vfs: add "notindexed" argument to invoke "ensuredir" with it in write mode

This patch uses "False" as default value of "notindexed" argument,
even though "vfs.makedir()" uses "True" for it, because "os.mkdir()"
doesn't set "_FILE_ATTRIBUTE_NOT_CONTENT_INDEXED" attribute to newly
created directories.

mercurial/scmutil.py

@@ -1,1046 +1,1060
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright 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 i18n import _
 from mercurial.node import nullrev
 import util, error, osutil, revset, similar, encoding, phases, parsers
 import pathutil
 import match as matchmod
 import os, errno, re, glob, tempfile
 
 if os.name == 'nt':
     import scmwindows as scmplatform
 else:
     import scmposix as scmplatform
 
 systemrcpath = scmplatform.systemrcpath
 userrcpath = scmplatform.userrcpath
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             if n not in repo:
                 # discovery should not have included the filtered revision,
                 # we have to explicitly exclude it until discovery is cleanup.
                 continue
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise util.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise util.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise util.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise util.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise util.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise util.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def tryread(self, path):
         '''gracefully return an empty string for missing files'''
         try:
             return self.read(path)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
         return ""
 
     def tryreadlines(self, path, mode='rb'):
         '''gracefully return an empty array for missing files'''
         try:
             return self.readlines(path, mode=mode)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
         return []
 
-    def open(self, path, mode="r", text=False, atomictemp=False):
+    def open(self, path, mode="r", text=False, atomictemp=False,
+             notindexed=False):
+        '''Open ``path`` file, which is relative to vfs root.
+
+        Newly created directories are marked as "not to be indexed by
+        the content indexing service", if ``notindexed`` is specified
+        for "write" mode access.
+        '''
         self.open = self.__call__
-        return self.__call__(path, mode, text, atomictemp)
+        return self.__call__(path, mode, text, atomictemp, notindexed)
 
     def read(self, path):
         fp = self(path, 'rb')
         try:
             return fp.read()
         finally:
             fp.close()
 
     def readlines(self, path, mode='rb'):
         fp = self(path, mode=mode)
         try:
             return fp.readlines()
         finally:
             fp.close()
 
     def write(self, path, data):
         fp = self(path, 'wb')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def append(self, path, data):
         fp = self(path, 'ab')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def chmod(self, path, mode):
         return os.chmod(self.join(path), mode)
 
     def exists(self, path=None):
         return os.path.exists(self.join(path))
 
     def fstat(self, fp):
         return util.fstat(fp)
 
     def isdir(self, path=None):
         return os.path.isdir(self.join(path))
 
     def isfile(self, path=None):
         return os.path.isfile(self.join(path))
 
     def islink(self, path=None):
         return os.path.islink(self.join(path))
 
     def lexists(self, path=None):
         return os.path.lexists(self.join(path))
 
     def lstat(self, path=None):
         return os.lstat(self.join(path))
 
     def listdir(self, path=None):
         return os.listdir(self.join(path))
 
     def makedir(self, path=None, notindexed=True):
         return util.makedir(self.join(path), notindexed)
 
     def makedirs(self, path=None, mode=None):
         return util.makedirs(self.join(path), mode)
 
     def makelock(self, info, path):
         return util.makelock(info, self.join(path))
 
     def mkdir(self, path=None):
         return os.mkdir(self.join(path))
 
     def mkstemp(self, suffix='', prefix='tmp', dir=None, text=False):
         fd, name = tempfile.mkstemp(suffix=suffix, prefix=prefix,
                                     dir=self.join(dir), text=text)
         dname, fname = util.split(name)
         if dir:
             return fd, os.path.join(dir, fname)
         else:
             return fd, fname
 
     def readdir(self, path=None, stat=None, skip=None):
         return osutil.listdir(self.join(path), stat, skip)
 
     def readlock(self, path):
         return util.readlock(self.join(path))
 
     def rename(self, src, dst):
         return util.rename(self.join(src), self.join(dst))
 
     def readlink(self, path):
         return os.readlink(self.join(path))
 
     def setflags(self, path, l, x):
         return util.setflags(self.join(path), l, x)
 
     def stat(self, path=None):
         return os.stat(self.join(path))
 
     def unlink(self, path=None):
         return util.unlink(self.join(path))
 
     def unlinkpath(self, path=None, ignoremissing=False):
         return util.unlinkpath(self.join(path), ignoremissing)
 
     def utime(self, path=None, t=None):
         return os.utime(self.join(path), t)
 
 class vfs(abstractvfs):
     '''Operate files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True, expandpath=False, realpath=False):
         if expandpath:
             base = util.expandpath(base)
         if realpath:
             base = os.path.realpath(base)
         self.base = base
         self._setmustaudit(audit)
         self.createmode = None
         self._trustnlink = None
 
     def _getmustaudit(self):
         return self._audit
 
     def _setmustaudit(self, onoff):
         self._audit = onoff
         if onoff:
             self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     @util.propertycache
     def _chmod(self):
         return util.checkexec(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None or not self._chmod:
             return
         os.chmod(name, self.createmode & 0666)
 
-    def __call__(self, path, mode="r", text=False, atomictemp=False):
+    def __call__(self, path, mode="r", text=False, atomictemp=False,
+                 notindexed=False):
+        '''Open ``path`` file, which is relative to vfs root.
+
+        Newly created directories are marked as "not to be indexed by
+        the content indexing service", if ``notindexed`` is specified
+        for "write" mode access.
+        '''
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise util.Abort("%s: %r" % (r, path))
         self.audit(path)
         f = self.join(path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ('r', 'rb'):
             dirname, basename = util.split(f)
             # If basename is empty, then the path is malformed because it points
             # to a directory. Let the posixfile() call below raise IOError.
             if basename:
                 if atomictemp:
-                    util.ensuredirs(dirname, self.createmode)
+                    util.ensuredirs(dirname, self.createmode, notindexed)
                     return util.atomictempfile(f, mode, self.createmode)
                 try:
                     if 'w' in mode:
                         util.unlink(f)
                         nlink = 0
                     else:
                         # nlinks() may behave differently for files on Windows
                         # shares if the file is open.
                         fd = util.posixfile(f)
                         nlink = util.nlinks(f)
                         if nlink < 1:
                             nlink = 2 # force mktempcopy (issue1922)
                         fd.close()
                 except (OSError, IOError), e:
                     if e.errno != errno.ENOENT:
                         raise
                     nlink = 0
-                    util.ensuredirs(dirname, self.createmode)
+                    util.ensuredirs(dirname, self.createmode, notindexed)
                 if nlink > 0:
                     if self._trustnlink is None:
                         self._trustnlink = nlink > 1 or util.checknlink(f)
                     if nlink > 1 or not self._trustnlink:
                         util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.audit(dst)
         linkname = self.join(dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         util.ensuredirs(os.path.dirname(linkname), self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError, err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             self.write(dst, src)
 
     def join(self, path):
         if path:
             return os.path.join(self.base, path)
         else:
             return self.base
 
 opener = vfs
 
 class auditvfs(object):
     def __init__(self, vfs):
         self.vfs = vfs
 
     def _getmustaudit(self):
         return self.vfs.mustaudit
 
     def _setmustaudit(self, onoff):
         self.vfs.mustaudit = onoff
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
 class filtervfs(abstractvfs, auditvfs):
     '''Wrapper vfs for filtering filenames with a function.'''
 
     def __init__(self, vfs, filter):
         auditvfs.__init__(self, vfs)
         self._filter = filter
 
     def __call__(self, path, *args, **kwargs):
         return self.vfs(self._filter(path), *args, **kwargs)
 
     def join(self, path):
         if path:
             return self.vfs.join(self._filter(path))
         else:
             return self.vfs.join(path)
 
 filteropener = filtervfs
 
 class readonlyvfs(abstractvfs, auditvfs):
     '''Wrapper vfs preventing any writing.'''
 
     def __init__(self, vfs):
         auditvfs.__init__(self, vfs)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb'):
             raise util.Abort('this vfs is read only')
         return self.vfs(path, mode, *args, **kw)
 
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = []
     defaultpath = os.path.join(util.datapath, 'default.d')
     if os.path.isdir(defaultpath):
         for f, kind in osutil.listdir(defaultpath):
             if f.endswith('.rc'):
                 path.append(os.path.join(defaultpath, f))
     path.extend(systemrcpath())
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 def revsingle(repo, revspec, default='.'):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if not l:
         raise util.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise util.Abort(_('empty revision range'))
 
     if first == second and len(revs) == 1 and _revrangesep not in revs[0]:
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 _revrangesep = ':'
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             return defval
         return repo[val].rev()
 
     seen, l = set(), revset.baseset([])
     for spec in revs:
         if l and not seen:
             seen = set(l)
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         try:
             if isinstance(spec, int):
                 seen.add(spec)
                 l = l + revset.baseset([spec])
                 continue
 
             if _revrangesep in spec:
                 start, end = spec.split(_revrangesep, 1)
                 start = revfix(repo, start, 0)
                 end = revfix(repo, end, len(repo) - 1)
                 if end == nullrev and start < 0:
                     start = nullrev
                 rangeiter = repo.changelog.revs(start, end)
                 if not seen and not l:
                     # by far the most common case: revs = ["-1:0"]
                     l = revset.baseset(rangeiter)
                     # defer syncing seen until next iteration
                     continue
                 newrevs = set(rangeiter)
                 if seen:
                     newrevs.difference_update(seen)
                     seen.update(newrevs)
                 else:
                     seen = newrevs
                 l = l + revset.baseset(sorted(newrevs, reverse=start > end))
                 continue
             elif spec and spec in repo: # single unquoted rev
                 rev = revfix(repo, spec, None)
                 if rev in seen:
                     continue
                 seen.add(rev)
                 l = l + revset.baseset([rev])
                 continue
         except error.RepoLookupError:
             pass
 
