subrepos: add function for iterating over ctx subrepos

mercurial/cmdutil.py

@@ -1,1300 +1,1293 b''
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import hex, bin, nullid, nullrev, short
 from i18n import _
 import os, sys, errno, re, glob, tempfile
 import util, templater, patch, error, encoding, templatekw
 import match as matchmod
-import similar, revset
+import similar, revset, subrepo
 
 revrangesep = ':'
 
 def parsealiases(cmd):
     return cmd.lstrip("^").split("|")
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
     for e in table.keys():
         aliases = parsealiases(e)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith("debug") or found.startswith("debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = choice.keys()
         clist.sort()
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return choice.values()[0]
 
     raise error.UnknownCommand(cmd)
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, ".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 def bail_if_changed(repo):
     if repo.dirstate.parents()[1] != nullid:
         raise util.Abort(_('outstanding uncommitted merge'))
     modified, added, removed, deleted = repo.status()[:4]
     if modified or added or removed or deleted:
         raise util.Abort(_("outstanding uncommitted changes"))
 
 def logmessage(opts):
     """ get the log message according to -m and -l option """
     message = opts.get('message')
     logfile = opts.get('logfile')
 
     if message and logfile:
         raise util.Abort(_('options --message and --logfile are mutually '
                            'exclusive'))
     if not message and logfile:
         try:
             if logfile == '-':
                 message = sys.stdin.read()
             else:
                 message = open(logfile).read()
         except IOError, inst:
             raise util.Abort(_("can't read commit message '%s': %s") %
                              (logfile, inst.strerror))
     return message
 
 def loglimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get('limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise util.Abort(_('limit must be a positive integer'))
         if limit <= 0:
             raise util.Abort(_('limit must be positive'))
     else:
         limit = None
     return limit
 
 def revpair(repo, revs):
     '''return pair of nodes, given list of revisions. second item can
     be None, meaning use working dir.'''
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             val = defval
         return repo.lookup(val)
 
     if not revs:
         return repo.dirstate.parents()[0], None
     end = None
     if len(revs) == 1:
         if revrangesep in revs[0]:
             start, end = revs[0].split(revrangesep, 1)
             start = revfix(repo, start, 0)
             end = revfix(repo, end, len(repo) - 1)
         else:
             start = revfix(repo, revs[0], None)
     elif len(revs) == 2:
         if revrangesep in revs[0] or revrangesep in revs[1]:
             raise util.Abort(_('too many revisions specified'))
         start = revfix(repo, revs[0], None)
         end = revfix(repo, revs[1], None)
     else:
         raise util.Abort(_('too many revisions specified'))
     return start, end
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             return defval
         return repo.changelog.rev(repo.lookup(val))
 
     seen, l = set(), []
     for spec in revs:
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         try:
             if revrangesep in spec:
                 start, end = spec.split(revrangesep, 1)
                 start = revfix(repo, start, 0)
                 end = revfix(repo, end, len(repo) - 1)
                 step = start > end and -1 or 1
                 for rev in xrange(start, end + step, step):
                     if rev in seen:
                         continue
                     seen.add(rev)
                     l.append(rev)
                 continue
             elif spec and spec in repo: # single unquoted rev
                 rev = revfix(repo, spec, None)
                 if rev in seen:
                     continue
                 seen.add(rev)
                 l.append(rev)
                 continue
         except error.RepoLookupError:
             pass
 
         # fall through to new-style queries if old-style fails
         m = revset.match(spec)
         for r in m(repo, range(len(repo))):
             if r not in seen:
                 l.append(r)
         seen.update(l)
 
     return l
 
 def make_filename(repo, pat, node,
                   total=None, seqno=None, revwidth=None, pathname=None):
     node_expander = {
         'H': lambda: hex(node),
         'R': lambda: str(repo.changelog.rev(node)),
         'h': lambda: short(node),
         }
     expander = {
         '%': lambda: '%',
         'b': lambda: os.path.basename(repo.root),
         }
 
     try:
         if node:
             expander.update(node_expander)
         if node:
             expander['r'] = (lambda:
                     str(repo.changelog.rev(node)).zfill(revwidth or 0))
         if total is not None:
             expander['N'] = lambda: str(total)
         if seqno is not None:
             expander['n'] = lambda: str(seqno)
         if total is not None and seqno is not None:
             expander['n'] = lambda: str(seqno).zfill(len(str(total)))
         if pathname is not None:
             expander['s'] = lambda: os.path.basename(pathname)
             expander['d'] = lambda: os.path.dirname(pathname) or '.'
             expander['p'] = lambda: pathname
 
         newname = []
         patlen = len(pat)
         i = 0
         while i < patlen:
             c = pat[i]
             if c == '%':
                 i += 1
                 c = pat[i]
                 c = expander[c]()
             newname.append(c)
             i += 1
         return ''.join(newname)
     except KeyError, inst:
         raise util.Abort(_("invalid format spec '%%%s' in output filename") %
                          inst.args[0])
 
 def make_file(repo, pat, node=None,
               total=None, seqno=None, revwidth=None, mode='wb', pathname=None):
 
     writable = 'w' in mode or 'a' in mode
 
     if not pat or pat == '-':
         return writable and sys.stdout or sys.stdin
     if hasattr(pat, 'write') and writable:
         return pat
     if hasattr(pat, 'read') and 'r' in mode:
         return pat
     return open(make_filename(repo, pat, node, total, seqno, revwidth,
                               pathname),
                 mode)
 
 def expandpats(pats):
     if not util.expandglobs:
         return list(pats)
     ret = []
     for p in pats:
         kind, name = matchmod._patsplit(p, None)
         if kind is None:
             try:
                 globbed = glob.glob(name)
             except re.error:
                 globbed = [name]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(p)
     return ret
 
 def match(repo, pats=[], opts={}, globbed=False, default='relpath'):
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
     m = matchmod.match(repo.root, repo.getcwd(), pats,
                        opts.get('include'), opts.get('exclude'), default,
                        auditor=repo.auditor)
     def badfn(f, msg):
         repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
     m.bad = badfn
     return m
 
 def matchall(repo):
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files):
     return matchmod.exact(repo.root, repo.getcwd(), files)
 
 def addremove(repo, pats=[], opts={}, dry_run=None, similarity=None):
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
     # we'd use status here, except handling of symlinks and ignore is tricky
     added, unknown, deleted, removed = [], [], [], []
     audit_path = util.path_auditor(repo.root)
     m = match(repo, pats, opts)
     for abs in repo.walk(m):
         target = repo.wjoin(abs)
         good = True
         try:
             audit_path(abs)
         except:
             good = False
         rel = m.rel(abs)
         exact = m.exact(abs)
         if good and abs not in repo.dirstate:
             unknown.append(abs)
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('adding %s\n') % ((pats and rel) or abs))
         elif repo.dirstate[abs] != 'r' and (not good or not os.path.lexists(target)
             or (os.path.isdir(target) and not os.path.islink(target))):
             deleted.append(abs)
             if repo.ui.verbose or not exact:
                 repo.ui.status(_('removing %s\n') % ((pats and rel) or abs))
         # for finding renames
         elif repo.dirstate[abs] == 'r':
             removed.append(abs)
         elif repo.dirstate[abs] == 'a':
             added.append(abs)
     copies = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo,
                 added + unknown, removed + deleted, similarity):
             if repo.ui.verbose or not m.exact(old) or not m.exact(new):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (m.rel(old), m.rel(new), score * 100))
             copies[new] = old
 
     if not dry_run:
         wctx = repo[None]
         wlock = repo.wlock()
         try:
             wctx.remove(deleted)
             wctx.add(unknown)
             for new, old in copies.iteritems():
                 wctx.copy(old, new)
         finally:
             wlock.release()
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get("after")
     dryrun = opts.get("dry_run")
     wctx = repo[None]
 
     def walkpat(pat):
         srcs = []
         badstates = after and '?' or '?r'
         m = match(repo, [pat], opts, globbed=True)
         for abs in repo.walk(m):
             state = repo.dirstate[abs]
             rel = m.rel(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == '?':
                     ui.warn(_('%s: not copying - file is not managed\n') % rel)
                 if exact and state == 'r':
                     ui.warn(_('%s: not copying - file has been marked for'
                               ' remove\n') % rel)
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = util.canonpath(repo.root, cwd, otarget)
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(_('%s: not overwriting - %s collides with %s\n') %
                     (reltarget, repo.pathto(abssrc, cwd),
                      repo.pathto(prevsrc, cwd)))
             return
 
