scmutil: use new dirs class in dirstate and context

The multiset-of-directories code was open coded in each of these
modules; this change gets rid of the duplication.

mercurial/context.py

@@ -1,1380 +1,1371 b''
 # 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, bin
 from i18n import _
 import ancestor, mdiff, error, util, scmutil, subrepo, patch, encoding, phases
 import copies
 import match as matchmod
 import os, errno, stat
 import obsolete as obsmod
 import repoview
 
 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, int):
             try:
                 self._node = repo.changelog.node(changeid)
             except IndexError:
                 raise error.RepoLookupError(
                     _("unknown revision '%s'") % changeid)
             self._rev = changeid
             return
         if isinstance(changeid, long):
             changeid = str(changeid)
         if changeid == '.':
             self._node = repo.dirstate.p1()
             self._rev = repo.changelog.rev(self._node)
             return
         if changeid == 'null':
             self._node = nullid
             self._rev = nullrev
             return
         if changeid == 'tip':
             self._node = repo.changelog.tip()
             self._rev = repo.changelog.rev(self._node)
             return
         if len(changeid) == 20:
             try:
                 self._node = changeid
                 self._rev = repo.changelog.rev(changeid)
                 return
             except LookupError:
                 pass
 
         try:
             r = int(changeid)
             if str(r) != changeid:
                 raise ValueError
             l = len(repo.changelog)
             if r < 0:
                 r += l
             if r < 0 or r >= l:
                 raise ValueError
             self._rev = r
             self._node = repo.changelog.node(r)
             return
         except (ValueError, OverflowError, IndexError):
             pass
 
         if len(changeid) == 40:
             try:
                 self._node = bin(changeid)
                 self._rev = repo.changelog.rev(self._node)
                 return
             except (TypeError, LookupError):
                 pass
 
         if changeid in repo._bookmarks:
             self._node = repo._bookmarks[changeid]
             self._rev = repo.changelog.rev(self._node)
             return
         if changeid in repo._tagscache.tags:
             self._node = repo._tagscache.tags[changeid]
             self._rev = repo.changelog.rev(self._node)
             return
         try:
             self._node = repo.branchtip(changeid)
             self._rev = repo.changelog.rev(self._node)
             return
         except error.RepoLookupError:
             pass
 
         self._node = repo.changelog._partialmatch(changeid)
         if self._node is not None:
             self._rev = repo.changelog.rev(self._node)
             return
 
         # lookup failed
         # check if it might have come from damaged dirstate
         #
         # XXX we could avoid the unfiltered if we had a recognizable exception
         # for filtered changeset access
         if changeid in repo.unfiltered().dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(changeid))
         try:
             if len(changeid) == 20:
                 changeid = hex(changeid)
         except TypeError:
             pass
         raise error.RepoLookupError(
             _("unknown revision '%s'") % changeid)
 
     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.rev())
 
     @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, self._repo.ui)
 
     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 encoding.tolocal(self._changeset[5].get("branch"))
     def closesbranch(self):
         return 'close' in self._changeset[5]
     def extra(self):
         return self._changeset[5]
     def tags(self):
         return self._repo.nodetags(self._node)
     def bookmarks(self):
         return self._repo.nodebookmarks(self._node)
     def phase(self):
         return self._repo._phasecache.phase(self._repo, self._rev)
     def phasestr(self):
         return phases.phasenames[self.phase()]
     def mutable(self):
         return self.phase() > phases.public
     def hidden(self):
         return self._rev in repoview.filterrevs(self._repo, 'visible')
 
     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 obsolete(self):
         """True if the changeset is obsolete"""
         return self.rev() in obsmod.getrevs(self._repo, 'obsolete')
 
     def extinct(self):
         """True if the changeset is extinct"""
         return self.rev() in obsmod.getrevs(self._repo, 'extinct')
 
     def unstable(self):
         """True if the changeset is not obsolete but it's ancestor are"""
         return self.rev() in obsmod.getrevs(self._repo, 'unstable')
 
     def bumped(self):
         """True if the changeset try to be a successor of a public changeset
 
         Only non-public and non-obsolete changesets may be bumped.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'bumped')
 
     def divergent(self):
         """Is a successors of a changeset with multiple possible successors set
 
         Only non-public and non-obsolete changesets may be divergent.
         """
         return self.rev() in obsmod.getrevs(self._repo, 'divergent')
 
     def troubled(self):
         """True if the changeset is either unstable, bumped or divergent"""
         return self.unstable() or self.bumped() or self.divergent()
 
     def troubles(self):
         """return the list of troubles affecting this changesets.
 