         # fall through to new-style queries if old-style fails
         m = revset.match(repo.ui, spec, repo)
         if seen or l:
             dl = [r for r in m(repo, revset.spanset(repo)) if r not in seen]
             l = l + revset.baseset(dl)
             seen.update(dl)
         else:
             l = m(repo, revset.spanset(repo))
 
     return l
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches.'''
     if pats == ("",):
         pats = []
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                          default)
     def badfn(f, msg):
         ctx._repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
     m.bad = badfn
     return m, pats
 
 def match(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files)
 
 def addremove(repo, pats=[], opts={}, dry_run=None, similarity=None):
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
     # we'd use status here, except handling of symlinks and ignore is tricky
     m = match(repo[None], pats, opts)
     rejected = []
     m.bad = lambda x, y: rejected.append(x)
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             rel = m.rel(abs)
             if abs in unknownset:
                 status = _('adding %s\n') % ((pats and rel) or abs)
             else:
                 status = _('removing %s\n') % ((pats and rel) or abs)
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files)
     rejected = []
     m.bad = lambda x, y: rejected.append(x)
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
                                 full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     wlock = repo.wlock()
     try:
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
     finally:
         wlock.release()
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see http://mercurial.selenic.com/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behaviour as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         return obj.join(fname)
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 class dirs(object):
     '''a multiset of directory names from a dirstate or manifest'''
 
     def __init__(self, map, skip=None):
         self._dirs = {}
         addpath = self.addpath
         if util.safehasattr(map, 'iteritems') and skip is not None:
             for f, s in map.iteritems():
                 if s[0] != skip:
                     addpath(f)
         else:
             for f in map:
                 addpath(f)
 
     def addpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if base in dirs:
                 dirs[base] += 1
                 return
             dirs[base] = 1
 
     def delpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if dirs[base] > 1:
                 dirs[base] -= 1
                 return
             del dirs[base]
 
     def __iter__(self):
         return self._dirs.iterkeys()
 
     def __contains__(self, d):
         return d in self._dirs
 
 if util.safehasattr(parsers, 'dirs'):
     dirs = parsers.dirs
 
 def finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)

mercurial/util.py

@@ -1,2186 +1,2191
 # util.py - Mercurial utility functions and platform specific implementations
 #
 #  Copyright 2005 K. Thananchayan <[e-mail]>
 #  Copyright 2005-2007 Matt Mackall <[e-mail]>
 #  Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Mercurial utility functions and platform specific implementations.
 
 This contains helper routines that are independent of the SCM core and
 hide platform-specific details from the core.
 """
 
 import i18n
 _ = i18n._
 import error, osutil, encoding
 import errno, shutil, sys, tempfile, traceback
 import re as remod
 import os, time, datetime, calendar, textwrap, signal, collections
 import imp, socket, urllib
 
 if os.name == 'nt':
     import windows as platform
 else:
     import posix as platform
 
 cachestat = platform.cachestat
 checkexec = platform.checkexec
 checklink = platform.checklink
 copymode = platform.copymode
 executablepath = platform.executablepath
 expandglobs = platform.expandglobs
 explainexit = platform.explainexit
 findexe = platform.findexe
 gethgcmd = platform.gethgcmd
 getuser = platform.getuser
 groupmembers = platform.groupmembers
 groupname = platform.groupname
 hidewindow = platform.hidewindow
 isexec = platform.isexec
 isowner = platform.isowner
 localpath = platform.localpath
 lookupreg = platform.lookupreg
 makedir = platform.makedir
 nlinks = platform.nlinks
 normpath = platform.normpath
 normcase = platform.normcase
 openhardlinks = platform.openhardlinks
 oslink = platform.oslink
 parsepatchoutput = platform.parsepatchoutput
 pconvert = platform.pconvert
 popen = platform.popen
 posixfile = platform.posixfile
 quotecommand = platform.quotecommand
 readpipe = platform.readpipe
 rename = platform.rename
 samedevice = platform.samedevice
 samefile = platform.samefile
 samestat = platform.samestat
 setbinary = platform.setbinary
 setflags = platform.setflags
 setsignalhandler = platform.setsignalhandler
 shellquote = platform.shellquote
 spawndetached = platform.spawndetached
 split = platform.split
 sshargs = platform.sshargs
 statfiles = getattr(osutil, 'statfiles', platform.statfiles)
 statisexec = platform.statisexec
 statislink = platform.statislink
 termwidth = platform.termwidth
 testpid = platform.testpid
 umask = platform.umask
 unlink = platform.unlink
 unlinkpath = platform.unlinkpath
 username = platform.username
 
 # Python compatibility
 
 _notset = object()
 
 def safehasattr(thing, attr):
     return getattr(thing, attr, _notset) is not _notset
 
 def sha1(s=''):
     '''
     Low-overhead wrapper around Python's SHA support
 
     >>> f = _fastsha1
     >>> a = sha1()
     >>> a = f()
     >>> a.hexdigest()
     'da39a3ee5e6b4b0d3255bfef95601890afd80709'
     '''
 
     return _fastsha1(s)
 
 def _fastsha1(s=''):
     # This function will import sha1 from hashlib or sha (whichever is
     # available) and overwrite itself with it on the first call.
     # Subsequent calls will go directly to the imported function.
     if sys.version_info >= (2, 5):
         from hashlib import sha1 as _sha1
     else:
         from sha import sha as _sha1
     global _fastsha1, sha1
     _fastsha1 = sha1 = _sha1
     return _sha1(s)
 
 def md5(s=''):
     try:
         from hashlib import md5 as _md5
     except ImportError:
         from md5 import md5 as _md5
     global md5
     md5 = _md5
     return _md5(s)
 
 DIGESTS = {
     'md5': md5,
     'sha1': sha1,
 }
 # List of digest types from strongest to weakest
 DIGESTS_BY_STRENGTH = ['sha1', 'md5']
 
 try:
     import hashlib
     DIGESTS.update({
         'sha512': hashlib.sha512,
     })
     DIGESTS_BY_STRENGTH.insert(0, 'sha512')
 except ImportError:
     pass
 
 for k in DIGESTS_BY_STRENGTH:
     assert k in DIGESTS
 
 class digester(object):
     """helper to compute digests.
 
     This helper can be used to compute one or more digests given their name.
 
     >>> d = digester(['md5', 'sha1'])
     >>> d.update('foo')
     >>> [k for k in sorted(d)]
     ['md5', 'sha1']
     >>> d['md5']
     'acbd18db4cc2f85cedef654fccc4a4d8'
     >>> d['sha1']
     '0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33'
     >>> digester.preferred(['md5', 'sha1'])
     'sha1'
     """
 
     def __init__(self, digests, s=''):
         self._hashes = {}
         for k in digests:
             if k not in DIGESTS:
                 raise Abort(_('unknown digest type: %s') % k)
             self._hashes[k] = DIGESTS[k]()
         if s:
             self.update(s)
 
     def update(self, data):
         for h in self._hashes.values():
             h.update(data)
 
     def __getitem__(self, key):
         if key not in DIGESTS:
             raise Abort(_('unknown digest type: %s') % k)
         return self._hashes[key].hexdigest()
 
     def __iter__(self):
         return iter(self._hashes)
 
     @staticmethod
     def preferred(supported):
         """returns the strongest digest type in both supported and DIGESTS."""
 
         for k in DIGESTS_BY_STRENGTH:
             if k in supported:
                 return k
         return None
 
 class digestchecker(object):
     """file handle wrapper that additionally checks content against a given
     size and digests.
 
         d = digestchecker(fh, size, {'md5': '...'})
 
     When multiple digests are given, all of them are validated.
     """
 
     def __init__(self, fh, size, digests):
         self._fh = fh
         self._size = size
         self._got = 0
         self._digests = dict(digests)
         self._digester = digester(self._digests.keys())
 
     def read(self, length=-1):
         content = self._fh.read(length)
         self._digester.update(content)
         self._got += len(content)
         return content
 
     def validate(self):
         if self._size != self._got:
             raise Abort(_('size mismatch: expected %d, got %d') %
                 (self._size, self._got))
         for k, v in self._digests.items():
             if v != self._digester[k]:
                 # i18n: first parameter is a digest name
                 raise Abort(_('%s mismatch: expected %s, got %s') %
                     (k, v, self._digester[k]))
 
 try:
     buffer = buffer
 except NameError:
     if sys.version_info[0] < 3:
         def buffer(sliceable, offset=0):
             return sliceable[offset:]
     else:
         def buffer(sliceable, offset=0):
             return memoryview(sliceable)[offset:]
 
 import subprocess
 closefds = os.name == 'posix'
 
 def popen2(cmd, env=None, newlines=False):
     # Setting bufsize to -1 lets the system decide the buffer size.
     # The default for bufsize is 0, meaning unbuffered. This leads to
     # poor performance on Mac OS X: http://bugs.python.org/issue4194
     p = subprocess.Popen(cmd, shell=True, bufsize=-1,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          universal_newlines=newlines,
                          env=env)
     return p.stdin, p.stdout
 
 def popen3(cmd, env=None, newlines=False):
     stdin, stdout, stderr, p = popen4(cmd, env, newlines)
     return stdin, stdout, stderr
 
 def popen4(cmd, env=None, newlines=False):
     p = subprocess.Popen(cmd, shell=True, bufsize=-1,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          stderr=subprocess.PIPE,
                          universal_newlines=newlines,
                          env=env)
     return p.stdin, p.stdout, p.stderr, p
 
 def version():
     """Return version information if available."""
     try:
         import __version__
         return __version__.version
     except ImportError:
         return 'unknown'
 
