dirstate: don't check state of subrepo directories

contrib/perf.py

@@ -1,153 +1,152
 # perf.py - performance test routines
 '''helper extension to measure performance'''
 
 from mercurial import cmdutil, match, commands
 import time, os, sys
 
 def timer(func, title=None):
     results = []
     begin = time.time()
     count = 0
     while 1:
         ostart = os.times()
         cstart = time.time()
         r = func()
         cstop = time.time()
         ostop = os.times()
         count += 1
         a, b = ostart, ostop
         results.append((cstop - cstart, b[0] - a[0], b[1]-a[1]))
         if cstop - begin > 3 and count >= 100:
             break
         if cstop - begin > 10 and count >= 3:
             break
     if title:
         sys.stderr.write("! %s\n" % title)
     if r:
         sys.stderr.write("! result: %s\n" % r)
     m = min(results)
     sys.stderr.write("! wall %f comb %f user %f sys %f (best of %d)\n"
                      % (m[0], m[1] + m[2], m[1], m[2], count))
 
 def perfwalk(ui, repo, *pats):
     try:
         m = cmdutil.match(repo, pats, {})
-        timer(lambda: len(list(repo.dirstate.walk(m, True, False))))
+        timer(lambda: len(list(repo.dirstate.walk(m, [], True, False))))
     except:
         try:
             m = cmdutil.match(repo, pats, {})
             timer(lambda: len([b for a,b,c in repo.dirstate.statwalk([], m)]))
         except:
             timer(lambda: len(list(cmdutil.walk(repo, pats, {}))))
 
 def perfstatus(ui, repo, *pats):
     #m = match.always(repo.root, repo.getcwd())
     #timer(lambda: sum(map(len, repo.dirstate.status(m, False, False, False))))
     timer(lambda: sum(map(len, repo.status())))
 
 def perfheads(ui, repo):
     timer(lambda: len(repo.changelog.heads()))
 
 def perftags(ui, repo):
     import mercurial.changelog, mercurial.manifest
     def t():
         repo.changelog = mercurial.changelog.changelog(repo.sopener)
         repo.manifest = mercurial.manifest.manifest(repo.sopener)
         repo._tags = None
         return len(repo.tags())
     timer(t)
 
 def perfdirstate(ui, repo):
     "a" in repo.dirstate
     def d():
         repo.dirstate.invalidate()
         "a" in repo.dirstate
     timer(d)
 
 def perfdirstatedirs(ui, repo):
     "a" in repo.dirstate
     def d():
         "a" in repo.dirstate._dirs
         del repo.dirstate._dirs
     timer(d)
 
 def perfmanifest(ui, repo):
     def d():
         t = repo.manifest.tip()
         m = repo.manifest.read(t)
         repo.manifest.mapcache = None
         repo.manifest._cache = None
     timer(d)
 
 def perfindex(ui, repo):
     import mercurial.changelog
     def d():
         t = repo.changelog.tip()
         repo.changelog = mercurial.changelog.changelog(repo.sopener)
         repo.changelog._loadindexmap()
     timer(d)
 
 def perfstartup(ui, repo):
     cmd = sys.argv[0]
     def d():
         os.system("HGRCPATH= %s version -q > /dev/null" % cmd)
     timer(d)
 
 def perfparents(ui, repo):
     nl = [repo.changelog.node(i) for i in xrange(1000)]
     def d():
         for n in nl:
             repo.changelog.parents(n)
     timer(d)
 
 def perflookup(ui, repo, rev):
     timer(lambda: len(repo.lookup(rev)))
 
 def perflog(ui, repo, **opts):
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=[], date='', user='',
                                copies=opts.get('rename')))
     ui.popbuffer()
 
 def perftemplating(ui, repo):
     ui.pushbuffer()
     timer(lambda: commands.log(ui, repo, rev=[], date='', user='',
                                template='{date|shortdate} [{rev}:{node|short}]'
                                ' {author|person}: {desc|firstline}\n'))
     ui.popbuffer()
 
 def perfdiffwd(ui, repo):
     """Profile diff of working directory changes"""
     options = {
         'w': 'ignore_all_space',
         'b': 'ignore_space_change',
         'B': 'ignore_blank_lines',
         }
 
     for diffopt in ('', 'w', 'b', 'B', 'wB'):
         opts = dict((options[c], '1') for c in diffopt)
         def d():
             ui.pushbuffer()
             commands.diff(ui, repo, **opts)
             ui.popbuffer()
         title = 'diffopts: %s' % (diffopt and ('-' + diffopt) or 'none')
         timer(d, title)
 
 cmdtable = {
     'perflookup': (perflookup, []),
     'perfparents': (perfparents, []),
     'perfstartup': (perfstartup, []),
     'perfstatus': (perfstatus, []),
     'perfwalk': (perfwalk, []),
     'perfmanifest': (perfmanifest, []),
     'perfindex': (perfindex, []),
     'perfheads': (perfheads, []),
     'perftags': (perftags, []),
     'perfdirstate': (perfdirstate, []),
     'perfdirstatedirs': (perfdirstate, []),
     'perflog': (perflog,
                 [('', 'rename', False, 'ask log to follow renames')]),
     'perftemplating': (perftemplating, []),
     'perfdiffwd': (perfdiffwd, []),
 }
-

hgext/inotify/__init__.py

@@ -1,87 +1,87
 # __init__.py - inotify-based status acceleration for Linux
 #
 # Copyright 2006, 2007, 2008 Bryan O'Sullivan <[e-mail]>
 # Copyright 2007, 2008 Brendan Cully <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 '''accelerate status report using Linux's inotify service'''
 
 # todo: socket permissions
 
 from mercurial.i18n import _
 from mercurial import cmdutil, util
 import server
 from client import client, QueryFailed
 
 def serve(ui, repo, **opts):
     '''start an inotify server for this repository'''
     server.start(ui, repo.dirstate, repo.root, opts)
 
 def debuginotify(ui, repo, **opts):
     '''debugging information for inotify extension
 
     Prints the list of directories being watched by the inotify server.
     '''
     cli = client(ui, repo)
     response = cli.debugquery()
 
     ui.write(_('directories being watched:\n'))
     for path in response:
         ui.write(('  %s/\n') % path)
 
 def reposetup(ui, repo):
     if not hasattr(repo, 'dirstate'):
         return
 
     class inotifydirstate(repo.dirstate.__class__):
 
         # We'll set this to false after an unsuccessful attempt so that
         # next calls of status() within the same instance don't try again
         # to start an inotify server if it won't start.
         _inotifyon = True
 
