tags: implement persistent tag caching (issue548).

- rename findglobaltags() to findglobaltags1() (so the "no cache"
  implementation is still there if we need it)
- add findglobaltags2() and make findglobaltags() an alias for it
  (disabling tag caching is a one-line patch)
- factor out tagcache class with methods readcache() and writecache();
  the expensive part of tag finding (iterate over heads and find
  .hgtags filenode) is now in tagcache.readcache()

mercurial/localrepo.py

@@ -1,2135 +1,2144 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License 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
         self._ubranchcache = None  # UTF-8 version of branchcache
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     @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 __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)
 
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[name] = node
         tags['tip'] = self.changelog.tip()
         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 self.branchcache is None:
             self.branchcache = {} # avoid recursion in changectx
         else:
             self.branchcache.clear() # keep using the same dict
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._ubranchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._ubranchcache = partial
 
         # the branch cache is stored on disk as UTF-8, but in the local
         # charset internally
         for k, v in partial.iteritems():
             self.branchcache[encoding.tolocal(k)] = v
         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.RepoError(_("unknown revision '%s'") % key)
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 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(_("journal already exists - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         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
         self._ubranchcache = None
         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):
         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):
         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)
 
             # 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)
 
             ret = self.commitctx(cctx, True)
 
             # 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.'''
-        # Do nothing for now: this is a placeholder that will be used
-        # when we add tag caching.
         # 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
-        pass
+
+        # 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)
             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):
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         bheads = branches[branch]
         # the cache returns heads ordered lowest to highest
         bheads.reverse()
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             bheads = self.changelog.nodesbetween([start], bheads)[2]
         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):
         common = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, common, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, common, remote_heads)
         if revs is not None:
             msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
         else:
             bases, heads = update, self.changelog.heads()
 
         def checkbranch(lheads, rheads, updatelh):
             '''
             check whether there are more local heads than remote heads on
             a specific branch.
 
             lheads: local branch heads
             rheads: remote branch heads
             updatelh: outgoing local branch heads
             '''
 
             warn = 0
 
             if not revs and len(lheads) > len(rheads):
                 warn = 1
             else:
                 updatelheads = [self.changelog.heads(x, lheads)
                                 for x in updatelh]
                 newheads = set(sum(updatelheads, [])) & set(lheads)
 
                 if not newheads:
                     return True
 
                 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[updatelh[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]
                         updatelh = [upd for upd in update
                                     if self[upd].branch() == lh]
                         if not updatelh:
                             continue
                         if not checkbranch(lheads, rheads, updatelh):
                             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
             cg = self._changegroup(common.keys(), '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):
         """This function generates a changegroup consisting of all the nodes
         that are descendents of any of the bases, and ancestors of any of
         the heads.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         if extranodes is None:
             # can we go through the fast path ?
             heads.sort()
             allheads = self.heads()
             allheads.sort()
             if heads == allheads:
                 common = []
                 # parents of bases are known from both sides
                 for n in bases:
                     for p in self.changelog.parents(n):
                         if p != nullid:
                             common.append(p)
                 return self._changegroup(common, source)
 
         self.hook('preoutgoing', throw=True, source=source)
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # msng is short for missing - compute the list of changesets in this
         # changegroup.
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
         self.changegroupinfo(msng_cl_lst, source)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = 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):
             haslst = list(hasset)
             haslst.sort(key=revlog.rev)
             for node in haslst:
                 parentlst = [p for p in revlog.parents(node) if p != nullid]
                 while parentlst:
                     n = parentlst.pop()
                     if n not in hasset:
                         hasset.add(n)
                         p = [p for p in revlog.parents(n) if p != nullid]
                         parentlst.extend(p)
             for n in hasset:
                 msngset.pop(n, None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = 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):
             next_rev = [0]
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r == next_rev[0]:
                     # If the last rev we looked at was the one just previous,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.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)
                 # Remember the revision we hope to see next.
                 next_rev[0] = r + 1
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we 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, common, source):
         """Generate a changegroup of all nodes that we have that a recipient
         doesn't.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         common is the set of common nodes between remote and self"""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         nodes = cl.findmissing(common)
         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():
             # 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

mercurial/tags.py

@@ -1,122 +1,310 b''
 # tags.py - read tag info from local repository
 #
 # Copyright 2009 Matt Mackall <[e-mail]>
 # Copyright 2009 Greg Ward <[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.
 
-# Currently this module only deals with reading tags.  Soon it will grow
-# support for caching tag info.  Eventually, it could take care of
-# updating (adding/removing/moving) tags too.
+# Currently this module only deals with reading and caching tags.
+# Eventually, it could take care of updating (adding/removing/moving)
+# tags too.
 
-from node import bin, hex
+import os
+from node import nullid, bin, hex, short
 from i18n import _
 import encoding
 import error
 
-def findglobaltags(ui, repo, alltags, tagtypes):
+def _debugalways(ui, *msg):
+    ui.write(*msg)
+
+def _debugconditional(ui, *msg):
+    ui.debug(*msg)
+
+def _debugnever(ui, *msg):
+    pass
+
+_debug = _debugalways
+_debug = _debugnever
+
+def findglobaltags1(ui, repo, alltags, tagtypes):
     '''Find global tags in repo by reading .hgtags from every head that
     has a distinct version of it.  Updates the dicts alltags, tagtypes
     in place: alltags maps tag name to (node, hist) pair (see _readtags()
     below), and tagtypes maps tag name to tag type ('global' in this
     case).'''
 
     seen = set()
     fctx = None
     ctxs = []                       # list of filectx
     for node in repo.heads():
         try:
             fnode = repo[node].filenode('.hgtags')
         except error.LookupError:
             continue
         if fnode not in seen:
             seen.add(fnode)
             if not fctx:
                 fctx = repo.filectx('.hgtags', fileid=fnode)
             else:
                 fctx = fctx.filectx(fnode)
             ctxs.append(fctx)
 
     # read the tags file from each head, ending with the tip
     for fctx in reversed(ctxs):
         filetags = _readtags(
             ui, repo, fctx.data().splitlines(), fctx)
         _updatetags(filetags, "global", alltags, tagtypes)
 
