merge with crew-stable

hgext/hbisect.py

@@ -1,312 +1,312 b''
 # bisect extension for mercurial
 #
 # Copyright 2005, 2006 Benoit Boissinot <[e-mail]>
 # Inspired by git bisect, extension skeleton taken from mq.py.
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from mercurial.i18n import _
 from mercurial import hg, util, commands, cmdutil
 import os, sys, sets
 
 versionstr = "0.0.3"
 
 def lookup_rev(ui, repo, rev=None):
     """returns rev or the checked-out revision if rev is None"""
     if not rev is None:
         return repo.lookup(rev)
     parents = [p for p in repo.dirstate.parents() if p != hg.nullid]
     if len(parents) != 1:
         raise util.Abort(_("unexpected number of parents, "
                            "please commit or revert"))
     return parents.pop()
 
 def check_clean(ui, repo):
     modified, added, removed, deleted, unknown = repo.status()[:5]
     if modified or added or removed:
         ui.warn("Repository is not clean, please commit or revert\n")
         sys.exit(1)
 
 class bisect(object):
     """dichotomic search in the DAG of changesets"""
     def __init__(self, ui, repo):
         self.repo = repo
         self.path = repo.join("bisect")
         self.opener = util.opener(self.path)
         self.ui = ui
         self.goodrevs = []
         self.badrev = None
         self.good_dirty = 0
         self.bad_dirty = 0
         self.good_path = "good"
         self.bad_path = "bad"
 
         if os.path.exists(os.path.join(self.path, self.good_path)):
             self.goodrevs = self.opener(self.good_path).read().splitlines()
             self.goodrevs = [hg.bin(x) for x in self.goodrevs]
         if os.path.exists(os.path.join(self.path, self.bad_path)):
             r = self.opener(self.bad_path).read().splitlines()
             if r:
                 self.badrev = hg.bin(r.pop(0))
 
     def write(self):
         if not os.path.isdir(self.path):
             return
         f = self.opener(self.good_path, "w")
         f.write("\n".join([hg.hex(r) for r in  self.goodrevs]))
         if len(self.goodrevs) > 0:
             f.write("\n")
         f = self.opener(self.bad_path, "w")
         if self.badrev:
             f.write(hg.hex(self.badrev) + "\n")
 
     def init(self):
         """start a new bisection"""
         if os.path.isdir(self.path):
             raise util.Abort(_("bisect directory already exists\n"))
         os.mkdir(self.path)
         check_clean(self.ui, self.repo)
         return 0
 
     def reset(self):
         """finish a bisection"""
         if os.path.isdir(self.path):
             sl = [os.path.join(self.path, p)
                   for p in [self.bad_path, self.good_path]]
             for s in sl:
                 if os.path.exists(s):
                     os.unlink(s)
             os.rmdir(self.path)
         # Not sure about this
         #self.ui.write("Going back to tip\n")
         #self.repo.update(self.repo.changelog.tip())
         return 1
 
     def num_ancestors(self, head=None, stop=None):
         """
         returns a dict with the mapping:
         node -> number of ancestors (self included)
         for all nodes who are ancestor of head and
         not in stop.
         """
         if head is None:
             head = self.badrev
         return self.__ancestors_and_nb_ancestors(head, stop)[1]
 
     def ancestors(self, head=None, stop=None):
         """
         returns the set of the ancestors of head (self included)
         who are not in stop.
         """
         if head is None:
             head = self.badrev
         return self.__ancestors_and_nb_ancestors(head, stop)[0]
 
     def __ancestors_and_nb_ancestors(self, head, stop=None):
         """
         if stop is None then ancestors of goodrevs are used as
         lower limit.
 
         returns (anc, n_child) where anc is the set of the ancestors of head
         and n_child is a dictionary with the following mapping:
         node -> number of ancestors (self included)
         """
         cl = self.repo.changelog
         if not stop:
             stop = sets.Set([])
             for i in xrange(len(self.goodrevs)-1, -1, -1):
                 g = self.goodrevs[i]
                 if g in stop:
                     continue
                 stop.update(cl.reachable(g))
         def num_children(a):
             """
             returns a dictionnary with the following mapping
             node -> [number of children, empty set]
             """
             d = {a: [0, sets.Set([])]}
             for i in xrange(cl.rev(a)+1):
                 n = cl.node(i)
                 if not d.has_key(n):
                     d[n] = [0, sets.Set([])]
                 parents = [p for p in cl.parents(n) if p != hg.nullid]
                 for p in parents:
                     d[p][0] += 1
             return d
 
         if head in stop:
-            raise util.Abort(_("Unconsistent state, %s:%s is good and bad")
+            raise util.Abort(_("Inconsistent state, %s:%s is good and bad")
                              % (cl.rev(head), hg.short(head)))
         n_child = num_children(head)
         for i in xrange(cl.rev(head)+1):
             n = cl.node(i)
             parents = [p for p in cl.parents(n) if p != hg.nullid]
             for p in parents:
                 n_child[p][0] -= 1
                 if not n in stop:
                     n_child[n][1].union_update(n_child[p][1])
                 if n_child[p][0] == 0:
                     n_child[p] = len(n_child[p][1])
             if not n in stop:
                 n_child[n][1].add(n)
             if n_child[n][0] == 0:
                 if n == head:
                     anc = n_child[n][1]
                 n_child[n] = len(n_child[n][1])
         return anc, n_child
 
     def next(self):
         if not self.badrev:
             raise util.Abort(_("You should give at least one bad revision"))
         if not self.goodrevs:
             self.ui.warn(_("No good revision given\n"))
             self.ui.warn(_("Marking the first revision as good\n"))
         ancestors, num_ancestors = self.__ancestors_and_nb_ancestors(
                                     self.badrev)
         tot = len(ancestors)
         if tot == 1:
             if ancestors.pop() != self.badrev:
                 raise util.Abort(_("Could not find the first bad revision"))
             self.ui.write(_("The first bad revision is:\n"))
             displayer = cmdutil.show_changeset(self.ui, self.repo, {})
             displayer.show(changenode=self.badrev)
             return None
         best_rev = None
         best_len = -1
         for n in ancestors:
             l = num_ancestors[n]
             l = min(l, tot - l)
             if l > best_len:
                 best_len = l
                 best_rev = n
         assert best_rev is not None
         nb_tests = 0
         q, r = divmod(tot, 2)
         while q:
             nb_tests += 1
             q, r = divmod(q, 2)
         msg = _("Testing changeset %s:%s (%s changesets remaining, "
                 "~%s tests)\n") % (self.repo.changelog.rev(best_rev),
                                    hg.short(best_rev), tot, nb_tests)
         self.ui.write(msg)
         return best_rev
 
     def autonext(self):
         """find and update to the next revision to test"""
         check_clean(self.ui, self.repo)
         rev = self.next()
         if rev is not None:
             return hg.clean(self.repo, rev)
 
     def good(self, rev):
         self.goodrevs.append(rev)
 
     def autogood(self, rev=None):
         """mark revision as good and update to the next revision to test"""
         check_clean(self.ui, self.repo)
         rev = lookup_rev(self.ui, self.repo, rev)
         self.good(rev)
         if self.badrev:
             return self.autonext()
 
     def bad(self, rev):
         self.badrev = rev
 
     def autobad(self, rev=None):
         """mark revision as bad and update to the next revision to test"""
         check_clean(self.ui, self.repo)
         rev = lookup_rev(self.ui, self.repo, rev)
         self.bad(rev)
         if self.goodrevs:
             self.autonext()
 
 # should we put it in the class ?
 def test(ui, repo, rev):
     """test the bisection code"""
     b = bisect(ui, repo)
     rev = repo.lookup(rev)
     ui.write("testing with rev %s\n" % hg.hex(rev))
     anc = b.ancestors()
     while len(anc) > 1:
         if not rev in anc:
             ui.warn("failure while bisecting\n")
             sys.exit(1)
         ui.write("it worked :)\n")
         new_rev = b.next()
         ui.write("choosing if good or bad\n")
         if rev in b.ancestors(head=new_rev):
             b.bad(new_rev)
             ui.write("it is bad\n")
         else:
             b.good(new_rev)
             ui.write("it is good\n")
         anc = b.ancestors()
         #repo.update(new_rev, force=True)
     for v in anc:
         if v != rev:
             ui.warn("fail to found cset! :(\n")
             return 1
     ui.write("Found bad cset: %s\n" % hg.hex(b.badrev))
     ui.write("Everything is ok :)\n")
     return 0
 
 def bisect_run(ui, repo, cmd=None, *args):
     """Dichotomic search in the DAG of changesets
 
 This extension helps to find changesets which cause problems.
 To use, mark the earliest changeset you know introduces the problem
 as bad, then mark the latest changeset which is free from the problem
 as good. Bisect will update your working directory to a revision for
 testing. Once you have performed tests, mark the working directory
 as bad or good and bisect will either update to another candidate
 changeset or announce that it has found the bad revision.
 
 Note: bisect expects bad revisions to be descendants of good revisions.
 If you are looking for the point at which a problem was fixed, then make
 the problem-free state "bad" and the problematic state "good."
 
 For subcommands see "hg bisect help\"
     """
     def help_(cmd=None, *args):
         """show help for a given bisect subcommand or all subcommands"""
         cmdtable = bisectcmdtable
         if cmd:
             doc = cmdtable[cmd][0].__doc__
             synopsis = cmdtable[cmd][2]
             ui.write(synopsis + "\n")
             ui.write("\n" + doc + "\n")
             return
         ui.write(_("list of subcommands for the bisect extension\n\n"))
         cmds = cmdtable.keys()
         cmds.sort()
         m = max([len(c) for c in cmds])
         for cmd in cmds:
             doc = cmdtable[cmd][0].__doc__.splitlines(0)[0].rstrip()
             ui.write(" %-*s   %s\n" % (m, cmd, doc))
 
     b = bisect(ui, repo)
     bisectcmdtable = {
         "init": (b.init, 0, _("hg bisect init")),
         "bad": (b.autobad, 1, _("hg bisect bad [<rev>]")),
         "good": (b.autogood, 1, _("hg bisect good [<rev>]")),
         "next": (b.autonext, 0, _("hg bisect next")),
         "reset": (b.reset, 0, _("hg bisect reset")),
         "help": (help_, 1, _("hg bisect help [<subcommand>]")),
     }
 
     if not bisectcmdtable.has_key(cmd):
         ui.warn(_("bisect: Unknown sub-command\n"))
         return help_()
     if len(args) > bisectcmdtable[cmd][1]:
         ui.warn(_("bisect: Too many arguments\n"))
         return help_()
     try:
         return bisectcmdtable[cmd][0](*args)
     finally:
         b.write()
 
 cmdtable = {
     "bisect": (bisect_run, [], _("hg bisect [help|init|reset|next|good|bad]")),
     #"bisect-test": (test, [], "hg bisect-test rev"),
 }

mercurial/hgweb/wsgicgi.py

@@ -1,72 +1,73 b''
 # hgweb/wsgicgi.py - CGI->WSGI translator
 #
 # Copyright 2006 Eric Hopper <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 #
 # This was originally copied from the public domain code at
 # http://www.python.org/dev/peps/pep-0333/#the-server-gateway-side
 
 import os, sys
 from mercurial import util
 
 def launch(application):
+    util.set_binary(sys.stdin)
     util.set_binary(sys.stdout)
 
     environ = dict(os.environ.items())
     environ['wsgi.input'] = sys.stdin
     environ['wsgi.errors'] = sys.stderr
     environ['wsgi.version'] = (1, 0)
     environ['wsgi.multithread'] = False
     environ['wsgi.multiprocess'] = True
     environ['wsgi.run_once'] = True
 
     if environ.get('HTTPS','off') in ('on','1'):
         environ['wsgi.url_scheme'] = 'https'
     else:
         environ['wsgi.url_scheme'] = 'http'
 
     headers_set = []
     headers_sent = []
     out = sys.stdout
 
     def write(data):
         if not headers_set:
             raise AssertionError("write() before start_response()")
 
         elif not headers_sent:
             # Before the first output, send the stored headers
             status, response_headers = headers_sent[:] = headers_set
             out.write('Status: %s\r\n' % status)
             for header in response_headers:
                 out.write('%s: %s\r\n' % header)
             out.write('\r\n')
 
         out.write(data)
         out.flush()
 
     def start_response(status, response_headers, exc_info=None):
         if exc_info:
             try:
                 if headers_sent:
                     # Re-raise original exception if headers sent
                     raise exc_info[0], exc_info[1], exc_info[2]
             finally:
                 exc_info = None     # avoid dangling circular ref
         elif headers_set:
             raise AssertionError("Headers already set!")
 
