filectx: use cmp(self, fctx) instead of cmp(self, text)

This allows more flexibility in implementation, and in particular,
lets the context decide if revision text has to be loaded or not.

mercurial/context.py

@@ -1,1086 +1,1086
 # context.py - changeset and file context objects for mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import nullid, nullrev, short, hex
 from i18n import _
 import ancestor, bdiff, error, util, subrepo, patch
 import os, errno, stat
 
 propertycache = util.propertycache
 
 class changectx(object):
     """A changecontext object makes access to data related to a particular
     changeset convenient."""
     def __init__(self, repo, changeid=''):
         """changeid is a revision number, node, or tag"""
         if changeid == '':
             changeid = '.'
         self._repo = repo
         if isinstance(changeid, (long, int)):
             self._rev = changeid
             self._node = self._repo.changelog.node(changeid)
         else:
             self._node = self._repo.lookup(changeid)
             self._rev = self._repo.changelog.rev(self._node)
 
     def __str__(self):
         return short(self.node())
 
     def __int__(self):
         return self.rev()
 
     def __repr__(self):
         return "<changectx %s>" % str(self)
 
     def __hash__(self):
         try:
             return hash(self._rev)
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return self._rev == other._rev
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def __nonzero__(self):
         return self._rev != nullrev
 
     @propertycache
     def _changeset(self):
         return self._repo.changelog.read(self.node())
 
     @propertycache
     def _manifest(self):
         return self._repo.manifest.read(self._changeset[0])
 
     @propertycache
     def _manifestdelta(self):
         return self._repo.manifest.readdelta(self._changeset[0])
 
     @propertycache
     def _parents(self):
         p = self._repo.changelog.parentrevs(self._rev)
         if p[1] == nullrev:
             p = p[:-1]
         return [changectx(self._repo, x) for x in p]
 
     @propertycache
     def substate(self):
         return subrepo.state(self)
 
     def __contains__(self, key):
         return key in self._manifest
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def __iter__(self):
         for f in sorted(self._manifest):
             yield f
 
     def changeset(self):
         return self._changeset
     def manifest(self):
         return self._manifest
     def manifestnode(self):
         return self._changeset[0]
 
     def rev(self):
         return self._rev
     def node(self):
         return self._node
     def hex(self):
         return hex(self._node)
     def user(self):
         return self._changeset[1]
     def date(self):
         return self._changeset[2]
     def files(self):
         return self._changeset[3]
     def description(self):
         return self._changeset[4]
     def branch(self):
         return self._changeset[5].get("branch")
     def extra(self):
         return self._changeset[5]
     def tags(self):
         return self._repo.nodetags(self._node)
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def p1(self):
         return self._parents[0]
 
     def p2(self):
         if len(self._parents) == 2:
             return self._parents[1]
         return changectx(self._repo, -1)
 
     def children(self):
         """return contexts for each child changeset"""
         c = self._repo.changelog.children(self._node)
         return [changectx(self._repo, x) for x in c]
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors(self._rev):
             yield changectx(self._repo, a)
 
     def descendants(self):
         for d in self._repo.changelog.descendants(self._rev):
             yield changectx(self._repo, d)
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.LookupError(self._node, path,
                                         _('not found in manifest'))
         if '_manifestdelta' in self.__dict__ or path in self.files():
             if path in self._manifestdelta:
                 return self._manifestdelta[path], self._manifestdelta.flags(path)
         node, flag = self._repo.manifest.find(self._changeset[0], path)
         if not node:
             raise error.LookupError(self._node, path,
                                     _('not found in manifest'))
 
         return node, flag
 
     def filenode(self, path):
         return self._fileinfo(path)[0]
 
     def flags(self, path):
         try:
             return self._fileinfo(path)[1]
         except error.LookupError:
             return ''
 
     def filectx(self, path, fileid=None, filelog=None):
         """get a file context from this changeset"""
         if fileid is None:
             fileid = self.filenode(path)
         return filectx(self._repo, path, fileid=fileid,
                        changectx=self, filelog=filelog)
 
     def ancestor(self, c2):
         """
         return the ancestor context of self and c2
         """
         # deal with workingctxs
         n2 = c2._node
         if n2 == None:
             n2 = c2._parents[0]._node
         n = self._repo.changelog.ancestor(self._node, n2)
         return changectx(self._repo, n)
 
     def walk(self, match):
         fset = set(match.files())
         # for dirstate.walk, files=['.'] means "walk the whole tree".
         # follow that here, too
         fset.discard('.')
         for fn in self:
             for ffn in fset:
                 # match if the file is the exact name or a directory
                 if ffn == fn or fn.startswith("%s/" % ffn):
                     fset.remove(ffn)
                     break
             if match(fn):
                 yield fn
         for fn in sorted(fset):
             if match.bad(fn, 'No such file in rev ' + str(self)) and match(fn):
                 yield fn
 
     def sub(self, path):
         return subrepo.subrepo(self, path)
 
     def diff(self, ctx2=None, match=None, **opts):
         """Returns a diff generator for the given contexts and matcher"""
         if ctx2 is None:
             ctx2 = self.p1()
         if ctx2 is not None and not isinstance(ctx2, changectx):
             ctx2 = self._repo[ctx2]
         diffopts = patch.diffopts(self._repo.ui, opts)
         return patch.diff(self._repo, ctx2.node(), self.node(),
                           match=match, opts=diffopts)
 
 class filectx(object):
     """A filecontext object makes access to data related to a particular
        filerevision convenient."""
     def __init__(self, repo, path, changeid=None, fileid=None,
                  filelog=None, changectx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
 
         assert (changeid is not None
                 or fileid is not None
                 or changectx is not None), \
                 ("bad args: changeid=%r, fileid=%r, changectx=%r"
                  % (changeid, fileid, changectx))
 
         if filelog:
             self._filelog = filelog
 
         if changeid is not None:
             self._changeid = changeid
         if changectx is not None:
             self._changectx = changectx
         if fileid is not None:
             self._fileid = fileid
 
     @propertycache
     def _changectx(self):
         return changectx(self._repo, self._changeid)
 
     @propertycache
     def _filelog(self):
         return self._repo.file(self._path)
 
     @propertycache
     def _changeid(self):
         if '_changectx' in self.__dict__:
             return self._changectx.rev()
         else:
             return self._filelog.linkrev(self._filerev)
 
     @propertycache
     def _filenode(self):
         if '_fileid' in self.__dict__:
             return self._filelog.lookup(self._fileid)
         else:
             return self._changectx.filenode(self._path)
 
     @propertycache
     def _filerev(self):
         return self._filelog.rev(self._filenode)
 