+def findglobaltags2(ui, repo, alltags, tagtypes):
+    '''Same as findglobaltags1(), but with caching.'''
+    (heads, tagfnode, shouldwrite) = _readtagcache(ui, repo)
+
+    _debug(ui, "reading tags from %d head(s): %s\n"
+           % (len(heads), map(short, reversed(heads))))
+    seen = set()                    # set of fnode
+    fctx = None
+    for head in reversed(heads):        # oldest to newest
+        assert head in repo.changelog.nodemap, \
+               "tag cache returned bogus head %s" % short(head)
+
+        fnode = tagfnode.get(head)
+        if fnode and fnode not in seen:
+            seen.add(fnode)
+            if not fctx:
+                fctx = repo.filectx('.hgtags', fileid=fnode)
+            else:
+                fctx = fctx.filectx(fnode)
+
+            filetags = _readtags(ui, repo, fctx.data().splitlines(), fctx)
+            _updatetags(filetags, 'global', alltags, tagtypes)
+
+    # and update the cache (if necessary)
+    if shouldwrite:
+        _writetagcache(ui, repo, heads, tagfnode)
+
+# Set this to findglobaltags1 to disable tag caching.
+findglobaltags = findglobaltags2
+
 def readlocaltags(ui, repo, alltags, tagtypes):
     '''Read local tags in repo.  Update alltags and tagtypes.'''
     try:
         data = encoding.fromlocal(repo.opener("localtags").read())
         # localtags are stored in the local character set
         # while the internal tag table is stored in UTF-8
         filetags = _readtags(
             ui, repo, data.splitlines(), "localtags")
         _updatetags(filetags, "local", alltags, tagtypes)
     except IOError:
         pass
 
 def _readtags(ui, repo, lines, fn):
     '''Read tag definitions from a file (or any source of lines).
     Return a mapping from tag name to (node, hist): node is the node id
     from the last line read for that name, and hist is the list of node
     ids previously associated with it (in file order).  All node ids are
     binary, not hex.'''
 
     filetags = {}               # map tag name to (node, hist)
     count = 0
 
     def warn(msg):
         ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
     for line in lines:
         count += 1
         if not line:
             continue
         try:
             (nodehex, name) = line.split(" ", 1)
         except ValueError:
             warn(_("cannot parse entry"))
             continue
         name = encoding.tolocal(name.strip()) # stored in UTF-8
         try:
             nodebin = bin(nodehex)
         except TypeError:
             warn(_("node '%s' is not well formed") % nodehex)
             continue
         if nodebin not in repo.changelog.nodemap:
             # silently ignore as pull -r might cause this
             continue
 
         # update filetags
         hist = []
         if name in filetags:
             n, hist = filetags[name]
             hist.append(n)
         filetags[name] = (nodebin, hist)
     return filetags
 
 def _updatetags(filetags, tagtype, alltags, tagtypes):
     '''Incorporate the tag info read from one file into the two
     dictionaries, alltags and tagtypes, that contain all tag
     info (global across all heads plus local).'''
 
     for name, nodehist in filetags.iteritems():
         if name not in alltags:
             alltags[name] = nodehist
             tagtypes[name] = tagtype
             continue
 
         # we prefer alltags[name] if:
         #  it supercedes us OR
         #  mutual supercedes and it has a higher rank
         # otherwise we win because we're tip-most
         anode, ahist = nodehist
         bnode, bhist = alltags[name]
         if (bnode != anode and anode in bhist and
             (bnode not in ahist or len(bhist) > len(ahist))):
             anode = bnode
         ahist.extend([n for n in bhist if n not in ahist])
         alltags[name] = anode, ahist
         tagtypes[name] = tagtype
 
+
+# The tag cache only stores info about heads, not the tag contents
+# from each head.  I.e. it doesn't try to squeeze out the maximum
+# performance, but is simpler has a better chance of actually
+# working correctly.  And this gives the biggest performance win: it
+# avoids looking up .hgtags in the manifest for every head, and it
+# can avoid calling heads() at all if there have been no changes to
+# the repo.
+
+def _readtagcache(ui, repo):
+    '''Read the tag cache and return a tuple (heads, fnodes,
+    shouldwrite).  heads is the list of all heads currently in the
+    repository (ordered from tip to oldest) and fnodes is a mapping from
+    head to .hgtags filenode.  Caller is responsible for reading tag
+    info from each head.'''
+
+    try:
+        cachefile = repo.opener('tags.cache', 'r')
+        _debug(ui, 'reading tag cache from %s\n' % cachefile.name)
+    except IOError:
+        cachefile = None
+
+    # The cache file consists of lines like
+    #   <headrev> <headnode> [<tagnode>]
+    # where <headrev> and <headnode> redundantly identify a repository
+    # head from the time the cache was written, and <tagnode> is the
+    # filenode of .hgtags on that head.  Heads with no .hgtags file will
+    # have no <tagnode>.  The cache is ordered from tip to oldest (which
+    # is part of why <headrev> is there: a quick visual check is all
+    # that's required to ensure correct order).
+    # 
+    # This information is enough to let us avoid the most expensive part
+    # of finding global tags, which is looking up <tagnode> in the
+    # manifest for each head.
+    cacherevs = []                      # list of headrev
+    cacheheads = []                     # list of headnode
+    cachefnode = {}                     # map headnode to filenode
+    if cachefile:
+        for line in cachefile:
+            line = line.rstrip().split()
+            cacherevs.append(int(line[0]))
+            headnode = bin(line[1])
+            cacheheads.append(headnode)
+            if len(line) == 3:
+                fnode = bin(line[2])
+                cachefnode[headnode] = fnode
+
+        cachefile.close()
+
+    tipnode = repo.changelog.tip()
+    tiprev = len(repo.changelog) - 1
+
+    # Case 1 (common): tip is the same, so nothing has changed.
+    # (Unchanged tip trivially means no changesets have been added.
+    # But, thanks to localrepository.destroyed(), it also means none
+    # have been destroyed by strip or rollback.)
+    if cacheheads and cacheheads[0] == tipnode and cacherevs[0] == tiprev:
+        _debug(ui, "tag cache: tip unchanged\n")
+        return (cacheheads, cachefnode, False)
+        
+    repoheads = repo.heads()
+
+    # Case 2 (uncommon): empty repo; get out quickly and don't bother
+    # writing an empty cache.
+    if repoheads == [nullid]:
+        return ([], {}, False)
+
+    # Case 3 (uncommon): cache file missing or empty.
+    if not cacheheads:
+        _debug(ui, 'tag cache: cache file missing or empty\n')
+
+    # Case 4 (uncommon): tip rev decreased.  This should only happen
+    # when we're called from localrepository.destroyed().  Refresh the
+    # cache so future invocations will not see disappeared heads in the
+    # cache.
+    elif cacheheads and tiprev < cacherevs[0]:
+        _debug(ui,
+               'tag cache: tip rev decremented (from %d to %d), '
+               'so we must be destroying nodes\n'
+               % (cacherevs[0], tiprev))
+
+    # Case 5 (common): tip has changed, so we've added/replaced heads.
+    else:
+        _debug(ui,
+               'tag cache: tip has changed (%d:%s); must find new heads\n'
+               % (tiprev, short(tipnode)))
+
+    # Luckily, the code to handle cases 3, 4, 5 is the same.  So the
+    # above if/elif/else can disappear once we're confident this thing
+    # actually works and we don't need the debug output.
+
+    # N.B. in case 4 (nodes destroyed), "new head" really means "newly
+    # exposed".
+    newheads = [head
+                for head in repoheads
+                if head not in set(cacheheads)]
+    _debug(ui, 'tag cache: found %d head(s) not in cache: %s\n'
+           % (len(newheads), map(short, newheads)))
+
+    # Now we have to lookup the .hgtags filenode for every new head.
+    # This is the most expensive part of finding tags, so performance
+    # depends primarily on the size of newheads.  Worst case: no cache
+    # file, so newheads == repoheads.
+    for head in newheads:
+        cctx = repo[head]
+        try:
+            fnode = cctx.filenode('.hgtags')
+            cachefnode[head] = fnode
+        except error.LookupError:
+            # no .hgtags file on this head
+            pass
+
+    # Caller has to iterate over all heads, but can use the filenodes in
+    # cachefnode to get to each .hgtags revision quickly.
+    return (repoheads, cachefnode, True)
+
+def _writetagcache(ui, repo, heads, tagfnode):
+
+    cachefile = repo.opener('tags.cache', 'w', atomictemp=True)
+    _debug(ui, 'writing cache file %s\n' % cachefile.name)
+
+    realheads = repo.heads()            # for sanity checks below
+    for head in heads:
+        # temporary sanity checks; these can probably be removed
+        # once this code has been in crew for a few weeks
+        assert head in repo.changelog.nodemap, \
+               'trying to write non-existent node %s to tag cache' % short(head)
+        assert head in realheads, \
+               'trying to write non-head %s to tag cache' % short(head)
+        assert head != nullid, \
+               'trying to write nullid to tag cache'
+
+        # This can't fail because of the first assert above.  When/if we
+        # remove that assert, we might want to catch LookupError here
+        # and downgrade it to a warning.
+        rev = repo.changelog.rev(head)
+
+        fnode = tagfnode.get(head)
+        if fnode:
+            cachefile.write('%d %s %s\n' % (rev, hex(head), hex(fnode)))
+        else:
+            cachefile.write('%d %s\n' % (rev, hex(head)))
+
+    cachefile.rename()
+    cachefile.close()