         # check for overwrites
         exists = os.path.exists(target)
         if not after and exists or after and state in 'mn':
             if not opts['force']:
                 ui.warn(_('%s: not overwriting - file exists\n') %
                         reltarget)
                 return
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(_('%s: not recording move - %s does not exist\n') %
                             (relsrc, reltarget))
                 else:
                     ui.warn(_('%s: not recording copy - %s does not exist\n') %
                             (relsrc, reltarget))
                 return
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or '.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 util.copyfile(src, target)
             except IOError, inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_('%s: deleted in working copy\n') % relsrc)
                 else:
                     ui.warn(_('%s: cannot copy - %s\n') %
                             (relsrc, inst.strerror))
                     return True # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_('moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_('copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         origsrc = repo.dirstate.copied(abssrc) or abssrc
         if abstarget == origsrc: # copying back a copy?
             if state not in 'mn' and not dryrun:
                 repo.dirstate.normallookup(abstarget)
         else:
             if repo.dirstate[origsrc] == 'a' and origsrc == abssrc:
                 if not ui.quiet:
                     ui.warn(_("%s has not been committed yet, so no copy "
                               "data will be stored for %s.\n")
                             % (repo.pathto(origsrc, cwd), reltarget))
                 if repo.dirstate[abstarget] in '?r' and not dryrun:
                     wctx.add([abstarget])
             elif not dryrun:
                 wctx.copy(origsrc, abstarget)
 
         if rename and not dryrun:
             wctx.remove([abssrc], not after)
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = util.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(os.sep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(dest,
                                          os.path.basename(util.localpath(p)))
         else:
             abspfx = util.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.exists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(os.sep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(os.sep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest,
                                              util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(dest,
                                         os.path.basename(util.localpath(p)))
                 else:
                     res = lambda p: dest
         return res
 
 
     pats = expandpats(pats)
     if not pats:
         raise util.Abort(_('no source or destination specified'))
     if len(pats) == 1:
         raise util.Abort(_('no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise util.Abort(_('with multiple sources, destination must be an '
                                'existing directory'))
         if util.endswithsep(dest):
             raise util.Abort(_('destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise util.Abort(_('no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     if errors:
         ui.warn(_('(consider using --after)\n'))
 
     return errors != 0
 
 def service(opts, parentfn=None, initfn=None, runfn=None, logfile=None,
     runargs=None, appendpid=False):
     '''Run a command as a service.'''
 
     if opts['daemon'] and not opts['daemon_pipefds']:
         # Signal child process startup with file removal
         lockfd, lockpath = tempfile.mkstemp(prefix='hg-service-')
         os.close(lockfd)
         try:
             if not runargs:
                 runargs = util.hgcmd() + sys.argv[1:]
             runargs.append('--daemon-pipefds=%s' % lockpath)
             # Don't pass --cwd to the child process, because we've already
             # changed directory.
             for i in xrange(1, len(runargs)):
                 if runargs[i].startswith('--cwd='):
                     del runargs[i]
                     break
                 elif runargs[i].startswith('--cwd'):
                     del runargs[i:i + 2]
                     break
             def condfn():
                 return not os.path.exists(lockpath)
             pid = util.rundetached(runargs, condfn)
             if pid < 0:
                 raise util.Abort(_('child process failed to start'))
         finally:
             try:
                 os.unlink(lockpath)
             except OSError, e:
                 if e.errno != errno.ENOENT:
                     raise
         if parentfn:
             return parentfn(pid)
         else:
             return
 
     if initfn:
         initfn()
 
     if opts['pid_file']:
         mode = appendpid and 'a' or 'w'
         fp = open(opts['pid_file'], mode)
         fp.write(str(os.getpid()) + '\n')
         fp.close()
 
     if opts['daemon_pipefds']:
         lockpath = opts['daemon_pipefds']
         try:
             os.setsid()
         except AttributeError:
             pass
         os.unlink(lockpath)
         util.hidewindow()
         sys.stdout.flush()
         sys.stderr.flush()
 
         nullfd = os.open(util.nulldev, os.O_RDWR)
         logfilefd = nullfd
         if logfile:
             logfilefd = os.open(logfile, os.O_RDWR | os.O_CREAT | os.O_APPEND)
         os.dup2(nullfd, 0)
         os.dup2(logfilefd, 1)
         os.dup2(logfilefd, 2)
         if nullfd not in (0, 1, 2):
             os.close(nullfd)
         if logfile and logfilefd not in (0, 1, 2):
             os.close(logfilefd)
 
     if runfn:
         return runfn()
 
 def export(repo, revs, template='hg-%h.patch', fp=None, switch_parent=False,
            opts=None):
     '''export changesets as hg patches.'''
 
     total = len(revs)
     revwidth = max([len(str(rev)) for rev in revs])
 
     def single(rev, seqno, fp):
         ctx = repo[rev]
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()
         if switch_parent:
             parents.reverse()
         prev = (parents and parents[0]) or nullid
 
         if not fp:
             fp = make_file(repo, template, node, total=total, seqno=seqno,
                            revwidth=revwidth, mode='ab')
         if fp != sys.stdout and hasattr(fp, 'name'):
             repo.ui.note("%s\n" % fp.name)
 
         fp.write("# HG changeset patch\n")
         fp.write("# User %s\n" % ctx.user())
         fp.write("# Date %d %d\n" % ctx.date())
         if branch and branch != 'default':
             fp.write("# Branch %s\n" % branch)
         fp.write("# Node ID %s\n" % hex(node))
         fp.write("# Parent  %s\n" % hex(prev))
         if len(parents) > 1:
             fp.write("# Parent  %s\n" % hex(parents[1]))
         fp.write(ctx.description().rstrip())
         fp.write("\n\n")
 
         for chunk in patch.diff(repo, prev, node, opts=opts):
             fp.write(chunk)
 
     for seqno, rev in enumerate(revs):
         single(rev, seqno + 1, fp)
 
 def diffordiffstat(ui, repo, diffopts, node1, node2, match,
                    changes=None, stat=False, fp=None, prefix='',
                    listsubrepos=False):
     '''show diff or diffstat.'''
     if fp is None:
         write = ui.write
     else:
         def write(s, **kw):
             fp.write(s)
 
     if stat:
         diffopts = diffopts.copy(context=0)
         width = 80
         if not ui.plain():
             width = util.termwidth()
         chunks = patch.diff(repo, node1, node2, match, changes, diffopts,
                             prefix=prefix)
         for chunk, label in patch.diffstatui(util.iterlines(chunks),
                                              width=width,
                                              git=diffopts.git):
             write(chunk, label=label)
     else:
         for chunk, label in patch.diffui(repo, node1, node2, match,
                                          changes, diffopts, prefix=prefix):
             write(chunk, label=label)
 
     if listsubrepos:
         ctx1 = repo[node1]
         ctx2 = repo[node2]
-        # Create a (subpath, ctx) mapping where we prefer subpaths
-        # from ctx1. The subpaths from ctx2 are important when the
-        # .hgsub file has been modified (in ctx2) but not yet
-        # committed (in ctx1).
-        subpaths = dict.fromkeys(ctx2.substate, ctx2)
-        subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
-        for subpath, ctx in subpaths.iteritems():
-            sub = ctx.sub(subpath)
+        for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
             if node2 is not None:
                 node2 = bin(ctx2.substate[subpath][1])
             submatch = matchmod.narrowmatcher(subpath, match)
             sub.diff(diffopts, node2, submatch, changes=changes,
                      stat=stat, fp=fp, prefix=prefix)
 
 class changeset_printer(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, patch, diffopts, buffered):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self.patch = patch
         self.diffopts = diffopts
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
 
     def flush(self, rev):
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
             return 1
         return 0
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, matchfn=None, **props):
         if self.buffered:
             self.ui.pushbuffer()
             self._show(ctx, copies, matchfn, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer(labeled=True)
         else:
             self._show(ctx, copies, matchfn, props)
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         rev = ctx.rev()
 
         if self.ui.quiet:
             self.ui.write("%d:%s\n" % (rev, short(changenode)),
                           label='log.node')
             return
 
         log = self.repo.changelog
         date = util.datestr(ctx.date())
 
         hexfunc = self.ui.debugflag and hex or short
 
         parents = [(p, hexfunc(log.node(p)))
                    for p in self._meaningful_parentrevs(log, rev)]
 
         self.ui.write(_("changeset:   %d:%s\n") % (rev, hexfunc(changenode)),
                       label='log.changeset')
 
         branch = ctx.branch()
         # don't show the default branch name
         if branch != 'default':
             branch = encoding.tolocal(branch)
             self.ui.write(_("branch:      %s\n") % branch,
                           label='log.branch')
         for tag in self.repo.nodetags(changenode):
             self.ui.write(_("tag:         %s\n") % tag,
                           label='log.tag')
         for parent in parents:
             self.ui.write(_("parent:      %d:%s\n") % parent,
                           label='log.parent')
 