     @propertycache
     def _repopath(self):
         return self._path
 
     def __nonzero__(self):
         try:
             self._filenode
             return True
         except error.LookupError:
             # file is missing
             return False
 
     def __str__(self):
         return "%s@%s" % (self.path(), short(self.node()))
 
     def __repr__(self):
         return "<filectx %s>" % str(self)
 
     def __hash__(self):
         try:
             return hash((self._path, self._filenode))
         except AttributeError:
             return id(self)
 
     def __eq__(self, other):
         try:
             return (self._path == other._path
                     and self._filenode == other._filenode)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not (self == other)
 
     def filectx(self, fileid):
         '''opens an arbitrary revision of the file without
         opening a new filelog'''
         return filectx(self._repo, self._path, fileid=fileid,
                        filelog=self._filelog)
 
     def filerev(self):
         return self._filerev
     def filenode(self):
         return self._filenode
     def flags(self):
         return self._changectx.flags(self._path)
     def filelog(self):
         return self._filelog
 
     def rev(self):
         if '_changectx' in self.__dict__:
             return self._changectx.rev()
         if '_changeid' in self.__dict__:
             return self._changectx.rev()
         return self._filelog.linkrev(self._filerev)
 
     def linkrev(self):
         return self._filelog.linkrev(self._filerev)
     def node(self):
         return self._changectx.node()
     def hex(self):
         return hex(self.node())
     def user(self):
         return self._changectx.user()
     def date(self):
         return self._changectx.date()
     def files(self):
         return self._changectx.files()
     def description(self):
         return self._changectx.description()
     def branch(self):
         return self._changectx.branch()
     def extra(self):
         return self._changectx.extra()
     def manifest(self):
         return self._changectx.manifest()
     def changectx(self):
         return self._changectx
 
     def data(self):
         return self._filelog.read(self._filenode)
     def path(self):
         return self._path
     def size(self):
         return self._filelog.size(self._filerev)
 
-    def cmp(self, text):
-        """compare text with stored file revision
+    def cmp(self, fctx):
+        """compare with other file context
 
-        returns True if text is different than what is stored.
+        returns True if different than fctx.
         """
-        return self._filelog.cmp(self._filenode, text)
+        return self._filelog.cmp(self._filenode, fctx.data())
 
     def renamed(self):
         """check if file was actually renamed in this changeset revision
 
         If rename logged in file revision, we report copy for changeset only
         if file revisions linkrev points back to the changeset in question
         or both changeset parents contain different file revisions.
         """
 
         renamed = self._filelog.renamed(self._filenode)
         if not renamed:
             return renamed
 
         if self.rev() == self.linkrev():
             return renamed
 
         name = self.path()
         fnode = self._filenode
         for p in self._changectx.parents():
             try:
                 if fnode == p.filenode(name):
                     return None
             except error.LookupError:
                 pass
         return renamed
 
     def parents(self):
         p = self._path
         fl = self._filelog
         pl = [(p, n, fl) for n in self._filelog.parents(self._filenode)]
 
         r = self._filelog.renamed(self._filenode)
         if r:
             pl[0] = (r[0], r[1], None)
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def children(self):
         # hard for renames
         c = self._filelog.children(self._filenode)
         return [filectx(self._repo, self._path, fileid=x,
                         filelog=self._filelog) for x in c]
 
     def annotate(self, follow=False, linenumber=None):
         '''returns a list of tuples of (ctx, line) for each line
         in the file, where ctx is the filectx of the node where
         that line was last changed.
         This returns tuples of ((ctx, linenumber), line) for each line,
         if "linenumber" parameter is NOT "None".
         In such tuples, linenumber means one at the first appearance
         in the managed file.
         To reduce annotation cost,
         this returns fixed value(False is used) as linenumber,
         if "linenumber" parameter is "False".'''
 
         def decorate_compat(text, rev):
             return ([rev] * len(text.splitlines()), text)
 
         def without_linenumber(text, rev):
             return ([(rev, False)] * len(text.splitlines()), text)
 
         def with_linenumber(text, rev):
             size = len(text.splitlines())
             return ([(rev, i) for i in xrange(1, size + 1)], text)
 
         decorate = (((linenumber is None) and decorate_compat) or
                     (linenumber and with_linenumber) or
                     without_linenumber)
 
         def pair(parent, child):
             for a1, a2, b1, b2 in bdiff.blocks(parent[1], child[1]):
                 child[0][b1:b2] = parent[0][a1:a2]
             return child
 
         getlog = util.lrucachefunc(lambda x: self._repo.file(x))
         def getctx(path, fileid):
             log = path == self._path and self._filelog or getlog(path)
             return filectx(self._repo, path, fileid=fileid, filelog=log)
         getctx = util.lrucachefunc(getctx)
 
         def parents(f):
             # we want to reuse filectx objects as much as possible
             p = f._path
             if f._filerev is None: # working dir
                 pl = [(n.path(), n.filerev()) for n in f.parents()]
             else:
                 pl = [(p, n) for n in f._filelog.parentrevs(f._filerev)]
 
             if follow:
                 r = f.renamed()
                 if r:
                     pl[0] = (r[0], getlog(r[0]).rev(r[1]))
 
             return [getctx(p, n) for p, n in pl if n != nullrev]
 
         # use linkrev to find the first changeset where self appeared
         if self.rev() != self.linkrev():
             base = self.filectx(self.filerev())
         else:
             base = self
 
         # find all ancestors
         needed = {base: 1}
         visit = [base]
         files = [base._path]
         while visit:
             f = visit.pop(0)
             for p in parents(f):
                 if p not in needed:
                     needed[p] = 1
                     visit.append(p)
                     if p._path not in files:
                         files.append(p._path)
                 else:
                     # count how many times we'll use this
                     needed[p] += 1
 
         # sort by revision (per file) which is a topological order
         visit = []
         for f in files:
             visit.extend(n for n in needed if n._path == f)
 
         hist = {}
         for f in sorted(visit, key=lambda x: x.rev()):
             curr = decorate(f.data(), f)
             for p in parents(f):
                 curr = pair(hist[p], curr)
                 # trim the history of unneeded revs
                 needed[p] -= 1
                 if not needed[p]:
                     del hist[p]
             hist[f] = curr
 
         return zip(hist[f][0], hist[f][1].splitlines(True))
 
     def ancestor(self, fc2, actx=None):
         """
         find the common ancestor file context, if any, of self, and fc2
 
         If actx is given, it must be the changectx of the common ancestor
         of self's and fc2's respective changesets.
         """
 
         if actx is None:
             actx = self.changectx().ancestor(fc2.changectx())
 
         # the trivial case: changesets are unrelated, files must be too
         if not actx:
             return None
 
         # the easy case: no (relevant) renames
         if fc2.path() == self.path() and self.path() in actx:
             return actx[self.path()]
         acache = {}
 