-        def status(self, match, ignored, clean, unknown=True):
+        def status(self, match, subrepos, ignored, clean, unknown=True):
             files = match.files()
             if '.' in files:
                 files = []
-            if self._inotifyon and not ignored and not self._dirty:
+            if self._inotifyon and not ignored and not subrepos and not self._dirty:
                 cli = client(ui, repo)
                 try:
                     result = cli.statusquery(files, match, False,
                                             clean, unknown)
                 except QueryFailed, instr:
                     ui.debug(str(instr))
                     # don't retry within the same hg instance
                     inotifydirstate._inotifyon = False
                     pass
                 else:
                     if ui.config('inotify', 'debug'):
                         r2 = super(inotifydirstate, self).status(
                             match, False, clean, unknown)
                         for c,a,b in zip('LMARDUIC', result, r2):
                             for f in a:
                                 if f not in b:
                                     ui.warn('*** inotify: %s +%s\n' % (c, f))
                             for f in b:
                                 if f not in a:
                                     ui.warn('*** inotify: %s -%s\n' % (c, f))
                         result = r2
                     return result
             return super(inotifydirstate, self).status(
-                match, ignored, clean, unknown)
+                match, subrepos, ignored, clean, unknown)
 
     repo.dirstate.__class__ = inotifydirstate
 
 cmdtable = {
     'debuginotify':
         (debuginotify, [], ('hg debuginotify')),
     '^inserve':
         (serve,
          [('d', 'daemon', None, _('run server in background')),
           ('', 'daemon-pipefds', '', _('used internally by daemon mode')),
           ('t', 'idle-timeout', '', _('minutes to sit idle before exiting')),
           ('', 'pid-file', '', _('name of file to write process ID to'))],
          _('hg inserve [OPTION]...')),
     }

mercurial/context.py

@@ -1,830 +1,831
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 from node import nullid, nullrev, short, hex
 from i18n import _
 import ancestor, bdiff, error, util, subrepo
 import os, errno
 
 propertycache = util.propertycache
 
 class changectx(object):
     """A changecontext object makes access to data related to a particular
     changeset convenient."""
     def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
         if changeid == '':
             changeid = '.'
         self._repo = repo
         if isinstance(changeid, (long, int)):
             self._rev = changeid
             self._node = self._repo.changelog.node(changeid)
         else:
             self._node = self._repo.lookup(changeid)
             self._rev = self._repo.changelog.rev(self._node)
 
     def __str__(self):
         return short(self.node())
 
     def __int__(self):
         return self.rev()
 
     def __repr__(self):
         return "<changectx %s>" % str(self)
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.read(self.node())
 
     @propertycache
     def _manifest(self):
         return self._repo.manifest.read(self._changeset[0])
 
     @propertycache
     def _manifestdelta(self):
         return self._repo.manifest.readdelta(self._changeset[0])
 
     @propertycache
     def _parents(self):
         p = self._repo.changelog.parentrevs(self._rev)
         if p[1] == nullrev:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     @propertycache
     def substate(self):
         return subrepo.state(self)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         for f in sorted(self._manifest):
             yield f
 
     def changeset(self): return self._changeset
     def manifest(self): return self._manifest
     def manifestnode(self): return self._changeset[0]
 
     def rev(self): return self._rev
     def node(self): return self._node
     def hex(self): return hex(self._node)
     def user(self): return self._changeset[1]
     def date(self): return self._changeset[2]
     def files(self): return self._changeset[3]
     def description(self): return self._changeset[4]
     def branch(self): return self._changeset[5].get("branch")
     def extra(self): return self._changeset[5]
     def tags(self): return self._repo.nodetags(self._node)
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         if len(self._parents) == 2:
             return self._parents[1]
         return changectx(self._repo, -1)
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors(self._rev):
             yield changectx(self._repo, a)
 
     def descendants(self):
         for d in self._repo.changelog.descendants(self._rev):
             yield changectx(self._repo, d)
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.LookupError(self._node, path,
                                         _('not found in manifest'))
         if '_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return self._manifestdelta[path], self._manifestdelta.flags(path)
         node, flag = self._repo.manifest.find(self._changeset[0], path)
         if not node:
             raise error.LookupError(self._node, path,
                                     _('not found in manifest'))
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return ''
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
     def ancestor(self, c2):
         """
         return the ancestor context of self and c2
         """
         # deal with workingctxs
         n2 = c2._node
         if n2 == None:
             n2 = c2._parents[0]._node
         n = self._repo.changelog.ancestor(self._node, n2)
         return changectx(self._repo, n)
 
     def walk(self, match):
         fset = set(match.files())
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
         for fn in self:
             for ffn in fset:
                 # match if the file is the exact name or a directory
                 if ffn == fn or fn.startswith("%s/" % ffn):
                     fset.remove(ffn)
                     break
             if match(fn):
                 yield fn
         for fn in sorted(fset):
             if match.bad(fn, 'No such file in rev ' + str(self)) and match(fn):
                 yield fn
 
     def sub(self, path):
         return subrepo.subrepo(self, path)
 
 class filectx(object):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
     def __init__(self, repo, path, changeid=None, fileid=None,
                  filelog=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (changeid is not None
                 or fileid is not None
                 or changectx is not None), \
                 ("bad args: changeid=%r, fileid=%r, changectx=%r"
                  % (changeid, fileid, changectx))
 
         if filelog:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         return changectx(self._repo, self._changeid)
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if '_changectx' in self.__dict__:
             return self._changectx.rev()
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if '_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     def __str__(self):
         return "%s@%s" % (self.path(), short(self.node()))
 
     def __repr__(self):
         return "<filectx %s>" % str(self)
 
     def __hash__(self):
         try:
             return hash((self._path, self._fileid))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (self._path == other._path
                     and self._fileid == other._fileid)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filectx(self, fileid):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(self._repo, self._path, fileid=fileid,
                        filelog=self._filelog)
 
     def filerev(self): return self._filerev
     def filenode(self): return self._filenode
     def flags(self): return self._changectx.flags(self._path)
     def filelog(self): return self._filelog
 
     def rev(self):
         if '_changectx' in self.__dict__:
             return self._changectx.rev()
         if '_changeid' in self.__dict__:
             return self._changectx.rev()
         return self._filelog.linkrev(self._filerev)
 
     def linkrev(self): return self._filelog.linkrev(self._filerev)
     def node(self): return self._changectx.node()
     def hex(self): return hex(self.node())
     def user(self): return self._changectx.user()
     def date(self): return self._changectx.date()
     def files(self): return self._changectx.files()
     def description(self): return self._changectx.description()
     def branch(self): return self._changectx.branch()
     def extra(self): return self._changectx.extra()
     def manifest(self): return self._changectx.manifest()
     def changectx(self): return self._changectx
 
     def data(self): return self._filelog.read(self._filenode)
     def path(self): return self._path
     def size(self): return self._filelog.size(self._filerev)
 
     def cmp(self, text): return self._filelog.cmp(self._filenode, text)
 
     def renamed(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return renamed
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def parents(self):
         p = self._path
         fl = self._filelog
         pl = [(p, n, fl) for n in self._filelog.parents(self._filenode)]
 
         r = self._filelog.renamed(self._filenode)
         if r:
             pl[0] = (r[0], r[1], None)
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p,n,l in pl if n != nullid]
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [filectx(self._repo, self._path, fileid=x,
                         filelog=self._filelog) for x in c]
 
     def annotate(self, follow=False, linenumber=None):
         '''returns a list of tuples of (ctx, line) for each line
         in the file, where ctx is the filectx of the node where
         that line was last changed.
         This returns tuples of ((ctx, linenumber), line) for each line,
         if "linenumber" parameter is NOT "None".
         In such tuples, linenumber means one at the first appearance
         in the managed file.
         To reduce annotation cost,
         this returns fixed value(False is used) as linenumber,
         if "linenumber" parameter is "False".'''
 