 # used by parsedate
 defaultdateformats = (
     '%Y-%m-%d %H:%M:%S',
     '%Y-%m-%d %I:%M:%S%p',
     '%Y-%m-%d %H:%M',
     '%Y-%m-%d %I:%M%p',
     '%Y-%m-%d',
     '%m-%d',
     '%m/%d',
     '%m/%d/%y',
     '%m/%d/%Y',
     '%a %b %d %H:%M:%S %Y',
     '%a %b %d %I:%M:%S%p %Y',
     '%a, %d %b %Y %H:%M:%S',        #  GNU coreutils "/bin/date --rfc-2822"
     '%b %d %H:%M:%S %Y',
     '%b %d %I:%M:%S%p %Y',
     '%b %d %H:%M:%S',
     '%b %d %I:%M:%S%p',
     '%b %d %H:%M',
     '%b %d %I:%M%p',
     '%b %d %Y',
     '%b %d',
     '%H:%M:%S',
     '%I:%M:%S%p',
     '%H:%M',
     '%I:%M%p',
 )
 
 extendeddateformats = defaultdateformats + (
     "%Y",
     "%Y-%m",
     "%b",
     "%b %Y",
     )
 
 def cachefunc(func):
     '''cache the result of function calls'''
     # XXX doesn't handle keywords args
     if func.func_code.co_argcount == 0:
         cache = []
         def f():
             if len(cache) == 0:
                 cache.append(func())
             return cache[0]
         return f
     cache = {}
     if func.func_code.co_argcount == 1:
         # we gain a small amount of time because
         # we don't need to pack/unpack the list
         def f(arg):
             if arg not in cache:
                 cache[arg] = func(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 cache[args] = func(*args)
             return cache[args]
 
     return f
 
 try:
     collections.deque.remove
     deque = collections.deque
 except AttributeError:
     # python 2.4 lacks deque.remove
     class deque(collections.deque):
         def remove(self, val):
             for i, v in enumerate(self):
                 if v == val:
                     del self[i]
                     break
 
 class sortdict(dict):
     '''a simple sorted dictionary'''
     def __init__(self, data=None):
         self._list = []
         if data:
             self.update(data)
     def copy(self):
         return sortdict(self)
     def __setitem__(self, key, val):
         if key in self:
             self._list.remove(key)
         self._list.append(key)
         dict.__setitem__(self, key, val)
     def __iter__(self):
         return self._list.__iter__()
     def update(self, src):
         for k in src:
             self[k] = src[k]
     def clear(self):
         dict.clear(self)
         self._list = []
     def items(self):
         return [(k, self[k]) for k in self._list]
     def __delitem__(self, key):
         dict.__delitem__(self, key)
         self._list.remove(key)
     def pop(self, key, *args, **kwargs):
         dict.pop(self, key, *args, **kwargs)
         try:
             self._list.remove(key)
         except ValueError:
             pass
     def keys(self):
         return self._list
     def iterkeys(self):
         return self._list.__iter__()
     def iteritems(self):
         for k in self._list:
             yield k, self[k]
     def insert(self, index, key, val):
         self._list.insert(index, key)
         dict.__setitem__(self, key, val)
 
 class lrucachedict(object):
     '''cache most recent gets from or sets to this dictionary'''
     def __init__(self, maxsize):
         self._cache = {}
         self._maxsize = maxsize
         self._order = deque()
 
     def __getitem__(self, key):
         value = self._cache[key]
         self._order.remove(key)
         self._order.append(key)
         return value
 
     def __setitem__(self, key, value):
         if key not in self._cache:
             if len(self._cache) >= self._maxsize:
                 del self._cache[self._order.popleft()]
         else:
             self._order.remove(key)
         self._cache[key] = value
         self._order.append(key)
 
     def __contains__(self, key):
         return key in self._cache
 
     def clear(self):
         self._cache.clear()
         self._order = deque()
 
 def lrucachefunc(func):
     '''cache most recent results of function calls'''
     cache = {}
     order = deque()
     if func.func_code.co_argcount == 1:
         def f(arg):
             if arg not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[arg] = func(arg)
             else:
                 order.remove(arg)
             order.append(arg)
             return cache[arg]
     else:
         def f(*args):
             if args not in cache:
                 if len(cache) > 20:
                     del cache[order.popleft()]
                 cache[args] = func(*args)
             else:
                 order.remove(args)
             order.append(args)
             return cache[args]
 
     return f
 
 class propertycache(object):
     def __init__(self, func):
         self.func = func
         self.name = func.__name__
     def __get__(self, obj, type=None):
         result = self.func(obj)
         self.cachevalue(obj, result)
         return result
 
     def cachevalue(self, obj, value):
         # __dict__ assignment required to bypass __setattr__ (eg: repoview)
         obj.__dict__[self.name] = value
 
 def pipefilter(s, cmd):
     '''filter string S through command CMD, returning its output'''
     p = subprocess.Popen(cmd, shell=True, close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE)
     pout, perr = p.communicate(s)
     return pout
 
 def tempfilter(s, cmd):
     '''filter string S through a pair of temporary files with CMD.
     CMD is used as a template to create the real command to be run,
     with the strings INFILE and OUTFILE replaced by the real names of
     the temporary files generated.'''
     inname, outname = None, None
     try:
         infd, inname = tempfile.mkstemp(prefix='hg-filter-in-')
         fp = os.fdopen(infd, 'wb')
         fp.write(s)
         fp.close()
         outfd, outname = tempfile.mkstemp(prefix='hg-filter-out-')
         os.close(outfd)
         cmd = cmd.replace('INFILE', inname)
         cmd = cmd.replace('OUTFILE', outname)
         code = os.system(cmd)
         if sys.platform == 'OpenVMS' and code & 1:
             code = 0
         if code:
             raise Abort(_("command '%s' failed: %s") %
                         (cmd, explainexit(code)))
         fp = open(outname, 'rb')
         r = fp.read()
         fp.close()
         return r
     finally:
         try:
             if inname:
                 os.unlink(inname)
         except OSError:
             pass
         try:
             if outname:
                 os.unlink(outname)
         except OSError:
             pass
 
 filtertable = {
     'tempfile:': tempfilter,
     'pipe:': pipefilter,
     }
 
 def filter(s, cmd):
     "filter a string through a command that transforms its input to its output"
     for name, fn in filtertable.iteritems():
         if cmd.startswith(name):
             return fn(s, cmd[len(name):].lstrip())
     return pipefilter(s, cmd)
 
 def binary(s):
     """return true if a string is binary data"""
     return bool(s and '\0' in s)
 
 def increasingchunks(source, min=1024, max=65536):
     '''return no less than min bytes per chunk while data remains,
     doubling min after each chunk until it reaches max'''
     def log2(x):
         if not x:
             return 0
         i = 0
         while x:
             x >>= 1
             i += 1
         return i - 1
 
     buf = []
     blen = 0
     for chunk in source:
         buf.append(chunk)
         blen += len(chunk)
         if blen >= min:
             if min < max:
                 min = min << 1
                 nmin = 1 << log2(blen)
                 if nmin > min:
                     min = nmin
                 if min > max:
                     min = max
             yield ''.join(buf)
             blen = 0
             buf = []
     if buf:
         yield ''.join(buf)
 
 Abort = error.Abort
 
 def always(fn):
     return True
 
 def never(fn):
     return False
 
 def pathto(root, n1, n2):
     '''return the relative path from one place to another.
     root should use os.sep to separate directories
     n1 should use os.sep to separate directories
     n2 should use "/" to separate directories
     returns an os.sep-separated path.
 
     If n1 is a relative path, it's assumed it's
     relative to root.
     n2 should always be relative to root.
     '''
     if not n1:
         return localpath(n2)
     if os.path.isabs(n1):
         if os.path.splitdrive(root)[0] != os.path.splitdrive(n1)[0]:
             return os.path.join(root, localpath(n2))
         n2 = '/'.join((pconvert(root), n2))
     a, b = splitpath(n1), n2.split('/')
     a.reverse()
     b.reverse()
     while a and b and a[-1] == b[-1]:
         a.pop()
         b.pop()
     b.reverse()
     return os.sep.join((['..'] * len(a)) + b) or '.'
 
 def mainfrozen():
     """return True if we are a frozen executable.
 
     The code supports py2exe (most common, Windows only) and tools/freeze
     (portable, not much used).
     """
     return (safehasattr(sys, "frozen") or # new py2exe
             safehasattr(sys, "importers") or # old py2exe
             imp.is_frozen("__main__")) # tools/freeze
 
 # the location of data files matching the source code
 if mainfrozen():
     # executable version (py2exe) doesn't support __file__
     datapath = os.path.dirname(sys.executable)
 else:
     datapath = os.path.dirname(__file__)
 
 i18n.setdatapath(datapath)
 
 _hgexecutable = None
 
 def hgexecutable():
     """return location of the 'hg' executable.
 