tests/test-mq

@@ -1,517 +1,526 b''
 #!/bin/sh
 
 checkundo()
 {
     if [ -f .hg/store/undo ]; then
 	echo ".hg/store/undo still exists after $1"
     fi
 }
 
 echo "[extensions]" >> $HGRCPATH
 echo "mq=" >> $HGRCPATH
 
 echo % help
 hg help mq
 
 hg init a
 cd a
 echo a > a
 hg ci -Ama
 
 hg clone . ../k
 
 mkdir b
 echo z > b/z
 hg ci -Ama
 
 echo % qinit
 
 hg qinit
 
 cd ..
 hg init b
 
 echo % -R qinit
 
 hg -R b qinit
 
 hg init c
 
 echo % qinit -c
 
 hg --cwd c qinit -c
 hg -R c/.hg/patches st
 
 echo '% qinit; qinit -c'
 hg init d
 cd d
 hg qinit
 hg qinit -c
 # qinit -c should create both files if they don't exist
 echo '  .hgignore:'
 cat .hg/patches/.hgignore
 echo '  series:'
 cat .hg/patches/series
 hg qinit -c 2>&1 | sed -e 's/repository.*already/repository already/'
 cd ..
 
 echo '% qinit; <stuff>; qinit -c'
 hg init e
 cd e
 hg qnew A
 checkundo qnew
 echo foo > foo
 hg add foo
 hg qrefresh
 hg qnew B
 echo >> foo
 hg qrefresh
 echo status >> .hg/patches/.hgignore
 echo bleh >> .hg/patches/.hgignore
 hg qinit -c
 hg -R .hg/patches status
 # qinit -c shouldn't touch these files if they already exist
 echo '  .hgignore:'
 cat .hg/patches/.hgignore
 echo '  series:'
 cat .hg/patches/series
 cd ..
 
 cd a
 
 hg qnew -m 'foo bar' test.patch
 
 echo % qrefresh
 
 echo a >> a
 hg qrefresh
 sed -e "s/^\(diff -r \)\([a-f0-9]* \)/\1 x/" \
     -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
     -e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/" .hg/patches/test.patch
 
 echo % empty qrefresh
 
 hg qrefresh -X a
 echo 'revision:'
 hg diff -r -2 -r -1
 echo 'patch:'
 cat .hg/patches/test.patch
 echo 'working dir diff:'
 hg diff --nodates -q
 # restore things
 hg qrefresh
 checkundo qrefresh
 
 echo % qpop
 
 hg qpop
 checkundo qpop
 
-echo % qpush
+echo % qpush with dump of tag cache
 
+# Dump the tag cache to ensure that it has exactly one head after qpush.
+rm -f .hg/tags.cache
+hg tags > /dev/null
+echo ".hg/tags.cache (pre qpush):"
+sed 's/ [0-9a-f]*//' .hg/tags.cache
 hg qpush
+hg tags > /dev/null
+echo ".hg/tags.cache (post qpush):"
+sed 's/ [0-9a-f]*//' .hg/tags.cache
+
 checkundo qpush
 
 cd ..
 
 echo % pop/push outside repo
 
 hg -R a qpop
 hg -R a qpush
 
 cd a
 hg qnew test2.patch
 
 echo % qrefresh in subdir
 
 cd b
 echo a > a
 hg add a
 hg qrefresh
 
 echo % pop/push -a in subdir
 
 hg qpop -a
 hg --traceback qpush -a
 
 echo % qseries
 hg qseries
 hg qpop
 hg qseries -vs
 hg qpush
 
 echo % qapplied
 hg qapplied
 
 echo % qtop
 hg qtop
 
 echo % qprev
 hg qprev
 
 echo % qnext
 hg qnext
 
 echo % pop, qnext, qprev, qapplied
 hg qpop
 hg qnext
 hg qprev
 hg qapplied
 
 echo % commit should fail
 hg commit
 
 echo % push should fail
 hg push ../../k
 
 echo % import should fail
 hg st .
 echo foo >> ../a
 hg diff > ../../import.diff
 hg revert --no-backup ../a
 hg import ../../import.diff
 hg st
 
 echo % qunapplied
 hg qunapplied
 
 echo % qpush/qpop with index
 hg qnew test1b.patch
 echo 1b > 1b
 hg add 1b
 hg qrefresh
 hg qpush 2
 hg qpop 0
 hg qpush test.patch+1
 hg qpush test.patch+2
 hg qpop test2.patch-1
 hg qpop test2.patch-2
 hg qpush test1b.patch+1
 
 echo % push should succeed
 hg qpop -a
 hg push ../../k
 
 echo % qpush/qpop error codes
 errorcode()
 {
     hg "$@" && echo "  $@ succeeds" || echo "  $@ fails"
 }
 