         if self.ui.debugflag:
             mnode = ctx.manifestnode()
             self.ui.write(_("manifest:    %d:%s\n") %
                           (self.repo.manifest.rev(mnode), hex(mnode)),
                           label='ui.debug log.manifest')
         self.ui.write(_("user:        %s\n") % ctx.user(),
                       label='log.user')
         self.ui.write(_("date:        %s\n") % date,
                       label='log.date')
 
         if self.ui.debugflag:
             files = self.repo.status(log.parents(changenode)[0], changenode)[:3]
             for key, value in zip([_("files:"), _("files+:"), _("files-:")],
                                   files):
                 if value:
                     self.ui.write("%-12s %s\n" % (key, " ".join(value)),
                                   label='ui.debug log.files')
         elif ctx.files() and self.ui.verbose:
             self.ui.write(_("files:       %s\n") % " ".join(ctx.files()),
                           label='ui.note log.files')
         if copies and self.ui.verbose:
             copies = ['%s (%s)' % c for c in copies]
             self.ui.write(_("copies:      %s\n") % ' '.join(copies),
                           label='ui.note log.copies')
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 self.ui.write(_("extra:       %s=%s\n")
                               % (key, value.encode('string_escape')),
                               label='ui.debug log.extra')
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(_("description:\n"),
                               label='ui.note log.description')
                 self.ui.write(description,
                               label='ui.note log.description')
                 self.ui.write("\n\n")
             else:
                 self.ui.write(_("summary:     %s\n") %
                               description.splitlines()[0],
                               label='log.summary')
         self.ui.write("\n")
 
         self.showpatch(changenode, matchfn)
 
     def showpatch(self, node, matchfn):
         if not matchfn:
             matchfn = self.patch
         if matchfn:
             stat = self.diffopts.get('stat')
             diff = self.diffopts.get('patch')
             diffopts = patch.diffopts(self.ui, self.diffopts)
             prev = self.repo.changelog.parents(node)[0]
             if stat:
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=True)
             if diff:
                 if stat:
                     self.ui.write("\n")
                 diffordiffstat(self.ui, self.repo, diffopts, prev, node,
                                match=matchfn, stat=False)
             self.ui.write("\n")
 
     def _meaningful_parentrevs(self, log, rev):
         """Return list of meaningful (or all if debug) parentrevs for rev.
 
         For merges (two non-nullrev revisions) both parents are meaningful.
         Otherwise the first parent revision is considered meaningful if it
         is not the preceding revision.
         """
         parents = log.parentrevs(rev)
         if not self.ui.debugflag and parents[1] == nullrev:
             if parents[0] >= rev - 1:
                 parents = []
             else:
                 parents = [parents[0]]
         return parents
 
 
 class changeset_templater(changeset_printer):
     '''format changeset information.'''
 
     def __init__(self, ui, repo, patch, diffopts, mapfile, buffered):
         changeset_printer.__init__(self, ui, repo, patch, diffopts, buffered)
         formatnode = ui.debugflag and (lambda x: x) or (lambda x: x[:12])
         defaulttempl = {
             'parent': '{rev}:{node|formatnode} ',
             'manifest': '{rev}:{node|formatnode}',
             'file_copy': '{name} ({source})',
             'extra': '{key}={value|stringescape}'
             }
         # filecopy is preserved for compatibility reasons
         defaulttempl['filecopy'] = defaulttempl['file_copy']
         self.t = templater.templater(mapfile, {'formatnode': formatnode},
                                      cache=defaulttempl)
         self.cache = {}
 
     def use_template(self, t):
         '''set template string to use'''
         self.t.cache['changeset'] = t
 
     def _meaningful_parentrevs(self, ctx):
         """Return list of meaningful (or all if debug) parentrevs for rev.
         """
         parents = ctx.parents()
         if len(parents) > 1:
             return parents
         if self.ui.debugflag:
             return [parents[0], self.repo['null']]
         if parents[0].rev() >= ctx.rev() - 1:
             return []
         return parents
 
     def _show(self, ctx, copies, matchfn, props):
         '''show a single changeset or file revision'''
 
         showlist = templatekw.showlist
 
         # showparents() behaviour depends on ui trace level which
         # causes unexpected behaviours at templating level and makes
         # it harder to extract it in a standalone function. Its
         # behaviour cannot be changed so leave it here for now.
         def showparents(**args):
             ctx = args['ctx']
             parents = [[('rev', p.rev()), ('node', p.hex())]
                        for p in self._meaningful_parentrevs(ctx)]
             return showlist('parent', parents, **args)
 
         props = props.copy()
         props.update(templatekw.keywords)
         props['parents'] = showparents
         props['templ'] = self.t
         props['ctx'] = ctx
         props['repo'] = self.repo
         props['revcache'] = {'copies': copies}
         props['cache'] = self.cache
 
         # find correct templates for current mode
 
         tmplmodes = [
             (True, None),
             (self.ui.verbose, 'verbose'),
             (self.ui.quiet, 'quiet'),
             (self.ui.debugflag, 'debug'),
         ]
 
         types = {'header': '', 'footer':'', 'changeset': 'changeset'}
         for mode, postfix  in tmplmodes:
             for type in types:
                 cur = postfix and ('%s_%s' % (type, postfix)) or type
                 if mode and cur in self.t:
                     types[type] = cur
 
         try:
 
             # write header
             if types['header']:
                 h = templater.stringify(self.t(types['header'], **props))
                 if self.buffered:
                     self.header[ctx.rev()] = h
                 else:
                     if self.lastheader != h:
                         self.lastheader = h
                         self.ui.write(h)
 
             # write changeset metadata, then patch if requested
             key = types['changeset']
             self.ui.write(templater.stringify(self.t(key, **props)))
             self.showpatch(ctx.node(), matchfn)
 
             if types['footer']:
                 if not self.footer:
                     self.footer = templater.stringify(self.t(types['footer'],
                                                       **props))
 
         except KeyError, inst:
             msg = _("%s: no key named '%s'")
             raise util.Abort(msg % (self.t.mapfile, inst.args[0]))
         except SyntaxError, inst:
             raise util.Abort('%s: %s' % (self.t.mapfile, inst.args[0]))
 
 def show_changeset(ui, repo, opts, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changeset_printer() is done.
     """
     # options
     patch = False
     if opts.get('patch') or opts.get('stat'):
         patch = matchall(repo)
 
     tmpl = opts.get('template')
     style = None
     if tmpl:
         tmpl = templater.parsestring(tmpl, quoted=False)
     else:
         style = opts.get('style')
 
     # ui settings
     if not (tmpl or style):
         tmpl = ui.config('ui', 'logtemplate')
         if tmpl:
             tmpl = templater.parsestring(tmpl)
         else:
             style = util.expandpath(ui.config('ui', 'style', ''))
 
     if not (tmpl or style):
         return changeset_printer(ui, repo, patch, opts, buffered)
 
     mapfile = None
     if style and not tmpl:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = (templater.templatepath('map-cmdline.' + mapfile)
                        or templater.templatepath(mapfile))
             if mapname:
                 mapfile = mapname
 
     try:
         t = changeset_templater(ui, repo, patch, opts, mapfile, buffered)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
     if tmpl:
         t.use_template(tmpl)
     return t
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = util.matchdate(date)
     m = matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(_("Found revision %s from %s\n") %
                       (rev, util.datestr(results[rev])))
             return str(rev)
 
     raise util.Abort(_("revision matching date not found"))
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     def increasing_windows(start, end, windowsize=8, sizelimit=512):
         if start < end:
             while start < end:
                 yield start, min(windowsize, end - start)
                 start += windowsize
                 if windowsize < sizelimit:
                     windowsize *= 2
         else:
             while start > end:
                 yield start, min(windowsize, start - end - 1)
                 start -= windowsize
                 if windowsize < sizelimit:
                     windowsize *= 2
 
     follow = opts.get('follow') or opts.get('follow_first')
 
     if not len(repo):
         return []
 
     if follow:
         defrange = '%s:0' % repo['.'].rev()
     else:
         defrange = '-1:0'
     revs = revrange(repo, opts['rev'] or [defrange])
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or (match.files() and opts.get('removed'))
     fncache = {}
     change = util.cachefunc(repo.changectx)
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if not slowpath and not match.files():
         # No files, no patterns.  Display all revs.
         wanted = set(revs)
     copies = []
 
     if not slowpath:
         # We only have to read through the filelog to find wanted revisions
 
         minrev, maxrev = min(revs), max(revs)
         def filerevgen(filelog, last):
             """
             Only files, no patterns.  Check the history of each file.
 
