vfs: add a 'reljoin' function for joining relative paths

The vfs.join method only works for absolute paths. We need something
that works for relative paths too when transforming filenames. Since
os.path.join may misbehave in tricky encoding situations, encapsulate
the new join method in our vfs abstraction. The default implementation
remains os.path.join, but this opens the door to other VFSes doing
something more intelligent based on their needs.

In the same go, we replace the usage of 'os.path.join' in transaction code.

mercurial/scmutil.py

@@ -1,1095 +1,1102
 # scmutil.py - Mercurial core utility functions
 #
 #  Copyright Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 from mercurial.node import nullrev
 import util, error, osutil, revset, similar, encoding, phases, parsers
 import pathutil
 import match as matchmod
 import os, errno, re, glob, tempfile
 
 if os.name == 'nt':
     import scmwindows as scmplatform
 else:
     import scmposix as scmplatform
 
 systemrcpath = scmplatform.systemrcpath
 userrcpath = scmplatform.userrcpath
 
 class status(tuple):
     '''Named tuple with a list of files per status. The 'deleted', 'unknown'
        and 'ignored' properties are only relevant to the working copy.
     '''
 
     __slots__ = ()
 
     def __new__(cls, modified, added, removed, deleted, unknown, ignored,
                 clean):
         return tuple.__new__(cls, (modified, added, removed, deleted, unknown,
                                    ignored, clean))
 
     @property
     def modified(self):
         '''files that have been modified'''
         return self[0]
 
     @property
     def added(self):
         '''files that have been added'''
         return self[1]
 
     @property
     def removed(self):
         '''files that have been removed'''
         return self[2]
 
     @property
     def deleted(self):
         '''files that are in the dirstate, but have been deleted from the
            working copy (aka "missing")
         '''
         return self[3]
 
     @property
     def unknown(self):
         '''files not in the dirstate that are not ignored'''
         return self[4]
 
     @property
     def ignored(self):
         '''files not in the dirstate that are ignored (by _dirignore())'''
         return self[5]
 
     @property
     def clean(self):
         '''files that have not been modified'''
         return self[6]
 
     def __repr__(self, *args, **kwargs):
         return (('<status modified=%r, added=%r, removed=%r, deleted=%r, '
                  'unknown=%r, ignored=%r, clean=%r>') % self)
 
 def itersubrepos(ctx1, ctx2):
     """find subrepos in ctx1 or ctx2"""
     # Create a (subpath, ctx) mapping where we prefer subpaths from
     # ctx1. The subpaths from ctx2 are important when the .hgsub file
     # has been modified (in ctx2) but not yet committed (in ctx1).
     subpaths = dict.fromkeys(ctx2.substate, ctx2)
     subpaths.update(dict.fromkeys(ctx1.substate, ctx1))
     for subpath, ctx in sorted(subpaths.iteritems()):
         yield subpath, ctx.sub(subpath)
 
 def nochangesfound(ui, repo, excluded=None):
     '''Report no changes for push/pull, excluded is None or a list of
     nodes excluded from the push/pull.
     '''
     secretlist = []
     if excluded:
         for n in excluded:
             if n not in repo:
                 # discovery should not have included the filtered revision,
                 # we have to explicitly exclude it until discovery is cleanup.
                 continue
             ctx = repo[n]
             if ctx.phase() >= phases.secret and not ctx.extinct():
                 secretlist.append(n)
 
     if secretlist:
         ui.status(_("no changes found (ignored %d secret changesets)\n")
                   % len(secretlist))
     else:
         ui.status(_("no changes found\n"))
 
 def checknewlabel(repo, lbl, kind):
     # Do not use the "kind" parameter in ui output.
     # It makes strings difficult to translate.
     if lbl in ['tip', '.', 'null']:
         raise util.Abort(_("the name '%s' is reserved") % lbl)
     for c in (':', '\0', '\n', '\r'):
         if c in lbl:
             raise util.Abort(_("%r cannot be used in a name") % c)
     try:
         int(lbl)
         raise util.Abort(_("cannot use an integer as a name"))
     except ValueError:
         pass
 
 def checkfilename(f):
     '''Check that the filename f is an acceptable filename for a tracked file'''
     if '\r' in f or '\n' in f:
         raise util.Abort(_("'\\n' and '\\r' disallowed in filenames: %r") % f)
 
 def checkportable(ui, f):
     '''Check if filename f is portable and warn or abort depending on config'''
     checkfilename(f)
     abort, warn = checkportabilityalert(ui)
     if abort or warn:
         msg = util.checkwinfilename(f)
         if msg:
             msg = "%s: %r" % (msg, f)
             if abort:
                 raise util.Abort(msg)
             ui.warn(_("warning: %s\n") % msg)
 
 def checkportabilityalert(ui):
     '''check if the user's config requests nothing, a warning, or abort for
     non-portable filenames'''
     val = ui.config('ui', 'portablefilenames', 'warn')
     lval = val.lower()
     bval = util.parsebool(val)
     abort = os.name == 'nt' or lval == 'abort'
     warn = bval or lval == 'warn'
     if bval is None and not (warn or abort or lval == 'ignore'):
         raise error.ConfigError(
             _("ui.portablefilenames value is invalid ('%s')") % val)
     return abort, warn
 
 class casecollisionauditor(object):
     def __init__(self, ui, abort, dirstate):
         self._ui = ui
         self._abort = abort
         allfiles = '\0'.join(dirstate._map)
         self._loweredfiles = set(encoding.lower(allfiles).split('\0'))
         self._dirstate = dirstate
         # The purpose of _newfiles is so that we don't complain about
         # case collisions if someone were to call this object with the
         # same filename twice.
         self._newfiles = set()
 
     def __call__(self, f):
         if f in self._newfiles:
             return
         fl = encoding.lower(f)
         if fl in self._loweredfiles and f not in self._dirstate:
             msg = _('possible case-folding collision for %s') % f
             if self._abort:
                 raise util.Abort(msg)
             self._ui.warn(_("warning: %s\n") % msg)
         self._loweredfiles.add(fl)
         self._newfiles.add(f)
 
