dirstate: move file type filtering to its source

This prepares us to move to a much faster statfiles implementation on Unix.

mercurial/dirstate.py

@@ -1,798 +1,795 b''
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 import errno
 
 from node import nullid
 from i18n import _
 import scmutil, util, ignore, osutil, parsers, encoding
 import struct, os, stat, errno
 import cStringIO
 
 _format = ">cllll"
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7fffffff
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
 def _finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)
 
 def _incdirs(dirs, path):
     for base in _finddirs(path):
         if base in dirs:
             dirs[base] += 1
             return
         dirs[base] = 1
 
 def _decdirs(dirs, path):
     for base in _finddirs(path):
         if dirs[base] > 1:
             dirs[base] -= 1
             return
         del dirs[base]
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         self._rootdir = os.path.join(root, '')
         self._dirty = False
         self._dirtypl = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _foldmap(self):
         f = {}
         for name in self._map:
             f[util.normcase(name)] = name
         for name in self._dirs:
             f[util.normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             fp = self._opener("dirstate")
             st = fp.read(40)
             fp.close()
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise util.Abort(_('working directory state appears damaged!'))
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
         dirs = {}
         for f, s in self._map.iteritems():
             if s[0] != 'r':
                 _incdirs(dirs, f)
         return dirs
 
     def dirs(self):
         return self._dirs
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = [self._join('.hgignore')]
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 files.append(util.expandpath(path))
         return ignore.ignore(self._root, files, self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and os.sep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.checkcase(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 p = self._join(x)
                 if os.path.islink(p):
                     return 'l'
                 if util.isexec(p):
                     return 'x'
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += os.sep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.normpath(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         self._dirty = self._dirtypl = True
         oldp2 = self._pl[1]
         self._pl = p1, p2
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             # Discard 'm' markers when moving away from a merge state
             for f, s in self._map.iteritems():
                 if s[0] == 'm':
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.normallookup(f)
         return copies
 
     def setbranch(self, branch):
         self._branch = encoding.fromlocal(branch)
         f = self._opener('branch', 'w', atomictemp=True)
         try:
             f.write(self._branch + '\n')
         finally:
             f.close()
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             st = self._opener.read("dirstate")
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         p = parsers.parse_dirstate(self._map, self._copymap, st)
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in ("_map", "_copymap", "_foldmap", "_branch", "_pl", "_dirs",
                 "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
             _decdirs(self._dirs, f)
 
     def _addpath(self, f, state, mode, size, mtime):
         oldstate = self[f]
         if state == 'a' or oldstate == 'r':
             scmutil.checkfilename(f)
             if f in self._dirs:
                 raise util.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in _finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise util.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
             _incdirs(self._dirs, f)
         self._dirty = True
         self._map[f] = (state, mode, size, mtime)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         s = os.lstat(self._join(f))
         mtime = int(s.st_mtime)
         self._addpath(f, 'n', s.st_mode,
                       s.st_size & _rangemask, mtime & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.otherparent(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._addpath(f, 'n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise util.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         self._addpath(f, 'n', 0, -2, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, 'a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             # backup the previous state
             entry = self._map[f]
             if entry[0] == 'm': # merge
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2: # other parent
                 size = -2
         self._map[f] = ('r', 0, size, 0)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         s = os.lstat(self._join(f))
         self._addpath(f, 'm', s.st_mode,
                       s.st_size & _rangemask, int(s.st_mtime) & _rangemask)
         if f in self._copymap:
             del self._copymap[f]
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         if f in self._map:
             self._dirty = True
             self._droppath(f)
             del self._map[f]
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._foldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 if exists is None:
                     exists = os.path.lexists(os.path.join(self._root, path))
                 if not exists:
                     # Maybe a path component exists
                     if not ignoremissing and '/' in path:
                         d, f = path.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, None)
                         folded = d + "/" + f
                     else:
                         # No path components, preserve original case
                         folded = path
                 else:
                     # recursively normalize leading directory components
                     # against dirstate
                     if '/' in normed:
                         d, f = normed.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, True)
                         r = self._root + "/" + d
                         folded = d + "/" + util.fspath(f, r)
                     else:
                         folded = util.fspath(normed, self._root)
                     self._foldmap[normed] = folded
 