 # we want to start with some patches applied
 hg qpush -a
 echo "  % pops all patches and succeeds"
 errorcode qpop -a
 echo "  % does nothing and succeeds"
 errorcode qpop -a
 echo "  % fails - nothing else to pop"
 errorcode qpop
 echo "  % pushes a patch and succeeds"
 errorcode qpush
 echo "  % pops a patch and succeeds"
 errorcode qpop
 echo "  % pushes up to test1b.patch and succeeds"
 errorcode qpush test1b.patch
 echo "  % does nothing and succeeds"
 errorcode qpush test1b.patch
 echo "  % does nothing and succeeds"
 errorcode qpop test1b.patch
 echo "  % fails - can't push to this patch"
 errorcode qpush test.patch
 echo "  % fails - can't pop to this patch"
 errorcode qpop test2.patch
 echo "  % pops up to test.patch and succeeds"
 errorcode qpop test.patch
 echo "  % pushes all patches and succeeds"
 errorcode qpush -a
 echo "  % does nothing and succeeds"
 errorcode qpush -a
 echo "  % fails - nothing else to push"
 errorcode qpush
 echo "  % does nothing and succeeds"
 errorcode qpush test2.patch
 
 
 echo % strip
 cd ../../b
 echo x>x
 hg ci -Ama
 hg strip tip 2>&1 | sed 's/\(saving bundle to \).*/\1/'
 hg unbundle .hg/strip-backup/*
 
 echo % strip with local changes, should complain
 hg up
 echo y>y
 hg add y
 hg strip tip | sed 's/\(saving bundle to \).*/\1/'
 echo % --force strip with local changes
 hg strip -f tip 2>&1 | sed 's/\(saving bundle to \).*/\1/'
 
 echo '% cd b; hg qrefresh'
 hg init refresh
 cd refresh
 echo a > a
 hg ci -Ama
 hg qnew -mfoo foo
 echo a >> a
 hg qrefresh
 mkdir b
 cd b
 echo f > f
 hg add f
 hg qrefresh
 sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
     -e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/" ../.hg/patches/foo
 echo % hg qrefresh .
 hg qrefresh .
 sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
     -e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/" ../.hg/patches/foo
 hg status
 
 echo % qpush failure
 cd ..
 hg qrefresh
 hg qnew -mbar bar
 echo foo > foo
 echo bar > bar
 hg add foo bar
 hg qrefresh
 hg qpop -a
 echo bar > foo
 hg qpush -a
 hg st
 
 echo % mq tags
 hg log --template '{rev} {tags}\n' -r qparent:qtip
 
 echo % bad node in status
 hg qpop
 hg strip -qn tip
 hg tip 2>&1 | sed -e 's/unknown node .*/unknown node/'
 hg branches 2>&1 | sed -e 's/unknown node .*/unknown node/'
 hg qpop 2>&1 | sed -e 's/unknown node .*/unknown node/'
 
 cat >>$HGRCPATH <<EOF
 [diff]
 git = True
 EOF
 cd ..
 hg init git
 cd git
 hg qinit
 
 hg qnew -m'new file' new
 echo foo > new
 chmod +x new
 hg add new
 hg qrefresh
 sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
     -e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/" .hg/patches/new
 
 hg qnew -m'copy file' copy
 hg cp new copy
 hg qrefresh
 sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
     -e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/" .hg/patches/copy
 
 hg qpop
 hg qpush
 hg qdiff
 cat >>$HGRCPATH <<EOF
 [diff]
 git = False
 EOF
 hg qdiff --git
 
 cd ..
 hg init slow
 cd slow
 hg qinit
 echo foo > foo
 hg add foo
 hg ci -m 'add foo'
 hg qnew bar
 echo bar > bar
 hg add bar
 hg mv foo baz
 hg qrefresh --git
 hg up -C 0
 echo >> foo
 hg ci -m 'change foo'
 hg up -C 1
 hg qrefresh --git 2>&1 | grep -v 'saving bundle'
 cat .hg/patches/bar
 hg log -vC --template '{rev} {file_copies%filecopy}\n' -r .
 hg qrefresh --git
 cat .hg/patches/bar
 hg log -vC --template '{rev} {file_copies%filecopy}\n' -r .
 hg qrefresh
 grep 'diff --git' .hg/patches/bar
 
 echo
 hg up -C 1
 echo >> foo
 hg ci -m 'change foo again'
 hg up -C 2
 hg mv bar quux
 hg mv baz bleh
 hg qrefresh --git 2>&1 | grep -v 'saving bundle'
 cat .hg/patches/bar
 hg log -vC --template '{rev} {file_copies%filecopy}\n' -r .
 hg mv quux fred
 hg mv bleh barney
 hg qrefresh --git
 cat .hg/patches/bar
 hg log -vC --template '{rev} {file_copies%filecopy}\n' -r .
 
 echo % refresh omitting an added file
 hg qnew baz
 echo newfile > newfile
 hg add newfile
 hg qrefresh
 hg st -A newfile
 hg qrefresh -X newfile
 hg st -A newfile
 hg revert newfile
 rm newfile
 hg qpop
 hg qdel baz
 
 echo % create a git patch
 echo a > alexander
 hg add alexander
 hg qnew -f --git addalexander
 grep diff .hg/patches/addalexander
 
 echo % create a git binary patch
 cat > writebin.py <<EOF
 import sys
 path = sys.argv[1]
 open(path, 'wb').write('BIN\x00ARY')
 EOF
 python writebin.py bucephalus
 
 python "$TESTDIR/md5sum.py" bucephalus
 hg add bucephalus
 hg qnew -f --git addbucephalus
 grep diff .hg/patches/addbucephalus
 
 echo % check binary patches can be popped and pushed
 hg qpop
 test -f bucephalus && echo % bucephalus should not be there
 hg qpush
 test -f bucephalus || echo % bucephalus should be there
 python "$TESTDIR/md5sum.py" bucephalus
 
 
 echo '% strip again'
 cd ..
 hg init strip
 cd strip
 touch foo
 hg add foo
 hg ci -m 'add foo'
 echo >> foo
 hg ci -m 'change foo 1'
 hg up -C 0
 echo 1 >> foo
 hg ci -m 'change foo 2'
 HGMERGE=true hg merge
 hg ci -m merge
 hg log
 hg strip 1 2>&1 | sed 's/\(saving bundle to \).*/\1/'
 checkundo strip
 hg log
 cd ..
 
 echo '% qclone'
 qlog()
 {
     echo 'main repo:'
     hg log --template '    rev {rev}: {desc}\n'
     echo 'patch repo:'
     hg -R .hg/patches log --template '    rev {rev}: {desc}\n'
 }
 hg init qclonesource
 cd qclonesource
 echo foo > foo
 hg add foo
 hg ci -m 'add foo'
 hg qinit
 hg qnew patch1
 echo bar >> foo
 hg qrefresh -m 'change foo'
 cd ..
 
