py3: replace os.environ with encoding.environ (part 1 of 5)

os.environ is a dictionary which has string elements on Python 3. We have
encoding.environ which take care of all these things. This is the first patch
of 5 patch series which tend to replace the occurences of os.environ with
encoding.environ as using os.environ will result in unusual behaviour.

mercurial/bookmarks.py

@@ -1,608 +1,607
 # Mercurial bookmark support code
 #
 # Copyright 2008 David Soria Parra <[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 __future__ import absolute_import
 
 import errno
-import os
 
 from .i18n import _
 from .node import (
     bin,
     hex,
 )
 from . import (
     encoding,
     error,
     lock as lockmod,
     obsolete,
     util,
 )
 
 def _getbkfile(repo):
     """Hook so that extensions that mess with the store can hook bm storage.
 
     For core, this just handles wether we should see pending
     bookmarks or the committed ones. Other extensions (like share)
     may need to tweak this behavior further.
     """
     bkfile = None
-    if 'HG_PENDING' in os.environ:
+    if 'HG_PENDING' in encoding.environ:
         try:
             bkfile = repo.vfs('bookmarks.pending')
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
     if bkfile is None:
         bkfile = repo.vfs('bookmarks')
     return bkfile
 
 
 class bmstore(dict):
     """Storage for bookmarks.
 
     This object should do all bookmark-related reads and writes, so
     that it's fairly simple to replace the storage underlying
     bookmarks without having to clone the logic surrounding
     bookmarks. This type also should manage the active bookmark, if
     any.
 
     This particular bmstore implementation stores bookmarks as
     {hash}\s{name}\n (the same format as localtags) in
     .hg/bookmarks. The mapping is stored as {name: nodeid}.
     """
 
     def __init__(self, repo):
         dict.__init__(self)
         self._repo = repo
         try:
             bkfile = _getbkfile(repo)
             for line in bkfile:
                 line = line.strip()
                 if not line:
                     continue
                 if ' ' not in line:
                     repo.ui.warn(_('malformed line in .hg/bookmarks: %r\n')
                                  % line)
                     continue
                 sha, refspec = line.split(' ', 1)
                 refspec = encoding.tolocal(refspec)
                 try:
                     self[refspec] = repo.changelog.lookup(sha)
                 except LookupError:
                     pass
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
         self._clean = True
         self._active = _readactive(repo, self)
         self._aclean = True
 
     @property
     def active(self):
         return self._active
 
     @active.setter
     def active(self, mark):
         if mark is not None and mark not in self:
             raise AssertionError('bookmark %s does not exist!' % mark)
 
         self._active = mark
         self._aclean = False
 
     def __setitem__(self, *args, **kwargs):
         self._clean = False
         return dict.__setitem__(self, *args, **kwargs)
 
     def __delitem__(self, key):
         self._clean = False
         return dict.__delitem__(self, key)
 
     def recordchange(self, tr):
         """record that bookmarks have been changed in a transaction
 
         The transaction is then responsible for updating the file content."""
         tr.addfilegenerator('bookmarks', ('bookmarks',), self._write,
                             location='plain')
         tr.hookargs['bookmark_moved'] = '1'
 
     def _writerepo(self, repo):
         """Factored out for extensibility"""
         rbm = repo._bookmarks
         if rbm.active not in self:
             rbm.active = None
             rbm._writeactive()
 
         with repo.wlock():
             file_ = repo.vfs('bookmarks', 'w', atomictemp=True,
                              checkambig=True)
             try:
                 self._write(file_)
             except: # re-raises
                 file_.discard()
                 raise
             finally:
                 file_.close()
 
     def _writeactive(self):
         if self._aclean:
             return
         with self._repo.wlock():
             if self._active is not None:
                 f = self._repo.vfs('bookmarks.current', 'w', atomictemp=True,
                                    checkambig=True)
                 try:
                     f.write(encoding.fromlocal(self._active))
                 finally:
                     f.close()
             else:
                 try:
                     self._repo.vfs.unlink('bookmarks.current')
                 except OSError as inst:
                     if inst.errno != errno.ENOENT:
                         raise
         self._aclean = True
 
     def _write(self, fp):
         for name, node in self.iteritems():
             fp.write("%s %s\n" % (hex(node), encoding.fromlocal(name)))
         self._clean = True
         self._repo.invalidatevolatilesets()
 
     def expandname(self, bname):
         if bname == '.':
             if self.active:
                 return self.active
             else:
                 raise error.Abort(_("no active bookmark"))
         return bname
 
 def _readactive(repo, marks):
     """
     Get the active bookmark. We can have an active bookmark that updates
     itself as we commit. This function returns the name of that bookmark.
     It is stored in .hg/bookmarks.current
     """
     mark = None
     try:
         file = repo.vfs('bookmarks.current')
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return None
     try:
         # No readline() in osutil.posixfile, reading everything is
         # cheap.
         # Note that it's possible for readlines() here to raise
         # IOError, since we might be reading the active mark over
         # static-http which only tries to load the file when we try
         # to read from it.
         mark = encoding.tolocal((file.readlines() or [''])[0])
         if mark == '' or mark not in marks:
             mark = None
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return None
     finally:
         file.close()
     return mark
 
 def activate(repo, mark):
     """
     Set the given bookmark to be 'active', meaning that this bookmark will
     follow new commits that are made.
     The name is recorded in .hg/bookmarks.current
     """
     repo._bookmarks.active = mark
     repo._bookmarks._writeactive()
 
 def deactivate(repo):
     """
     Unset the active bookmark in this repository.
     """
     repo._bookmarks.active = None
     repo._bookmarks._writeactive()
 
 def isactivewdirparent(repo):
     """
     Tell whether the 'active' bookmark (the one that follows new commits)
     points to one of the parents of the current working directory (wdir).
 
     While this is normally the case, it can on occasion be false; for example,
     immediately after a pull, the active bookmark can be moved to point
     to a place different than the wdir. This is solved by running `hg update`.
     """
     mark = repo._activebookmark
     marks = repo._bookmarks
     parents = [p.node() for p in repo[None].parents()]
     return (mark in marks and marks[mark] in parents)
 
 def deletedivergent(repo, deletefrom, bm):
     '''Delete divergent versions of bm on nodes in deletefrom.
 
     Return True if at least one bookmark was deleted, False otherwise.'''
     deleted = False
     marks = repo._bookmarks
     divergent = [b for b in marks if b.split('@', 1)[0] == bm.split('@', 1)[0]]
     for mark in divergent:
         if mark == '@' or '@' not in mark:
             # can't be divergent by definition
             continue
         if mark and marks[mark] in deletefrom:
             if mark != bm:
                 del marks[mark]
                 deleted = True
     return deleted
 
 def calculateupdate(ui, repo, checkout):
     '''Return a tuple (targetrev, movemarkfrom) indicating the rev to
     check out and where to move the active bookmark from, if needed.'''
     movemarkfrom = None
     if checkout is None:
         activemark = repo._activebookmark
         if isactivewdirparent(repo):
             movemarkfrom = repo['.'].node()
         elif activemark:
             ui.status(_("updating to active bookmark %s\n") % activemark)
             checkout = activemark
     return (checkout, movemarkfrom)
 
 def update(repo, parents, node):
     deletefrom = parents
     marks = repo._bookmarks
     update = False
     active = marks.active
     if not active:
         return False
 
     if marks[active] in parents:
         new = repo[node]
         divs = [repo[b] for b in marks
                 if b.split('@', 1)[0] == active.split('@', 1)[0]]
         anc = repo.changelog.ancestors([new.rev()])
         deletefrom = [b.node() for b in divs if b.rev() in anc or b == new]
         if validdest(repo, repo[marks[active]], new):
             marks[active] = new.node()
             update = True
 
     if deletedivergent(repo, deletefrom, active):
         update = True
 
     if update:
         lock = tr = None
         try:
             lock = repo.lock()
             tr = repo.transaction('bookmark')
             marks.recordchange(tr)
             tr.close()
         finally:
             lockmod.release(tr, lock)
     return update
 
 def listbinbookmarks(repo):
     # We may try to list bookmarks on a repo type that does not
     # support it (e.g., statichttprepository).
     marks = getattr(repo, '_bookmarks', {})
 
     hasnode = repo.changelog.hasnode
     for k, v in marks.iteritems():
         # don't expose local divergent bookmarks
         if hasnode(v) and ('@' not in k or k.endswith('@')):
             yield k, v
 
 def listbookmarks(repo):
     d = {}
     for book, node in listbinbookmarks(repo):
         d[book] = hex(node)
     return d
 
 def pushbookmark(repo, key, old, new):
     w = l = tr = None
     try:
         w = repo.wlock()
         l = repo.lock()
         tr = repo.transaction('bookmarks')
         marks = repo._bookmarks
         existing = hex(marks.get(key, ''))
         if existing != old and existing != new:
             return False
         if new == '':
             del marks[key]
         else:
             if new not in repo:
                 return False
             marks[key] = repo[new].node()
         marks.recordchange(tr)
         tr.close()
         return True
     finally:
         lockmod.release(tr, l, w)
 
 def comparebookmarks(repo, srcmarks, dstmarks, targets=None):
     '''Compare bookmarks between srcmarks and dstmarks
 
     This returns tuple "(addsrc, adddst, advsrc, advdst, diverge,
     differ, invalid)", each are list of bookmarks below:
 
     :addsrc:  added on src side (removed on dst side, perhaps)
     :adddst:  added on dst side (removed on src side, perhaps)
     :advsrc:  advanced on src side
     :advdst:  advanced on dst side
     :diverge: diverge
     :differ:  changed, but changeset referred on src is unknown on dst
     :invalid: unknown on both side
     :same:    same on both side
 
     Each elements of lists in result tuple is tuple "(bookmark name,
     changeset ID on source side, changeset ID on destination
     side)". Each changeset IDs are 40 hexadecimal digit string or
     None.
 
     Changeset IDs of tuples in "addsrc", "adddst", "differ" or
      "invalid" list may be unknown for repo.
 
     If "targets" is specified, only bookmarks listed in it are
     examined.
     '''
 
     if targets:
         bset = set(targets)
     else:
         srcmarkset = set(srcmarks)
         dstmarkset = set(dstmarks)
         bset = srcmarkset | dstmarkset
 
     results = ([], [], [], [], [], [], [], [])
     addsrc = results[0].append
     adddst = results[1].append
     advsrc = results[2].append
     advdst = results[3].append
     diverge = results[4].append
     differ = results[5].append
     invalid = results[6].append
     same = results[7].append
 
     for b in sorted(bset):
         if b not in srcmarks:
             if b in dstmarks:
                 adddst((b, None, dstmarks[b]))
             else:
                 invalid((b, None, None))
         elif b not in dstmarks:
             addsrc((b, srcmarks[b], None))
         else:
             scid = srcmarks[b]
             dcid = dstmarks[b]
             if scid == dcid:
                 same((b, scid, dcid))
             elif scid in repo and dcid in repo:
                 sctx = repo[scid]
                 dctx = repo[dcid]
                 if sctx.rev() < dctx.rev():
                     if validdest(repo, sctx, dctx):
                         advdst((b, scid, dcid))
                     else:
                         diverge((b, scid, dcid))
                 else:
                     if validdest(repo, dctx, sctx):
                         advsrc((b, scid, dcid))
                     else:
                         diverge((b, scid, dcid))
             else:
                 # it is too expensive to examine in detail, in this case
                 differ((b, scid, dcid))
 
     return results
 
 def _diverge(ui, b, path, localmarks, remotenode):
     '''Return appropriate diverged bookmark for specified ``path``
 
     This returns None, if it is failed to assign any divergent
     bookmark name.
 
     This reuses already existing one with "@number" suffix, if it
     refers ``remotenode``.
     '''
     if b == '@':
         b = ''
     # try to use an @pathalias suffix
     # if an @pathalias already exists, we overwrite (update) it
     if path.startswith("file:"):
         path = util.url(path).path
     for p, u in ui.configitems("paths"):
         if u.startswith("file:"):
             u = util.url(u).path
         if path == u:
             return '%s@%s' % (b, p)
 
     # assign a unique "@number" suffix newly
     for x in range(1, 100):
         n = '%s@%d' % (b, x)
         if n not in localmarks or localmarks[n] == remotenode:
             return n
 
     return None
 
 def unhexlifybookmarks(marks):
     binremotemarks = {}
     for name, node in marks.items():
         binremotemarks[name] = bin(node)
     return binremotemarks
 
 def updatefromremote(ui, repo, remotemarks, path, trfunc, explicit=()):
     ui.debug("checking for updated bookmarks\n")
     localmarks = repo._bookmarks
     (addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same
     ) = comparebookmarks(repo, remotemarks, localmarks)
 
     status = ui.status
     warn = ui.warn
     if ui.configbool('ui', 'quietbookmarkmove', False):
         status = warn = ui.debug
 
     explicit = set(explicit)
     changed = []
     for b, scid, dcid in addsrc:
         if scid in repo: # add remote bookmarks for changes we already have
             changed.append((b, scid, status,
                             _("adding remote bookmark %s\n") % (b)))
         elif b in explicit:
             explicit.remove(b)
             ui.warn(_("remote bookmark %s points to locally missing %s\n")
                     % (b, hex(scid)[:12]))
 
     for b, scid, dcid in advsrc:
         changed.append((b, scid, status,
                         _("updating bookmark %s\n") % (b)))
     # remove normal movement from explicit set
     explicit.difference_update(d[0] for d in changed)
 
     for b, scid, dcid in diverge:
         if b in explicit:
             explicit.discard(b)
             changed.append((b, scid, status,
                             _("importing bookmark %s\n") % (b)))
         else:
             db = _diverge(ui, b, path, localmarks, scid)
             if db:
                 changed.append((db, scid, warn,
                                 _("divergent bookmark %s stored as %s\n") %
                                 (b, db)))
             else:
                 warn(_("warning: failed to assign numbered name "
                        "to divergent bookmark %s\n") % (b))
     for b, scid, dcid in adddst + advdst:
         if b in explicit:
             explicit.discard(b)
             changed.append((b, scid, status,
                             _("importing bookmark %s\n") % (b)))
     for b, scid, dcid in differ:
         if b in explicit:
             explicit.remove(b)
             ui.warn(_("remote bookmark %s points to locally missing %s\n")
                     % (b, hex(scid)[:12]))
 
     if changed:
         tr = trfunc()
         for b, node, writer, msg in sorted(changed):
             localmarks[b] = node
             writer(msg)
         localmarks.recordchange(tr)
 
 def incoming(ui, repo, other):
     '''Show bookmarks incoming from other to repo
     '''
     ui.status(_("searching for changed bookmarks\n"))
 
     remotemarks = unhexlifybookmarks(other.listkeys('bookmarks'))
     r = comparebookmarks(repo, remotemarks, repo._bookmarks)
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = r
 
     incomings = []
     if ui.debugflag:
         getid = lambda id: id
     else:
         getid = lambda id: id[:12]
     if ui.verbose:
         def add(b, id, st):
             incomings.append("   %-25s %s %s\n" % (b, getid(id), st))
     else:
         def add(b, id, st):
             incomings.append("   %-25s %s\n" % (b, getid(id)))
     for b, scid, dcid in addsrc:
         # i18n: "added" refers to a bookmark
         add(b, hex(scid), _('added'))
     for b, scid, dcid in advsrc:
         # i18n: "advanced" refers to a bookmark
         add(b, hex(scid), _('advanced'))
     for b, scid, dcid in diverge:
         # i18n: "diverged" refers to a bookmark
         add(b, hex(scid), _('diverged'))
     for b, scid, dcid in differ:
         # i18n: "changed" refers to a bookmark
         add(b, hex(scid), _('changed'))
 
     if not incomings:
         ui.status(_("no changed bookmarks found\n"))
         return 1
 
     for s in sorted(incomings):
         ui.write(s)
 
     return 0
 
 def outgoing(ui, repo, other):
     '''Show bookmarks outgoing from repo to other
     '''
     ui.status(_("searching for changed bookmarks\n"))
 
     remotemarks = unhexlifybookmarks(other.listkeys('bookmarks'))
     r = comparebookmarks(repo, repo._bookmarks, remotemarks)
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = r
 
     outgoings = []
     if ui.debugflag:
         getid = lambda id: id
     else:
         getid = lambda id: id[:12]
     if ui.verbose:
         def add(b, id, st):
             outgoings.append("   %-25s %s %s\n" % (b, getid(id), st))
     else:
         def add(b, id, st):
             outgoings.append("   %-25s %s\n" % (b, getid(id)))
     for b, scid, dcid in addsrc:
         # i18n: "added refers to a bookmark
         add(b, hex(scid), _('added'))
     for b, scid, dcid in adddst:
         # i18n: "deleted" refers to a bookmark
         add(b, ' ' * 40, _('deleted'))
     for b, scid, dcid in advsrc:
         # i18n: "advanced" refers to a bookmark
         add(b, hex(scid), _('advanced'))
     for b, scid, dcid in diverge:
         # i18n: "diverged" refers to a bookmark
         add(b, hex(scid), _('diverged'))
     for b, scid, dcid in differ:
         # i18n: "changed" refers to a bookmark
         add(b, hex(scid), _('changed'))
 
     if not outgoings:
         ui.status(_("no changed bookmarks found\n"))
         return 1
 
     for s in sorted(outgoings):
         ui.write(s)
 
     return 0
 
 def summary(repo, other):
     '''Compare bookmarks between repo and other for "hg summary" output
 