             Examines filelog entries within minrev, maxrev linkrev range
             Returns an iterator yielding (linkrev, parentlinkrevs, copied)
             tuples in backwards order
             """
             cl_count = len(repo)
             revs = []
             for j in xrange(0, last + 1):
                 linkrev = filelog.linkrev(j)
                 if linkrev < minrev:
                     continue
                 # only yield rev for which we have the changelog, it can
                 # happen while doing "hg log" during a pull or commit
                 if linkrev > maxrev or linkrev >= cl_count:
                     break
 
                 parentlinkrevs = []
                 for p in filelog.parentrevs(j):
                     if p != nullrev:
                         parentlinkrevs.append(filelog.linkrev(p))
                 n = filelog.node(j)
                 revs.append((linkrev, parentlinkrevs,
                              follow and filelog.renamed(n)))
 
             return reversed(revs)
         def iterfiles():
             for filename in match.files():
                 yield filename, None
             for filename_node in copies:
                 yield filename_node
         for file_, node in iterfiles():
             filelog = repo.file(file_)
             if not len(filelog):
                 if node is None:
                     # A zero count may be a directory or deleted file, so
                     # try to find matching entries on the slow path.
                     if follow:
                         raise util.Abort(
                             _('cannot follow nonexistent file: "%s"') % file_)
                     slowpath = True
                     break
                 else:
                     continue
 
             if node is None:
                 last = len(filelog) - 1
             else:
                 last = filelog.rev(node)
 
 
             # keep track of all ancestors of the file
             ancestors = set([filelog.linkrev(last)])
 
             # iterate from latest to oldest revision
             for rev, flparentlinkrevs, copied in filerevgen(filelog, last):
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
                 fncache.setdefault(rev, []).append(file_)
                 wanted.add(rev)
                 if copied:
                     copies.append(copied)
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise util.Abort(_('can only follow copies/renames for explicit '
                                'filenames'))
 
         # The slow path checks files modified in every changeset.
         for i in sorted(revs):
             ctx = change(i)
             matches = filter(match, ctx.files())
             if matches:
                 fncache[i] = matches
                 wanted.add(i)
 
     class followfilter(object):
         def __init__(self, onlyfirst=False):
             self.startrev = nullrev
             self.roots = set()
             self.onlyfirst = onlyfirst
 
         def match(self, rev):
             def realparents(rev):
                 if self.onlyfirst:
                     return repo.changelog.parentrevs(rev)[0:1]
                 else:
                     return filter(lambda x: x != nullrev,
                                   repo.changelog.parentrevs(rev))
 
             if self.startrev == nullrev:
                 self.startrev = rev
                 return True
 
             if rev > self.startrev:
                 # forward: all descendants
                 if not self.roots:
                     self.roots.add(self.startrev)
                 for parent in realparents(rev):
                     if parent in self.roots:
                         self.roots.add(rev)
                         return True
             else:
                 # backwards: all parents
                 if not self.roots:
                     self.roots.update(realparents(self.startrev))
                 if rev in self.roots:
                     self.roots.remove(rev)
                     self.roots.update(realparents(rev))
                     return True
 
             return False
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get('prune', ()):
         rev = repo.changelog.rev(repo.lookup(rev))
         ff = followfilter()
         stop = min(revs[0], revs[-1])
         for x in xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted.discard(x)
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and not match.files():
             ff = followfilter(onlyfirst=opts.get('follow_first'))
             def want(rev):
                 return ff.match(rev) and rev in wanted
         else:
             def want(rev):
                 return rev in wanted
 
         for i, window in increasing_windows(0, len(revs)):
             nrevs = [rev for rev in revs[i:i + window] if want(rev)]
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
                     def fns_generator():
                         for f in ctx.files():
                             if match(f):
                                 yield f
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
     return iterate()
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get('date')
     if date:
         opts['date'] = util.parsedate(date)
     message = logmessage(opts)
 
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get('addremove'):
         addremove(repo, pats, opts)
 
     return commitfunc(ui, repo, message, match(repo, pats, opts), opts)
 
 def commiteditor(repo, ctx, subs):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(repo, ctx, subs)
 
 def commitforceeditor(repo, ctx, subs):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append("")
     edittext.append("") # Empty line between message and comments.
     edittext.append(_("HG: Enter commit message."
                       "  Lines beginning with 'HG:' are removed."))
     edittext.append(_("HG: Leave message empty to abort commit."))
     edittext.append("HG: --")
     edittext.append(_("HG: user: %s") % ctx.user())
     if ctx.p2():
         edittext.append(_("HG: branch merge"))
     if ctx.branch():
         edittext.append(_("HG: branch '%s'")
                         % encoding.tolocal(ctx.branch()))
     edittext.extend([_("HG: subrepo %s") % s for s in subs])
     edittext.extend([_("HG: added %s") % f for f in added])
     edittext.extend([_("HG: changed %s") % f for f in modified])
     edittext.extend([_("HG: removed %s") % f for f in removed])
     if not added and not modified and not removed:
         edittext.append(_("HG: no files changed"))
     edittext.append("")
     # run editor in the repository root
     olddir = os.getcwd()
     os.chdir(repo.root)
     text = repo.ui.edit("\n".join(edittext), ctx.user())
     text = re.sub("(?m)^HG:.*\n", "", text)
     os.chdir(olddir)
 
     if not text.strip():
         raise util.Abort(_("empty commit message"))
 
     return text

mercurial/localrepo.py

@@ -1,1870 +1,1863 b''
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup, subrepo, discovery, pushkey
 import changelog, dirstate, filelog, manifest, context
 import lock, transaction, store, encoding
 import util, extensions, hook, error
 import match as matchmod
 import merge as mergemod
 import tags as tagsmod
 import url as urlmod
 from lock import release
 import weakref, errno, os, time, inspect
 propertycache = util.propertycache
 
 class localrepository(repo.repository):
     capabilities = set(('lookup', 'changegroupsubset', 'branchmap', 'pushkey'))
     supported = set('revlogv1 store fncache shared parentdelta'.split())
 
     def __init__(self, baseui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(util.expandpath(path))
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.auditor = util.path_auditor(self.root, self._checknested)
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
         self.baseui = baseui
         self.ui = baseui.copy()
 
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     util.makedirs(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if self.ui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     if self.ui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 if self.ui.configbool('format', 'parentdelta', False):
                     requirements.append("parentdelta")
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             requirements = set()
             try:
                 requirements = set(self.opener("requires").read().splitlines())
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
             for r in requirements - self.supported:
                 raise error.RepoError(_("requirement '%s' not supported") % r)
 
         self.sharedpath = self.path
         try:
             s = os.path.realpath(self.opener("sharedpath").read())
             if not os.path.exists(s):
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(requirements, self.sharedpath, util.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
         self.sopener.options = {}
         if 'parentdelta' in requirements:
             self.sopener.options['parentdelta'] = 1
 
         # These two define the set of tags for this repository.  _tags
         # maps tag name to node; _tagtypes maps tag name to 'global' or
         # 'local'.  (Global tags are defined by .hgtags across all
         # heads, and local tags are defined in .hg/localtags.)  They
         # constitute the in-memory cache of tags.
         self._tags = None
         self._tagtypes = None
 
         self._branchcache = None  # in UTF-8
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = os.sep.join(parts)
             if prefix in ctx.substate:
                 if prefix == subpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
 
     @propertycache
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         self.sopener.options['defversion'] = c.version
         return c
 
     @propertycache
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @propertycache
     def dirstate(self):
         return dirstate.dirstate(self.opener, self.ui, self.root)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             return bool(self.lookup(changeid))
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, names, node, message, local, user, date, extra={}):
         if isinstance(names, str):
             allchars = names
             names = (names,)
         else:
             allchars = ''.join(names)
         for c in self.tag_disallowed:
             if c in allchars:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if self._tagtypes and name in self._tagtypes:
                     old = self._tags.get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError:
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self._tags is None:
             (self._tags, self._tagtypes) = self._findtags()
 
         return self._tags
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         self.tags()
 
         return self._tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().iteritems():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in sorted(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().iteritems():
                 self.nodetagscache.setdefault(n, []).append(t)
             for tags in self.nodetagscache.itervalues():
                 tags.sort()
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             ctxgen = (self[r] for r in xrange(lrev + 1, tiprev + 1))
             self._updatebranchcache(partial, ctxgen)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def updatebranchcache(self):
         tip = self.changelog.tip()
         if self._branchcache is not None and self._branchcachetip == tip:
             return self._branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._branchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._branchcache = partial
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         self.updatebranchcache()
         return self._branchcache
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             tip = heads[-1]
             for h in reversed(heads):
                 if 'close' not in self.changelog.read(h)[5]:
                     tip = h
                     break
             bt[bn] = tip
         return bt
 