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs")
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, files):
         self.clear()
         for f in files:
             if 'x' in files.flags(f):
                 self._map[f] = ('n', 0777, -1, 0)
             else:
                 self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         st = self._opener("dirstate", "w", atomictemp=True)
 
         def finish(s):
             st.write(s)
             st.close()
             self._lastnormaltime = 0
             self._dirty = self._dirtypl = False
 
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st).st_mtime
         copymap = self._copymap
         try:
             finish(parsers.pack_dirstate(self._map, copymap, self._pl, now))
             return
         except AttributeError:
             pass
 
         now = int(now)
         cs = cStringIO.StringIO()
         pack = struct.pack
         write = cs.write
         write("".join(self._pl))
         for f, e in self._map.iteritems():
             if e[0] == 'n' and e[3] == now:
                 # The file was last modified "simultaneously" with the current
                 # write to dirstate (i.e. within the same second for file-
                 # systems with a granularity of 1 sec). This commonly happens
                 # for at least a couple of files on 'update'.
                 # The user could change the file without changing its size
                 # within the same second. Invalidate the file's stat data in
                 # dirstate, forcing future 'status' calls to compare the
                 # contents of the file. This prevents mistakenly treating such
                 # files as clean.
                 e = (e[0], 0, -1, -1)   # mark entry as 'unset'
                 self._map[f] = e
 
             if f in copymap:
                 f = "%s\0%s" % (f, copymap[f])
             e = pack(_format, e[0], e[1], e[2], e[3], len(f))
             write(e)
             write(f)
         finish(cs.getvalue())
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in _finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def walk(self, match, subrepos, unknown, ignored):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
         '''
 
         def fwarn(f, msg):
             self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
             return False
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif not unknown:
             # if unknown and ignored are False, skip step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         badfn = match.bad
         dmap = self._map
         normpath = util.normpath
         listdir = osutil.listdir
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         work = []
         wadd = work.append
 
         exact = skipstep3 = False
         if matchfn == match.exact: # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.files() and not match.anypats(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             skipstep3 = False
         else:
             normalize = lambda x, y, z: x
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         # step 1: find all explicit files
         for ff in files:
             nf = normalize(normpath(ff), False, True)
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     skipstep3 = False
                     if nf in dmap:
                         #file deleted on disk but still in dirstate
                         results[nf] = None
                     match.dir(nf)
                     if not dirignore(nf):
                         wadd(nf)
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError, inst:
                 if nf in dmap: # does it exactly match a file?
                     results[nf] = None
                 else: # does it match a directory?
                     prefix = nf + "/"
                     for fn in dmap:
                         if fn.startswith(prefix):
                             match.dir(nf)
                             skipstep3 = False
                             break
                     else:
                         badfn(ff, inst.strerror)
 
         # step 2: visit subdirectories
         while work:
             nd = work.pop()
             skip = None
             if nd == '.':
                 nd = ''
             else:
                 skip = '.hg'
             try:
                 entries = listdir(join(nd), stat=True, skip=skip)
             except OSError, inst:
                 if inst.errno in (errno.EACCES, errno.ENOENT):
                     fwarn(nd, inst.strerror)
                     continue
                 raise
             for f, kind, st in entries:
                 nf = normalize(nd and (nd + "/" + f) or f, True, True)
                 if nf not in results:
                     if kind == dirkind:
                         if not ignore(nf):
                             match.dir(nf)
                             wadd(nf)
                         if nf in dmap and matchfn(nf):
                             results[nf] = None
                     elif kind == regkind or kind == lnkkind:
                         if nf in dmap:
                             if matchfn(nf):
                                 results[nf] = st
                         elif matchfn(nf) and not ignore(nf):
                             results[nf] = st
                     elif nf in dmap and matchfn(nf):
                         results[nf] = None
 