         # prime the ancestor cache for the working directory
         for c in (self, fc2):
             if c._filerev is None:
                 pl = [(n.path(), n.filenode()) for n in c.parents()]
                 acache[(c._path, None)] = pl
 
         flcache = {self._repopath:self._filelog, fc2._repopath:fc2._filelog}
         def parents(vertex):
             if vertex in acache:
                 return acache[vertex]
             f, n = vertex
             if f not in flcache:
                 flcache[f] = self._repo.file(f)
             fl = flcache[f]
             pl = [(f, p) for p in fl.parents(n) if p != nullid]
             re = fl.renamed(n)
             if re:
                 pl.append(re)
             acache[vertex] = pl
             return pl
 
         a, b = (self._path, self._filenode), (fc2._path, fc2._filenode)
         v = ancestor.ancestor(a, b, parents)
         if v:
             f, n = v
             return filectx(self._repo, f, fileid=n, filelog=flcache[f])
 
         return None
 
     def ancestors(self):
         seen = set(str(self))
         visit = [self]
         while visit:
             for parent in visit.pop(0).parents():
                 s = str(parent)
                 if s not in seen:
                     visit.append(parent)
                     seen.add(s)
                     yield parent
 
 class workingctx(changectx):
     """A workingctx object makes access to data related to
     the current working directory convenient.
     date - any valid date string or (unixtime, offset), or None.
     user - username string, or None.
     extra - a dictionary of extra values, or None.
     changes - a list of file lists as returned by localrepo.status()
                or None to use the repository status.
     """
     def __init__(self, repo, text="", user=None, date=None, extra=None,
                  changes=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         if date:
             self._date = util.parsedate(date)
         if user:
             self._user = user
         if changes:
             self._status = list(changes[:4])
             self._unknown = changes[4]
             self._ignored = changes[5]
             self._clean = changes[6]
         else:
             self._unknown = None
             self._ignored = None
             self._clean = None
 
         self._extra = {}
         if extra:
             self._extra = extra.copy()
         if 'branch' not in self._extra:
             branch = self._repo.dirstate.branch()
             try:
                 branch = branch.decode('UTF-8').encode('UTF-8')
             except UnicodeDecodeError:
                 raise util.Abort(_('branch name not in UTF-8!'))
             self._extra['branch'] = branch
         if self._extra['branch'] == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __nonzero__(self):
         return True
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the working directory"""
 
         if self._unknown is None:
             self.status(unknown=True)
 
         man = self._parents[0].manifest().copy()
         copied = self._repo.dirstate.copies()
         if len(self._parents) > 1:
             man2 = self.p2().manifest()
             def getman(f):
                 if f in man:
                     return man
                 return man2
         else:
             getman = lambda f: man
         def cf(f):
             f = copied.get(f, f)
             return getman(f).flags(f)
         ff = self._repo.dirstate.flagfunc(cf)
         modified, added, removed, deleted = self._status
         unknown = self._unknown
         for i, l in (("a", added), ("m", modified), ("u", unknown)):
             for f in l:
                 orig = copied.get(f, f)
                 man[f] = getman(orig).get(orig, nullid) + i
                 try:
                     man.set(f, ff(f))
                 except OSError:
                     pass
 
         for f in deleted + removed:
             if f in man:
                 del man[f]
 
         return man
 
     @propertycache
     def _status(self):
         return self._repo.status()[:4]
 
     @propertycache
     def _user(self):
         return self._repo.ui.username()
 
     @propertycache
     def _date(self):
         return util.makedate()
 
     @propertycache
     def _parents(self):
         p = self._repo.dirstate.parents()
         if p[1] == nullid:
             p = p[:-1]
         self._parents = [changectx(self._repo, x) for x in p]
         return self._parents
 
     def status(self, ignored=False, clean=False, unknown=False):
         """Explicit status query
         Unless this method is used to query the working copy status, the
         _status property will implicitly read the status using its default
         arguments."""
         stat = self._repo.status(ignored=ignored, clean=clean, unknown=unknown)
         self._unknown = self._ignored = self._clean = None
         if unknown:
             self._unknown = stat[4]
         if ignored:
             self._ignored = stat[5]
         if clean:
             self._clean = stat[6]
         self._status = stat[:4]
         return stat
 
     def manifest(self):
         return self._manifest
     def user(self):
         return self._user or self._repo.ui.username()
     def date(self):
         return self._date
     def description(self):
         return self._text
     def files(self):
         return sorted(self._status[0] + self._status[1] + self._status[2])
 
     def modified(self):
         return self._status[0]
     def added(self):
         return self._status[1]
     def removed(self):
         return self._status[2]
     def deleted(self):
         return self._status[3]
     def unknown(self):
         assert self._unknown is not None  # must call status first
         return self._unknown
     def ignored(self):
         assert self._ignored is not None  # must call status first
         return self._ignored
     def clean(self):
         assert self._clean is not None  # must call status first
         return self._clean
     def branch(self):
         return self._extra['branch']
     def extra(self):
         return self._extra
 
     def tags(self):
         t = []
         [t.extend(p.tags()) for p in self.parents()]
         return t
 
     def children(self):
         return []
 
     def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         orig = self._repo.dirstate.copies().get(path, path)
 
         def findflag(ctx):
             mnode = ctx.changeset()[0]
             node, flag = self._repo.manifest.find(mnode, orig)
             ff = self._repo.dirstate.flagfunc(lambda x: flag or '')
             try:
                 return ff(path)
             except OSError:
                 pass
 
         flag = findflag(self._parents[0])
         if flag is None and len(self.parents()) > 1:
             flag = findflag(self._parents[1])
         if flag is None or self._repo.dirstate[path] == 'r':
             return ''
         return flag
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return workingfilectx(self._repo, path, workingctx=self,
                               filelog=filelog)
 
     def ancestor(self, c2):
         """return the ancestor context of self and c2"""
         return self._parents[0].ancestor(c2) # punt on two parents for now
 
     def walk(self, match):
         return sorted(self._repo.dirstate.walk(match, self.substate.keys(),
                                                True, False))
 
     def dirty(self, missing=False):
         "check whether a working directory is modified"
         # check subrepos first
         for s in self.substate:
             if self.sub(s).dirty():
                 return True
         # check current working dir
         return (self.p2() or self.branch() != self.p1().branch() or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
     def add(self, list):
         wlock = self._repo.wlock()
         ui, ds = self._repo.ui, self._repo.dirstate
         try:
             rejected = []
             for f in list:
                 p = self._repo.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     ui.warn(_("%s: up to %d MB of RAM may be required "
                               "to manage this file\n"
                               "(use 'hg revert %s' to cancel the "
                               "pending addition)\n")
                               % (f, 3 * st.st_size // 1000000, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     ui.warn(_("%s not added: only files and symlinks "
                               "supported currently\n") % f)
                     rejected.append(p)
                 elif ds[f] in 'amn':
                     ui.warn(_("%s already tracked!\n") % f)
                 elif ds[f] == 'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, list):
         wlock = self._repo.wlock()
         try:
             for f in list:
                 if self._repo.dirstate[f] != 'a':
                     self._repo.ui.warn(_("%s not added!\n") % f)
                 else:
                     self._repo.dirstate.forget(f)
         finally:
             wlock.release()
 
     def remove(self, list, unlink=False):
         if unlink:
             for f in list:
                 try:
                     util.unlink(self._repo.wjoin(f))
                 except OSError, inst:
                     if inst.errno != errno.ENOENT:
                         raise
         wlock = self._repo.wlock()
         try:
             for f in list:
                 if unlink and os.path.exists(self._repo.wjoin(f)):
                     self._repo.ui.warn(_("%s still exists!\n") % f)
                 elif self._repo.dirstate[f] == 'a':
                     self._repo.dirstate.forget(f)
                 elif f not in self._repo.dirstate:
                     self._repo.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self._repo.dirstate.remove(f)
         finally:
             wlock.release()
 