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branchheads.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
                 if not l:
                     continue
                 node, label = l.split(" ", 1)
                 partial.setdefault(label.strip(), []).append(bin(node))
         except KeyboardInterrupt:
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branchheads.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, nodes in branches.iteritems():
                 for node in nodes:
                     f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, ctxgen):
         # collect new branch entries
         newbranches = {}
         for c in ctxgen:
             newbranches.setdefault(c.branch(), []).append(c.node())
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newnodes in newbranches.iteritems():
             bheads = partial.setdefault(branch, [])
             bheads.extend(newnodes)
             if len(bheads) <= 1:
                 continue
             # starting from tip means fewer passes over reachable
             while newnodes:
                 latest = newnodes.pop()
                 if latest not in bheads:
                     continue
                 minbhrev = self[min([self[bh].rev() for bh in bheads])].node()
                 reachable = self.changelog.reachable(latest, minbhrev)
                 reachable.remove(latest)
                 bheads = [b for b in bheads if b not in reachable]
             partial[branch] = bheads
 
     def lookup(self, key):
         if isinstance(key, int):
             return self.changelog.node(key)
         elif key == '.':
             return self.dirstate.parents()[0]
         elif key == 'null':
             return nullid
         elif key == 'tip':
             return self.changelog.tip()
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
 
         # can't find key, check if it might have come from damaged dirstate
         if key in self.dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(key))
         try:
             if len(key) == 20:
                 key = hex(key)
         except:
             pass
         raise error.RepoLookupError(_("unknown revision '%s'") % key)
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
 
     def _filter(self, filter, filename, data):
         self._loadfilter(filter)
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self, desc):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise error.RepoError(
                 _("abandoned transaction found - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
         self.opener("journal.desc", "w").write("%d\n%s\n" % (len(self), desc))
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch")),
                    (self.join("journal.desc"), self.join("undo.desc"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         lock = self.lock()
         try:
             if os.path.exists(self.sjoin("journal")):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"),
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self, dryrun=False):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 try:
                     args = self.opener("undo.desc", "r").read().splitlines()
                     if len(args) >= 3 and self.ui.verbose:
                         desc = _("rolling back to revision %s"
                                  " (undo %s: %s)\n") % (
                                  int(args[0]) - 1, args[1], args[2])
                     elif len(args) >= 2:
                         desc = _("rolling back to revision %s (undo %s)\n") % (
                                  int(args[0]) - 1, args[1])
                 except IOError:
                     desc = _("rolling back unknown transaction\n")
                 self.ui.status(desc)
                 if dryrun:
                     return
                 transaction.rollback(self.sopener, self.sjoin("undo"),
                                      self.ui.warn)
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 try:
                     branch = self.opener("undo.branch").read()
                     self.dirstate.setbranch(branch)
                 except IOError:
                     self.ui.warn(_("Named branch could not be reset, "
                                    "current branch still is: %s\n")
                                  % encoding.tolocal(self.dirstate.branch()))
                 self.invalidate()
                 self.dirstate.invalidate()
                 self.destroyed()
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(lock, wlock)
 
     def invalidatecaches(self):
         self._tags = None
         self._tagtypes = None
         self.nodetagscache = None
         self._branchcache = None # in UTF-8
         self._branchcachetip = None
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if a in self.__dict__:
                 delattr(self, a)
         self.invalidatecaches()
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)'''
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
         Use this before modifying files in .hg.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(" %s: searching for copy revision for %s\n" %
                               (fname, cfname))
                 for ancestor in self['.'].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
             meta["copy"] = cfname
             meta["copyrev"] = hex(crev)
             fparent1, fparent2 = nullid, newfparent
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 != fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
 
         def fail(f, msg):
             raise util.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.dir = vdirs.append
             match.bad = fail
 
         wlock = self.wlock()
         try:
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if (not force and merge and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             changes = self.status(match=match, clean=force)
             if force:
                 changes[0].extend(changes[6]) # mq may commit unchanged files
 
             # check subrepos
             subs = []
             removedsubs = set()
             for p in wctx.parents():
                 removedsubs.update(s for s in p.substate if match(s))
             for s in wctx.substate:
                 removedsubs.discard(s)
                 if match(s) and wctx.sub(s).dirty():
                     subs.append(s)
             if (subs or removedsubs):
                 if (not match('.hgsub') and
                     '.hgsub' in (wctx.modified() + wctx.added())):
                     raise util.Abort(_("can't commit subrepos without .hgsub"))
                 if '.hgsubstate' not in changes[0]:
                     changes[0].insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force and match.files():
                 matched = set(changes[0] + changes[1] + changes[2])
 
                 for f in match.files():
                     if f == '.' or f in matched or f in wctx.substate:
                         continue
                     if f in changes[3]: # missing
                         fail(f, _('file not found!'))
                     if f in vdirs: # visited directory
                         d = f + '/'
                         for mf in matched:
                             if mf.startswith(d):
                                 break
                         else:
                             fail(f, _("no match under directory!"))
                     elif f not in self.dirstate:
                         fail(f, _("file not tracked!"))
 
             if (not force and not extra.get("close") and not merge
                 and not (changes[0] or changes[1] or changes[2])
                 and wctx.branch() == wctx.p1().branch()):
                 return None
 
             ms = mergemod.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
 
             cctx = context.workingctx(self, text, user, date, extra, changes)
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # commit subs
             if subs or removedsubs:
                 state = wctx.substate.copy()
                 for s in sorted(subs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.relpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     state[s] = (state[s][0], sr)
                 subrepo.writestate(self, state)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfile = self.opener('last-message.txt', 'wb')
             msgfile.write(cctx._text)
             msgfile.close()
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1, parent2=hookp2)
                 ret = self.commitctx(cctx, True)
             except:
                 if edited:
                     msgfn = self.pathto(msgfile.name[len(self.root)+1:])
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
 
             # update dirstate and mergestate
             for f in changes[0] + changes[1]:
                 self.dirstate.normal(f)
             for f in changes[2]:
                 self.dirstate.forget(f)
             self.dirstate.setparents(ret)
             ms.reset()
         finally:
             wlock.release()
 
         self.hook("commit", node=hex(ret), parent1=hookp1, parent2=hookp2)
         return ret
 
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = ctx.removed()
         p1, p2 = ctx.p1(), ctx.p2()
         m1 = p1.manifest().copy()
         m2 = p2.manifest()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             # check in files
             new = {}
             changed = []
             linkrev = len(self)
             for f in sorted(ctx.modified() + ctx.added()):
                 self.ui.note(f + "\n")
                 try:
                     fctx = ctx[f]
                     new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                               changed)
                     m1.set(f, fctx.flags())
                 except OSError, inst:
                     self.ui.warn(_("trouble committing %s!\n") % f)
                     raise
                 except IOError, inst:
                     errcode = getattr(inst, 'errno', errno.ENOENT)
                     if error or errcode and errcode != errno.ENOENT:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     else:
                         removed.append(f)
 
             # update manifest
             m1.update(new)
             removed = [f for f in sorted(removed) if f in m1 or f in m2]
             drop = [f for f in removed if f in m1]
             for f in drop:
                 del m1[f]
             mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                    p2.manifestnode(), (new, drop))
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, changed + removed, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             tr.close()
 
             if self._branchcache:
                 self.updatebranchcache()
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.'''
         # XXX it might be nice if we could take the list of destroyed
         # nodes, but I don't see an easy way for rollback() to do that
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidatecaches()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or matchmod.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 if f not in ctx1:
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
             match.bad = bad
 
         if working: # we need to scan the working dir
             subrepos = []
             if '.hgsub' in self.dirstate:
                 subrepos = ctx1.substate.keys()
             s = self.dirstate.status(match, subrepos, listignored,
                                      listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f])):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     if listclean:
                         clean += fixup
 
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn])))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
 
         if listsubrepos:
-            # Create a (subpath, ctx) mapping where we prefer subpaths
-            # from ctx1. The subpaths from ctx2 are important when the
-            # .hgsub file has been modified (in ctx2) but not yet
-            # committed (in ctx1).
-            subpaths = dict.fromkeys(ctx2.substate, ctx2)
-            subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
-            for subpath, ctx in subpaths.iteritems():
-                sub = ctx.sub(subpath)
+            for subpath, sub in subrepo.itersubrepos(ctx1, ctx2):
                 if working:
                     rev2 = None
                 else:
                     rev2 = ctx2.substate[subpath][1]
                 try:
                     submatch = matchmod.narrowmatcher(subpath, match)
                     s = sub.status(rev2, match=submatch, ignored=listignored,
                                    clean=listclean, unknown=listunknown,
                                    listsubrepos=True)
                     for rfiles, sfiles in zip(r, s):
                         rfiles.extend("%s/%s" % (subpath, f) for f in sfiles)
                 except error.LookupError:
                     self.ui.status(_("skipping missing subrepository: %s\n")
                                    % subpath)
 