     Defaults to $HG or 'hg' in the search path.
     """
     if _hgexecutable is None:
         hg = os.environ.get('HG')
         mainmod = sys.modules['__main__']
         if hg:
             _sethgexecutable(hg)
         elif mainfrozen():
             _sethgexecutable(sys.executable)
         elif os.path.basename(getattr(mainmod, '__file__', '')) == 'hg':
             _sethgexecutable(mainmod.__file__)
         else:
             exe = findexe('hg') or os.path.basename(sys.argv[0])
             _sethgexecutable(exe)
     return _hgexecutable
 
 def _sethgexecutable(path):
     """set location of the 'hg' executable"""
     global _hgexecutable
     _hgexecutable = path
 
 def system(cmd, environ={}, cwd=None, onerr=None, errprefix=None, out=None):
     '''enhanced shell command execution.
     run with environment maybe modified, maybe in different dir.
 
     if command fails and onerr is None, return status, else raise onerr
     object as exception.
 
     if out is specified, it is assumed to be a file-like object that has a
     write() method. stdout and stderr will be redirected to out.'''
     try:
         sys.stdout.flush()
     except Exception:
         pass
     def py2shell(val):
         'convert python object into string that is useful to shell'
         if val is None or val is False:
             return '0'
         if val is True:
             return '1'
         return str(val)
     origcmd = cmd
     cmd = quotecommand(cmd)
     if sys.platform == 'plan9' and (sys.version_info[0] == 2
                                     and sys.version_info[1] < 7):
         # subprocess kludge to work around issues in half-baked Python
         # ports, notably bichued/python:
         if not cwd is None:
             os.chdir(cwd)
         rc = os.system(cmd)
     else:
         env = dict(os.environ)
         env.update((k, py2shell(v)) for k, v in environ.iteritems())
         env['HG'] = hgexecutable()
         if out is None or out == sys.__stdout__:
             rc = subprocess.call(cmd, shell=True, close_fds=closefds,
                                  env=env, cwd=cwd)
         else:
             proc = subprocess.Popen(cmd, shell=True, close_fds=closefds,
                                     env=env, cwd=cwd, stdout=subprocess.PIPE,
                                     stderr=subprocess.STDOUT)
             while True:
                 line = proc.stdout.readline()
                 if not line:
                     break
                 out.write(line)
             proc.wait()
             rc = proc.returncode
         if sys.platform == 'OpenVMS' and rc & 1:
             rc = 0
     if rc and onerr:
         errmsg = '%s %s' % (os.path.basename(origcmd.split(None, 1)[0]),
                             explainexit(rc)[0])
         if errprefix:
             errmsg = '%s: %s' % (errprefix, errmsg)
         raise onerr(errmsg)
     return rc
 
 def checksignature(func):
     '''wrap a function with code to check for calling errors'''
     def check(*args, **kwargs):
         try:
             return func(*args, **kwargs)
         except TypeError:
             if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
                 raise error.SignatureError
             raise
 
     return check
 
 def copyfile(src, dest):
     "copy a file, preserving mode and atime/mtime"
     if os.path.lexists(dest):
         unlink(dest)
     if os.path.islink(src):
         os.symlink(os.readlink(src), dest)
     else:
         try:
             shutil.copyfile(src, dest)
             shutil.copymode(src, dest)
         except shutil.Error, inst:
             raise Abort(str(inst))
 
 def copyfiles(src, dst, hardlink=None):
     """Copy a directory tree using hardlinks if possible"""
 
     if hardlink is None:
         hardlink = (os.stat(src).st_dev ==
                     os.stat(os.path.dirname(dst)).st_dev)
 
     num = 0
     if os.path.isdir(src):
         os.mkdir(dst)
         for name, kind in osutil.listdir(src):
             srcname = os.path.join(src, name)
             dstname = os.path.join(dst, name)
             hardlink, n = copyfiles(srcname, dstname, hardlink)
             num += n
     else:
         if hardlink:
             try:
                 oslink(src, dst)
             except (IOError, OSError):
                 hardlink = False
                 shutil.copy(src, dst)
         else:
             shutil.copy(src, dst)
         num += 1
 
     return hardlink, num
 
 _winreservednames = '''con prn aux nul
     com1 com2 com3 com4 com5 com6 com7 com8 com9
     lpt1 lpt2 lpt3 lpt4 lpt5 lpt6 lpt7 lpt8 lpt9'''.split()
 _winreservedchars = ':*?"<>|'
 def checkwinfilename(path):
     r'''Check that the base-relative path is a valid filename on Windows.
     Returns None if the path is ok, or a UI string describing the problem.
 
     >>> checkwinfilename("just/a/normal/path")
     >>> checkwinfilename("foo/bar/con.xml")
     "filename contains 'con', which is reserved on Windows"
     >>> checkwinfilename("foo/con.xml/bar")
     "filename contains 'con', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/xml.con")
     >>> checkwinfilename("foo/bar/AUX/bla.txt")
     "filename contains 'AUX', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/bla:.txt")
     "filename contains ':', which is reserved on Windows"
     >>> checkwinfilename("foo/bar/b\07la.txt")
     "filename contains '\\x07', which is invalid on Windows"
     >>> checkwinfilename("foo/bar/bla ")
     "filename ends with ' ', which is not allowed on Windows"
     >>> checkwinfilename("../bar")
     >>> checkwinfilename("foo\\")
     "filename ends with '\\', which is invalid on Windows"
     >>> checkwinfilename("foo\\/bar")
     "directory name ends with '\\', which is invalid on Windows"
     '''
     if path.endswith('\\'):
         return _("filename ends with '\\', which is invalid on Windows")
     if '\\/' in path:
         return _("directory name ends with '\\', which is invalid on Windows")
     for n in path.replace('\\', '/').split('/'):
         if not n:
             continue
         for c in n:
             if c in _winreservedchars:
                 return _("filename contains '%s', which is reserved "
                          "on Windows") % c
             if ord(c) <= 31:
                 return _("filename contains %r, which is invalid "
                          "on Windows") % c
         base = n.split('.')[0]
         if base and base.lower() in _winreservednames:
             return _("filename contains '%s', which is reserved "
                      "on Windows") % base
         t = n[-1]
         if t in '. ' and n not in '..':
             return _("filename ends with '%s', which is not allowed "
                      "on Windows") % t
 
 if os.name == 'nt':
     checkosfilename = checkwinfilename
 else:
     checkosfilename = platform.checkosfilename
 
 def makelock(info, pathname):
     try:
         return os.symlink(info, pathname)
     except OSError, why:
         if why.errno == errno.EEXIST:
             raise
     except AttributeError: # no symlink in os
         pass
 
     ld = os.open(pathname, os.O_CREAT | os.O_WRONLY | os.O_EXCL)
     os.write(ld, info)
     os.close(ld)
 
 def readlock(pathname):
     try:
         return os.readlink(pathname)
     except OSError, why:
         if why.errno not in (errno.EINVAL, errno.ENOSYS):
             raise
     except AttributeError: # no symlink in os
         pass
     fp = posixfile(pathname)
     r = fp.read()
     fp.close()
     return r
 
 def fstat(fp):
     '''stat file object that may not have fileno method.'''
     try:
         return os.fstat(fp.fileno())
     except AttributeError:
         return os.stat(fp.name)
 
 # File system features
 
 def checkcase(path):
     """
     Return true if the given path is on a case-sensitive filesystem
 
     Requires a path (like /foo/.hg) ending with a foldable final
     directory component.
     """
     s1 = os.stat(path)
     d, b = os.path.split(path)
     b2 = b.upper()
     if b == b2:
         b2 = b.lower()
         if b == b2:
             return True # no evidence against case sensitivity
     p2 = os.path.join(d, b2)
     try:
         s2 = os.stat(p2)
         if s2 == s1:
             return False
         return True
     except OSError:
         return True
 
 try:
     import re2
     _re2 = None
 except ImportError:
     _re2 = False
 
 class _re(object):
     def _checkre2(self):
         global _re2
         try:
             # check if match works, see issue3964
             _re2 = bool(re2.match(r'\[([^\[]+)\]', '[ui]'))
         except ImportError:
             _re2 = False
 
     def compile(self, pat, flags=0):
         '''Compile a regular expression, using re2 if possible
 
         For best performance, use only re2-compatible regexp features. The
         only flags from the re module that are re2-compatible are
         IGNORECASE and MULTILINE.'''
         if _re2 is None:
             self._checkre2()
         if _re2 and (flags & ~(remod.IGNORECASE | remod.MULTILINE)) == 0:
             if flags & remod.IGNORECASE:
                 pat = '(?i)' + pat
             if flags & remod.MULTILINE:
                 pat = '(?m)' + pat
             try:
                 return re2.compile(pat)
             except re2.error:
                 pass
         return remod.compile(pat, flags)
 
     @propertycache
     def escape(self):
         '''Return the version of escape corresponding to self.compile.
 
         This is imperfect because whether re2 or re is used for a particular
         function depends on the flags, etc, but it's the best we can do.
         '''
         global _re2
         if _re2 is None:
             self._checkre2()
         if _re2:
             return re2.escape
         else:
             return remod.escape
 
 re = _re()
 
 _fspathcache = {}
 def fspath(name, root):
     '''Get name in the case stored in the filesystem
 
     The name should be relative to root, and be normcase-ed for efficiency.
 
     Note that this function is unnecessary, and should not be
     called, for case-sensitive filesystems (simply because it's expensive).
 
