Merge with crew-stable

mercurial/localrepo.py

@@ -1,2172 +1,2171 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)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         self.tags()
 
         return self._tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().iteritems():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in sorted(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().iteritems():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchmap(self):
         tip = self.changelog.tip()
         if self.branchcache is not None and self._branchcachetip == tip:
             return self.branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if 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.RepoLookupError(_("unknown revision '%s'") % key)
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = match_.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise error.RepoError(_("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):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self['.'].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
             meta["copy"] = cfname
             meta["copyrev"] = hex(crev)
             fparent1, fparent2 = nullid, newfparent
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 !=  fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = match_.always(self.root, '')
 
         if not force:
             vdirs = []
             match.dir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             p1, p2 = self.dirstate.parents()
             wctx = self[None]
 
             if (not force and p2 != nullid and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             for s in wctx.substate:
                 if match(s) and wctx.sub(s).dirty():
                     subs.append(s)
             if subs and '.hgsubstate' not in changes[0]:
                 changes[0].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             if (not force and not extra.get("close") and p2 == nullid
                 and not (changes[0] or changes[1] or changes[2])
                 and self[None].branch() == self['.'].branch()):
                 return None
 
             ms = merge_.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
 
             cctx = context.workingctx(self, (p1, p2), text, user, date,
                                       extra, changes)
             if editor:
                 cctx._text = editor(self, cctx, subs)
 
             # 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.'''
         # XXX it might be nice if we could take the list of destroyed
         # nodes, but I don't see an easy way for rollback() to do that
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         tags_.findglobaltags(self.ui, self, {}, {})
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or match_.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 if f not in ctx1:
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             s = self.dirstate.status(match, listignored, listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f].data())):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 if listclean:
                     clean += fixup
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn].data())))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
         [l.sort() for l in r]
         return r
 
     def add(self, list):
         wlock = self.wlock()
         try:
             rejected = []
             for f in list:
                 p = self.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     self.ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     self.ui.warn(_("%s: files over 10MB may cause memory and"
                                    " performance problems\n"
                                    "(use 'hg revert %s' to unadd the file)\n")
                                    % (f, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     self.ui.warn(_("%s not added: only files and symlinks "
                                    "supported currently\n") % f)
                     rejected.append(p)
                 elif self.dirstate[f] in 'amn':
                     self.ui.warn(_("%s already tracked!\n") % f)
                 elif self.dirstate[f] == 'r':
                     self.dirstate.normallookup(f)
                 else:
                     self.dirstate.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, list):
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'a':
                     self.ui.warn(_("%s not added!\n") % f)
                 else:
                     self.dirstate.forget(f)
         finally:
             wlock.release()
 
     def remove(self, list, unlink=False):
         if unlink:
             for f in list:
                 try:
                     util.unlink(self.wjoin(f))
                 except OSError, inst:
                     if inst.errno != errno.ENOENT:
                         raise
         wlock = self.wlock()
         try:
             for f in list:
                 if unlink and os.path.exists(self.wjoin(f)):
                     self.ui.warn(_("%s still exists!\n") % f)
                 elif self.dirstate[f] == 'a':
                     self.dirstate.forget(f)
                 elif f not in self.dirstate:
                     self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self.dirstate.remove(f)
         finally:
             wlock.release()
 
     def undelete(self, list):
         manifests = [self.manifest.read(self.changelog.read(p)[0])
                      for p in self.dirstate.parents() if p != nullid]
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'r':
                     self.ui.warn(_("%s not removed!\n") % f)
                 else:
                     m = f in manifests[0] and manifests[0] or manifests[1]
                     t = self.file(f).read(m[f])
                     self.wwrite(f, t, m.flags(f))
                     self.dirstate.normal(f)
         finally:
             wlock.release()
 
     def copy(self, source, dest):
         p = self.wjoin(dest)
         if not (os.path.exists(p) or os.path.islink(p)):
             self.ui.warn(_("%s does not exist!\n") % dest)
         elif not (os.path.isfile(p) or os.path.islink(p)):
             self.ui.warn(_("copy failed: %s is not a file or a "
                            "symbolic link\n") % dest)
         else:
             wlock = self.wlock()
             try:
                 if self.dirstate[dest] in '?r':
                     self.dirstate.add(dest)
                 self.dirstate.copy(source, dest)
             finally:
                 wlock.release()
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         return [n for (r, n) in sorted(heads)]
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if
                       ('close' not in self.changelog.read(h)[5])]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         return self.findcommonincoming(remote, base, heads, force)[1]
 
     def findcommonincoming(self, remote, base=None, heads=None, force=False):
         """Return a tuple (common, missing roots, heads) used to identify
         missing nodes from remote.
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         """
         m = self.changelog.nodemap
         search = []
         fetch = set()
         seen = set()
         seenbranch = set()
         if base is None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid], [nullid], list(heads)
             return [nullid], [], []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         heads = unknown
         if not unknown:
             return base.keys(), [], []
 
         req = set(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug("examining %s:%s\n"
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug("branch already found\n")
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug("found incomplete branch %s:%s\n"
                                   % (short(n[0]), short(n[1])))
                     search.append(n[0:2]) # schedule branch range for scanning
                     seenbranch.add(n)
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug("found new changeset %s\n" %
                                           short(n[1]))
                             fetch.add(n[1]) # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req.add(p)
                 seen.add(n[0])
 
             if r:
                 reqcnt += 1
                 self.ui.debug("request %d: %s\n" %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug("received %s:%s\n" %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             newsearch = []
             reqcnt += 1
             for n, l in zip(search, remote.between(search)):
                 l.append(n[1])
                 p = n[0]
                 f = 1
                 for i in l:
                     self.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
                     if i in m:
                         if f <= 2:
                             self.ui.debug("found new branch changeset %s\n" %
                                               short(p))
                             fetch.add(p)
                             base[i] = 1
                         else:
                             self.ui.debug("narrowed branch search to %s:%s\n"
                                           % (short(p), short(i)))
                             newsearch.append((p, i))
                         break
                     p, f = i, f * 2
                 search = newsearch
 
         # sanity check our fetch list
         for f in fetch:
             if f in m:
                 raise error.RepoError(_("already have changeset ")
                                       + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug("found new changesets starting at " +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug("%d total queries\n" % reqcnt)
 
         return base.keys(), list(fetch), heads
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base is None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug("common changesets up to "
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = set(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         remain.remove(nullid)
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 remain.remove(n)
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = set()
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads.add(p1)
                 if p2 in heads:
                     updated_heads.add(p2)
 