         headers_set[:] = [status, response_headers]
         return write
 
     result = application(environ, start_response)
     try:
         for data in result:
             if data:    # don't send headers until body appears
                 write(data)
         if not headers_sent:
             write('')   # send headers now if body was empty
     finally:
         if hasattr(result,'close'):
             result.close()

mercurial/localrepo.py

@@ -1,1950 +1,1950 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from node import *
 from i18n import _
 import repo, changegroup
 import changelog, dirstate, filelog, manifest, context
 import re, lock, transaction, tempfile, stat, mdiff, errno, ui
 import os, revlog, time, util
 
 class localrepository(repo.repository):
     capabilities = ('lookup', 'changegroupsubset')
     supported = ('revlogv1', 'store')
 
     def __del__(self):
         self.transhandle = None
     def __init__(self, parentui, path=None, create=0):
         repo.repository.__init__(self)
         if not path:
             p = os.getcwd()
             while not os.path.isdir(os.path.join(p, ".hg")):
                 oldp = p
                 p = os.path.dirname(p)
                 if p == oldp:
                     raise repo.RepoError(_("There is no Mercurial repository"
                                            " here (.hg not found)"))
             path = p
 
         self.root = os.path.realpath(path)
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     os.mkdir(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if parentui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise repo.RepoError(_("repository %s not found") % path)
         elif create:
             raise repo.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             try:
                 requirements = self.opener("requires").read().splitlines()
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
                 requirements = []
         # check them
         for r in requirements:
             if r not in self.supported:
                 raise repo.RepoError(_("requirement '%s' not supported") % r)
 
         # setup store
         if "store" in requirements:
             self.encodefn = util.encodefilename
             self.decodefn = util.decodefilename
             self.spath = os.path.join(self.path, "store")
         else:
             self.encodefn = lambda x: x
             self.decodefn = lambda x: x
             self.spath = self.path
         self.sopener = util.encodedopener(util.opener(self.spath), self.encodefn)
 
         self.ui = ui.ui(parentui=parentui)
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
         except IOError:
             pass
 
         self.changelog = changelog.changelog(self.sopener)
         self.sopener.defversion = self.changelog.version
         self.manifest = manifest.manifest(self.sopener)
 
         fallback = self.ui.config('ui', 'fallbackencoding')
         if fallback:
             util._fallbackencoding = fallback
 
         self.tagscache = None
         self.branchcache = None
         self.nodetagscache = None
         self.filterpats = {}
         self.transhandle = None
 
         self.dirstate = dirstate.dirstate(self.opener, self.ui, self.root)
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         def callhook(hname, funcname):
             '''call python hook. hook is callable object, looked up as
             name in python module. if callable returns "true", hook
             fails, else passes. if hook raises exception, treated as
             hook failure. exception propagates if throw is "true".
 
             reason for "true" meaning "hook failed" is so that
             unmodified commands (e.g. mercurial.commands.update) can
             be run as hooks without wrappers to convert return values.'''
 
             self.ui.note(_("calling hook %s: %s\n") % (hname, funcname))
             obj = funcname
             if not callable(obj):
                 d = funcname.rfind('.')
                 if d == -1:
                     raise util.Abort(_('%s hook is invalid ("%s" not in '
                                        'a module)') % (hname, funcname))
                 modname = funcname[:d]
                 try:
                     obj = __import__(modname)
                 except ImportError:
                     try:
                         # extensions are loaded with hgext_ prefix
                         obj = __import__("hgext_%s" % modname)
                     except ImportError:
                         raise util.Abort(_('%s hook is invalid '
                                            '(import of "%s" failed)') %
                                          (hname, modname))
                 try:
                     for p in funcname.split('.')[1:]:
                         obj = getattr(obj, p)
                 except AttributeError, err:
                     raise util.Abort(_('%s hook is invalid '
                                        '("%s" is not defined)') %
                                      (hname, funcname))
                 if not callable(obj):
                     raise util.Abort(_('%s hook is invalid '
                                        '("%s" is not callable)') %
                                      (hname, funcname))
             try:
                 r = obj(ui=self.ui, repo=self, hooktype=name, **args)
             except (KeyboardInterrupt, util.SignalInterrupt):
                 raise
             except Exception, exc:
                 if isinstance(exc, util.Abort):
                     self.ui.warn(_('error: %s hook failed: %s\n') %
                                  (hname, exc.args[0]))
                 else:
                     self.ui.warn(_('error: %s hook raised an exception: '
                                    '%s\n') % (hname, exc))
                 if throw:
                     raise
                 self.ui.print_exc()
                 return True
             if r:
                 if throw:
                     raise util.Abort(_('%s hook failed') % hname)
                 self.ui.warn(_('warning: %s hook failed\n') % hname)
             return r
 
         def runhook(name, cmd):
             self.ui.note(_("running hook %s: %s\n") % (name, cmd))
             env = dict([('HG_' + k.upper(), v) for k, v in args.iteritems()])
             r = util.system(cmd, environ=env, cwd=self.root)
             if r:
                 desc, r = util.explain_exit(r)
                 if throw:
                     raise util.Abort(_('%s hook %s') % (name, desc))
                 self.ui.warn(_('warning: %s hook %s\n') % (name, desc))
             return r
 
         r = False
         hooks = [(hname, cmd) for hname, cmd in self.ui.configitems("hooks")
                  if hname.split(".", 1)[0] == name and cmd]
         hooks.sort()
         for hname, cmd in hooks:
             if callable(cmd):
                 r = callhook(hname, cmd) or r
             elif cmd.startswith('python:'):
                 r = callhook(hname, cmd[7:].strip()) or r
             else:
                 r = runhook(hname, cmd) or r
         return r
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, name, node, message, local, user, date, parent=None):
         use_dirstate = parent is None
 
         for c in self.tag_disallowed:
             if c in name:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         self.hook('pretag', throw=True, node=hex(node), tag=name, local=local)
 
         if local:
             # local tags are stored in the current charset
             self.opener('localtags', 'a').write('%s %s\n' % (hex(node), name))
             self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         # committed tags are stored in UTF-8
         line = '%s %s\n' % (hex(node), util.fromlocal(name))
         if use_dirstate:
             self.wfile('.hgtags', 'ab').write(line)
         else:
             ntags = self.filectx('.hgtags', parent).data()
             self.wfile('.hgtags', 'ab').write(ntags + line)
         if use_dirstate and self.dirstate.state('.hgtags') == '?':
             self.add(['.hgtags'])
 
         tagnode = self.commit(['.hgtags'], message, user, date, p1=parent)
 
         self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, name, node, message, local, user, date):
         '''tag a revision with a symbolic name.
 
         if local is True, the tag is stored in a per-repository file.
         otherwise, it is stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tag in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
 
         self._tag(name, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self.tagscache:
             return self.tagscache
 
         globaltags = {}
 
         def readtags(lines, fn):
             filetags = {}
             count = 0
 
             def warn(msg):
                 self.ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
             for l in lines:
                 count += 1
                 if not l:
                     continue
                 s = l.split(" ", 1)
                 if len(s) != 2:
                     warn(_("cannot parse entry"))
                     continue
                 node, key = s
                 key = util.tolocal(key.strip()) # stored in UTF-8
                 try:
                     bin_n = bin(node)
                 except TypeError:
                     warn(_("node '%s' is not well formed") % node)
                     continue
                 if bin_n not in self.changelog.nodemap:
                     warn(_("tag '%s' refers to unknown node") % key)
                     continue
 
                 h = []
                 if key in filetags:
                     n, h = filetags[key]
                     h.append(n)
                 filetags[key] = (bin_n, h)
 
             for k,nh in filetags.items():
                 if k not in globaltags:
                     globaltags[k] = nh
                     continue
                 # we prefer the global tag if:
                 #  it supercedes us OR
                 #  mutual supercedes and it has a higher rank
                 # otherwise we win because we're tip-most
                 an, ah = nh
                 bn, bh = globaltags[k]
                 if bn != an and an in bh and \
                    (bn not in ah or len(bh) > len(ah)):
                     an = bn
-                ah.append([n for n in bh if n not in ah])
+                ah.extend([n for n in bh if n not in ah])
                 globaltags[k] = an, ah
 
         # read the tags file from each head, ending with the tip
         f = None
         for rev, node, fnode in self._hgtagsnodes():
             f = (f and f.filectx(fnode) or
                  self.filectx('.hgtags', fileid=fnode))
             readtags(f.data().splitlines(), f)
 
         try:
             data = util.fromlocal(self.opener("localtags").read())
             # localtags are stored in the local character set
             # while the internal tag table is stored in UTF-8
             readtags(data.splitlines(), "localtags")
         except IOError:
             pass
 
         self.tagscache = {}
         for k,nh in globaltags.items():
             n = nh[0]
             if n != nullid:
                 self.tagscache[k] = n
         self.tagscache['tip'] = self.changelog.tip()
 
         return self.tagscache
 
     def _hgtagsnodes(self):
         heads = self.heads()
         heads.reverse()
         last = {}
         ret = []
         for node in heads:
             c = self.changectx(node)
             rev = c.rev()
             try:
                 fnode = c.filenode('.hgtags')
             except revlog.LookupError:
                 continue
             ret.append((rev, node, fnode))
             if fnode in last:
                 ret[last[fnode]] = None
             last[fnode] = len(ret) - 1
         return [item for item in ret if item]
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().items():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         l.sort()
         return [(t, n) for r, t, n in l]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().items():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self):
         partial, last, lrev = self._readbranchcache()
 
         tiprev = self.changelog.count() - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchtags(self):
         if self.branchcache is not None:
             return self.branchcache
 
         self.branchcache = {} # avoid recursion in changectx
         partial = self._branchtags()
 