     def undelete(self, list):
         pctxs = self.parents()
         wlock = self._repo.wlock()
         try:
             for f in list:
                 if self._repo.dirstate[f] != 'r':
                     self._repo.ui.warn(_("%s not removed!\n") % f)
                 else:
                     fctx = f in pctxs[0] and pctxs[0] or pctxs[1]
                     t = fctx.data()
                     self._repo.wwrite(f, t, fctx.flags())
                     self._repo.dirstate.normal(f)
         finally:
             wlock.release()
 
     def copy(self, source, dest):
         p = self._repo.wjoin(dest)
         if not (os.path.exists(p) or os.path.islink(p)):
             self._repo.ui.warn(_("%s does not exist!\n") % dest)
         elif not (os.path.isfile(p) or os.path.islink(p)):
             self._repo.ui.warn(_("copy failed: %s is not a file or a "
                                  "symbolic link\n") % dest)
         else:
             wlock = self._repo.wlock()
             try:
                 if self._repo.dirstate[dest] in '?r':
                     self._repo.dirstate.add(dest)
                 self._repo.dirstate.copy(source, dest)
             finally:
                 wlock.release()
 
 class workingfilectx(filectx):
     """A workingfilectx object makes access to data related to a particular
        file in the working directory convenient."""
     def __init__(self, repo, path, filelog=None, workingctx=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         self._repo = repo
         self._path = path
         self._changeid = None
         self._filerev = self._filenode = None
 
         if filelog:
             self._filelog = filelog
         if workingctx:
             self._changectx = workingctx
 
     @propertycache
     def _changectx(self):
         return workingctx(self._repo)
 
     def __nonzero__(self):
         return True
 
     def __str__(self):
         return "%s@%s" % (self.path(), self._changectx)
 
     def data(self):
         return self._repo.wread(self._path)
     def renamed(self):
         rp = self._repo.dirstate.copied(self._path)
         if not rp:
             return None
         return rp, self._changectx._parents[0]._manifest.get(rp, nullid)
 
     def parents(self):
         '''return parent filectxs, following copies if necessary'''
         def filenode(ctx, path):
             return ctx._manifest.get(path, nullid)
 
         path = self._path
         fl = self._filelog
         pcl = self._changectx._parents
         renamed = self.renamed()
 
         if renamed:
             pl = [renamed + (None,)]
         else:
             pl = [(path, filenode(pcl[0], path), fl)]
 
         for pc in pcl[1:]:
             pl.append((path, filenode(pc, path), fl))
 
         return [filectx(self._repo, p, fileid=n, filelog=l)
                 for p, n, l in pl if n != nullid]
 
     def children(self):
         return []
 
     def size(self):
         return os.lstat(self._repo.wjoin(self._path)).st_size
     def date(self):
         t, tz = self._changectx.date()
         try:
             return (int(os.lstat(self._repo.wjoin(self._path)).st_mtime), tz)
         except OSError, err:
             if err.errno != errno.ENOENT:
                 raise
             return (t, tz)
 
-    def cmp(self, text):
-        """compare text with disk content
+    def cmp(self, fctx):
+        """compare with other file context
 
-        returns True if text is different than what is on disk.
+        returns True if different than fctx.
         """
-        return self._repo.wread(self._path) != text
+        return self._repo.wread(self._path) != fctx.data()
 
 class memctx(object):
     """Use memctx to perform in-memory commits via localrepo.commitctx().
 
     Revision information is supplied at initialization time while
     related files data and is made available through a callback
     mechanism.  'repo' is the current localrepo, 'parents' is a
     sequence of two parent revisions identifiers (pass None for every
     missing parent), 'text' is the commit message and 'files' lists
     names of files touched by the revision (normalized and relative to
     repository root).
 
     filectxfn(repo, memctx, path) is a callable receiving the
     repository, the current memctx object and the normalized path of
     requested file, relative to repository root. It is fired by the
     commit function for every file in 'files', but calls order is
     undefined. If the file is available in the revision being
     committed (updated or added), filectxfn returns a memfilectx
     object. If the file was removed, filectxfn raises an
     IOError. Moved files are represented by marking the source file
     removed and the new file added with copy information (see
     memfilectx).
 
     user receives the committer name and defaults to current
     repository username, date is the commit date in any format
     supported by util.parsedate() and defaults to current date, extra
     is a dictionary of metadata or is left empty.
     """
     def __init__(self, repo, parents, text, files, filectxfn, user=None,
                  date=None, extra=None):
         self._repo = repo
         self._rev = None
         self._node = None
         self._text = text
         self._date = date and util.parsedate(date) or util.makedate()
         self._user = user
         parents = [(p or nullid) for p in parents]
         p1, p2 = parents
         self._parents = [changectx(self._repo, p) for p in (p1, p2)]
         files = sorted(set(files))
         self._status = [files, [], [], [], []]
         self._filectxfn = filectxfn
 
         self._extra = extra and extra.copy() or {}
         if 'branch' not in self._extra:
             self._extra['branch'] = 'default'
         elif self._extra.get('branch') == '':
             self._extra['branch'] = 'default'
 
     def __str__(self):
         return str(self._parents[0]) + "+"
 
     def __int__(self):
         return self._rev
 
     def __nonzero__(self):
         return True
 
     def __getitem__(self, key):
         return self.filectx(key)
 
     def p1(self):
         return self._parents[0]
     def p2(self):
         return self._parents[1]
 
     def user(self):
         return self._user or self._repo.ui.username()
     def date(self):
         return self._date
     def description(self):
         return self._text
     def files(self):
         return self.modified()
     def modified(self):
         return self._status[0]
     def added(self):
         return self._status[1]
     def removed(self):
         return self._status[2]
     def deleted(self):
         return self._status[3]
     def unknown(self):
         return self._status[4]
     def ignored(self):
         return self._status[5]
     def clean(self):
         return self._status[6]
     def branch(self):
         return self._extra['branch']
     def extra(self):
         return self._extra
     def flags(self, f):
         return self[f].flags()
 
     def parents(self):
         """return contexts for each parent changeset"""
         return self._parents
 
     def filectx(self, path, filelog=None):
         """get a file context from the working directory"""
         return self._filectxfn(self._repo, self, path)
 
     def commit(self):
         """commit context to the repo"""
         return self._repo.commitctx(self)
 
 class memfilectx(object):
     """memfilectx represents an in-memory file to commit.
 