         # step 3: report unseen items in the dmap hash
         if not skipstep3 and not exact:
             visit = sorted([f for f in dmap if f not in results and matchfn(f)])
             for nf, st in zip(visit, util.statfiles([join(i) for i in visit])):
-                if (not st is None and
-                    getkind(st.st_mode) not in (regkind, lnkkind)):
-                    st = None
                 results[nf] = st
         for s in subrepos:
             del results[s]
         del results['.hg']
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a tuple of lists (unsure, modified, added,
         removed, deleted, unknown, ignored, clean), where:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           added:
             files that have been explicitly added with hg add
           removed:
             files that have been explicitly removed with hg remove
           deleted:
             files that have been deleted through other means ("missing")
           unknown:
             files not in the dirstate that are not ignored
           ignored:
             files not in the dirstate that are ignored
             (by _dirignore())
           clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
 
         lnkkind = stat.S_IFLNK
 
         for fn, st in self.walk(match, subrepos, listunknown,
                                 listignored).iteritems():
             if fn not in dmap:
                 if (listignored or match.exact(fn)) and self._dirignore(fn):
                     if listignored:
                         iadd(fn)
                 elif listunknown:
                     uadd(fn)
                 continue
 
             state, mode, size, time = dmap[fn]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 # The "mode & lnkkind != lnkkind or self._checklink"
                 # lines are an expansion of "islink => checklink"
                 # where islink means "is this a link?" and checklink
                 # means "can we check links?".
                 mtime = int(st.st_mtime)
                 if (size >= 0 and
                     ((size != st.st_size and size != st.st_size & _rangemask)
                      or ((mode ^ st.st_mode) & 0100 and self._checkexec))
                     and (mode & lnkkind != lnkkind or self._checklink)
                     or size == -2 # other parent
                     or fn in self._copymap):
                     madd(fn)
                 elif ((time != mtime and time != mtime & _rangemask)
                       and (mode & lnkkind != lnkkind or self._checklink)):
                     ladd(fn)
                 elif mtime == self._lastnormaltime:
                     # fn may have been changed in the same timeslot without
                     # changing its size. This can happen if we quickly do
                     # multiple commits in a single transaction.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)

mercurial/posix.py

@@ -1,479 +1,485 b''
 # 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 i18n import _
 import encoding
 import os, sys, errno, stat, getpass, pwd, grp, tempfile, unicodedata
 
 posixfile = open
 normpath = os.path.normpath
 samestat = os.path.samestat
 oslink = os.link
 unlink = os.unlink
 rename = os.rename
 expandglobs = False
 
 umask = os.umask(0)
 os.umask(umask)
 
 def split(p):
     '''Same as os.path.split, but faster'''
     ht = p.rsplit('/', 1)
     if len(ht) == 1:
         return '', p
     nh = ht[0].rstrip('/')
     if nh:
         return nh, ht[1]
     return ht
 
 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 & 0100 != 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 = 0666 & ~umask # avoid restatting for chmod
 
     sx = s & 0100
     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 & 0444) >> 2 & ~umask)
     elif not x and sx:
         # Turn off all +x bits
         os.chmod(f, s & 0666)
 
 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 & 0777
     except OSError, inst:
         if inst.errno != errno.ENOENT:
             raise
         st_mode = mode
         if st_mode is None:
             st_mode = ~umask
         st_mode &= 0666
     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
         fh, fn = tempfile.mkstemp(dir=path, prefix='hg-checkexec-')
         try:
             os.close(fh)
             m = os.stat(fn).st_mode & 0777
             new_file_has_exec = m & EXECFLAGS
             os.chmod(fn, m ^ EXECFLAGS)
             exec_flags_cannot_flip = ((os.stat(fn).st_mode & 0777) == m)
         finally:
             os.unlink(fn)
     except (IOError, OSError):
         # we don't care, the user probably won't be able to commit anyway
         return False
     return not (new_file_has_exec or exec_flags_cannot_flip)
 
 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
     name = tempfile.mktemp(dir=path, prefix='hg-checklink-')
     try:
         os.symlink(".", name)
         os.unlink(name)
         return True
     except (OSError, AttributeError):
         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()
 
 if sys.platform == 'darwin':
     import fcntl # only needed on darwin, missing on jython
 
     def normcase(path):
         try:
             u = path.decode('utf-8')
         except UnicodeDecodeError:
             # percent-encode any characters that don't round-trip
             p2 = path.decode('utf-8', 'ignore').encode('utf-8')
             s = ""
             pos = 0
             for c in path:
                 if p2[pos:pos + 1] == c:
                     s += c
                     pos += 1
                 else:
                     s += "%%%02X" % ord(c)
             u = s.decode('utf-8')
 
         # Decompose then lowercase (HFS+ technote specifies lower)
         return unicodedata.normalize('NFD', u).lower().encode('utf-8')
 
     def realpath(path):
         '''
         Returns the true, canonical file system path equivalent to the given
         path.
 