     This returns "(# of incoming, # of outgoing)" tuple.
     '''
     remotemarks = unhexlifybookmarks(other.listkeys('bookmarks'))
     r = comparebookmarks(repo, remotemarks, repo._bookmarks)
     addsrc, adddst, advsrc, advdst, diverge, differ, invalid, same = r
     return (len(addsrc), len(adddst))
 
 def validdest(repo, old, new):
     """Is the new bookmark destination a valid update from the old one"""
     repo = repo.unfiltered()
     if old == new:
         # Old == new -> nothing to update.
         return False
     elif not old:
         # old is nullrev, anything is valid.
         # (new != nullrev has been excluded by the previous check)
         return True
     elif repo.obsstore:
         return new.node() in obsolete.foreground(repo, [old.node()])
     else:
         # still an independent clause as it is lazier (and therefore faster)
         return old.descendant(new)

mercurial/dirstate.py

@@ -1,1260 +1,1260
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import errno
 import os
 import stat
 
 from .i18n import _
 from .node import nullid
 from . import (
     encoding,
     error,
     match as matchmod,
     osutil,
     parsers,
     pathutil,
     pycompat,
     scmutil,
     util,
 )
 
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7fffffff
 
 dirstatetuple = parsers.dirstatetuple
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
 def _getfsnow(vfs):
     '''Get "now" timestamp on filesystem'''
     tmpfd, tmpname = vfs.mkstemp()
     try:
         return os.fstat(tmpfd).st_mtime
     finally:
         os.close(tmpfd)
         vfs.unlink(tmpname)
 
 def nonnormalentries(dmap):
     '''Compute the nonnormal dirstate entries from the dmap'''
     try:
         return parsers.nonnormalentries(dmap)
     except AttributeError:
         return set(fname for fname, e in dmap.iteritems()
                    if e[0] != 'n' or e[3] == -1)
 
 def _trypending(root, vfs, filename):
     '''Open  file to be read according to HG_PENDING environment variable
 
     This opens '.pending' of specified 'filename' only when HG_PENDING
     is equal to 'root'.
 
     This returns '(fp, is_pending_opened)' tuple.
     '''
-    if root == os.environ.get('HG_PENDING'):
+    if root == encoding.environ.get('HG_PENDING'):
         try:
             return (vfs('%s.pending' % filename), True)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
     return (vfs(filename), False)
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
         # UNC path pointing to root share (issue4557)
         self._rootdir = pathutil.normasprefix(root)
         # internal config: ui.forcecwd
         forcecwd = ui.config('ui', 'forcecwd')
         if forcecwd:
             self._cwd = forcecwd
         self._dirty = False
         self._dirtypl = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
         self._parentwriters = 0
         self._filename = 'dirstate'
         self._pendingfilename = '%s.pending' % self._filename
         self._plchangecallbacks = {}
         self._origpl = None
 
         # for consistent view between _pl() and _read() invocations
         self._pendingmode = None
 
     def beginparentchange(self):
         '''Marks the beginning of a set of changes that involve changing
         the dirstate parents. If there is an exception during this time,
         the dirstate will not be written when the wlock is released. This
         prevents writing an incoherent dirstate where the parent doesn't
         match the contents.
         '''
         self._parentwriters += 1
 
     def endparentchange(self):
         '''Marks the end of a set of changes that involve changing the
         dirstate parents. Once all parent changes have been marked done,
         the wlock will be free to write the dirstate on release.
         '''
         if self._parentwriters > 0:
             self._parentwriters -= 1
 
     def pendingparentchange(self):
         '''Returns true if the dirstate is in the middle of a set of changes
         that modify the dirstate parent.
         '''
         return self._parentwriters > 0
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _nonnormalset(self):
         return nonnormalentries(self._map)
 
     @propertycache
     def _filefoldmap(self):
         try:
             makefilefoldmap = parsers.make_file_foldmap
         except AttributeError:
             pass
         else:
             return makefilefoldmap(self._map, util.normcasespec,
                                    util.normcasefallback)
 
         f = {}
         normcase = util.normcase
         for name, s in self._map.iteritems():
             if s[0] != 'r':
                 f[normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     @propertycache
     def _dirfoldmap(self):
         f = {}
         normcase = util.normcase
         for name in self._dirs:
             f[normcase(name)] = name
         return f
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             fp = self._opendirstatefile()
             st = fp.read(40)
             fp.close()
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise error.Abort(_('working directory state appears damaged!'))
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
         return util.dirs(self._map, 'r')
 
     def dirs(self):
         return self._dirs
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = self._ignorefiles()
         if not files:
             return util.never
 
         pats = ['include:%s' % f for f in files]
         return matchmod.match(self._root, '', [], pats, warn=self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and pycompat.ossep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.fscasesensitive(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return 'l'
                     if util.statisexec(st):
                         return 'x'
                 except OSError:
                     pass
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     @propertycache
     def _cwd(self):
         return pycompat.getcwd()
 
     def getcwd(self):
         '''Return the path from which a canonical path is calculated.
 
         This path should be used to resolve file patterns or to convert
         canonical paths back to file paths for display. It shouldn't be
         used to get real file paths. Use vfs functions instead.
         '''
         cwd = self._cwd
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += pycompat.ossep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.pconvert(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def iteritems(self):
         return self._map.iteritems()
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         if self._parentwriters == 0:
             raise ValueError("cannot set dirstate parent without "
                              "calling dirstate.beginparentchange")
 
         self._dirty = self._dirtypl = True
         oldp2 = self._pl[1]
         if self._origpl is None:
             self._origpl = self._pl
         self._pl = p1, p2
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             for f, s in self._map.iteritems():
                 # Discard 'm' markers when moving away from a merge state
                 if s[0] == 'm':
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.normallookup(f)
                 # Also fix up otherparent markers
                 elif s[0] == 'n' and s[2] == -2:
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.add(f)
         return copies
 
     def setbranch(self, branch):
         self._branch = encoding.fromlocal(branch)
         f = self._opener('branch', 'w', atomictemp=True, checkambig=True)
         try:
             f.write(self._branch + '\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache['_branch']
             if ce:
                 ce.refresh()
         except: # re-raises
             f.discard()
             raise
 
     def _opendirstatefile(self):
         fp, mode = _trypending(self._root, self._opener, self._filename)
         if self._pendingmode is not None and self._pendingmode != mode:
             fp.close()
             raise error.Abort(_('working directory state may be '
                                 'changed parallelly'))
         self._pendingmode = mode
         return fp
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             fp = self._opendirstatefile()
             try:
                 st = fp.read()
             finally:
                 fp.close()
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         if util.safehasattr(parsers, 'dict_new_presized'):
             # Make an estimate of the number of files in the dirstate based on
             # its size. From a linear regression on a set of real-world repos,
             # all over 10,000 files, the size of a dirstate entry is 85
             # bytes. The cost of resizing is significantly higher than the cost
             # of filling in a larger presized dict, so subtract 20% from the
             # size.
             #
             # This heuristic is imperfect in many ways, so in a future dirstate
             # format update it makes sense to just record the number of entries
             # on write.
             self._map = parsers.dict_new_presized(len(st) / 71)
 
         # Python's garbage collector triggers a GC each time a certain number
         # of container objects (the number being defined by
         # gc.get_threshold()) are allocated. parse_dirstate creates a tuple
         # for each file in the dirstate. The C version then immediately marks
         # them as not to be tracked by the collector. However, this has no
         # effect on when GCs are triggered, only on what objects the GC looks
         # into. This means that O(number of files) GCs are unavoidable.
         # Depending on when in the process's lifetime the dirstate is parsed,
         # this can get very expensive. As a workaround, disable GC while
         # parsing the dirstate.
         #
         # (we cannot decorate the function directly since it is in a C module)
         parse_dirstate = util.nogc(parsers.parse_dirstate)
         p = parse_dirstate(self._map, self._copymap, st)
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in ("_map", "_copymap", "_filefoldmap", "_dirfoldmap", "_branch",
                   "_pl", "_dirs", "_ignore", "_nonnormalset"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
         self._parentwriters = 0
         self._origpl = None
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
             self._dirs.delpath(f)
 
         if "_filefoldmap" in self.__dict__:
             normed = util.normcase(f)
             if normed in self._filefoldmap:
                 del self._filefoldmap[normed]
 
     def _addpath(self, f, state, mode, size, mtime):
         oldstate = self[f]
         if state == 'a' or oldstate == 'r':
             scmutil.checkfilename(f)
             if f in self._dirs:
                 raise error.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in util.finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise error.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
             self._dirs.addpath(f)
         self._dirty = True
         self._map[f] = dirstatetuple(state, mode, size, mtime)
         if state != 'n' or mtime == -1:
             self._nonnormalset.add(f)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         s = os.lstat(self._join(f))
         mtime = s.st_mtime
         self._addpath(f, 'n', s.st_mode,
                       s.st_size & _rangemask, mtime & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
         if f in self._nonnormalset:
             self._nonnormalset.remove(f)
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.otherparent(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._addpath(f, 'n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
         if f in self._nonnormalset:
             self._nonnormalset.remove(f)
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise error.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         if f in self and self[f] == 'n':
             # merge-like
             self._addpath(f, 'm', 0, -2, -1)
         else:
             # add-like
             self._addpath(f, 'n', 0, -2, -1)
 
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, 'a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             # backup the previous state
             entry = self._map[f]
             if entry[0] == 'm': # merge
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2: # other parent
                 size = -2
         self._map[f] = dirstatetuple('r', 0, size, 0)
         self._nonnormalset.add(f)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         return self.otherparent(f)
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         if f in self._map:
             self._dirty = True
             self._droppath(f)
             del self._map[f]
             if f in self._nonnormalset:
                 self._nonnormalset.remove(f)
             if f in self._copymap:
                 del self._copymap[f]
 
     def _discoverpath(self, path, normed, ignoremissing, exists, storemap):
         if exists is None:
             exists = os.path.lexists(os.path.join(self._root, path))
         if not exists:
             # Maybe a path component exists
             if not ignoremissing and '/' in path:
                 d, f = path.rsplit('/', 1)
                 d = self._normalize(d, False, ignoremissing, None)
                 folded = d + "/" + f
             else:
                 # No path components, preserve original case
                 folded = path
         else:
             # recursively normalize leading directory components
             # against dirstate
             if '/' in normed:
                 d, f = normed.rsplit('/', 1)
                 d = self._normalize(d, False, ignoremissing, True)
                 r = self._root + "/" + d
                 folded = d + "/" + util.fspath(f, r)
             else:
                 folded = util.fspath(normed, self._root)
             storemap[normed] = folded
 
         return folded
 
     def _normalizefile(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._filefoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 folded = self._discoverpath(path, normed, ignoremissing, exists,
                                             self._filefoldmap)
         return folded
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._filefoldmap.get(normed, None)
         if folded is None:
             folded = self._dirfoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 # store discovered result in dirfoldmap so that future
                 # normalizefile calls don't start matching directories
                 folded = self._discoverpath(path, normed, ignoremissing, exists,
                                             self._dirfoldmap)
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map = {}
         self._nonnormalset = set()
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs")
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         if changedfiles is None:
             # Rebuild entire dirstate
             changedfiles = allfiles
             lastnormaltime = self._lastnormaltime
             self.clear()
             self._lastnormaltime = lastnormaltime
 
         if self._origpl is None:
             self._origpl = self._pl
         self._pl = (parent, nullid)
         for f in changedfiles:
             if f in allfiles:
                 self.normallookup(f)
             else:
                 self.drop(f)
 
         self._dirty = True
 
     def write(self, tr):
         if not self._dirty:
             return
 
         filename = self._filename
         if tr:
             # 'dirstate.write()' is not only for writing in-memory
             # changes out, but also for dropping ambiguous timestamp.
             # delayed writing re-raise "ambiguous timestamp issue".
             # See also the wiki page below for detail:
             # https://www.mercurial-scm.org/wiki/DirstateTransactionPlan
 
             # emulate dropping timestamp in 'parsers.pack_dirstate'
             now = _getfsnow(self._opener)
             dmap = self._map
             for f, e in dmap.iteritems():
                 if e[0] == 'n' and e[3] == now:
                     dmap[f] = dirstatetuple(e[0], e[1], e[2], -1)
                     self._nonnormalset.add(f)
 
             # emulate that all 'dirstate.normal' results are written out
             self._lastnormaltime = 0
 
             # delay writing in-memory changes out
             tr.addfilegenerator('dirstate', (self._filename,),
                                 self._writedirstate, location='plain')
             return
 
         st = self._opener(filename, "w", atomictemp=True, checkambig=True)
         self._writedirstate(st)
 
     def addparentchangecallback(self, category, callback):
         """add a callback to be called when the wd parents are changed
 
         Callback will be called with the following arguments:
             dirstate, (oldp1, oldp2), (newp1, newp2)
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._plchangecallbacks[category] = callback
 
     def _writedirstate(self, st):
         # notify callbacks about parents change
         if self._origpl is not None and self._origpl != self._pl:
             for c, callback in sorted(self._plchangecallbacks.iteritems()):
                 callback(self, self._origpl, self._pl)
             self._origpl = None
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st).st_mtime & _rangemask
 
         # enough 'delaywrite' prevents 'pack_dirstate' from dropping
         # timestamp of each entries in dirstate, because of 'now > mtime'
         delaywrite = self._ui.configint('debug', 'dirstate.delaywrite', 0)
         if delaywrite > 0:
             # do we have any files to delay for?
             for f, e in self._map.iteritems():
                 if e[0] == 'n' and e[3] == now:
                     import time # to avoid useless import
                     # rather than sleep n seconds, sleep until the next
                     # multiple of n seconds
                     clock = time.time()
                     start = int(clock) - (int(clock) % delaywrite)
                     end = start + delaywrite
                     time.sleep(end - clock)
                     now = end # trust our estimate that the end is near now
                     break
 
         st.write(parsers.pack_dirstate(self._map, self._copymap, self._pl, now))
         self._nonnormalset = nonnormalentries(self._map)
         st.close()
         self._lastnormaltime = 0
         self._dirty = self._dirtypl = False
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in util.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def _ignorefiles(self):
         files = []
         if os.path.exists(self._join('.hgignore')):
             files.append(self._join('.hgignore'))
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 # we need to use os.path.join here rather than self._join
                 # because path is arbitrary and user-specified
                 files.append(os.path.join(self._rootdir, util.expandpath(path)))
         return files
 
     def _ignorefileandline(self, f):
         files = collections.deque(self._ignorefiles())
         visited = set()
         while files:
             i = files.popleft()
             patterns = matchmod.readpatternfile(i, self._ui.warn,
                                                 sourceinfo=True)
             for pattern, lineno, line in patterns:
                 kind, p = matchmod._patsplit(pattern, 'glob')
                 if kind == "subinclude":
                     if p not in visited:
                         files.append(p)
                     continue
                 m = matchmod.match(self._root, '', [], [pattern],
                                    warn=self._ui.warn)
                 if m(f):
                     return (i, lineno, line)
             visited.add(i)
         return (None, -1, "")
 
     def _walkexplicit(self, match, subrepos):
         '''Get stat data about the files explicitly specified by match.
 