     See memctx for more details.
     """
     def __init__(self, path, data, islink=False, isexec=False, copied=None):
         """
         path is the normalized file path relative to repository root.
         data is the file content as a string.
         islink is True if the file is a symbolic link.
         isexec is True if the file is executable.
         copied is the source file path if current file was copied in the
         revision being committed, or None."""
         self._path = path
         self._data = data
         self._flags = (islink and 'l' or '') + (isexec and 'x' or '')
         self._copied = None
         if copied:
             self._copied = (copied, nullid)
 
     def __nonzero__(self):
         return True
     def __str__(self):
         return "%s@%s" % (self.path(), self._changectx)
     def path(self):
         return self._path
     def data(self):
         return self._data
     def flags(self):
         return self._flags
     def isexec(self):
         return 'x' in self._flags
     def islink(self):
         return 'l' in self._flags
     def renamed(self):
         return self._copied

mercurial/filemerge.py

@@ -1,259 +1,259
 # filemerge.py - file-level merge handling for Mercurial
 #
 # Copyright 2006, 2007, 2008 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 short
 from i18n import _
 import util, simplemerge, match, error
 import os, tempfile, re, filecmp
 
 def _toolstr(ui, tool, part, default=""):
     return ui.config("merge-tools", tool + "." + part, default)
 
 def _toolbool(ui, tool, part, default=False):
     return ui.configbool("merge-tools", tool + "." + part, default)
 
 def _toollist(ui, tool, part, default=[]):
     return ui.configlist("merge-tools", tool + "." + part, default)
 
 _internal = ['internal:' + s
              for s in 'fail local other merge prompt dump'.split()]
 
 def _findtool(ui, tool):
     if tool in _internal:
         return tool
     k = _toolstr(ui, tool, "regkey")
     if k:
         p = util.lookup_reg(k, _toolstr(ui, tool, "regname"))
         if p:
             p = util.find_exe(p + _toolstr(ui, tool, "regappend"))
             if p:
                 return p
     return util.find_exe(_toolstr(ui, tool, "executable", tool))
 
 def _picktool(repo, ui, path, binary, symlink):
     def check(tool, pat, symlink, binary):
         tmsg = tool
         if pat:
             tmsg += " specified for " + pat
         if not _findtool(ui, tool):
             if pat: # explicitly requested tool deserves a warning
                 ui.warn(_("couldn't find merge tool %s\n") % tmsg)
             else: # configured but non-existing tools are more silent
                 ui.note(_("couldn't find merge tool %s\n") % tmsg)
         elif symlink and not _toolbool(ui, tool, "symlink"):
             ui.warn(_("tool %s can't handle symlinks\n") % tmsg)
         elif binary and not _toolbool(ui, tool, "binary"):
             ui.warn(_("tool %s can't handle binary\n") % tmsg)
         elif not util.gui() and _toolbool(ui, tool, "gui"):
             ui.warn(_("tool %s requires a GUI\n") % tmsg)
         else:
             return True
         return False
 
     # HGMERGE takes precedence
     hgmerge = os.environ.get("HGMERGE")
     if hgmerge:
         return (hgmerge, hgmerge)
 
     # then patterns
     for pat, tool in ui.configitems("merge-patterns"):
         mf = match.match(repo.root, '', [pat])
         if mf(path) and check(tool, pat, symlink, False):
             toolpath = _findtool(ui, tool)
             return (tool, '"' + toolpath + '"')
 
     # then merge tools
     tools = {}
     for k, v in ui.configitems("merge-tools"):
         t = k.split('.')[0]
         if t not in tools:
             tools[t] = int(_toolstr(ui, t, "priority", "0"))
     names = tools.keys()
     tools = sorted([(-p, t) for t, p in tools.items()])
     uimerge = ui.config("ui", "merge")
     if uimerge:
         if uimerge not in names:
             return (uimerge, uimerge)
         tools.insert(0, (None, uimerge)) # highest priority
     tools.append((None, "hgmerge")) # the old default, if found
     for p, t in tools:
         if check(t, None, symlink, binary):
             toolpath = _findtool(ui, t)
             return (t, '"' + toolpath + '"')
     # internal merge as last resort
     return (not (symlink or binary) and "internal:merge" or None, None)
 
 def _eoltype(data):
     "Guess the EOL type of a file"
     if '\0' in data: # binary
         return None
     if '\r\n' in data: # Windows
         return '\r\n'
     if '\r' in data: # Old Mac
         return '\r'
     if '\n' in data: # UNIX
         return '\n'
     return None # unknown
 
 def _matcheol(file, origfile):
     "Convert EOL markers in a file to match origfile"
     tostyle = _eoltype(open(origfile, "rb").read())
     if tostyle:
         data = open(file, "rb").read()
         style = _eoltype(data)
         if style:
             newdata = data.replace(style, tostyle)
             if newdata != data:
                 open(file, "wb").write(newdata)
 
 def filemerge(repo, mynode, orig, fcd, fco, fca):
     """perform a 3-way merge in the working directory
 
     mynode = parent node before merge
     orig = original local filename before merge
     fco = other file context
     fca = ancestor file context
     fcd = local file context for current/destination file
     """
 
     def temp(prefix, ctx):
         pre = "%s~%s." % (os.path.basename(ctx.path()), prefix)
         (fd, name) = tempfile.mkstemp(prefix=pre)
         data = repo.wwritedata(ctx.path(), ctx.data())
         f = os.fdopen(fd, "wb")
         f.write(data)
         f.close()
         return name
 
     def isbin(ctx):
         try:
             return util.binary(ctx.data())
         except IOError:
             return False
 
-    if not fco.cmp(fcd.data()): # files identical?
+    if not fco.cmp(fcd): # files identical?
         return None
 
     if fca == fco: # backwards, use working dir parent as ancestor
         fca = fcd.parents()[0]
 
     ui = repo.ui
     fd = fcd.path()
     binary = isbin(fcd) or isbin(fco) or isbin(fca)
     symlink = 'l' in fcd.flags() + fco.flags()
     tool, toolpath = _picktool(repo, ui, fd, binary, symlink)
     ui.debug("picked tool '%s' for %s (binary %s symlink %s)\n" %
                (tool, fd, binary, symlink))
 
     if not tool or tool == 'internal:prompt':
         tool = "internal:local"
         if ui.promptchoice(_(" no tool found to merge %s\n"
                              "keep (l)ocal or take (o)ther?") % fd,
                            (_("&Local"), _("&Other")), 0):
             tool = "internal:other"
     if tool == "internal:local":
         return 0
     if tool == "internal:other":
         repo.wwrite(fd, fco.data(), fco.flags())
         return 0
     if tool == "internal:fail":
         return 1
 
     # do the actual merge
     a = repo.wjoin(fd)
     b = temp("base", fca)
     c = temp("other", fco)
     out = ""
     back = a + ".orig"
     util.copyfile(a, back)
 
     if orig != fco.path():
         ui.status(_("merging %s and %s to %s\n") % (orig, fco.path(), fd))
     else:
         ui.status(_("merging %s\n") % fd)
 
     ui.debug("my %s other %s ancestor %s\n" % (fcd, fco, fca))
 
     # do we attempt to simplemerge first?
     try:
         premerge = _toolbool(ui, tool, "premerge", not (binary or symlink))
     except error.ConfigError:
         premerge = _toolstr(ui, tool, "premerge").lower()
         valid = 'keep'.split()
         if premerge not in valid:
             _valid = ', '.join(["'" + v + "'" for v in valid])
             raise error.ConfigError(_("%s.premerge not valid "
                                       "('%s' is neither boolean nor %s)") %
                                     (tool, premerge, _valid))
 
     if premerge:
         r = simplemerge.simplemerge(ui, a, b, c, quiet=True)
         if not r:
             ui.debug(" premerge successful\n")
             os.unlink(back)
             os.unlink(b)
             os.unlink(c)
             return 0
         if premerge != 'keep':
             util.copyfile(back, a) # restore from backup and try again
 
     env = dict(HG_FILE=fd,
                HG_MY_NODE=short(mynode),
                HG_OTHER_NODE=str(fco.changectx()),
                HG_BASE_NODE=str(fca.changectx()),
                HG_MY_ISLINK='l' in fcd.flags(),
                HG_OTHER_ISLINK='l' in fco.flags(),
                HG_BASE_ISLINK='l' in fca.flags())
 