         # this is the set of all roots we have to push
         if heads:
             return subset, list(updated_heads)
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             common, fetch, rheads = self.findcommonincoming(remote, heads=heads,
                                                             force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None and remote.capable('changegroupsubset'):
                 heads = rheads
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if not remote.capable('changegroupsubset'):
                     raise util.Abort(_("Partial pull cannot be done because "
                                        "other repository doesn't support "
                                        "changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             lock.release()
 
     def push(self, remote, force=False, revs=None):
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if remote.capable('unbundle'):
             return self.push_unbundle(remote, force, revs)
         return self.push_addchangegroup(remote, force, revs)
 
     def prepush(self, remote, force, revs):
         '''Analyze the local and remote repositories and determine which
         changesets need to be pushed to the remote.  Return a tuple
         (changegroup, remoteheads).  changegroup is a readable file-like
         object whose read() returns successive changegroup chunks ready to
         be sent over the wire.  remoteheads is the list of remote heads.
         '''
         common = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, common, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, common, remote_heads)
-        if revs is not None:
-            msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
-        else:
-            bases, heads = update, self.changelog.heads()
+        msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
 
-        def checkbranch(lheads, rheads, updatelh):
+        def checkbranch(lheads, rheads, updatelb):
             '''
             check whether there are more local heads than remote heads on
             a specific branch.
 
             lheads: local branch heads
             rheads: remote branch heads
-            updatelh: outgoing local branch heads
+            updatelb: outgoing local branch bases
             '''
 
             warn = 0
 
             if not revs and len(lheads) > len(rheads):
                 warn = 1
             else:
+                # add local heads involved in the push
                 updatelheads = [self.changelog.heads(x, lheads)
-                                for x in updatelh]
+                                for x in updatelb]
                 newheads = set(sum(updatelheads, [])) & set(lheads)
 
                 if not newheads:
                     return True
 
+                # add heads we don't have or that are not involved in the push
                 for r in rheads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.add(r)
                     else:
                         newheads.add(r)
                 if len(newheads) > len(rheads):
                     warn = 1
 
             if warn:
                 if not rheads: # new branch requires --force
                     self.ui.warn(_("abort: push creates new"
                                    " remote branch '%s'!\n") %
-                                   self[updatelh[0]].branch())
+                                   self[updatelb[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
+                        updatelb = [upd for upd in update
                                     if self[upd].branch() == lh]
-                        if not updatelh:
+                        if not updatelb:
                             continue
-                        if not checkbranch(lheads, rheads, updatelh):
+                        if not checkbranch(lheads, rheads, updatelb):
                             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):
         """Compute a changegroup consisting of all the nodes that are
         descendents of any of the bases and ancestors of any of the heads.
         Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         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):
         """Compute the changegroup of all nodes that we have that a recipient
         doesn't.  Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         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():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
             changedfiles = set()
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuprevlink_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         yield chnk
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """add changegroup to repo.
 
         return values:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - less heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction()
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             chunkiter = changegroup.chunkiter(source)
             if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             chunkiter = changegroup.chunkiter(source)
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             self.manifest.addgroup(chunkiter, revmap, trp)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug("adding %s revisions\n" % f)
                 fl = self.file(f)
                 o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
 
             newheads = len(cl.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
         finally:
             del tr
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug("updating the branch cache\n")
             self.branchtags()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             # for backwards compat, name was partially encoded
             ofp = self.sopener(store.decodedir(name), 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True

mercurial/util.py

@@ -1,1286 +1,1290 b''
 # util.py - Mercurial utility functions and platform specfic implementations
 #
 #  Copyright 2005 K. Thananchayan <[e-mail]>
 #  Copyright 2005-2007 Matt Mackall <[e-mail]>
 #  Copyright 2006 Vadim Gelfer <[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.
 
 """Mercurial utility functions and platform specfic implementations.
 
 This contains helper routines that are independent of the SCM core and
 hide platform-specific details from the core.
 """
 
 from i18n import _
-import error, osutil
+import error, osutil, encoding
 import cStringIO, errno, re, shutil, sys, tempfile, traceback
 import os, stat, time, calendar, random, textwrap
 import imp
 
 # Python compatibility
 
 def sha1(s):
     return _fastsha1(s)
 
 def _fastsha1(s):
     # This function will import sha1 from hashlib or sha (whichever is
     # available) and overwrite itself with it on the first call.
     # Subsequent calls will go directly to the imported function.
     try:
         from hashlib import sha1 as _sha1
     except ImportError:
         from sha import sha as _sha1
     global _fastsha1, sha1
     _fastsha1 = sha1 = _sha1
     return _sha1(s)
 
 import subprocess
 closefds = os.name == 'posix'
 def popen2(cmd):
     # Setting bufsize to -1 lets the system decide the buffer size.
     # The default for bufsize is 0, meaning unbuffered. This leads to
     # poor performance on Mac OS X: http://bugs.python.org/issue4194
     p = subprocess.Popen(cmd, shell=True, bufsize=-1,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE)
     return p.stdin, p.stdout
 def popen3(cmd):
     p = subprocess.Popen(cmd, shell=True, bufsize=-1,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          stderr=subprocess.PIPE)
     return p.stdin, p.stdout, p.stderr
 
 def version():
     """Return version information if available."""
     try:
         import __version__
         return __version__.version
     except ImportError:
         return 'unknown'
 
 # used by parsedate
 defaultdateformats = (
     '%Y-%m-%d %H:%M:%S',
     '%Y-%m-%d %I:%M:%S%p',
     '%Y-%m-%d %H:%M',
     '%Y-%m-%d %I:%M%p',
     '%Y-%m-%d',
     '%m-%d',
     '%m/%d',
     '%m/%d/%y',
     '%m/%d/%Y',
     '%a %b %d %H:%M:%S %Y',
     '%a %b %d %I:%M:%S%p %Y',
     '%a, %d %b %Y %H:%M:%S',        #  GNU coreutils "/bin/date --rfc-2822"
     '%b %d %H:%M:%S %Y',
     '%b %d %I:%M:%S%p %Y',
     '%b %d %H:%M:%S',
     '%b %d %I:%M:%S%p',
     '%b %d %H:%M',
     '%b %d %I:%M%p',
     '%b %d %Y',
     '%b %d',
     '%H:%M:%S',
     '%I:%M:%S%p',
     '%H:%M',
     '%I:%M%p',
 )
 
 extendeddateformats = defaultdateformats + (
     "%Y",
     "%Y-%m",
     "%b",
     "%b %Y",
     )
 