         [l.sort() for l in r]
         return r
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads]
         return [n for (r, n) in sorted(heads)]
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches[branch]))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         if not closed:
             bheads = [h for h in bheads if
                       ('close' not in self.changelog.read(h)[5])]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             tmp = discovery.findcommonincoming(self, remote, heads=heads,
                                                force=force)
             common, fetch, rheads = tmp
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
             elif heads is None and remote.capable('changegroupsubset'):
                 # issue1320, avoid a race if remote changed after discovery
                 heads = rheads
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if not remote.capable('changegroupsubset'):
                     raise util.Abort(_("partial pull cannot be done because "
                                        "other repository doesn't support "
                                        "changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url(), lock=lock)
         finally:
             lock.release()
 
     def push(self, remote, force=False, revs=None, newbranch=False):
         '''Push outgoing changesets (limited by revs) from the current
         repository to remote. Return an integer:
           - 0 means HTTP error *or* nothing to push
           - 1 means we pushed and remote head count is unchanged *or*
             we have outgoing changesets but refused to push
           - other values as described by addchangegroup()
         '''
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         lock = None
         unbundle = remote.capable('unbundle')
         if not unbundle:
             lock = remote.lock()
         try:
             ret = discovery.prepush(self, remote, force, revs, newbranch)
             if ret[0] is None:
                 # and here we return 0 for "nothing to push" or 1 for
                 # "something to push but I refuse"
                 return ret[1]
 
             cg, remote_heads = ret
             if unbundle:
                 # local repo finds heads on server, finds out what revs it must
                 # push.  once revs transferred, if server finds it has
                 # different heads (someone else won commit/push race), server
                 # aborts.
                 if force:
                     remote_heads = ['force']
                 # ssh: return remote's addchangegroup()
                 # http: return remote's addchangegroup() or 0 for error
                 return remote.unbundle(cg, remote_heads, 'push')
             else:
                 # we return an integer indicating remote head count change
                 return remote.addchangegroup(cg, 'push', self.url(), lock=lock)
         finally:
             if lock is not None:
                 lock.release()
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug("list of changesets:\n")
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source, extranodes=None):
         """Compute a changegroup consisting of all the nodes that are
         descendents of any of the bases and ancestors of any of the heads.
         Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # Compute the list of changesets in this changegroup.
         # 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.
         if not bases:
             bases = [nullid]
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
 
         if extranodes is None:
             # can we go through the fast path ?
             heads.sort()
             allheads = self.heads()
             allheads.sort()
             if heads == allheads:
                 return self._changegroup(msng_cl_lst, source)
 
         # slow path
         self.hook('preoutgoing', throw=True, source=source)
 
         self.changegroupinfo(msng_cl_lst, source)
 
         # We assume that all ancestors of bases are known
         commonrevs = set(cl.ancestors(*[cl.rev(n) for n in bases]))
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r - 1 in mnfst.parentrevs(r):
                     # If the previous rev is one of the parents,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.iteritems():
                         # And if the file is in the list of files we care
                         # about.
                         if f in changedfiles:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
             return collect_msng_filenodes
 
         # 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(revlog, missingnodes):
             hasset = set()
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in missingnodes:
                 clrev = revlog.linkrev(revlog.rev(n))
                 if clrev in commonrevs:
                     hasset.add(n)
             for n in hasset:
                 missingnodes.pop(n, None)
             for r in revlog.ancestors(*[revlog.rev(n) for n in hasset]):
                 missingnodes.pop(revlog.node(r), None)
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = set()
             collect = changegroup.collector(cl, msng_mnfst_set, 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, collect)
             for cnt, chnk in enumerate(group):
                 yield chnk
                 self.ui.progress(_('bundling changes'), cnt, unit=_('chunks'))
             self.ui.progress(_('bundling changes'), None)
 
             prune(mnfst, msng_mnfst_set)
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(key=mnfst.rev)
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst,
                                 lambda mnode: msng_mnfst_set[mnode],
                                 filenode_collector(changedfiles))
             for cnt, chnk in enumerate(group):
                 yield chnk
                 self.ui.progress(_('bundling manifests'), cnt, unit=_('chunks'))
             self.ui.progress(_('bundling manifests'), None)
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     msng_filenode_set.setdefault(fname, {})
                     changedfiles.add(fname)
             # Go through all our files in order sorted by name.
             cnt = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 missingfnodes = msng_filenode_set.pop(fname, {})
                 prune(filerevlog, missingfnodes)
                 add_extra_nodes(fname, missingfnodes)
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if missingfnodes:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision # (topological order)
                     nodeiter = list(missingfnodes)
                     nodeiter.sort(key=filerevlog.rev)
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(nodeiter,
                                              lambda fnode: missingfnodes[fnode])
                     for chnk in group:
                         self.ui.progress(
                             _('bundling files'), cnt, item=fname, unit=_('chunks'))
                         cnt += 1
                         yield chnk
             # Signal that no more groups are left.
             yield changegroup.closechunk()
             self.ui.progress(_('bundling files'), None)
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     def _changegroup(self, nodes, source):
         """Compute the changegroup of all nodes that we have that a recipient
         doesn't.  Return a chunkbuffer object whose read() method will return
         successive changegroup chunks.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         nodes is the set of nodes to send"""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         revset = set([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(log):
             for r in log:
                 if log.linkrev(r) in revset:
                     yield log.node(r)
 
         def lookuplinkrev_func(revlog):
             def lookuplinkrev(n):
                 return cl.node(revlog.linkrev(revlog.rev(n)))
             return lookuplinkrev
 
         def gengroup():
             '''yield a sequence of changegroup chunks (strings)'''
             # construct a list of all changed files
             changedfiles = set()
             mmfs = {}
             collect = changegroup.collector(cl, mmfs, changedfiles)
 
             for cnt, chnk in enumerate(cl.group(nodes, identity, collect)):
                 self.ui.progress(_('bundling changes'), cnt, unit=_('chunks'))
                 yield chnk
             self.ui.progress(_('bundling changes'), None)
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for cnt, chnk in enumerate(mnfst.group(nodeiter,
                                                    lookuplinkrev_func(mnfst))):
                 self.ui.progress(_('bundling manifests'), cnt, unit=_('chunks'))
                 yield chnk
             self.ui.progress(_('bundling manifests'), None)
 
             cnt = 0
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuplinkrev_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         self.ui.progress(
                             _('bundling files'), cnt, item=fname, unit=_('chunks'))
                         cnt += 1
                         yield chnk
             self.ui.progress(_('bundling files'), None)
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False, lock=None):
         """Add the changegroup returned by source.read() to this repo.
         srctype is a string like 'push', 'pull', or 'unbundle'.  url is
         the URL of the repo where this changegroup is coming from.
 
         Return an integer summarizing the change to this repo:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - fewer heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug("add changeset %s\n" % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
         efiles = set()
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction("\n".join([srctype, urlmod.hidepassword(url)]))
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             class prog(object):
                 step = _('changesets')
                 count = 1
                 ui = self.ui
                 total = None
                 def __call__(self):
                     self.ui.progress(self.step, self.count, unit=_('chunks'),
                                      total=self.total)
                     self.count += 1
             pr = prog()
             chunkiter = changegroup.chunkiter(source, progress=pr)
             if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
             for c in xrange(clstart, clend):
                 efiles.update(self[c].files())
             efiles = len(efiles)
             self.ui.progress(_('changesets'), None)
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             pr.step = _('manifests')
             pr.count = 1
             pr.total = changesets # manifests <= changesets
             chunkiter = changegroup.chunkiter(source, progress=pr)
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             self.manifest.addgroup(chunkiter, revmap, trp)
             self.ui.progress(_('manifests'), None)
 
             needfiles = {}
             if self.ui.configbool('server', 'validate', default=False):
                 # validate incoming csets have their manifests
                 for cset in xrange(clstart, clend):
                     mfest = self.changelog.read(self.changelog.node(cset))[0]
                     mfest = self.manifest.readdelta(mfest)
                     # store file nodes we must see
                     for f, n in mfest.iteritems():
                         needfiles.setdefault(f, set()).add(n)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             pr.step = 'files'
             pr.count = 1
             pr.total = efiles
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug("adding %s revisions\n" % f)
                 pr()
                 fl = self.file(f)
                 o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
                 if f in needfiles:
                     needs = needfiles[f]
                     for new in xrange(o, len(fl)):
                         n = fl.node(new)
                         if n in needs:
                             needs.remove(n)
                     if not needs:
                         del needfiles[f]
             self.ui.progress(_('files'), None)
 
             for f, needs in needfiles.iteritems():
                 fl = self.file(f)
                 for n in needs:
                     try:
                         fl.rev(n)
                     except error.LookupError:
                         raise util.Abort(
                             _('missing file data for %s:%s - run hg verify') %
                             (f, hex(n)))
 
             newheads = len(cl.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
         finally:
             tr.release()
             if lock:
                 lock.release()
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug("updating the branch cache\n")
             self.updatebranchcache()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             # for backwards compat, name was partially encoded
             ofp = self.sopener(store.decodedir(name), 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
     def pushkey(self, namespace, key, old, new):
         return pushkey.push(self, namespace, key, old, new)
 
     def listkeys(self, namespace):
         return pushkey.list(self, namespace)
 
