removing subrepo %s\n') % self._path)
 
         def onerror(function, path, excinfo):
             if function is not os.remove:
                 raise
             # read-only files cannot be unlinked under Windows
             s = os.stat(path)
             if (s.st_mode & stat.S_IWRITE) != 0:
                 raise
             os.chmod(path, stat.S_IMODE(s.st_mode) | stat.S_IWRITE)
             os.remove(path)
 
         path = self._ctx._repo.wjoin(self._path)
         shutil.rmtree(path, onerror=onerror)
         try:
             os.removedirs(os.path.dirname(path))
         except OSError:
             pass
 
     def get(self, state, overwrite=False):
         if overwrite:
             self._svncommand(['revert', '--recursive'])
         args = ['checkout']
         if self._svnversion >= (1, 5):
             args.append('--force')
         # The revision must be specified at the end of the URL to properly
         # update to a directory which has since been deleted and recreated.
         args.append('%s@%s' % (state[0], state[1]))
         status, err = self._svncommand(args, failok=True)
         if not re.search('Checked out revision [0-9]+.', status):
             if ('is already a working copy for a different URL' in err
                 and (self._wcchanged() == (False, False))):
                 # obstructed but clean working copy, so just blow it away.
                 self.remove()
                 self.get(state, overwrite=False)
                 return
             raise util.Abort((status or err).splitlines()[-1])
         self._ui.status(status)
 
     def merge(self, state):
         old = self._state[1]
         new = state[1]
         if new != self._wcrev():
             dirty = old == self._wcrev() or self._wcchanged()[0]
             if _updateprompt(self._ui, self, dirty, self._wcrev(), new):
                 self.get(state, False)
 
     def push(self, opts):
         # push is a no-op for SVN
         return True
 
     def files(self):
         output = self._svncommand(['list'])
         # This works because svn forbids \n in filenames.
         return output.splitlines()
 
     def filedata(self, name):
         return self._svncommand(['cat'], name)
 
 
 class gitsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         # TODO add git version check.
         self._state = state
         self._ctx = ctx
         self._path = path
         self._relpath = os.path.join(reporelpath(ctx._repo), path)
         self._abspath = ctx._repo.wjoin(path)
         self._subparent = ctx._repo
         self._ui = ctx._repo.ui
 
     def _gitcommand(self, commands, env=None, stream=False):
         return self._gitdir(commands, env=env, stream=stream)[0]
 
     def _gitdir(self, commands, env=None, stream=False):
         return self._gitnodir(commands, env=env, stream=stream,
                               cwd=self._abspath)
 
     def _gitnodir(self, commands, env=None, stream=False, cwd=None):
         """Calls the git command
 
         The methods tries to call the git command. versions previor to 1.6.0
         are not supported and very probably fail.
         """
         self._ui.debug('%s: git %s\n' % (self._relpath, ' '.join(commands)))
         # unless ui.quiet is set, print git's stderr,
         # which is mostly progress and useful info
         errpipe = None
         if self._ui.quiet:
             errpipe = open(os.devnull, 'w')
         p = subprocess.Popen(['git'] + commands, bufsize=-1, cwd=cwd, env=env,
                              close_fds=util.closefds,
                              stdout=subprocess.PIPE, stderr=errpipe)
         if stream:
             return p.stdout, None
 
         retdata = p.stdout.read().strip()
         # wait for the child to exit to avoid race condition.
         p.wait()
 
         if p.returncode != 0 and p.returncode != 1:
             # there are certain error codes that are ok
             command = commands[0]
             if command in ('cat-file', 'symbolic-ref'):
                 return retdata, p.returncode
             # for all others, abort
             raise util.Abort('git %s error %d in %s' %
                              (command, p.returncode, self._relpath))
 
         return retdata, p.returncode
 
     def _gitmissing(self):
         return not os.path.exists(os.path.join(self._abspath, '.git'))
 
     def _gitstate(self):
         return self._gitcommand(['rev-parse', 'HEAD'])
 
     def _gitcurrentbranch(self):
         current, err = self._gitdir(['symbolic-ref', 'HEAD', '--quiet'])
         if err:
             current = None
         return current
 
     def _gitremote(self, remote):
         out = self._gitcommand(['remote', 'show', '-n', remote])
         line = out.split('\n')[1]
         i = line.index('URL: ') + len('URL: ')
         return line[i:]
 
     def _githavelocally(self, revision):
         out, code = self._gitdir(['cat-file', '-e', revision])
         return code == 0
 
     def _gitisancestor(self, r1, r2):
         base = self._gitcommand(['merge-base', r1, r2])
         return base == r1
 
     def _gitisbare(self):
         return self._gitcommand(['config', '--bool', 'core.bare']) == 'true'
 
     def _gitupdatestat(self):
         """This must be run before git diff-index.
         diff-index only looks at changes to file stat;
         this command looks at file contents and updates the stat."""
         self._gitcommand(['update-index', '-q', '--refresh'])
 
     def _gitbranchmap(self):
         '''returns 2 things:
         a map from git branch to revision
         a map from revision to branches'''
         branch2rev = {}
         rev2branch = {}
 