 def cachefunc(func):
     '''cache the result of function calls'''
     # XXX doesn't handle keywords args
     cache = {}
     if func.func_code.co_argcount == 1:
         # we gain a small amount of time because
         # we don't need to pack/unpack the list
         def f(arg):
             if arg not in cache:
                 cache[arg] = func(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 cache[args] = func(*args)
             return cache[args]
 
     return f
 
 def lrucachefunc(func):
     '''cache most recent results of function calls'''
     cache = {}
     order = []
     if func.func_code.co_argcount == 1:
         def f(arg):
             if arg not in cache:
                 if len(cache) > 20:
                     del cache[order.pop(0)]
                 cache[arg] = func(arg)
             else:
                 order.remove(arg)
             order.append(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 if len(cache) > 20:
                     del cache[order.pop(0)]
                 cache[args] = func(*args)
             else:
                 order.remove(args)
             order.append(args)
             return cache[args]
 
     return f
 
 class propertycache(object):
     def __init__(self, func):
         self.func = func
         self.name = func.__name__
     def __get__(self, obj, type=None):
         result = self.func(obj)
         setattr(obj, self.name, result)
         return result
 
 def pipefilter(s, cmd):
     '''filter string S through command CMD, returning its output'''
     p = subprocess.Popen(cmd, shell=True, close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE)
     pout, perr = p.communicate(s)
     return pout
 
 def tempfilter(s, cmd):
     '''filter string S through a pair of temporary files with CMD.
     CMD is used as a template to create the real command to be run,
     with the strings INFILE and OUTFILE replaced by the real names of
     the temporary files generated.'''
     inname, outname = None, None
     try:
         infd, inname = tempfile.mkstemp(prefix='hg-filter-in-')
         fp = os.fdopen(infd, 'wb')
         fp.write(s)
         fp.close()
         outfd, outname = tempfile.mkstemp(prefix='hg-filter-out-')
         os.close(outfd)
         cmd = cmd.replace('INFILE', inname)
         cmd = cmd.replace('OUTFILE', outname)
         code = os.system(cmd)
         if sys.platform == 'OpenVMS' and code & 1:
             code = 0
         if code: raise Abort(_("command '%s' failed: %s") %
                              (cmd, explain_exit(code)))
         return open(outname, 'rb').read()
     finally:
         try:
             if inname: os.unlink(inname)
         except: pass
         try:
             if outname: os.unlink(outname)
         except: pass
 
 filtertable = {
     'tempfile:': tempfilter,
     'pipe:': pipefilter,
     }
 
 def filter(s, cmd):
     "filter a string through a command that transforms its input to its output"
     for name, fn in filtertable.iteritems():
         if cmd.startswith(name):
             return fn(s, cmd[len(name):].lstrip())
     return pipefilter(s, cmd)
 
 def binary(s):
     """return true if a string is binary data"""
     return bool(s and '\0' in s)
 
 def increasingchunks(source, min=1024, max=65536):
     '''return no less than min bytes per chunk while data remains,
     doubling min after each chunk until it reaches max'''
     def log2(x):
         if not x:
             return 0
         i = 0
         while x:
             x >>= 1
             i += 1
         return i - 1
 
     buf = []
     blen = 0
     for chunk in source:
         buf.append(chunk)
         blen += len(chunk)
         if blen >= min:
             if min < max:
                 min = min << 1
                 nmin = 1 << log2(blen)
                 if nmin > min:
                     min = nmin
                 if min > max:
                     min = max
             yield ''.join(buf)
             blen = 0
             buf = []
     if buf:
         yield ''.join(buf)
 
 Abort = error.Abort
 
 def always(fn): return True
 def never(fn): return False
 
 def pathto(root, n1, n2):
     '''return the relative path from one place to another.
     root should use os.sep to separate directories
     n1 should use os.sep to separate directories
     n2 should use "/" to separate directories
     returns an os.sep-separated path.
 
     If n1 is a relative path, it's assumed it's
     relative to root.
     n2 should always be relative to root.
     '''
     if not n1: return localpath(n2)
     if os.path.isabs(n1):
         if os.path.splitdrive(root)[0] != os.path.splitdrive(n1)[0]:
             return os.path.join(root, localpath(n2))
         n2 = '/'.join((pconvert(root), n2))
     a, b = splitpath(n1), n2.split('/')
     a.reverse()
     b.reverse()
     while a and b and a[-1] == b[-1]:
         a.pop()
         b.pop()
     b.reverse()
     return os.sep.join((['..'] * len(a)) + b) or '.'
 
 def canonpath(root, cwd, myname):
     """return the canonical path of myname, given cwd and root"""
     if endswithsep(root):
         rootsep = root
     else:
         rootsep = root + os.sep
     name = myname
     if not os.path.isabs(name):
         name = os.path.join(root, cwd, name)
     name = os.path.normpath(name)
     audit_path = path_auditor(root)
     if name != rootsep and name.startswith(rootsep):
         name = name[len(rootsep):]
         audit_path(name)
         return pconvert(name)
     elif name == root:
         return ''
     else:
         # Determine whether `name' is in the hierarchy at or beneath `root',
         # by iterating name=dirname(name) until that causes no change (can't
         # check name == '/', because that doesn't work on windows).  For each
         # `name', compare dev/inode numbers.  If they match, the list `rel'
         # holds the reversed list of components making up the relative file
         # name we want.
         root_st = os.stat(root)
         rel = []
         while True:
             try:
                 name_st = os.stat(name)
             except OSError:
                 break
             if samestat(name_st, root_st):
                 if not rel:
                     # name was actually the same as root (maybe a symlink)
                     return ''
                 rel.reverse()
                 name = os.path.join(*rel)
                 audit_path(name)
                 return pconvert(name)
             dirname, basename = os.path.split(name)
             rel.append(basename)
             if dirname == name:
                 break
             name = dirname
 
         raise Abort('%s not under root' % myname)
 
 _hgexecutable = None
 
 def main_is_frozen():
     """return True if we are a frozen executable.
 
     The code supports py2exe (most common, Windows only) and tools/freeze
     (portable, not much used).
     """
     return (hasattr(sys, "frozen") or # new py2exe
             hasattr(sys, "importers") or # old py2exe
             imp.is_frozen("__main__")) # tools/freeze
 
 def hgexecutable():
     """return location of the 'hg' executable.
 