     if tool == "internal:merge":
         r = simplemerge.simplemerge(ui, a, b, c, label=['local', 'other'])
     elif tool == 'internal:dump':
         a = repo.wjoin(fd)
         util.copyfile(a, a + ".local")
         repo.wwrite(fd + ".other", fco.data(), fco.flags())
         repo.wwrite(fd + ".base", fca.data(), fca.flags())
         return 1 # unresolved
     else:
         args = _toolstr(ui, tool, "args", '$local $base $other')
         if "$output" in args:
             out, a = a, back # read input from backup, write to original
         replace = dict(local=a, base=b, other=c, output=out)
         args = re.sub("\$(local|base|other|output)",
             lambda x: '"%s"' % util.localpath(replace[x.group()[1:]]), args)
         r = util.system(toolpath + ' ' + args, cwd=repo.root, environ=env)
 
     if not r and (_toolbool(ui, tool, "checkconflicts") or
                   'conflicts' in _toollist(ui, tool, "check")):
         if re.match("^(<<<<<<< .*|=======|>>>>>>> .*)$", fcd.data()):
             r = 1
 
     checked = False
     if 'prompt' in _toollist(ui, tool, "check"):
         checked = True
         if ui.promptchoice(_("was merge of '%s' successful (yn)?") % fd,
                            (_("&Yes"), _("&No")), 1):
             r = 1
 
     if not r and not checked and (_toolbool(ui, tool, "checkchanged") or
                                   'changed' in _toollist(ui, tool, "check")):
         if filecmp.cmp(repo.wjoin(fd), back):
             if ui.promptchoice(_(" output file %s appears unchanged\n"
                                  "was merge successful (yn)?") % fd,
                                (_("&Yes"), _("&No")), 1):
                 r = 1
 
     if _toolbool(ui, tool, "fixeol"):
         _matcheol(repo.wjoin(fd), back)
 
     if r:
         ui.warn(_("merging %s failed!\n") % fd)
     else:
         os.unlink(back)
 
     os.unlink(b)
     os.unlink(c)
     return r

mercurial/localrepo.py

@@ -1,1802 +1,1802
 # 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'.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.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'
                     )
                 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 = {}
 
         # These two define the set of tags for this repository.  _tags
         # maps tag name to node; _tagtypes maps tag name to 'global' or
         # 'local'.  (Global tags are defined by .hgtags across all
         # heads, and local tags are defined in .hg/localtags.)  They
         # constitute the in-memory cache of tags.
         self._tags = None
         self._tagtypes = None
 
         self._branchcache = None  # in UTF-8
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     @propertycache
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         self.sopener.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 branchmap(self):
         '''returns a dictionary {branch: [branchheads]}'''
         tip = self.changelog.tip()
         if self._branchcache is not None and self._branchcachetip == tip:
             return self._branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._branchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._branchcache = partial
 
         return self._branchcache
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             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 rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _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 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.branchtags()
             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):
         """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].data())):
+                        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].data())))):
+                         (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
         [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.branchtags()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size)))
             # for backwards compat, name was partially encoded
             ofp = self.sopener(store.decodedir(name), 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
     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/merge.py

@@ -1,527 +1,527
 # merge.py - directory-level update/merge handling for Mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from node import nullid, nullrev, hex, bin
 from i18n import _
 import util, filemerge, copies, subrepo
 import errno, os, shutil
 
 class mergestate(object):
     '''track 3-way merge state of individual files'''
     def __init__(self, repo):
         self._repo = repo
         self._read()
     def reset(self, node=None):
         self._state = {}
         if node:
             self._local = node
         shutil.rmtree(self._repo.join("merge"), True)
     def _read(self):
         self._state = {}
         try:
             f = self._repo.opener("merge/state")
             for i, l in enumerate(f):
                 if i == 0:
                     self._local = bin(l[:-1])
                 else:
                     bits = l[:-1].split("\0")
                     self._state[bits[0]] = bits[1:]
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
     def _write(self):
         f = self._repo.opener("merge/state", "w")
         f.write(hex(self._local) + "\n")
         for d, v in self._state.iteritems():
             f.write("\0".join([d] + v) + "\n")
     def add(self, fcl, fco, fca, fd, flags):
         hash = util.sha1(fcl.path()).hexdigest()
         self._repo.opener("merge/" + hash, "w").write(fcl.data())
         self._state[fd] = ['u', hash, fcl.path(), fca.path(),
                            hex(fca.filenode()), fco.path(), flags]
         self._write()
     def __contains__(self, dfile):
         return dfile in self._state
     def __getitem__(self, dfile):
         return self._state[dfile][0]
     def __iter__(self):
         l = self._state.keys()
         l.sort()
         for f in l:
             yield f
     def mark(self, dfile, state):
         self._state[dfile][0] = state
         self._write()
     def resolve(self, dfile, wctx, octx):
         if self[dfile] == 'r':
             return 0
         state, hash, lfile, afile, anode, ofile, flags = self._state[dfile]
         f = self._repo.opener("merge/" + hash)
         self._repo.wwrite(dfile, f.read(), flags)
         fcd = wctx[dfile]
         fco = octx[ofile]
         fca = self._repo.filectx(afile, fileid=anode)
         r = filemerge.filemerge(self._repo, self._local, lfile, fcd, fco, fca)
         if not r:
             self.mark(dfile, 'r')
         return r
 
 def _checkunknown(wctx, mctx):
     "check for collisions between unknown files and files in mctx"
     for f in wctx.unknown():
-        if f in mctx and mctx[f].cmp(wctx[f].data()):
+        if f in mctx and mctx[f].cmp(wctx[f]):
             raise util.Abort(_("untracked file in working directory differs"
                                " from file in requested revision: '%s'") % f)
 
 def _checkcollision(mctx):
     "check for case folding collisions in the destination context"
     folded = {}
     for fn in mctx:
         fold = fn.lower()
         if fold in folded:
             raise util.Abort(_("case-folding collision between %s and %s")
                              % (fn, folded[fold]))
         folded[fold] = fn
 
 def _forgetremoved(wctx, mctx, branchmerge):
     """
     Forget removed files
 
     If we're jumping between revisions (as opposed to merging), and if
     neither the working directory nor the target rev has the file,
     then we need to remove it from the dirstate, to prevent the
     dirstate from listing the file when it is no longer in the
     manifest.
 