         Equivalent means, in this case, resulting in the same, unique
         file system link to the path. Every file system entry, whether a file,
         directory, hard link or symbolic link or special, will have a single
         path preferred by the system, but may allow multiple, differing path
         lookups to point to it.
 
         Most regular UNIX file systems only allow a file system entry to be
         looked up by its distinct path. Obviously, this does not apply to case
         insensitive file systems, whether case preserving or not. The most
         complex issue to deal with is file systems transparently reencoding the
         path, such as the non-standard Unicode normalisation required for HFS+
         and HFSX.
         '''
         # Constants copied from /usr/include/sys/fcntl.h
         F_GETPATH = 50
         O_SYMLINK = 0x200000
 
         try:
             fd = os.open(path, O_SYMLINK)
         except OSError, err:
             if err.errno == errno.ENOENT:
                 return path
             raise
 
         try:
             return fcntl.fcntl(fd, F_GETPATH, '\0' * 1024).rstrip('\0')
         finally:
             os.close(fd)
 elif sys.version_info < (2, 4, 2, 'final'):
     # Workaround for http://bugs.python.org/issue1213894 (os.path.realpath
     # didn't resolve symlinks that were the first component of the path.)
     def realpath(path):
         if os.path.isabs(path):
             return os.path.realpath(path)
         else:
             return os.path.realpath('./' + path)
 else:
     # Fallback to the likely inadequate Python builtin function.
     realpath = os.path.realpath
 
 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] != os.sep):
             # 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] == os.sep:
                 return mp + encoding.upper(path[mplen:])
 
         return encoding.upper(path)
 
     # 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
 
 def shellquote(s):
     if os.sys.platform == 'OpenVMS':
         return '"%s"' % 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, 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 os.sep in command:
         return findexisting(command)
 
     if sys.platform == 'plan9':
         return findexisting(os.path.join('/bin', command))
 
     for path in os.environ.get('PATH', '').split(os.pathsep):
         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 and yield stat or None if file does not exist.'
+    '''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, 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 termwidth():
     try:
         import termios, array, fcntl
         for dev in (sys.stderr, sys.stdout, sys.stdin):
             try:
                 try:
                     fd = dev.fileno()
                 except AttributeError:
                     continue
                 if not os.isatty(fd):
                     continue
                 try:
                     arri = fcntl.ioctl(fd, termios.TIOCGWINSZ, '\0' * 8)
                     width = array.array('h', arri)[1]
                     if width > 0:
                         return width
                 except AttributeError:
                     pass
             except ValueError:
                 pass
             except IOError, e:
                 if e[0] == errno.EINVAL:
                     pass
                 else:
                     raise
     except ImportError:
         pass
     return 80
 
 def makedir(path, notindexed):
     os.mkdir(path)
 
 def unlinkpath(f):
     """unlink and remove the directory if it is empty"""
     os.unlink(f)
     # 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:
             return self.stat == other.stat
         except AttributeError:
             return False
 
     def __ne__(self, other):
         return not self == other
 
 def executablepath():
     return None # available on Windows only

mercurial/windows.py

@@ -1,329 +1,335 b''
 # windows.py - Windows 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 i18n import _
 import osutil, encoding
-import errno, msvcrt, os, re, sys, _winreg
+import errno, msvcrt, os, re, stat, sys, _winreg
 
 import win32
 executablepath = win32.executablepath
 getuser = win32.getuser
 hidewindow = win32.hidewindow
 makedir = win32.makedir
 nlinks = win32.nlinks
 oslink = win32.oslink
 samedevice = win32.samedevice
 samefile = win32.samefile
 setsignalhandler = win32.setsignalhandler
 spawndetached = win32.spawndetached
 split = os.path.split
 termwidth = win32.termwidth
 testpid = win32.testpid
 unlink = win32.unlink
 