         Troubles are returned as strings. possible values are:
         - unstable,
         - bumped,
         - divergent.
         """
         troubles = []
         if self.unstable():
             troubles.append('unstable')
         if self.bumped():
             troubles.append('bumped')
         if self.divergent():
             troubles.append('divergent')
         return troubles
 
     def _fileinfo(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest[path], self._manifest.flags(path)
             except KeyError:
                 raise error.ManifestLookupError(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.ManifestLookupError(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 is None:
             n2 = c2._parents[0]._node
         n = self._repo.changelog.ancestor(self._node, n2)
         return changectx(self._repo, n)
 
     def descendant(self, other):
         """True if other is descendant of this changeset"""
         return self._repo.changelog.descendant(self._rev, other._rev)
 
     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:
             if fn in fset:
                 # specified pattern is the exact name
                 fset.remove(fn)
             if match(fn):
                 yield fn
         for fn in sorted(fset):
             if fn in self._dirs:
                 # specified pattern is a directory
                 continue
             if match.bad(fn, _('no such file in rev %s') % self) and match(fn):
                 yield fn
 
     def sub(self, path):
         return subrepo.subrepo(self, path)
 
     def match(self, pats=[], include=None, exclude=None, default='glob'):
         r = self._repo
         return matchmod.match(r.root, r.getcwd(), pats,
                               include, exclude, default,
                               auditor=r.auditor, ctx=self)
 
     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)
 
     @propertycache
     def _dirs(self):
-        dirs = set()
-        for f in self._manifest:
-            pos = f.rfind('/')
-            while pos != -1:
-                f = f[:pos]
-                if f in dirs:
-                    break # dirs already contains this and above
-                dirs.add(f)
-                pos = f.rfind('/')
-        return dirs
+        return scmutil.dirs(self._manifest)
 
     def dirs(self):
         return self._dirs
 
     def dirty(self):
         return False
 
 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):
         try:
             return changectx(self._repo, self._changeid)
         except error.RepoLookupError:
             # Linkrev may point to any revision in the repository.  When the
             # repository is filtered this may lead to `filectx` trying to build
             # `changectx` for filtered revision. In such case we fallback to
             # creating `changectx` on the unfiltered version of the reposition.
             # This fallback should not be an issue because `changectx` from
             # `filectx` are not used in complex operations that care about
             # filtering.
             #
             # This fallback is a cheap and dirty fix that prevent several
             # crashes. It does not ensure the behavior is correct. However the
             # behavior was not correct before filtering either and "incorrect
             # behavior" is seen as better as "crash"
             #
             # Linkrevs have several serious troubles with filtering that are
             # complicated to solve. Proper handling of the issue here should be
             # considered when solving linkrev issue are on the table.
             return changectx(self._repo.unfiltered(), 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 phase(self):
         return self._changectx.phase()
     def phasestr(self):
         return self._changectx.phasestr()
     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 isbinary(self):
         try:
             return util.binary(self.data())
         except IOError:
             return False
 
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         if (fctx._filerev is None
             and (self._repo._encodefilterpats
                  # if file data starts with '\1\n', empty metadata block is
                  # prepended, which adds 4 bytes to filelog.size().
                  or self.size() - 4 == fctx.size())
             or self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
 
         return True
 
     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 p1(self):
         return self.parents()[0]
 
     def p2(self):
         p = self.parents()
         if len(p) == 2:
             return p[1]
         return filectx(self._repo, self._path, fileid=-1, filelog=self._filelog)
 
     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, diffopts=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):
             blocks = mdiff.allblocks(parent[1], child[1], opts=diffopts,
                                      refine=True)
             for (a1, a2, b1, b2), t in blocks:
                 # Changed blocks ('!') or blocks made only of blank lines ('~')
                 # belong to the child.
                 if t == '=':
                     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
 
         # This algorithm would prefer to be recursive, but Python is a
         # bit recursion-hostile. Instead we do an iterative
         # depth-first search.
 
         visit = [base]
         hist = {}
         pcache = {}
         needed = {base: 1}
         while visit:
             f = visit[-1]
             if f not in pcache:
                 pcache[f] = parents(f)
 
             ready = True
             pl = pcache[f]
             for p in pl:
                 if p not in hist:
                     ready = False
                     visit.append(p)
                     needed[p] = needed.get(p, 0) + 1
             if ready:
                 visit.pop()
                 curr = decorate(f.data(), f)
                 for p in pl:
                     curr = pair(hist[p], curr)
                     if needed[p] == 1:
                         del hist[p]
                     else:
                         needed[p] -= 1
 
                 hist[f] = curr
                 pcache[f] = []
 
         return zip(hist[base][0], hist[base][1].splitlines(True))
 
     def ancestor(self, fc2, actx):
         """
         find the common ancestor file context, if any, of self, and fc2
 
         actx must be the changectx of the common ancestor
         of self's and fc2's respective changesets.
         """
 