 # repo with unversioned patch dir
 hg qclone qclonesource failure
 
 cd qclonesource
 hg qinit -c
 hg qci -m checkpoint
 qlog
 cd ..
 
 # repo with patches applied
 hg qclone qclonesource qclonedest
 cd qclonedest
 qlog
 cd ..
 
 # repo with patches unapplied
 cd qclonesource
 hg qpop -a
 qlog
 cd ..
 hg qclone qclonesource qclonedest2
 cd qclonedest2
 qlog
 cd ..
 
 echo % 'test applying on an empty file (issue 1033)'
 hg init empty
 cd empty
 touch a
 hg ci -Am addempty
 echo a > a
 hg qnew -f -e changea
 hg qpop
 hg qpush
 cd ..
 
 echo % test qpush with --force, issue1087
 hg init forcepush
 cd forcepush
 echo hello > hello.txt
 echo bye > bye.txt
 hg ci -Ama
 hg qnew -d '0 0' empty
 hg qpop
 echo world >> hello.txt
 
 echo % qpush should fail, local changes
 hg qpush
 
 echo % apply force, should not discard changes with empty patch
 hg qpush -f 2>&1 | sed 's,^.*/patch,patch,g'
 hg diff --config diff.nodates=True
 hg qdiff --config diff.nodates=True
 hg log -l1 -p
 hg qref -d '0 0'
 hg qpop
 echo universe >> hello.txt
 echo universe >> bye.txt
 
 echo % qpush should fail, local changes
 hg qpush
 
 echo % apply force, should discard changes in hello, but not bye
 hg qpush -f
 hg st
 hg diff --config diff.nodates=True
 hg qdiff --config diff.nodates=True
 
 echo % test popping revisions not in working dir ancestry
 hg qseries -v
 hg up qparent
 hg qpop

tests/test-mq.out

@@ -1,573 +1,577 b''
 % help
 mq extension - manage a stack of patches
 
 This extension lets you work with a stack of patches in a Mercurial
 repository. It manages two stacks of patches - all known patches, and applied
 patches (subset of known patches).
 
 Known patches are represented as patch files in the .hg/patches directory.
 Applied patches are both patch files and changesets.
 
 Common tasks (use "hg help command" for more details):
 
 prepare repository to work with patches   qinit
 create new patch                          qnew
 import existing patch                     qimport
 
 print patch series                        qseries
 print applied patches                     qapplied
 print name of top applied patch           qtop
 
 add known patch to applied stack          qpush
 remove patch from applied stack           qpop
 refresh contents of top applied patch     qrefresh
 
 list of commands:
 
  qapplied     print the patches already applied
  qclone       clone main and patch repository at same time
  qcommit      commit changes in the queue repository
  qdelete      remove patches from queue
  qdiff        diff of the current patch and subsequent modifications
  qfinish      move applied patches into repository history
  qfold        fold the named patches into the current patch
  qgoto        push or pop patches until named patch is at top of stack
  qguard       set or print guards for a patch
  qheader      print the header of the topmost or specified patch
  qimport      import a patch
  qinit        init a new queue repository
  qnew         create a new patch
  qnext        print the name of the next patch
  qpop         pop the current patch off the stack
  qprev        print the name of the previous patch
  qpush        push the next patch onto the stack
  qrefresh     update the current patch
  qrename      rename a patch
  qrestore     restore the queue state saved by a revision
  qsave        save current queue state
  qselect      set or print guarded patches to push
  qseries      print the entire series file
  qtop         print the name of the current patch
  qunapplied   print the patches not yet applied
  strip        strip a revision and all its descendants from the repository
 
 enabled extensions:
 
  mq   manage a stack of patches
 
 use "hg -v help mq" to show aliases and global options
 adding a
 updating working directory
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 adding b/z
 % qinit
 % -R qinit
 % qinit -c
 A .hgignore
 A series
 % qinit; qinit -c
   .hgignore:
 ^\.hg
 ^\.mq
 syntax: glob
 status
 guards
   series:
 abort: repository already exists!
 % qinit; <stuff>; qinit -c
 adding .hg/patches/A
 adding .hg/patches/B
 A .hgignore
 A A
 A B
 A series
   .hgignore:
 status
 bleh
   series:
 A
 B
 % qrefresh
 foo bar
 
 diff -r  xa
 --- a/a
 +++ b/a
 @@ -1,1 +1,2 @@
  a
 +a
 % empty qrefresh
 revision:
 patch:
 foo bar
 