         Return a triple (results, dirsfound, dirsnotfound).
         - results is a mapping from filename to stat result. It also contains
           listings mapping subrepos and .hg to None.
         - dirsfound is a list of files found to be directories.
         - dirsnotfound is a list of files that the dirstate thinks are
           directories and that were not found.'''
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         matchedir = match.explicitdir
         badfn = match.bad
         dmap = self._map
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         dirsfound = []
         foundadd = dirsfound.append
         dirsnotfound = []
         notfoundadd = dirsnotfound.append
 
         if not match.isexact() and self._checkcase:
             normalize = self._normalize
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['.']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         alldirs = None
         for ff in files:
             # constructing the foldmap is expensive, so don't do it for the
             # common case where files is ['.']
             if normalize and ff != '.':
                 nf = normalize(ff, False, True)
             else:
                 nf = ff
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     if nf in dmap:
                         # file replaced by dir on disk but still in dirstate
                         results[nf] = None
                     if matchedir:
                         matchedir(nf)
                     foundadd((nf, ff))
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError as inst: # nf not found on disk - it is dirstate only
                 if nf in dmap: # does it exactly match a missing file?
                     results[nf] = None
                 else: # does it match a missing directory?
                     if alldirs is None:
                         alldirs = util.dirs(dmap)
                     if nf in alldirs:
                         if matchedir:
                             matchedir(nf)
                         notfoundadd(nf)
                     else:
                         badfn(ff, inst.strerror)
 
         # Case insensitive filesystems cannot rely on lstat() failing to detect
         # a case-only rename.  Prune the stat object for any file that does not
         # match the case in the filesystem, if there are multiple files that
         # normalize to the same path.
         if match.isexact() and self._checkcase:
             normed = {}
 
             for f, st in results.iteritems():
                 if st is None:
                     continue
 
                 nc = util.normcase(f)
                 paths = normed.get(nc)
 
                 if paths is None:
                     paths = set()
                     normed[nc] = paths
 
                 paths.add(f)
 
             for norm, paths in normed.iteritems():
                 if len(paths) > 1:
                     for path in paths:
                         folded = self._discoverpath(path, norm, True, None,
                                                     self._dirfoldmap)
                         if path != folded:
                             results[path] = None
 
         return results, dirsfound, dirsnotfound
 
     def walk(self, match, subrepos, unknown, ignored, full=True):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         If full is False, maybe skip some known-clean files.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
 
         '''
         # full is a flag that extensions that hook into walk can use -- this
         # implementation doesn't use it at all. This satisfies the contract
         # because we only guarantee a "maybe".
 
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif unknown:
             ignore = self._ignore
             dirignore = self._dirignore
         else:
             # if not unknown and not ignored, drop dir recursion and step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         matchtdir = match.traversedir
         dmap = self._map
         listdir = osutil.listdir
         lstat = os.lstat
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
 
         exact = skipstep3 = False
         if match.isexact(): # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.prefix(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             normalizefile = self._normalizefile
             skipstep3 = False
         else:
             normalize = self._normalize
             normalizefile = None
 
         # step 1: find all explicit files
         results, work, dirsnotfound = self._walkexplicit(match, subrepos)
 
         skipstep3 = skipstep3 and not (work or dirsnotfound)
         work = [d for d in work if not dirignore(d[0])]
 
         # step 2: visit subdirectories
         def traverse(work, alreadynormed):
             wadd = work.append
             while work:
                 nd = work.pop()
                 skip = None
                 if nd == '.':
                     nd = ''
                 else:
                     skip = '.hg'
                 try:
                     entries = listdir(join(nd), stat=True, skip=skip)
                 except OSError as inst:
                     if inst.errno in (errno.EACCES, errno.ENOENT):
                         match.bad(self.pathto(nd), inst.strerror)
                         continue
                     raise
                 for f, kind, st in entries:
                     if normalizefile:
                         # even though f might be a directory, we're only
                         # interested in comparing it to files currently in the
                         # dmap -- therefore normalizefile is enough
                         nf = normalizefile(nd and (nd + "/" + f) or f, True,
                                            True)
                     else:
                         nf = nd and (nd + "/" + f) or f
                     if nf not in results:
                         if kind == dirkind:
                             if not ignore(nf):
                                 if matchtdir:
                                     matchtdir(nf)
                                 wadd(nf)
                             if nf in dmap and (matchalways or matchfn(nf)):
                                 results[nf] = None
                         elif kind == regkind or kind == lnkkind:
                             if nf in dmap:
                                 if matchalways or matchfn(nf):
                                     results[nf] = st
                             elif ((matchalways or matchfn(nf))
                                   and not ignore(nf)):
                                 # unknown file -- normalize if necessary
                                 if not alreadynormed:
                                     nf = normalize(nf, False, True)
                                 results[nf] = st
                         elif nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
 
         for nd, d in work:
             # alreadynormed means that processwork doesn't have to do any
             # expensive directory normalization
             alreadynormed = not normalize or nd == d
             traverse([d], alreadynormed)
 
         for s in subrepos:
             del results[s]
         del results['.hg']
 
         # step 3: visit remaining files from dmap
         if not skipstep3 and not exact:
             # If a dmap file is not in results yet, it was either
             # a) not matching matchfn b) ignored, c) missing, or d) under a
             # symlink directory.
             if not results and matchalways:
                 visit = dmap.keys()
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked all dirs under the roots
                 # that wasn't ignored, and everything that matched was stat'ed
                 # and is already in results.
                 # The rest must thus be ignored or under a symlink.
                 audit_path = pathutil.pathauditor(self._root)
 
                 for nf in iter(visit):
                     # If a stat for the same file was already added with a
                     # different case, don't add one for this, since that would
                     # make it appear as if the file exists under both names
                     # on disk.
                     if (normalizefile and
                         normalizefile(nf, True, True) in results):
                         results[nf] = None
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     elif audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                             # file was just ignored, no links, and exists
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         # which we in this case report as missing
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat and check everything we missed.
                 nf = iter(visit).next
                 for st in util.statfiles([join(i) for i in visit]):
                     results[nf()] = st
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a pair of (unsure, status), where status is of type
         scmutil.status and:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           status.modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           status.clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         copymap = self._copymap
         lastnormaltime = self._lastnormaltime
 
         # We need to do full walks when either
         # - we're listing all clean files, or
         # - match.traversedir does something, because match.traversedir should
         #   be called for every dir in the working dir
         full = listclean or match.traversedir is not None
         for fn, st in self.walk(match, subrepos, listunknown, listignored,
                                 full=full).iteritems():
             if fn not in dmap:
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 else:
                     uadd(fn)
                 continue
 
             # This is equivalent to 'state, mode, size, time = dmap[fn]' but not
             # written like that for performance reasons. dmap[fn] is not a
             # Python tuple in compiled builds. The CPython UNPACK_SEQUENCE
             # opcode has fast paths when the value to be unpacked is a tuple or
             # a list, but falls back to creating a full-fledged iterator in
             # general. That is much slower than simply accessing and storing the
             # tuple members one by one.
             t = dmap[fn]
             state = t[0]
             mode = t[1]
             size = t[2]
             time = t[3]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 if (size >= 0 and
                     ((size != st.st_size and size != st.st_size & _rangemask)
                      or ((mode ^ st.st_mode) & 0o100 and checkexec))
                     or size == -2 # other parent
                     or fn in copymap):
                     madd(fn)
                 elif time != st.st_mtime and time != st.st_mtime & _rangemask:
                     ladd(fn)
                 elif st.st_mtime == lastnormaltime:
                     # fn may have just been marked as normal and it may have
                     # changed in the same second without changing its size.
                     # This can happen if we quickly do multiple commits.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, scmutil.status(modified, added, removed, deleted,
                                        unknown, ignored, clean))
 
     def matches(self, match):
         '''
         return files in the dirstate (in whatever state) filtered by match
         '''
         dmap = self._map
         if match.always():
             return dmap.keys()
         files = match.files()
         if match.isexact():
             # fast path -- filter the other way around, since typically files is
             # much smaller than dmap
             return [f for f in files if f in dmap]
         if match.prefix() and all(fn in dmap for fn in files):
             # fast path -- all the values are known to be files, so just return
             # that
             return list(files)
         return [f for f in dmap if match(f)]
 
     def _actualfilename(self, tr):
         if tr:
             return self._pendingfilename
         else:
             return self._filename
 
     def savebackup(self, tr, suffix='', prefix=''):
         '''Save current dirstate into backup file with suffix'''
         assert len(suffix) > 0 or len(prefix) > 0
         filename = self._actualfilename(tr)
 
         # use '_writedirstate' instead of 'write' to write changes certainly,
         # because the latter omits writing out if transaction is running.
         # output file will be used to create backup of dirstate at this point.
         self._writedirstate(self._opener(filename, "w", atomictemp=True,
                                          checkambig=True))
 
         if tr:
             # ensure that subsequent tr.writepending returns True for
             # changes written out above, even if dirstate is never
             # changed after this
             tr.addfilegenerator('dirstate', (self._filename,),
                                 self._writedirstate, location='plain')
 
             # ensure that pending file written above is unlinked at
             # failure, even if tr.writepending isn't invoked until the
             # end of this transaction
             tr.registertmp(filename, location='plain')
 
         self._opener.write(prefix + self._filename + suffix,
                            self._opener.tryread(filename))
 
     def restorebackup(self, tr, suffix='', prefix=''):
         '''Restore dirstate by backup file with suffix'''
         assert len(suffix) > 0 or len(prefix) > 0
         # this "invalidate()" prevents "wlock.release()" from writing
         # changes of dirstate out after restoring from backup file
         self.invalidate()
         filename = self._actualfilename(tr)
         # using self._filename to avoid having "pending" in the backup filename
         self._opener.rename(prefix + self._filename + suffix, filename,
                             checkambig=True)
 
     def clearbackup(self, tr, suffix='', prefix=''):
         '''Clear backup file with suffix'''
         assert len(suffix) > 0 or len(prefix) > 0
         # using self._filename to avoid having "pending" in the backup filename
         self._opener.unlink(prefix + self._filename + suffix)

mercurial/localrepo.py

@@ -1,2004 +1,2004
 # localrepo.py - read/write repository class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import hashlib
 import inspect
 import os
 import random
 import time
 import weakref
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     short,
     wdirrev,
 )
 from . import (
     bookmarks,
     branchmap,
     bundle2,
     changegroup,
     changelog,
     context,
     dirstate,
     dirstateguard,
     encoding,
     error,
     exchange,
     extensions,
     filelog,
     hook,
     lock as lockmod,
     manifest,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     namespaces,
     obsolete,
     pathutil,
     peer,
     phases,
     pushkey,
     repoview,
     revset,
     scmutil,
     store,
     subrepo,
     tags as tagsmod,
     transaction,
     util,
 )
 
 release = lockmod.release
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 class repofilecache(scmutil.filecache):
     """All filecache usage on repo are done for logic that should be unfiltered
     """
 
     def __get__(self, repo, type=None):
         if repo is None:
             return self
         return super(repofilecache, self).__get__(repo.unfiltered(), type)
     def __set__(self, repo, value):
         return super(repofilecache, self).__set__(repo.unfiltered(), value)
     def __delete__(self, repo):
         return super(repofilecache, self).__delete__(repo.unfiltered())
 
 class storecache(repofilecache):
     """filecache for files in the store"""
     def join(self, obj, fname):
         return obj.sjoin(fname)
 
 class unfilteredpropertycache(util.propertycache):
     """propertycache that apply to unfiltered repo only"""
 
     def __get__(self, repo, type=None):
         unfi = repo.unfiltered()
         if unfi is repo:
             return super(unfilteredpropertycache, self).__get__(unfi)
         return getattr(unfi, self.name)
 
 class filteredpropertycache(util.propertycache):
     """propertycache that must take filtering in account"""
 
     def cachevalue(self, obj, value):
         object.__setattr__(obj, self.name, value)
 
 
 def hasunfilteredcache(repo, name):
     """check if a repo has an unfilteredpropertycache value for <name>"""
     return name in vars(repo.unfiltered())
 
 def unfilteredmethod(orig):
     """decorate method that always need to be run on unfiltered version"""
     def wrapper(repo, *args, **kwargs):
         return orig(repo.unfiltered(), *args, **kwargs)
     return wrapper
 
 moderncaps = set(('lookup', 'branchmap', 'pushkey', 'known', 'getbundle',
                   'unbundle'))
 legacycaps = moderncaps.union(set(['changegroupsubset']))
 
 class localpeer(peer.peerrepository):
     '''peer for a local repo; reflects only the most recent API'''
 
     def __init__(self, repo, caps=moderncaps):
         peer.peerrepository.__init__(self)
         self._repo = repo.filtered('served')
         self.ui = repo.ui
         self._caps = repo._restrictcapabilities(caps)
         self.requirements = repo.requirements
         self.supportedformats = repo.supportedformats
 
     def close(self):
         self._repo.close()
 
     def _capabilities(self):
         return self._caps
 
     def local(self):
         return self._repo
 
     def canpush(self):
         return True
 
     def url(self):
         return self._repo.url()
 
     def lookup(self, key):
         return self._repo.lookup(key)
 
     def branchmap(self):
         return self._repo.branchmap()
 
     def heads(self):
         return self._repo.heads()
 
     def known(self, nodes):
         return self._repo.known(nodes)
 
     def getbundle(self, source, heads=None, common=None, bundlecaps=None,
                   **kwargs):
         chunks = exchange.getbundlechunks(self._repo, source, heads=heads,
                                           common=common, bundlecaps=bundlecaps,
                                           **kwargs)
         cb = util.chunkbuffer(chunks)
 
         if bundlecaps is not None and 'HG20' in bundlecaps:
             # When requesting a bundle2, getbundle returns a stream to make the
             # wire level function happier. We need to build a proper object
             # from it in local peer.
             return bundle2.getunbundler(self.ui, cb)
         else:
             return changegroup.getunbundler('01', cb, None)
 
     # TODO We might want to move the next two calls into legacypeer and add
     # unbundle instead.
 
     def unbundle(self, cg, heads, url):
         """apply a bundle on a repo
 
         This function handles the repo locking itself."""
         try:
             try:
                 cg = exchange.readbundle(self.ui, cg, None)
                 ret = exchange.unbundle(self._repo, cg, heads, 'push', url)
                 if util.safehasattr(ret, 'getchunks'):
                     # This is a bundle20 object, turn it into an unbundler.
                     # This little dance should be dropped eventually when the
                     # API is finally improved.
                     stream = util.chunkbuffer(ret.getchunks())
                     ret = bundle2.getunbundler(self.ui, stream)
                 return ret
             except Exception as exc:
                 # If the exception contains output salvaged from a bundle2
                 # reply, we need to make sure it is printed before continuing
                 # to fail. So we build a bundle2 with such output and consume
                 # it directly.
                 #
                 # This is not very elegant but allows a "simple" solution for
                 # issue4594
                 output = getattr(exc, '_bundle2salvagedoutput', ())
                 if output:
                     bundler = bundle2.bundle20(self._repo.ui)
                     for out in output:
                         bundler.addpart(out)
                     stream = util.chunkbuffer(bundler.getchunks())
                     b = bundle2.getunbundler(self.ui, stream)
                     bundle2.processbundle(self._repo, b)
                 raise
         except error.PushRaced as exc:
             raise error.ResponseError(_('push failed:'), str(exc))
 
     def lock(self):
         return self._repo.lock()
 
     def addchangegroup(self, cg, source, url):
         return cg.apply(self._repo, source, url)
 
     def pushkey(self, namespace, key, old, new):
         return self._repo.pushkey(namespace, key, old, new)
 
     def listkeys(self, namespace):
         return self._repo.listkeys(namespace)
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
 class locallegacypeer(localpeer):
     '''peer extension which implements legacy methods too; used for tests with
     restricted capabilities'''
 
     def __init__(self, repo):
         localpeer.__init__(self, repo, caps=legacycaps)
 
     def branches(self, nodes):
         return self._repo.branches(nodes)
 
     def between(self, pairs):
         return self._repo.between(pairs)
 
     def changegroup(self, basenodes, source):
         return changegroup.changegroup(self._repo, basenodes, source)
 
     def changegroupsubset(self, bases, heads, source):
         return changegroup.changegroupsubset(self._repo, bases, heads, source)
 
 class localrepository(object):
 
     supportedformats = set(('revlogv1', 'generaldelta', 'treemanifest',
                             'manifestv2'))
     _basesupported = supportedformats | set(('store', 'fncache', 'shared',
                                              'dotencode'))
     openerreqs = set(('revlogv1', 'generaldelta', 'treemanifest', 'manifestv2'))
     filtername = None
 