         def decorate_compat(text, rev):
             return ([rev] * len(text.splitlines()), text)
 
         def without_linenumber(text, rev):
             return ([(rev, False)] * len(text.splitlines()), text)
 
         def with_linenumber(text, rev):
             size = len(text.splitlines())
             return ([(rev, i) for i in xrange(1, size + 1)], text)
 
         decorate = (((linenumber is None) and decorate_compat) or
                     (linenumber and with_linenumber) or
                     without_linenumber)
 
         def pair(parent, child):
             for a1, a2, b1, b2 in bdiff.blocks(parent[1], child[1]):
                 child[0][b1:b2] = parent[0][a1:a2]
             return child
 
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
         def getctx(path, fileid):
             log = path == self._path and self._filelog or getlog(path)
             return filectx(self._repo, path, fileid=fileid, filelog=log)
         getctx = util.lrucachefunc(getctx)
 
         def parents(f):
             # we want to reuse filectx objects as much as possible
             p = f._path
             if f._filerev is None: # working dir
                 pl = [(n.path(), n.filerev()) for n in f.parents()]
             else:
                 pl = [(p, n) for n in f._filelog.parentrevs(f._filerev)]
 
             if follow:
                 r = f.renamed()
                 if r:
                     pl[0] = (r[0], getlog(r[0]).rev(r[1]))
 
             return [getctx(p, n) for p, n in pl if n != nullrev]
 
         # use linkrev to find the first changeset where self appeared
         if self.rev() != self.linkrev():
             base = self.filectx(self.filerev())
         else:
             base = self
 
         # find all ancestors
         needed = {base: 1}
         visit = [base]
         files = [base._path]
         while visit:
             f = visit.pop(0)
             for p in parents(f):
                 if p not in needed:
                     needed[p] = 1
                     visit.append(p)
                     if p._path not in files:
                         files.append(p._path)
                 else:
                     # count how many times we'll use this
                     needed[p] += 1
 
         # sort by revision (per file) which is a topological order
         visit = []
         for f in files:
             visit.extend(n for n in needed if n._path == f)
 
         hist = {}
         for f in sorted(visit, key=lambda x: x.rev()):
             curr = decorate(f.data(), f)
             for p in parents(f):
                 curr = pair(hist[p], curr)
                 # trim the history of unneeded revs
                 needed[p] -= 1
                 if not needed[p]:
                     del hist[p]
             hist[f] = curr
 
         return zip(hist[f][0], hist[f][1].splitlines(True))
 
     def ancestor(self, fc2):
         """
         find the common ancestor file context, if any, of self, and fc2
         """
 
         actx = self.changectx().ancestor(fc2.changectx())
 
         # the trivial case: changesets are unrelated, files must be too
         if not actx:
             return None
 
         # the easy case: no (relevant) renames
         if fc2.path() == self.path() and self.path() in actx:
             return actx[self.path()]
         acache = {}
 
         # prime the ancestor cache for the working directory
         for c in (self, fc2):
             if c._filerev is None:
                 pl = [(n.path(), n.filenode()) for n in c.parents()]
                 acache[(c._path, None)] = pl
 
         flcache = {self._repopath:self._filelog, fc2._repopath:fc2._filelog}
         def parents(vertex):
             if vertex in acache:
                 return acache[vertex]
             f, n = vertex
             if f not in flcache:
                 flcache[f] = self._repo.file(f)
             fl = flcache[f]
             pl = [(f, p) for p in fl.parents(n) if p != nullid]
             re = fl.renamed(n)
             if re:
                 pl.append(re)
             acache[vertex] = pl
             return pl
 
         a, b = (self._path, self._filenode), (fc2._path, fc2._filenode)
         v = ancestor.ancestor(a, b, parents)
         if v:
             f, n = v
             return filectx(self._repo, f, fileid=n, filelog=flcache[f])
 
         return None
 
 class workingctx(changectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     parents - a pair of parent nodeids, or None to use the dirstate.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
     def __init__(self, repo, parents=None, text="", user=None, date=None,
                  extra=None, changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = util.parsedate(date)
         if user:
             self._user = user
         if parents:
             self._parents = [changectx(self._repo, p) for p in parents]
         if changes:
             self._status = list(changes)
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if 'branch' not in self._extra:
             branch = self._repo.dirstate.branch()
             try:
                 branch = branch.decode('UTF-8').encode('UTF-8')
             except UnicodeDecodeError:
                 raise util.Abort(_('branch name not in UTF-8!'))
             self._extra['branch'] = branch
         if self._extra['branch'] == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __nonzero__(self):
         return True
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the working directory"""
 
         man = self._parents[0].manifest().copy()
         copied = self._repo.dirstate.copies()
         cf = lambda x: man.flags(copied.get(x, x))
         ff = self._repo.dirstate.flagfunc(cf)
         modified, added, removed, deleted, unknown = self._status[:5]
         for i, l in (("a", added), ("m", modified), ("u", unknown)):
             for f in l:
                 man[f] = man.get(copied.get(f, f), nullid) + i
                 try:
                     man.set(f, ff(f))
                 except OSError:
                     pass
 
         for f in deleted + removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         return self._repo.status(unknown=True)
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         return util.makedate()
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         self._parents = [changectx(self._repo, x) for x in p]
         return self._parents
 
     def manifest(self): return self._manifest
 
     def user(self): return self._user or self._repo.ui.username()
     def date(self): return self._date
     def description(self): return self._text
     def files(self):
         return sorted(self._status[0] + self._status[1] + self._status[2])
 
     def modified(self): return self._status[0]
     def added(self): return self._status[1]
     def removed(self): return self._status[2]
     def deleted(self): return self._status[3]
     def unknown(self): return self._status[4]
     def clean(self): return self._status[5]
     def branch(self): return self._extra['branch']
     def extra(self): return self._extra
 
     def tags(self):
         t = []
         [t.extend(p.tags()) for p in self.parents()]
         return t
 
     def children(self):
         return []
 
     def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         pnode = self._parents[0].changeset()[0]
         orig = self._repo.dirstate.copies().get(path, path)
         node, flag = self._repo.manifest.find(pnode, orig)
         try:
             ff = self._repo.dirstate.flagfunc(lambda x: flag or '')
             return ff(path)
         except OSError:
             pass
 
         if not node or path in self.deleted() or path in self.removed():
             return ''
         return flag
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(self._repo, path, workingctx=self,
                               filelog=filelog)
 