 working dir diff:
 --- a/a
 +++ b/a
 @@ -1,1 +1,2 @@
  a
 +a
 % qpop
 popping test.patch
 patch queue now empty
-% qpush
+% qpush with dump of tag cache
+.hg/tags.cache (pre qpush):
+1
 applying test.patch
 now at: test.patch
+.hg/tags.cache (post qpush):
+2
 % pop/push outside repo
 popping test.patch
 patch queue now empty
 applying test.patch
 now at: test.patch
 % qrefresh in subdir
 % pop/push -a in subdir
 popping test2.patch
 popping test.patch
 patch queue now empty
 applying test.patch
 applying test2.patch
 now at: test2.patch
 % qseries
 test.patch
 test2.patch
 popping test2.patch
 now at: test.patch
 0 A test.patch: foo bar
 1 U test2.patch: 
 applying test2.patch
 now at: test2.patch
 % qapplied
 test.patch
 test2.patch
 % qtop
 test2.patch
 % qprev
 test.patch
 % qnext
 all patches applied
 % pop, qnext, qprev, qapplied
 popping test2.patch
 now at: test.patch
 test2.patch
 only one patch applied
 test.patch
 % commit should fail
 abort: cannot commit over an applied mq patch
 % push should fail
 pushing to ../../k
 abort: source has mq patches applied
 % import should fail
 abort: cannot import over an applied patch
 % qunapplied
 test2.patch
 % qpush/qpop with index
 applying test2.patch
 now at: test2.patch
 popping test2.patch
 popping test1b.patch
 now at: test.patch
 applying test1b.patch
 now at: test1b.patch
 applying test2.patch
 now at: test2.patch
 popping test2.patch
 now at: test1b.patch
 popping test1b.patch
 now at: test.patch
 applying test1b.patch
 applying test2.patch
 now at: test2.patch
 % push should succeed
 popping test2.patch
 popping test1b.patch
 popping test.patch
 patch queue now empty
 pushing to ../../k
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 % qpush/qpop error codes
 applying test.patch
 applying test1b.patch
 applying test2.patch
 now at: test2.patch
   % pops all patches and succeeds
 popping test2.patch
 popping test1b.patch
 popping test.patch
 patch queue now empty
   qpop -a succeeds
   % does nothing and succeeds
 no patches applied
   qpop -a succeeds
   % fails - nothing else to pop
 no patches applied
   qpop fails
   % pushes a patch and succeeds
 applying test.patch
 now at: test.patch
   qpush succeeds
   % pops a patch and succeeds
 popping test.patch
 patch queue now empty
   qpop succeeds
   % pushes up to test1b.patch and succeeds
 applying test.patch
 applying test1b.patch
 now at: test1b.patch
   qpush test1b.patch succeeds
   % does nothing and succeeds
 qpush: test1b.patch is already at the top
   qpush test1b.patch succeeds
   % does nothing and succeeds
 qpop: test1b.patch is already at the top
   qpop test1b.patch succeeds
   % fails - can't push to this patch
 abort: cannot push to a previous patch: test.patch
   qpush test.patch fails
   % fails - can't pop to this patch
 abort: patch test2.patch is not applied
   qpop test2.patch fails
   % pops up to test.patch and succeeds
 popping test1b.patch
 now at: test.patch
   qpop test.patch succeeds
   % pushes all patches and succeeds
 applying test1b.patch
 applying test2.patch
 now at: test2.patch
   qpush -a succeeds
   % does nothing and succeeds
 all patches are currently applied
   qpush -a succeeds
   % fails - nothing else to push
 patch series already fully applied
   qpush fails
   % does nothing and succeeds
 qpush: test2.patch is already at the top
   qpush test2.patch succeeds
 % strip
 adding x
 0 files updated, 0 files merged, 1 files removed, 0 files unresolved
 saving bundle to 
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 (run 'hg update' to get a working copy)
 % strip with local changes, should complain
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 abort: local changes found
 % --force strip with local changes
 0 files updated, 0 files merged, 1 files removed, 0 files unresolved
 saving bundle to 
 % cd b; hg qrefresh
 adding a
 foo
 
 diff -r cb9a9f314b8b a
 --- a/a
 +++ b/a
 @@ -1,1 +1,2 @@
  a
 +a
 diff -r cb9a9f314b8b b/f
 --- /dev/null
 +++ b/b/f
 @@ -0,0 +1,1 @@
 +f
 % hg qrefresh .
 foo
 
 diff -r cb9a9f314b8b b/f
 --- /dev/null
 +++ b/b/f
 @@ -0,0 +1,1 @@
 +f
 M a
 % qpush failure
 popping bar
 popping foo
 patch queue now empty
 applying foo
 applying bar
 file foo already exists
 1 out of 1 hunks FAILED -- saving rejects to file foo.rej
 patch failed, unable to continue (try -v)
 patch failed, rejects left in working dir
 errors during apply, please fix and refresh bar
 ? foo
 ? foo.rej
 % mq tags
 0 qparent
 1 qbase foo
 2 qtip bar tip
 % bad node in status
 popping bar
 now at: foo
 changeset:   0:cb9a9f314b8b
 mq status file refers to unknown node
 tag:         tip
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     a
 
 mq status file refers to unknown node
 default                        0:cb9a9f314b8b
 abort: trying to pop unknown node
 new file
 
 diff --git a/new b/new
 new file mode 100755
 --- /dev/null
 +++ b/new
 @@ -0,0 +1,1 @@
 +foo
 copy file
 
 diff --git a/new b/copy
 copy from new
 copy to copy
 popping copy
 now at: new
 applying copy
 now at: copy
 diff --git a/new b/copy
 copy from new
 copy to copy
 diff --git a/new b/copy
 copy from new
 copy to copy
 1 files updated, 0 files merged, 2 files removed, 0 files unresolved
 created new head
 2 files updated, 0 files merged, 1 files removed, 0 files unresolved
 popping bar
 adding branch
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 patch queue now empty
 (working directory not at a head)
 applying bar
 now at: bar
 diff --git a/bar b/bar
 new file mode 100644
 --- /dev/null
 +++ b/bar
 @@ -0,0 +1,1 @@
 +bar
 diff --git a/foo b/baz
 rename from foo
 rename to baz
 2 baz (foo)
 diff --git a/bar b/bar
 new file mode 100644
 --- /dev/null
 +++ b/bar
 @@ -0,0 +1,1 @@
 +bar
 diff --git a/foo b/baz
 rename from foo
 rename to baz
 2 baz (foo)
 diff --git a/bar b/bar
 diff --git a/foo b/baz
 
 1 files updated, 0 files merged, 2 files removed, 0 files unresolved
 2 files updated, 0 files merged, 1 files removed, 0 files unresolved
 popping bar
 adding branch
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 patch queue now empty
 (working directory not at a head)
 applying bar
 now at: bar
 diff --git a/foo b/bleh
 rename from foo
 rename to bleh
 diff --git a/quux b/quux
 new file mode 100644
 --- /dev/null
 +++ b/quux
 @@ -0,0 +1,1 @@
 +bar
 3 bleh (foo)
 diff --git a/foo b/barney
 rename from foo
 rename to barney
 diff --git a/fred b/fred
 new file mode 100644
 --- /dev/null
 +++ b/fred
 @@ -0,0 +1,1 @@
 +bar
 3 barney (foo)
 % refresh omitting an added file
 C newfile
 A newfile
 popping baz
 now at: bar
 % create a git patch
 diff --git a/alexander b/alexander
 % create a git binary patch
 8ba2a2f3e77b55d03051ff9c24ad65e7  bucephalus
 diff --git a/bucephalus b/bucephalus
 % check binary patches can be popped and pushed
 popping addbucephalus
 now at: addalexander
 applying addbucephalus
 now at: addbucephalus
 8ba2a2f3e77b55d03051ff9c24ad65e7  bucephalus
 % strip again
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 created new head
 merging foo
 0 files updated, 1 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 changeset:   3:99615015637b
 tag:         tip
 parent:      2:20cbbe65cff7
 parent:      1:d2871fc282d4
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     merge
 
 changeset:   2:20cbbe65cff7
 parent:      0:53245c60e682
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     change foo 2
 
 changeset:   1:d2871fc282d4
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     change foo 1
 
 changeset:   0:53245c60e682
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     add foo
 
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 saving bundle to 
 saving bundle to 
 adding branch
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 changeset:   1:20cbbe65cff7
 tag:         tip
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     change foo 2
 
 changeset:   0:53245c60e682
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     add foo
 