 class abstractvfs(object):
     """Abstract base class; cannot be instantiated"""
 
     def __init__(self, *args, **kwargs):
         '''Prevent instantiation; don't call this from subclasses.'''
         raise NotImplementedError('attempted instantiating ' + str(type(self)))
 
     def tryread(self, path):
         '''gracefully return an empty string for missing files'''
         try:
             return self.read(path)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
         return ""
 
     def tryreadlines(self, path, mode='rb'):
         '''gracefully return an empty array for missing files'''
         try:
             return self.readlines(path, mode=mode)
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
         return []
 
     def open(self, path, mode="r", text=False, atomictemp=False,
              notindexed=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
         '''
         self.open = self.__call__
         return self.__call__(path, mode, text, atomictemp, notindexed)
 
     def read(self, path):
         fp = self(path, 'rb')
         try:
             return fp.read()
         finally:
             fp.close()
 
     def readlines(self, path, mode='rb'):
         fp = self(path, mode=mode)
         try:
             return fp.readlines()
         finally:
             fp.close()
 
     def write(self, path, data):
         fp = self(path, 'wb')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def writelines(self, path, data, mode='wb', notindexed=False):
         fp = self(path, mode=mode, notindexed=notindexed)
         try:
             return fp.writelines(data)
         finally:
             fp.close()
 
     def append(self, path, data):
         fp = self(path, 'ab')
         try:
             return fp.write(data)
         finally:
             fp.close()
 
     def chmod(self, path, mode):
         return os.chmod(self.join(path), mode)
 
     def exists(self, path=None):
         return os.path.exists(self.join(path))
 
     def fstat(self, fp):
         return util.fstat(fp)
 
     def isdir(self, path=None):
         return os.path.isdir(self.join(path))
 
     def isfile(self, path=None):
         return os.path.isfile(self.join(path))
 
     def islink(self, path=None):
         return os.path.islink(self.join(path))
 
+    def reljoin(self, *paths):
+        """join various elements of a path together (as os.path.join would do)
+
+        The vfs base is not injected so that path stay relative. This exists
+        to allow handling of strange encoding if needed."""
+        return os.path.join(*paths)
+
     def lexists(self, path=None):
         return os.path.lexists(self.join(path))
 
     def lstat(self, path=None):
         return os.lstat(self.join(path))
 
     def listdir(self, path=None):
         return os.listdir(self.join(path))
 
     def makedir(self, path=None, notindexed=True):
         return util.makedir(self.join(path), notindexed)
 
     def makedirs(self, path=None, mode=None):
         return util.makedirs(self.join(path), mode)
 
     def makelock(self, info, path):
         return util.makelock(info, self.join(path))
 
     def mkdir(self, path=None):
         return os.mkdir(self.join(path))
 
     def mkstemp(self, suffix='', prefix='tmp', dir=None, text=False):
         fd, name = tempfile.mkstemp(suffix=suffix, prefix=prefix,
                                     dir=self.join(dir), text=text)
         dname, fname = util.split(name)
         if dir:
             return fd, os.path.join(dir, fname)
         else:
             return fd, fname
 
     def readdir(self, path=None, stat=None, skip=None):
         return osutil.listdir(self.join(path), stat, skip)
 
     def readlock(self, path):
         return util.readlock(self.join(path))
 
     def rename(self, src, dst):
         return util.rename(self.join(src), self.join(dst))
 
     def readlink(self, path):
         return os.readlink(self.join(path))
 
     def setflags(self, path, l, x):
         return util.setflags(self.join(path), l, x)
 
     def stat(self, path=None):
         return os.stat(self.join(path))
 
     def unlink(self, path=None):
         return util.unlink(self.join(path))
 
     def unlinkpath(self, path=None, ignoremissing=False):
         return util.unlinkpath(self.join(path), ignoremissing)
 
     def utime(self, path=None, t=None):
         return os.utime(self.join(path), t)
 
 class vfs(abstractvfs):
     '''Operate files relative to a base directory
 
     This class is used to hide the details of COW semantics and
     remote file access from higher level code.
     '''
     def __init__(self, base, audit=True, expandpath=False, realpath=False):
         if expandpath:
             base = util.expandpath(base)
         if realpath:
             base = os.path.realpath(base)
         self.base = base
         self._setmustaudit(audit)
         self.createmode = None
         self._trustnlink = None
 
     def _getmustaudit(self):
         return self._audit
 
     def _setmustaudit(self, onoff):
         self._audit = onoff
         if onoff:
             self.audit = pathutil.pathauditor(self.base)
         else:
             self.audit = util.always
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
     @util.propertycache
     def _cansymlink(self):
         return util.checklink(self.base)
 
     @util.propertycache
     def _chmod(self):
         return util.checkexec(self.base)
 
     def _fixfilemode(self, name):
         if self.createmode is None or not self._chmod:
             return
         os.chmod(name, self.createmode & 0666)
 
     def __call__(self, path, mode="r", text=False, atomictemp=False,
                  notindexed=False):
         '''Open ``path`` file, which is relative to vfs root.
 