         # the easy case: no (relevant) renames
         if fc2.path() == self.path() and self.path() in actx:
             return actx[self.path()]
 
         # the next easiest cases: unambiguous predecessor (name trumps
         # history)
         if self.path() in actx and fc2.path() not in actx:
             return actx[self.path()]
         if fc2.path() in actx and self.path() not in actx:
             return actx[fc2.path()]
 
         # prime the ancestor cache for the working directory
         acache = {}
         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, followfirst=False):
         visit = {}
         c = self
         cut = followfirst and 1 or None
         while True:
             for parent in c.parents()[:cut]:
                 visit[(parent.rev(), parent.node())] = parent
             if not visit:
                 break
             c = visit.pop(max(visit))
             yield c
 
     def copies(self, c2):
         if not util.safehasattr(self, "_copycache"):
             self._copycache = {}
         sc2 = str(c2)
         if sc2 not in self._copycache:
             self._copycache[sc2] = copies.pathcopies(c2)
         return self._copycache[sc2]
 
 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:
             try:
                 branch = encoding.fromlocal(self._repo.dirstate.branch())
             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 __repr__(self):
         return "<workingctx %s>" % str(self)
 
     def __nonzero__(self):
         return True
 
     def __contains__(self, key):
         return self._repo.dirstate[key] not in "?r"
 
     def _buildflagfunc(self):
         # Create a fallback function for getting file flags when the
         # filesystem doesn't support them
 
         copiesget = self._repo.dirstate.copies().get
 
         if len(self._parents) < 2:
             # when we have one parent, it's easy: copy from parent
             man = self._parents[0].manifest()
             def func(f):
                 f = copiesget(f, f)
                 return man.flags(f)
         else:
             # merges are tricky: we try to reconstruct the unstored
             # result from the merge (issue1802)
             p1, p2 = self._parents
             pa = p1.ancestor(p2)
             m1, m2, ma = p1.manifest(), p2.manifest(), pa.manifest()
 
             def func(f):
                 f = copiesget(f, f) # may be wrong for merges with copies
                 fl1, fl2, fla = m1.flags(f), m2.flags(f), ma.flags(f)
                 if fl1 == fl2:
                     return fl1
                 if fl1 == fla:
                     return fl2
                 if fl2 == fla:
                     return fl1
                 return '' # punt for conflicts
 
         return func
 
     @propertycache
     def _flagfunc(self):
         return self._repo.dirstate.flagfunc(self._buildflagfunc)
 
     @propertycache
     def _manifest(self):
         """generate a manifest corresponding to the working directory"""
 
         man = self._parents[0].manifest().copy()
         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
 
         copied = self._repo.dirstate.copies()
         ff = self._flagfunc
         modified, added, removed, deleted = self._status
         for i, l in (("a", added), ("m", modified)):
             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
 
     def __iter__(self):
         d = self._repo.dirstate
         for f in d:
             if d[f] != 'r':
                 yield f
 
     @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]
         return [changectx(self._repo, x) for x in p]
 
     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 encoding.tolocal(self._extra['branch'])
     def closesbranch(self):
         return 'close' in self._extra
     def extra(self):
         return self._extra
 
     def tags(self):
         t = []
         for p in self.parents():
             t.extend(p.tags())
         return t
 
     def bookmarks(self):
         b = []
         for p in self.parents():
             b.extend(p.bookmarks())
         return b
 
     def phase(self):
         phase = phases.draft # default phase to draft
         for p in self.parents():
             phase = max(phase, p.phase())
         return phase
 
     def hidden(self):
         return False
 
     def children(self):
         return []
 
     def flags(self, path):
         if '_manifest' in self.__dict__:
             try:
                 return self._manifest.flags(path)
             except KeyError:
                 return ''
 
         try:
             return self._flagfunc(path)
         except OSError:
             return ''
 