 umask = 0022
 
 # wrap osutil.posixfile to provide friendlier exceptions
 def posixfile(name, mode='r', buffering=-1):
     try:
         return osutil.posixfile(name, mode, buffering)
     except WindowsError, err:
         raise IOError(err.errno, '%s: %s' % (name, err.strerror))
 posixfile.__doc__ = osutil.posixfile.__doc__
 
 class winstdout(object):
     '''stdout on windows misbehaves if sent through a pipe'''
 
     def __init__(self, fp):
         self.fp = fp
 
     def __getattr__(self, key):
         return getattr(self.fp, key)
 
     def close(self):
         try:
             self.fp.close()
         except IOError:
             pass
 
     def write(self, s):
         try:
             # This is workaround for "Not enough space" error on
             # writing large size of data to console.
             limit = 16000
             l = len(s)
             start = 0
             self.softspace = 0
             while start < l:
                 end = start + limit
                 self.fp.write(s[start:end])
                 start = end
         except IOError, inst:
             if inst.errno != 0:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
     def flush(self):
         try:
             return self.fp.flush()
         except IOError, inst:
             if inst.errno != errno.EINVAL:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
 sys.__stdout__ = sys.stdout = winstdout(sys.stdout)
 
 def _is_win_9x():
     '''return true if run on windows 95, 98 or me.'''
     try:
         return sys.getwindowsversion()[3] == 1
     except AttributeError:
         return 'command' in os.environ.get('comspec', '')
 
 def openhardlinks():
     return not _is_win_9x()
 
 def parsepatchoutput(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if pf[0] == '`':
         pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh or Plink'''
     pflag = 'plink' in sshcmd.lower() and '-P' or '-p'
     args = user and ("%s@%s" % (user, host)) or host
     return port and ("%s %s %s" % (args, pflag, port)) or args
 
 def setflags(f, l, x):
     pass
 
 def copymode(src, dst, mode=None):
     pass
 
 def checkexec(path):
     return False
 
 def checklink(path):
     return False
 
 def setbinary(fd):
     # When run without console, pipes may expose invalid
     # fileno(), usually set to -1.
     fno = getattr(fd, 'fileno', None)
     if fno is not None and fno() >= 0:
         msvcrt.setmode(fno(), os.O_BINARY)
 
 def pconvert(path):
     return path.replace(os.sep, '/')
 
 def localpath(path):
     return path.replace('/', '\\')
 
 def normpath(path):
     return pconvert(os.path.normpath(path))
 
 def normcase(path):
     return encoding.upper(path)
 
 def realpath(path):
     '''
     Returns the true, canonical file system path equivalent to the given
     path.
     '''
     # TODO: There may be a more clever way to do this that also handles other,
     # less common file systems.
     return os.path.normpath(normcase(os.path.realpath(path)))
 
 def samestat(s1, s2):
     return False
 
 # A sequence of backslashes is special iff it precedes a double quote:
 # - if there's an even number of backslashes, the double quote is not
 #   quoted (i.e. it ends the quoted region)
 # - if there's an odd number of backslashes, the double quote is quoted
 # - in both cases, every pair of backslashes is unquoted into a single
 #   backslash
 # (See http://msdn2.microsoft.com/en-us/library/a1y7w461.aspx )
 # So, to quote a string, we must surround it in double quotes, double
 # the number of backslashes that precede double quotes and add another
 # backslash before every double quote (being careful with the double
 # quote we've appended to the end)
 _quotere = None
 def shellquote(s):
     global _quotere
     if _quotere is None:
         _quotere = re.compile(r'(\\*)("|\\$)')
     return '"%s"' % _quotere.sub(r'\1\1\\\2', s)
 
 def quotecommand(cmd):
     """Build a command string suitable for os.popen* calls."""
     if sys.version_info < (2, 7, 1):
         # Python versions since 2.7.1 do this extra quoting themselves
         return '"' + cmd + '"'
     return cmd
 
 def popen(command, mode='r'):
     # Work around "popen spawned process may not write to stdout
     # under windows"
     # http://bugs.python.org/issue1366
     command += " 2> %s" % os.devnull
     return os.popen(quotecommand(command), mode)
 
 def explainexit(code):
     return _("exited with status %d") % code, code
 
 # if you change this stub into a real check, please try to implement the
 # username and groupname functions above, too.
 def isowner(st):
     return True
 