         Newly created directories are marked as "not to be indexed by
         the content indexing service", if ``notindexed`` is specified
         for "write" mode access.
         '''
         if self._audit:
             r = util.checkosfilename(path)
             if r:
                 raise util.Abort("%s: %r" % (r, path))
         self.audit(path)
         f = self.join(path)
 
         if not text and "b" not in mode:
             mode += "b" # for that other OS
 
         nlink = -1
         if mode not in ('r', 'rb'):
             dirname, basename = util.split(f)
             # If basename is empty, then the path is malformed because it points
             # to a directory. Let the posixfile() call below raise IOError.
             if basename:
                 if atomictemp:
                     util.ensuredirs(dirname, self.createmode, notindexed)
                     return util.atomictempfile(f, mode, self.createmode)
                 try:
                     if 'w' in mode:
                         util.unlink(f)
                         nlink = 0
                     else:
                         # nlinks() may behave differently for files on Windows
                         # shares if the file is open.
                         fd = util.posixfile(f)
                         nlink = util.nlinks(f)
                         if nlink < 1:
                             nlink = 2 # force mktempcopy (issue1922)
                         fd.close()
                 except (OSError, IOError), e:
                     if e.errno != errno.ENOENT:
                         raise
                     nlink = 0
                     util.ensuredirs(dirname, self.createmode, notindexed)
                 if nlink > 0:
                     if self._trustnlink is None:
                         self._trustnlink = nlink > 1 or util.checknlink(f)
                     if nlink > 1 or not self._trustnlink:
                         util.rename(util.mktempcopy(f), f)
         fp = util.posixfile(f, mode)
         if nlink == 0:
             self._fixfilemode(f)
         return fp
 
     def symlink(self, src, dst):
         self.audit(dst)
         linkname = self.join(dst)
         try:
             os.unlink(linkname)
         except OSError:
             pass
 
         util.ensuredirs(os.path.dirname(linkname), self.createmode)
 
         if self._cansymlink:
             try:
                 os.symlink(src, linkname)
             except OSError, err:
                 raise OSError(err.errno, _('could not symlink to %r: %s') %
                               (src, err.strerror), linkname)
         else:
             self.write(dst, src)
 
     def join(self, path):
         if path:
             return os.path.join(self.base, path)
         else:
             return self.base
 
 opener = vfs
 
 class auditvfs(object):
     def __init__(self, vfs):
         self.vfs = vfs
 
     def _getmustaudit(self):
         return self.vfs.mustaudit
 
     def _setmustaudit(self, onoff):
         self.vfs.mustaudit = onoff
 
     mustaudit = property(_getmustaudit, _setmustaudit)
 
 class filtervfs(abstractvfs, auditvfs):
     '''Wrapper vfs for filtering filenames with a function.'''
 
     def __init__(self, vfs, filter):
         auditvfs.__init__(self, vfs)
         self._filter = filter
 
     def __call__(self, path, *args, **kwargs):
         return self.vfs(self._filter(path), *args, **kwargs)
 
     def join(self, path):
         if path:
             return self.vfs.join(self._filter(path))
         else:
             return self.vfs.join(path)
 
 filteropener = filtervfs
 
 class readonlyvfs(abstractvfs, auditvfs):
     '''Wrapper vfs preventing any writing.'''
 
     def __init__(self, vfs):
         auditvfs.__init__(self, vfs)
 
     def __call__(self, path, mode='r', *args, **kw):
         if mode not in ('r', 'rb'):
             raise util.Abort('this vfs is read only')
         return self.vfs(path, mode, *args, **kw)
 
 
 def walkrepos(path, followsym=False, seen_dirs=None, recurse=False):
     '''yield every hg repository under path, always recursively.
     The recurse flag will only control recursion into repo working dirs'''
     def errhandler(err):
         if err.filename == path:
             raise err
     samestat = getattr(os.path, 'samestat', None)
     if followsym and samestat is not None:
         def adddir(dirlst, dirname):
             match = False
             dirstat = os.stat(dirname)
             for lstdirstat in dirlst:
                 if samestat(dirstat, lstdirstat):
                     match = True
                     break
             if not match:
                 dirlst.append(dirstat)
             return not match
     else:
         followsym = False
 
     if (seen_dirs is None) and followsym:
         seen_dirs = []
         adddir(seen_dirs, path)
     for root, dirs, files in os.walk(path, topdown=True, onerror=errhandler):
         dirs.sort()
         if '.hg' in dirs:
             yield root # found a repository
             qroot = os.path.join(root, '.hg', 'patches')
             if os.path.isdir(os.path.join(qroot, '.hg')):
                 yield qroot # we have a patch queue repo here
             if recurse:
                 # avoid recursing inside the .hg directory
                 dirs.remove('.hg')
             else:
                 dirs[:] = [] # don't descend further
         elif followsym:
             newdirs = []
             for d in dirs:
                 fname = os.path.join(root, d)
                 if adddir(seen_dirs, fname):
                     if os.path.islink(fname):
                         for hgname in walkrepos(fname, True, seen_dirs):
                             yield hgname
                     else:
                         newdirs.append(d)
             dirs[:] = newdirs
 
 def osrcpath():
     '''return default os-specific hgrc search path'''
     path = []
     defaultpath = os.path.join(util.datapath, 'default.d')
     if os.path.isdir(defaultpath):
         for f, kind in osutil.listdir(defaultpath):
             if f.endswith('.rc'):
                 path.append(os.path.join(defaultpath, f))
     path.extend(systemrcpath())
     path.extend(userrcpath())
     path = [os.path.normpath(f) for f in path]
     return path
 
 _rcpath = None
 
 def rcpath():
     '''return hgrc search path. if env var HGRCPATH is set, use it.
     for each item in path, if directory, use files ending in .rc,
     else use item.
     make HGRCPATH empty to only look in .hg/hgrc of current repo.
     if no HGRCPATH, use default os-specific path.'''
     global _rcpath
     if _rcpath is None:
         if 'HGRCPATH' in os.environ:
             _rcpath = []
             for p in os.environ['HGRCPATH'].split(os.pathsep):
                 if not p:
                     continue
                 p = util.expandpath(p)
                 if os.path.isdir(p):
                     for f, kind in osutil.listdir(p):
                         if f.endswith('.rc'):
                             _rcpath.append(os.path.join(p, f))
                 else:
                     _rcpath.append(p)
         else:
             _rcpath = osrcpath()
     return _rcpath
 
 def revsingle(repo, revspec, default='.'):
     if not revspec and revspec != 0:
         return repo[default]
 
     l = revrange(repo, [revspec])
     if not l:
         raise util.Abort(_('empty revision set'))
     return repo[l.last()]
 
 def revpair(repo, revs):
     if not revs:
         return repo.dirstate.p1(), None
 
     l = revrange(repo, revs)
 
     if not l:
         first = second = None
     elif l.isascending():
         first = l.min()
         second = l.max()
     elif l.isdescending():
         first = l.max()
         second = l.min()
     else:
         first = l.first()
         second = l.last()
 
     if first is None:
         raise util.Abort(_('empty revision range'))
 
     if first == second and len(revs) == 1 and _revrangesep not in revs[0]:
         return repo.lookup(first), None
 
     return repo.lookup(first), repo.lookup(second)
 