     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, sorted(self.substate),
                                                True, False))
 
     def dirty(self, missing=False, merge=True, branch=True):
         "check whether a working directory is modified"
         # check subrepos first
         for s in sorted(self.substate):
             if self.sub(s).dirty():
                 return True
         # check current working dir
         return ((merge and self.p2()) or
                 (branch and self.branch() != self.p1().branch()) or
                 self.modified() or self.added() or self.removed() or
                 (missing and self.deleted()))
 
     def add(self, list, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         wlock = self._repo.wlock()
         ui, ds = self._repo.ui, self._repo.dirstate
         try:
             rejected = []
             for f in list:
                 scmutil.checkportable(ui, join(f))
                 p = self._repo.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except OSError:
                     ui.warn(_("%s does not exist!\n") % join(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, join(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") % join(f))
                     rejected.append(p)
                 elif ds[f] in 'amn':
                     ui.warn(_("%s already tracked!\n") % join(f))
                 elif ds[f] == 'r':
                     ds.normallookup(f)
                 else:
                     ds.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, files, prefix=""):
         join = lambda f: os.path.join(prefix, f)
         wlock = self._repo.wlock()
         try:
             rejected = []
             for f in files:
                 if f not in self._repo.dirstate:
                     self._repo.ui.warn(_("%s not tracked!\n") % join(f))
                     rejected.append(f)
                 elif self._repo.dirstate[f] != 'a':
                     self._repo.dirstate.remove(f)
                 else:
                     self._repo.dirstate.drop(f)
             return rejected
         finally:
             wlock.release()
 
     def ancestors(self):
         for a in self._repo.changelog.ancestors(
             [p.rev() for p in self._parents]):
             yield changectx(self._repo, a)
 
     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][f] or pctxs[1][f]
                     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.lexists(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()
 
     def markcommitted(self, node):
         """Perform post-commit cleanup necessary after commiting this workingctx
 
         Specifically, this updates backing stores this working context
         wraps to reflect the fact that the changes reflected by this
         workingctx have been committed.  For example, it marks
         modified and added files as normal in the dirstate.
 
         """
 
         for f in self.modified() + self.added():
             self._repo.dirstate.normal(f)
         for f in self.removed():
             self._repo.dirstate.drop(f)
         self._repo.dirstate.setparents(node)
 
     def dirs(self):
-        return set(self._repo.dirstate.dirs())
+        return self._repo.dirstate.dirs()
 
 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 __repr__(self):
         return "<workingfilectx %s>" % str(self)
 
     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, fctx):
         """compare with other file context
 
         returns True if different than fctx.
         """
         # fctx should be a filectx (not a workingfilectx)
         # invert comparison to reuse the same code path
         return fctx.cmp(self)
 
 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 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 encoding.tolocal(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/copies.py

@@ -1,388 +1,388 b''
 # copies.py - copy detection for Mercurial
 #
 # Copyright 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.
 
 import util
 import heapq
 
 def _nonoverlap(d1, d2, d3):
     "Return list of elements in d1 not in d2 or d3"
     return sorted([d for d in d1 if d not in d3 and d not in d2])
 
 def _dirname(f):
     s = f.rfind("/")
     if s == -1:
         return ""
     return f[:s]
 
 def _findlimit(repo, a, b):
     """Find the earliest revision that's an ancestor of a or b but not both,
     None if no such revision exists.
     """
     # basic idea:
     # - mark a and b with different sides
     # - if a parent's children are all on the same side, the parent is
     #   on that side, otherwise it is on no side
     # - walk the graph in topological order with the help of a heap;
     #   - add unseen parents to side map
     #   - clear side of any parent that has children on different sides
     #   - track number of interesting revs that might still be on a side
     #   - track the lowest interesting rev seen
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
     working = len(cl) # pseudo rev for the working directory
     if a is None:
         a = working
     if b is None:
         b = working
 
     side = {a: -1, b: 1}
     visit = [-a, -b]
     heapq.heapify(visit)
     interesting = len(visit)
     hascommonancestor = False
     limit = working
 
     while interesting:
         r = -heapq.heappop(visit)
         if r == working:
             parents = [cl.rev(p) for p in repo.dirstate.parents()]
         else:
             parents = cl.parentrevs(r)
         for p in parents:
             if p < 0:
                 continue
             if p not in side:
                 # first time we see p; add it to visit
                 side[p] = side[r]
                 if side[p]:
                     interesting += 1
                 heapq.heappush(visit, -p)
             elif side[p] and side[p] != side[r]:
                 # p was interesting but now we know better
                 side[p] = 0
                 interesting -= 1
                 hascommonancestor = True
         if side[r]:
             limit = r # lowest rev visited
             interesting -= 1
 
     if not hascommonancestor:
         return None
     return limit
 
 def _chain(src, dst, a, b):
     '''chain two sets of copies a->b'''
     t = a.copy()
     for k, v in b.iteritems():
         if v in t:
             # found a chain
             if t[v] != k:
                 # file wasn't renamed back to itself
                 t[k] = t[v]
             if v not in dst:
                 # chain was a rename, not a copy
                 del t[v]
         if v in src:
             # file is a copy of an existing file
             t[k] = v
 