     The root should be normcase-ed, too.
     '''
     def _makefspathcacheentry(dir):
         return dict((normcase(n), n) for n in os.listdir(dir))
 
     seps = os.sep
     if os.altsep:
         seps = seps + os.altsep
     # Protect backslashes. This gets silly very quickly.
     seps.replace('\\','\\\\')
     pattern = remod.compile(r'([^%s]+)|([%s]+)' % (seps, seps))
     dir = os.path.normpath(root)
     result = []
     for part, sep in pattern.findall(name):
         if sep:
             result.append(sep)
             continue
 
         if dir not in _fspathcache:
             _fspathcache[dir] = _makefspathcacheentry(dir)
         contents = _fspathcache[dir]
 
         found = contents.get(part)
         if not found:
             # retry "once per directory" per "dirstate.walk" which
             # may take place for each patches of "hg qpush", for example
             _fspathcache[dir] = contents = _makefspathcacheentry(dir)
             found = contents.get(part)
 
         result.append(found or part)
         dir = os.path.join(dir, part)
 
     return ''.join(result)
 
 def checknlink(testfile):
     '''check whether hardlink count reporting works properly'''
 
     # testfile may be open, so we need a separate file for checking to
     # work around issue2543 (or testfile may get lost on Samba shares)
     f1 = testfile + ".hgtmp1"
     if os.path.lexists(f1):
         return False
     try:
         posixfile(f1, 'w').close()
     except IOError:
         return False
 
     f2 = testfile + ".hgtmp2"
     fd = None
     try:
         try:
             oslink(f1, f2)
         except OSError:
             return False
 
         # nlinks() may behave differently for files on Windows shares if
         # the file is open.
         fd = posixfile(f2)
         return nlinks(f2) > 1
     finally:
         if fd is not None:
             fd.close()
         for f in (f1, f2):
             try:
                 os.unlink(f)
             except OSError:
                 pass
 
 def endswithsep(path):
     '''Check path ends with os.sep or os.altsep.'''
     return path.endswith(os.sep) or os.altsep and path.endswith(os.altsep)
 
 def splitpath(path):
     '''Split path by os.sep.
     Note that this function does not use os.altsep because this is
     an alternative of simple "xxx.split(os.sep)".
     It is recommended to use os.path.normpath() before using this
     function if need.'''
     return path.split(os.sep)
 
 def gui():
     '''Are we running in a GUI?'''
     if sys.platform == 'darwin':
         if 'SSH_CONNECTION' in os.environ:
             # handle SSH access to a box where the user is logged in
             return False
         elif getattr(osutil, 'isgui', None):
             # check if a CoreGraphics session is available
             return osutil.isgui()
         else:
             # pure build; use a safe default
             return True
     else:
         return os.name == "nt" or os.environ.get("DISPLAY")
 
 def mktempcopy(name, emptyok=False, createmode=None):
     """Create a temporary file with the same contents from name
 
     The permission bits are copied from the original file.
 
     If the temporary file is going to be truncated immediately, you
     can use emptyok=True as an optimization.
 
     Returns the name of the temporary file.
     """
     d, fn = os.path.split(name)
     fd, temp = tempfile.mkstemp(prefix='.%s-' % fn, dir=d)
     os.close(fd)
     # Temporary files are created with mode 0600, which is usually not
     # what we want.  If the original file already exists, just copy
     # its mode.  Otherwise, manually obey umask.
     copymode(name, temp, createmode)
     if emptyok:
         return temp
     try:
         try:
             ifp = posixfile(name, "rb")
         except IOError, inst:
             if inst.errno == errno.ENOENT:
                 return temp
             if not getattr(inst, 'filename', None):
                 inst.filename = name
             raise
         ofp = posixfile(temp, "wb")
         for chunk in filechunkiter(ifp):
             ofp.write(chunk)
         ifp.close()
         ofp.close()
     except: # re-raises
         try: os.unlink(temp)
         except OSError: pass
         raise
     return temp
 
 class atomictempfile(object):
     '''writable file object that atomically updates a file
 
     All writes will go to a temporary copy of the original file. Call
     close() when you are done writing, and atomictempfile will rename
     the temporary copy to the original name, making the changes
     visible. If the object is destroyed without being closed, all your
     writes are discarded.
     '''
     def __init__(self, name, mode='w+b', createmode=None):
         self.__name = name      # permanent name
         self._tempname = mktempcopy(name, emptyok=('w' in mode),
                                     createmode=createmode)
         self._fp = posixfile(self._tempname, mode)
 
         # delegated methods
         self.write = self._fp.write
         self.seek = self._fp.seek
         self.tell = self._fp.tell
         self.fileno = self._fp.fileno
 
     def close(self):
         if not self._fp.closed:
             self._fp.close()
             rename(self._tempname, localpath(self.__name))
 
     def discard(self):
         if not self._fp.closed:
             try:
                 os.unlink(self._tempname)
             except OSError:
                 pass
             self._fp.close()
 
     def __del__(self):
         if safehasattr(self, '_fp'): # constructor actually did something
             self.discard()
 
 def makedirs(name, mode=None, notindexed=False):
     """recursive directory creation with parent mode inheritance"""
     try:
         makedir(name, notindexed)
     except OSError, err:
         if err.errno == errno.EEXIST:
             return
         if err.errno != errno.ENOENT or not name:
             raise
         parent = os.path.dirname(os.path.abspath(name))
         if parent == name:
             raise
         makedirs(parent, mode, notindexed)
         makedir(name, notindexed)
     if mode is not None:
         os.chmod(name, mode)
 
-def ensuredirs(name, mode=None):
-    """race-safe recursive directory creation"""
+def ensuredirs(name, mode=None, notindexed=False):
+    """race-safe recursive directory creation
+
+    Newly created directories are marked as "not to be indexed by
+    the content indexing service", if ``notindexed`` is specified
+    for "write" mode access.
+    """
     if os.path.isdir(name):
         return
     parent = os.path.dirname(os.path.abspath(name))
     if parent != name:
-        ensuredirs(parent, mode)
+        ensuredirs(parent, mode, notindexed)
     try:
-        os.mkdir(name)
+        makedir(name, notindexed)
     except OSError, err:
         if err.errno == errno.EEXIST and os.path.isdir(name):
             # someone else seems to have won a directory creation race
             return
         raise
     if mode is not None:
         os.chmod(name, mode)
 
 def readfile(path):
     fp = open(path, 'rb')
     try:
         return fp.read()
     finally:
         fp.close()
 
 def writefile(path, text):
     fp = open(path, 'wb')
     try:
         fp.write(text)
     finally:
         fp.close()
 
 def appendfile(path, text):
     fp = open(path, 'ab')
     try:
         fp.write(text)
     finally:
         fp.close()
 
 class chunkbuffer(object):
     """Allow arbitrary sized chunks of data to be efficiently read from an
     iterator over chunks of arbitrary size."""
 
     def __init__(self, in_iter):
         """in_iter is the iterator that's iterating over the input chunks.
         targetsize is how big a buffer to try to maintain."""
         def splitbig(chunks):
             for chunk in chunks:
                 if len(chunk) > 2**20:
                     pos = 0
                     while pos < len(chunk):
                         end = pos + 2 ** 18
                         yield chunk[pos:end]
                         pos = end
                 else:
                     yield chunk
         self.iter = splitbig(in_iter)
         self._queue = deque()
 
     def read(self, l=None):
         """Read L bytes of data from the iterator of chunks of data.
         Returns less than L bytes if the iterator runs dry.
 
         If size parameter is omitted, read everything"""
         left = l
         buf = []
         queue = self._queue
         while left is None or left > 0:
             # refill the queue
             if not queue:
                 target = 2**18
                 for chunk in self.iter:
                     queue.append(chunk)
                     target -= len(chunk)
                     if target <= 0:
                         break
                 if not queue:
                     break
 
             chunk = queue.popleft()
             if left is not None:
                 left -= len(chunk)
             if left is not None and left < 0:
                 queue.appendleft(chunk[left:])
                 buf.append(chunk[:left])
             else:
                 buf.append(chunk)
 
         return ''.join(buf)
 
 def filechunkiter(f, size=65536, limit=None):
     """Create a generator that produces the data in the file size
     (default 65536) bytes at a time, up to optional limit (default is
     to read all data).  Chunks may be less than size bytes if the
     chunk is the last chunk in the file, or the file is a socket or
     some other type of file that sometimes reads less data than is
     requested."""
     assert size >= 0
     assert limit is None or limit >= 0
     while True:
         if limit is None:
             nbytes = size
         else:
             nbytes = min(limit, size)
         s = nbytes and f.read(nbytes)
         if not s:
             break
         if limit:
             limit -= len(s)
         yield s
 
 def makedate(timestamp=None):
     '''Return a unix timestamp (or the current time) as a (unixtime,
     offset) tuple based off the local timezone.'''
     if timestamp is None:
         timestamp = time.time()
     if timestamp < 0:
         hint = _("check your clock")
         raise Abort(_("negative timestamp: %d") % timestamp, hint=hint)
     delta = (datetime.datetime.utcfromtimestamp(timestamp) -
              datetime.datetime.fromtimestamp(timestamp))
     tz = delta.days * 86400 + delta.seconds
     return timestamp, tz
 
 def datestr(date=None, format='%a %b %d %H:%M:%S %Y %1%2'):
     """represent a (unixtime, offset) tuple as a localized time.
     unixtime is seconds since the epoch, and offset is the time zone's
     number of seconds away from UTC. if timezone is false, do not
     append time zone to string."""
     t, tz = date or makedate()
     if t < 0:
         t = 0   # time.gmtime(lt) fails on Windows for lt < -43200
         tz = 0
     if "%1" in format or "%2" in format or "%z" in format:
         sign = (tz > 0) and "-" or "+"
         minutes = abs(tz) // 60
         format = format.replace("%z", "%1%2")
         format = format.replace("%1", "%c%02d" % (sign, minutes // 60))
         format = format.replace("%2", "%02d" % (minutes % 60))
     try:
         t = time.gmtime(float(t) - tz)
     except ValueError:
         # time was out of range
         t = time.gmtime(sys.maxint)
     s = time.strftime(format, t)
     return s
 
 def shortdate(date=None):
     """turn (timestamp, tzoff) tuple into iso 8631 date."""
     return datestr(date, format='%Y-%m-%d')
 
 def strdate(string, format, defaults=[]):
     """parse a localized time string and return a (unixtime, offset) tuple.
     if the string cannot be parsed, ValueError is raised."""
     def timezone(string):
         tz = string.split()[-1]
         if tz[0] in "+-" and len(tz) == 5 and tz[1:].isdigit():
             sign = (tz[0] == "+") and 1 or -1
             hours = int(tz[1:3])
             minutes = int(tz[3:5])
             return -sign * (hours * 60 + minutes) * 60
         if tz == "GMT" or tz == "UTC":
             return 0
         return None
 
     # NOTE: unixtime = localunixtime + offset
     offset, date = timezone(string), string
     if offset is not None:
         date = " ".join(string.split()[:-1])
 
     # add missing elements from defaults
     usenow = False # default to using biased defaults
     for part in ("S", "M", "HI", "d", "mb", "yY"): # decreasing specificity
         found = [True for p in part if ("%"+p) in format]
         if not found:
             date += "@" + defaults[part][usenow]
             format += "@%" + part[0]
         else:
             # We've found a specific time element, less specific time
             # elements are relative to today
             usenow = True
 
     timetuple = time.strptime(date, format)
     localunixtime = int(calendar.timegm(timetuple))
     if offset is None:
         # local timezone
         unixtime = int(time.mktime(timetuple))
         offset = unixtime - localunixtime
     else:
         unixtime = localunixtime + offset
     return unixtime, offset
 
 def parsedate(date, formats=None, bias={}):
     """parse a localized date/time and return a (unixtime, offset) tuple.
 