     Defaults to $HG or 'hg' in the search path.
     """
     if _hgexecutable is None:
         hg = os.environ.get('HG')
         if hg:
             set_hgexecutable(hg)
         elif main_is_frozen():
             set_hgexecutable(sys.executable)
         else:
             set_hgexecutable(find_exe('hg') or 'hg')
     return _hgexecutable
 
 def set_hgexecutable(path):
     """set location of the 'hg' executable"""
     global _hgexecutable
     _hgexecutable = path
 
 def system(cmd, environ={}, cwd=None, onerr=None, errprefix=None):
     '''enhanced shell command execution.
     run with environment maybe modified, maybe in different dir.
 
     if command fails and onerr is None, return status.  if ui object,
     print error message and return status, else raise onerr object as
     exception.'''
     def py2shell(val):
         'convert python object into string that is useful to shell'
         if val is None or val is False:
             return '0'
         if val is True:
             return '1'
         return str(val)
     oldenv = {}
     for k in environ:
         oldenv[k] = os.environ.get(k)
     if cwd is not None:
         oldcwd = os.getcwd()
     origcmd = cmd
     if os.name == 'nt':
         cmd = '"%s"' % cmd
     try:
         for k, v in environ.iteritems():
             os.environ[k] = py2shell(v)
         os.environ['HG'] = hgexecutable()
         if cwd is not None and oldcwd != cwd:
             os.chdir(cwd)
         rc = os.system(cmd)
         if sys.platform == 'OpenVMS' and rc & 1:
             rc = 0
         if rc and onerr:
             errmsg = '%s %s' % (os.path.basename(origcmd.split(None, 1)[0]),
                                 explain_exit(rc)[0])
             if errprefix:
                 errmsg = '%s: %s' % (errprefix, errmsg)
             try:
                 onerr.warn(errmsg + '\n')
             except AttributeError:
                 raise onerr(errmsg)
         return rc
     finally:
         for k, v in oldenv.iteritems():
             if v is None:
                 del os.environ[k]
             else:
                 os.environ[k] = v
         if cwd is not None and oldcwd != cwd:
             os.chdir(oldcwd)
 
 def checksignature(func):
     '''wrap a function with code to check for calling errors'''
     def check(*args, **kwargs):
         try:
             return func(*args, **kwargs)
         except TypeError:
             if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
                 raise error.SignatureError
             raise
 
     return check
 
 # os.path.lexists is not available on python2.3
 def lexists(filename):
     "test whether a file with this name exists. does not follow symlinks"
     try:
         os.lstat(filename)
     except:
         return False
     return True
 
 def rename(src, dst):
     """forcibly rename a file"""
     try:
         os.rename(src, dst)
     except OSError, err: # FIXME: check err (EEXIST ?)
 
         # On windows, rename to existing file is not allowed, so we
         # must delete destination first. But if a file is open, unlink
         # schedules it for delete but does not delete it. Rename
         # happens immediately even for open files, so we rename
         # destination to a temporary name, then delete that. Then
         # rename is safe to do.
         # The temporary name is chosen at random to avoid the situation
         # where a file is left lying around from a previous aborted run.
         # The usual race condition this introduces can't be avoided as
         # we need the name to rename into, and not the file itself. Due
         # to the nature of the operation however, any races will at worst
         # lead to the rename failing and the current operation aborting.
 
         def tempname(prefix):
             for tries in xrange(10):
                 temp = '%s-%08x' % (prefix, random.randint(0, 0xffffffff))
                 if not os.path.exists(temp):
                     return temp
             raise IOError, (errno.EEXIST, "No usable temporary filename found")
 
         temp = tempname(dst)
         os.rename(dst, temp)
         os.unlink(temp)
         os.rename(src, dst)
 
 def unlink(f):
     """unlink and remove the directory if it is empty"""
     os.unlink(f)
     # try removing directories that might now be empty
     try:
         os.removedirs(os.path.dirname(f))
     except OSError:
         pass
 
 def copyfile(src, dest):
     "copy a file, preserving mode and atime/mtime"
     if os.path.islink(src):
         try:
             os.unlink(dest)
         except:
             pass
         os.symlink(os.readlink(src), dest)
     else:
         try:
             shutil.copyfile(src, dest)
             shutil.copystat(src, dest)
         except shutil.Error, inst:
             raise Abort(str(inst))
 
 def copyfiles(src, dst, hardlink=None):
     """Copy a directory tree using hardlinks if possible"""
 
     if hardlink is None:
         hardlink = (os.stat(src).st_dev ==
                     os.stat(os.path.dirname(dst)).st_dev)
 
     if os.path.isdir(src):
         os.mkdir(dst)
         for name, kind in osutil.listdir(src):
             srcname = os.path.join(src, name)
             dstname = os.path.join(dst, name)
             copyfiles(srcname, dstname, hardlink)
     else:
         if hardlink:
             try:
                 os_link(src, dst)
             except (IOError, OSError):
                 hardlink = False
                 shutil.copy(src, dst)
         else:
             shutil.copy(src, dst)
 
 class path_auditor(object):
     '''ensure that a filesystem path contains no banned components.
     the following properties of a path are checked:
 
     - under top-level .hg
     - starts at the root of a windows drive
     - contains ".."
     - traverses a symlink (e.g. a/symlink_here/b)
     - inside a nested repository'''
 
     def __init__(self, root):
         self.audited = set()
         self.auditeddir = set()
         self.root = root
 
     def __call__(self, path):
         if path in self.audited:
             return
         normpath = os.path.normcase(path)
         parts = splitpath(normpath)
         if (os.path.splitdrive(path)[0]
             or parts[0].lower() in ('.hg', '.hg.', '')
             or os.pardir in parts):
             raise Abort(_("path contains illegal component: %s") % path)
         if '.hg' in path.lower():
             lparts = [p.lower() for p in parts]
             for p in '.hg', '.hg.':
                 if p in lparts[1:]:
                     pos = lparts.index(p)
                     base = os.path.join(*parts[:pos])
                     raise Abort(_('path %r is inside repo %r') % (path, base))
         def check(prefix):
             curpath = os.path.join(self.root, prefix)
             try:
                 st = os.lstat(curpath)
             except OSError, err:
                 # EINVAL can be raised as invalid path syntax under win32.
                 # They must be ignored for patterns can be checked too.
                 if err.errno not in (errno.ENOENT, errno.ENOTDIR, errno.EINVAL):
                     raise
             else:
                 if stat.S_ISLNK(st.st_mode):
                     raise Abort(_('path %r traverses symbolic link %r') %
                                 (path, prefix))
                 elif (stat.S_ISDIR(st.st_mode) and
                       os.path.isdir(os.path.join(curpath, '.hg'))):
                     raise Abort(_('path %r is inside repo %r') %
                                 (path, prefix))
         parts.pop()
         prefixes = []
         while parts:
             prefix = os.sep.join(parts)
             if prefix in self.auditeddir:
                 break
             check(prefix)
             prefixes.append(prefix)
             parts.pop()
 