     # remove criss-crossed copies
     for k, v in t.items():
         if k in src and v in dst:
             del t[k]
 
     return t
 
 def _tracefile(fctx, actx):
     '''return file context that is the ancestor of fctx present in actx'''
     stop = actx.rev()
     am = actx.manifest()
 
     for f in fctx.ancestors():
         if am.get(f.path(), None) == f.filenode():
             return f
         if f.rev() < stop:
             return None
 
 def _dirstatecopies(d):
     ds = d._repo.dirstate
     c = ds.copies().copy()
     for k in c.keys():
         if ds[k] not in 'anm':
             del c[k]
     return c
 
 def _forwardcopies(a, b):
     '''find {dst@b: src@a} copy mapping where a is an ancestor of b'''
 
     # check for working copy
     w = None
     if b.rev() is None:
         w = b
         b = w.p1()
         if a == b:
             # short-circuit to avoid issues with merge states
             return _dirstatecopies(w)
 
     # find where new files came from
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
     missing = set(b.manifest().iterkeys())
     missing.difference_update(a.manifest().iterkeys())
 
     for f in missing:
         ofctx = _tracefile(b[f], a)
         if ofctx:
             cm[f] = ofctx.path()
 
     # combine copies from dirstate if necessary
     if w is not None:
         cm = _chain(a, w, cm, _dirstatecopies(w))
 
     return cm
 
 def _backwardrenames(a, b):
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(f.iteritems()):
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 def pathcopies(x, y):
     '''find {dst@y: src@x} copy mapping for directed compare'''
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
         return _forwardcopies(x, y)
     if a == y:
         return _backwardrenames(x, y)
     return _chain(x, y, _backwardrenames(x, a), _forwardcopies(a, y))
 
 def mergecopies(repo, c1, c2, ca):
     """
     Find moves and copies between context c1 and c2 that are relevant
     for merging.
 
     Returns four dicts: "copy", "movewithdir", "diverge", and
     "renamedelete".
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return {}, {}, {}, {}
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return repo.dirstate.copies(), {}, {}, {}
 
     limit = _findlimit(repo, c1.rev(), c2.rev())
     if limit is None:
         # no common ancestor, no copies
         return {}, {}, {}, {}
     m1 = c1.manifest()
     m2 = c2.manifest()
     ma = ca.manifest()
 
     def makectx(f, n):
         if len(n) != 20: # in a working context?
             if c1.rev() is None:
                 return c1.filectx(f)
             return c2.filectx(f)
         return repo.filectx(f, fileid=n)
 
     ctx = util.lrucachefunc(makectx)
     copy = {}
     movewithdir = {}
     fullcopy = {}
     diverge = {}
 
     def related(f1, f2, limit):
         # Walk back to common ancestor to see if the two files originate
         # from the same file. Since workingfilectx's rev() is None it messes
         # up the integer comparison logic, hence the pre-step check for
         # None (f1 and f2 can only be workingfilectx's initially).
 
         if f1 == f2:
             return f1 # a match
 
         g1, g2 = f1.ancestors(), f2.ancestors()
         try:
             f1r, f2r = f1.rev(), f2.rev()
 
             if f1r is None:
                 f1 = g1.next()
             if f2r is None:
                 f2 = g2.next()
 
             while True:
                 f1r, f2r = f1.rev(), f2.rev()
                 if f1r > f2r:
                     f1 = g1.next()
                 elif f2r > f1r:
                     f2 = g2.next()
                 elif f1 == f2:
                     return f1 # a match
                 elif f1r == f2r or f1r < limit or f2r < limit:
                     return False # copy no longer relevant
         except StopIteration:
             return False
 
     def checkcopies(f, m1, m2):
         '''check possible copies of f from m1 to m2'''
         of = None
         seen = set([f])
         for oc in ctx(f, m1[f]).ancestors():
             ocr = oc.rev()
             of = oc.path()
             if of in seen:
                 # check limit late - grab last rename before
                 if ocr < limit:
                     break
                 continue
             seen.add(of)
 
             fullcopy[f] = of # remember for dir rename detection
             if of not in m2:
                 continue # no match, keep looking
             if m2[of] == ma.get(of):
                 break # no merge needed, quit early
             c2 = ctx(of, m2[of])
             cr = related(oc, c2, ca.rev())
             if cr and (of == f or of == c2.path()): # non-divergent
                 copy[f] = of
                 of = None
                 break
 