 % qclone
 abort: versioned patch repository not found (see qinit -c)
 adding .hg/patches/patch1
 main repo:
     rev 1: change foo
     rev 0: add foo
 patch repo:
     rev 0: checkpoint
 updating working directory
 3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 main repo:
     rev 0: add foo
 patch repo:
     rev 0: checkpoint
 popping patch1
 patch queue now empty
 main repo:
     rev 0: add foo
 patch repo:
     rev 0: checkpoint
 updating working directory
 3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 main repo:
     rev 0: add foo
 patch repo:
     rev 0: checkpoint
 % test applying on an empty file (issue 1033)
 adding a
 popping changea
 patch queue now empty
 applying changea
 now at: changea
 % test qpush with --force, issue1087
 adding bye.txt
 adding hello.txt
 popping empty
 patch queue now empty
 % qpush should fail, local changes
 abort: local changes found, refresh first
 % apply force, should not discard changes with empty patch
 applying empty
 patch empty is empty
 now at: empty
 diff -r bf5fc3f07a0a hello.txt
 --- a/hello.txt
 +++ b/hello.txt
 @@ -1,1 +1,2 @@
  hello
 +world
 diff -r 9ecee4f634e3 hello.txt
 --- a/hello.txt
 +++ b/hello.txt
 @@ -1,1 +1,2 @@
  hello
 +world
 changeset:   1:bf5fc3f07a0a
 tag:         qtip
 tag:         tip
 tag:         empty
 tag:         qbase
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     imported patch empty
 
 
 popping empty
 patch queue now empty
 % qpush should fail, local changes
 abort: local changes found, refresh first
 % apply force, should discard changes in hello, but not bye
 applying empty
 now at: empty
 M bye.txt
 diff -r ba252371dbc1 bye.txt
 --- a/bye.txt
 +++ b/bye.txt
 @@ -1,1 +1,2 @@
  bye
 +universe
 diff -r 9ecee4f634e3 bye.txt
 --- a/bye.txt
 +++ b/bye.txt
 @@ -1,1 +1,2 @@
  bye
 +universe
 diff -r 9ecee4f634e3 hello.txt
 --- a/hello.txt
 +++ b/hello.txt
 @@ -1,1 +1,3 @@
  hello
 +world
 +universe
 % test popping revisions not in working dir ancestry
 0 A empty
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 popping empty
 patch queue now empty

tests/test-tags

@@ -1,191 +1,202 b''
 #!/bin/sh
 
+cacheexists() {
+    [ -f .hg/tags.cache ] && echo "tag cache exists" || echo "no tag cache"
+}
+
 echo "% setup"
 mkdir t
 cd t
 hg init
+cacheexists
 hg id
+cacheexists
 echo a > a
 hg add a
 hg commit -m "test"
 hg co
 hg identify
+cacheexists
 
 echo "% create local tag with long name"
 T=`hg identify --debug --id`
 hg tag -l "This is a local tag with a really long name!"
 hg tags
 rm .hg/localtags
 
 echo "% create a tag behind hg's back"
 echo "$T first" > .hgtags
 cat .hgtags
 hg add .hgtags
 hg commit -m "add tags"
 hg tags
 hg identify
 
+# repeat with cold tag cache
+rm -f .hg/tags.cache
+hg identify
+
 echo "% create a branch"
 echo bb > a
 hg status
 hg identify
 hg co first
 hg id
 hg -v id
 hg status
 echo 1 > b
 hg add b
 hg commit -m "branch"
 hg id
 
 echo "% merge the two heads"
 hg merge 1
 hg id
 hg status
 
 hg commit -m "merge"
 
 echo "% create fake head, make sure tag not visible afterwards"
 cp .hgtags tags
 hg tag last
 hg rm .hgtags
 hg commit -m "remove"
 
 mv tags .hgtags
 hg add .hgtags
 hg commit -m "readd"
 
 hg tags
 
 echo "% add invalid tags"
 echo "spam" >> .hgtags
 echo >> .hgtags
 echo "foo bar" >> .hgtags
 echo "$T invalid" | sed "s/..../a5a5/" >> .hg/localtags
 echo "committing .hgtags:"
 cat .hgtags 
 hg commit -m "tags"
 
 echo "% report tag parse error on other head"
 hg up 3
 echo 'x y' >> .hgtags
 hg commit -m "head"
 
 hg tags
 hg tip
 
 echo "% test tag precedence rules"
 cd ..
 hg init t2
 cd t2
 echo foo > foo
 hg add foo
 hg ci -m 'add foo'      # rev 0
 hg tag bar              # rev 1
 echo >> foo
 hg ci -m 'change foo 1' # rev 2
 hg up -C 1
 hg tag -r 1 -f bar      # rev 3
 hg up -C 1
 echo >> foo
 hg ci -m 'change foo 2' # rev 4
 hg tags
 hg tags         # repeat in case of cache effects
 
 dumptags() {
     rev=$1
     echo "rev $rev: .hgtags:"
     hg cat -r$rev .hgtags
 }
 
 echo "% detailed dump of tag info"
 echo "heads:"
 hg heads -q             # expect 4, 3, 2
 dumptags 2
 dumptags 3
 dumptags 4
 echo ".hg/tags.cache:"
 [ -f .hg/tags.cache ] && cat .hg/tags.cache || echo "no such file"
 
 echo "% test tag removal"
 hg tag --remove bar     # rev 5
 hg tip -vp
 hg tags
 hg tags                 # again, try to expose cache bugs
 
 echo '% remove nonexistent tag'
 hg tag --remove foobar
 hg tip
 
 echo "% rollback undoes tag operation"
 hg rollback             # destroy rev 5 (restore bar)
 hg tags
 hg tags
 
 echo "% test tag rank"
 cd ..
 hg init t3
 cd t3
 echo foo > foo
 hg add foo
 hg ci -m 'add foo'       # rev 0
 hg tag -f bar            # rev 1 bar -> 0
 hg tag -f bar            # rev 2 bar -> 1
 hg tag -fr 0 bar         # rev 3 bar -> 0
 hg tag -fr 1 bar         # rev 4 bar -> 1
 hg tag -fr 0 bar         # rev 5 bar -> 0
 hg tags
 hg co 3
 echo barbar > foo
 hg ci -m 'change foo'    # rev 6
 hg tags
 
 echo "% don't allow moving tag without -f"
 hg tag -r 3 bar
 hg tags
 
 echo "% strip 1: expose an old head"
 hg --config extensions.mq= strip 5 > /dev/null 2>&1
 hg tags                  # partly stale cache
 hg tags                  # up-to-date cache
 echo "% strip 2: destroy whole branch, no old head exposed"
 hg --config extensions.mq= strip 4 > /dev/null 2>&1 
 hg tags                  # partly stale
 rm -f .hg/tags.cache
 hg tags                  # cold cache
 