         self.audited.add(path)
         # only add prefixes to the cache after checking everything: we don't
         # want to add "foo/bar/baz" before checking if there's a "foo/.hg"
         self.auditeddir.update(prefixes)
 
 def nlinks(pathname):
     """Return number of hardlinks for the given file."""
     return os.lstat(pathname).st_nlink
 
 if hasattr(os, 'link'):
     os_link = os.link
 else:
     def os_link(src, dst):
         raise OSError(0, _("Hardlinks not supported"))
 
 def lookup_reg(key, name=None, scope=None):
     return None
 
 if os.name == 'nt':
     from windows import *
 else:
     from posix import *
 
 def makelock(info, pathname):
     try:
         return os.symlink(info, pathname)
     except OSError, why:
         if why.errno == errno.EEXIST:
             raise
     except AttributeError: # no symlink in os
         pass
 
     ld = os.open(pathname, os.O_CREAT | os.O_WRONLY | os.O_EXCL)
     os.write(ld, info)
     os.close(ld)
 
 def readlock(pathname):
     try:
         return os.readlink(pathname)
     except OSError, why:
         if why.errno not in (errno.EINVAL, errno.ENOSYS):
             raise
     except AttributeError: # no symlink in os
         pass
     return posixfile(pathname).read()
 
 def fstat(fp):
     '''stat file object that may not have fileno method.'''
     try:
         return os.fstat(fp.fileno())
     except AttributeError:
         return os.stat(fp.name)
 
 # File system features
 
 def checkcase(path):
     """
     Check whether the given path is on a case-sensitive filesystem
 
     Requires a path (like /foo/.hg) ending with a foldable final
     directory component.
     """
     s1 = os.stat(path)
     d, b = os.path.split(path)
     p2 = os.path.join(d, b.upper())
     if path == p2:
         p2 = os.path.join(d, b.lower())
     try:
         s2 = os.stat(p2)
         if s2 == s1:
             return False
         return True
     except:
         return True
 
 _fspathcache = {}
 def fspath(name, root):
     '''Get name in the case stored in the filesystem
 
     The name is either relative to root, or it is an absolute path starting
     with root. Note that this function is unnecessary, and should not be
     called, for case-sensitive filesystems (simply because it's expensive).
     '''
     # If name is absolute, make it relative
     if name.lower().startswith(root.lower()):
         l = len(root)
         if name[l] == os.sep or name[l] == os.altsep:
             l = l + 1
         name = name[l:]
 
     if not os.path.exists(os.path.join(root, name)):
         return None
 
     seps = os.sep
     if os.altsep:
         seps = seps + os.altsep
     # Protect backslashes. This gets silly very quickly.
     seps.replace('\\','\\\\')
     pattern = re.compile(r'([^%s]+)|([%s]+)' % (seps, seps))
     dir = os.path.normcase(os.path.normpath(root))
     result = []
     for part, sep in pattern.findall(name):
         if sep:
             result.append(sep)
             continue
 
         if dir not in _fspathcache:
             _fspathcache[dir] = os.listdir(dir)
         contents = _fspathcache[dir]
 
         lpart = part.lower()
         lenp = len(part)
         for n in contents:
             if lenp == len(n) and n.lower() == lpart:
                 result.append(n)
                 break
         else:
             # Cannot happen, as the file exists!
             result.append(part)
         dir = os.path.join(dir, lpart)
 
     return ''.join(result)
 
 def checkexec(path):
     """
     Check whether the given path is on a filesystem with UNIX-like exec flags
 
     Requires a directory (like /foo/.hg)
     """
 
     # VFAT on some Linux versions can flip mode but it doesn't persist
     # a FS remount. Frequently we can detect it if files are created
     # with exec bit on.
 
     try:
         EXECFLAGS = stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH
         fh, fn = tempfile.mkstemp("", "", path)
         try:
             os.close(fh)
             m = os.stat(fn).st_mode & 0777
             new_file_has_exec = m & EXECFLAGS
             os.chmod(fn, m ^ EXECFLAGS)
             exec_flags_cannot_flip = ((os.stat(fn).st_mode & 0777) == m)
         finally:
             os.unlink(fn)
     except (IOError, OSError):
         # we don't care, the user probably won't be able to commit anyway
         return False
     return not (new_file_has_exec or exec_flags_cannot_flip)
 
 def checklink(path):
     """check whether the given path is on a symlink-capable filesystem"""
     # mktemp is not racy because symlink creation will fail if the
     # file already exists
     name = tempfile.mktemp(dir=path)
     try:
         os.symlink(".", name)
         os.unlink(name)
         return True
     except (OSError, AttributeError):
         return False
 
 def needbinarypatch():
     """return True if patches should be applied in binary mode by default."""
     return os.name == 'nt'
 
 def endswithsep(path):
     '''Check path ends with os.sep or os.altsep.'''
     return path.endswith(os.sep) or os.altsep and path.endswith(os.altsep)
 
 def splitpath(path):
     '''Split path by os.sep.
     Note that this function does not use os.altsep because this is
     an alternative of simple "xxx.split(os.sep)".
     It is recommended to use os.path.normpath() before using this
     function if need.'''
     return path.split(os.sep)
 
 def gui():
     '''Are we running in a GUI?'''
     return os.name == "nt" or os.name == "mac" or os.environ.get("DISPLAY")
 
 def mktempcopy(name, emptyok=False, createmode=None):
     """Create a temporary file with the same contents from name
 
     The permission bits are copied from the original file.
 
     If the temporary file is going to be truncated immediately, you
     can use emptyok=True as an optimization.
 