 def findexe(command):
     '''Find executable for command searching like cmd.exe does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     An extension from PATHEXT is found and added if not present.
     If command isn't found None is returned.'''
     pathext = os.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
     pathexts = [ext for ext in pathext.lower().split(os.pathsep)]
     if os.path.splitext(command)[1].lower() in pathexts:
         pathexts = ['']
 
     def findexisting(pathcommand):
         'Will append extension (if needed) and return existing file'
         for ext in pathexts:
             executable = pathcommand + ext
             if os.path.exists(executable):
                 return executable
         return None
 
     if os.sep in command:
         return findexisting(command)
 
     for path in os.environ.get('PATH', '').split(os.pathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return findexisting(os.path.expanduser(os.path.expandvars(command)))
 
+_wantedkinds = set([stat.S_IFREG, stat.S_IFLNK])
+
 def statfiles(files):
-    '''Stat each file in files and yield stat or None if file does not exist.
+    '''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.
+
     Cluster and cache stat per directory to minimize number of OS stat calls.'''
     dircache = {} # dirname -> filename -> status | None if file does not exist
+    getkind = stat.S_IFMT
     for nf in files:
         nf  = normcase(nf)
         dir, base = os.path.split(nf)
         if not dir:
             dir = '.'
         cache = dircache.get(dir, None)
         if cache is None:
             try:
                 dmap = dict([(normcase(n), s)
-                    for n, k, s in osutil.listdir(dir, True)])
+                             for n, k, s in osutil.listdir(dir, True)
+                             if getkind(s) in _wantedkinds])
             except OSError, err:
                 # handle directory not found in Python version prior to 2.5
                 # Python <= 2.4 returns native Windows code 3 in errno
                 # Python >= 2.5 returns ENOENT and adds winerror field
                 # EINVAL is raised if dir is not a directory.
                 if err.errno not in (3, errno.ENOENT, errno.EINVAL,
                                      errno.ENOTDIR):
                     raise
                 dmap = {}
             cache = dircache.setdefault(dir, dmap)
         yield cache.get(base, None)
 
 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."""
     return None
 
 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."""
     return None
 
 def _removedirs(name):
     """special version of os.removedirs that does not remove symlinked
     directories or junction points if they actually contain files"""
     if osutil.listdir(name):
         return
     os.rmdir(name)
     head, tail = os.path.split(name)
     if not tail:
         head, tail = os.path.split(head)
     while head and tail:
         try:
             if osutil.listdir(head):
                 return
             os.rmdir(head)
         except (ValueError, OSError):
             break
         head, tail = os.path.split(head)
 
 def unlinkpath(f):
     """unlink and remove the directory if it is empty"""
     unlink(f)
     # try removing directories that might now be empty
     try:
         _removedirs(os.path.dirname(f))
     except OSError:
         pass
 
 def rename(src, dst):
     '''atomically rename file src to dst, replacing dst if it exists'''
     try:
         os.rename(src, dst)
     except OSError, e:
         if e.errno != errno.EEXIST:
             raise
         unlink(dst)
         os.rename(src, dst)
 
 def gethgcmd():
     return [sys.executable] + sys.argv[:1]
 
 def groupmembers(name):
     # Don't support groups on Windows for now
     raise KeyError
 
 def isexec(f):
     return False
 
 class cachestat(object):
     def __init__(self, path):
         pass
 
     def cacheable(self):
         return False
 
 def lookupreg(key, valname=None, scope=None):
     ''' Look up a key/value name in the Windows registry.
 
     valname: value name. If unspecified, the default value for the key
     is used.
     scope: optionally specify scope for registry lookup, this can be
     a sequence of scopes to look up in order. Default (CURRENT_USER,
     LOCAL_MACHINE).
     '''
     if scope is None:
         scope = (_winreg.HKEY_CURRENT_USER, _winreg.HKEY_LOCAL_MACHINE)
     elif not isinstance(scope, (list, tuple)):
         scope = (scope,)
     for s in scope:
         try:
             val = _winreg.QueryValueEx(_winreg.OpenKey(s, key), valname)[0]
             # never let a Unicode string escape into the wild
             return encoding.tolocal(val.encode('UTF-8'))
         except EnvironmentError:
             pass
 
 expandglobs = True