     def ancestor(self, c2):
         """return the ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
     def walk(self, match):
-        return sorted(self._repo.dirstate.walk(match, True, False))
+        return sorted(self._repo.dirstate.walk(match, self.substate.keys(),
+                                               True, False))
 
     def dirty(self, missing=False):
         "check whether a working directory is modified"
 
         return (self.p2() or self.branch() != self.p1().branch() or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
 class workingfilectx(filectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
     def __init__(self, repo, path, filelog=None, workingctx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog:
             self._filelog = filelog
         if workingctx:
             self._changectx = workingctx
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def __nonzero__(self):
         return True
 
     def __str__(self):
         return "%s@%s" % (self.path(), self._changectx)
 
     def data(self): return self._repo.wread(self._path)
     def renamed(self):
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p,n,l in pl if n != nullid]
 
     def children(self):
         return []
 
     def size(self): return os.stat(self._repo.wjoin(self._path)).st_size
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (int(os.lstat(self._repo.wjoin(self._path)).st_mtime), tz)
         except OSError, err:
             if err.errno != errno.ENOENT: raise
             return (t, tz)
 
     def cmp(self, text): return self._repo.wread(self._path) == text
 
 class memctx(object):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn raises an
     IOError. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by util.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
     def __init__(self, repo, parents, text, files, filectxfn, user=None,
                  date=None, extra=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         self._date = date and util.parsedate(date) or util.makedate()
         self._user = user
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [changectx(self._repo, p) for p in (p1, p2)]
         files = sorted(set(files))
         self._status = [files, [], [], [], []]
         self._filectxfn = filectxfn
 
         self._extra = extra and extra.copy() or {}
         if 'branch' not in self._extra:
             self._extra['branch'] = 'default'
         elif self._extra.get('branch') == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __int__(self):
         return self._rev
 
     def __nonzero__(self):
         return True
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def p1(self): return self._parents[0]
     def p2(self): return self._parents[1]
 
     def user(self): return self._user or self._repo.ui.username()
     def date(self): return self._date
     def description(self): return self._text
     def files(self): return self.modified()
     def modified(self): return self._status[0]
     def added(self): return self._status[1]
     def removed(self): return self._status[2]
     def deleted(self): return self._status[3]
     def unknown(self): return self._status[4]
     def clean(self): return self._status[5]
     def branch(self): return self._extra['branch']
     def extra(self): return self._extra
     def flags(self, f): return self[f].flags()
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return self._filectxfn(self._repo, self, path)
 
 class memfilectx(object):
     """memfilectx represents an in-memory file to commit.
 
     See memctx for more details.
     """
     def __init__(self, path, data, islink, isexec, copied):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         self._path = path
         self._data = data
         self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
         self._copied = None
         if copied:
             self._copied = (copied, nullid)
 
     def __nonzero__(self): return True
     def __str__(self): return "%s@%s" % (self.path(), self._changectx)
     def path(self): return self._path
     def data(self): return self._data
     def flags(self): return self._flags
     def isexec(self): return 'x' in self._flags
     def islink(self): return 'l' in self._flags
     def renamed(self): return self._copied

mercurial/dirstate.py

@@ -1,644 +1,647
 # dirstate.py - working directory tracking 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, incorporated herein by reference.
 
 from node import nullid
 from i18n import _
 import util, ignore, osutil, parsers
 import struct, os, stat, errno
 import cStringIO
 
 _unknown = ('?', 0, 0, 0)
 _format = ">cllll"
 propertycache = util.propertycache
 
 def _finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)
 
 def _incdirs(dirs, path):
     for base in _finddirs(path):
         if base in dirs:
             dirs[base] += 1
             return
         dirs[base] = 1
 
 def _decdirs(dirs, path):
     for base in _finddirs(path):
         if dirs[base] > 1:
             dirs[base] -= 1
             return
         del dirs[base]
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._root = root
         self._rootdir = os.path.join(root, '')
         self._dirty = False
         self._dirtypl = False
         self._ui = ui
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _foldmap(self):
         f = {}
         for name in self._map:
             f[os.path.normcase(name)] = name
         return f
 
     @propertycache
     def _branch(self):
         try:
             return self._opener("branch").read().strip() or "default"
         except IOError:
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             st = self._opener("dirstate").read(40)
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise util.Abort(_('working directory state appears damaged!'))
         except IOError, err:
             if err.errno != errno.ENOENT: raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
         dirs = {}
         for f,s in self._map.iteritems():
             if s[0] != 'r':
                 _incdirs(dirs, f)
         return dirs
 
     @propertycache
     def _ignore(self):
         files = [self._join('.hgignore')]
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 files.append(util.expandpath(path))
         return ignore.ignore(self._root, files, self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and os.sep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.checkcase(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, fallback):
         if self._checklink:
             if self._checkexec:
                 def f(x):
                     p = self._join(x)
                     if os.path.islink(p):
                         return 'l'
                     if util.is_exec(p):
                         return 'x'
                     return ''
                 return f
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.is_exec(self._join(x)):
                     return 'x'
                 return ''
             return f
         return fallback
 
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root: return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += os.sep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.normpath(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def parents(self):
         return self._pl
 
     def branch(self):
         return self._branch
 
     def setparents(self, p1, p2=nullid):
         self._dirty = self._dirtypl = True
         self._pl = p1, p2
 
     def setbranch(self, branch):
         self._branch = branch
         self._opener("branch", "w").write(branch + '\n')
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             st = self._opener("dirstate").read()
         except IOError, err:
             if err.errno != errno.ENOENT: raise
             return
         if not st:
             return
 
         p = parsers.parse_dirstate(self._map, self._copymap, st)
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in "_map _copymap _foldmap _branch _pl _dirs _ignore".split():
             if a in self.__dict__:
                 delattr(self, a)
         self._dirty = False
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
             _decdirs(self._dirs, f)
 
     def _addpath(self, f, check=False):
         oldstate = self[f]
         if check or oldstate == "r":
             if '\r' in f or '\n' in f:
                 raise util.Abort(
                     _("'\\n' and '\\r' disallowed in filenames: %r") % f)
             if f in self._dirs:
                 raise util.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in _finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise util.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
             _incdirs(self._dirs, f)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         self._dirty = True
         self._addpath(f)
         s = os.lstat(self._join(f))
         self._map[f] = ('n', s.st_mode, s.st_size, int(s.st_mtime))
         if f in self._copymap:
             del self._copymap[f]
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' or dirty before being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.normaldirty(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._dirty = True
         self._addpath(f)
         self._map[f] = ('n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def normaldirty(self, f):
         '''Mark a file normal, but dirty.'''
         self._dirty = True
         self._addpath(f)
         self._map[f] = ('n', 0, -2, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._dirty = True
         self._addpath(f, True)
         self._map[f] = ('a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             entry = self._map[f]
             if entry[0] == 'm':
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2:
                 size = -2
         self._map[f] = ('r', 0, size, 0)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         self._dirty = True
         s = os.lstat(self._join(f))
         self._addpath(f)
         self._map[f] = ('m', s.st_mode, s.st_size, int(s.st_mtime))
         if f in self._copymap:
             del self._copymap[f]
 