     Returns the name of the temporary file.
     """
     d, fn = os.path.split(name)
     fd, temp = tempfile.mkstemp(prefix='.%s-' % fn, dir=d)
     os.close(fd)
     # Temporary files are created with mode 0600, which is usually not
     # what we want.  If the original file already exists, just copy
     # its mode.  Otherwise, manually obey umask.
     try:
         st_mode = os.lstat(name).st_mode & 0777
     except OSError, inst:
         if inst.errno != errno.ENOENT:
             raise
         st_mode = createmode
         if st_mode is None:
             st_mode = ~umask
         st_mode &= 0666
     os.chmod(temp, st_mode)
     if emptyok:
         return temp
     try:
         try:
             ifp = posixfile(name, "rb")
         except IOError, inst:
             if inst.errno == errno.ENOENT:
                 return temp
             if not getattr(inst, 'filename', None):
                 inst.filename = name
             raise
         ofp = posixfile(temp, "wb")
         for chunk in filechunkiter(ifp):
             ofp.write(chunk)
         ifp.close()
         ofp.close()
     except:
         try: os.unlink(temp)
         except: pass
         raise
     return temp
 
 class atomictempfile(object):
     """file-like object that atomically updates a file
 
     All writes will be redirected to a temporary copy of the original
     file.  When rename is called, the copy is renamed to the original
     name, making the changes visible.
     """
     def __init__(self, name, mode, createmode):
         self.__name = name
         self._fp = None
         self.temp = mktempcopy(name, emptyok=('w' in mode),
                                createmode=createmode)
         self._fp = posixfile(self.temp, mode)
 
     def __getattr__(self, name):
         return getattr(self._fp, name)
 
     def rename(self):
         if not self._fp.closed:
             self._fp.close()
             rename(self.temp, localpath(self.__name))
 
     def __del__(self):
         if not self._fp:
             return
         if not self._fp.closed:
             try:
                 os.unlink(self.temp)
             except: pass
             self._fp.close()
 
 def makedirs(name, mode=None):
     """recursive directory creation with parent mode inheritance"""
     try:
         os.mkdir(name)
         if mode is not None:
             os.chmod(name, mode)
         return
     except OSError, err:
         if err.errno == errno.EEXIST:
             return
         if err.errno != errno.ENOENT:
             raise
     parent = os.path.abspath(os.path.dirname(name))
     makedirs(parent, mode)
     makedirs(name, mode)
 
 class opener(object):
     """Open files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     """
     def __init__(self, base, audit=True):
         self.base = base
         if audit:
             self.audit_path = path_auditor(base)
         else:
             self.audit_path = always
         self.createmode = None
 
     @propertycache
     def _can_symlink(self):
         return checklink(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None:
             return
         os.chmod(name, self.createmode & 0666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False):
         self.audit_path(path)
         f = os.path.join(self.base, path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ("r", "rb"):
             try:
                 nlink = nlinks(f)
             except OSError:
                 nlink = 0
                 d = os.path.dirname(f)
                 if not os.path.isdir(d):
                     makedirs(d, self.createmode)
             if atomictemp:
                 return atomictempfile(f, mode, self.createmode)
             if nlink > 1:
                 rename(mktempcopy(f), f)
         fp = posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.audit_path(dst)
         linkname = os.path.join(self.base, dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         dirname = os.path.dirname(linkname)
         if not os.path.exists(dirname):
             makedirs(dirname, self.createmode)
 
         if self._can_symlink:
             try:
                 os.symlink(src, linkname)
             except OSError, err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             f = self(dst, "w")
             f.write(src)
             f.close()
             self._fixfilemode(dst)
 
 class chunkbuffer(object):
     """Allow arbitrary sized chunks of data to be efficiently read from an
     iterator over chunks of arbitrary size."""
 
     def __init__(self, in_iter):
         """in_iter is the iterator that's iterating over the input chunks.
         targetsize is how big a buffer to try to maintain."""
         self.iter = iter(in_iter)
         self.buf = ''
         self.targetsize = 2**16
 
     def read(self, l):
         """Read L bytes of data from the iterator of chunks of data.
         Returns less than L bytes if the iterator runs dry."""
         if l > len(self.buf) and self.iter:
             # Clamp to a multiple of self.targetsize
             targetsize = max(l, self.targetsize)
             collector = cStringIO.StringIO()
             collector.write(self.buf)
             collected = len(self.buf)
             for chunk in self.iter:
                 collector.write(chunk)
                 collected += len(chunk)
                 if collected >= targetsize:
                     break
             if collected < targetsize:
                 self.iter = False
             self.buf = collector.getvalue()
         if len(self.buf) == l:
             s, self.buf = str(self.buf), ''
         else:
             s, self.buf = self.buf[:l], buffer(self.buf, l)
         return s
 
 def filechunkiter(f, size=65536, limit=None):
     """Create a generator that produces the data in the file size
     (default 65536) bytes at a time, up to optional limit (default is
     to read all data).  Chunks may be less than size bytes if the
     chunk is the last chunk in the file, or the file is a socket or
     some other type of file that sometimes reads less data than is
     requested."""
     assert size >= 0
     assert limit is None or limit >= 0
     while True:
         if limit is None: nbytes = size
         else: nbytes = min(limit, size)
         s = nbytes and f.read(nbytes)
         if not s: break
         if limit: limit -= len(s)
         yield s
 
 def makedate():
     lt = time.localtime()
     if lt[8] == 1 and time.daylight:
         tz = time.altzone
     else:
         tz = time.timezone
     return time.mktime(lt), tz
 
 def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'):
     """represent a (unixtime, offset) tuple as a localized time.
     unixtime is seconds since the epoch, and offset is the time zone's
     number of seconds away from UTC. if timezone is false, do not
     append time zone to string."""
     t, tz = date or makedate()
     if "%1" in format or "%2" in format:
         sign = (tz > 0) and "-" or "+"
         minutes = abs(tz) // 60
         format = format.replace("%1", "%c%02d" % (sign, minutes // 60))
         format = format.replace("%2", "%02d" % (minutes % 60))
     s = time.strftime(format, time.gmtime(float(t) - tz))
     return s
 
 def shortdate(date=None):
     """turn (timestamp, tzoff) tuple into iso 8631 date."""
     return datestr(date, format='%Y-%m-%d')
 
 def strdate(string, format, defaults=[]):
     """parse a localized time string and return a (unixtime, offset) tuple.
     if the string cannot be parsed, ValueError is raised."""
     def timezone(string):
         tz = string.split()[-1]
         if tz[0] in "+-" and len(tz) == 5 and tz[1:].isdigit():
             sign = (tz[0] == "+") and 1 or -1
             hours = int(tz[1:3])
             minutes = int(tz[3:5])
             return -sign * (hours * 60 + minutes) * 60
         if tz == "GMT" or tz == "UTC":
             return 0
         return None
 
     # NOTE: unixtime = localunixtime + offset
     offset, date = timezone(string), string
     if offset != None:
         date = " ".join(string.split()[:-1])
 
     # add missing elements from defaults
     for part in defaults:
         found = [True for p in part if ("%"+p) in format]
         if not found:
             date += "@" + defaults[part]
             format += "@%" + part[0]
 
     timetuple = time.strptime(date, format)
     localunixtime = int(calendar.timegm(timetuple))
     if offset is None:
         # local timezone
         unixtime = int(time.mktime(timetuple))
         offset = unixtime - localunixtime
     else:
         unixtime = localunixtime + offset
     return unixtime, offset
 
 def parsedate(date, formats=None, defaults=None):
     """parse a localized date/time string and return a (unixtime, offset) tuple.
 