 # 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/subrepo.py

@@ -1,482 +1,492 b''
 # subrepo.py - sub-repository handling for Mercurial
 #
 # Copyright 2009-2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import errno, os, re, xml.dom.minidom, shutil, urlparse, posixpath
 from i18n import _
 import config, util, node, error, cmdutil
 hg = None
 
 nullstate = ('', '', 'empty')
 
 def state(ctx, ui):
     """return a state dict, mapping subrepo paths configured in .hgsub
     to tuple: (source from .hgsub, revision from .hgsubstate, kind
     (key in types dict))
     """
     p = config.config()
     def read(f, sections=None, remap=None):
         if f in ctx:
             p.parse(f, ctx[f].data(), sections, remap, read)
         else:
             raise util.Abort(_("subrepo spec file %s not found") % f)
 
     if '.hgsub' in ctx:
         read('.hgsub')
 
     for path, src in ui.configitems('subpaths'):
         p.set('subpaths', path, src, ui.configsource('subpaths', path))
 
     rev = {}
     if '.hgsubstate' in ctx:
         try:
             for l in ctx['.hgsubstate'].data().splitlines():
                 revision, path = l.split(" ", 1)
                 rev[path] = revision
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
 
     state = {}
     for path, src in p[''].items():
         kind = 'hg'
         if src.startswith('['):
             if ']' not in src:
                 raise util.Abort(_('missing ] in subrepo source'))
             kind, src = src.split(']', 1)
             kind = kind[1:]
 
         for pattern, repl in p.items('subpaths'):
             # Turn r'C:\foo\bar' into r'C:\\foo\\bar' since re.sub
             # does a string decode.
             repl = repl.encode('string-escape')
             # However, we still want to allow back references to go
             # through unharmed, so we turn r'\\1' into r'\1'. Again,
             # extra escapes are needed because re.sub string decodes.
             repl = re.sub(r'\\\\([0-9]+)', r'\\\1', repl)
             try:
                 src = re.sub(pattern, repl, src, 1)
             except re.error, e:
                 raise util.Abort(_("bad subrepository pattern in %s: %s")
                                  % (p.source('subpaths', pattern), e))
 
         state[path] = (src.strip(), rev.get(path, ''), kind)
 
     return state
 
 def writestate(repo, state):
     """rewrite .hgsubstate in (outer) repo with these subrepo states"""
     repo.wwrite('.hgsubstate',
                 ''.join(['%s %s\n' % (state[s][1], s)
                          for s in sorted(state)]), '')
 
 def submerge(repo, wctx, mctx, actx):
     """delegated from merge.applyupdates: merging of .hgsubstate file
     in working context, merging context and ancestor context"""
     if mctx == actx: # backwards?
         actx = wctx.p1()
     s1 = wctx.substate
     s2 = mctx.substate
     sa = actx.substate
     sm = {}
 
     repo.ui.debug("subrepo merge %s %s %s\n" % (wctx, mctx, actx))
 
     def debug(s, msg, r=""):
         if r:
             r = "%s:%s:%s" % r
         repo.ui.debug("  subrepo %s: %s %s\n" % (s, msg, r))
 
     for s, l in s1.items():
         a = sa.get(s, nullstate)
         ld = l # local state with possible dirty flag for compares
         if wctx.sub(s).dirty():
             ld = (l[0], l[1] + "+")
         if wctx == actx: # overwrite
             a = ld
 
         if s in s2:
             r = s2[s]
             if ld == r or r == a: # no change or local is newer
                 sm[s] = l
                 continue
             elif ld == a: # other side changed
                 debug(s, "other changed, get", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
             elif ld[0] != r[0]: # sources differ
                 if repo.ui.promptchoice(
                     _(' subrepository sources for %s differ\n'
                       'use (l)ocal source (%s) or (r)emote source (%s)?')
                       % (s, l[0], r[0]),
                       (_('&Local'), _('&Remote')), 0):
                     debug(s, "prompt changed, get", r)
                     wctx.sub(s).get(r)
                     sm[s] = r
             elif ld[1] == a[1]: # local side is unchanged
                 debug(s, "other side changed, get", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
             else:
                 debug(s, "both sides changed, merge with", r)
                 wctx.sub(s).merge(r)
                 sm[s] = l
         elif ld == a: # remote removed, local unchanged
             debug(s, "remote removed, remove")
             wctx.sub(s).remove()
         else:
             if repo.ui.promptchoice(
                 _(' local changed subrepository %s which remote removed\n'
                   'use (c)hanged version or (d)elete?') % s,
                 (_('&Changed'), _('&Delete')), 0):
                 debug(s, "prompt remove")
                 wctx.sub(s).remove()
 
     for s, r in s2.items():
         if s in s1:
             continue
         elif s not in sa:
             debug(s, "remote added, get", r)
             mctx.sub(s).get(r)
             sm[s] = r
         elif r != sa[s]:
             if repo.ui.promptchoice(
                 _(' remote changed subrepository %s which local removed\n'
                   'use (c)hanged version or (d)elete?') % s,
                 (_('&Changed'), _('&Delete')), 0) == 0:
                 debug(s, "prompt recreate", r)
                 wctx.sub(s).get(r)
                 sm[s] = r
 
     # record merged .hgsubstate
     writestate(repo, sm)
 
 def relpath(sub):
     """return path to this subrepo as seen from outermost repo"""
     if not hasattr(sub, '_repo'):
         return sub._path
     parent = sub._repo
     while hasattr(parent, '_subparent'):
         parent = parent._subparent
     return sub._repo.root[len(parent.root)+1:]
 
 def _abssource(repo, push=False):
     """return pull/push path of repo - either based on parent repo
     .hgsub info or on the subrepos own config"""
     if hasattr(repo, '_subparent'):
         source = repo._subsource
         if source.startswith('/') or '://' in source:
             return source
         parent = _abssource(repo._subparent, push)
         if '://' in parent:
             if parent[-1] == '/':
                 parent = parent[:-1]
             r = urlparse.urlparse(parent + '/' + source)
             r = urlparse.urlunparse((r[0], r[1],
                                      posixpath.normpath(r[2]),
                                      r[3], r[4], r[5]))
             return r
         return posixpath.normpath(os.path.join(parent, repo._subsource))
     if push and repo.ui.config('paths', 'default-push'):
         return repo.ui.config('paths', 'default-push', repo.root)
     return repo.ui.config('paths', 'default', repo.root)
 
+def itersubrepos(ctx1, ctx2):
+    """find subrepos in ctx1 or ctx2"""
+    # Create a (subpath, ctx) mapping where we prefer subpaths from
+    # ctx1. The subpaths from ctx2 are important when the .hgsub file
+    # has been modified (in ctx2) but not yet committed (in ctx1).
+    subpaths = dict.fromkeys(ctx2.substate, ctx2)
+    subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
+    for subpath, ctx in sorted(subpaths.iteritems()):
+        yield subpath, ctx.sub(subpath)
+
 def subrepo(ctx, path):
     """return instance of the right subrepo class for subrepo in path"""
     # subrepo inherently violates our import layering rules
     # because it wants to make repo objects from deep inside the stack
     # so we manually delay the circular imports to not break
     # scripts that don't use our demand-loading
     global hg
     import hg as h
     hg = h
 
     util.path_auditor(ctx._repo.root)(path)
     state = ctx.substate.get(path, nullstate)
     if state[2] not in types:
         raise util.Abort(_('unknown subrepo type %s') % state[2])
     return types[state[2]](ctx, path, state[:2])
 