 _revrangesep = ':'
 
 def revrange(repo, revs):
     """Yield revision as strings from a list of revision specifications."""
 
     def revfix(repo, val, defval):
         if not val and val != 0 and defval is not None:
             return defval
         return repo[val].rev()
 
     seen, l = set(), revset.baseset([])
     for spec in revs:
         if l and not seen:
             seen = set(l)
         # attempt to parse old-style ranges first to deal with
         # things like old-tag which contain query metacharacters
         try:
             if isinstance(spec, int):
                 seen.add(spec)
                 l = l + revset.baseset([spec])
                 continue
 
             if _revrangesep in spec:
                 start, end = spec.split(_revrangesep, 1)
                 start = revfix(repo, start, 0)
                 end = revfix(repo, end, len(repo) - 1)
                 if end == nullrev and start < 0:
                     start = nullrev
                 rangeiter = repo.changelog.revs(start, end)
                 if not seen and not l:
                     # by far the most common case: revs = ["-1:0"]
                     l = revset.baseset(rangeiter)
                     # defer syncing seen until next iteration
                     continue
                 newrevs = set(rangeiter)
                 if seen:
                     newrevs.difference_update(seen)
                     seen.update(newrevs)
                 else:
                     seen = newrevs
                 l = l + revset.baseset(sorted(newrevs, reverse=start > end))
                 continue
             elif spec and spec in repo: # single unquoted rev
                 rev = revfix(repo, spec, None)
                 if rev in seen:
                     continue
                 seen.add(rev)
                 l = l + revset.baseset([rev])
                 continue
         except error.RepoLookupError:
             pass
 
         # fall through to new-style queries if old-style fails
         m = revset.match(repo.ui, spec, repo)
         if seen or l:
             dl = [r for r in m(repo, revset.spanset(repo)) if r not in seen]
             l = l + revset.baseset(dl)
             seen.update(dl)
         else:
             l = m(repo, revset.spanset(repo))
 
     return l
 
 def expandpats(pats):
     '''Expand bare globs when running on windows.
     On posix we assume it already has already been done by sh.'''
     if not util.expandglobs:
         return list(pats)
     ret = []
     for kindpat in pats:
         kind, pat = matchmod._patsplit(kindpat, None)
         if kind is None:
             try:
                 globbed = glob.glob(pat)
             except re.error:
                 globbed = [pat]
             if globbed:
                 ret.extend(globbed)
                 continue
         ret.append(kindpat)
     return ret
 
 def matchandpats(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     '''Return a matcher and the patterns that were used.
     The matcher will warn about bad matches.'''
     if pats == ("",):
         pats = []
     if not globbed and default == 'relpath':
         pats = expandpats(pats or [])
 
     m = ctx.match(pats, opts.get('include'), opts.get('exclude'),
                          default)
     def badfn(f, msg):
         ctx._repo.ui.warn("%s: %s\n" % (m.rel(f), msg))
     m.bad = badfn
     return m, pats
 
 def match(ctx, pats=[], opts={}, globbed=False, default='relpath'):
     '''Return a matcher that will warn about bad matches.'''
     return matchandpats(ctx, pats, opts, globbed, default)[0]
 
 def matchall(repo):
     '''Return a matcher that will efficiently match everything.'''
     return matchmod.always(repo.root, repo.getcwd())
 
 def matchfiles(repo, files):
     '''Return a matcher that will efficiently match exactly these files.'''
     return matchmod.exact(repo.root, repo.getcwd(), files)
 
 def addremove(repo, matcher, prefix, opts={}, dry_run=None, similarity=None):
     m = matcher
     if dry_run is None:
         dry_run = opts.get('dry_run')
     if similarity is None:
         similarity = float(opts.get('similarity') or 0)
 
     ret = 0
     join = lambda f: os.path.join(prefix, f)
 
     def matchessubrepo(matcher, subpath):
         if matcher.exact(subpath):
             return True
         for f in matcher.files():
             if f.startswith(subpath):
                 return True
         return False
 
     wctx = repo[None]
     for subpath in sorted(wctx.substate):
         if opts.get('subrepos') or matchessubrepo(m, subpath):
             sub = wctx.sub(subpath)
             try:
                 submatch = matchmod.narrowmatcher(subpath, m)
                 if sub.addremove(submatch, prefix, opts, dry_run, similarity):
                     ret = 1
             except error.LookupError:
                 repo.ui.status(_("skipping missing subrepository: %s\n")
                                  % join(subpath))
 
     rejected = []
     origbad = m.bad
     def badfn(f, msg):
         if f in m.files():
             origbad(f, msg)
         rejected.append(f)
 
     m.bad = badfn
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
     m.bad = origbad
 
     unknownset = set(unknown + forgotten)
     toprint = unknownset.copy()
     toprint.update(deleted)
     for abs in sorted(toprint):
         if repo.ui.verbose or not m.exact(abs):
             if abs in unknownset:
                 status = _('adding %s\n') % m.uipath(join(abs))
             else:
                 status = _('removing %s\n') % m.uipath(join(abs))
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     if not dry_run:
         _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return ret
 
 def marktouched(repo, files, similarity=0.0):
     '''Assert that files have somehow been operated upon. files are relative to
     the repo root.'''
     m = matchfiles(repo, files)
     rejected = []
     m.bad = lambda x, y: rejected.append(x)
 
     added, unknown, deleted, removed, forgotten = _interestingfiles(repo, m)
 
     if repo.ui.verbose:
         unknownset = set(unknown + forgotten)
         toprint = unknownset.copy()
         toprint.update(deleted)
         for abs in sorted(toprint):
             if abs in unknownset:
                 status = _('adding %s\n') % abs
             else:
                 status = _('removing %s\n') % abs
             repo.ui.status(status)
 
     renames = _findrenames(repo, m, added + unknown, removed + deleted,
                            similarity)
 