         out = self._gitcommand(['for-each-ref', '--format',
                                 '%(objectname) %(refname)'])
         for line in out.split('\n'):
             revision, ref = line.split(' ')
             if (not ref.startswith('refs/heads/') and
                 not ref.startswith('refs/remotes/')):
                 continue
             if ref.startswith('refs/remotes/') and ref.endswith('/HEAD'):
                 continue # ignore remote/HEAD redirects
             branch2rev[ref] = revision
             rev2branch.setdefault(revision, []).append(ref)
         return branch2rev, rev2branch
 
     def _gittracking(self, branches):
         'return map of remote branch to local tracking branch'
         # assumes no more than one local tracking branch for each remote
         tracking = {}
         for b in branches:
             if b.startswith('refs/remotes/'):
                 continue
             bname = b.split('/', 2)[2]
             remote = self._gitcommand(['config', 'branch.%s.remote' % bname])
             if remote:
                 ref = self._gitcommand(['config', 'branch.%s.merge' % bname])
                 tracking['refs/remotes/%s/%s' %
                          (remote, ref.split('/', 2)[2])] = b
         return tracking
 
     def _abssource(self, source):
         if '://' not in source:
             # recognize the scp syntax as an absolute source
             colon = source.find(':')
             if colon != -1 and '/' not in source[:colon]:
                 return source
         self._subsource = source
         return _abssource(self)
 
     def _fetch(self, source, revision):
         if self._gitmissing():
             source = self._abssource(source)
             self._ui.status(_('cloning subrepo %s from %s\n') %
                             (self._relpath, source))
             self._gitnodir(['clone', source, self._abspath])
         if self._githavelocally(revision):
             return
         self._ui.status(_('pulling subrepo %s from %s\n') %
                         (self._relpath, self._gitremote('origin')))
         # try only origin: the originally cloned repo
         self._gitcommand(['fetch'])
         if not self._githavelocally(revision):
             raise util.Abort(_("revision %s does not exist in subrepo %s\n") %
                                (revision, self._relpath))
 
     def dirty(self, ignoreupdate=False):
         if self._gitmissing():
             return self._state[1] != ''
         if self._gitisbare():
             return True
         if not ignoreupdate and self._state[1] != self._gitstate():
             # different version checked out
             return True
         # check for staged changes or modified files; ignore untracked files
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
         return code == 1
 
     def get(self, state, overwrite=False):
         source, revision, kind = state
         if not revision:
             self.remove()
             return
         self._fetch(source, revision)
         # if the repo was set to be bare, unbare it
         if self._gitisbare():
             self._gitcommand(['config', 'core.bare', 'false'])
             if self._gitstate() == revision:
                 self._gitcommand(['reset', '--hard', 'HEAD'])
                 return
         elif self._gitstate() == revision:
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # reset --hard will otherwise throw away files added for commit,
                 # not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 self._gitcommand(['reset', '--hard', 'HEAD'])
             return
         branch2rev, rev2branch = self._gitbranchmap()
 
         def checkout(args):
             cmd = ['checkout']
             if overwrite:
                 # first reset the index to unmark new files for commit, because
                 # the -f option will otherwise throw away files added for
                 # commit, not just unmark them.
                 self._gitcommand(['reset', 'HEAD'])
                 cmd.append('-f')
             self._gitcommand(cmd + args)
 
         def rawcheckout():
             # no branch to checkout, check it out with no branch
             self._ui.warn(_('checking out detached HEAD in subrepo %s\n') %
                           self._relpath)
             self._ui.warn(_('check out a git branch if you intend '
                             'to make changes\n'))
             checkout(['-q', revision])
 
         if revision not in rev2branch:
             rawcheckout()
             return
         branches = rev2branch[revision]
         firstlocalbranch = None
         for b in branches:
             if b == 'refs/heads/master':
                 # master trumps all other branches
                 checkout(['refs/heads/master'])
                 return
             if not firstlocalbranch and not b.startswith('refs/remotes/'):
                 firstlocalbranch = b
         if firstlocalbranch:
             checkout([firstlocalbranch])
             return
 
         tracking = self._gittracking(branch2rev.keys())
         # choose a remote branch already tracked if possible
         remote = branches[0]
         if remote not in tracking:
             for b in branches:
                 if b in tracking:
                     remote = b
                     break
 
         if remote not in tracking:
             # create a new local tracking branch
             local = remote.split('/', 2)[2]
             checkout(['-b', local, remote])
         elif self._gitisancestor(branch2rev[tracking[remote]], remote):
             # When updating to a tracked remote branch,
             # if the local tracking branch is downstream of it,
             # a normal `git pull` would have performed a "fast-forward merge"
             # which is equivalent to updating the local branch to the remote.
             # Since we are only looking at branching at update, we need to
             # detect this situation and perform this action lazily.
             if tracking[remote] != self._gitcurrentbranch():
                 checkout([tracking[remote]])
             self._gitcommand(['merge', '--ff', remote])
         else:
             # a real merge would be required, just checkout the revision
             rawcheckout()
 
