# dirstate.py - working directory tracking for mercurial

#

# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import collections

import contextlib

import errno

import os

import stat

from .i18n import _

from .node import nullid

from . import (

    encoding,

    error,

    match as matchmod,

    pathutil,

    policy,

    pycompat,

    scmutil,

    txnutil,

    util,

)

parsers = policy.importmod(r'parsers')

propertycache = util.propertycache

filecache = scmutil.filecache

_rangemask = 0x7fffffff

dirstatetuple = parsers.dirstatetuple

class repocache(filecache):

    """filecache for files in .hg/"""

    def join(self, obj, fname):

        return obj._opener.join(fname)

class rootcache(filecache):

    """filecache for files in the repository root"""

    def join(self, obj, fname):

        return obj._join(fname)

def _getfsnow(vfs):

    '''Get "now" timestamp on filesystem'''

    tmpfd, tmpname = vfs.mkstemp()

    try:

        return os.fstat(tmpfd).st_mtime

    finally:

        os.close(tmpfd)

        vfs.unlink(tmpname)

class dirstate(object):

    def __init__(self, opener, ui, root, validate, sparsematchfn):

        '''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._sparsematchfn = sparsematchfn

        # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is

        # UNC path pointing to root share (issue4557)

        self._rootdir = pathutil.normasprefix(root)

        self._dirty = False

        self._dirtypl = False

        self._lastnormaltime = 0

        self._ui = ui

        self._filecache = {}

        self._parentwriters = 0

        self._filename = 'dirstate'

        self._pendingfilename = '%s.pending' % self._filename

        self._plchangecallbacks = {}

        self._origpl = None

        self._updatedfiles = set()

    @contextlib.contextmanager

    def parentchange(self):

        '''Context manager for handling dirstate parents.

        If an exception occurs in the scope of the context manager,

        the incoherent dirstate won't be written when wlock is

        released.

        '''

        self._parentwriters += 1

        yield

        # Typically we want the "undo" step of a context manager in a

        # finally block so it happens even when an exception

        # occurs. In this case, however, we only want to decrement

        # parentwriters if the code in the with statement exits

        # normally, so we don't have a try/finally here on purpose.

        self._parentwriters -= 1

    def beginparentchange(self):

        '''Marks the beginning of a set of changes that involve changing

        the dirstate parents. If there is an exception during this time,

        the dirstate will not be written when the wlock is released. This

        prevents writing an incoherent dirstate where the parent doesn't

        match the contents.

        '''

        self._ui.deprecwarn('beginparentchange is obsoleted by the '

                            'parentchange context manager.', '4.3')

        self._parentwriters += 1

    def endparentchange(self):

        '''Marks the end of a set of changes that involve changing the

        dirstate parents. Once all parent changes have been marked done,

        the wlock will be free to write the dirstate on release.

        '''

        self._ui.deprecwarn('endparentchange is obsoleted by the '

                            'parentchange context manager.', '4.3')

        if self._parentwriters > 0:

            self._parentwriters -= 1

    def pendingparentchange(self):

        '''Returns true if the dirstate is in the middle of a set of changes

        that modify the dirstate parent.

        '''

        return self._parentwriters > 0

    @propertycache

    def _map(self):

        '''Return the dirstate contents as a map from filename to

        (state, mode, size, time).'''

        self._read()

        return self._map

    @propertycache

    def _identity(self):

        self._read()

        return self._identity

    @propertycache

    def _nonnormalset(self):

        nonnorm, otherparents = self._map.nonnormalentries()

        self._otherparentset = otherparents

        return nonnorm

    @propertycache

    def _otherparentset(self):

        nonnorm, otherparents = self._map.nonnormalentries()

        self._nonnormalset = nonnorm

        return otherparents

    @propertycache

    def _filefoldmap(self):

        return self._map.filefoldmap()

    @propertycache

    def _dirfoldmap(self):

        f = {}

        normcase = util.normcase

        for name in self._dirs:

            f[normcase(name)] = name

        return f

    @property

    def _sparsematcher(self):

        """The matcher for the sparse checkout.

        The working directory may not include every file from a manifest. The

        matcher obtained by this property will match a path if it is to be

        included in the working directory.

        """

        # TODO there is potential to cache this property. For now, the matcher

        # is resolved on every access. (But the called function does use a

        # cache to keep the lookup fast.)

        return self._sparsematchfn()

    @repocache('branch')

    def _branch(self):

        try:

            return self._opener.read("branch").strip() or "default"

        except IOError as inst:

            if inst.errno != errno.ENOENT:

                raise

            return "default"

    @propertycache

    def _pl(self):

        try:

            st = fp.read(40)

            fp.close()

            l = len(st)

            if l == 40:

                return st[:20], st[20:40]

            elif l > 0 and l < 40:

                raise error.Abort(_('working directory state appears damaged!'))

        except IOError as err:

            if err.errno != errno.ENOENT:

                raise

        return [nullid, nullid]

    @propertycache

    def _dirs(self):

        return self._map.dirs()

    def dirs(self):

        return self._dirs

    @rootcache('.hgignore')

    def _ignore(self):

        files = self._ignorefiles()

        if not files:

            return matchmod.never(self._root, '')

        pats = ['include:%s' % f for f in files]

        return matchmod.match(self._root, '', [], pats, warn=self._ui.warn)

    @propertycache

    def _slash(self):

        return self._ui.configbool('ui', 'slash') and pycompat.ossep != '/'

    @propertycache

    def _checklink(self):

        return util.checklink(self._root)