     def forget(self, f):
         '''Forget a file.'''
         self._dirty = True
         try:
             self._droppath(f)
             del self._map[f]
         except KeyError:
             self._ui.warn(_("not in dirstate: %s\n") % f)
 
     def _normalize(self, path, knownpath):
         norm_path = os.path.normcase(path)
         fold_path = self._foldmap.get(norm_path, None)
         if fold_path is None:
             if knownpath or not os.path.exists(os.path.join(self._root, path)):
                 fold_path = path
             else:
                 fold_path = self._foldmap.setdefault(norm_path,
                                 util.fspath(path, self._root))
         return fold_path
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs");
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._dirty = True
 
     def rebuild(self, parent, files):
         self.clear()
         for f in files:
             if 'x' in files.flags(f):
                 self._map[f] = ('n', 0777, -1, 0)
             else:
                 self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         st = self._opener("dirstate", "w", atomictemp=True)
 
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = int(util.fstat(st).st_mtime)
 
         cs = cStringIO.StringIO()
         copymap = self._copymap
         pack = struct.pack
         write = cs.write
         write("".join(self._pl))
         for f, e in self._map.iteritems():
             if f in copymap:
                 f = "%s\0%s" % (f, copymap[f])
 
             if e[0] == 'n' and e[3] == now:
                 # The file was last modified "simultaneously" with the current
                 # write to dirstate (i.e. within the same second for file-
                 # systems with a granularity of 1 sec). This commonly happens
                 # for at least a couple of files on 'update'.
                 # The user could change the file without changing its size
                 # within the same second. Invalidate the file's stat data in
                 # dirstate, forcing future 'status' calls to compare the
                 # contents of the file. This prevents mistakenly treating such
                 # files as clean.
                 e = (e[0], 0, -1, -1)   # mark entry as 'unset'
 
             e = pack(_format, e[0], e[1], e[2], e[3], len(f))
             write(e)
             write(f)
         st.write(cs.getvalue())
         st.rename()
         self._dirty = self._dirtypl = False
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in _finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
-    def walk(self, match, unknown, ignored):
+    def walk(self, match, subrepos, unknown, ignored):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
         '''
 
         def fwarn(f, msg):
             self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
             return False
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode): kind = _('character device')
             elif stat.S_ISBLK(mode): kind = _('block device')
             elif stat.S_ISFIFO(mode): kind = _('fifo')
             elif stat.S_ISSOCK(mode): kind = _('socket')
             elif stat.S_ISDIR(mode): kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif not unknown:
             # if unknown and ignored are False, skip step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         badfn = match.bad
         dmap = self._map
         normpath = util.normpath
         listdir = osutil.listdir
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         work = []
         wadd = work.append
 
         if self._checkcase:
             normalize = self._normalize
         else:
             normalize = lambda x, y: x
 
         exact = skipstep3 = False
         if matchfn == match.exact: # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.files() and not match.anypats(): # match.match, no patterns
             skipstep3 = True
 
         files = set(match.files())
         if not files or '.' in files:
             files = ['']
-        results = {'.hg': None}
+        results = dict.fromkeys(subrepos)
+        results['.hg'] = None
 
         # step 1: find all explicit files
         for ff in sorted(files):
             nf = normalize(normpath(ff), False)
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     skipstep3 = False
                     if nf in dmap:
                         #file deleted on disk but still in dirstate
                         results[nf] = None
                     match.dir(nf)
                     if not dirignore(nf):
                         wadd(nf)
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError, inst:
                 if nf in dmap: # does it exactly match a file?
                     results[nf] = None
                 else: # does it match a directory?
                     prefix = nf + "/"
                     for fn in dmap:
                         if fn.startswith(prefix):
                             match.dir(nf)
                             skipstep3 = False
                             break
                     else:
                         badfn(ff, inst.strerror)
 
         # step 2: visit subdirectories
         while work:
             nd = work.pop()
             skip = None
             if nd == '.':
                 nd = ''
             else:
                 skip = '.hg'
             try:
                 entries = listdir(join(nd), stat=True, skip=skip)
             except OSError, inst:
                 if inst.errno == errno.EACCES:
                     fwarn(nd, inst.strerror)
                     continue
                 raise
             for f, kind, st in entries:
                 nf = normalize(nd and (nd + "/" + f) or f, True)
                 if nf not in results:
                     if kind == dirkind:
                         if not ignore(nf):
                             match.dir(nf)
                             wadd(nf)
                         if nf in dmap and matchfn(nf):
                             results[nf] = None
                     elif kind == regkind or kind == lnkkind:
                         if nf in dmap:
                             if matchfn(nf):
                                 results[nf] = st
                         elif matchfn(nf) and not ignore(nf):
                             results[nf] = st
                     elif nf in dmap and matchfn(nf):
                         results[nf] = None
 
         # step 3: report unseen items in the dmap hash
         if not skipstep3 and not exact:
             visit = sorted([f for f in dmap if f not in results and matchfn(f)])
             for nf, st in zip(visit, util.statfiles([join(i) for i in visit])):
                 if not st is None and not getkind(st.st_mode) in (regkind, lnkkind):
                     st = None
                 results[nf] = st
-
+        for s in subrepos:
+            del results[s]
         del results['.hg']
         return results
 
-    def status(self, match, ignored, clean, unknown):
+    def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a tuple of lists (unsure, modified, added,
         removed, deleted, unknown, ignored, clean), where:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           added:
             files that have been explicitly added with hg add
           removed:
             files that have been explicitly removed with hg remove
           deleted:
             files that have been deleted through other means ("missing")
           unknown:
             files not in the dirstate that are not ignored
           ignored:
             files not in the dirstate that are ignored
             (by _dirignore())
           clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
 
-        for fn, st in self.walk(match, listunknown, listignored).iteritems():
+        for fn, st in self.walk(match, subrepos, listunknown,
+                                listignored).iteritems():
             if fn not in dmap:
                 if (listignored or match.exact(fn)) and self._dirignore(fn):
                     if listignored:
                         iadd(fn)
                 elif listunknown:
                     uadd(fn)
                 continue
 
             state, mode, size, time = dmap[fn]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 if (size >= 0 and
                     (size != st.st_size
                      or ((mode ^ st.st_mode) & 0100 and self._checkexec))
                     or size == -2
                     or fn in self._copymap):
                     madd(fn)
                 elif time != int(st.st_mtime):
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)

mercurial/localrepo.py

@@ -1,2162 +1,2164
 # 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, incorporated herein by reference.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup, subrepo
 import changelog, dirstate, filelog, manifest, context
 import lock, transaction, store, encoding
 import util, extensions, hook, error
 import match as match_
 import merge as merge_
 import tags as tags_
 from lock import release
 import weakref, stat, errno, os, time, inspect
 propertycache = util.propertycache
 
 class localrepository(repo.repository):
     capabilities = set(('lookup', 'changegroupsubset', 'branchmap'))
     supported = set('revlogv1 store fncache shared'.split())
 
     def __init__(self, baseui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(path)
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
         self.baseui = baseui
         self.ui = baseui.copy()
 