         # the branch cache is stored on disk as UTF-8, but in the local
         # charset internally
         for k, v in partial.items():
             self.branchcache[util.tolocal(k)] = v
         return self.branchcache
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branch.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if not (lrev < self.changelog.count() and
                     self.changelog.node(lrev) == last): # sanity check
                 # invalidate the cache
                 raise ValueError('Invalid branch cache: unknown tip')
             for l in lines:
                 if not l: continue
                 node, label = l.split(" ", 1)
                 partial[label.strip()] = bin(node)
         except (KeyboardInterrupt, util.SignalInterrupt):
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branch.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, node in branches.iteritems():
                 f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, start, end):
         for r in xrange(start, end):
             c = self.changectx(r)
             b = c.branch()
             partial[b] = c.node()
 
     def lookup(self, key):
         if key == '.':
             key = self.dirstate.parents()[0]
             if key == nullid:
                 raise repo.RepoError(_("no revision checked out"))
         elif key == 'null':
             return nullid
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
         raise repo.RepoError(_("unknown revision '%s'") % key)
 
     def dev(self):
         return os.lstat(self.path).st_dev
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def sjoin(self, f):
         f = self.encodefn(f)
         return os.path.join(self.spath, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid=None):
         return context.changectx(self, changeid)
 
     def workingctx(self):
         return context.workingctx(self)
 
     def parents(self, changeid=None):
         '''
         get list of changectxs for parents of changeid or working directory
         '''
         if changeid is None:
             pl = self.dirstate.parents()
         else:
             n = self.changelog.lookup(changeid)
             pl = self.changelog.parents(n)
         if pl[1] == nullid:
             return [self.changectx(pl[0])]
         return [self.changectx(pl[0]), self.changectx(pl[1])]
 
     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 wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 mf = util.matcher(self.root, "", [pat], [], [])[1]
                 l.append((mf, cmd))
             self.filterpats[filter] = l
 
         for mf, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug(_("filtering %s through %s\n") % (filename, cmd))
                 data = util.filter(data, cmd)
                 break
 
         return data
 
     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)
         if "l" in flags:
             f = self.wjoin(filename)
             try:
                 os.unlink(f)
             except OSError:
                 pass
             d = os.path.dirname(f)
             if not os.path.exists(d):
                 os.makedirs(d)
             os.symlink(data, f)
         else:
             try:
                 if self._link(filename):
                     os.unlink(self.wjoin(filename))
             except OSError:
                 pass
             self.wopener(filename, 'w').write(data)
             util.set_exec(self.wjoin(filename), "x" in flags)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         tr = self.transhandle
         if tr != None and tr.running():
             return tr.nest()
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                        self.sjoin("journal"),
                                        aftertrans(renames))
         self.transhandle = tr
         return tr
 
     def recover(self):
         l = self.lock()
         if os.path.exists(self.sjoin("journal")):
             self.ui.status(_("rolling back interrupted transaction\n"))
             transaction.rollback(self.sopener, self.sjoin("journal"))
             self.reload()
             return True
         else:
             self.ui.warn(_("no interrupted transaction available\n"))
             return False
 
     def rollback(self, wlock=None, lock=None):
         if not wlock:
             wlock = self.wlock()
         if not lock:
             lock = self.lock()
         if os.path.exists(self.sjoin("undo")):
             self.ui.status(_("rolling back last transaction\n"))
             transaction.rollback(self.sopener, self.sjoin("undo"))
             util.rename(self.join("undo.dirstate"), self.join("dirstate"))
             self.reload()
             self.wreload()
         else:
             self.ui.warn(_("no rollback information available\n"))
 
     def wreload(self):
         self.dirstate.reload()
 
     def reload(self):
         self.changelog.load()
         self.manifest.load()
         self.tagscache = None
         self.nodetagscache = None
 
     def do_lock(self, lockname, wait, releasefn=None, acquirefn=None,
                 desc=None):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except lock.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def lock(self, wait=1):
         return self.do_lock(self.sjoin("lock"), wait, acquirefn=self.reload,
                             desc=_('repository %s') % self.origroot)
 
     def wlock(self, wait=1):
         return self.do_lock(self.join("wlock"), wait, self.dirstate.write,
                             self.wreload,
                             desc=_('working directory of %s') % self.origroot)
 
     def filecommit(self, fn, manifest1, manifest2, linkrev, transaction, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         t = self.wread(fn)
         fl = self.file(fn)
         fp1 = manifest1.get(fn, nullid)
         fp2 = manifest2.get(fn, nullid)
 
         meta = {}
         cp = self.dirstate.copied(fn)
         if cp:
             # 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
             #
             meta["copy"] = cp
             if not manifest2: # not a branch merge
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
                 fp2 = nullid
             elif fp2 != nullid: # copied on remote side
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
             elif fp1 != nullid: # copied on local side, reversed
                 meta["copyrev"] = hex(manifest2.get(cp))
                 fp2 = fp1
             else: # directory rename
                 meta["copyrev"] = hex(manifest1.get(cp, nullid))
             self.ui.debug(_(" %s: copy %s:%s\n") %
                           (fn, cp, meta["copyrev"]))
             fp1 = nullid
         elif fp2 != nullid:
             # is one parent an ancestor of the other?
             fpa = fl.ancestor(fp1, fp2)
             if fpa == fp1:
                 fp1, fp2 = fp2, nullid
             elif fpa == fp2:
                 fp2 = nullid
 
             # is the file unmodified from the parent? report existing entry
             if fp2 == nullid and not fl.cmp(fp1, t):
                 return fp1
 
         changelist.append(fn)
         return fl.add(t, meta, transaction, linkrev, fp1, fp2)
 
     def rawcommit(self, files, text, user, date, p1=None, p2=None, wlock=None, extra={}):
         if p1 is None:
             p1, p2 = self.dirstate.parents()
         return self.commit(files=files, text=text, user=user, date=date,
                            p1=p1, p2=p2, wlock=wlock, extra=extra)
 
     def commit(self, files=None, text="", user=None, date=None,
                match=util.always, force=False, lock=None, wlock=None,
                force_editor=False, p1=None, p2=None, extra={}):
 
         commit = []
         remove = []
         changed = []
         use_dirstate = (p1 is None) # not rawcommit
         extra = extra.copy()
 
         if use_dirstate:
             if files:
                 for f in files:
                     s = self.dirstate.state(f)
                     if s in 'nmai':
                         commit.append(f)
                     elif s == 'r':
                         remove.append(f)
                     else:
                         self.ui.warn(_("%s not tracked!\n") % f)
             else:
                 changes = self.status(match=match)[:5]
                 modified, added, removed, deleted, unknown = changes
                 commit = modified + added
                 remove = removed
         else:
             commit = files
 
         if use_dirstate:
             p1, p2 = self.dirstate.parents()
             update_dirstate = True
         else:
             p1, p2 = p1, p2 or nullid
             update_dirstate = (self.dirstate.parents()[0] == p1)
 
         c1 = self.changelog.read(p1)
         c2 = self.changelog.read(p2)
         m1 = self.manifest.read(c1[0]).copy()
         m2 = self.manifest.read(c2[0])
 
         if use_dirstate:
             branchname = self.workingctx().branch()
             try:
                 branchname = branchname.decode('UTF-8').encode('UTF-8')
             except UnicodeDecodeError:
                 raise util.Abort(_('branch name not in UTF-8!'))
         else:
             branchname = ""
 
         if use_dirstate:
             oldname = c1[5].get("branch") # stored in UTF-8
             if not commit and not remove and not force and p2 == nullid and \
                    branchname == oldname:
                 self.ui.status(_("nothing changed\n"))
                 return None
 
         xp1 = hex(p1)
         if p2 == nullid: xp2 = ''
         else: xp2 = hex(p2)
 
         self.hook("precommit", throw=True, parent1=xp1, parent2=xp2)
 
         if not wlock:
             wlock = self.wlock()
         if not lock:
             lock = self.lock()
         tr = self.transaction()
 
         # check in files
         new = {}
         linkrev = self.changelog.count()
         commit.sort()
         is_exec = util.execfunc(self.root, m1.execf)
         is_link = util.linkfunc(self.root, m1.linkf)
         for f in commit:
             self.ui.note(f + "\n")
             try:
                 new[f] = self.filecommit(f, m1, m2, linkrev, tr, changed)
                 m1.set(f, is_exec(f), is_link(f))
             except (OSError, IOError):
                 if use_dirstate:
                     self.ui.warn(_("trouble committing %s!\n") % f)
                     raise
                 else:
                     remove.append(f)
 
         # update manifest
         m1.update(new)
         remove.sort()
         removed = []
 
         for f in remove:
             if f in m1:
                 del m1[f]
                 removed.append(f)
         mn = self.manifest.add(m1, tr, linkrev, c1[0], c2[0], (new, removed))
 
         # add changeset
         new = new.keys()
         new.sort()
 
         user = user or self.ui.username()
         if not text or force_editor:
             edittext = []
             if text:
                 edittext.append(text)
             edittext.append("")
             edittext.append("HG: user: %s" % user)
             if p2 != nullid:
                 edittext.append("HG: branch merge")
             if branchname:
                 edittext.append("HG: branch %s" % util.tolocal(branchname))
             edittext.extend(["HG: changed %s" % f for f in changed])
             edittext.extend(["HG: removed %s" % f for f in removed])
             if not changed and not remove:
                 edittext.append("HG: no files changed")
             edittext.append("")
             # run editor in the repository root
             olddir = os.getcwd()
             os.chdir(self.root)
             text = self.ui.edit("\n".join(edittext), user)
             os.chdir(olddir)
 
         lines = [line.rstrip() for line in text.rstrip().splitlines()]
         while lines and not lines[0]:
             del lines[0]
         if not lines:
             return None
         text = '\n'.join(lines)
         if branchname:
             extra["branch"] = branchname
         n = self.changelog.add(mn, changed + removed, text, tr, p1, p2,
                                user, date, extra)
         self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                   parent2=xp2)
         tr.close()
 
         if self.branchcache and "branch" in extra:
             self.branchcache[util.tolocal(extra["branch"])] = n
 
         if use_dirstate or update_dirstate:
             self.dirstate.setparents(n)
             if use_dirstate:
                 self.dirstate.update(new, "n")
                 self.dirstate.forget(removed)
 
         self.hook("commit", node=hex(n), parent1=xp1, parent2=xp2)
         return n
 
     def walk(self, node=None, files=[], match=util.always, badmatch=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
 
         results are yielded in a tuple (src, filename), where src
         is one of:
         'f' the file was found in the directory tree
         'm' the file was only in the dirstate and not in the tree
         'b' file was not found and matched badmatch
         '''
 