         if of in ma:
             diverge.setdefault(of, []).append(f)
 
     repo.ui.debug("  searching for copies back to rev %d\n" % limit)
 
     u1 = _nonoverlap(m1, m2, ma)
     u2 = _nonoverlap(m2, m1, ma)
 
     if u1:
         repo.ui.debug("  unmatched files in local:\n   %s\n"
                       % "\n   ".join(u1))
     if u2:
         repo.ui.debug("  unmatched files in other:\n   %s\n"
                       % "\n   ".join(u2))
 
     for f in u1:
         checkcopies(f, m1, m2)
     for f in u2:
         checkcopies(f, m2, m1)
 
     renamedelete = {}
     renamedelete2 = set()
     diverge2 = set()
     for of, fl in diverge.items():
         if len(fl) == 1 or of in c1 or of in c2:
             del diverge[of] # not actually divergent, or not a rename
             if of not in c1 and of not in c2:
                 # renamed on one side, deleted on the other side, but filter
                 # out files that have been renamed and then deleted
                 renamedelete[of] = [f for f in fl if f in c1 or f in c2]
                 renamedelete2.update(fl) # reverse map for below
         else:
             diverge2.update(fl) # reverse map for below
 
     if fullcopy:
         repo.ui.debug("  all copies found (* = to merge, ! = divergent, "
                       "% = renamed and deleted):\n")
         for f in sorted(fullcopy):
             note = ""
             if f in copy:
                 note += "*"
             if f in diverge2:
                 note += "!"
             if f in renamedelete2:
                 note += "%"
             repo.ui.debug("   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f,
                                                               note))
     del diverge2
 
     if not fullcopy:
         return copy, movewithdir, diverge, renamedelete
 
     repo.ui.debug("  checking for directory renames\n")
 
     # generate a directory move map
     d1, d2 = c1.dirs(), c2.dirs()
-    d1.add('')
-    d2.add('')
+    d1.addpath('/')
+    d2.addpath('/')
     invalid = set()
     dirmove = {}
 
     # examine each file copy for a potential directory move, which is
     # when all the files in a directory are moved to a new directory
     for dst, src in fullcopy.iteritems():
         dsrc, ddst = _dirname(src), _dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif dsrc in d1 and ddst in d1:
             # directory wasn't entirely moved locally
             invalid.add(dsrc)
         elif dsrc in d2 and ddst in d2:
             # directory wasn't entirely moved remotely
             invalid.add(dsrc)
         elif dsrc in dirmove and dirmove[dsrc] != ddst:
             # files from the same directory moved to two different places
             invalid.add(dsrc)
         else:
             # looks good so far
             dirmove[dsrc + "/"] = ddst + "/"
 
     for i in invalid:
         if i in dirmove:
             del dirmove[i]
     del d1, d2, invalid
 
     if not dirmove:
         return copy, movewithdir, diverge, renamedelete
 
     for d in dirmove:
         repo.ui.debug("   discovered dir src: '%s' -> dst: '%s'\n" %
                       (d, dirmove[d]))
 
     # check unaccounted nonoverlapping files against directory moves
     for f in u1 + u2:
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
                     # new file added in a directory that was moved, move it
                     df = dirmove[d] + f[len(d):]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(("   pending file src: '%s' -> "
                                        "dst: '%s'\n") % (f, df))
                     break
 
     return copy, movewithdir, diverge, renamedelete

mercurial/dirstate.py

@@ -1,832 +1,814 b''
 # dirstate.py - working directory tracking 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.
 import errno
 
 from node import nullid
 from i18n import _
 import scmutil, util, ignore, osutil, parsers, encoding
 import os, stat, errno, gc
 
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7fffffff
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
-def _incdirs(dirs, path):
-    for base in scmutil.finddirs(path):
-        if base in dirs:
-            dirs[base] += 1
-            return
-        dirs[base] = 1
-
-def _decdirs(dirs, path):
-    for base in scmutil.finddirs(path):
-        if dirs[base] > 1:
-            dirs[base] -= 1
-            return
-        del dirs[base]
-
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         self._rootdir = os.path.join(root, '')
         self._dirty = False
         self._dirtypl = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _foldmap(self):
         f = {}
         for name in self._map:
             f[util.normcase(name)] = name
         for name in self._dirs:
             f[util.normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             fp = self._opener("dirstate")
             st = fp.read(40)
             fp.close()
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise util.Abort(_('working directory state appears damaged!'))
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
-        dirs = {}
-        for f, s in self._map.iteritems():
-            if s[0] != 'r':
-                _incdirs(dirs, f)
-        return dirs
+        return scmutil.dirs(self._map, 'r')
 