     # a list of (ui, featureset) functions.
     # only functions defined in module of enabled extensions are invoked
     featuresetupfuncs = set()
 
     def __init__(self, baseui, path, create=False):
         self.requirements = set()
         self.wvfs = scmutil.vfs(path, expandpath=True, realpath=True)
         self.wopener = self.wvfs
         self.root = self.wvfs.base
         self.path = self.wvfs.join(".hg")
         self.origroot = path
         self.auditor = pathutil.pathauditor(self.root, self._checknested)
         self.nofsauditor = pathutil.pathauditor(self.root, self._checknested,
                                                 realfs=False)
         self.vfs = scmutil.vfs(self.path)
         self.opener = self.vfs
         self.baseui = baseui
         self.ui = baseui.copy()
         self.ui.copy = baseui.copy # prevent copying repo configuration
         # A list of callback to shape the phase if no data were found.
         # Callback are in the form: func(repo, roots) --> processed root.
         # This list it to be filled by extension during repo setup
         self._phasedefaults = []
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         if self.featuresetupfuncs:
             self.supported = set(self._basesupported) # use private copy
             extmods = set(m.__name__ for n, m
                           in extensions.extensions(self.ui))
             for setupfunc in self.featuresetupfuncs:
                 if setupfunc.__module__ in extmods:
                     setupfunc(self.ui, self.supported)
         else:
             self.supported = self._basesupported
 
         if not self.vfs.isdir():
             if create:
                 self.requirements = newreporequirements(self)
 
                 if not self.wvfs.exists():
                     self.wvfs.makedirs()
                 self.vfs.makedir(notindexed=True)
 
                 if 'store' in self.requirements:
                     self.vfs.mkdir("store")
 
                     # create an invalid changelog
                     self.vfs.append(
                         "00changelog.i",
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             try:
                 self.requirements = scmutil.readrequires(
                         self.vfs, self.supported)
             except IOError as inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
         self.sharedpath = self.path
         try:
             vfs = scmutil.vfs(self.vfs.read("sharedpath").rstrip('\n'),
                               realpath=True)
             s = vfs.base
             if not vfs.exists():
                 raise error.RepoError(
                     _('.hg/sharedpath points to nonexistent directory %s') % s)
             self.sharedpath = s
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.store = store.store(
                 self.requirements, self.sharedpath, scmutil.vfs)
         self.spath = self.store.path
         self.svfs = self.store.vfs
         self.sjoin = self.store.join
         self.vfs.createmode = self.store.createmode
         self._applyopenerreqs()
         if create:
             self._writerequirements()
 
         self._dirstatevalidatewarned = False
 
         self._branchcaches = {}
         self._revbranchcache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
         # A cache for various files under .hg/ that tracks file changes,
         # (used by the filecache decorator)
         #
         # Maps a property name to its util.filecacheentry
         self._filecache = {}
 
         # hold sets of revision to be filtered
         # should be cleared when something might have changed the filter value:
         # - new changesets,
         # - phase change,
         # - new obsolescence marker,
         # - working directory parent change,
         # - bookmark changes
         self.filteredrevcache = {}
 
         # generic mapping between names and nodes
         self.names = namespaces.namespaces()
 
     def close(self):
         self._writecaches()
 
     def _writecaches(self):
         if self._revbranchcache:
             self._revbranchcache.write()
 
     def _restrictcapabilities(self, caps):
         if self.ui.configbool('experimental', 'bundle2-advertise', True):
             caps = set(caps)
             capsblob = bundle2.encodecaps(bundle2.getrepocaps(self))
             caps.add('bundle2=' + urlreq.quote(capsblob))
         return caps
 
     def _applyopenerreqs(self):
         self.svfs.options = dict((r, 1) for r in self.requirements
                                            if r in self.openerreqs)
         # experimental config: format.chunkcachesize
         chunkcachesize = self.ui.configint('format', 'chunkcachesize')
         if chunkcachesize is not None:
             self.svfs.options['chunkcachesize'] = chunkcachesize
         # experimental config: format.maxchainlen
         maxchainlen = self.ui.configint('format', 'maxchainlen')
         if maxchainlen is not None:
             self.svfs.options['maxchainlen'] = maxchainlen
         # experimental config: format.manifestcachesize
         manifestcachesize = self.ui.configint('format', 'manifestcachesize')
         if manifestcachesize is not None:
             self.svfs.options['manifestcachesize'] = manifestcachesize
         # experimental config: format.aggressivemergedeltas
         aggressivemergedeltas = self.ui.configbool('format',
             'aggressivemergedeltas', False)
         self.svfs.options['aggressivemergedeltas'] = aggressivemergedeltas
         self.svfs.options['lazydeltabase'] = not scmutil.gddeltaconfig(self.ui)
 
     def _writerequirements(self):
         scmutil.writerequires(self.vfs, self.requirements)
 
     def _checknested(self, path):
         """Determine if path is a legal nested repository."""
         if not path.startswith(self.root):
             return False
         subpath = path[len(self.root) + 1:]
         normsubpath = util.pconvert(subpath)
 
         # XXX: Checking against the current working copy is wrong in
         # the sense that it can reject things like
         #
         #   $ hg cat -r 10 sub/x.txt
         #
         # if sub/ is no longer a subrepository in the working copy
         # parent revision.
         #
         # However, it can of course also allow things that would have
         # been rejected before, such as the above cat command if sub/
         # is a subrepository now, but was a normal directory before.
         # The old path auditor would have rejected by mistake since it
         # panics when it sees sub/.hg/.
         #
         # All in all, checking against the working copy seems sensible
         # since we want to prevent access to nested repositories on
         # the filesystem *now*.
         ctx = self[None]
         parts = util.splitpath(subpath)
         while parts:
             prefix = '/'.join(parts)
             if prefix in ctx.substate:
                 if prefix == normsubpath:
                     return True
                 else:
                     sub = ctx.sub(prefix)
                     return sub.checknested(subpath[len(prefix) + 1:])
             else:
                 parts.pop()
         return False
 
     def peer(self):
         return localpeer(self) # not cached to avoid reference cycle
 
     def unfiltered(self):
         """Return unfiltered version of the repository
 
         Intended to be overwritten by filtered repo."""
         return self
 
     def filtered(self, name):
         """Return a filtered version of a repository"""
         # build a new class with the mixin and the current class
         # (possibly subclass of the repo)
         class proxycls(repoview.repoview, self.unfiltered().__class__):
             pass
         return proxycls(self, name)
 
     @repofilecache('bookmarks', 'bookmarks.current')
     def _bookmarks(self):
         return bookmarks.bmstore(self)
 
     @property
     def _activebookmark(self):
         return self._bookmarks.active
 
     def bookmarkheads(self, bookmark):
         name = bookmark.split('@', 1)[0]
         heads = []
         for mark, n in self._bookmarks.iteritems():
             if mark.split('@', 1)[0] == name:
                 heads.append(n)
         return heads
 
     # _phaserevs and _phasesets depend on changelog. what we need is to
     # call _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache('phaseroots', '00changelog.i')
     def _phasecache(self):
         return phases.phasecache(self, self._phasedefaults)
 
     @storecache('obsstore')
     def obsstore(self):
         # read default format for new obsstore.
         # developer config: format.obsstore-version
         defaultformat = self.ui.configint('format', 'obsstore-version', None)
         # rely on obsstore class default when possible.
         kwargs = {}
         if defaultformat is not None:
             kwargs['defaultformat'] = defaultformat
         readonly = not obsolete.isenabled(self, obsolete.createmarkersopt)
         store = obsolete.obsstore(self.svfs, readonly=readonly,
                                   **kwargs)
         if store and readonly:
             self.ui.warn(
                 _('obsolete feature not enabled but %i markers found!\n')
                 % len(list(store)))
         return store
 
     @storecache('00changelog.i')
     def changelog(self):
         c = changelog.changelog(self.svfs)
-        if 'HG_PENDING' in os.environ:
-            p = os.environ['HG_PENDING']
+        if 'HG_PENDING' in encoding.environ:
+            p = encoding.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         return c
 
     def _constructmanifest(self):
         # This is a temporary function while we migrate from manifest to
         # manifestlog. It allows bundlerepo and unionrepo to intercept the
         # manifest creation.
         return manifest.manifestrevlog(self.svfs)
 
     @storecache('00manifest.i')
     def manifestlog(self):
         return manifest.manifestlog(self.svfs, self)
 
     @repofilecache('dirstate')
     def dirstate(self):
         return dirstate.dirstate(self.vfs, self.ui, self.root,
                                  self._dirstatevalidate)
 
     def _dirstatevalidate(self, node):
         try:
             self.changelog.rev(node)
             return node
         except error.LookupError:
             if not self._dirstatevalidatewarned:
                 self._dirstatevalidatewarned = True
                 self.ui.warn(_("warning: ignoring unknown"
                                " working parent %s!\n") % short(node))
             return nullid
 
     def __getitem__(self, changeid):
         if changeid is None or changeid == wdirrev:
             return context.workingctx(self)
         if isinstance(changeid, slice):
             return [context.changectx(self, i)
                     for i in xrange(*changeid.indices(len(self)))
                     if i not in self.changelog.filteredrevs]
         return context.changectx(self, changeid)
 
     def __contains__(self, changeid):
         try:
             self[changeid]
             return True
         except error.RepoLookupError:
             return False
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         return iter(self.changelog)
 
     def revs(self, expr, *args):
         '''Find revisions matching a revset.
 
         The revset is specified as a string ``expr`` that may contain
         %-formatting to escape certain types. See ``revset.formatspec``.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
 
         Returns a revset.abstractsmartset, which is a list-like interface
         that contains integer revisions.
         '''
         expr = revset.formatspec(expr, *args)
         m = revset.match(None, expr)
         return m(self)
 
     def set(self, expr, *args):
         '''Find revisions matching a revset and emit changectx instances.
 
         This is a convenience wrapper around ``revs()`` that iterates the
         result and is a generator of changectx instances.
 
         Revset aliases from the configuration are not expanded. To expand
         user aliases, consider calling ``scmutil.revrange()``.
         '''
         for r in self.revs(expr, *args):
             yield self[r]
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         """Call a hook, passing this repo instance.
 
         This a convenience method to aid invoking hooks. Extensions likely
         won't call this unless they have registered a custom hook or are
         replacing code that is expected to call a hook.
         """
         return hook.hook(self.ui, self, name, throw, **args)
 
     @unfilteredmethod
     def _tag(self, names, node, message, local, user, date, extra=None,
              editor=False):
         if isinstance(names, str):
             names = (names,)
 
         branches = self.branchmap()
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
             if name in branches:
                 self.ui.warn(_("warning: tag %s conflicts with existing"
                 " branch name\n") % name)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 if munge:
                     m = munge(name)
                 else:
                     m = name
 
                 if (self._tagscache.tagtypes and
                     name in self._tagscache.tagtypes):
                     old = self.tags().get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.vfs('localtags', 'r+')
             except IOError:
                 fp = self.vfs('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError as e:
             if e.errno != errno.ENOENT:
                 raise
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         fp.close()
 
         self.invalidatecaches()
 
         if '.hgtags' not in self.dirstate:
             self[None].add(['.hgtags'])
 
         m = matchmod.exact(self.root, '', ['.hgtags'])
         tagnode = self.commit(message, user, date, extra=extra, match=m,
                               editor=editor)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date, editor=False):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         if not local:
             m = matchmod.exact(self.root, '', ['.hgtags'])
             if any(self.status(match=m, unknown=True, ignored=True)):
                 raise error.Abort(_('working copy of .hgtags is changed'),
                                  hint=_('please commit .hgtags manually'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date, editor=editor)
 
     @filteredpropertycache
     def _tagscache(self):
         '''Returns a tagscache object that contains various tags related
         caches.'''
 
         # This simplifies its cache management by having one decorated
         # function (this one) and the rest simply fetch things from it.
         class tagscache(object):
             def __init__(self):
                 # These two define the set of tags for this repository. tags
                 # maps tag name to node; tagtypes maps tag name to 'global' or
                 # 'local'. (Global tags are defined by .hgtags across all
                 # heads, and local tags are defined in .hg/localtags.)
                 # They constitute the in-memory cache of tags.
                 self.tags = self.tagtypes = None
 
                 self.nodetagscache = self.tagslist = None
 
         cache = tagscache()
         cache.tags, cache.tagtypes = self._findtags()
 
         return cache
 
     def tags(self):
         '''return a mapping of tag to node'''
         t = {}
         if self.changelog.filteredrevs:
             tags, tt = self._findtags()
         else:
             tags = self._tagscache.tags
         for k, v in tags.iteritems():
             try:
                 # ignore tags to unknown nodes
                 self.changelog.rev(v)
                 t[k] = v
             except (error.LookupError, ValueError):
                 pass
         return t
 
     def _findtags(self):
         '''Do the hard work of finding tags.  Return a pair of dicts
         (tags, tagtypes) where tags maps tag name to node, and tagtypes
         maps tag name to a string like \'global\' or \'local\'.
         Subclasses or extensions are free to add their own tags, but
         should be aware that the returned dicts will be retained for the
         duration of the localrepo object.'''
 
         # XXX what tagtype should subclasses/extensions use?  Currently
         # mq and bookmarks add tags, but do not set the tagtype at all.
         # Should each extension invent its own tag type?  Should there
         # be one tagtype for all such "virtual" tags?  Or is the status
         # quo fine?
 
         alltags = {}                    # map tag name to (node, hist)
         tagtypes = {}
 
         tagsmod.findglobaltags(self.ui, self, alltags, tagtypes)
         tagsmod.readlocaltags(self.ui, self, alltags, tagtypes)
 
         # Build the return dicts.  Have to re-encode tag names because
         # the tags module always uses UTF-8 (in order not to lose info
         # writing to the cache), but the rest of Mercurial wants them in
         # local encoding.
         tags = {}
         for (name, (node, hist)) in alltags.iteritems():
             if node != nullid:
                 tags[encoding.tolocal(name)] = node
         tags['tip'] = self.changelog.tip()
         tagtypes = dict([(encoding.tolocal(name), value)
                          for (name, value) in tagtypes.iteritems()])
         return (tags, tagtypes)
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         return self._tagscache.tagtypes.get(tagname)
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         if not self._tagscache.tagslist:
             l = []
             for t, n in self.tags().iteritems():
                 l.append((self.changelog.rev(n), t, n))
             self._tagscache.tagslist = [(t, n) for r, t, n in sorted(l)]
 
         return self._tagscache.tagslist
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self._tagscache.nodetagscache:
             nodetagscache = {}
             for t, n in self._tagscache.tags.iteritems():
                 nodetagscache.setdefault(n, []).append(t)
             for tags in nodetagscache.itervalues():
                 tags.sort()
             self._tagscache.nodetagscache = nodetagscache
         return self._tagscache.nodetagscache.get(node, [])
 
     def nodebookmarks(self, node):
         """return the list of bookmarks pointing to the specified node"""
         marks = []
         for bookmark, n in self._bookmarks.iteritems():
             if n == node:
                 marks.append(bookmark)
         return sorted(marks)
 
     def branchmap(self):
         '''returns a dictionary {branch: [branchheads]} with branchheads
         ordered by increasing revision number'''
         branchmap.updatecache(self)
         return self._branchcaches[self.filtername]
 
     @unfilteredmethod
     def revbranchcache(self):
         if not self._revbranchcache:
             self._revbranchcache = branchmap.revbranchcache(self.unfiltered())
         return self._revbranchcache
 
     def branchtip(self, branch, ignoremissing=False):
         '''return the tip node for a given branch
 
         If ignoremissing is True, then this method will not raise an error.
         This is helpful for callers that only expect None for a missing branch
         (e.g. namespace).
 