     The date may be a "unixtime offset" string or in one of the specified
     formats. If the date already is a (unixtime, offset) tuple, it is returned.
 
     >>> parsedate(' today ') == parsedate(\
                                   datetime.date.today().strftime('%b %d'))
     True
     >>> parsedate( 'yesterday ') == parsedate((datetime.date.today() -\
                                                datetime.timedelta(days=1)\
                                               ).strftime('%b %d'))
     True
     >>> now, tz = makedate()
     >>> strnow, strtz = parsedate('now')
     >>> (strnow - now) < 1
     True
     >>> tz == strtz
     True
     """
     if not date:
         return 0, 0
     if isinstance(date, tuple) and len(date) == 2:
         return date
     if not formats:
         formats = defaultdateformats
     date = date.strip()
 
     if date == _('now'):
         return makedate()
     if date == _('today'):
         date = datetime.date.today().strftime('%b %d')
     elif date == _('yesterday'):
         date = (datetime.date.today() -
                 datetime.timedelta(days=1)).strftime('%b %d')
 
     try:
         when, offset = map(int, date.split(' '))
     except ValueError:
         # fill out defaults
         now = makedate()
         defaults = {}
         for part in ("d", "mb", "yY", "HI", "M", "S"):
             # this piece is for rounding the specific end of unknowns
             b = bias.get(part)
             if b is None:
                 if part[0] in "HMS":
                     b = "00"
                 else:
                     b = "0"
 
             # this piece is for matching the generic end to today's date
             n = datestr(now, "%" + part[0])
 
             defaults[part] = (b, n)
 
         for format in formats:
             try:
                 when, offset = strdate(date, format, defaults)
             except (ValueError, OverflowError):
                 pass
             else:
                 break
         else:
             raise Abort(_('invalid date: %r') % date)
     # validate explicit (probably user-specified) date and
     # time zone offset. values must fit in signed 32 bits for
     # current 32-bit linux runtimes. timezones go from UTC-12
     # to UTC+14
     if abs(when) > 0x7fffffff:
         raise Abort(_('date exceeds 32 bits: %d') % when)
     if when < 0:
         raise Abort(_('negative date value: %d') % when)
     if offset < -50400 or offset > 43200:
         raise Abort(_('impossible time zone offset: %d') % offset)
     return when, offset
 
 def matchdate(date):
     """Return a function that matches a given date match specifier
 
     Formats include:
 
     '{date}' match a given date to the accuracy provided
 
     '<{date}' on or before a given date
 
     '>{date}' on or after a given date
 
     >>> p1 = parsedate("10:29:59")
     >>> p2 = parsedate("10:30:00")
     >>> p3 = parsedate("10:30:59")
     >>> p4 = parsedate("10:31:00")
     >>> p5 = parsedate("Sep 15 10:30:00 1999")
     >>> f = matchdate("10:30")
     >>> f(p1[0])
     False
     >>> f(p2[0])
     True
     >>> f(p3[0])
     True
     >>> f(p4[0])
     False
     >>> f(p5[0])
     False
     """
 
     def lower(date):
         d = {'mb': "1", 'd': "1"}
         return parsedate(date, extendeddateformats, d)[0]
 
     def upper(date):
         d = {'mb': "12", 'HI': "23", 'M': "59", 'S': "59"}
         for days in ("31", "30", "29"):
             try:
                 d["d"] = days
                 return parsedate(date, extendeddateformats, d)[0]
             except Abort:
                 pass
         d["d"] = "28"
         return parsedate(date, extendeddateformats, d)[0]
 
     date = date.strip()
 
     if not date:
         raise Abort(_("dates cannot consist entirely of whitespace"))
     elif date[0] == "<":
         if not date[1:]:
             raise Abort(_("invalid day spec, use '<DATE'"))
         when = upper(date[1:])
         return lambda x: x <= when
     elif date[0] == ">":
         if not date[1:]:
             raise Abort(_("invalid day spec, use '>DATE'"))
         when = lower(date[1:])
         return lambda x: x >= when
     elif date[0] == "-":
         try:
             days = int(date[1:])
         except ValueError:
             raise Abort(_("invalid day spec: %s") % date[1:])
         if days < 0:
             raise Abort(_("%s must be nonnegative (see 'hg help dates')")
                 % date[1:])
         when = makedate()[0] - days * 3600 * 24
         return lambda x: x >= when
     elif " to " in date:
         a, b = date.split(" to ")
         start, stop = lower(a), upper(b)
         return lambda x: x >= start and x <= stop
     else:
         start, stop = lower(date), upper(date)
         return lambda x: x >= start and x <= stop
 
 def shortuser(user):
     """Return a short representation of a user name or email address."""
     f = user.find('@')
     if f >= 0:
         user = user[:f]
     f = user.find('<')
     if f >= 0:
         user = user[f + 1:]
     f = user.find(' ')
     if f >= 0:
         user = user[:f]
     f = user.find('.')
     if f >= 0:
         user = user[:f]
     return user
 
 def emailuser(user):
     """Return the user portion of an email address."""
     f = user.find('@')
     if f >= 0:
         user = user[:f]
     f = user.find('<')
     if f >= 0:
         user = user[f + 1:]
     return user
 
 def email(author):
     '''get email of author.'''
     r = author.find('>')
     if r == -1:
         r = None
     return author[author.find('<') + 1:r]
 
 def ellipsis(text, maxlength=400):
     """Trim string to at most maxlength (default: 400) columns in display."""
     return encoding.trim(text, maxlength, ellipsis='...')
 
 def unitcountfn(*unittable):
     '''return a function that renders a readable count of some quantity'''
 
     def go(count):
         for multiplier, divisor, format in unittable:
             if count >= divisor * multiplier:
                 return format % (count / float(divisor))
         return unittable[-1][2] % count
 
     return go
 
 bytecount = unitcountfn(
     (100, 1 << 30, _('%.0f GB')),
     (10, 1 << 30, _('%.1f GB')),
     (1, 1 << 30, _('%.2f GB')),
     (100, 1 << 20, _('%.0f MB')),
     (10, 1 << 20, _('%.1f MB')),
     (1, 1 << 20, _('%.2f MB')),
     (100, 1 << 10, _('%.0f KB')),
     (10, 1 << 10, _('%.1f KB')),
     (1, 1 << 10, _('%.2f KB')),
     (1, 1, _('%.0f bytes')),
     )
 
 def uirepr(s):
     # Avoid double backslash in Windows path repr()
     return repr(s).replace('\\\\', '\\')
 
 # delay import of textwrap
 def MBTextWrapper(**kwargs):
     class tw(textwrap.TextWrapper):
         """
         Extend TextWrapper for width-awareness.
 
         Neither number of 'bytes' in any encoding nor 'characters' is
         appropriate to calculate terminal columns for specified string.
 
         Original TextWrapper implementation uses built-in 'len()' directly,
         so overriding is needed to use width information of each characters.
 
         In addition, characters classified into 'ambiguous' width are
         treated as wide in East Asian area, but as narrow in other.
 
         This requires use decision to determine width of such characters.
         """
         def __init__(self, **kwargs):
             textwrap.TextWrapper.__init__(self, **kwargs)
 
             # for compatibility between 2.4 and 2.6
             if getattr(self, 'drop_whitespace', None) is None:
                 self.drop_whitespace = kwargs.get('drop_whitespace', True)
 
         def _cutdown(self, ucstr, space_left):
             l = 0
             colwidth = encoding.ucolwidth
             for i in xrange(len(ucstr)):
                 l += colwidth(ucstr[i])
                 if space_left < l:
                     return (ucstr[:i], ucstr[i:])
             return ucstr, ''
 
         # overriding of base class
         def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width):
             space_left = max(width - cur_len, 1)
 
             if self.break_long_words:
                 cut, res = self._cutdown(reversed_chunks[-1], space_left)
                 cur_line.append(cut)
                 reversed_chunks[-1] = res
             elif not cur_line:
                 cur_line.append(reversed_chunks.pop())
 
         # this overriding code is imported from TextWrapper of python 2.6
         # to calculate columns of string by 'encoding.ucolwidth()'
         def _wrap_chunks(self, chunks):
             colwidth = encoding.ucolwidth
 
             lines = []
             if self.width <= 0:
                 raise ValueError("invalid width %r (must be > 0)" % self.width)
 
             # Arrange in reverse order so items can be efficiently popped
             # from a stack of chucks.
             chunks.reverse()
 
             while chunks:
 
                 # Start the list of chunks that will make up the current line.
                 # cur_len is just the length of all the chunks in cur_line.
                 cur_line = []
                 cur_len = 0
 
                 # Figure out which static string will prefix this line.
                 if lines:
                     indent = self.subsequent_indent
                 else:
                     indent = self.initial_indent
 
                 # Maximum width for this line.
                 width = self.width - len(indent)
 
                 # First chunk on line is whitespace -- drop it, unless this
                 # is the very beginning of the text (i.e. no lines started yet).
                 if self.drop_whitespace and chunks[-1].strip() == '' and lines:
                     del chunks[-1]
 
                 while chunks:
                     l = colwidth(chunks[-1])
 