 echo "% test tag rank with 3 heads"
 cd ..
 hg init t4
 cd t4
 echo foo > foo
 hg add
 hg ci -m 'add foo'                 # rev 0
 hg tag bar                         # rev 1 bar -> 0
 hg tag -f bar                      # rev 2 bar -> 1
 hg up -qC 0
 hg tag -fr 2 bar                   # rev 3 bar -> 2
 hg tags
 hg up -qC 0
 hg tag -m 'retag rev 0' -fr 0 bar  # rev 4 bar -> 0, but bar stays at 2
 echo "% bar should still point to rev 2"
 hg tags
 
 
 echo "% remove local as global and global as local"
 # test that removing global/local tags does not get confused when trying
 # to remove a tag of type X which actually only exists as a type Y
 cd ..
 hg init t5
 cd t5
 echo foo > foo
 hg add
 hg ci -m 'add foo'                 # rev 0
 
 hg tag -r 0 -l localtag
 hg tag --remove localtag
 
 hg tag -r 0 globaltag
 hg tag --remove -l globaltag
 hg tags -v
 exit 0

tests/test-tags.out

@@ -1,145 +1,151 b''
 % setup
+no tag cache
 000000000000 tip
+no tag cache
 0 files updated, 0 files merged, 0 files removed, 0 files unresolved
 acb14030fe0a tip
+tag cache exists
 % create local tag with long name
 tip                                0:acb14030fe0a
 This is a local tag with a really long name!     0:acb14030fe0a
 % create a tag behind hg's back
 acb14030fe0a21b60322c440ad2d20cf7685a376 first
 tip                                1:b9154636be93
 first                              0:acb14030fe0a
 b9154636be93 tip
+b9154636be93 tip
 % create a branch
 M a
 b9154636be93+ tip
 0 files updated, 0 files merged, 1 files removed, 0 files unresolved
 acb14030fe0a+ first
 acb14030fe0a+ first
 M a
 created new head
 c8edf04160c7 tip
 % merge the two heads
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 c8edf04160c7+b9154636be93+ tip
 M .hgtags
 % create fake head, make sure tag not visible afterwards
 tip                                6:35ff301afafe
 first                              0:acb14030fe0a
 % add invalid tags
 committing .hgtags:
 acb14030fe0a21b60322c440ad2d20cf7685a376 first
 spam
 
 foo bar
 % report tag parse error on other head
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 created new head
 .hgtags@75d9f02dfe28, line 2: cannot parse entry
 .hgtags@75d9f02dfe28, line 4: node 'foo' is not well formed
 .hgtags@c4be69a18c11, line 2: node 'x' is not well formed
 tip                                8:c4be69a18c11
 first                              0:acb14030fe0a
 changeset:   8:c4be69a18c11
 .hgtags@75d9f02dfe28, line 2: cannot parse entry
 .hgtags@75d9f02dfe28, line 4: node 'foo' is not well formed
 .hgtags@c4be69a18c11, line 2: node 'x' is not well formed
 tag:         tip
 parent:      3:ac5e980c4dc0
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     head
 
 % test tag precedence rules
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 created new head
 tip                                4:0c192d7d5e6b
 bar                                1:78391a272241
 tip                                4:0c192d7d5e6b
 bar                                1:78391a272241
 % detailed dump of tag info
 heads:
 4:0c192d7d5e6b
 3:6fa450212aeb
 2:7a94127795a3
 rev 2: .hgtags:
 bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 rev 3: .hgtags:
 bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 78391a272241d70354aa14c874552cad6b51bb42 bar
 rev 4: .hgtags:
 bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 .hg/tags.cache:
-no such file
+4 0c192d7d5e6b78a714de54a2e9627952a877e25a 0c04f2a8af31de17fab7422878ee5a2dadbc943d
+3 6fa450212aeb2a21ed616a54aea39a4a27894cd7 7d3b718c964ef37b89e550ebdafd5789e76ce1b0
+2 7a94127795a33c10a370c93f731fd9fea0b79af6 0c04f2a8af31de17fab7422878ee5a2dadbc943d
 % test tag removal
 changeset:   5:5f6e8655b1c7
 tag:         tip
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 files:       .hgtags
 description:
 Removed tag bar
 
 
 diff -r 0c192d7d5e6b -r 5f6e8655b1c7 .hgtags
 --- a/.hgtags	Thu Jan 01 00:00:00 1970 +0000
 +++ b/.hgtags	Thu Jan 01 00:00:00 1970 +0000
 @@ -1,1 +1,3 @@
  bbd179dfa0a71671c253b3ae0aa1513b60d199fa bar
 +78391a272241d70354aa14c874552cad6b51bb42 bar
 +0000000000000000000000000000000000000000 bar
 
 tip                                5:5f6e8655b1c7
 tip                                5:5f6e8655b1c7
 % remove nonexistent tag
 abort: tag 'foobar' does not exist
 changeset:   5:5f6e8655b1c7
 tag:         tip
 user:        test
 date:        Thu Jan 01 00:00:00 1970 +0000
 summary:     Removed tag bar
 
 % rollback undoes tag operation
 rolling back last transaction
 tip                                4:0c192d7d5e6b
 bar                                1:78391a272241
 tip                                4:0c192d7d5e6b
 bar                                1:78391a272241
 % test tag rank
 tip                                5:85f05169d91d
 bar                                0:bbd179dfa0a7
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 created new head
 tip                                6:735c3ca72986
 bar                                0:bbd179dfa0a7
 % don't allow moving tag without -f
 abort: tag 'bar' already exists (use -f to force)
 tip                                6:735c3ca72986
 bar                                0:bbd179dfa0a7
 % strip 1: expose an old head
 tip                                5:735c3ca72986
 bar                                1:78391a272241
 tip                                5:735c3ca72986
 bar                                1:78391a272241
 % strip 2: destroy whole branch, no old head exposed
 tip                                4:735c3ca72986
 bar                                0:bbd179dfa0a7
 tip                                4:735c3ca72986
 bar                                0:bbd179dfa0a7
 % test tag rank with 3 heads
 adding foo
 tip                                3:197c21bbbf2c
 bar                                2:6fa450212aeb
 % bar should still point to rev 2
 tip                                4:3b4b14ed0202
 bar                                2:6fa450212aeb
 % remove local as global and global as local
 adding foo
 abort: tag 'localtag' is not a global tag
 abort: tag 'globaltag' is not a local tag
 tip                                1:a0b6fe111088
 localtag                           0:bbd179dfa0a7 local
 globaltag                          0:bbd179dfa0a7