         '''
         try:
             return self.branchmap().branchtip(branch)
         except KeyError:
             if not ignoremissing:
                 raise error.RepoLookupError(_("unknown branch '%s'") % branch)
             else:
                 pass
 
     def lookup(self, key):
         return self[key].node()
 
     def lookupbranch(self, key, remote=None):
         repo = remote or self
         if key in repo.branchmap():
             return key
 
         repo = (remote and remote.local()) and remote or self
         return repo[key].branch()
 
     def known(self, nodes):
         cl = self.changelog
         nm = cl.nodemap
         filtered = cl.filteredrevs
         result = []
         for n in nodes:
             r = nm.get(n)
             resp = not (r is None or r in filtered)
             result.append(resp)
         return result
 
     def local(self):
         return self
 
     def publishing(self):
         # it's safe (and desirable) to trust the publish flag unconditionally
         # so that we don't finalize changes shared between users via ssh or nfs
         return self.ui.configbool('phases', 'publish', True, untrusted=True)
 
     def cancopy(self):
         # so statichttprepo's override of local() works
         if not self.local():
             return False
         if not self.publishing():
             return True
         # if publishing we can't copy if there is filtered content
         return not self.filtered('visible').changelog.filteredrevs
 
     def shared(self):
         '''the type of shared repository (None if not shared)'''
         if self.sharedpath != self.path:
             return 'store'
         return None
 
     def join(self, f, *insidef):
         return self.vfs.join(os.path.join(f, *insidef))
 
     def wjoin(self, f, *insidef):
         return self.vfs.reljoin(self.root, f, *insidef)
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.svfs, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def setparents(self, p1, p2=nullid):
         self.dirstate.beginparentchange()
         copies = self.dirstate.setparents(p1, p2)
         pctx = self[p1]
         if copies:
             # Adjust copy records, the dirstate cannot do it, it
             # requires access to parents manifests. Preserve them
             # only for entries added to first parent.
             for f in copies:
                 if f not in pctx and copies[f] in pctx:
                     self.dirstate.copy(copies[f], f)
         if p2 == nullid:
             for f, s in sorted(self.dirstate.copies().items()):
                 if f not in pctx and s not in pctx:
                     self.dirstate.copy(None, f)
         self.dirstate.endparentchange()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wvfs(f, mode)
 
     def _link(self, f):
         return self.wvfs.islink(f)
 
     def _loadfilter(self, filter):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = matchmod.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
         return self.filterpats[filter]
 
     def _filter(self, filterpats, filename, data):
         for mf, fn, cmd in filterpats:
             if mf(filename):
                 self.ui.debug("filtering %s through %s\n" % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     @unfilteredpropertycache
     def _encodefilterpats(self):
         return self._loadfilter('encode')
 
     @unfilteredpropertycache
     def _decodefilterpats(self):
         return self._loadfilter('decode')
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = self.wvfs.readlink(filename)
         else:
             data = self.wvfs.read(filename)
         return self._filter(self._encodefilterpats, filename, data)
 
     def wwrite(self, filename, data, flags, backgroundclose=False):
         """write ``data`` into ``filename`` in the working directory
 
         This returns length of written (maybe decoded) data.
         """
         data = self._filter(self._decodefilterpats, filename, data)
         if 'l' in flags:
             self.wvfs.symlink(data, filename)
         else:
             self.wvfs.write(filename, data, backgroundclose=backgroundclose)
             if 'x' in flags:
                 self.wvfs.setflags(filename, False, True)
         return len(data)
 
     def wwritedata(self, filename, data):
         return self._filter(self._decodefilterpats, filename, data)
 
     def currenttransaction(self):
         """return the current transaction or None if non exists"""
         if self._transref:
             tr = self._transref()
         else:
             tr = None
 
         if tr and tr.running():
             return tr
         return None
 
     def transaction(self, desc, report=None):
         if (self.ui.configbool('devel', 'all-warnings')
                 or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is None:
                 raise error.ProgrammingError('transaction requires locking')
         tr = self.currenttransaction()
         if tr is not None:
             return tr.nest()
 
         # abort here if the journal already exists
         if self.svfs.exists("journal"):
             raise error.RepoError(
                 _("abandoned transaction found"),
                 hint=_("run 'hg recover' to clean up transaction"))
 
         idbase = "%.40f#%f" % (random.random(), time.time())
         txnid = 'TXN:' + hashlib.sha1(idbase).hexdigest()
         self.hook('pretxnopen', throw=True, txnname=desc, txnid=txnid)
 
         self._writejournal(desc)
         renames = [(vfs, x, undoname(x)) for vfs, x in self._journalfiles()]
         if report:
             rp = report
         else:
             rp = self.ui.warn
         vfsmap = {'plain': self.vfs} # root of .hg/
         # we must avoid cyclic reference between repo and transaction.
         reporef = weakref.ref(self)
         def validate(tr):
             """will run pre-closing hooks"""
             reporef().hook('pretxnclose', throw=True,
                            txnname=desc, **tr.hookargs)
         def releasefn(tr, success):
             repo = reporef()
             if success:
                 # this should be explicitly invoked here, because
                 # in-memory changes aren't written out at closing
                 # transaction, if tr.addfilegenerator (via
                 # dirstate.write or so) isn't invoked while
                 # transaction running
                 repo.dirstate.write(None)
             else:
                 # discard all changes (including ones already written
                 # out) in this transaction
                 repo.dirstate.restorebackup(None, prefix='journal.')
 
                 repo.invalidate(clearfilecache=True)
 
         tr = transaction.transaction(rp, self.svfs, vfsmap,
                                      "journal",
                                      "undo",
                                      aftertrans(renames),
                                      self.store.createmode,
                                      validator=validate,
                                      releasefn=releasefn)
 
         tr.hookargs['txnid'] = txnid
         # note: writing the fncache only during finalize mean that the file is
         # outdated when running hooks. As fncache is used for streaming clone,
         # this is not expected to break anything that happen during the hooks.
         tr.addfinalize('flush-fncache', self.store.write)
         def txnclosehook(tr2):
             """To be run if transaction is successful, will schedule a hook run
             """
             # Don't reference tr2 in hook() so we don't hold a reference.
             # This reduces memory consumption when there are multiple
             # transactions per lock. This can likely go away if issue5045
             # fixes the function accumulation.
             hookargs = tr2.hookargs
 
             def hook():
                 reporef().hook('txnclose', throw=False, txnname=desc,
                                **hookargs)
             reporef()._afterlock(hook)
         tr.addfinalize('txnclose-hook', txnclosehook)
         def txnaborthook(tr2):
             """To be run if transaction is aborted
             """
             reporef().hook('txnabort', throw=False, txnname=desc,
                            **tr2.hookargs)
         tr.addabort('txnabort-hook', txnaborthook)
         # avoid eager cache invalidation. in-memory data should be identical
         # to stored data if transaction has no error.
         tr.addpostclose('refresh-filecachestats', self._refreshfilecachestats)
         self._transref = weakref.ref(tr)
         return tr
 
     def _journalfiles(self):
         return ((self.svfs, 'journal'),
                 (self.vfs, 'journal.dirstate'),
                 (self.vfs, 'journal.branch'),
                 (self.vfs, 'journal.desc'),
                 (self.vfs, 'journal.bookmarks'),
                 (self.svfs, 'journal.phaseroots'))
 
     def undofiles(self):
         return [(vfs, undoname(x)) for vfs, x in self._journalfiles()]
 
     def _writejournal(self, desc):
         self.dirstate.savebackup(None, prefix='journal.')
         self.vfs.write("journal.branch",
                           encoding.fromlocal(self.dirstate.branch()))
         self.vfs.write("journal.desc",
                           "%d\n%s\n" % (len(self), desc))
         self.vfs.write("journal.bookmarks",
                           self.vfs.tryread("bookmarks"))
         self.svfs.write("journal.phaseroots",
                            self.svfs.tryread("phaseroots"))
 
     def recover(self):
         with self.lock():
             if self.svfs.exists("journal"):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 vfsmap = {'': self.svfs,
                           'plain': self.vfs,}
                 transaction.rollback(self.svfs, vfsmap, "journal",
                                      self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
 
     def rollback(self, dryrun=False, force=False):
         wlock = lock = dsguard = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if self.svfs.exists("undo"):
                 dsguard = dirstateguard.dirstateguard(self, 'rollback')
 
                 return self._rollback(dryrun, force, dsguard)
             else:
                 self.ui.warn(_("no rollback information available\n"))
                 return 1
         finally:
             release(dsguard, lock, wlock)
 
     @unfilteredmethod # Until we get smarter cache management
     def _rollback(self, dryrun, force, dsguard):
         ui = self.ui
         try:
             args = self.vfs.read('undo.desc').splitlines()
             (oldlen, desc, detail) = (int(args[0]), args[1], None)
             if len(args) >= 3:
                 detail = args[2]
             oldtip = oldlen - 1
 
             if detail and ui.verbose:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s: %s)\n')
                        % (oldtip, desc, detail))
             else:
                 msg = (_('repository tip rolled back to revision %s'
                          ' (undo %s)\n')
                        % (oldtip, desc))
         except IOError:
             msg = _('rolling back unknown transaction\n')
             desc = None
 
         if not force and self['.'] != self['tip'] and desc == 'commit':
             raise error.Abort(
                 _('rollback of last commit while not checked out '
                   'may lose data'), hint=_('use -f to force'))
 
         ui.status(msg)
         if dryrun:
             return 0
 
         parents = self.dirstate.parents()
         self.destroying()
         vfsmap = {'plain': self.vfs, '': self.svfs}
         transaction.rollback(self.svfs, vfsmap, 'undo', ui.warn)
         if self.vfs.exists('undo.bookmarks'):
             self.vfs.rename('undo.bookmarks', 'bookmarks', checkambig=True)
         if self.svfs.exists('undo.phaseroots'):
             self.svfs.rename('undo.phaseroots', 'phaseroots', checkambig=True)
         self.invalidate()
 
         parentgone = (parents[0] not in self.changelog.nodemap or
                       parents[1] not in self.changelog.nodemap)
         if parentgone:
             # prevent dirstateguard from overwriting already restored one
             dsguard.close()
 
             self.dirstate.restorebackup(None, prefix='undo.')
             try:
                 branch = self.vfs.read('undo.branch')
                 self.dirstate.setbranch(encoding.tolocal(branch))
             except IOError:
                 ui.warn(_('named branch could not be reset: '
                           'current branch is still \'%s\'\n')
                         % self.dirstate.branch())
 
             parents = tuple([p.rev() for p in self[None].parents()])
             if len(parents) > 1:
                 ui.status(_('working directory now based on '
                             'revisions %d and %d\n') % parents)
             else:
                 ui.status(_('working directory now based on '
                             'revision %d\n') % parents)
             mergemod.mergestate.clean(self, self['.'].node())
 
         # TODO: if we know which new heads may result from this rollback, pass
         # them to destroy(), which will prevent the branchhead cache from being
         # invalidated.
         self.destroyed()
         return 0
 
     def invalidatecaches(self):
 
         if '_tagscache' in vars(self):
             # can't use delattr on proxy
             del self.__dict__['_tagscache']
 
         self.unfiltered()._branchcaches.clear()
         self.invalidatevolatilesets()
 
     def invalidatevolatilesets(self):
         self.filteredrevcache.clear()
         obsolete.clearobscaches(self)
 
     def invalidatedirstate(self):
         '''Invalidates the dirstate, causing the next call to dirstate
         to check if it was modified since the last time it was read,
         rereading it if it has.
 
         This is different to dirstate.invalidate() that it doesn't always
         rereads the dirstate. Use dirstate.invalidate() if you want to
         explicitly read the dirstate again (i.e. restoring it to a previous
         known good state).'''
         if hasunfilteredcache(self, 'dirstate'):
             for k in self.dirstate._filecache:
                 try:
                     delattr(self.dirstate, k)
                 except AttributeError:
                     pass
             delattr(self.unfiltered(), 'dirstate')
 
     def invalidate(self, clearfilecache=False):
         '''Invalidates both store and non-store parts other than dirstate
 
         If a transaction is running, invalidation of store is omitted,
         because discarding in-memory changes might cause inconsistency
         (e.g. incomplete fncache causes unintentional failure, but
         redundant one doesn't).
         '''
         unfiltered = self.unfiltered() # all file caches are stored unfiltered
         for k in self._filecache.keys():
             # dirstate is invalidated separately in invalidatedirstate()
             if k == 'dirstate':
                 continue
 
             if clearfilecache:
                 del self._filecache[k]
             try:
                 delattr(unfiltered, k)
             except AttributeError:
                 pass
         self.invalidatecaches()
         if not self.currenttransaction():
             # TODO: Changing contents of store outside transaction
             # causes inconsistency. We should make in-memory store
             # changes detectable, and abort if changed.
             self.store.invalidatecaches()
 
     def invalidateall(self):
         '''Fully invalidates both store and non-store parts, causing the
         subsequent operation to reread any outside changes.'''
         # extension should hook this to invalidate its caches
         self.invalidate()
         self.invalidatedirstate()
 
     @unfilteredmethod
     def _refreshfilecachestats(self, tr):
         """Reload stats of cached files so that they are flagged as valid"""
         for k, ce in self._filecache.items():
             if k == 'dirstate' or k not in self.__dict__:
                 continue
             ce.refresh()
 
     def _lock(self, vfs, lockname, wait, releasefn, acquirefn, desc,
               inheritchecker=None, parentenvvar=None):
         parentlock = None
         # the contents of parentenvvar are used by the underlying lock to
         # determine whether it can be inherited
         if parentenvvar is not None:
-            parentlock = os.environ.get(parentenvvar)
+            parentlock = encoding.environ.get(parentenvvar)
         try:
             l = lockmod.lock(vfs, lockname, 0, releasefn=releasefn,
                              acquirefn=acquirefn, desc=desc,
                              inheritchecker=inheritchecker,
                              parentlock=parentlock)
         except error.LockHeld as inst:
             if not wait:
                 raise
             # show more details for new-style locks
             if ':' in inst.locker:
                 host, pid = inst.locker.split(":", 1)
                 self.ui.warn(
                     _("waiting for lock on %s held by process %r "
                       "on host %r\n") % (desc, pid, host))
             else:
                 self.ui.warn(_("waiting for lock on %s held by %r\n") %
                              (desc, inst.locker))
             # default to 600 seconds timeout
             l = lockmod.lock(vfs, lockname,
                              int(self.ui.config("ui", "timeout", "600")),
                              releasefn=releasefn, acquirefn=acquirefn,
                              desc=desc)
             self.ui.warn(_("got lock after %s seconds\n") % l.delay)
         return l
 
     def _afterlock(self, callback):
         """add a callback to be run when the repository is fully unlocked
 
         The callback will be executed when the outermost lock is released
         (with wlock being higher level than 'lock')."""
         for ref in (self._wlockref, self._lockref):
             l = ref and ref()
             if l and l.held:
                 l.postrelease.append(callback)
                 break
         else: # no lock have been found.
             callback()
 
     def lock(self, wait=True):
         '''Lock the repository store (.hg/store) and return a weak reference
         to the lock. Use this before modifying the store (e.g. committing or
         stripping). If you are opening a transaction, get a lock as well.)
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._currentlock(self._lockref)
         if l is not None:
             l.lock()
             return l
 
         l = self._lock(self.svfs, "lock", wait, None,
                        self.invalidate, _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def _wlockchecktransaction(self):
         if self.currenttransaction() is not None:
             raise error.LockInheritanceContractViolation(
                 'wlock cannot be inherited in the middle of a transaction')
 
     def wlock(self, wait=True):
         '''Lock the non-store parts of the repository (everything under
         .hg except .hg/store) and return a weak reference to the lock.
 
         Use this before modifying files in .hg.
 