                     # Can at least squeeze this chunk onto the current line.
                     if cur_len + l <= width:
                         cur_line.append(chunks.pop())
                         cur_len += l
 
                     # Nope, this line is full.
                     else:
                         break
 
                 # The current line is full, and the next chunk is too big to
                 # fit on *any* line (not just this one).
                 if chunks and colwidth(chunks[-1]) > width:
                     self._handle_long_word(chunks, cur_line, cur_len, width)
 
                 # If the last chunk on this line is all whitespace, drop it.
                 if (self.drop_whitespace and
                     cur_line and cur_line[-1].strip() == ''):
                     del cur_line[-1]
 
                 # Convert current line back to a string and store it in list
                 # of all lines (return value).
                 if cur_line:
                     lines.append(indent + ''.join(cur_line))
 
             return lines
 
     global MBTextWrapper
     MBTextWrapper = tw
     return tw(**kwargs)
 
 def wrap(line, width, initindent='', hangindent=''):
     maxindent = max(len(hangindent), len(initindent))
     if width <= maxindent:
         # adjust for weird terminal size
         width = max(78, maxindent + 1)
     line = line.decode(encoding.encoding, encoding.encodingmode)
     initindent = initindent.decode(encoding.encoding, encoding.encodingmode)
     hangindent = hangindent.decode(encoding.encoding, encoding.encodingmode)
     wrapper = MBTextWrapper(width=width,
                             initial_indent=initindent,
                             subsequent_indent=hangindent)
     return wrapper.fill(line).encode(encoding.encoding)
 
 def iterlines(iterator):
     for chunk in iterator:
         for line in chunk.splitlines():
             yield line
 
 def expandpath(path):
     return os.path.expanduser(os.path.expandvars(path))
 
 def hgcmd():
     """Return the command used to execute current hg
 
     This is different from hgexecutable() because on Windows we want
     to avoid things opening new shell windows like batch files, so we
     get either the python call or current executable.
     """
     if mainfrozen():
         return [sys.executable]
     return gethgcmd()
 
 def rundetached(args, condfn):
     """Execute the argument list in a detached process.
 
     condfn is a callable which is called repeatedly and should return
     True once the child process is known to have started successfully.
     At this point, the child process PID is returned. If the child
     process fails to start or finishes before condfn() evaluates to
     True, return -1.
     """
     # Windows case is easier because the child process is either
     # successfully starting and validating the condition or exiting
     # on failure. We just poll on its PID. On Unix, if the child
     # process fails to start, it will be left in a zombie state until
     # the parent wait on it, which we cannot do since we expect a long
     # running process on success. Instead we listen for SIGCHLD telling
     # us our child process terminated.
     terminated = set()
     def handler(signum, frame):
         terminated.add(os.wait())
     prevhandler = None
     SIGCHLD = getattr(signal, 'SIGCHLD', None)
     if SIGCHLD is not None:
         prevhandler = signal.signal(SIGCHLD, handler)
     try:
         pid = spawndetached(args)
         while not condfn():
             if ((pid in terminated or not testpid(pid))
                 and not condfn()):
                 return -1
             time.sleep(0.1)
         return pid
     finally:
         if prevhandler is not None:
             signal.signal(signal.SIGCHLD, prevhandler)
 
 try:
     any, all = any, all
 except NameError:
     def any(iterable):
         for i in iterable:
             if i:
                 return True
         return False
 
     def all(iterable):
         for i in iterable:
             if not i:
                 return False
         return True
 
 def interpolate(prefix, mapping, s, fn=None, escape_prefix=False):
     """Return the result of interpolating items in the mapping into string s.
 
     prefix is a single character string, or a two character string with
     a backslash as the first character if the prefix needs to be escaped in
     a regular expression.
 
     fn is an optional function that will be applied to the replacement text
     just before replacement.
 
     escape_prefix is an optional flag that allows using doubled prefix for
     its escaping.
     """
     fn = fn or (lambda s: s)
     patterns = '|'.join(mapping.keys())
     if escape_prefix:
         patterns += '|' + prefix
         if len(prefix) > 1:
             prefix_char = prefix[1:]
         else:
             prefix_char = prefix
         mapping[prefix_char] = prefix_char
     r = remod.compile(r'%s(%s)' % (prefix, patterns))
     return r.sub(lambda x: fn(mapping[x.group()[1:]]), s)
 
 def getport(port):
     """Return the port for a given network service.
 
     If port is an integer, it's returned as is. If it's a string, it's
     looked up using socket.getservbyname(). If there's no matching
     service, util.Abort is raised.
     """
     try:
         return int(port)
     except ValueError:
         pass
 
     try:
         return socket.getservbyname(port)
     except socket.error:
         raise Abort(_("no port number associated with service '%s'") % port)
 
 _booleans = {'1': True, 'yes': True, 'true': True, 'on': True, 'always': True,
              '0': False, 'no': False, 'false': False, 'off': False,
              'never': False}
 
 def parsebool(s):
     """Parse s into a boolean.
 
     If s is not a valid boolean, returns None.
     """
     return _booleans.get(s.lower(), None)
 
 _hexdig = '0123456789ABCDEFabcdef'
 _hextochr = dict((a + b, chr(int(a + b, 16)))
                  for a in _hexdig for b in _hexdig)
 
 def _urlunquote(s):
     """Decode HTTP/HTML % encoding.
 
     >>> _urlunquote('abc%20def')
     'abc def'
     """
     res = s.split('%')
     # fastpath
     if len(res) == 1:
         return s
     s = res[0]
     for item in res[1:]:
         try:
             s += _hextochr[item[:2]] + item[2:]
         except KeyError:
             s += '%' + item
         except UnicodeDecodeError:
             s += unichr(int(item[:2], 16)) + item[2:]
     return s
 
 class url(object):
     r"""Reliable URL parser.
 
     This parses URLs and provides attributes for the following
     components:
 
     <scheme>://<user>:<passwd>@<host>:<port>/<path>?<query>#<fragment>
 
     Missing components are set to None. The only exception is
     fragment, which is set to '' if present but empty.
 
     If parsefragment is False, fragment is included in query. If
     parsequery is False, query is included in path. If both are
     False, both fragment and query are included in path.
 
     See http://www.ietf.org/rfc/rfc2396.txt for more information.
 
     Note that for backward compatibility reasons, bundle URLs do not
     take host names. That means 'bundle://../' has a path of '../'.
 
     Examples:
 
     >>> url('http://www.ietf.org/rfc/rfc2396.txt')
     <url scheme: 'http', host: 'www.ietf.org', path: 'rfc/rfc2396.txt'>
     >>> url('ssh://[::1]:2200//home/joe/repo')
     <url scheme: 'ssh', host: '[::1]', port: '2200', path: '/home/joe/repo'>
     >>> url('file:///home/joe/repo')
     <url scheme: 'file', path: '/home/joe/repo'>
     >>> url('file:///c:/temp/foo/')
     <url scheme: 'file', path: 'c:/temp/foo/'>
     >>> url('bundle:foo')
     <url scheme: 'bundle', path: 'foo'>
     >>> url('bundle://../foo')
     <url scheme: 'bundle', path: '../foo'>
     >>> url(r'c:\foo\bar')
     <url path: 'c:\\foo\\bar'>
     >>> url(r'\\blah\blah\blah')
     <url path: '\\\\blah\\blah\\blah'>
     >>> url(r'\\blah\blah\blah#baz')
     <url path: '\\\\blah\\blah\\blah', fragment: 'baz'>
     >>> url(r'file:///C:\users\me')
     <url scheme: 'file', path: 'C:\\users\\me'>
 
     Authentication credentials:
 
     >>> url('ssh://joe:xyz@x/repo')
     <url scheme: 'ssh', user: 'joe', passwd: 'xyz', host: 'x', path: 'repo'>
     >>> url('ssh://joe@x/repo')
     <url scheme: 'ssh', user: 'joe', host: 'x', path: 'repo'>
 
     Query strings and fragments:
 
     >>> url('http://host/a?b#c')
     <url scheme: 'http', host: 'host', path: 'a', query: 'b', fragment: 'c'>
     >>> url('http://host/a?b#c', parsequery=False, parsefragment=False)
     <url scheme: 'http', host: 'host', path: 'a?b#c'>
     """
 
     _safechars = "!~*'()+"
     _safepchars = "/!~*'()+:\\"
     _matchscheme = remod.compile(r'^[a-zA-Z0-9+.\-]+:').match
 
     def __init__(self, path, parsequery=True, parsefragment=True):
         # We slowly chomp away at path until we have only the path left
         self.scheme = self.user = self.passwd = self.host = None
         self.port = self.path = self.query = self.fragment = None
         self._localpath = True
         self._hostport = ''
         self._origpath = path
 
         if parsefragment and '#' in path:
             path, self.fragment = path.split('#', 1)
             if not path:
                 path = None
 
         # special case for Windows drive letters and UNC paths
         if hasdriveletter(path) or path.startswith(r'\\'):
             self.path = path
             return
 
         # For compatibility reasons, we can't handle bundle paths as
         # normal URLS
         if path.startswith('bundle:'):
             self.scheme = 'bundle'
             path = path[7:]
             if path.startswith('//'):
                 path = path[2:]
             self.path = path
             return
 
         if self._matchscheme(path):
             parts = path.split(':', 1)
             if parts[0]:
                 self.scheme, path = parts
                 self._localpath = False
 
         if not path:
             path = None
             if self._localpath:
                 self.path = ''
                 return
         else:
             if self._localpath:
                 self.path = path
                 return
 
             if parsequery and '?' in path:
                 path, self.query = path.split('?', 1)
                 if not path:
                     path = None
                 if not self.query:
                     self.query = None
 