     If we're merging, and the other revision has removed a file
     that is not present in the working directory, we need to mark it
     as removed.
     """
 
     action = []
     state = branchmerge and 'r' or 'f'
     for f in wctx.deleted():
         if f not in mctx:
             action.append((f, state))
 
     if not branchmerge:
         for f in wctx.removed():
             if f not in mctx:
                 action.append((f, "f"))
 
     return action
 
 def manifestmerge(repo, p1, p2, pa, overwrite, partial):
     """
     Merge p1 and p2 with ancestor ma and generate merge action list
 
     overwrite = whether we clobber working files
     partial = function to filter file lists
     """
 
     def fmerge(f, f2, fa):
         """merge flags"""
         a, m, n = ma.flags(fa), m1.flags(f), m2.flags(f2)
         if m == n: # flags agree
             return m # unchanged
         if m and n and not a: # flags set, don't agree, differ from parent
             r = repo.ui.promptchoice(
                 _(" conflicting flags for %s\n"
                   "(n)one, e(x)ec or sym(l)ink?") % f,
                 (_("&None"), _("E&xec"), _("Sym&link")), 0)
             if r == 1:
                 return "x" # Exec
             if r == 2:
                 return "l" # Symlink
             return ""
         if m and m != a: # changed from a to m
             return m
         if n and n != a: # changed from a to n
             return n
         return '' # flag was cleared
 
     def act(msg, m, f, *args):
         repo.ui.debug(" %s: %s -> %s\n" % (f, msg, m))
         action.append((f, m) + args)
 
     action, copy = [], {}
 
     if overwrite:
         pa = p1
     elif pa == p2: # backwards
         pa = p1.p1()
     elif pa and repo.ui.configbool("merge", "followcopies", True):
         dirs = repo.ui.configbool("merge", "followdirs", True)
         copy, diverge = copies.copies(repo, p1, p2, pa, dirs)
         for of, fl in diverge.iteritems():
             act("divergent renames", "dr", of, fl)
 
     repo.ui.note(_("resolving manifests\n"))
     repo.ui.debug(" overwrite %s partial %s\n" % (overwrite, bool(partial)))
     repo.ui.debug(" ancestor %s local %s remote %s\n" % (pa, p1, p2))
 
     m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
     copied = set(copy.values())
 
     if '.hgsubstate' in m1:
         # check whether sub state is modified
         for s in p1.substate:
             if p1.sub(s).dirty():
                 m1['.hgsubstate'] += "+"
                 break
 
     # Compare manifests
     for f, n in m1.iteritems():
         if partial and not partial(f):
             continue
         if f in m2:
             rflags = fmerge(f, f, f)
             a = ma.get(f, nullid)
             if n == m2[f] or m2[f] == a: # same or local newer
                 # is file locally modified or flags need changing?
                 # dirstate flags may need to be made current
                 if m1.flags(f) != rflags or n[20:]:
                     act("update permissions", "e", f, rflags)
             elif n == a: # remote newer
                 act("remote is newer", "g", f, rflags)
             else: # both changed
                 act("versions differ", "m", f, f, f, rflags, False)
         elif f in copied: # files we'll deal with on m2 side
             pass
         elif f in copy:
             f2 = copy[f]
             if f2 not in m2: # directory rename
                 act("remote renamed directory to " + f2, "d",
                     f, None, f2, m1.flags(f))
             else: # case 2 A,B/B/B or case 4,21 A/B/B
                 act("local copied/moved to " + f2, "m",
                     f, f2, f, fmerge(f, f2, f2), False)
         elif f in ma: # clean, a different, no remote
             if n != ma[f]:
                 if repo.ui.promptchoice(
                     _(" local changed %s which remote deleted\n"
                       "use (c)hanged version or (d)elete?") % f,
                     (_("&Changed"), _("&Delete")), 0):
                     act("prompt delete", "r", f)
                 else:
                     act("prompt keep", "a", f)
             elif n[20:] == "a": # added, no remote
                 act("remote deleted", "f", f)
             elif n[20:] != "u":
                 act("other deleted", "r", f)
 
     for f, n in m2.iteritems():
         if partial and not partial(f):
             continue
         if f in m1 or f in copied: # files already visited
             continue
         if f in copy:
             f2 = copy[f]
             if f2 not in m1: # directory rename
                 act("local renamed directory to " + f2, "d",
                     None, f, f2, m2.flags(f))
             elif f2 in m2: # rename case 1, A/A,B/A
                 act("remote copied to " + f, "m",
                     f2, f, f, fmerge(f2, f, f2), False)
             else: # case 3,20 A/B/A
                 act("remote moved to " + f, "m",
                     f2, f, f, fmerge(f2, f, f2), True)
         elif f not in ma:
             act("remote created", "g", f, m2.flags(f))
         elif n != ma[f]:
             if repo.ui.promptchoice(
                 _("remote changed %s which local deleted\n"
                   "use (c)hanged version or leave (d)eleted?") % f,
                 (_("&Changed"), _("&Deleted")), 0) == 0:
                 act("prompt recreating", "g", f, m2.flags(f))
 
     return action
 
 def actionkey(a):
     return a[1] == 'r' and -1 or 0, a
 
 def applyupdates(repo, action, wctx, mctx, actx):
     """apply the merge action list to the working directory
 
     wctx is the working copy context
     mctx is the context to be merged into the working copy
     actx is the context of the common ancestor
     """
 
     updated, merged, removed, unresolved = 0, 0, 0, 0
     ms = mergestate(repo)
     ms.reset(wctx.parents()[0].node())
     moves = []
     action.sort(key=actionkey)
     substate = wctx.substate # prime
 
     # prescan for merges
     u = repo.ui
     for a in action:
         f, m = a[:2]
         if m == 'm': # merge
             f2, fd, flags, move = a[2:]
             if f == '.hgsubstate': # merged internally
                 continue
             repo.ui.debug("preserving %s for resolve of %s\n" % (f, fd))
             fcl = wctx[f]
             fco = mctx[f2]
             fca = fcl.ancestor(fco, actx) or repo.filectx(f, fileid=nullrev)
             ms.add(fcl, fco, fca, fd, flags)
             if f != fd and move:
                 moves.append(f)
 
     # remove renamed files after safely stored
     for f in moves:
         if util.lexists(repo.wjoin(f)):
             repo.ui.debug("removing %s\n" % f)
             os.unlink(repo.wjoin(f))
 
     audit_path = util.path_auditor(repo.root)
 
     numupdates = len(action)
     for i, a in enumerate(action):
         f, m = a[:2]
         u.progress('update', i + 1, item=f, total=numupdates, unit='files')
         if f and f[0] == "/":
             continue
         if m == "r": # remove
             repo.ui.note(_("removing %s\n") % f)
             audit_path(f)
             if f == '.hgsubstate': # subrepo states need updating
                 subrepo.submerge(repo, wctx, mctx, wctx)
             try:
                 util.unlink(repo.wjoin(f))
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     repo.ui.warn(_("update failed to remove %s: %s!\n") %
                                  (f, inst.strerror))
             removed += 1
         elif m == "m": # merge
             if f == '.hgsubstate': # subrepo states need updating
                 subrepo.submerge(repo, wctx, mctx, wctx.ancestor(mctx))
                 continue
             f2, fd, flags, move = a[2:]
             r = ms.resolve(fd, wctx, mctx)
             if r is not None and r > 0:
                 unresolved += 1
             else:
                 if r is None:
                     updated += 1
                 else:
                     merged += 1
             util.set_flags(repo.wjoin(fd), 'l' in flags, 'x' in flags)
             if f != fd and move and util.lexists(repo.wjoin(f)):
                 repo.ui.debug("removing %s\n" % f)
                 os.unlink(repo.wjoin(f))
         elif m == "g": # get
             flags = a[2]
             repo.ui.note(_("getting %s\n") % f)
             t = mctx.filectx(f).data()
             repo.wwrite(f, t, flags)
             updated += 1
             if f == '.hgsubstate': # subrepo states need updating
                 subrepo.submerge(repo, wctx, mctx, wctx)
         elif m == "d": # directory rename
             f2, fd, flags = a[2:]
             if f:
                 repo.ui.note(_("moving %s to %s\n") % (f, fd))
                 t = wctx.filectx(f).data()
                 repo.wwrite(fd, t, flags)
                 util.unlink(repo.wjoin(f))
             if f2:
                 repo.ui.note(_("getting %s to %s\n") % (f2, fd))
                 t = mctx.filectx(f2).data()
                 repo.wwrite(fd, t, flags)
             updated += 1
         elif m == "dr": # divergent renames
             fl = a[2]
             repo.ui.warn(_("warning: detected divergent renames of %s to:\n") % f)
             for nf in fl:
                 repo.ui.warn(" %s\n" % nf)
         elif m == "e": # exec
             flags = a[2]
             util.set_flags(repo.wjoin(f), 'l' in flags, 'x' in flags)
     u.progress('update', None, total=numupdates, unit='files')
 