 # subrepo classes need to implement the following abstract class:
 
 class abstractsubrepo(object):
 
     def dirty(self):
         """returns true if the dirstate of the subrepo does not match
         current stored state
         """
         raise NotImplementedError
 
     def checknested(path):
         """check if path is a subrepository within this repository"""
         return False
 
     def commit(self, text, user, date):
         """commit the current changes to the subrepo with the given
         log message. Use given user and date if possible. Return the
         new state of the subrepo.
         """
         raise NotImplementedError
 
     def remove(self):
         """remove the subrepo
 
         (should verify the dirstate is not dirty first)
         """
         raise NotImplementedError
 
     def get(self, state):
         """run whatever commands are needed to put the subrepo into
         this state
         """
         raise NotImplementedError
 
     def merge(self, state):
         """merge currently-saved state with the new state."""
         raise NotImplementedError
 
     def push(self, force):
         """perform whatever action is analogous to 'hg push'
 
         This may be a no-op on some systems.
         """
         raise NotImplementedError
 
 
     def status(self, rev2, **opts):
         return [], [], [], [], [], [], []
 
     def diff(self, diffopts, node2, match, prefix, **opts):
         pass
 
 class hgsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         r = ctx._repo
         root = r.wjoin(path)
         create = False
         if not os.path.exists(os.path.join(root, '.hg')):
             create = True
             util.makedirs(root)
         self._repo = hg.repository(r.ui, root, create=create)
         self._repo._subparent = r
         self._repo._subsource = state[0]
 
         if create:
             fp = self._repo.opener("hgrc", "w", text=True)
             fp.write('[paths]\n')
 
             def addpathconfig(key, value):
                 fp.write('%s = %s\n' % (key, value))
                 self._repo.ui.setconfig('paths', key, value)
 
             defpath = _abssource(self._repo)
             defpushpath = _abssource(self._repo, True)
             addpathconfig('default', defpath)
             if defpath != defpushpath:
                 addpathconfig('default-push', defpushpath)
             fp.close()
 
     def status(self, rev2, **opts):
         try:
             rev1 = self._state[1]
             ctx1 = self._repo[rev1]
             ctx2 = self._repo[rev2]
             return self._repo.status(ctx1, ctx2, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_("warning: %s in %s\n")
                                % (inst, relpath(self)))
             return [], [], [], [], [], [], []
 
     def diff(self, diffopts, node2, match, prefix, **opts):
         try:
             node1 = node.bin(self._state[1])
             cmdutil.diffordiffstat(self._repo.ui, self._repo, diffopts,
                                    node1, node2, match,
                                    prefix=os.path.join(prefix, self._path),
                                    listsubrepos=True, **opts)
         except error.RepoLookupError, inst:
             self._repo.ui.warn(_("warning: %s in %s\n")
                                % (inst, relpath(self)))
 
     def dirty(self):
         r = self._state[1]
         if r == '':
             return True
         w = self._repo[None]
         if w.p1() != self._repo[r]: # version checked out change
             return True
         return w.dirty() # working directory changed
 
     def checknested(self, path):
         return self._repo._checknested(self._repo.wjoin(path))
 
     def commit(self, text, user, date):
         self._repo.ui.debug("committing subrepo %s\n" % relpath(self))
         n = self._repo.commit(text, user, date)
         if not n:
             return self._repo['.'].hex() # different version checked out
         return node.hex(n)
 
     def remove(self):
         # we can't fully delete the repository as it may contain
         # local-only history
         self._repo.ui.note(_('removing subrepo %s\n') % relpath(self))
         hg.clean(self._repo, node.nullid, False)
 
     def _get(self, state):
         source, revision, kind = state
         try:
             self._repo.lookup(revision)
         except error.RepoError:
             self._repo._subsource = source
             srcurl = _abssource(self._repo)
             self._repo.ui.status(_('pulling subrepo %s from %s\n')
                                  % (relpath(self), srcurl))
             other = hg.repository(self._repo.ui, srcurl)
             self._repo.pull(other)
 
     def get(self, state):
         self._get(state)
         source, revision, kind = state
         self._repo.ui.debug("getting subrepo %s\n" % self._path)
         hg.clean(self._repo, revision, False)
 
     def merge(self, state):
         self._get(state)
         cur = self._repo['.']
         dst = self._repo[state[1]]
         anc = dst.ancestor(cur)
         if anc == cur:
             self._repo.ui.debug("updating subrepo %s\n" % relpath(self))
             hg.update(self._repo, state[1])
         elif anc == dst:
             self._repo.ui.debug("skipping subrepo %s\n" % relpath(self))
         else:
             self._repo.ui.debug("merging subrepo %s\n" % relpath(self))
             hg.merge(self._repo, state[1], remind=False)
 
     def push(self, force):
         # push subrepos depth-first for coherent ordering
         c = self._repo['']
         subs = c.substate # only repos that are committed
         for s in sorted(subs):
             if not c.sub(s).push(force):
                 return False
 
         dsturl = _abssource(self._repo, True)
         self._repo.ui.status(_('pushing subrepo %s to %s\n') %
             (relpath(self), dsturl))
         other = hg.repository(self._repo.ui, dsturl)
         return self._repo.push(other, force)
 
 class svnsubrepo(abstractsubrepo):
     def __init__(self, ctx, path, state):
         self._path = path
         self._state = state
         self._ctx = ctx
         self._ui = ctx._repo.ui
 
     def _svncommand(self, commands, filename=''):
         path = os.path.join(self._ctx._repo.origroot, self._path, filename)
         cmd = ['svn'] + commands + [path]
         cmd = [util.shellquote(arg) for arg in cmd]
         cmd = util.quotecommand(' '.join(cmd))
         env = dict(os.environ)
         # Avoid localized output, preserve current locale for everything else.
         env['LC_MESSAGES'] = 'C'
         write, read, err = util.popen3(cmd, env=env, newlines=True)
         retdata = read.read()
         err = err.read().strip()
         if err:
             raise util.Abort(err)
         return retdata
 
     def _wcrev(self):
         output = self._svncommand(['info', '--xml'])
         doc = xml.dom.minidom.parseString(output)
         entries = doc.getElementsByTagName('entry')
         if not entries:
             return 0
         return int(entries[0].getAttribute('revision') or 0)
 
     def _wcchanged(self):
         """Return (changes, extchanges) where changes is True
         if the working directory was changed, and extchanges is
         True if any of these changes concern an external entry.
         """
         output = self._svncommand(['status', '--xml'])
         externals, changes = [], []
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             s = e.getElementsByTagName('wc-status')
             if not s:
                 continue
             item = s[0].getAttribute('item')
             props = s[0].getAttribute('props')
             path = e.getAttribute('path')
             if item == 'external':
                 externals.append(path)
             if (item not in ('', 'normal', 'unversioned', 'external')
                 or props not in ('', 'none')):
                 changes.append(path)
         for path in changes:
             for ext in externals:
                 if path == ext or path.startswith(ext + os.sep):
                     return True, True
         return bool(changes), False
 
     def dirty(self):
         if self._wcrev() == self._state[1] and not self._wcchanged()[0]:
             return False
         return True
 
     def commit(self, text, user, date):
         # user and date are out of our hands since svn is centralized
         changed, extchanged = self._wcchanged()
         if not changed:
             return self._wcrev()
         if extchanged:
             # Do not try to commit externals
             raise util.Abort(_('cannot commit svn externals'))
         commitinfo = self._svncommand(['commit', '-m', text])
         self._ui.status(commitinfo)
         newrev = re.search('Committed revision ([0-9]+).', commitinfo)
         if not newrev:
             raise util.Abort(commitinfo.splitlines()[-1])
         newrev = newrev.groups()[0]
         self._ui.status(self._svncommand(['update', '-r', newrev]))
         return newrev
 
     def remove(self):
         if self.dirty():
             self._ui.warn(_('not removing repo %s because '
                             'it has changes.\n' % self._path))
             return
         self._ui.note(_('removing subrepo %s\n') % self._path)
         shutil.rmtree(self._ctx.repo.join(self._path))
 
     def get(self, state):
         status = self._svncommand(['checkout', state[0], '--revision', state[1]])
         if not re.search('Checked out revision [0-9]+.', status):
             raise util.Abort(status.splitlines()[-1])
         self._ui.status(status)
 
     def merge(self, state):
         old = int(self._state[1])
         new = int(state[1])
         if new > old:
             self.get(state)
 
     def push(self, force):
         # push is a no-op for SVN
         return True
 
 types = {
     'hg': hgsubrepo,
     'svn': svnsubrepo,
     }