         if node:
             fdict = dict.fromkeys(files)
             # for dirstate.walk, files=['.'] means "walk the whole tree".
             # follow that here, too
             fdict.pop('.', None)
             mdict = self.manifest.read(self.changelog.read(node)[0])
             mfiles = mdict.keys()
             mfiles.sort()
             for fn in mfiles:
                 for ffn in fdict:
                     # match if the file is the exact name or a directory
                     if ffn == fn or fn.startswith("%s/" % ffn):
                         del fdict[ffn]
                         break
                 if match(fn):
                     yield 'm', fn
             ffiles = fdict.keys()
             ffiles.sort()
             for fn in ffiles:
                 if badmatch and badmatch(fn):
                     if match(fn):
                         yield 'b', fn
                 else:
                     self.ui.warn(_('%s: No such file in rev %s\n') % (
                         util.pathto(self.root, self.getcwd(), fn), short(node)))
         else:
             for src, fn in self.dirstate.walk(files, match, badmatch=badmatch):
                 yield src, fn
 
     def status(self, node1=None, node2=None, files=[], match=util.always,
                 wlock=None, list_ignored=False, list_clean=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 fcmp(fn, getnode):
             t1 = self.wread(fn)
             return self.file(fn).cmp(getnode(fn), t1)
 
         def mfmatches(node):
             change = self.changelog.read(node)
             mf = self.manifest.read(change[0]).copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         modified, added, removed, deleted, unknown = [], [], [], [], []
         ignored, clean = [], []
 
         compareworking = False
         if not node1 or (not node2 and node1 == self.dirstate.parents()[0]):
             compareworking = True
 
         if not compareworking:
             # read the manifest from node1 before the manifest from node2,
             # so that we'll hit the manifest cache if we're going through
             # all the revisions in parent->child order.
             mf1 = mfmatches(node1)
 
         mywlock = False
 
         # are we comparing the working directory?
         if not node2:
             (lookup, modified, added, removed, deleted, unknown,
              ignored, clean) = self.dirstate.status(files, match,
                                                     list_ignored, list_clean)
 
             # are we comparing working dir against its parent?
             if compareworking:
                 if lookup:
                     # do a full compare of any files that might have changed
                     mnode = self.changelog.read(self.dirstate.parents()[0])[0]
                     getnode = lambda fn: (self.manifest.find(mnode, fn)[0] or
                                           nullid)
                     for f in lookup:
                         if fcmp(f, getnode):
                             modified.append(f)
                         else:
                             clean.append(f)
                             if not wlock and not mywlock:
                                 mywlock = True
                                 try:
                                     wlock = self.wlock(wait=0)
                                 except lock.LockException:
                                     pass
                             if wlock:
                                 self.dirstate.update([f], "n")
             else:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 # XXX: create it in dirstate.py ?
                 mf2 = mfmatches(self.dirstate.parents()[0])
                 is_exec = util.execfunc(self.root, mf2.execf)
                 is_link = util.linkfunc(self.root, mf2.linkf)
                 for f in lookup + modified + added:
                     mf2[f] = ""
                     mf2.set(f, is_exec(f), is_link(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
 
             if mywlock and wlock:
                 wlock.release()
         else:
             # we are comparing two revisions
             mf2 = mfmatches(node2)
 
         if not compareworking:
             # flush lists from dirstate before comparing manifests
             modified, added, clean = [], [], []
 
             # make sure to sort the files so we talk to the disk in a
             # reasonable order
             mf2keys = mf2.keys()
             mf2keys.sort()
             getnode = lambda fn: mf1.get(fn, nullid)
             for fn in mf2keys:
                 if mf1.has_key(fn):
                     if mf1.flags(fn) != mf2.flags(fn) or \
                        (mf1[fn] != mf2[fn] and (mf2[fn] != "" or
                                                 fcmp(fn, getnode))):
                         modified.append(fn)
                     elif list_clean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
 
             removed = mf1.keys()
 
         # sort and return results:
         for l in modified, added, removed, deleted, unknown, ignored, clean:
             l.sort()
         return (modified, added, removed, deleted, unknown, ignored, clean)
 
     def add(self, list, wlock=None):
         if not wlock:
             wlock = self.wlock()
         for f in list:
             p = self.wjoin(f)
             islink = os.path.islink(p)
             size = os.lstat(p).st_size
             if 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 islink and not os.path.exists(p):
                 self.ui.warn(_("%s does not exist!\n") % f)
             elif not islink and not os.path.isfile(p):
                 self.ui.warn(_("%s not added: only files and symlinks "
                                "supported currently\n") % f)
             elif self.dirstate.state(f) in 'an':
                 self.ui.warn(_("%s already tracked!\n") % f)
             else:
                 self.dirstate.update([f], "a")
 
     def forget(self, list, wlock=None):
         if not wlock:
             wlock = self.wlock()
         for f in list:
             if self.dirstate.state(f) not in 'ai':
                 self.ui.warn(_("%s not added!\n") % f)
             else:
                 self.dirstate.forget([f])
 
     def remove(self, list, unlink=False, wlock=None):
         if unlink:
             for f in list:
                 try:
                     util.unlink(self.wjoin(f))
                 except OSError, inst:
                     if inst.errno != errno.ENOENT:
                         raise
         if not wlock:
             wlock = self.wlock()
         for f in list:
             if unlink and os.path.exists(self.wjoin(f)):
                 self.ui.warn(_("%s still exists!\n") % f)
             elif self.dirstate.state(f) == 'a':
                 self.dirstate.forget([f])
             elif f not in self.dirstate:
                 self.ui.warn(_("%s not tracked!\n") % f)
             else:
                 self.dirstate.update([f], "r")
 
     def undelete(self, list, wlock=None):
         p = self.dirstate.parents()[0]
         mn = self.changelog.read(p)[0]
         m = self.manifest.read(mn)
         if not wlock:
             wlock = self.wlock()
         for f in list:
             if self.dirstate.state(f) not in  "r":
                 self.ui.warn("%s not removed!\n" % f)
             else:
                 t = self.file(f).read(m[f])
                 self.wwrite(f, t, m.flags(f))
                 self.dirstate.update([f], "n")
 
     def copy(self, source, dest, wlock=None):
         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:
             if not wlock:
                 wlock = self.wlock()
             if self.dirstate.state(dest) == '?':
                 self.dirstate.update([dest], "a")
             self.dirstate.copy(source, dest)
 
     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]
         heads.sort()
         return [n for (r, n) in heads]
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         m = self.changelog.nodemap
         search = []
         fetch = {}
         seen = {}
         seenbranch = {}
         if base == None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid]
             return []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         if not unknown:
             return []
 
         req = dict.fromkeys(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug(_("examining %s:%s\n")
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug(_("branch already found\n"))
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug(_("found incomplete branch %s:%s\n")
                                   % (short(n[0]), short(n[1])))
                     search.append(n) # schedule branch range for scanning
                     seenbranch[n] = 1
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug(_("found new changeset %s\n") %
                                           short(n[1]))
                             fetch[n[1]] = 1 # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req[p] = 1
                 seen[n[0]] = 1
 
             if r:
                 reqcnt += 1
                 self.ui.debug(_("request %d: %s\n") %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug(_("received %s:%s\n") %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             n = search.pop(0)
             reqcnt += 1
             l = remote.between([(n[0], n[1])])[0]
             l.append(n[1])
             p = n[0]
             f = 1
             for i in l:
                 self.ui.debug(_("narrowing %d:%d %s\n") % (f, len(l), short(i)))
                 if i in m:
                     if f <= 2:
                         self.ui.debug(_("found new branch changeset %s\n") %
                                           short(p))
                         fetch[p] = 1
                         base[i] = 1
                     else:
                         self.ui.debug(_("narrowed branch search to %s:%s\n")
                                       % (short(p), short(i)))
                         search.append((p, i))
                     break
                 p, f = i, f * 2
 
         # sanity check our fetch list
         for f in fetch.keys():
             if f in m:
                 raise repo.RepoError(_("already have changeset ") + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug(_("found new changesets starting at ") +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug(_("%d total queries\n") % reqcnt)
 
         return fetch.keys()
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base == None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug(_("common changesets up to ")
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = dict.fromkeys(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         del remain[nullid]
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 del remain[n]
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = {}
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads[p1] = True
                 if p2 in heads:
                     updated_heads[p2] = True
 
         # this is the set of all roots we have to push
         if heads:
             return subset, updated_heads.keys()
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False, lock=None):
         mylock = False
         if not lock:
             lock = self.lock()
             mylock = True
 
         try:
             fetch = self.findincoming(remote, force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if 'changegroupsubset' not in remote.capabilities:
                     raise util.Abort(_("Partial pull cannot be done because other repository doesn't support changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             if mylock:
                 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):
         base = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, base, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, base, remote_heads)
         if revs is not None:
             msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
         else:
             bases, heads = update, self.changelog.heads()
 
         if not bases:
             self.ui.status(_("no changes found\n"))
             return None, 1
         elif not force:
             # check if we're creating new remote heads
             # to be a remote head after push, node must be either
             # - unknown locally
             # - a local outgoing head descended from update
             # - a remote head that's known locally and not
             #   ancestral to an outgoing head
 
             warn = 0
 
             if remote_heads == [nullid]:
                 warn = 0
             elif not revs and len(heads) > len(remote_heads):
                 warn = 1
             else:
                 newheads = list(heads)
                 for r in remote_heads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.append(r)
                     else:
                         newheads.append(r)
                 if len(newheads) > len(remote_heads):
                     warn = 1
 
             if warn:
                 self.ui.warn(_("abort: push creates new remote branches!\n"))
                 self.ui.status(_("(did you forget to merge?"
                                  " use push -f to force)\n"))
                 return None, 1
             elif inc:
                 self.ui.warn(_("note: unsynced remote changes!\n"))
 
 
         if revs is None:
             cg = self.changegroup(update, 'push')
         else:
             cg = self.changegroupsubset(update, revs, 'push')
         return cg, remote_heads
 
     def push_addchangegroup(self, remote, force, revs):
         lock = remote.lock()
 
         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]
 
     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):
         self.ui.note(_("%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):
         """This function generates a changegroup consisting of all the nodes
         that are descendents of any of the bases, and ancestors of any of
         the heads.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to."""
 