     _markchanges(repo, unknown + forgotten, deleted, renames)
 
     for f in rejected:
         if f in m.files():
             return 1
     return 0
 
 def _interestingfiles(repo, matcher):
     '''Walk dirstate with matcher, looking for files that addremove would care
     about.
 
     This is different from dirstate.status because it doesn't care about
     whether files are modified or clean.'''
     added, unknown, deleted, removed, forgotten = [], [], [], [], []
     audit_path = pathutil.pathauditor(repo.root)
 
     ctx = repo[None]
     dirstate = repo.dirstate
     walkresults = dirstate.walk(matcher, sorted(ctx.substate), True, False,
                                 full=False)
     for abs, st in walkresults.iteritems():
         dstate = dirstate[abs]
         if dstate == '?' and audit_path.check(abs):
             unknown.append(abs)
         elif dstate != 'r' and not st:
             deleted.append(abs)
         elif dstate == 'r' and st:
             forgotten.append(abs)
         # for finding renames
         elif dstate == 'r' and not st:
             removed.append(abs)
         elif dstate == 'a':
             added.append(abs)
 
     return added, unknown, deleted, removed, forgotten
 
 def _findrenames(repo, matcher, added, removed, similarity):
     '''Find renames from removed files to added ones.'''
     renames = {}
     if similarity > 0:
         for old, new, score in similar.findrenames(repo, added, removed,
                                                    similarity):
             if (repo.ui.verbose or not matcher.exact(old)
                 or not matcher.exact(new)):
                 repo.ui.status(_('recording removal of %s as rename to %s '
                                  '(%d%% similar)\n') %
                                (matcher.rel(old), matcher.rel(new),
                                 score * 100))
             renames[new] = old
     return renames
 
 def _markchanges(repo, unknown, deleted, renames):
     '''Marks the files in unknown as added, the files in deleted as removed,
     and the files in renames as copied.'''
     wctx = repo[None]
     wlock = repo.wlock()
     try:
         wctx.forget(deleted)
         wctx.add(unknown)
         for new, old in renames.iteritems():
             wctx.copy(old, new)
     finally:
         wlock.release()
 
 def dirstatecopy(ui, repo, wctx, src, dst, dryrun=False, cwd=None):
     """Update the dirstate to reflect the intent of copying src to dst. For
     different reasons it might not end with dst being marked as copied from src.
     """
     origsrc = repo.dirstate.copied(src) or src
     if dst == origsrc: # copying back a copy?
         if repo.dirstate[dst] not in 'mn' and not dryrun:
             repo.dirstate.normallookup(dst)
     else:
         if repo.dirstate[origsrc] == 'a' and origsrc == src:
             if not ui.quiet:
                 ui.warn(_("%s has not been committed yet, so no copy "
                           "data will be stored for %s.\n")
                         % (repo.pathto(origsrc, cwd), repo.pathto(dst, cwd)))
             if repo.dirstate[dst] in '?r' and not dryrun:
                 wctx.add([dst])
         elif not dryrun:
             wctx.copy(origsrc, dst)
 
 def readrequires(opener, supported):
     '''Reads and parses .hg/requires and checks if all entries found
     are in the list of supported features.'''
     requirements = set(opener.read("requires").splitlines())
     missings = []
     for r in requirements:
         if r not in supported:
             if not r or not r[0].isalnum():
                 raise error.RequirementError(_(".hg/requires file is corrupt"))
             missings.append(r)
     missings.sort()
     if missings:
         raise error.RequirementError(
             _("repository requires features unknown to this Mercurial: %s")
             % " ".join(missings),
             hint=_("see http://mercurial.selenic.com/wiki/MissingRequirement"
                    " for more information"))
     return requirements
 
 class filecachesubentry(object):
     def __init__(self, path, stat):
         self.path = path
         self.cachestat = None
         self._cacheable = None
 
         if stat:
             self.cachestat = filecachesubentry.stat(self.path)
 
             if self.cachestat:
                 self._cacheable = self.cachestat.cacheable()
             else:
                 # None means we don't know yet
                 self._cacheable = None
 
     def refresh(self):
         if self.cacheable():
             self.cachestat = filecachesubentry.stat(self.path)
 
     def cacheable(self):
         if self._cacheable is not None:
             return self._cacheable
 
         # we don't know yet, assume it is for now
         return True
 
     def changed(self):
         # no point in going further if we can't cache it
         if not self.cacheable():
             return True
 
         newstat = filecachesubentry.stat(self.path)
 
         # we may not know if it's cacheable yet, check again now
         if newstat and self._cacheable is None:
             self._cacheable = newstat.cacheable()
 
             # check again
             if not self._cacheable:
                 return True
 
         if self.cachestat != newstat:
             self.cachestat = newstat
             return True
         else:
             return False
 
     @staticmethod
     def stat(path):
         try:
             return util.cachestat(path)
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
 
 class filecacheentry(object):
     def __init__(self, paths, stat=True):
         self._entries = []
         for path in paths:
             self._entries.append(filecachesubentry(path, stat))
 
     def changed(self):
         '''true if any entry has changed'''
         for entry in self._entries:
             if entry.changed():
                 return True
         return False
 
     def refresh(self):
         for entry in self._entries:
             entry.refresh()
 
 class filecache(object):
     '''A property like decorator that tracks files under .hg/ for updates.
 