             # // is required to specify a host/authority
             if path and path.startswith('//'):
                 parts = path[2:].split('/', 1)
                 if len(parts) > 1:
                     self.host, path = parts
                 else:
                     self.host = parts[0]
                     path = None
                 if not self.host:
                     self.host = None
                     # path of file:///d is /d
                     # path of file:///d:/ is d:/, not /d:/
                     if path and not hasdriveletter(path):
                         path = '/' + path
 
             if self.host and '@' in self.host:
                 self.user, self.host = self.host.rsplit('@', 1)
                 if ':' in self.user:
                     self.user, self.passwd = self.user.split(':', 1)
                 if not self.host:
                     self.host = None
 
             # Don't split on colons in IPv6 addresses without ports
             if (self.host and ':' in self.host and
                 not (self.host.startswith('[') and self.host.endswith(']'))):
                 self._hostport = self.host
                 self.host, self.port = self.host.rsplit(':', 1)
                 if not self.host:
                     self.host = None
 
             if (self.host and self.scheme == 'file' and
                 self.host not in ('localhost', '127.0.0.1', '[::1]')):
                 raise Abort(_('file:// URLs can only refer to localhost'))
 
         self.path = path
 
         # leave the query string escaped
         for a in ('user', 'passwd', 'host', 'port',
                   'path', 'fragment'):
             v = getattr(self, a)
             if v is not None:
                 setattr(self, a, _urlunquote(v))
 
     def __repr__(self):
         attrs = []
         for a in ('scheme', 'user', 'passwd', 'host', 'port', 'path',
                   'query', 'fragment'):
             v = getattr(self, a)
             if v is not None:
                 attrs.append('%s: %r' % (a, v))
         return '<url %s>' % ', '.join(attrs)
 
     def __str__(self):
         r"""Join the URL's components back into a URL string.
 
         Examples:
 
         >>> str(url('http://user:pw@host:80/c:/bob?fo:oo#ba:ar'))
         'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'
         >>> str(url('http://user:pw@host:80/?foo=bar&baz=42'))
         'http://user:pw@host:80/?foo=bar&baz=42'
         >>> str(url('http://user:pw@host:80/?foo=bar%3dbaz'))
         'http://user:pw@host:80/?foo=bar%3dbaz'
         >>> str(url('ssh://user:pw@[::1]:2200//home/joe#'))
         'ssh://user:pw@[::1]:2200//home/joe#'
         >>> str(url('http://localhost:80//'))
         'http://localhost:80//'
         >>> str(url('http://localhost:80/'))
         'http://localhost:80/'
         >>> str(url('http://localhost:80'))
         'http://localhost:80/'
         >>> str(url('bundle:foo'))
         'bundle:foo'
         >>> str(url('bundle://../foo'))
         'bundle:../foo'
         >>> str(url('path'))
         'path'
         >>> str(url('file:///tmp/foo/bar'))
         'file:///tmp/foo/bar'
         >>> str(url('file:///c:/tmp/foo/bar'))
         'file:///c:/tmp/foo/bar'
         >>> print url(r'bundle:foo\bar')
         bundle:foo\bar
         >>> print url(r'file:///D:\data\hg')
         file:///D:\data\hg
         """
         if self._localpath:
             s = self.path
             if self.scheme == 'bundle':
                 s = 'bundle:' + s
             if self.fragment:
                 s += '#' + self.fragment
             return s
 
         s = self.scheme + ':'
         if self.user or self.passwd or self.host:
             s += '//'
         elif self.scheme and (not self.path or self.path.startswith('/')
                               or hasdriveletter(self.path)):
             s += '//'
             if hasdriveletter(self.path):
                 s += '/'
         if self.user:
             s += urllib.quote(self.user, safe=self._safechars)
         if self.passwd:
             s += ':' + urllib.quote(self.passwd, safe=self._safechars)
         if self.user or self.passwd:
             s += '@'
         if self.host:
             if not (self.host.startswith('[') and self.host.endswith(']')):
                 s += urllib.quote(self.host)
             else:
                 s += self.host
         if self.port:
             s += ':' + urllib.quote(self.port)
         if self.host:
             s += '/'
         if self.path:
             # TODO: similar to the query string, we should not unescape the
             # path when we store it, the path might contain '%2f' = '/',
             # which we should *not* escape.
             s += urllib.quote(self.path, safe=self._safepchars)
         if self.query:
             # we store the query in escaped form.
             s += '?' + self.query
         if self.fragment is not None:
             s += '#' + urllib.quote(self.fragment, safe=self._safepchars)
         return s
 
     def authinfo(self):
         user, passwd = self.user, self.passwd
         try:
             self.user, self.passwd = None, None
             s = str(self)
         finally:
             self.user, self.passwd = user, passwd
         if not self.user:
             return (s, None)
         # authinfo[1] is passed to urllib2 password manager, and its
         # URIs must not contain credentials. The host is passed in the
         # URIs list because Python < 2.4.3 uses only that to search for
         # a password.
         return (s, (None, (s, self.host),
                     self.user, self.passwd or ''))
 
     def isabs(self):
         if self.scheme and self.scheme != 'file':
             return True # remote URL
         if hasdriveletter(self.path):
             return True # absolute for our purposes - can't be joined()
         if self.path.startswith(r'\\'):
             return True # Windows UNC path
         if self.path.startswith('/'):
             return True # POSIX-style
         return False
 
     def localpath(self):
         if self.scheme == 'file' or self.scheme == 'bundle':
             path = self.path or '/'
             # For Windows, we need to promote hosts containing drive
             # letters to paths with drive letters.
             if hasdriveletter(self._hostport):
                 path = self._hostport + '/' + self.path
             elif (self.host is not None and self.path
                   and not hasdriveletter(path)):
                 path = '/' + path
             return path
         return self._origpath
 
     def islocal(self):
         '''whether localpath will return something that posixfile can open'''
         return (not self.scheme or self.scheme == 'file'
                 or self.scheme == 'bundle')
 
 def hasscheme(path):
     return bool(url(path).scheme)
 
 def hasdriveletter(path):
     return path and path[1:2] == ':' and path[0:1].isalpha()
 
 def urllocalpath(path):
     return url(path, parsequery=False, parsefragment=False).localpath()
 
 def hidepassword(u):
     '''hide user credential in a url string'''
     u = url(u)
     if u.passwd:
         u.passwd = '***'
     return str(u)
 
 def removeauth(u):
     '''remove all authentication information from a url string'''
     u = url(u)
     u.user = u.passwd = None
     return str(u)
 
 def isatty(fd):
     try:
         return fd.isatty()
     except AttributeError:
         return False
 
 timecount = unitcountfn(
     (1, 1e3, _('%.0f s')),
     (100, 1, _('%.1f s')),
     (10, 1, _('%.2f s')),
     (1, 1, _('%.3f s')),
     (100, 0.001, _('%.1f ms')),
     (10, 0.001, _('%.2f ms')),
     (1, 0.001, _('%.3f ms')),
     (100, 0.000001, _('%.1f us')),
     (10, 0.000001, _('%.2f us')),
     (1, 0.000001, _('%.3f us')),
     (100, 0.000000001, _('%.1f ns')),
     (10, 0.000000001, _('%.2f ns')),
     (1, 0.000000001, _('%.3f ns')),
     )
 
 _timenesting = [0]
 
 def timed(func):
     '''Report the execution time of a function call to stderr.
 
     During development, use as a decorator when you need to measure
     the cost of a function, e.g. as follows:
 
     @util.timed
     def foo(a, b, c):
         pass
     '''
 
     def wrapper(*args, **kwargs):
         start = time.time()
         indent = 2
         _timenesting[0] += indent
         try:
             return func(*args, **kwargs)
         finally:
             elapsed = time.time() - start
             _timenesting[0] -= indent
             sys.stderr.write('%s%s: %s\n' %
                              (' ' * _timenesting[0], func.__name__,
                               timecount(elapsed)))
     return wrapper
 
 _sizeunits = (('m', 2**20), ('k', 2**10), ('g', 2**30),
               ('kb', 2**10), ('mb', 2**20), ('gb', 2**30), ('b', 1))
 
 def sizetoint(s):
     '''Convert a space specifier to a byte count.
 
     >>> sizetoint('30')
     30
     >>> sizetoint('2.2kb')
     2252
     >>> sizetoint('6M')
     6291456
     '''
     t = s.strip().lower()
     try:
         for k, u in _sizeunits:
             if t.endswith(k):
                 return int(float(t[:-len(k)]) * u)
         return int(t)
     except ValueError:
         raise error.ParseError(_("couldn't parse size: %s") % s)
 
 class hooks(object):
     '''A collection of hook functions that can be used to extend a
     function's behaviour. Hooks are called in lexicographic order,
     based on the names of their sources.'''
 
     def __init__(self):
         self._hooks = []
 
     def add(self, source, hook):
         self._hooks.append((source, hook))
 
     def __call__(self, *args):
         self._hooks.sort(key=lambda x: x[0])
         results = []
         for source, hook in self._hooks:
             results.append(hook(*args))
         return results
 
 def debugstacktrace(msg='stacktrace', skip=0, f=sys.stderr, otherf=sys.stdout):
     '''Writes a message to f (stderr) with a nicely formatted stacktrace.
     Skips the 'skip' last entries. By default it will flush stdout first.
     It can be used everywhere and do intentionally not require an ui object.
     Not be used in production code but very convenient while developing.
     '''
     if otherf:
         otherf.flush()
     f.write('%s at:\n' % msg)
     entries = [('%s:%s' % (fn, ln), func)
         for fn, ln, func, _text in traceback.extract_stack()[:-skip - 1]]
     if entries:
         fnmax = max(len(entry[0]) for entry in entries)
         for fnln, func in entries:
             f.write(' %-*s in %s\n' % (fnmax, fnln, func))
     f.flush()
 
 # convenient shortcut
 dst = debugstacktrace