         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)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = {}
         # We assume that all parents of bases are known heads.
         for n in bases:
             for p in cl.parents(n):
                 if p != nullid:
                     knownheads[p] = 1
         knownheads = knownheads.keys()
         if knownheads:
             # Now that we know what heads are known, we can compute which
             # changesets are known.  The recipient must know about all
             # changesets required to reach the known heads from the null
             # changeset.
             has_cl_set, junk, junk = cl.nodesbetween(None, knownheads)
             junk = None
             # Transform the list into an ersatz set.
             has_cl_set = dict.fromkeys(has_cl_set)
         else:
             # If there were no known heads, the recipient cannot be assumed to
             # know about any changesets.
             has_cl_set = {}
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[mnfst.count() - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function.  Sets up an environment for the
         # inner function.
         def cmp_by_rev_func(revlog):
             # Compare two nodes by their revision number in the environment's
             # revision history.  Since the revision number both represents the
             # most efficient order to read the nodes in, and represents a
             # topological sorting of the nodes, this function is often useful.
             def cmp_by_rev(a, b):
                 return cmp(revlog.rev(a), revlog.rev(b))
             return cmp_by_rev
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune_parents(revlog, hasset, msngset):
             haslst = hasset.keys()
             haslst.sort(cmp_by_rev_func(revlog))
             for node in haslst:
                 parentlst = [p for p in revlog.parents(node) if p != nullid]
                 while parentlst:
                     n = parentlst.pop()
                     if n not in hasset:
                         hasset[n] = 1
                         p = [p for p in revlog.parents(n) if p != nullid]
                         parentlst.extend(p)
             for n in hasset:
                 msngset.pop(n, None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = {}
             for n in msng_mnfst_set:
                 # If a 'missing' manifest thinks it belongs to a changenode
                 # the recipient is assumed to have, obviously the recipient
                 # must have that manifest.
                 linknode = cl.node(mnfst.linkrev(n))
                 if linknode in has_cl_set:
                     has_mnfst_set[n] = 1
             prune_parents(mnfst, has_mnfst_set, msng_mnfst_set)
 
         # Use the information collected in collect_manifests_and_files to say
         # which changenode any manifestnode belongs to.
         def lookup_manifest_link(mnfstnode):
             return msng_mnfst_set[mnfstnode]
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             next_rev = [0]
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r == next_rev[0]:
                     # If the last rev we looked at was the one just previous,
                     # we only need to see a diff.
                     delta = mdiff.patchtext(mnfst.delta(mnfstnode))
                     # For each line in the delta
                     for dline in delta.splitlines():
                         # get the filename and filenode for that line
                         f, fnode = dline.split('\0')
                         fnode = bin(fnode[:40])
                         f = changedfiles.get(f, None)
                         # And if the file is in the list of files we care
                         # about.
                         if f is not None:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
                 # Remember the revision we hope to see next.
                 next_rev[0] = r + 1
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we now the recipient must have.
         def prune_filenodes(f, filerevlog):
             msngset = msng_filenode_set[f]
             hasset = {}
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in msngset:
                 clnode = cl.node(filerevlog.linkrev(n))
                 if clnode in has_cl_set:
                     hasset[n] = 1
             prune_parents(filerevlog, hasset, msngset)
 
         # A function generator function that sets up the a context for the
         # inner function.
         def lookup_filenode_link_func(fname):
             msngset = msng_filenode_set[fname]
             # Lookup the changenode the filenode belongs to.
             def lookup_filenode_link(fnode):
                 return msngset[fnode]
             return lookup_filenode_link
 
         # 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()
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(cmp_by_rev_func(mnfst))
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
                                 filenode_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             changedfiles = changedfiles.keys()
             changedfiles.sort()
             # Go through all our files in order sorted by name.
             for fname in changedfiles:
                 filerevlog = self.file(fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 if msng_filenode_set.has_key(fname):
                     prune_filenodes(fname, filerevlog)
                     msng_filenode_lst = msng_filenode_set[fname].keys()
                 else:
                     msng_filenode_lst = []
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if len(msng_filenode_lst) > 0:
                     yield changegroup.genchunk(fname)
                     # Sort the filenodes by their revision #
                     msng_filenode_lst.sort(cmp_by_rev_func(filerevlog))
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(msng_filenode_lst,
                                              lookup_filenode_link_func(fname))
                     for chnk in group:
                         yield chnk
                 if msng_filenode_set.has_key(fname):
                     # Don't need this anymore, toss it to free memory.
                     del msng_filenode_set[fname]
             # Signal that no more groups are left.
             yield changegroup.closechunk()
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         """Generate a changegroup of all nodes that we have that a recipient
         doesn't.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them."""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         nodes = cl.nodesbetween(basenodes, None)[0]
         revset = dict.fromkeys([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes)
 
         def identity(x):
             return x
 
         def gennodelst(revlog):
             for r in xrange(0, revlog.count()):
                 n = revlog.node(r)
                 if revlog.linkrev(n) in revset:
                     yield n
 
         def changed_file_collector(changedfileset):
             def collect_changed_files(clnode):
                 c = cl.read(clnode)
                 for fname in c[3]:
                     changedfileset[fname] = 1
             return collect_changed_files
 
         def lookuprevlink_func(revlog):
             def lookuprevlink(n):
                 return cl.node(revlog.linkrev(n))
             return lookuprevlink
 
         def gengroup():
             # construct a list of all changed files
             changedfiles = {}
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
             changedfiles = changedfiles.keys()
             changedfiles.sort()
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in changedfiles:
                 filerevlog = self.file(fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.genchunk(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):
         """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 cl.count()
 
         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
 
         tr = self.transaction()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         # pull off the changeset group
         self.ui.status(_("adding changesets\n"))
         cor = cl.count() - 1
         chunkiter = changegroup.chunkiter(source)
         if cl.addgroup(chunkiter, csmap, tr, 1) is None:
             raise util.Abort(_("received changelog group is empty"))
         cnr = cl.count() - 1
         changesets = cnr - cor
 
         # pull off the manifest group
         self.ui.status(_("adding manifests\n"))
         chunkiter = changegroup.chunkiter(source)
         # no need to check for empty manifest group here:
         # if the result of the merge of 1 and 2 is the same in 3 and 4,
         # no new manifest will be created and the manifest group will
         # be empty during the pull
         self.manifest.addgroup(chunkiter, revmap, tr)
 
         # 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 = fl.count()
             chunkiter = changegroup.chunkiter(source)
             if fl.addgroup(chunkiter, revmap, tr) is None:
                 raise util.Abort(_("received file revlog group is empty"))
             revisions += fl.count() - o
             files += 1
 
         # make changelog see real files again
         cl.finalize(tr)
 
         newheads = len(self.changelog.heads())
         heads = ""
         if oldheads and newheads != oldheads:
             heads = _(" (%+d heads)") % (newheads - oldheads)
 
         self.ui.status(_("added %d changesets"
                          " with %d changes to %d files%s\n")
                          % (changesets, revisions, files, heads))
 
         if changesets > 0:
             self.hook('pretxnchangegroup', throw=True,
                       node=hex(self.changelog.node(cor+1)), source=srctype,
                       url=url)
 
         tr.close()
 
         if changesets > 0:
             self.hook("changegroup", node=hex(self.changelog.node(cor+1)),
                       source=srctype, url=url)
 
             for i in xrange(cor + 1, cnr + 1):
                 self.hook("incoming", node=hex(self.changelog.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise util.UnexpectedOutput(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except ValueError, TypeError:
             raise util.UnexpectedOutput(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except ValueError, TypeError:
                 raise util.UnexpectedOutput(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             ofp = self.sopener(name, 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.reload()
         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/revlog.py

@@ -1,1296 +1,1297 b''
 """
 revlog.py - storage back-end for mercurial
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches
 
 Copyright 2005, 2006 Matt Mackall <[e-mail]>
 
 This software may be used and distributed according to the terms
 of the GNU General Public License, incorporated herein by reference.
 """
 
 from node import *
 from i18n import _
 import binascii, changegroup, errno, ancestor, mdiff, os
 import sha, struct, util, zlib
 
 # revlog version strings
 REVLOGV0 = 0
 REVLOGNG = 1
 
 # revlog flags
 REVLOGNGINLINEDATA = (1 << 16)
 REVLOG_DEFAULT_FLAGS = REVLOGNGINLINEDATA
 
 REVLOG_DEFAULT_FORMAT = REVLOGNG
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 
 def hash(text, p1, p2):
     """generate a hash from the given text and its parent hashes
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     l = [p1, p2]
     l.sort()
     s = sha.new(l[0])
     s.update(l[1])
     s.update(text)
     return s.digest()
 
 def compress(text):
     """ generate a possibly-compressed representation of text """
     if not text: return ("", text)
     if len(text) < 44:
         if text[0] == '\0': return ("", text)
         return ('u', text)
     bin = zlib.compress(text)
     if len(bin) > len(text):
         if text[0] == '\0': return ("", text)
         return ('u', text)
     return ("", bin)
 
 def decompress(bin):
     """ decompress the given input """
     if not bin: return bin
     t = bin[0]
     if t == '\0': return bin
     if t == 'x': return zlib.decompress(bin)
     if t == 'u': return bin[1:]
     raise RevlogError(_("unknown compression type %r") % t)
 
 indexformatv0 = ">4l20s20s20s"
 v0shaoffset = 56
 # index ng:
 # 6 bytes offset
 # 2 bytes flags
 # 4 bytes compressed length
 # 4 bytes uncompressed length
 # 4 bytes: base rev
 # 4 bytes link rev
 # 4 bytes parent 1 rev
 # 4 bytes parent 2 rev
 # 32 bytes: nodeid
 indexformatng = ">Qiiiiii20s12x"
 ngshaoffset = 32
 versionformat = ">I"
 
 class lazyparser(object):
     """
     this class avoids the need to parse the entirety of large indices
     """
 
     # lazyparser is not safe to use on windows if win32 extensions not
     # available. it keeps file handle open, which make it not possible
     # to break hardlinks on local cloned repos.
     safe_to_use = os.name != 'nt' or (not util.is_win_9x() and
                                       hasattr(util, 'win32api'))
 
     def __init__(self, dataf, size, indexformat, shaoffset):
         self.dataf = dataf
         self.format = indexformat
         self.s = struct.calcsize(indexformat)
         self.indexformat = indexformat
         self.datasize = size
         self.l = size/self.s
         self.index = [None] * self.l
         self.map = {nullid: nullrev}
         self.allmap = 0
         self.all = 0
         self.mapfind_count = 0
         self.shaoffset = shaoffset
 
     def loadmap(self):
         """
         during a commit, we need to make sure the rev being added is
         not a duplicate.  This requires loading the entire index,
         which is fairly slow.  loadmap can load up just the node map,
         which takes much less time.
         """
         if self.allmap: return
         end = self.datasize
         self.allmap = 1
         cur = 0
         count = 0
         blocksize = self.s * 256
         self.dataf.seek(0)
         while cur < end:
             data = self.dataf.read(blocksize)
             off = 0
             for x in xrange(256):
                 n = data[off + self.shaoffset:off + self.shaoffset + 20]
                 self.map[n] = count
                 count += 1
                 if count >= self.l:
                     break
                 off += self.s
             cur += blocksize
 
     def loadblock(self, blockstart, blocksize, data=None):
         if self.all: return
         if data is None:
             self.dataf.seek(blockstart)
             if blockstart + blocksize > self.datasize:
                 # the revlog may have grown since we've started running,
                 # but we don't have space in self.index for more entries.
                 # limit blocksize so that we don't get too much data.
                 blocksize = max(self.datasize - blockstart, 0)
             data = self.dataf.read(blocksize)
         lend = len(data) / self.s
         i = blockstart / self.s
         off = 0
         # lazyindex supports __delitem__
         if lend > len(self.index) - i:
             lend = len(self.index) - i
         for x in xrange(lend):
             if self.index[i + x] == None:
                 b = data[off : off + self.s]
                 self.index[i + x] = b
                 n = b[self.shaoffset:self.shaoffset + 20]
                 self.map[n] = i + x
             off += self.s
 
     def findnode(self, node):
         """search backwards through the index file for a specific node"""
         if self.allmap: return None
 