     The date may be a "unixtime offset" string or in one of the specified
     formats. If the date already is a (unixtime, offset) tuple, it is returned.
     """
     if not date:
         return 0, 0
     if isinstance(date, tuple) and len(date) == 2:
         return date
     if not formats:
         formats = defaultdateformats
     date = date.strip()
     try:
         when, offset = map(int, date.split(' '))
     except ValueError:
         # fill out defaults
         if not defaults:
             defaults = {}
         now = makedate()
         for part in "d mb yY HI M S".split():
             if part not in defaults:
                 if part[0] in "HMS":
                     defaults[part] = "00"
                 else:
                     defaults[part] = datestr(now, "%" + part[0])
 
         for format in formats:
             try:
                 when, offset = strdate(date, format, defaults)
             except (ValueError, OverflowError):
                 pass
             else:
                 break
         else:
             raise Abort(_('invalid date: %r ') % date)
     # validate explicit (probably user-specified) date and
     # time zone offset. values must fit in signed 32 bits for
     # current 32-bit linux runtimes. timezones go from UTC-12
     # to UTC+14
     if abs(when) > 0x7fffffff:
         raise Abort(_('date exceeds 32 bits: %d') % when)
     if offset < -50400 or offset > 43200:
         raise Abort(_('impossible time zone offset: %d') % offset)
     return when, offset
 
 def matchdate(date):
     """Return a function that matches a given date match specifier
 
     Formats include:
 
     '{date}' match a given date to the accuracy provided
 
     '<{date}' on or before a given date
 
     '>{date}' on or after a given date
 
     """
 
     def lower(date):
         d = dict(mb="1", d="1")
         return parsedate(date, extendeddateformats, d)[0]
 
     def upper(date):
         d = dict(mb="12", HI="23", M="59", S="59")
         for days in "31 30 29".split():
             try:
                 d["d"] = days
                 return parsedate(date, extendeddateformats, d)[0]
             except:
                 pass
         d["d"] = "28"
         return parsedate(date, extendeddateformats, d)[0]
 
     date = date.strip()
     if date[0] == "<":
         when = upper(date[1:])
         return lambda x: x <= when
     elif date[0] == ">":
         when = lower(date[1:])
         return lambda x: x >= when
     elif date[0] == "-":
         try:
             days = int(date[1:])
         except ValueError:
             raise Abort(_("invalid day spec: %s") % date[1:])
         when = makedate()[0] - days * 3600 * 24
         return lambda x: x >= when
     elif " to " in date:
         a, b = date.split(" to ")
         start, stop = lower(a), upper(b)
         return lambda x: x >= start and x <= stop
     else:
         start, stop = lower(date), upper(date)
         return lambda x: x >= start and x <= stop
 
 def shortuser(user):
     """Return a short representation of a user name or email address."""
     f = user.find('@')
     if f >= 0:
         user = user[:f]
     f = user.find('<')
     if f >= 0:
         user = user[f+1:]
     f = user.find(' ')
     if f >= 0:
         user = user[:f]
     f = user.find('.')
     if f >= 0:
         user = user[:f]
     return user
 
 def email(author):
     '''get email of author.'''
     r = author.find('>')
     if r == -1: r = None
     return author[author.find('<')+1:r]
 
 def ellipsis(text, maxlength=400):
     """Trim string to at most maxlength (default: 400) characters."""
     if len(text) <= maxlength:
         return text
     else:
         return "%s..." % (text[:maxlength-3])
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, recursively.'''
     def errhandler(err):
         if err.filename == path:
             raise err
     if followsym and hasattr(os.path, 'samestat'):
         def _add_dir_if_not_there(dirlst, dirname):
             match = False
             samestat = os.path.samestat
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         _add_dir_if_not_there(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if _add_dir_if_not_there(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 _rcpath = None
 
 def os_rcpath():
     '''return default os-specific hgrc search path'''
     path = system_rcpath()
     path.extend(user_rcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p: continue
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = os_rcpath()
     return _rcpath
 
 def bytecount(nbytes):
     '''return byte count formatted as readable string, with units'''
 
     units = (
         (100, 1<<30, _('%.0f GB')),
         (10, 1<<30, _('%.1f GB')),
         (1, 1<<30, _('%.2f GB')),
         (100, 1<<20, _('%.0f MB')),
         (10, 1<<20, _('%.1f MB')),
         (1, 1<<20, _('%.2f MB')),
         (100, 1<<10, _('%.0f KB')),
         (10, 1<<10, _('%.1f KB')),
         (1, 1<<10, _('%.2f KB')),
         (1, 1, _('%.0f bytes')),
         )
 
     for multiplier, divisor, format in units:
         if nbytes >= divisor * multiplier:
             return format % (nbytes / float(divisor))
     return units[-1][2] % nbytes
 
 def drop_scheme(scheme, path):
     sc = scheme + ':'
     if path.startswith(sc):
         path = path[len(sc):]
         if path.startswith('//'):
             path = path[2:]
     return path
 
 def uirepr(s):
     # Avoid double backslash in Windows path repr()
     return repr(s).replace('\\\\', '\\')
 
 def termwidth():
     if 'COLUMNS' in os.environ:
         try:
             return int(os.environ['COLUMNS'])
         except ValueError:
             pass
     try:
         import termios, array, fcntl
         for dev in (sys.stdout, sys.stdin):
             try:
                 try:
                     fd = dev.fileno()
                 except AttributeError:
                     continue
                 if not os.isatty(fd):
                     continue
                 arri = fcntl.ioctl(fd, termios.TIOCGWINSZ, '\0' * 8)
                 return array.array('h', arri)[1]
             except ValueError:
                 pass
     except ImportError:
         pass
     return 80
 