         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):
                     os.mkdir(path)
                 os.mkdir(self.path)
                 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")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             requirements = set()
             try:
                 requirements = set(self.opener("requires").read().splitlines())
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
             for r in requirements - self.supported:
                 raise error.RepoError(_("requirement '%s' not supported") % r)
 
         self.sharedpath = self.path
         try:
             s = os.path.realpath(self.opener("sharedpath").read())
             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, util.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
 
         # 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 = None
         self._tagtypes = None
 
         self._branchcache = None  # in UTF-8
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     @propertycache
     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')
         self.sopener.defversion = c.version
         return c
 
     @propertycache
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @propertycache
     def dirstate(self):
         return dirstate.dirstate(self.opener, self.ui, self.root)
 
     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 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)
 
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if self._tagtypes and name in self._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:
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         if '.hgtags' not in self.dirstate:
             self.add(['.hgtags'])
 
         m = match_.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'''
 
         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)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self._tags is None:
             (self._tags, self._tagtypes) = self._findtags()
 
         return self._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 = {}
 
         tags_.findglobaltags(self.ui, self, alltags, tagtypes)
         tags_.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:
                 tags[encoding.tolocal(name)] = node
         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
         '''
 
         self.tags()
 
         return self._tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().iteritems():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in sorted(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().iteritems():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchmap(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
 
         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():
             head = None
             for i in range(len(heads)-1, -1, -1):
                 h = heads[i]
                 if 'close' not in self.changelog.read(h)[5]:
                     head = h
                     break
             # no open heads were found
             if head is None:
                 head = heads[-1]
             bt[bn] = head
         return bt
 
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branchheads.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
                 if not l: continue
                 node, label = l.split(" ", 1)
                 partial.setdefault(label.strip(), []).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("branchheads.cache", "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), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, start, end):
         # collect new branch entries
         newbranches = {}
         for r in xrange(start, end):
             c = self[r]
             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) < 2:
                 continue
             newbheads = []
             # starting from tip means fewer passes over reachable
             while newnodes:
                 latest = newnodes.pop()
                 if latest not in bheads:
                     continue
                 minbhrev = self[min([self[bh].rev() for bh in bheads])].node()
                 reachable = self.changelog.reachable(latest, minbhrev)
                 bheads = [b for b in bheads if b not in reachable]
                 newbheads.insert(0, latest)
             bheads.extend(newbheads)
             partial[branch] = bheads
 
     def lookup(self, key):
         if isinstance(key, int):
             return self.changelog.node(key)
         elif key == '.':
             return self.dirstate.parents()[0]
         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.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:
             pass
         raise error.RepoLookupError(_("unknown revision '%s'") % key)
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = match_.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
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         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"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         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):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 self.ui.status(_("rolling back last transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("undo"), self.ui.warn)
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 try:
                     branch = self.opener("undo.branch").read()
                     self.dirstate.setbranch(branch)
                 except IOError:
                     self.ui.warn(_("Named branch could not be reset, "
                                    "current branch still is: %s\n")
                                  % encoding.tolocal(self.dirstate.branch()))
                 self.invalidate()
                 self.dirstate.invalidate()
                 self.destroyed()
             else:
                 self.ui.warn(_("no rollback information available\n"))
         finally:
             release(lock, wlock)
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if a in self.__dict__:
                 delattr(self, a)
         self._tags = None
         self._tagtypes = None
         self.nodetagscache = None
         self._branchcache = None # in UTF-8
         self._branchcachetip = None
 
     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 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
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''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
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         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['.'].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
             meta["copy"] = cfname
             meta["copyrev"] = hex(crev)
             fparent1, fparent2 = nullid, newfparent
         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 = match_.always(self.root, '')
 
         if not force:
             vdirs = []
             match.dir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             p1, p2 = self.dirstate.parents()
             wctx = self[None]
 
             if (not force and p2 != nullid and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             for s in wctx.substate:
                 if match(s) and wctx.sub(s).dirty():
                     subs.append(s)
             if subs and '.hgsubstate' not in changes[0]:
                 changes[0].insert(0, '.hgsubstate')
 
             # 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 p2 == nullid
                 and not (changes[0] or changes[1] or changes[2])
                 and self[None].branch() == self['.'].branch()):
                 return None
 
             ms = merge_.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
 
             cctx = context.workingctx(self, (p1, p2), text, user, date,
                                       extra, changes)
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs
             if subs:
                 state = wctx.substate.copy()
                 for s in subs:
                     self.ui.status(_('committing subrepository %s\n') % s)
                     sr = wctx.sub(s).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.
             msgfile = self.opener('last-message.txt', 'wb')
             msgfile.write(cctx._text)
             msgfile.close()
 
             try:
                 ret = self.commitctx(cctx, True)
             except:
                 if edited:
                     msgfn = self.pathto(msgfile.name[len(self.root)+1:])
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update dirstate and mergestate
             for f in changes[0] + changes[1]:
                 self.dirstate.normal(f)
             for f in changes[2]:
                 self.dirstate.forget(f)
             self.dirstate.setparents(ret)
             ms.reset()
 
             return ret
 
         finally:
             wlock.release()
 
     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 = ctx.removed()
         p1, p2 = ctx.p1(), ctx.p2()
         m1 = p1.manifest().copy()
         m2 = p2.manifest()
         user = ctx.user()
 
         xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
         self.hook("precommit", throw=True, parent1=xp1, parent2=xp2)
 
         lock = self.lock()
         try:
             tr = self.transaction()
             trp = weakref.proxy(tr)
 
             # 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, IOError):
                     if error:
                         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))
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, changed + removed, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             tr.close()
 
             if self._branchcache:
                 self.branchtags()
 
             self.hook("commit", node=hex(n), parent1=xp1, parent2=xp2)
             return n
         finally:
             del tr
             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.
         tags_.findglobaltags(self.ui, self, {}, {})
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         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 match_.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
-            s = self.dirstate.status(match, listignored, listclean, listunknown)
+            subrepos = ctx1.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].data())):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 if listclean:
                     clean += fixup
 