     return updated, merged, removed, unresolved
 
 def recordupdates(repo, action, branchmerge):
     "record merge actions to the dirstate"
 
     for a in action:
         f, m = a[:2]
         if m == "r": # remove
             if branchmerge:
                 repo.dirstate.remove(f)
             else:
                 repo.dirstate.forget(f)
         elif m == "a": # re-add
             if not branchmerge:
                 repo.dirstate.add(f)
         elif m == "f": # forget
             repo.dirstate.forget(f)
         elif m == "e": # exec change
             repo.dirstate.normallookup(f)
         elif m == "g": # get
             if branchmerge:
                 repo.dirstate.otherparent(f)
             else:
                 repo.dirstate.normal(f)
         elif m == "m": # merge
             f2, fd, flag, move = a[2:]
             if branchmerge:
                 # We've done a branch merge, mark this file as merged
                 # so that we properly record the merger later
                 repo.dirstate.merge(fd)
                 if f != f2: # copy/rename
                     if move:
                         repo.dirstate.remove(f)
                     if f != fd:
                         repo.dirstate.copy(f, fd)
                     else:
                         repo.dirstate.copy(f2, fd)
             else:
                 # We've update-merged a locally modified file, so
                 # we set the dirstate to emulate a normal checkout
                 # of that file some time in the past. Thus our
                 # merge will appear as a normal local file
                 # modification.
                 if f2 == fd: # file not locally copied/moved
                     repo.dirstate.normallookup(fd)
                 if move:
                     repo.dirstate.forget(f)
         elif m == "d": # directory rename
             f2, fd, flag = a[2:]
             if not f2 and f not in repo.dirstate:
                 # untracked file moved
                 continue
             if branchmerge:
                 repo.dirstate.add(fd)
                 if f:
                     repo.dirstate.remove(f)
                     repo.dirstate.copy(f, fd)
                 if f2:
                     repo.dirstate.copy(f2, fd)
             else:
                 repo.dirstate.normal(fd)
                 if f:
                     repo.dirstate.forget(f)
 
 def update(repo, node, branchmerge, force, partial):
     """
     Perform a merge between the working directory and the given node
 
     node = the node to update to, or None if unspecified
     branchmerge = whether to merge between branches
     force = whether to force branch merging or file overwriting
     partial = a function to filter file lists (dirstate not updated)
 
     The table below shows all the behaviors of the update command
     given the -c and -C or no options, whether the working directory
     is dirty, whether a revision is specified, and the relationship of
     the parent rev to the target rev (linear, on the same named
     branch, or on another named branch).
 
     This logic is tested by test-update-branches.
 
     -c  -C  dirty  rev  |  linear   same  cross
      n   n    n     n   |    ok     (1)     x
      n   n    n     y   |    ok     ok     ok
      n   n    y     *   |   merge   (2)    (2)
      n   y    *     *   |    ---  discard  ---
      y   n    y     *   |    ---    (3)    ---
      y   n    n     *   |    ---    ok     ---
      y   y    *     *   |    ---    (4)    ---
 
     x = can't happen
     * = don't-care
     1 = abort: crosses branches (use 'hg merge' or 'hg update -c')
     2 = abort: crosses branches (use 'hg merge' to merge or
                  use 'hg update -C' to discard changes)
     3 = abort: uncommitted local changes
     4 = incompatible options (checked in commands.py)
     """
 
     onode = node
     wlock = repo.wlock()
     try:
         wc = repo[None]
         if node is None:
             # tip of current branch
             try:
                 node = repo.branchtags()[wc.branch()]
             except KeyError:
                 if wc.branch() == "default": # no default branch!
                     node = repo.lookup("tip") # update to tip
                 else:
                     raise util.Abort(_("branch %s not found") % wc.branch())
         overwrite = force and not branchmerge
         pl = wc.parents()
         p1, p2 = pl[0], repo[node]
         pa = p1.ancestor(p2)
         fp1, fp2, xp1, xp2 = p1.node(), p2.node(), str(p1), str(p2)
         fastforward = False
 
         ### check phase
         if not overwrite and len(pl) > 1:
             raise util.Abort(_("outstanding uncommitted merges"))
         if branchmerge:
             if pa == p2:
                 raise util.Abort(_("merging with a working directory ancestor"
                                    " has no effect"))
             elif pa == p1:
                 if p1.branch() != p2.branch():
                     fastforward = True
                 else:
                     raise util.Abort(_("nothing to merge (use 'hg update'"
                                        " or check 'hg heads')"))
             if not force and (wc.files() or wc.deleted()):
                 raise util.Abort(_("outstanding uncommitted changes "
                                    "(use 'hg status' to list changes)"))
         elif not overwrite:
             if pa == p1 or pa == p2: # linear
                 pass # all good
             elif wc.files() or wc.deleted():
                 raise util.Abort(_("crosses branches (use 'hg merge' to merge "
                                  "or use 'hg update -C' to discard changes)"))
             elif onode is None:
                 raise util.Abort(_("crosses branches (use 'hg merge' or use "
                                    "'hg update -c')"))
             else:
                 # Allow jumping branches if clean and specific rev given
                 overwrite = True
 
         ### calculate phase
         action = []
         wc.status(unknown=True) # prime cache
         if not force:
             _checkunknown(wc, p2)
         if not util.checkcase(repo.path):
             _checkcollision(p2)
         action += _forgetremoved(wc, p2, branchmerge)
         action += manifestmerge(repo, wc, p2, pa, overwrite, partial)
 
         ### apply phase
         if not branchmerge: # just jump to the new rev
             fp1, fp2, xp1, xp2 = fp2, nullid, xp2, ''
         if not partial:
             repo.hook('preupdate', throw=True, parent1=xp1, parent2=xp2)
 
         stats = applyupdates(repo, action, wc, p2, pa)
 
         if not partial:
             repo.dirstate.setparents(fp1, fp2)
             recordupdates(repo, action, branchmerge)
             if not branchmerge and not fastforward:
                 repo.dirstate.setbranch(p2.branch())
     finally:
         wlock.release()
 
     if not partial:
         repo.hook('update', parent1=xp1, parent2=xp2, error=stats[3])
     return stats