         If both 'lock' and 'wlock' must be acquired, ensure you always acquires
         'wlock' first to avoid a dead-lock hazard.'''
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         # We do not need to check for non-waiting lock acquisition.  Such
         # acquisition would not cause dead-lock as they would just fail.
         if wait and (self.ui.configbool('devel', 'all-warnings')
                      or self.ui.configbool('devel', 'check-locks')):
             if self._currentlock(self._lockref) is not None:
                 self.ui.develwarn('"wlock" acquired after "lock"')
 
         def unlock():
             if self.dirstate.pendingparentchange():
                 self.dirstate.invalidate()
             else:
                 self.dirstate.write(None)
 
             self._filecache['dirstate'].refresh()
 
         l = self._lock(self.vfs, "wlock", wait, unlock,
                        self.invalidatedirstate, _('working directory of %s') %
                        self.origroot,
                        inheritchecker=self._wlockchecktransaction,
                        parentenvvar='HG_WLOCK_LOCKER')
         self._wlockref = weakref.ref(l)
         return l
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not."""
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def currentwlock(self):
         """Returns the wlock if it's held, or None if it's not."""
         return self._currentlock(self._wlockref)
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = manifest2.get(fname, nullid)
         if isinstance(fctx, context.filectx):
             node = fctx.filenode()
             if node in [fparent1, fparent2]:
                 self.ui.debug('reusing %s filelog entry\n' % fname)
                 if manifest1.flags(fname) != fctx.flags():
                     changelist.append(fname)
                 return node
 
         flog = self.file(fname)
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # Here, we used to search backwards through history to try to find
             # where the file copy came from if the source of a copy was not in
             # the parent directory. However, this doesn't actually make sense to
             # do (what does a copy from something not in your working copy even
             # mean?) and it causes bugs (eg, issue4476). Instead, we will warn
             # the user that copy information was dropped, so if they didn't
             # expect this outcome it can be fixed, but this is the correct
             # behavior in this circumstance.
 
             if crev:
                 self.ui.debug(" %s: copy %s:%s\n" % (fname, cfname, hex(crev)))
                 meta["copy"] = cfname
                 meta["copyrev"] = hex(crev)
                 fparent1, fparent2 = nullid, newfparent
             else:
                 self.ui.warn(_("warning: can't find ancestor for '%s' "
                                "copied from '%s'!\n") % (fname, cfname))
 
         elif fparent1 == nullid:
             fparent1, fparent2 = fparent2, nullid
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestors = flog.commonancestorsheads(fparent1, fparent2)
             if fparent1 in fparentancestors:
                 fparent1, fparent2 = fparent2, nullid
             elif fparent2 in fparentancestors:
                 fparent2 = nullid
 
         # is the file changed?
         text = fctx.data()
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
         # are just the flags changed during merge?
         elif fname in manifest1 and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def checkcommitpatterns(self, wctx, vdirs, match, status, fail):
         """check for commit arguments that aren't committable"""
         if match.isexact() or match.prefix():
             matched = set(status.modified + status.added + status.removed)
 
             for f in match.files():
                 f = self.dirstate.normalize(f)
                 if f == '.' or f in matched or f in wctx.substate:
                     continue
                 if f in status.deleted:
                     fail(f, _('file not found!'))
                 if f in vdirs: # visited directory
                     d = f + '/'
                     for mf in matched:
                         if mf.startswith(d):
                             break
                     else:
                         fail(f, _("no match under directory!"))
                 elif f not in self.dirstate:
                     fail(f, _("file not tracked!"))
 
     @unfilteredmethod
     def commit(self, text="", user=None, date=None, match=None, force=False,
                editor=False, extra=None):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory,
         match can be used to filter the committed files. If editor is
         supplied, it is called to get a commit message.
         """
         if extra is None:
             extra = {}
 
         def fail(f, msg):
             raise error.Abort('%s: %s' % (f, msg))
 
         if not match:
             match = matchmod.always(self.root, '')
 
         if not force:
             vdirs = []
             match.explicitdir = vdirs.append
             match.bad = fail
 
         wlock = lock = tr = None
         try:
             wlock = self.wlock()
             lock = self.lock() # for recent changelog (see issue4368)
 
             wctx = self[None]
             merge = len(wctx.parents()) > 1
 
             if not force and merge and match.ispartial():
                 raise error.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             status = self.status(match=match, clean=force)
             if force:
                 status.modified.extend(status.clean) # mq may commit clean files
 
             # check subrepos
             subs = []
             commitsubs = set()
             newstate = wctx.substate.copy()
             # only manage subrepos and .hgsubstate if .hgsub is present
             if '.hgsub' in wctx:
                 # we'll decide whether to track this ourselves, thanks
                 for c in status.modified, status.added, status.removed:
                     if '.hgsubstate' in c:
                         c.remove('.hgsubstate')
 
                 # compare current state to last committed state
                 # build new substate based on last committed state
                 oldstate = wctx.p1().substate
                 for s in sorted(newstate.keys()):
                     if not match(s):
                         # ignore working copy, use old state if present
                         if s in oldstate:
                             newstate[s] = oldstate[s]
                             continue
                         if not force:
                             raise error.Abort(
                                 _("commit with new subrepo %s excluded") % s)
                     dirtyreason = wctx.sub(s).dirtyreason(True)
                     if dirtyreason:
                         if not self.ui.configbool('ui', 'commitsubrepos'):
                             raise error.Abort(dirtyreason,
                                 hint=_("use --subrepos for recursive commit"))
                         subs.append(s)
                         commitsubs.add(s)
                     else:
                         bs = wctx.sub(s).basestate()
                         newstate[s] = (newstate[s][0], bs, newstate[s][2])
                         if oldstate.get(s, (None, None, None))[1] != bs:
                             subs.append(s)
 
                 # check for removed subrepos
                 for p in wctx.parents():
                     r = [s for s in p.substate if s not in newstate]
                     subs += [s for s in r if match(s)]
                 if subs:
                     if (not match('.hgsub') and
                         '.hgsub' in (wctx.modified() + wctx.added())):
                         raise error.Abort(
                             _("can't commit subrepos without .hgsub"))
                     status.modified.insert(0, '.hgsubstate')
 
             elif '.hgsub' in status.removed:
                 # clean up .hgsubstate when .hgsub is removed
                 if ('.hgsubstate' in wctx and
                     '.hgsubstate' not in (status.modified + status.added +
                                           status.removed)):
                     status.removed.insert(0, '.hgsubstate')
 
             # make sure all explicit patterns are matched
             if not force:
                 self.checkcommitpatterns(wctx, vdirs, match, status, fail)
 
             cctx = context.workingcommitctx(self, status,
                                             text, user, date, extra)
 
             # internal config: ui.allowemptycommit
             allowemptycommit = (wctx.branch() != wctx.p1().branch()
                                 or extra.get('close') or merge or cctx.files()
                                 or self.ui.configbool('ui', 'allowemptycommit'))
             if not allowemptycommit:
                 return None
 
             if merge and cctx.deleted():
                 raise error.Abort(_("cannot commit merge with missing files"))
 
             ms = mergemod.mergestate.read(self)
             mergeutil.checkunresolved(ms)
 
             if editor:
                 cctx._text = editor(self, cctx, subs)
             edited = (text != cctx._text)
 
             # Save commit message in case this transaction gets rolled back
             # (e.g. by a pretxncommit hook).  Leave the content alone on
             # the assumption that the user will use the same editor again.
             msgfn = self.savecommitmessage(cctx._text)
 
             # commit subs and write new state
             if subs:
                 for s in sorted(commitsubs):
                     sub = wctx.sub(s)
                     self.ui.status(_('committing subrepository %s\n') %
                         subrepo.subrelpath(sub))
                     sr = sub.commit(cctx._text, user, date)
                     newstate[s] = (newstate[s][0], sr)
                 subrepo.writestate(self, newstate)
 
             p1, p2 = self.dirstate.parents()
             hookp1, hookp2 = hex(p1), (p2 != nullid and hex(p2) or '')
             try:
                 self.hook("precommit", throw=True, parent1=hookp1,
                           parent2=hookp2)
                 tr = self.transaction('commit')
                 ret = self.commitctx(cctx, True)
             except: # re-raises
                 if edited:
                     self.ui.write(
                         _('note: commit message saved in %s\n') % msgfn)
                 raise
             # update bookmarks, dirstate and mergestate
             bookmarks.update(self, [p1, p2], ret)
             cctx.markcommitted(ret)
             ms.reset()
             tr.close()
 
         finally:
             lockmod.release(tr, lock, wlock)
 
         def commithook(node=hex(ret), parent1=hookp1, parent2=hookp2):
             # hack for command that use a temporary commit (eg: histedit)
             # temporary commit got stripped before hook release
             if self.changelog.hasnode(ret):
                 self.hook("commit", node=node, parent1=parent1,
                           parent2=parent2)
         self._afterlock(commithook)
         return ret
 
     @unfilteredmethod
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
         Revision information is passed via the context argument.
         """
 
         tr = None
         p1, p2 = ctx.p1(), ctx.p2()
         user = ctx.user()
 
         lock = self.lock()
         try:
             tr = self.transaction("commit")
             trp = weakref.proxy(tr)
 
             if ctx.manifestnode():
                 # reuse an existing manifest revision
                 mn = ctx.manifestnode()
                 files = ctx.files()
             elif ctx.files():
                 m1ctx = p1.manifestctx()
                 m2ctx = p2.manifestctx()
                 mctx = m1ctx.copy()
 
                 m = mctx.read()
                 m1 = m1ctx.read()
                 m2 = m2ctx.read()
 
                 # check in files
                 added = []
                 changed = []
                 removed = list(ctx.removed())
                 linkrev = len(self)
                 self.ui.note(_("committing files:\n"))
                 for f in sorted(ctx.modified() + ctx.added()):
                     self.ui.note(f + "\n")
                     try:
                         fctx = ctx[f]
                         if fctx is None:
                             removed.append(f)
                         else:
                             added.append(f)
                             m[f] = self._filecommit(fctx, m1, m2, linkrev,
                                                     trp, changed)
                             m.setflag(f, fctx.flags())
                     except OSError as inst:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     except IOError as inst:
                         errcode = getattr(inst, 'errno', errno.ENOENT)
                         if error or errcode and errcode != errno.ENOENT:
                             self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
 
                 # update manifest
                 self.ui.note(_("committing manifest\n"))
                 removed = [f for f in sorted(removed) if f in m1 or f in m2]
                 drop = [f for f in removed if f in m]
                 for f in drop:
                     del m[f]
                 mn = mctx.write(trp, linkrev,
                                 p1.manifestnode(), p2.manifestnode(),
                                 added, drop)
                 files = changed + removed
             else:
                 mn = p1.manifestnode()
                 files = []
 
             # update changelog
             self.ui.note(_("committing changelog\n"))
             self.changelog.delayupdate(tr)
             n = self.changelog.add(mn, files, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2)
             # set the new commit is proper phase
             targetphase = subrepo.newcommitphase(self.ui, ctx)
             if targetphase:
                 # retract boundary do not alter parent changeset.
                 # if a parent have higher the resulting phase will
                 # be compliant anyway
                 #
                 # if minimal phase was 0 we don't need to retract anything
                 phases.retractboundary(self, tr, targetphase, [n])
             tr.close()
             branchmap.updatecache(self.filtered('served'))
             return n
         finally:
             if tr:
                 tr.release()
             lock.release()
 
     @unfilteredmethod
     def destroying(self):
         '''Inform the repository that nodes are about to be destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done before destroying history.
 
         This is mostly useful for saving state that is in memory and waiting
         to be flushed when the current lock is released. Because a call to
         destroyed is imminent, the repo will be invalidated causing those
         changes to stay in memory (waiting for the next unlock), or vanish
         completely.
         '''
         # When using the same lock to commit and strip, the phasecache is left
         # dirty after committing. Then when we strip, the repo is invalidated,
         # causing those changes to disappear.
         if '_phasecache' in vars(self):
             self._phasecache.write()
 
     @unfilteredmethod
     def destroyed(self):
         '''Inform the repository that nodes have been destroyed.
         Intended for use by strip and rollback, so there's a common
         place for anything that has to be done after destroying history.
         '''
         # When one tries to:
         # 1) destroy nodes thus calling this method (e.g. strip)
         # 2) use phasecache somewhere (e.g. commit)
         #
         # then 2) will fail because the phasecache contains nodes that were
         # removed. We can either remove phasecache from the filecache,
         # causing it to reload next time it is accessed, or simply filter
         # the removed nodes now and write the updated cache.
         self._phasecache.filterunknown(self)
         self._phasecache.write()
 
         # update the 'served' branch cache to help read only server process
         # Thanks to branchcache collaboration this is done from the nearest
         # filtered subset and it is expected to be fast.
         branchmap.updatecache(self.filtered('served'))
 
         # Ensure the persistent tag cache is updated.  Doing it now
         # means that the tag cache only has to worry about destroyed
         # heads immediately after a strip/rollback.  That in turn
         # guarantees that "cachetip == currenttip" (comparing both rev
         # and node) always means no nodes have been added or destroyed.
 
         # XXX this is suboptimal when qrefresh'ing: we strip the current
         # head, refresh the tag cache, then immediately add a new head.
         # But I think doing it this way is necessary for the "instant
         # tag cache retrieval" case to work.
         self.invalidate()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False,
                listsubrepos=False):
         '''a convenience method that calls node1.status(node2)'''
         return self[node1].status(node2, match, ignored, clean, unknown,
                                   listsubrepos)
 
     def heads(self, start=None):
         heads = self.changelog.heads(start)
         # sort the output in rev descending order
         return sorted(heads, key=self.changelog.rev, reverse=True)
 
     def branchheads(self, branch=None, start=None, closed=False):
         '''return a (possibly filtered) list of heads for the given branch
 
         Heads are returned in topological order, from newest to oldest.
         If branch is None, use the dirstate branch.
         If start is not None, return only heads reachable from start.
         If closed is True, return heads that are marked as closed as well.
         '''
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         # the cache returns heads ordered lowest to highest
         bheads = list(reversed(branches.branchheads(branch, closed=closed)))
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             fbheads = set(self.changelog.nodesbetween([start], bheads)[2])
             bheads = [h for h in bheads if h in fbheads]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while True:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def checkpush(self, pushop):
         """Extensions can override this function if additional checks have
         to be performed before pushing, or call it if they override push
         command.
         """
         pass
 
     @unfilteredpropertycache
     def prepushoutgoinghooks(self):
         """Return util.hooks consists of a pushop with repo, remote, outgoing
         methods, which are called before pushing changesets.
         """
         return util.hooks()
 
     def pushkey(self, namespace, key, old, new):
         try:
             tr = self.currenttransaction()
             hookargs = {}
             if tr is not None:
                 hookargs.update(tr.hookargs)
             hookargs['namespace'] = namespace
             hookargs['key'] = key
             hookargs['old'] = old
             hookargs['new'] = new
             self.hook('prepushkey', throw=True, **hookargs)
         except error.HookAbort as exc:
             self.ui.write_err(_("pushkey-abort: %s\n") % exc)
             if exc.hint:
                 self.ui.write_err(_("(%s)\n") % exc.hint)
             return False
         self.ui.debug('pushing key for "%s:%s"\n' % (namespace, key))
         ret = pushkey.push(self, namespace, key, old, new)
         def runhook():
             self.hook('pushkey', namespace=namespace, key=key, old=old, new=new,
                       ret=ret)
         self._afterlock(runhook)
         return ret
 
     def listkeys(self, namespace):
         self.hook('prelistkeys', throw=True, namespace=namespace)
         self.ui.debug('listing keys for "%s"\n' % namespace)
         values = pushkey.list(self, namespace)
         self.hook('listkeys', namespace=namespace, values=values)
         return values
 
     def debugwireargs(self, one, two, three=None, four=None, five=None):
         '''used to test argument passing over the wire'''
         return "%s %s %s %s %s" % (one, two, three, four, five)
 
     def savecommitmessage(self, text):
         fp = self.vfs('last-message.txt', 'wb')
         try:
             fp.write(text)
         finally:
             fp.close()
         return self.pathto(fp.name[len(self.root) + 1:])
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for vfs, src, dest in renamefiles:
             try:
                 vfs.rename(src, dest)
             except OSError: # journal file does not yet exist
                 pass
     return a
 
 def undoname(fn):
     base, name = os.path.split(fn)
     assert name.startswith('journal')
     return os.path.join(base, name.replace('journal', 'undo', 1))
 
 def instance(ui, path, create):
     return localrepository(ui, util.urllocalpath(path), create)
 
 def islocal(path):
     return True
 
 def newreporequirements(repo):
     """Determine the set of requirements for a new local repository.
 
     Extensions can wrap this function to specify custom requirements for
     new repositories.
     """
     ui = repo.ui
     requirements = set(['revlogv1'])
     if ui.configbool('format', 'usestore', True):
         requirements.add('store')
         if ui.configbool('format', 'usefncache', True):
             requirements.add('fncache')
             if ui.configbool('format', 'dotencode', True):
                 requirements.add('dotencode')
 
     if scmutil.gdinitconfig(ui):
         requirements.add('generaldelta')
     if ui.configbool('experimental', 'treemanifest', False):
         requirements.add('treemanifest')
     if ui.configbool('experimental', 'manifestv2', False):
         requirements.add('manifestv2')
 
     return requirements

mercurial/phases.py

@@ -1,481 +1,481
 """ Mercurial phases support code
 
     ---
 
     Copyright 2011 Pierre-Yves David <[e-mail]>
                    Logilab SA        <[e-mail]>
                    Augie Fackler     <[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.
 
     ---
 
 This module implements most phase logic in mercurial.
 
 
 Basic Concept
 =============
 
 A 'changeset phase' is an indicator that tells us how a changeset is
 manipulated and communicated. The details of each phase is described
 below, here we describe the properties they have in common.
 