                 # update dirstate for files that are actually clean
                 if 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 (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn].data())))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
         [l.sort() for l in r]
         return r
 
     def add(self, list):
         wlock = self.wlock()
         try:
             rejected = []
             for f in list:
                 p = self.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     self.ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     self.ui.warn(_("%s: files over 10MB may cause memory and"
                                    " performance problems\n"
                                    "(use 'hg revert %s' to unadd the file)\n")
                                    % (f, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     self.ui.warn(_("%s not added: only files and symlinks "
                                    "supported currently\n") % f)
                     rejected.append(p)
                 elif self.dirstate[f] in 'amn':
                     self.ui.warn(_("%s already tracked!\n") % f)
                 elif self.dirstate[f] == 'r':
                     self.dirstate.normallookup(f)
                 else:
                     self.dirstate.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, list):
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'a':
                     self.ui.warn(_("%s not added!\n") % f)
                 else:
                     self.dirstate.forget(f)
         finally:
             wlock.release()
 
     def remove(self, list, unlink=False):
         if unlink:
             for f in list:
                 try:
                     util.unlink(self.wjoin(f))
                 except OSError, inst:
                     if inst.errno != errno.ENOENT:
                         raise
         wlock = self.wlock()
         try:
             for f in list:
                 if unlink and os.path.exists(self.wjoin(f)):
                     self.ui.warn(_("%s still exists!\n") % f)
                 elif self.dirstate[f] == 'a':
                     self.dirstate.forget(f)
                 elif f not in self.dirstate:
                     self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self.dirstate.remove(f)
         finally:
             wlock.release()
 
     def undelete(self, list):
         manifests = [self.manifest.read(self.changelog.read(p)[0])
                      for p in self.dirstate.parents() if p != nullid]
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'r':
                     self.ui.warn(_("%s not removed!\n") % f)
                 else:
                     m = f in manifests[0] and manifests[0] or manifests[1]
                     t = self.file(f).read(m[f])
                     self.wwrite(f, t, m.flags(f))
                     self.dirstate.normal(f)
         finally:
             wlock.release()
 
     def copy(self, source, dest):
         p = self.wjoin(dest)
         if not (os.path.exists(p) or os.path.islink(p)):
             self.ui.warn(_("%s does not exist!\n") % dest)
         elif not (os.path.isfile(p) or os.path.islink(p)):
             self.ui.warn(_("copy failed: %s is not a file or a "
                            "symbolic link\n") % dest)
         else:
             wlock = self.wlock()
             try:
                 if self.dirstate[dest] in '?r':
                     self.dirstate.add(dest)
                 self.dirstate.copy(source, dest)
             finally:
                 wlock.release()
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         return [n for (r, n) in sorted(heads)]
 
     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 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom 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 findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         return self.findcommonincoming(remote, base, heads, force)[1]
 
     def findcommonincoming(self, remote, base=None, heads=None, force=False):
         """Return a tuple (common, missing roots, heads) used to identify
         missing nodes from remote.
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         """
         m = self.changelog.nodemap
         search = []
         fetch = set()
         seen = set()
         seenbranch = set()
         if base is None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid], [nullid], list(heads)
             return [nullid], [], []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         heads = unknown
         if not unknown:
             return base.keys(), [], []
 
         req = set(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug("examining %s:%s\n"
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug("branch already found\n")
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug("found incomplete branch %s:%s\n"
                                   % (short(n[0]), short(n[1])))
                     search.append(n[0:2]) # schedule branch range for scanning
                     seenbranch.add(n)
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug("found new changeset %s\n" %
                                           short(n[1]))
                             fetch.add(n[1]) # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req.add(p)
                 seen.add(n[0])
 
             if r:
                 reqcnt += 1
                 self.ui.debug("request %d: %s\n" %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug("received %s:%s\n" %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             newsearch = []
             reqcnt += 1
             for n, l in zip(search, remote.between(search)):
                 l.append(n[1])
                 p = n[0]
                 f = 1
                 for i in l:
                     self.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
                     if i in m:
                         if f <= 2:
                             self.ui.debug("found new branch changeset %s\n" %
                                               short(p))
                             fetch.add(p)
                             base[i] = 1
                         else:
                             self.ui.debug("narrowed branch search to %s:%s\n"
                                           % (short(p), short(i)))
                             newsearch.append((p, i))
                         break
                     p, f = i, f * 2
                 search = newsearch
 
         # sanity check our fetch list
         for f in fetch:
             if f in m:
                 raise error.RepoError(_("already have changeset ")
                                       + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug("found new changesets starting at " +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug("%d total queries\n" % reqcnt)
 
         return base.keys(), list(fetch), heads
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base is None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug("common changesets up to "
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = set(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         remain.remove(nullid)
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 remain.remove(n)
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = set()
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads.add(p1)
                 if p2 in heads:
                     updated_heads.add(p2)
 
         # this is the set of all roots we have to push
         if heads:
             return subset, list(updated_heads)
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             common, fetch, rheads = self.findcommonincoming(remote, heads=heads,
                                                             force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None and remote.capable('changegroupsubset'):
                 heads = rheads
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if not remote.capable('changegroupsubset'):
                     raise util.Abort(_("Partial pull cannot be done because "
                                        "other repository doesn't support "
                                        "changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             lock.release()
 
     def push(self, remote, force=False, revs=None):
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if remote.capable('unbundle'):
             return self.push_unbundle(remote, force, revs)
         return self.push_addchangegroup(remote, force, revs)
 
     def prepush(self, remote, force, revs):
         '''Analyze the local and remote repositories and determine which
         changesets need to be pushed to the remote.  Return a tuple
         (changegroup, remoteheads).  changegroup is a readable file-like
         object whose read() returns successive changegroup chunks ready to
         be sent over the wire.  remoteheads is the list of remote heads.
         '''
         common = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, common, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, common, remote_heads)
         msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
 
         def checkbranch(lheads, rheads, updatelb):
             '''
             check whether there are more local heads than remote heads on
             a specific branch.
 
             lheads: local branch heads
             rheads: remote branch heads
             updatelb: outgoing local branch bases
             '''
 
             warn = 0
 
             if not revs and len(lheads) > len(rheads):
                 warn = 1
             else:
                 # add local heads involved in the push
                 updatelheads = [self.changelog.heads(x, lheads)
                                 for x in updatelb]
                 newheads = set(sum(updatelheads, [])) & set(lheads)
 
                 if not newheads:
                     return True
 
                 # add heads we don't have or that are not involved in the push
                 for r in rheads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.add(r)
                     else:
                         newheads.add(r)
                 if len(newheads) > len(rheads):
                     warn = 1
 
             if warn:
                 if not rheads: # new branch requires --force
                     self.ui.warn(_("abort: push creates new"
                                    " remote branch '%s'!\n") %
                                    self[lheads[0]].branch())
                 else:
                     self.ui.warn(_("abort: push creates new remote heads!\n"))
 
                 self.ui.status(_("(did you forget to merge?"
                                  " use push -f to force)\n"))
                 return False
             return True
 
         if not bases:
             self.ui.status(_("no changes found\n"))
             return None, 1
         elif not force:
             # Check for each named branch if we're creating new remote heads.
             # To be a remote head after push, node must be either:
             # - unknown locally
             # - a local outgoing head descended from update
             # - a remote head that's known locally and not
             #   ancestral to an outgoing head
             #
             # New named branches cannot be created without --force.
 