     def dirs(self):
         return self._dirs
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = [self._join('.hgignore')]
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 files.append(util.expandpath(path))
         return ignore.ignore(self._root, files, self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and os.sep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.checkcase(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return 'l'
                     if util.statisexec(st):
                         return 'x'
                 except OSError:
                     pass
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += os.sep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.normpath(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def iteritems(self):
         return self._map.iteritems()
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         self._dirty = self._dirtypl = True
         oldp2 = self._pl[1]
         self._pl = p1, p2
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             # Discard 'm' markers when moving away from a merge state
             for f, s in self._map.iteritems():
                 if s[0] == 'm':
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.normallookup(f)
         return copies
 
     def setbranch(self, branch):
         self._branch = encoding.fromlocal(branch)
         f = self._opener('branch', 'w', atomictemp=True)
         try:
             f.write(self._branch + '\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache['_branch']
             if ce:
                 ce.refresh()
         except: # re-raises
             f.discard()
             raise
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             st = self._opener.read("dirstate")
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         # Python's garbage collector triggers a GC each time a certain number
         # of container objects (the number being defined by
         # gc.get_threshold()) are allocated. parse_dirstate creates a tuple
         # for each file in the dirstate. The C version then immediately marks
         # them as not to be tracked by the collector. However, this has no
         # effect on when GCs are triggered, only on what objects the GC looks
         # into. This means that O(number of files) GCs are unavoidable.
         # Depending on when in the process's lifetime the dirstate is parsed,
         # this can get very expensive. As a workaround, disable GC while
         # parsing the dirstate.
         gcenabled = gc.isenabled()
         gc.disable()
         try:
             p = parsers.parse_dirstate(self._map, self._copymap, st)
         finally:
             if gcenabled:
                 gc.enable()
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in ("_map", "_copymap", "_foldmap", "_branch", "_pl", "_dirs",
                 "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
-            _decdirs(self._dirs, f)
+            self._dirs.delpath(f)
 
     def _addpath(self, f, state, mode, size, mtime):
         oldstate = self[f]
         if state == 'a' or oldstate == 'r':
             scmutil.checkfilename(f)
             if f in self._dirs:
                 raise util.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in scmutil.finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise util.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
-            _incdirs(self._dirs, f)
+            self._dirs.addpath(f)
         self._dirty = True
         self._map[f] = (state, mode, size, mtime)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         s = os.lstat(self._join(f))
         mtime = int(s.st_mtime)
         self._addpath(f, 'n', s.st_mode,
                       s.st_size & _rangemask, mtime & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.otherparent(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._addpath(f, 'n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise util.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         self._addpath(f, 'n', 0, -2, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, 'a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             # backup the previous state
             entry = self._map[f]
             if entry[0] == 'm': # merge
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2: # other parent
                 size = -2
         self._map[f] = ('r', 0, size, 0)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         s = os.lstat(self._join(f))
         self._addpath(f, 'm', s.st_mode,
                       s.st_size & _rangemask, int(s.st_mtime) & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         if f in self._map:
             self._dirty = True
             self._droppath(f)
             del self._map[f]
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._foldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 if exists is None:
                     exists = os.path.lexists(os.path.join(self._root, path))
                 if not exists:
                     # Maybe a path component exists
                     if not ignoremissing and '/' in path:
                         d, f = path.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, None)
                         folded = d + "/" + f
                     else:
                         # No path components, preserve original case
                         folded = path
                 else:
                     # recursively normalize leading directory components
                     # against dirstate
                     if '/' in normed:
                         d, f = normed.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, True)
                         r = self._root + "/" + d
                         folded = d + "/" + util.fspath(f, r)
                     else:
                         folded = util.fspath(normed, self._root)
                     self._foldmap[normed] = folded
 
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs")
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         changedfiles = changedfiles or allfiles
         oldmap = self._map
         self.clear()
         for f in allfiles:
             if f not in changedfiles:
                 self._map[f] = oldmap[f]
             else:
                 if 'x' in allfiles.flags(f):
                     self._map[f] = ('n', 0777, -1, 0)
                 else:
                     self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         st = self._opener("dirstate", "w", atomictemp=True)
 
         def finish(s):
             st.write(s)
             st.close()
             self._lastnormaltime = 0
             self._dirty = self._dirtypl = False
 