 Like bookmarks, phases are not stored in history and thus are not
 permanent and leave no audit trail.
 
 First, no changeset can be in two phases at once. Phases are ordered,
 so they can be considered from lowest to highest. The default, lowest
 phase is 'public' - this is the normal phase of existing changesets. A
 child changeset can not be in a lower phase than its parents.
 
 These phases share a hierarchy of traits:
 
             immutable shared
     public:     X        X
     draft:               X
     secret:
 
 Local commits are draft by default.
 
 Phase Movement and Exchange
 ===========================
 
 Phase data is exchanged by pushkey on pull and push. Some servers have
 a publish option set, we call such a server a "publishing server".
 Pushing a draft changeset to a publishing server changes the phase to
 public.
 
 A small list of fact/rules define the exchange of phase:
 
 * old client never changes server states
 * pull never changes server states
 * publish and old server changesets are seen as public by client
 * any secret changeset seen in another repository is lowered to at
   least draft
 
 Here is the final table summing up the 49 possible use cases of phase
 exchange:
 
                            server
                   old     publish      non-publish
                  N   X    N   D   P    N   D   P
     old client
     pull
      N           -   X/X  -   X/D X/P  -   X/D X/P
      X           -   X/X  -   X/D X/P  -   X/D X/P
     push
      X           X/X X/X  X/P X/P X/P  X/D X/D X/P
     new client
     pull
      N           -   P/X  -   P/D P/P  -   D/D P/P
      D           -   P/X  -   P/D P/P  -   D/D P/P
      P           -   P/X  -   P/D P/P  -   P/D P/P
     push
      D           P/X P/X  P/P P/P P/P  D/D D/D P/P
      P           P/X P/X  P/P P/P P/P  P/P P/P P/P
 
 Legend:
 
     A/B = final state on client / state on server
 
     * N = new/not present,
     * P = public,
     * D = draft,
     * X = not tracked (i.e., the old client or server has no internal
           way of recording the phase.)
 
     passive = only pushes
 
 
     A cell here can be read like this:
 
     "When a new client pushes a draft changeset (D) to a publishing
     server where it's not present (N), it's marked public on both
     sides (P/P)."
 
 Note: old client behave as a publishing server with draft only content
 - other people see it as public
 - content is pushed as draft
 
 """
 
 from __future__ import absolute_import
 
 import errno
-import os
 
 from .i18n import _
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
     short,
 )
 from . import (
+    encoding,
     error,
 )
 
 allphases = public, draft, secret = range(3)
 trackedphases = allphases[1:]
 phasenames = ['public', 'draft', 'secret']
 
 def _readroots(repo, phasedefaults=None):
     """Read phase roots from disk
 
     phasedefaults is a list of fn(repo, roots) callable, which are
     executed if the phase roots file does not exist. When phases are
     being initialized on an existing repository, this could be used to
     set selected changesets phase to something else than public.
 
     Return (roots, dirty) where dirty is true if roots differ from
     what is being stored.
     """
     repo = repo.unfiltered()
     dirty = False
     roots = [set() for i in allphases]
     try:
         f = None
-        if 'HG_PENDING' in os.environ:
+        if 'HG_PENDING' in encoding.environ:
             try:
                 f = repo.svfs('phaseroots.pending')
             except IOError as inst:
                 if inst.errno != errno.ENOENT:
                     raise
         if f is None:
             f = repo.svfs('phaseroots')
         try:
             for line in f:
                 phase, nh = line.split()
                 roots[int(phase)].add(bin(nh))
         finally:
             f.close()
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         if phasedefaults:
             for f in phasedefaults:
                 roots = f(repo, roots)
         dirty = True
     return roots, dirty
 
 class phasecache(object):
     def __init__(self, repo, phasedefaults, _load=True):
         if _load:
             # Cheap trick to allow shallow-copy without copy module
             self.phaseroots, self.dirty = _readroots(repo, phasedefaults)
             self._phaserevs = None
             self._phasesets = None
             self.filterunknown(repo)
             self.opener = repo.svfs
 
     def copy(self):
         # Shallow copy meant to ensure isolation in
         # advance/retractboundary(), nothing more.
         ph = self.__class__(None, None, _load=False)
         ph.phaseroots = self.phaseroots[:]
         ph.dirty = self.dirty
         ph.opener = self.opener
         ph._phaserevs = self._phaserevs
         ph._phasesets = self._phasesets
         return ph
 
     def replace(self, phcache):
         """replace all values in 'self' with content of phcache"""
         for a in ('phaseroots', 'dirty', 'opener', '_phaserevs', '_phasesets'):
             setattr(self, a, getattr(phcache, a))
 
     def _getphaserevsnative(self, repo):
         repo = repo.unfiltered()
         nativeroots = []
         for phase in trackedphases:
             nativeroots.append(map(repo.changelog.rev, self.phaseroots[phase]))
         return repo.changelog.computephases(nativeroots)
 
     def _computephaserevspure(self, repo):
         repo = repo.unfiltered()
         revs = [public] * len(repo.changelog)
         self._phaserevs = revs
         self._populatephaseroots(repo)
         for phase in trackedphases:
             roots = map(repo.changelog.rev, self.phaseroots[phase])
             if roots:
                 for rev in roots:
                     revs[rev] = phase
                 for rev in repo.changelog.descendants(roots):
                     revs[rev] = phase
 
     def loadphaserevs(self, repo):
         """ensure phase information is loaded in the object"""
         if self._phaserevs is None:
             try:
                 if repo.ui.configbool('experimental',
                                       'nativephaseskillswitch'):
                     self._computephaserevspure(repo)
                 else:
                     res = self._getphaserevsnative(repo)
                     self._phaserevs, self._phasesets = res
             except AttributeError:
                 self._computephaserevspure(repo)
 
     def invalidate(self):
         self._phaserevs = None
         self._phasesets = None
 
     def _populatephaseroots(self, repo):
         """Fills the _phaserevs cache with phases for the roots.
         """
         cl = repo.changelog
         phaserevs = self._phaserevs
         for phase in trackedphases:
             roots = map(cl.rev, self.phaseroots[phase])
             for root in roots:
                 phaserevs[root] = phase
 
     def phase(self, repo, rev):
         # We need a repo argument here to be able to build _phaserevs
         # if necessary. The repository instance is not stored in
         # phasecache to avoid reference cycles. The changelog instance
         # is not stored because it is a filecache() property and can
         # be replaced without us being notified.
         if rev == nullrev:
             return public
         if rev < nullrev:
             raise ValueError(_('cannot lookup negative revision'))
         if self._phaserevs is None or rev >= len(self._phaserevs):
             self.invalidate()
             self.loadphaserevs(repo)
         return self._phaserevs[rev]
 
     def write(self):
         if not self.dirty:
             return
         f = self.opener('phaseroots', 'w', atomictemp=True, checkambig=True)
         try:
             self._write(f)
         finally:
             f.close()
 
     def _write(self, fp):
         for phase, roots in enumerate(self.phaseroots):
             for h in roots:
                 fp.write('%i %s\n' % (phase, hex(h)))
         self.dirty = False
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
         tr.addfilegenerator('phase', ('phaseroots',), self._write)
         tr.hookargs['phases_moved'] = '1'
 
     def advanceboundary(self, repo, tr, targetphase, nodes):
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
 
         repo = repo.unfiltered()
         delroots = [] # set of root deleted by this path
         for phase in xrange(targetphase + 1, len(allphases)):
             # filter nodes that are not in a compatible phase already
             nodes = [n for n in nodes
                      if self.phase(repo, repo[n].rev()) >= phase]
             if not nodes:
                 break # no roots to move anymore
             olds = self.phaseroots[phase]
             roots = set(ctx.node() for ctx in repo.set(
                     'roots((%ln::) - (%ln::%ln))', olds, olds, nodes))
             if olds != roots:
                 self._updateroots(phase, roots, tr)
                 # some roots may need to be declared for lower phases
                 delroots.extend(olds - roots)
             # declare deleted root in the target phase
             if targetphase != 0:
                 self.retractboundary(repo, tr, targetphase, delroots)
         repo.invalidatevolatilesets()
 
     def retractboundary(self, repo, tr, targetphase, nodes):
         # Be careful to preserve shallow-copied values: do not update
         # phaseroots values, replace them.
 
         repo = repo.unfiltered()
         currentroots = self.phaseroots[targetphase]
         newroots = [n for n in nodes
                     if self.phase(repo, repo[n].rev()) < targetphase]
         if newroots:
             if nullid in newroots:
                 raise error.Abort(_('cannot change null revision phase'))
             currentroots = currentroots.copy()
             currentroots.update(newroots)
 
             # Only compute new roots for revs above the roots that are being
             # retracted.
             minnewroot = min(repo[n].rev() for n in newroots)
             aboveroots = [n for n in currentroots
                           if repo[n].rev() >= minnewroot]
             updatedroots = repo.set('roots(%ln::)', aboveroots)
 
             finalroots = set(n for n in currentroots if repo[n].rev() <
                              minnewroot)
             finalroots.update(ctx.node() for ctx in updatedroots)
 
             self._updateroots(targetphase, finalroots, tr)
         repo.invalidatevolatilesets()
 
     def filterunknown(self, repo):
         """remove unknown nodes from the phase boundary
 
         Nothing is lost as unknown nodes only hold data for their descendants.
         """
         filtered = False
         nodemap = repo.changelog.nodemap # to filter unknown nodes
         for phase, nodes in enumerate(self.phaseroots):
             missing = sorted(node for node in nodes if node not in nodemap)
             if missing:
                 for mnode in missing:
                     repo.ui.debug(
                         'removing unknown node %s from %i-phase boundary\n'
                         % (short(mnode), phase))
                 nodes.symmetric_difference_update(missing)
                 filtered = True
         if filtered:
             self.dirty = True
         # filterunknown is called by repo.destroyed, we may have no changes in
         # root but phaserevs contents is certainly invalid (or at least we
         # have not proper way to check that). related to issue 3858.
         #
         # The other caller is __init__ that have no _phaserevs initialized
         # anyway. If this change we should consider adding a dedicated
         # "destroyed" function to phasecache or a proper cache key mechanism
         # (see branchmap one)
         self.invalidate()
 
 def advanceboundary(repo, tr, targetphase, nodes):
     """Add nodes to a phase changing other nodes phases if necessary.
 
     This function move boundary *forward* this means that all nodes
     are set in the target phase or kept in a *lower* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.advanceboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def retractboundary(repo, tr, targetphase, nodes):
     """Set nodes back to a phase changing other nodes phases if
     necessary.
 
     This function move boundary *backward* this means that all nodes
     are set in the target phase or kept in a *higher* phase.
 
     Simplify boundary to contains phase roots only."""
     phcache = repo._phasecache.copy()
     phcache.retractboundary(repo, tr, targetphase, nodes)
     repo._phasecache.replace(phcache)
 
 def listphases(repo):
     """List phases root for serialization over pushkey"""
     keys = {}
     value = '%i' % draft
     for root in repo._phasecache.phaseroots[draft]:
         keys[hex(root)] = value
 
     if repo.publishing():
         # Add an extra data to let remote know we are a publishing
         # repo. Publishing repo can't just pretend they are old repo.
         # When pushing to a publishing repo, the client still need to
         # push phase boundary
         #
         # Push do not only push changeset. It also push phase data.
         # New phase data may apply to common changeset which won't be
         # push (as they are common). Here is a very simple example:
         #
         # 1) repo A push changeset X as draft to repo B
         # 2) repo B make changeset X public
         # 3) repo B push to repo A. X is not pushed but the data that
         #    X as now public should
         #
         # The server can't handle it on it's own as it has no idea of
         # client phase data.
         keys['publishing'] = 'True'
     return keys
 
 def pushphase(repo, nhex, oldphasestr, newphasestr):
     """List phases root for serialization over pushkey"""
     repo = repo.unfiltered()
     with repo.lock():
         currentphase = repo[nhex].phase()
         newphase = abs(int(newphasestr)) # let's avoid negative index surprise
         oldphase = abs(int(oldphasestr)) # let's avoid negative index surprise
         if currentphase == oldphase and newphase < oldphase:
             with repo.transaction('pushkey-phase') as tr:
                 advanceboundary(repo, tr, newphase, [bin(nhex)])
             return 1
         elif currentphase == newphase:
             # raced, but got correct result
             return 1
         else:
             return 0
 
 def analyzeremotephases(repo, subset, roots):
     """Compute phases heads and root in a subset of node from root dict
 
     * subset is heads of the subset
     * roots is {<nodeid> => phase} mapping. key and value are string.
 
     Accept unknown element input
     """
     repo = repo.unfiltered()
     # build list from dictionary
     draftroots = []
     nodemap = repo.changelog.nodemap # to filter unknown nodes
     for nhex, phase in roots.iteritems():
         if nhex == 'publishing': # ignore data related to publish option
             continue
         node = bin(nhex)
         phase = int(phase)
         if phase == public:
             if node != nullid:
                 repo.ui.warn(_('ignoring inconsistent public root'
                                ' from remote: %s\n') % nhex)
         elif phase == draft:
             if node in nodemap:
                 draftroots.append(node)
         else:
             repo.ui.warn(_('ignoring unexpected root from remote: %i %s\n')
                          % (phase, nhex))
     # compute heads
     publicheads = newheads(repo, subset, draftroots)
     return publicheads, draftroots
 
 def newheads(repo, heads, roots):
     """compute new head of a subset minus another
 
     * `heads`: define the first subset
     * `roots`: define the second we subtract from the first"""
     repo = repo.unfiltered()
     revset = repo.set('heads((%ln + parents(%ln)) - (%ln::%ln))',
                       heads, roots, roots, heads)
     return [c.node() for c in revset]
 
 
 def newcommitphase(ui):
     """helper to get the target phase of new commit
 
     Handle all possible values for the phases.new-commit options.
 
     """
     v = ui.config('phases', 'new-commit', draft)
     try:
         return phasenames.index(v)
     except ValueError:
         try:
             return int(v)
         except ValueError:
             msg = _("phases.new-commit: not a valid phase name ('%s')")
             raise error.ConfigError(msg % v)
 
 def hassecret(repo):
     """utility function that check if a repo have any secret changeset."""
     return bool(repo._phasecache.phaseroots[2])

mercurial/posix.py

@@ -1,652 +1,652
 # posix.py - Posix utility function implementations for Mercurial
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import fcntl
 import getpass
 import grp
 import os
 import pwd
 import re
 import select
 import stat
 import sys
 import tempfile
 import unicodedata
 
 from .i18n import _
 from . import (
     encoding,
     pycompat,
 )
 
 posixfile = open
 normpath = os.path.normpath
 samestat = os.path.samestat
 try:
     oslink = os.link
 except AttributeError:
     # Some platforms build Python without os.link on systems that are
     # vaguely unix-like but don't have hardlink support. For those
     # poor souls, just say we tried and that it failed so we fall back
     # to copies.
     def oslink(src, dst):
         raise OSError(errno.EINVAL,
                       'hardlinks not supported: %s to %s' % (src, dst))
 unlink = os.unlink
 rename = os.rename
 removedirs = os.removedirs
 expandglobs = False
 
 umask = os.umask(0)
 os.umask(umask)
 
 def split(p):
     '''Same as posixpath.split, but faster
 
     >>> import posixpath
     >>> for f in ['/absolute/path/to/file',
     ...           'relative/path/to/file',
     ...           'file_alone',
     ...           'path/to/directory/',
     ...           '/multiple/path//separators',
     ...           '/file_at_root',
     ...           '///multiple_leading_separators_at_root',
     ...           '']:
     ...     assert split(f) == posixpath.split(f), f
     '''
     ht = p.rsplit('/', 1)
     if len(ht) == 1:
         return '', p
     nh = ht[0].rstrip('/')
     if nh:
         return nh, ht[1]
     return ht[0] + '/', ht[1]
 
 def openhardlinks():
     '''return true if it is safe to hold open file handles to hardlinks'''
     return True
 
 def nlinks(name):
     '''return number of hardlinks for the given file'''
     return os.lstat(name).st_nlink
 
 def parsepatchoutput(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if os.sys.platform == 'OpenVMS':
         if pf[0] == '`':
             pf = pf[1:-1] # Remove the quotes
     else:
         if pf.startswith("'") and pf.endswith("'") and " " in pf:
             pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh'''
     args = user and ("%s@%s" % (user, host)) or host
     return port and ("%s -p %s" % (args, port)) or args
 
 def isexec(f):
     """check whether a file is executable"""
     return (os.lstat(f).st_mode & 0o100 != 0)
 
 def setflags(f, l, x):
     s = os.lstat(f).st_mode
     if l:
         if not stat.S_ISLNK(s):
             # switch file to link
             fp = open(f)
             data = fp.read()
             fp.close()
             os.unlink(f)
             try:
                 os.symlink(data, f)
             except OSError:
                 # failed to make a link, rewrite file
                 fp = open(f, "w")
                 fp.write(data)
                 fp.close()
         # no chmod needed at this point
         return
     if stat.S_ISLNK(s):
         # switch link to file
         data = os.readlink(f)
         os.unlink(f)
         fp = open(f, "w")
         fp.write(data)
         fp.close()
         s = 0o666 & ~umask # avoid restatting for chmod
 
     sx = s & 0o100
     if x and not sx:
         # Turn on +x for every +r bit when making a file executable
         # and obey umask.
         os.chmod(f, s | (s & 0o444) >> 2 & ~umask)
     elif not x and sx:
         # Turn off all +x bits
         os.chmod(f, s & 0o666)
 
 def copymode(src, dst, mode=None):
     '''Copy the file mode from the file at path src to dst.
     If src doesn't exist, we're using mode instead. If mode is None, we're
     using umask.'''
     try:
         st_mode = os.lstat(src).st_mode & 0o777
     except OSError as inst:
         if inst.errno != errno.ENOENT:
             raise
         st_mode = mode
         if st_mode is None:
             st_mode = ~umask
         st_mode &= 0o666
     os.chmod(dst, st_mode)
 
 def checkexec(path):
     """
     Check whether the given path is on a filesystem with UNIX-like exec flags
 