             if remote_heads != [nullid]:
                 if remote.capable('branchmap'):
                     localhds = {}
                     if not revs:
                         localhds = self.branchmap()
                     else:
                         for n in heads:
                             branch = self[n].branch()
                             if branch in localhds:
                                 localhds[branch].append(n)
                             else:
                                 localhds[branch] = [n]
 
                     remotehds = remote.branchmap()
 
                     for lh in localhds:
                         if lh in remotehds:
                             rheads = remotehds[lh]
                         else:
                             rheads = []
                         lheads = localhds[lh]
                         if not checkbranch(lheads, rheads, update):
                             return None, 0
                 else:
                     if not checkbranch(heads, remote_heads, update):
                         return None, 0
 
             if inc:
                 self.ui.warn(_("note: unsynced remote changes!\n"))
 
 
         if revs is None:
             # use the fast path, no race possible on push
             nodes = self.changelog.findmissing(common.keys())
             cg = self._changegroup(nodes, 'push')
         else:
             cg = self.changegroupsubset(update, revs, 'push')
         return cg, remote_heads
 
     def push_addchangegroup(self, remote, force, revs):
         lock = remote.lock()
         try:
             ret = self.prepush(remote, force, revs)
             if ret[0] is not None:
                 cg, remote_heads = ret
                 return remote.addchangegroup(cg, 'push', self.url())
             return ret[1]
         finally:
             lock.release()
 
     def push_unbundle(self, remote, force, revs):
         # local repo finds heads on server, finds out what revs it
         # must push.  once revs transferred, if server finds it has
         # different heads (someone else won commit/push race), server
         # aborts.
 
         ret = self.prepush(remote, force, revs)
         if ret[0] is not None:
             cg, remote_heads = ret
             if force: remote_heads = ['force']
             return remote.unbundle(cg, remote_heads, 'push')
         return ret[1]
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug("list of changesets:\n")
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source, extranodes=None):
         """Compute a changegroup consisting of all the nodes that are
         descendents 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.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # msng is short for missing - compute the list of changesets in this
         # changegroup.
         if not bases:
             bases = [nullid]
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
 
         if extranodes is None:
             # can we go through the fast path ?
             heads.sort()
             allheads = self.heads()
             allheads.sort()
             if heads == allheads:
                 return self._changegroup(msng_cl_lst, source)
 
         # slow path
         self.hook('preoutgoing', throw=True, source=source)
 
         self.changegroupinfo(msng_cl_lst, source)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = set()
         # We assume that all parents of bases are known heads.
         for n in bases:
             knownheads.update(cl.parents(n))
         knownheads.discard(nullid)
         knownheads = list(knownheads)
         if knownheads:
             # Now that we know what heads are known, we can compute which
             # changesets are known.  The recipient must know about all
             # changesets required to reach the known heads from the null
             # changeset.
             has_cl_set, junk, junk = cl.nodesbetween(None, knownheads)
             junk = None
             # Transform the list into a set.
             has_cl_set = set(has_cl_set)
         else:
             # If there were no known heads, the recipient cannot be assumed to
             # know about any changesets.
             has_cl_set = set()
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune_parents(revlog, hasset, msngset):
             for r in revlog.ancestors(*[revlog.rev(n) for n in hasset]):
                 msngset.pop(revlog.node(r), None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = set()
             for n in msng_mnfst_set:
                 # If a 'missing' manifest thinks it belongs to a changenode
                 # the recipient is assumed to have, obviously the recipient
                 # must have that manifest.
                 linknode = cl.node(mnfst.linkrev(mnfst.rev(n)))
                 if linknode in has_cl_set:
                     has_mnfst_set.add(n)
             prune_parents(mnfst, has_mnfst_set, msng_mnfst_set)
 
         # Use the information collected in collect_manifests_and_files to say
         # which changenode any manifestnode belongs to.
         def lookup_manifest_link(mnfstnode):
             return msng_mnfst_set[mnfstnode]
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r - 1 in mnfst.parentrevs(r):
                     # If the previous rev is one of the parents,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.iteritems():
                         f = changedfiles.get(f, None)
                         # And if the file is in the list of files we care
                         # about.
                         if f is not None:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we know the recipient must have.
         def prune_filenodes(f, filerevlog):
             msngset = msng_filenode_set[f]
             hasset = set()
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in msngset:
                 clnode = cl.node(filerevlog.linkrev(filerevlog.rev(n)))
                 if clnode in has_cl_set:
                     hasset.add(n)
             prune_parents(filerevlog, hasset, msngset)
 
         # A function generator function that sets up the a context for the
         # inner function.
         def lookup_filenode_link_func(fname):
             msngset = msng_filenode_set[fname]
             # Lookup the changenode the filenode belongs to.
             def lookup_filenode_link(fnode):
                 return msngset[fnode]
             return lookup_filenode_link
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = {}
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             group = cl.group(msng_cl_lst, identity,
                              manifest_and_file_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # The list of manifests has been collected by the generator
             # calling our functions back.
             prune_manifests()
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(key=mnfst.rev)
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
                                 filenode_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     msng_filenode_set.setdefault(fname, {})
                     changedfiles[fname] = 1
             # Go through all our files in order sorted by name.
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 if fname in msng_filenode_set:
                     prune_filenodes(fname, filerevlog)
                     add_extra_nodes(fname, msng_filenode_set[fname])
                     msng_filenode_lst = msng_filenode_set[fname].keys()
                 else:
                     msng_filenode_lst = []
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if len(msng_filenode_lst) > 0:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision #
                     msng_filenode_lst.sort(key=filerevlog.rev)
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(msng_filenode_lst,
                                              lookup_filenode_link_func(fname))
                     for chnk in group:
                         yield chnk
                 if fname in msng_filenode_set:
                     # Don't need this anymore, toss it to free memory.
                     del msng_filenode_set[fname]
             # Signal that no more groups are left.
             yield changegroup.closechunk()
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         # 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"""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         revset = set([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(log):
             for r in log:
                 if log.linkrev(r) in revset:
                     yield log.node(r)
 
         def changed_file_collector(changedfileset):
             def collect_changed_files(clnode):
                 c = cl.read(clnode)
                 changedfileset.update(c[3])
             return collect_changed_files
 
         def lookuprevlink_func(revlog):
             def lookuprevlink(n):
                 return cl.node(revlog.linkrev(revlog.rev(n)))
             return lookuprevlink
 
         def gengroup():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
             changedfiles = set()
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuprevlink_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         yield chnk
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """add changegroup to repo.
 
         return values:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - less heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction()
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             chunkiter = changegroup.chunkiter(source)
             if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             chunkiter = changegroup.chunkiter(source)
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             self.manifest.addgroup(chunkiter, revmap, trp)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug("adding %s revisions\n" % f)
                 fl = self.file(f)
                 o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
 
             newheads = len(cl.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
         finally:
             del tr
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug("updating the branch cache\n")
             self.branchtags()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise 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)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True