     Records stat info when called in _filecache.
 
     On subsequent calls, compares old stat info with new info, and recreates the
     object when any of the files changes, updating the new stat info in
     _filecache.
 
     Mercurial either atomic renames or appends for files under .hg,
     so to ensure the cache is reliable we need the filesystem to be able
     to tell us if a file has been replaced. If it can't, we fallback to
     recreating the object on every call (essentially the same behaviour as
     propertycache).
 
     '''
     def __init__(self, *paths):
         self.paths = paths
 
     def join(self, obj, fname):
         """Used to compute the runtime path of a cached file.
 
         Users should subclass filecache and provide their own version of this
         function to call the appropriate join function on 'obj' (an instance
         of the class that its member function was decorated).
         """
         return obj.join(fname)
 
     def __call__(self, func):
         self.func = func
         self.name = func.__name__
         return self
 
     def __get__(self, obj, type=None):
         # do we need to check if the file changed?
         if self.name in obj.__dict__:
             assert self.name in obj._filecache, self.name
             return obj.__dict__[self.name]
 
         entry = obj._filecache.get(self.name)
 
         if entry:
             if entry.changed():
                 entry.obj = self.func(obj)
         else:
             paths = [self.join(obj, path) for path in self.paths]
 
             # We stat -before- creating the object so our cache doesn't lie if
             # a writer modified between the time we read and stat
             entry = filecacheentry(paths, True)
             entry.obj = self.func(obj)
 
             obj._filecache[self.name] = entry
 
         obj.__dict__[self.name] = entry.obj
         return entry.obj
 
     def __set__(self, obj, value):
         if self.name not in obj._filecache:
             # we add an entry for the missing value because X in __dict__
             # implies X in _filecache
             paths = [self.join(obj, path) for path in self.paths]
             ce = filecacheentry(paths, False)
             obj._filecache[self.name] = ce
         else:
             ce = obj._filecache[self.name]
 
         ce.obj = value # update cached copy
         obj.__dict__[self.name] = value # update copy returned by obj.x
 
     def __delete__(self, obj):
         try:
             del obj.__dict__[self.name]
         except KeyError:
             raise AttributeError(self.name)
 
 class dirs(object):
     '''a multiset of directory names from a dirstate or manifest'''
 
     def __init__(self, map, skip=None):
         self._dirs = {}
         addpath = self.addpath
         if util.safehasattr(map, 'iteritems') and skip is not None:
             for f, s in map.iteritems():
                 if s[0] != skip:
                     addpath(f)
         else:
             for f in map:
                 addpath(f)
 
     def addpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if base in dirs:
                 dirs[base] += 1
                 return
             dirs[base] = 1
 
     def delpath(self, path):
         dirs = self._dirs
         for base in finddirs(path):
             if dirs[base] > 1:
                 dirs[base] -= 1
                 return
             del dirs[base]
 
     def __iter__(self):
         return self._dirs.iterkeys()
 
     def __contains__(self, d):
         return d in self._dirs
 
 if util.safehasattr(parsers, 'dirs'):
     dirs = parsers.dirs
 
 def finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)

mercurial/transaction.py

@@ -1,498 +1,498
 # transaction.py - simple journaling scheme for mercurial
 #
 # This transaction scheme is intended to gracefully handle program
 # errors and interruptions. More serious failures like system crashes
 # can be recovered with an fsck-like tool. As the whole repository is
 # effectively log-structured, this should amount to simply truncating
 # anything that isn't referenced in the changelog.
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import os
 import errno
 import error, util
 
 version = 2
 
 def active(func):
     def _active(self, *args, **kwds):
         if self.count == 0:
             raise error.Abort(_(
                 'cannot use transaction when it is already committed/aborted'))
         return func(self, *args, **kwds)
     return _active
 
 def _playback(journal, report, opener, vfsmap, entries, backupentries,
               unlink=True):
     for f, o, _ignore in entries:
         if o or not unlink:
             try:
                 fp = opener(f, 'a')
                 fp.truncate(o)
                 fp.close()
             except IOError:
                 report(_("failed to truncate %s\n") % f)
                 raise
         else:
             try:
                 opener.unlink(f)
             except (IOError, OSError), inst:
                 if inst.errno != errno.ENOENT:
                     raise
 
     backupfiles = []
     for l, f, b, c in backupentries:
         if l not in vfsmap and c:
             report("couldn't handle %s: unknown cache location %s\n"
                         % (b, l))
         vfs = vfsmap[l]
         try:
             if f and b:
                 filepath = vfs.join(f)
                 backuppath = vfs.join(b)
                 try:
                     util.copyfile(backuppath, filepath)
                     backupfiles.append(b)
                 except IOError:
                     report(_("failed to recover %s\n") % f)
             else:
                 target = f or b
                 try:
                     vfs.unlink(target)
                 except (IOError, OSError), inst:
                     if inst.errno != errno.ENOENT:
                         raise
         except (IOError, OSError, util.Abort), inst:
             if not c:
                 raise
 
     opener.unlink(journal)
     backuppath = "%s.backupfiles" % journal
     if opener.exists(backuppath):
         opener.unlink(backuppath)
     try:
         for f in backupfiles:
             if opener.exists(f):
                 opener.unlink(f)
     except (IOError, OSError, util.Abort), inst:
         # only pure backup file remains, it is sage to ignore any error
         pass
 
 class transaction(object):
     def __init__(self, report, opener, vfsmap, journal, after=None,
                  createmode=None):
         """Begin a new transaction
 
         Begins a new transaction that allows rolling back writes in the event of
         an exception.
 