 def wrap(line, hangindent, width=None):
     if width is None:
         width = termwidth() - 2
     if width <= hangindent:
         # adjust for weird terminal size
         width = max(78, hangindent + 1)
     padding = '\n' + ' ' * hangindent
-    return padding.join(textwrap.wrap(line, width=width - hangindent))
+    # To avoid corrupting multi-byte characters in line, we must wrap
+    # a Unicode string instead of a bytestring.
+    u = line.decode(encoding.encoding)
+    w = padding.join(textwrap.wrap(u, width=width - hangindent))
+    return w.encode(encoding.encoding)
 
 def iterlines(iterator):
     for chunk in iterator:
         for line in chunk.splitlines():
             yield line

tests/test-push-warn

@@ -1,126 +1,143 b''
 #!/bin/sh
 
 mkdir a
 cd a
 hg init
 echo foo > t1
 hg add t1
 hg commit -m "1" -d "1000000 0"
 
 cd ..
 hg clone a b
 
 cd a
 echo foo > t2
 hg add t2
 hg commit -m "2" -d "1000000 0"
 
 cd ../b
 echo foo > t3
 hg add t3
 hg commit -m "3" -d "1000000 0"
 
 hg push ../a
 hg pull ../a
 hg push ../a
 hg merge
 hg commit -m "4" -d "1000000 0"
 hg push ../a
 cd ..
 
 hg init c
 cd c
 for i in 0 1 2; do
     echo $i >> foo
     hg ci -Am $i -d "1000000 0"
 done
 cd ..
 
 hg clone c d
 cd d
 for i in 0 1; do
     hg co -C $i
     echo d-$i >> foo
     hg ci -m d-$i -d "1000000 0"
 done
 
 HGMERGE=true hg merge 3
 hg ci -m c-d -d "1000000 0"
 
 hg push ../c; echo $?
 hg push -r 2 ../c; echo $?
 hg push -r 3 ../c; echo $?
 hg push -r 3 -r 4 ../c; echo $?
 hg push -f -r 3 -r 4 ../c; echo $?
 hg push -r 5 ../c; echo $?
 
 # issue 450
 hg init ../e
 hg push -r 0 ../e ; echo $?
 hg push -r 1 ../e ; echo $?
 
 cd ..
 
 # issue 736
 echo % issue 736
 hg init f
 cd f
 hg -q branch a
 echo 0 > foo
 hg -q ci -d "1000000 0" -Am 0
 echo 1 > foo
 hg -q ci -d "1000000 0" -m 1
 hg -q up 0
 echo 2 > foo
 hg -q ci -d "1000000 0" -m 2
 hg -q up 0
 hg -q branch b
 echo 3 > foo
 hg -q ci -d "1000000 0" -m 3
 cd ..
 
 hg -q clone f g
 cd g
 
 echo % push on existing branch and new branch
 hg -q up 1
 echo 4 > foo
 hg -q ci -d "1000000 0" -m 4
 hg -q up 0
 echo 5 > foo
 hg -q branch c
 hg -q ci -d "1000000 0" -m 5
 hg push -r 4 -r 5 ../f; echo $?
 
 echo % fail on multiple head push
 hg -q up 1
 echo 6 > foo
 hg -q ci -d "1000000 0" -m 6
 hg push -r 4 -r 6 ../f; echo $?
 
 echo % push replacement head on existing branches
 hg -q up 3
 echo 7 > foo
 hg -q ci -d "1000000 0" -m 7
 hg push -r 6 -r 7 ../f; echo $?
 
 echo % merge of branch a to other branch b followed by unrelated push on branch a
 hg -q up 6
 HGMERGE=true hg -q merge 7
 hg -q ci -d "1000000 0" -m 8
 hg -q up 7
 echo 9 > foo
 hg -q ci -d "1000000 0" -m 9
 hg push -r 8 ../f; echo $?
 hg push -r 9 ../f; echo $?
 
 echo % cheating the counting algorithm
 hg -q up 8
 HGMERGE=true hg -q merge 2
 hg -q ci -d "1000000 0" -m 10
 hg -q up 1
 echo 11 > foo
 hg -q ci -d "1000000 0" -m 11
 hg push -r 10 -r 11 ../f; echo $?
 
+echo % checking prepush logic does not allow silently pushing multiple new heads
+cd ..
+hg init g
+echo init > g/init
+hg -R g ci -Am init
+echo a > g/a
+hg -R g ci -Am a
+hg clone g h
+hg -R g up 0
+echo b > g/b
+hg -R g ci -Am b
+hg -R h up 0
+echo c > h/c
+hg -R h ci -Am c
+hg -R h push g
+echo
+
 exit 0

tests/test-push-warn.out

@@ -1,126 +1,143 b''
 updating working directory
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 pushing to ../a
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 pulling from ../a
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files (+1 heads)
 (run 'hg heads' to see heads, 'hg merge' to merge)
 pushing to ../a
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 pushing to ../a
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 2 changesets with 1 changes to 1 files
 adding foo
 updating working directory
 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
 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)
 pushing to ../c
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 1
 pushing to ../c
 searching for changes
 no changes found
 0
 pushing to ../c
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 1
 pushing to ../c
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 1
 pushing to ../c
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 2 changesets with 2 changes to 1 files (+2 heads)
 0
 pushing to ../c
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files (-1 heads)
 0
 pushing to ../e
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 0
 pushing to ../e
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files
 0
 % issue 736
 % push on existing branch and new branch
 pushing to ../f
 searching for changes
 abort: push creates new remote branch 'c'!
 (did you forget to merge? use push -f to force)
 1
 % fail on multiple head push
 pushing to ../f
 searching for changes
 abort: push creates new remote heads!
 (did you forget to merge? use push -f to force)
 1
 % push replacement head on existing branches
 pushing to ../f
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 2 changesets with 2 changes to 1 files
 0
 % merge of branch a to other branch b followed by unrelated push on branch a
 pushing to ../f
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files (-1 heads)
 0
 pushing to ../f
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 1 changesets with 1 changes to 1 files (+1 heads)
 0
 % cheating the counting algorithm
 pushing to ../f
 searching for changes
 adding changesets
 adding manifests
 adding file changes
 added 2 changesets with 2 changes to 1 files
 0
+% checking prepush logic does not allow silently pushing multiple new heads
+abort: repository g already exists!
+adding init
+adding a
+updating working directory
+3 files updated, 0 files merged, 0 files removed, 0 files unresolved
+1 files updated, 0 files merged, 2 files removed, 0 files unresolved
+adding b
+created new head
+1 files updated, 0 files merged, 2 files removed, 0 files unresolved
+adding c
+created new head
+pushing to g
+searching for changes
+abort: push creates new remote heads!
+(did you forget to merge? use push -f to force)
+