     Requires a directory (like /foo/.hg)
     """
 
     # VFAT on some Linux versions can flip mode but it doesn't persist
     # a FS remount. Frequently we can detect it if files are created
     # with exec bit on.
 
     try:
         EXECFLAGS = stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH
         cachedir = os.path.join(path, '.hg', 'cache')
         if os.path.isdir(cachedir):
             checkisexec = os.path.join(cachedir, 'checkisexec')
             checknoexec = os.path.join(cachedir, 'checknoexec')
 
             try:
                 m = os.stat(checkisexec).st_mode
             except OSError as e:
                 if e.errno != errno.ENOENT:
                     raise
                 # checkisexec does not exist - fall through ...
             else:
                 # checkisexec exists, check if it actually is exec
                 if m & EXECFLAGS != 0:
                     # ensure checkisexec exists, check it isn't exec
                     try:
                         m = os.stat(checknoexec).st_mode
                     except OSError as e:
                         if e.errno != errno.ENOENT:
                             raise
                         file(checknoexec, 'w').close() # might fail
                         m = os.stat(checknoexec).st_mode
                     if m & EXECFLAGS == 0:
                         # check-exec is exec and check-no-exec is not exec
                         return True
                     # checknoexec exists but is exec - delete it
                     os.unlink(checknoexec)
                 # checkisexec exists but is not exec - delete it
                 os.unlink(checkisexec)
 
             # check using one file, leave it as checkisexec
             checkdir = cachedir
         else:
             # check directly in path and don't leave checkisexec behind
             checkdir = path
             checkisexec = None
         fh, fn = tempfile.mkstemp(dir=checkdir, prefix='hg-checkexec-')
         try:
             os.close(fh)
             m = os.stat(fn).st_mode
             if m & EXECFLAGS == 0:
                 os.chmod(fn, m & 0o777 | EXECFLAGS)
                 if os.stat(fn).st_mode & EXECFLAGS != 0:
                     if checkisexec is not None:
                         os.rename(fn, checkisexec)
                         fn = None
                     return True
         finally:
             if fn is not None:
                 os.unlink(fn)
     except (IOError, OSError):
         # we don't care, the user probably won't be able to commit anyway
         return False
 
 def checklink(path):
     """check whether the given path is on a symlink-capable filesystem"""
     # mktemp is not racy because symlink creation will fail if the
     # file already exists
     while True:
         cachedir = os.path.join(path, '.hg', 'cache')
         checklink = os.path.join(cachedir, 'checklink')
         # try fast path, read only
         if os.path.islink(checklink):
             return True
         if os.path.isdir(cachedir):
             checkdir = cachedir
         else:
             checkdir = path
             cachedir = None
         name = tempfile.mktemp(dir=checkdir, prefix='checklink-')
         try:
             fd = None
             if cachedir is None:
                 fd = tempfile.NamedTemporaryFile(dir=checkdir,
                                                  prefix='hg-checklink-')
                 target = os.path.basename(fd.name)
             else:
                 # create a fixed file to link to; doesn't matter if it
                 # already exists.
                 target = 'checklink-target'
                 open(os.path.join(cachedir, target), 'w').close()
             try:
                 os.symlink(target, name)
                 if cachedir is None:
                     os.unlink(name)
                 else:
                     try:
                         os.rename(name, checklink)
                     except OSError:
                         os.unlink(name)
                 return True
             except OSError as inst:
                 # link creation might race, try again
                 if inst[0] == errno.EEXIST:
                     continue
                 raise
             finally:
                 if fd is not None:
                     fd.close()
         except AttributeError:
             return False
         except OSError as inst:
             # sshfs might report failure while successfully creating the link
             if inst[0] == errno.EIO and os.path.exists(name):
                 os.unlink(name)
             return False
 
 def checkosfilename(path):
     '''Check that the base-relative path is a valid filename on this platform.
     Returns None if the path is ok, or a UI string describing the problem.'''
     pass # on posix platforms, every path is ok
 
 def setbinary(fd):
     pass
 
 def pconvert(path):
     return path
 
 def localpath(path):
     return path
 
 def samefile(fpath1, fpath2):
     """Returns whether path1 and path2 refer to the same file. This is only
     guaranteed to work for files, not directories."""
     return os.path.samefile(fpath1, fpath2)
 
 def samedevice(fpath1, fpath2):
     """Returns whether fpath1 and fpath2 are on the same device. This is only
     guaranteed to work for files, not directories."""
     st1 = os.lstat(fpath1)
     st2 = os.lstat(fpath2)
     return st1.st_dev == st2.st_dev
 
 # os.path.normcase is a no-op, which doesn't help us on non-native filesystems
 def normcase(path):
     return path.lower()
 
 # what normcase does to ASCII strings
 normcasespec = encoding.normcasespecs.lower
 # fallback normcase function for non-ASCII strings
 normcasefallback = normcase
 
 if sys.platform == 'darwin':
 
     def normcase(path):
         '''
         Normalize a filename for OS X-compatible comparison:
         - escape-encode invalid characters
         - decompose to NFD
         - lowercase
         - omit ignored characters [200c-200f, 202a-202e, 206a-206f,feff]
 
         >>> normcase('UPPER')
         'upper'
         >>> normcase('Caf\xc3\xa9')
         'cafe\\xcc\\x81'
         >>> normcase('\xc3\x89')
         'e\\xcc\\x81'
         >>> normcase('\xb8\xca\xc3\xca\xbe\xc8.JPG') # issue3918
         '%b8%ca%c3\\xca\\xbe%c8.jpg'
         '''
 
         try:
             return encoding.asciilower(path)  # exception for non-ASCII
         except UnicodeDecodeError:
             return normcasefallback(path)
 
     normcasespec = encoding.normcasespecs.lower
 
     def normcasefallback(path):
         try:
             u = path.decode('utf-8')
         except UnicodeDecodeError:
             # OS X percent-encodes any bytes that aren't valid utf-8
             s = ''
             pos = 0
             l = len(path)
             while pos < l:
                 try:
                     c = encoding.getutf8char(path, pos)
                     pos += len(c)
                 except ValueError:
                     c = '%%%02X' % ord(path[pos])
                     pos += 1
                 s += c
 
             u = s.decode('utf-8')
 
         # Decompose then lowercase (HFS+ technote specifies lower)
         enc = unicodedata.normalize('NFD', u).lower().encode('utf-8')
         # drop HFS+ ignored characters
         return encoding.hfsignoreclean(enc)
 
 if sys.platform == 'cygwin':
     # workaround for cygwin, in which mount point part of path is
     # treated as case sensitive, even though underlying NTFS is case
     # insensitive.
 
     # default mount points
     cygwinmountpoints = sorted([
             "/usr/bin",
             "/usr/lib",
             "/cygdrive",
             ], reverse=True)
 
     # use upper-ing as normcase as same as NTFS workaround
     def normcase(path):
         pathlen = len(path)
         if (pathlen == 0) or (path[0] != pycompat.ossep):
             # treat as relative
             return encoding.upper(path)
 
         # to preserve case of mountpoint part
         for mp in cygwinmountpoints:
             if not path.startswith(mp):
                 continue
 
             mplen = len(mp)
             if mplen == pathlen: # mount point itself
                 return mp
             if path[mplen] == pycompat.ossep:
                 return mp + encoding.upper(path[mplen:])
 
         return encoding.upper(path)
 
     normcasespec = encoding.normcasespecs.other
     normcasefallback = normcase
 
     # Cygwin translates native ACLs to POSIX permissions,
     # but these translations are not supported by native
     # tools, so the exec bit tends to be set erroneously.
     # Therefore, disable executable bit access on Cygwin.
     def checkexec(path):
         return False
 
     # Similarly, Cygwin's symlink emulation is likely to create
     # problems when Mercurial is used from both Cygwin and native
     # Windows, with other native tools, or on shared volumes
     def checklink(path):
         return False
 
 _needsshellquote = None
 def shellquote(s):
     if os.sys.platform == 'OpenVMS':
         return '"%s"' % s
     global _needsshellquote
     if _needsshellquote is None:
         _needsshellquote = re.compile(r'[^a-zA-Z0-9._/+-]').search
     if s and not _needsshellquote(s):
         # "s" shouldn't have to be quoted
         return s
     else:
         return "'%s'" % s.replace("'", "'\\''")
 
 def quotecommand(cmd):
     return cmd
 
 def popen(command, mode='r'):
     return os.popen(command, mode)
 
 def testpid(pid):
     '''return False if pid dead, True if running or not sure'''
     if os.sys.platform == 'OpenVMS':
         return True
     try:
         os.kill(pid, 0)
         return True
     except OSError as inst:
         return inst.errno != errno.ESRCH
 
 def explainexit(code):
     """return a 2-tuple (desc, code) describing a subprocess status
     (codes from kill are negative - not os.system/wait encoding)"""
     if code >= 0:
         return _("exited with status %d") % code, code
     return _("killed by signal %d") % -code, -code
 
 def isowner(st):
     """Return True if the stat object st is from the current user."""
     return st.st_uid == os.getuid()
 
 def findexe(command):
     '''Find executable for command searching like which does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     If command isn't found None is returned.'''
     if sys.platform == 'OpenVMS':
         return command
 
     def findexisting(executable):
         'Will return executable if existing file'
         if os.path.isfile(executable) and os.access(executable, os.X_OK):
             return executable
         return None
 
     if pycompat.ossep in command:
         return findexisting(command)
 
     if sys.platform == 'plan9':
         return findexisting(os.path.join('/bin', command))
 
-    for path in os.environ.get('PATH', '').split(pycompat.ospathsep):
+    for path in encoding.environ.get('PATH', '').split(pycompat.ospathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return None
 
 def setsignalhandler():
     pass
 
 _wantedkinds = set([stat.S_IFREG, stat.S_IFLNK])
 
 def statfiles(files):
     '''Stat each file in files. Yield each stat, or None if a file does not
     exist or has a type we don't care about.'''
     lstat = os.lstat
     getkind = stat.S_IFMT
     for nf in files:
         try:
             st = lstat(nf)
             if getkind(st.st_mode) not in _wantedkinds:
                 st = None
         except OSError as err:
             if err.errno not in (errno.ENOENT, errno.ENOTDIR):
                 raise
             st = None
         yield st
 
 def getuser():
     '''return name of current user'''
     return getpass.getuser()
 
 def username(uid=None):
     """Return the name of the user with the given uid.
 
     If uid is None, return the name of the current user."""
 
     if uid is None:
         uid = os.getuid()
     try:
         return pwd.getpwuid(uid)[0]
     except KeyError:
         return str(uid)
 
 def groupname(gid=None):
     """Return the name of the group with the given gid.
 
     If gid is None, return the name of the current group."""
 
     if gid is None:
         gid = os.getgid()
     try:
         return grp.getgrgid(gid)[0]
     except KeyError:
         return str(gid)
 
 def groupmembers(name):
     """Return the list of members of the group with the given
     name, KeyError if the group does not exist.
     """
     return list(grp.getgrnam(name).gr_mem)
 
 def spawndetached(args):
     return os.spawnvp(os.P_NOWAIT | getattr(os, 'P_DETACH', 0),
                       args[0], args)
 
 def gethgcmd():
     return sys.argv[:1]
 
 def makedir(path, notindexed):
     os.mkdir(path)
 
 def unlinkpath(f, ignoremissing=False):
     """unlink and remove the directory if it is empty"""
     try:
         os.unlink(f)
     except OSError as e:
         if not (ignoremissing and e.errno == errno.ENOENT):
             raise
     # try removing directories that might now be empty
     try:
         os.removedirs(os.path.dirname(f))
     except OSError:
         pass
 
 def lookupreg(key, name=None, scope=None):
     return None
 
 def hidewindow():
     """Hide current shell window.
 
     Used to hide the window opened when starting asynchronous
     child process under Windows, unneeded on other systems.
     """
     pass
 
 class cachestat(object):
     def __init__(self, path):
         self.stat = os.stat(path)
 
     def cacheable(self):
         return bool(self.stat.st_ino)
 
     __hash__ = object.__hash__
 
     def __eq__(self, other):
         try:
             # Only dev, ino, size, mtime and atime are likely to change. Out
             # of these, we shouldn't compare atime but should compare the
             # rest. However, one of the other fields changing indicates
             # something fishy going on, so return False if anything but atime
             # changes.
             return (self.stat.st_mode == other.stat.st_mode and
                     self.stat.st_ino == other.stat.st_ino and
                     self.stat.st_dev == other.stat.st_dev and
                     self.stat.st_nlink == other.stat.st_nlink and
                     self.stat.st_uid == other.stat.st_uid and
                     self.stat.st_gid == other.stat.st_gid and
                     self.stat.st_size == other.stat.st_size and
                     self.stat.st_mtime == other.stat.st_mtime and
                     self.stat.st_ctime == other.stat.st_ctime)
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not self == other
 
 def executablepath():
     return None # available on Windows only
 
 def statislink(st):
     '''check whether a stat result is a symlink'''
     return st and stat.S_ISLNK(st.st_mode)
 
 def statisexec(st):
     '''check whether a stat result is an executable file'''
     return st and (st.st_mode & 0o100 != 0)
 
 def poll(fds):
     """block until something happens on any file descriptor
 
     This is a generic helper that will check for any activity
     (read, write.  exception) and return the list of touched files.
 
     In unsupported cases, it will raise a NotImplementedError"""
     try:
         res = select.select(fds, fds, fds)
     except ValueError: # out of range file descriptor
         raise NotImplementedError()
     return sorted(list(set(sum(res, []))))
 
 def readpipe(pipe):
     """Read all available data from a pipe."""
     # We can't fstat() a pipe because Linux will always report 0.
     # So, we set the pipe to non-blocking mode and read everything
     # that's available.
     flags = fcntl.fcntl(pipe, fcntl.F_GETFL)
     flags |= os.O_NONBLOCK
     oldflags = fcntl.fcntl(pipe, fcntl.F_SETFL, flags)
 
     try:
         chunks = []
         while True:
             try:
                 s = pipe.read()
                 if not s:
                     break
                 chunks.append(s)
             except IOError:
                 break
 
         return ''.join(chunks)
     finally:
         fcntl.fcntl(pipe, fcntl.F_SETFL, oldflags)
 
 def bindunixsocket(sock, path):
     """Bind the UNIX domain socket to the specified path"""
     # use relative path instead of full path at bind() if possible, since
     # AF_UNIX path has very small length limit (107 chars) on common
     # platforms (see sys/un.h)
     dirname, basename = os.path.split(path)
     bakwdfd = None
     if dirname:
         bakwdfd = os.open('.', os.O_DIRECTORY)
         os.chdir(dirname)
     sock.bind(basename)
     if bakwdfd:
         os.fchdir(bakwdfd)
         os.close(bakwdfd)