         # hg log will cause many many searches for the manifest
         # nodes.  After we get called a few times, just load the whole
         # thing.
         if self.mapfind_count > 8:
             self.loadmap()
             if node in self.map:
                 return node
             return None
         self.mapfind_count += 1
         last = self.l - 1
         while self.index[last] != None:
             if last == 0:
                 self.all = 1
                 self.allmap = 1
                 return None
             last -= 1
         end = (last + 1) * self.s
         blocksize = self.s * 256
         while end >= 0:
             start = max(end - blocksize, 0)
             self.dataf.seek(start)
             data = self.dataf.read(end - start)
             findend = end - start
             while True:
                 # we're searching backwards, so weh have to make sure
                 # we don't find a changeset where this node is a parent
                 off = data.rfind(node, 0, findend)
                 findend = off
                 if off >= 0:
                     i = off / self.s
                     off = i * self.s
                     n = data[off + self.shaoffset:off + self.shaoffset + 20]
                     if n == node:
                         self.map[n] = i + start / self.s
                         return node
                 else:
                     break
             end -= blocksize
         return None
 
     def loadindex(self, i=None, end=None):
         if self.all: return
         all = False
         if i == None:
             blockstart = 0
             blocksize = (512 / self.s) * self.s
             end = self.datasize
             all = True
         else:
             if end:
                 blockstart = i * self.s
                 end = end * self.s
                 blocksize = end - blockstart
             else:
                 blockstart = (i & ~63) * self.s
                 blocksize = self.s * 64
                 end = blockstart + blocksize
         while blockstart < end:
             self.loadblock(blockstart, blocksize)
             blockstart += blocksize
         if all: self.all = True
 
 class lazyindex(object):
     """a lazy version of the index array"""
     def __init__(self, parser):
         self.p = parser
     def __len__(self):
         return len(self.p.index)
     def load(self, pos):
         if pos < 0:
             pos += len(self.p.index)
         self.p.loadindex(pos)
         return self.p.index[pos]
     def __getitem__(self, pos):
         ret = self.p.index[pos] or self.load(pos)
         if isinstance(ret, str):
             ret = struct.unpack(self.p.indexformat, ret)
         return ret
     def __setitem__(self, pos, item):
         self.p.index[pos] = item
     def __delitem__(self, pos):
         del self.p.index[pos]
     def append(self, e):
         self.p.index.append(e)
 
 class lazymap(object):
     """a lazy version of the node map"""
     def __init__(self, parser):
         self.p = parser
     def load(self, key):
         n = self.p.findnode(key)
         if n == None:
             raise KeyError(key)
     def __contains__(self, key):
         if key in self.p.map:
             return True
         self.p.loadmap()
         return key in self.p.map
     def __iter__(self):
         yield nullid
         for i in xrange(self.p.l):
             ret = self.p.index[i]
             if not ret:
                 self.p.loadindex(i)
                 ret = self.p.index[i]
             if isinstance(ret, str):
                 ret = struct.unpack(self.p.indexformat, ret)
             yield ret[-1]
     def __getitem__(self, key):
         try:
             return self.p.map[key]
         except KeyError:
             try:
                 self.load(key)
                 return self.p.map[key]
             except KeyError:
                 raise KeyError("node " + hex(key))
     def __setitem__(self, key, val):
         self.p.map[key] = val
     def __delitem__(self, key):
         del self.p.map[key]
 
 class RevlogError(Exception): pass
 class LookupError(RevlogError): pass
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, includings its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
     """
     def __init__(self, opener, indexfile):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = indexfile[:-2] + ".d"
         self.opener = opener
 
         self.indexstat = None
         self.cache = None
         self.chunkcache = None
         self.defversion = REVLOG_DEFAULT_VERSION
         if hasattr(opener, "defversion"):
             self.defversion = opener.defversion
             if self.defversion & REVLOGNG:
                 self.defversion |= REVLOGNGINLINEDATA
         self.load()
 
     def load(self):
         v = self.defversion
         try:
             f = self.opener(self.indexfile)
             i = f.read(4)
             f.seek(0)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             i = ""
         else:
             try:
                 st = util.fstat(f)
             except AttributeError, inst:
                 st = None
             else:
                 oldst = self.indexstat
                 if (oldst and st.st_dev == oldst.st_dev
                     and st.st_ino == oldst.st_ino
                     and st.st_mtime == oldst.st_mtime
-                    and st.st_ctime == oldst.st_ctime):
+                    and st.st_ctime == oldst.st_ctime
+                    and st.st_size == oldst.st_size):
                     return
                 self.indexstat = st
             if len(i) > 0:
                 v = struct.unpack(versionformat, i)[0]
         flags = v & ~0xFFFF
         fmt = v & 0xFFFF
         if fmt == REVLOGV0:
             if flags:
                 raise RevlogError(_("index %s unknown flags %#04x for format v0")
                                   % (self.indexfile, flags >> 16))
         elif fmt == REVLOGNG:
             if flags & ~REVLOGNGINLINEDATA:
                 raise RevlogError(_("index %s unknown flags %#04x for revlogng")
                                   % (self.indexfile, flags >> 16))
         else:
             raise RevlogError(_("index %s unknown format %d")
                               % (self.indexfile, fmt))
         self.version = v
         if v == REVLOGV0:
             self.indexformat = indexformatv0
             shaoffset = v0shaoffset
         else:
             self.indexformat = indexformatng
             shaoffset = ngshaoffset
 
         if i:
             if (lazyparser.safe_to_use and not self.inlinedata() and
                 st and st.st_size > 10000):
                 # big index, let's parse it on demand
                 parser = lazyparser(f, st.st_size, self.indexformat, shaoffset)
                 self.index = lazyindex(parser)
                 self.nodemap = lazymap(parser)
             else:
                 self.parseindex(f, st)
             if self.version != REVLOGV0:
                 e = list(self.index[0])
                 type = self.ngtype(e[0])
                 e[0] = self.offset_type(0, type)
                 self.index[0] = e
         else:
             self.nodemap = {nullid: nullrev}
             self.index = []
 
 
     def parseindex(self, fp, st):
         s = struct.calcsize(self.indexformat)
         self.index = []
         self.nodemap =  {nullid: nullrev}
         inline = self.inlinedata()
         n = 0
         leftover = None
         while True:
             if st:
                 data = fp.read(65536)
             else:
                 # hack for httprangereader, it doesn't do partial reads well
                 data = fp.read()
             if not data:
                 break
             if n == 0 and self.inlinedata():
                 # cache the first chunk
                 self.chunkcache = (0, data)
             if leftover:
                 data = leftover + data
                 leftover = None
             off = 0
             l = len(data)
             while off < l:
                 if l - off < s:
                     leftover = data[off:]
                     break
                 cur = data[off:off + s]
                 off += s
                 e = struct.unpack(self.indexformat, cur)
                 self.index.append(e)
                 self.nodemap[e[-1]] = n
                 n += 1
                 if inline:
                     if e[1] < 0:
                         break
                     off += e[1]
                     if off > l:
                         # some things don't seek well, just read it
                         fp.read(off - l)
                         break
             if not st:
                 break
 
 
     def ngoffset(self, q):
         if q & 0xFFFF:
             raise RevlogError(_('%s: incompatible revision flag %x') %
                               (self.indexfile, q))
         return long(q >> 16)
 
     def ngtype(self, q):
         return int(q & 0xFFFF)
 
     def offset_type(self, offset, type):
         return long(long(offset) << 16 | type)
 
     def loadindex(self, start, end):
         """load a block of indexes all at once from the lazy parser"""
         if isinstance(self.index, lazyindex):
             self.index.p.loadindex(start, end)
 
     def loadindexmap(self):
         """loads both the map and the index from the lazy parser"""
         if isinstance(self.index, lazyindex):
             p = self.index.p
             p.loadindex()
             self.nodemap = p.map
 
     def loadmap(self):
         """loads the map from the lazy parser"""
         if isinstance(self.nodemap, lazymap):
             self.nodemap.p.loadmap()
             self.nodemap = self.nodemap.p.map
 
     def inlinedata(self): return self.version & REVLOGNGINLINEDATA
     def tip(self): return self.node(len(self.index) - 1)
     def count(self): return len(self.index)
     def node(self, rev):
         return rev == nullrev and nullid or self.index[rev][-1]
     def rev(self, node):
         try:
             return self.nodemap[node]
         except KeyError:
             raise LookupError(_('%s: no node %s') % (self.indexfile, hex(node)))
     def linkrev(self, node):
         return (node == nullid) and nullrev or self.index[self.rev(node)][-4]
     def parents(self, node):
         if node == nullid: return (nullid, nullid)
         r = self.rev(node)
         d = self.index[r][-3:-1]
         if self.version == REVLOGV0:
             return d
         return (self.node(d[0]), self.node(d[1]))
     def parentrevs(self, rev):
         if rev == nullrev:
             return (nullrev, nullrev)
         d = self.index[rev][-3:-1]
         if self.version == REVLOGV0:
             return (self.rev(d[0]), self.rev(d[1]))
         return d
     def start(self, rev):
         if rev == nullrev:
             return 0
         if self.version != REVLOGV0:
             return self.ngoffset(self.index[rev][0])
         return self.index[rev][0]
 
     def end(self, rev): return self.start(rev) + self.length(rev)
 
     def size(self, rev):
         """return the length of the uncompressed text for a given revision"""
         if rev == nullrev:
             return 0
         l = -1
         if self.version != REVLOGV0:
             l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(self.node(rev))
         return len(t)
 
         # alternate implementation, The advantage to this code is it
         # will be faster for a single revision.  But, the results are not
         # cached, so finding the size of every revision will be slower.
         """
         if self.cache and self.cache[1] == rev:
             return len(self.cache[2])
 
         base = self.base(rev)
         if self.cache and self.cache[1] >= base and self.cache[1] < rev:
             base = self.cache[1]
             text = self.cache[2]
         else:
             text = self.revision(self.node(base))
 
         l = len(text)
         for x in xrange(base + 1, rev + 1):
             l = mdiff.patchedsize(l, self.chunk(x))
         return l
         """
 
     def length(self, rev):
         if rev == nullrev:
             return 0
         else:
             return self.index[rev][1]
     def base(self, rev):
         if (rev == nullrev):
             return nullrev
         else:
             return self.index[rev][-5]
 
     def reachable(self, node, stop=None):
         """return a hash of all nodes ancestral to a given node, including
          the node itself, stopping when stop is matched"""
         reachable = {}
         visit = [node]
         reachable[node] = 1
         if stop:
             stopn = self.rev(stop)
         else:
             stopn = 0
         while visit:
             n = visit.pop(0)
             if n == stop:
                 continue
             if n == nullid:
                 continue
             for p in self.parents(n):
                 if self.rev(p) < stopn:
                     continue
                 if p not in reachable:
                     reachable[p] = 1
                     visit.append(p)
         return reachable
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a tuple containing three elements. Elements 1 and 2 contain
         a final list bases and heads after all the unreachable ones have been
         pruned.  Element 0 contains a topologically sorted list of all
 
         nodes that satisfy these constraints:
         1. All nodes must be descended from a node in roots (the nodes on
            roots are considered descended from themselves).
         2. All nodes must also be ancestors of a node in heads (the nodes in
            heads are considered to be their own ancestors).
 