     def commit(self, text, user, date):
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         cmd = ['commit', '-a', '-m', text]
         env = os.environ.copy()
         if user:
             cmd += ['--author', user]
         if date:
             # git's date parser silently ignores when seconds < 1e9
             # convert to ISO8601
             env['GIT_AUTHOR_DATE'] = util.datestr(date,
                                                   '%Y-%m-%dT%H:%M:%S %1%2')
         self._gitcommand(cmd, env=env)
         # make sure commit works otherwise HEAD might not exist under certain
         # circumstances
         return self._gitstate()
 
     def merge(self, state):
         source, revision, kind = state
         self._fetch(source, revision)
         base = self._gitcommand(['merge-base', revision, self._state[1]])
         self._gitupdatestat()
         out, code = self._gitdir(['diff-index', '--quiet', 'HEAD'])
 
         def mergefunc():
             if base == revision:
                 self.get(state) # fast forward merge
             elif base != self._state[1]:
                 self._gitcommand(['merge', '--no-commit', revision])
 
         if self.dirty():
             if self._gitstate() != revision:
                 dirty = self._gitstate() == self._state[1] or code != 0
                 if _updateprompt(self._ui, self, dirty,
                                  self._state[1][:7], revision[:7]):
                     mergefunc()
         else:
             mergefunc()
 
     def push(self, opts):
         force = opts.get('force')
 
         if not self._state[1]:
             return True
         if self._gitmissing():
             raise util.Abort(_("subrepo %s is missing") % self._relpath)
         # if a branch in origin contains the revision, nothing to do
         branch2rev, rev2branch = self._gitbranchmap()
         if self._state[1] in rev2branch:
             for b in rev2branch[self._state[1]]:
                 if b.startswith('refs/remotes/origin/'):
                     return True
         for b, revision in branch2rev.iteritems():
             if b.startswith('refs/remotes/origin/'):
                 if self._gitisancestor(self._state[1], revision):
                     return True
         # otherwise, try to push the currently checked out branch
         cmd = ['push']
         if force:
             cmd.append('--force')
 
         current = self._gitcurrentbranch()
         if current:
             # determine if the current branch is even useful
             if not self._gitisancestor(self._state[1], current):
                 self._ui.warn(_('unrelated git branch checked out '
                                 'in subrepo %s\n') % self._relpath)
                 return False
             self._ui.status(_('pushing branch %s of subrepo %s\n') %
                             (current.split('/', 2)[2], self._relpath))
             self._gitcommand(cmd + ['origin', current])
             return True
         else:
             self._ui.warn(_('no branch checked out in subrepo %s\n'
                             'cannot push revision %s') %
                           (self._relpath, self._state[1]))
             return False
 
     def remove(self):
         if self._gitmissing():
             return
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n') % self._relpath)
             return
         # we can't fully delete the repository as it may contain
         # local-only history
         self._ui.note(_('removing subrepo %s\n') % self._relpath)
         self._gitcommand(['config', 'core.bare', 'true'])
         for f in os.listdir(self._abspath):
             if f == '.git':
                 continue
             path = os.path.join(self._abspath, f)
             if os.path.isdir(path) and not os.path.islink(path):
                 shutil.rmtree(path)
             else:
                 os.remove(path)
 
     def archive(self, ui, archiver, prefix):
         source, revision = self._state
         if not revision:
             return
         self._fetch(source, revision)
 
         # Parse git's native archive command.
         # This should be much faster than manually traversing the trees
         # and objects with many subprocess calls.
         tarstream = self._gitcommand(['archive', revision], stream=True)
         tar = tarfile.open(fileobj=tarstream, mode='r|')
         relpath = subrelpath(self)
         ui.progress(_('archiving (%s)') % relpath, 0, unit=_('files'))
         for i, info in enumerate(tar):
             if info.isdir():
                 continue
             if info.issym():
                 data = info.linkname
             else:
                 data = tar.extractfile(info).read()
             archiver.addfile(os.path.join(prefix, self._path, info.name),
                              info.mode, info.issym(), data)
             ui.progress(_('archiving (%s)') % relpath, i + 1,
                         unit=_('files'))
         ui.progress(_('archiving (%s)') % relpath, None)
 
 
     def status(self, rev2, **opts):
         rev1 = self._state[1]
         if self._gitmissing() or not rev1:
             # if the repo is missing, return no results
             return [], [], [], [], [], [], []
         modified, added, removed = [], [], []
         self._gitupdatestat()
         if rev2:
             command = ['diff-tree', rev1, rev2]
         else:
             command = ['diff-index', rev1]
         out = self._gitcommand(command)
         for line in out.split('\n'):
             tab = line.find('\t')
             if tab == -1:
                 continue
             status, f = line[tab - 1], line[tab + 1:]
             if status == 'M':
                 modified.append(f)
             elif status == 'A':
                 added.append(f)
             elif status == 'D':
                 removed.append(f)
 
         deleted = unknown = ignored = clean = []
         return modified, added, removed, deleted, unknown, ignored, clean
 
 types = {
     'hg': hgsubrepo,
     'svn': svnsubrepo,
     'git': gitsubrepo,
     }