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st).st_mtime
         finish(parsers.pack_dirstate(self._map, self._copymap, self._pl, now))
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in scmutil.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def walk(self, match, subrepos, unknown, ignored):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
         '''
 
         def fwarn(f, msg):
             self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
             return False
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif not unknown:
             # if unknown and ignored are False, skip step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         badfn = match.bad
         dmap = self._map
         normpath = util.normpath
         listdir = osutil.listdir
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         work = []
         wadd = work.append
 
         exact = skipstep3 = False
         if matchfn == match.exact: # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.files() and not match.anypats(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             skipstep3 = False
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         # step 1: find all explicit files
         for ff in files:
             if normalize:
                 nf = normalize(normpath(ff), False, True)
             else:
                 nf = normpath(ff)
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     skipstep3 = False
                     if nf in dmap:
                         #file deleted on disk but still in dirstate
                         results[nf] = None
                     match.dir(nf)
                     if not dirignore(nf):
                         wadd(nf)
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError, inst:
                 if nf in dmap: # does it exactly match a file?
                     results[nf] = None
                 else: # does it match a directory?
                     prefix = nf + "/"
                     for fn in dmap:
                         if fn.startswith(prefix):
                             match.dir(nf)
                             skipstep3 = False
                             break
                     else:
                         badfn(ff, inst.strerror)
 
         # step 2: visit subdirectories
         while work:
             nd = work.pop()
             skip = None
             if nd == '.':
                 nd = ''
             else:
                 skip = '.hg'
             try:
                 entries = listdir(join(nd), stat=True, skip=skip)
             except OSError, inst:
                 if inst.errno in (errno.EACCES, errno.ENOENT):
                     fwarn(nd, inst.strerror)
                     continue
                 raise
             for f, kind, st in entries:
                 if normalize:
                     nf = normalize(nd and (nd + "/" + f) or f, True, True)
                 else:
                     nf = nd and (nd + "/" + f) or f
                 if nf not in results:
                     if kind == dirkind:
                         if not ignore(nf):
                             match.dir(nf)
                             wadd(nf)
                         if nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
                     elif kind == regkind or kind == lnkkind:
                         if nf in dmap:
                             if matchalways or matchfn(nf):
                                 results[nf] = st
                         elif (matchalways or matchfn(nf)) and not ignore(nf):
                             results[nf] = st
                     elif nf in dmap and (matchalways or matchfn(nf)):
                         results[nf] = None
 
         for s in subrepos:
             del results[s]
         del results['.hg']
 
         # step 3: report unseen items in the dmap hash
         if not skipstep3 and not exact:
             if not results and matchalways:
                 visit = dmap.keys()
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked the full directory tree above.
                 # So if a file is not seen it was either a) not matching matchfn
                 # b) ignored, c) missing, or d) under a symlink directory.
                 audit_path = scmutil.pathauditor(self._root)
 
                 for nf in iter(visit):
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     if ignore(nf) and audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat everything we missed.
                 nf = iter(visit).next
                 for st in util.statfiles([join(i) for i in visit]):
                     results[nf()] = st
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a tuple of lists (unsure, modified, added,
         removed, deleted, unknown, ignored, clean), where:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           added:
             files that have been explicitly added with hg add
           removed:
             files that have been explicitly removed with hg remove
           deleted:
             files that have been deleted through other means ("missing")
           unknown:
             files not in the dirstate that are not ignored
           ignored:
             files not in the dirstate that are ignored
             (by _dirignore())
           clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         checklink = self._checklink
         copymap = self._copymap
         lastnormaltime = self._lastnormaltime
 
         lnkkind = stat.S_IFLNK
 
         for fn, st in self.walk(match, subrepos, listunknown,
                                 listignored).iteritems():
             if fn not in dmap:
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 elif listunknown:
                     uadd(fn)
                 continue
 
             state, mode, size, time = dmap[fn]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 # The "mode & lnkkind != lnkkind or self._checklink"
                 # lines are an expansion of "islink => checklink"
                 # where islink means "is this a link?" and checklink
                 # means "can we check links?".
                 mtime = int(st.st_mtime)
                 if (size >= 0 and
                     ((size != st.st_size and size != st.st_size & _rangemask)
                      or ((mode ^ st.st_mode) & 0100 and checkexec))
                     and (mode & lnkkind != lnkkind or checklink)
                     or size == -2 # other parent
                     or fn in copymap):
                     madd(fn)
                 elif ((time != mtime and time != mtime & _rangemask)
                       and (mode & lnkkind != lnkkind or checklink)):
                     ladd(fn)
                 elif mtime == lastnormaltime:
                     # fn may have been changed in the same timeslot without
                     # changing its size. This can happen if we quickly do
                     # multiple commits in a single transaction.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)