         If roots is unspecified, nullid is assumed as the only root.
         If heads is unspecified, it is taken to be the output of the
         heads method (i.e. a list of all nodes in the repository that
         have no children)."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendent of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in xrange(0, self.count())],
                     [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = self.count() - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = {}
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, 0)
             # Start at the top and keep marking parents until we're done.
             nodestotag = heads.keys()
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendent of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors[n] = 1 # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.extend([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [n for n in roots if n in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(n) for n in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a 'set' (i.e. a dictionary where the
         # values don't matter.
         descendents = dict.fromkeys(roots, 1)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendents.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descedents, empty parents will look like
         # they're descendents.
         for r in xrange(max(lowestrev, 0), highestrev + 1):
             n = self.node(r)
             isdescendent = False
             if lowestrev == nullrev:  # Everybody is a descendent of nullid
                 isdescendent = True
             elif n in descendents:
                 # n is already a descendent
                 isdescendent = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendents before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendents, it's not a root.
                     if (p[0] in descendents) or (p[1] in descendents):
                         roots.pop(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendent if either of its parents are
                 # descendents.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendents) or (p[1] in descendents):
                     descendents[n] = 1
                     isdescendent = True
             if isdescendent and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendents and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = 1
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = 1
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [n for n in heads.iterkeys() if heads[n] != 0]
         roots = roots.keys()
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = dict.fromkeys([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = {startrev: 1}
         heads = {startrev: 1}
 
         parentrevs = self.parentrevs
         for r in xrange(startrev + 1, self.count()):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable[r] = 1
                     heads[r] = 1
                 if p in heads and p not in stoprevs:
                     del heads[p]
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in range(p + 1, self.count()):
             for pr in self.parentrevs(r):
                 if pr == p:
                     c.append(self.node(r))
         return c
 
     def _match(self, id):
         if isinstance(id, (long, int)):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 r = self.rev(node) # quick search the index
                 return node
             except LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if str(rev) != id: raise ValueError
             if rev < 0: rev = self.count() + rev
             if rev < 0 or rev >= self.count(): raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 r = self.rev(node)
                 return node
             except TypeError:
                 pass
 
     def _partialmatch(self, id):
         if len(id) < 40:
             try:
                 # hex(node)[:...]
                 bin_id = bin(id[:len(id) & ~1]) # grab an even number of digits
                 node = None
                 for n in self.nodemap:
                     if n.startswith(bin_id) and hex(n).startswith(id):
                         if node is not None:
                             raise LookupError(_("Ambiguous identifier"))
                         node = n
                 if node is not None:
                     return node
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
 
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise LookupError(_("No match found"))
 
     def cmp(self, node, text):
         """compare text with a given file revision"""
         p1, p2 = self.parents(node)
         return hash(text, p1, p2) != node
 
     def makenode(self, node, text):
         """calculate a file nodeid for text, descended or possibly
         unchanged from node"""
 
         if self.cmp(node, text):
             return hash(text, node, nullid)
         return node
 
     def diff(self, a, b):
         """return a delta between two revisions"""
         return mdiff.textdiff(a, b)
 
     def patches(self, t, pl):
         """apply a list of patches to a string"""
         return mdiff.patches(t, pl)
 
     def chunk(self, rev, df=None, cachelen=4096):
         start, length = self.start(rev), self.length(rev)
         inline = self.inlinedata()
         if inline:
             start += (rev + 1) * struct.calcsize(self.indexformat)
         end = start + length
         def loadcache(df):
             cache_length = max(cachelen, length) # 4k
             if not df:
                 if inline:
                     df = self.opener(self.indexfile)
                 else:
                     df = self.opener(self.datafile)
             df.seek(start)
             self.chunkcache = (start, df.read(cache_length))
 
         if not self.chunkcache:
             loadcache(df)
 
         cache_start = self.chunkcache[0]
         cache_end = cache_start + len(self.chunkcache[1])
         if start >= cache_start and end <= cache_end:
             # it is cached
             offset = start - cache_start
         else:
             loadcache(df)
             offset = 0
 
         #def checkchunk():
         #    df = self.opener(self.datafile)
         #    df.seek(start)
         #    return df.read(length)
         #assert s == checkchunk()
         return decompress(self.chunkcache[1][offset:offset + length])
 
     def delta(self, node):
         """return or calculate a delta between a node and its predecessor"""
         r = self.rev(node)
         return self.revdiff(r - 1, r)
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         b1 = self.base(rev1)
         b2 = self.base(rev2)
         if b1 == b2 and rev1 + 1 == rev2:
             return self.chunk(rev2)
         else:
             return self.diff(self.revision(self.node(rev1)),
                              self.revision(self.node(rev2)))
 
     def revision(self, node):
         """return an uncompressed revision of a given"""
         if node == nullid: return ""
         if self.cache and self.cache[0] == node: return self.cache[2]
 
         # look up what we need to read
         text = None
         rev = self.rev(node)
         base = self.base(rev)
 
         if self.inlinedata():
             # we probably have the whole chunk cached
             df = None
         else:
             df = self.opener(self.datafile)
 
         # do we have useful data cached?
         if self.cache and self.cache[1] >= base and self.cache[1] < rev:
             base = self.cache[1]
             text = self.cache[2]
             self.loadindex(base, rev + 1)
         else:
             self.loadindex(base, rev + 1)
             text = self.chunk(base, df=df)
 
         bins = []
         for r in xrange(base + 1, rev + 1):
             bins.append(self.chunk(r, df=df))
 
         text = self.patches(text, bins)
 
         p1, p2 = self.parents(node)
         if node != hash(text, p1, p2):
             raise RevlogError(_("integrity check failed on %s:%d")
                               % (self.datafile, rev))
 
         self.cache = (node, rev, text)
         return text
 
     def checkinlinesize(self, tr, fp=None):
         if not self.inlinedata():
             return
         if not fp:
             fp = self.opener(self.indexfile, 'r')
             fp.seek(0, 2)
         size = fp.tell()
         if size < 131072:
             return
         trinfo = tr.find(self.indexfile)
         if trinfo == None:
             raise RevlogError(_("%s not found in the transaction")
                               % self.indexfile)
 
         trindex = trinfo[2]
         dataoff = self.start(trindex)
 
         tr.add(self.datafile, dataoff)
         df = self.opener(self.datafile, 'w')
         calc = struct.calcsize(self.indexformat)
         for r in xrange(self.count()):
             start = self.start(r) + (r + 1) * calc
             length = self.length(r)
             fp.seek(start)
             d = fp.read(length)
             df.write(d)
         fp.close()
         df.close()
         fp = self.opener(self.indexfile, 'w', atomictemp=True)
         self.version &= ~(REVLOGNGINLINEDATA)
         if self.count():
             x = self.index[0]
             e = struct.pack(self.indexformat, *x)[4:]
             l = struct.pack(versionformat, self.version)
             fp.write(l)
             fp.write(e)
 
         for i in xrange(1, self.count()):
             x = self.index[i]
             e = struct.pack(self.indexformat, *x)
             fp.write(e)
 
         # if we don't call rename, the temp file will never replace the
         # real index
         fp.rename()
 
         tr.replace(self.indexfile, trindex * calc)
         self.chunkcache = None
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         d - an optional precomputed delta
         """
         if not self.inlinedata():
             dfh = self.opener(self.datafile, "a")
         else:
             dfh = None
         ifh = self.opener(self.indexfile, "a+")
         return self._addrevision(text, transaction, link, p1, p2, d, ifh, dfh)
 
     def _addrevision(self, text, transaction, link, p1, p2, d, ifh, dfh):
         if text is None: text = ""
         if p1 is None: p1 = self.tip()
         if p2 is None: p2 = nullid
 
         node = hash(text, p1, p2)
 
         if node in self.nodemap:
             return node
 
         n = self.count()
         t = n - 1
 
         if n:
             base = self.base(t)
             start = self.start(base)
             end = self.end(t)
             if not d:
                 prev = self.revision(self.tip())
                 d = self.diff(prev, text)
             data = compress(d)
             l = len(data[1]) + len(data[0])
             dist = end - start + l
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if not n or dist > len(text) * 2:
             data = compress(text)
             l = len(data[1]) + len(data[0])
             base = n
         else:
             base = self.base(t)
 
         offset = 0
         if t >= 0:
             offset = self.end(t)
 
         if self.version == REVLOGV0:
             e = (offset, l, base, link, p1, p2, node)
         else:
             e = (self.offset_type(offset, 0), l, len(text),
                  base, link, self.rev(p1), self.rev(p2), node)
 
         self.index.append(e)
         self.nodemap[node] = n
         entry = struct.pack(self.indexformat, *e)
 
         if not self.inlinedata():
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, n * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             dfh.flush()
         else:
             ifh.seek(0, 2)
             transaction.add(self.indexfile, ifh.tell(), self.count() - 1)
 
         if len(self.index) == 1 and self.version != REVLOGV0:
             l = struct.pack(versionformat, self.version)
             ifh.write(l)
             entry = entry[4:]
 
         ifh.write(entry)
 
         if self.inlinedata():
             ifh.write(data[0])
             ifh.write(data[1])
             self.checkinlinesize(transaction, ifh)
 
         self.cache = (node, n, text)
         return node
 
     def ancestor(self, a, b):
         """calculate the least common ancestor of nodes a and b"""
 
         def parents(rev):
             return [p for p in self.parentrevs(rev) if p != nullrev]
 
         c = ancestor.ancestor(self.rev(a), self.rev(b), parents)
         if c is None:
             return nullid
 
         return self.node(c)
 
     def group(self, nodelist, lookup, infocollect=None):
         """calculate a delta group
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. the first delta is
         parent(nodes[0]) -> nodes[0] the receiver is guaranteed to
         have this parent as it has all history before these
         changesets. parent is parent[0]
         """
         revs = [self.rev(n) for n in nodelist]
 
         # if we don't have any revisions touched by these changesets, bail
         if not revs:
             yield changegroup.closechunk()
             return
 
         # add the parent of the first rev
         p = self.parents(self.node(revs[0]))[0]
         revs.insert(0, self.rev(p))
 
         # build deltas
         for d in xrange(0, len(revs) - 1):
             a, b = revs[d], revs[d + 1]
             nb = self.node(b)
 
             if infocollect is not None:
                 infocollect(nb)
 
             d = self.revdiff(a, b)
             p = self.parents(nb)
             meta = nb + p[0] + p[1] + lookup(nb)
             yield changegroup.genchunk("%s%s" % (meta, d))
 
         yield changegroup.closechunk()
 
     def addgroup(self, revs, linkmapper, transaction, unique=0):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
         """
 