         * `after`: called after the transaction has been committed
         * `createmode`: the mode of the journal file that will be created
         """
         self.count = 1
         self.usages = 1
         self.report = report
         # a vfs to the store content
         self.opener = opener
         # a map to access file in various {location -> vfs}
         vfsmap = vfsmap.copy()
         vfsmap[''] = opener  # set default value
         self._vfsmap = vfsmap
         self.after = after
         self.entries = []
         self.map = {}
         self.journal = journal
         self._queue = []
         # a dict of arguments to be passed to hooks
         self.hookargs = {}
         self.file = opener.open(self.journal, "w")
 
         # a list of ('location', 'path', 'backuppath', cache) entries.
         # - if 'backuppath' is empty, no file existed at backup time
         # - if 'path' is empty, this is a temporary transaction file
         # - if 'location' is not empty, the path is outside main opener reach.
         #   use 'location' value as a key in a vfsmap to find the right 'vfs'
         # (cache is currently unused)
         self._backupentries = []
         self._backupmap = {}
         self._backupjournal = "%s.backupfiles" % journal
         self._backupsfile = opener.open(self._backupjournal, 'w')
         self._backupsfile.write('%d\n' % version)
 
         if createmode is not None:
             opener.chmod(self.journal, createmode & 0666)
             opener.chmod(self._backupjournal, createmode & 0666)
 
         # hold file generations to be performed on commit
         self._filegenerators = {}
         # hold callback to write pending data for hooks
         self._pendingcallback = {}
         # True is any pending data have been written ever
         self._anypending = False
         # holds callback to call when writing the transaction
         self._finalizecallback = {}
         # hold callback for post transaction close
         self._postclosecallback = {}
 
     def __del__(self):
         if self.journal:
             self._abort()
 
     @active
     def startgroup(self):
         """delay registration of file entry
 
         This is used by strip to delay vision of strip offset. The transaction
         sees either none or all of the strip actions to be done."""
         self._queue.append([])
 
     @active
     def endgroup(self):
         """apply delayed registration of file entry.
 
         This is used by strip to delay vision of strip offset. The transaction
         sees either none or all of the strip actions to be done."""
         q = self._queue.pop()
         for f, o, data in q:
             self._addentry(f, o, data)
 
     @active
     def add(self, file, offset, data=None):
         """record the state of an append-only file before update"""
         if file in self.map or file in self._backupmap:
             return
         if self._queue:
             self._queue[-1].append((file, offset, data))
             return
 
         self._addentry(file, offset, data)
 
     def _addentry(self, file, offset, data):
         """add a append-only entry to memory and on-disk state"""
         if file in self.map or file in self._backupmap:
             return
         self.entries.append((file, offset, data))
         self.map[file] = len(self.entries) - 1
         # add enough data to the journal to do the truncate
         self.file.write("%s\0%d\n" % (file, offset))
         self.file.flush()
 
     @active
     def addbackup(self, file, hardlink=True, location=''):
         """Adds a backup of the file to the transaction
 
         Calling addbackup() creates a hardlink backup of the specified file
         that is used to recover the file in the event of the transaction
         aborting.
 
         * `file`: the file path, relative to .hg/store
         * `hardlink`: use a hardlink to quickly create the backup
         """
         if self._queue:
             msg = 'cannot use transaction.addbackup inside "group"'
             raise RuntimeError(msg)
 
         if file in self.map or file in self._backupmap:
             return
         dirname, filename = os.path.split(file)
         backupfilename = "%s.backup.%s" % (self.journal, filename)
-        backupfile = os.path.join(dirname, backupfilename)
         vfs = self._vfsmap[location]
+        backupfile = vfs.reljoin(dirname, backupfilename)
         if vfs.exists(file):
             filepath = vfs.join(file)
             backuppath = vfs.join(backupfile)
             util.copyfiles(filepath, backuppath, hardlink=hardlink)
         else:
             backupfile = ''
 
         self._addbackupentry((location, file, backupfile, False))
 
     def _addbackupentry(self, entry):
         """register a new backup entry and write it to disk"""
         self._backupentries.append(entry)
         self._backupmap[file] = len(self._backupentries) - 1
         self._backupsfile.write("%s\0%s\0%s\0%d\n" % entry)
         self._backupsfile.flush()
 
     @active
     def registertmp(self, tmpfile, location=''):
         """register a temporary transaction file
 
         Such files will be deleted when the transaction exits (on both
         failure and success).
         """
         self._addbackupentry((location, '', tmpfile, False))
 
     @active
     def addfilegenerator(self, genid, filenames, genfunc, order=0,
                          location=''):
         """add a function to generates some files at transaction commit
 
         The `genfunc` argument is a function capable of generating proper
         content of each entry in the `filename` tuple.
 
         At transaction close time, `genfunc` will be called with one file
         object argument per entries in `filenames`.
 
         The transaction itself is responsible for the backup, creation and
         final write of such file.
 
         The `genid` argument is used to ensure the same set of file is only
         generated once. Call to `addfilegenerator` for a `genid` already
         present will overwrite the old entry.
 
         The `order` argument may be used to control the order in which multiple
         generator will be executed.
 
         The `location` arguments may be used to indicate the files are located
         outside of the the standard directory for transaction. It should match
         one of the key of the `transaction.vfsmap` dictionary.
         """
         # For now, we are unable to do proper backup and restore of custom vfs
         # but for bookmarks that are handled outside this mechanism.
         self._filegenerators[genid] = (order, filenames, genfunc, location)
 
     def _generatefiles(self, suffix=''):
         # write files registered for generation
         any = False
         for entry in sorted(self._filegenerators.values()):
             any = True
             order, filenames, genfunc, location = entry
             vfs = self._vfsmap[location]
             files = []
             try:
                 for name in filenames:
                     name += suffix
                     if suffix:
                         self.registertmp(name, location=location)
                     else:
                         self.addbackup(name, location=location)
                     files.append(vfs(name, 'w', atomictemp=True))
                 genfunc(*files)
             finally:
                 for f in files:
                     f.close()
         return any
 