         #track the base of the current delta log
         r = self.count()
         t = r - 1
         node = None
 
         base = prev = nullrev
         start = end = textlen = 0
         if r:
             end = self.end(t)
 
         ifh = self.opener(self.indexfile, "a+")
         ifh.seek(0, 2)
         transaction.add(self.indexfile, ifh.tell(), self.count())
         if self.inlinedata():
             dfh = None
         else:
             transaction.add(self.datafile, end)
             dfh = self.opener(self.datafile, "a")
 
         # loop through our set of deltas
         chain = None
         for chunk in revs:
             node, p1, p2, cs = struct.unpack("20s20s20s20s", chunk[:80])
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 # if unique:
                 #    raise RevlogError(_("already have %s") % hex(node[:4]))
                 chain = node
                 continue
             delta = chunk[80:]
 
             for p in (p1, p2):
                 if not p in self.nodemap:
                     raise LookupError(_("unknown parent %s") % short(p))
 
             if not chain:
                 # retrieve the parent revision of the delta chain
                 chain = p1
                 if not chain in self.nodemap:
                     raise LookupError(_("unknown base %s") % short(chain[:4]))
 
             # full versions are inserted when the needed deltas become
             # comparable to the uncompressed text or when the previous
             # version is not the one we have a delta against. We use
             # the size of the previous full rev as a proxy for the
             # current size.
 
             if chain == prev:
                 tempd = compress(delta)
                 cdelta = tempd[0] + tempd[1]
                 textlen = mdiff.patchedsize(textlen, delta)
 
             if chain != prev or (end - start + len(cdelta)) > textlen * 2:
                 # flush our writes here so we can read it in revision
                 if dfh:
                     dfh.flush()
                 ifh.flush()
                 text = self.revision(chain)
                 text = self.patches(text, [delta])
                 chk = self._addrevision(text, transaction, link, p1, p2, None,
                                         ifh, dfh)
                 if not dfh and not self.inlinedata():
                     # addrevision switched from inline to conventional
                     # reopen the index
                     dfh = self.opener(self.datafile, "a")
                     ifh = self.opener(self.indexfile, "a")
                 if chk != node:
                     raise RevlogError(_("consistency error adding group"))
                 textlen = len(text)
             else:
                 if self.version == REVLOGV0:
                     e = (end, len(cdelta), base, link, p1, p2, node)
                 else:
                     e = (self.offset_type(end, 0), len(cdelta), textlen, base,
                          link, self.rev(p1), self.rev(p2), node)
                 self.index.append(e)
                 self.nodemap[node] = r
                 if self.inlinedata():
                     ifh.write(struct.pack(self.indexformat, *e))
                     ifh.write(cdelta)
                     self.checkinlinesize(transaction, ifh)
                     if not self.inlinedata():
                         dfh = self.opener(self.datafile, "a")
                         ifh = self.opener(self.indexfile, "a")
                 else:
                     dfh.write(cdelta)
                     ifh.write(struct.pack(self.indexformat, *e))
 
             t, r, chain, prev = r, r + 1, node, node
             base = self.base(t)
             start = self.start(base)
             end = self.end(t)
 
         return node
 
     def strip(self, rev, minlink):
         if self.count() == 0 or rev >= self.count():
             return
 
         if isinstance(self.index, lazyindex):
             self.loadindexmap()
 
         # When stripping away a revision, we need to make sure it
         # does not actually belong to an older changeset.
         # The minlink parameter defines the oldest revision
         # we're allowed to strip away.
         while minlink > self.index[rev][-4]:
             rev += 1
             if rev >= self.count():
                 return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self.inlinedata():
             df = self.opener(self.datafile, "a")
             df.truncate(end)
             end = rev * struct.calcsize(self.indexformat)
         else:
             end += rev * struct.calcsize(self.indexformat)
 
         indexf = self.opener(self.indexfile, "a")
         indexf.truncate(end)
 
         # then reset internal state in memory to forget those revisions
         self.cache = None
         self.chunkcache = None
         for x in xrange(rev, self.count()):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:]
 
     def checksize(self):
         expected = 0
         if self.count():
             expected = self.end(self.count() - 1)
 
         try:
             f = self.opener(self.datafile)
             f.seek(0, 2)
             actual = f.tell()
             dd = actual - expected
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             s = struct.calcsize(self.indexformat)
             i = actual / s
             di = actual - (i * s)
             if self.inlinedata():
                 databytes = 0
                 for r in xrange(self.count()):
                     databytes += self.length(r)
                 dd = 0
                 di = actual - self.count() * s - databytes
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
 

tests/test-tags

@@ -1,107 +1,124 b''
 #!/bin/sh
 
 mkdir t
 cd t
 hg init
 hg id
 echo a > a
 hg add a
 hg commit -m "test" -d "1000000 0"
 hg co
 hg identify
 T=`hg tip --debug | head -n 1 | cut -d : -f 3`
 hg tag -l "This is a local tag with a really long name!"
 hg tags
 rm .hg/localtags
 echo "$T first" > .hgtags
 cat .hgtags
 hg add .hgtags
 hg commit -m "add tags" -d "1000000 0"
 hg tags
 hg identify
 echo bb > a
 hg status
 hg identify
 hg co first
 hg id
 hg -v id
 hg status
 echo 1 > b
 hg add b
 hg commit -m "branch" -d "1000000 0"
 hg id
 hg merge 1
 hg id
 hg status
 
 hg commit -m "merge" -d "1000000 0"
 
 # create fake head, make sure tag not visible afterwards
 cp .hgtags tags
 hg tag -d "1000000 0" last
 hg rm .hgtags
 hg commit -m "remove" -d "1000000 0"
 
 mv tags .hgtags
 hg add .hgtags
 hg commit -m "readd" -d "1000000 0"
 
 hg tags
 
 # invalid tags
 echo "spam" >> .hgtags
 echo >> .hgtags
 echo "foo bar" >> .hgtags
 echo "$T invalid" | sed "s/..../a5a5/" >> .hg/localtags
 hg commit -m "tags" -d "1000000 0"
 
 # report tag parse error on other head
 hg up 3
 echo 'x y' >> .hgtags
 hg commit -m "head" -d "1000000 0"
 
 hg tags
 hg tip
 
 # test tag precedence rules
 cd ..
 hg init t2
 cd t2
 echo foo > foo
 hg add foo
 hg ci -m 'add foo' -d '1000000 0'      # rev 0
 hg tag -d '1000000 0' bar              # rev 1
 echo >> foo
 hg ci -m 'change foo 1' -d '1000000 0' # rev 2
 hg up -C 1
 hg tag -r 1 -d '1000000 0' -f bar      # rev 3
 hg up -C 1
 echo >> foo
 hg ci -m 'change foo 2' -d '1000000 0' # rev 4
 hg tags
 
 # test tag removal
 hg tag --remove -d '1000000 0' bar 
 hg tip
 hg tags
 
 # test tag rank
 cd ..
 hg init t3
 cd t3
 echo foo > foo
 hg add foo
 hg ci -m 'add foo' -d '1000000 0'       # rev 0
 hg tag -d '1000000 0' -f bar            # rev 1 bar -> 0
 hg tag -d '1000000 0' -f bar            # rev 2 bar -> 1
 hg tag -d '1000000 0' -fr 0 bar         # rev 3 bar -> 0
 hg tag -d '1000000 0' -fr 1 bar         # rev 3 bar -> 1
 hg tag -d '1000000 0' -fr 0 bar         # rev 4 bar -> 0
 hg tags
 hg co 3
 echo barbar > foo
 hg ci -m 'change foo' -d '1000000 0'    # rev 0
 hg tags
 
 hg tag -d '1000000 0' -r 3 bar         # should complain
-hg tags
  No newline at end of file
+hg tags
+
+# test tag rank with 3 heads
+cd ..
+hg init t4
+cd t4
+echo foo > foo
+hg add
+hg ci -m 'add foo' -d '0 0'                # rev 0
+hg tag -d '0 0' bar                        # rev 1 bar -> 0
+hg tag -d '0 0' -f bar                     # rev 2 bar -> 1
+hg up -qC 0
+hg tag -d '0 0' -fr 2 bar                  # rev 3 bar -> 2
+hg tags
+hg up -qC 0
+hg tag -d '0 0' -m 'retag rev 0' -fr 0 bar # rev 4 bar -> 0, but bar stays at 2
+echo % bar should still point to rev 2
+hg tags

tests/test-tags.out

@@ -1,59 +1,65 b''
 unknown
 0 files updated, 0 files merged, 0 files removed, 0 files unresolved
 0acdaf898367 tip
 tip                                0:0acdaf898367
 This is a local tag with a really long name!     0:0acdaf898367
 0acdaf8983679e0aac16e811534eb49d7ee1f2b4 first
 tip                                1:8a3ca90d111d
 first                              0:0acdaf898367
 8a3ca90d111d tip
 M a
 8a3ca90d111d+ tip
 0 files updated, 0 files merged, 1 files removed, 0 files unresolved
 0acdaf898367+ first
 0acdaf898367+ first
 M a
 8216907a933d tip
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 (branch merge, don't forget to commit)
 8216907a933d+8a3ca90d111d+ tip
 M .hgtags
 tip                                6:e2174d339386
 first                              0:0acdaf898367
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 .hgtags@c071f74ab5eb, line 2: cannot parse entry
 .hgtags@c071f74ab5eb, line 4: node 'foo' is not well formed
 .hgtags@4ca6f1b1a68c, line 2: node 'x' is not well formed
 localtags, line 1: tag 'invalid' refers to unknown node
 tip                                8:4ca6f1b1a68c
 first                              0:0acdaf898367
 changeset:   8:4ca6f1b1a68c
 .hgtags@c071f74ab5eb, line 2: cannot parse entry
 .hgtags@c071f74ab5eb, line 4: node 'foo' is not well formed
 .hgtags@4ca6f1b1a68c, line 2: node 'x' is not well formed
 localtags, line 1: tag 'invalid' refers to unknown node
 tag:         tip
 parent:      3:b2ef3841386b
 user:        test
 date:        Mon Jan 12 13:46:40 1970 +0000
 summary:     head
 
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 tip                                4:36195b728445
 bar                                1:b204a97e6e8d
 changeset:   5:57e1983b4a60
 tag:         tip
 user:        test
 date:        Mon Jan 12 13:46:40 1970 +0000
 summary:     Removed tag bar
 
 tip                                5:57e1983b4a60
 tip                                5:d8bb4d1eff25
 bar                                0:b409d9da318e
 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 tip                                6:b5ff9d142648
 bar                                0:b409d9da318e
 abort: a tag named bar already exists (use -f to force)
 tip                                6:b5ff9d142648
 bar                                0:b409d9da318e
+adding foo
+tip                                3:ca8479b4351c
+bar                                2:72b852876a42
+% bar should still point to rev 2
+tip                                4:40af5d225513
+bar                                2:72b852876a42