     @active
     def find(self, file):
         if file in self.map:
             return self.entries[self.map[file]]
         if file in self._backupmap:
             return self._backupentries[self._backupmap[file]]
         return None
 
     @active
     def replace(self, file, offset, data=None):
         '''
         replace can only replace already committed entries
         that are not pending in the queue
         '''
 
         if file not in self.map:
             raise KeyError(file)
         index = self.map[file]
         self.entries[index] = (file, offset, data)
         self.file.write("%s\0%d\n" % (file, offset))
         self.file.flush()
 
     @active
     def nest(self):
         self.count += 1
         self.usages += 1
         return self
 
     def release(self):
         if self.count > 0:
             self.usages -= 1
         # if the transaction scopes are left without being closed, fail
         if self.count > 0 and self.usages == 0:
             self._abort()
 
     def running(self):
         return self.count > 0
 
     def addpending(self, category, callback):
         """add a callback to be called when the transaction is pending
 
         The transaction will be given as callback's first argument.
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._pendingcallback[category] = callback
 
     @active
     def writepending(self):
         '''write pending file to temporary version
 
         This is used to allow hooks to view a transaction before commit'''
         categories = sorted(self._pendingcallback)
         for cat in categories:
             # remove callback since the data will have been flushed
             any = self._pendingcallback.pop(cat)(self)
             self._anypending = self._anypending or any
         self._anypending |= self._generatefiles(suffix='.pending')
         return self._anypending
 
     @active
     def addfinalize(self, category, callback):
         """add a callback to be called when the transaction is closed
 
         The transaction will be given as callback's first argument.
 
         Category is a unique identifier to allow overwriting old callbacks with
         newer callbacks.
         """
         self._finalizecallback[category] = callback
 
     @active
     def addpostclose(self, category, callback):
         """add a callback to be called after the transaction is closed
 
         The transaction will be given as callback's first argument.
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._postclosecallback[category] = callback
 
     @active
     def close(self):
         '''commit the transaction'''
         if self.count == 1:
             self._generatefiles()
             categories = sorted(self._finalizecallback)
             for cat in categories:
                 self._finalizecallback[cat](self)
 
         self.count -= 1
         if self.count != 0:
             return
         self.file.close()
         self._backupsfile.close()
         # cleanup temporary files
         for l, f, b, c in self._backupentries:
             if l not in self._vfsmap and c:
                 self.report("couldn't remote %s: unknown cache location %s\n"
                             % (b, l))
                 continue
             vfs = self._vfsmap[l]
             if not f and b and vfs.exists(b):
                 try:
                     vfs.unlink(b)
                 except (IOError, OSError, util.Abort), inst:
                     if not c:
                         raise
                     # Abort may be raise by read only opener
                     self.report("couldn't remote %s: %s\n"
                                 % (vfs.join(b), inst))
         self.entries = []
         if self.after:
             self.after()
         if self.opener.isfile(self.journal):
             self.opener.unlink(self.journal)
         if self.opener.isfile(self._backupjournal):
             self.opener.unlink(self._backupjournal)
             for _l, _f, b, c in self._backupentries:
                 if l not in self._vfsmap and c:
                     self.report("couldn't remote %s: unknown cache location"
                                 "%s\n" % (b, l))
                     continue
                 vfs = self._vfsmap[l]
                 if b and vfs.exists(b):
                     try:
                         vfs.unlink(b)
                     except (IOError, OSError, util.Abort), inst:
                         if not c:
                             raise
                         # Abort may be raise by read only opener
                         self.report("couldn't remote %s: %s\n"
                                     % (vfs.join(b), inst))
         self._backupentries = []
         self.journal = None
         # run post close action
         categories = sorted(self._postclosecallback)
         for cat in categories:
             self._postclosecallback[cat](self)
 
     @active
     def abort(self):
         '''abort the transaction (generally called on error, or when the
         transaction is not explicitly committed before going out of
         scope)'''
         self._abort()
 
     def _abort(self):
         self.count = 0
         self.usages = 0
         self.file.close()
         self._backupsfile.close()
 
         try:
             if not self.entries and not self._backupentries:
                 if self.journal:
                     self.opener.unlink(self.journal)
                 if self._backupjournal:
                     self.opener.unlink(self._backupjournal)
                 return
 
             self.report(_("transaction abort!\n"))
 
             try:
                 _playback(self.journal, self.report, self.opener, self._vfsmap,
                           self.entries, self._backupentries, False)
                 self.report(_("rollback completed\n"))
             except Exception:
                 self.report(_("rollback failed - please run hg recover\n"))
         finally:
             self.journal = None
 
 
 def rollback(opener, vfsmap, file, report):
     """Rolls back the transaction contained in the given file
 
     Reads the entries in the specified file, and the corresponding
     '*.backupfiles' file, to recover from an incomplete transaction.
 
     * `file`: a file containing a list of entries, specifying where
     to truncate each file.  The file should contain a list of
     file\0offset pairs, delimited by newlines. The corresponding
     '*.backupfiles' file should contain a list of file\0backupfile
     pairs, delimited by \0.
     """
     entries = []
     backupentries = []
 
     fp = opener.open(file)
     lines = fp.readlines()
     fp.close()
     for l in lines:
         try:
             f, o = l.split('\0')
             entries.append((f, int(o), None))
         except ValueError:
             report(_("couldn't read journal entry %r!\n") % l)
 
     backupjournal = "%s.backupfiles" % file
     if opener.exists(backupjournal):
         fp = opener.open(backupjournal)
         lines = fp.readlines()
         if lines:
             ver = lines[0][:-1]
             if ver == str(version):
                 for line in lines[1:]:
                     if line:
                         # Shave off the trailing newline
                         line = line[:-1]
                         l, f, b, c = line.split('\0')
                         backupentries.append((l, f, b, bool(c)))
             else:
                 report(_("journal was created by a different version of "
                          "Mercurial"))
 
     _playback(file, report, opener, vfsmap, entries, backupentries)