    @propertycache

    def _checkexec(self):

        return util.checkexec(self._root)

    @propertycache

    def _checkcase(self):

        return not util.fscasesensitive(self._join('.hg'))

    def _join(self, f):

        # much faster than os.path.join()

        # it's safe because f is always a relative path

        return self._rootdir + f

    def flagfunc(self, buildfallback):

        if self._checklink and self._checkexec:

            def f(x):

                try:

                    st = os.lstat(self._join(x))

                    if util.statislink(st):

                        return 'l'

                    if util.statisexec(st):

                        return 'x'

                except OSError:

                    pass

                return ''

            return f

        fallback = buildfallback()

        if self._checklink:

            def f(x):

                if os.path.islink(self._join(x)):

                    return 'l'

                if 'x' in fallback(x):

                    return 'x'

                return ''

            return f

        if self._checkexec:

            def f(x):

                if 'l' in fallback(x):

                    return 'l'

                if util.isexec(self._join(x)):

                    return 'x'

                return ''

            return f

        else:

            return fallback

    @propertycache

    def _cwd(self):

        # internal config: ui.forcecwd

        forcecwd = self._ui.config('ui', 'forcecwd')

        if forcecwd:

            return forcecwd

        return pycompat.getcwd()

    def getcwd(self):

        '''Return the path from which a canonical path is calculated.

        This path should be used to resolve file patterns or to convert

        canonical paths back to file paths for display. It shouldn't be

        used to get real file paths. Use vfs functions instead.

        '''

        cwd = self._cwd

        if cwd == self._root:

            return ''

        # self._root ends with a path separator if self._root is '/' or 'C:\'

        rootsep = self._root

        if not util.endswithsep(rootsep):

            rootsep += pycompat.ossep

        if cwd.startswith(rootsep):

            return cwd[len(rootsep):]

        else:

            # we're outside the repo. return an absolute path.

            return cwd

    def pathto(self, f, cwd=None):

        if cwd is None:

            cwd = self.getcwd()

        path = util.pathto(self._root, cwd, f)

        if self._slash:

            return util.pconvert(path)

        return path

    def __getitem__(self, key):

        '''Return the current state of key (a filename) in the dirstate.

        States are:

          n  normal

          m  needs merging

          r  marked for removal

          a  marked for addition

          ?  not tracked

        '''

        return self._map.get(key, ("?",))[0]

    def __contains__(self, key):

        return key in self._map

    def __iter__(self):

        return iter(sorted(self._map))

    def items(self):

        return self._map.iteritems()

    iteritems = items

    def parents(self):

        return [self._validate(p) for p in self._pl]

    def p1(self):

        return self._validate(self._pl[0])

    def p2(self):

        return self._validate(self._pl[1])

    def branch(self):

        return encoding.tolocal(self._branch)

    def setparents(self, p1, p2=nullid):

        """Set dirstate parents to p1 and p2.

        When moving from two parents to one, 'm' merged entries a

        adjusted to normal and previous copy records discarded and

        returned by the call.

        See localrepo.setparents()

        """

        if self._parentwriters == 0:

            raise ValueError("cannot set dirstate parent without "

                             "calling dirstate.beginparentchange")

        self._dirty = self._dirtypl = True

        oldp2 = self._pl[1]

        if self._origpl is None:

            self._origpl = self._pl

        self._pl = p1, p2

        copies = {}

        if oldp2 != nullid and p2 == nullid:

            candidatefiles = self._nonnormalset.union(self._otherparentset)

            for f in candidatefiles:

                s = self._map.get(f)

                if s is None:

                    continue

                # Discard 'm' markers when moving away from a merge state

                if s[0] == 'm':

                    source = self._map.copymap.get(f)

                    if source:

                        copies[f] = source

                    self.normallookup(f)

                # Also fix up otherparent markers

                elif s[0] == 'n' and s[2] == -2:

                    source = self._map.copymap.get(f)

                    if source:

                        copies[f] = source

                    self.add(f)

        return copies

    def setbranch(self, branch):

        self._branch = encoding.fromlocal(branch)

        f = self._opener('branch', 'w', atomictemp=True, checkambig=True)

        try:

            f.write(self._branch + '\n')

            f.close()

            # make sure filecache has the correct stat info for _branch after

            # replacing the underlying file

            ce = self._filecache['_branch']

            if ce:

                ce.refresh()

        except: # re-raises

            f.discard()

            raise

    def _read(self):

        # ignore HG_PENDING because identity is used only for writing

        self._identity = util.filestat.frompath(

            self._opener.join(self._filename))

        try:

            try:

                st = fp.read()

            finally:

                fp.close()

        except IOError as err:

            if err.errno != errno.ENOENT:

                raise

            return

        if not st:

            return

        if util.safehasattr(parsers, 'dict_new_presized'):

            # Make an estimate of the number of files in the dirstate based on

            # its size. From a linear regression on a set of real-world repos,

            # all over 10,000 files, the size of a dirstate entry is 85

            # bytes. The cost of resizing is significantly higher than the cost

            # of filling in a larger presized dict, so subtract 20% from the

            # size.

            #

            # This heuristic is imperfect in many ways, so in a future dirstate

            # format update it makes sense to just record the number of entries

            # on write.

            self._map._map = parsers.dict_new_presized(len(st) / 71)

        # Python's garbage collector triggers a GC each time a certain number

        # of container objects (the number being defined by

        # gc.get_threshold()) are allocated. parse_dirstate creates a tuple

        # for each file in the dirstate. The C version then immediately marks

        # them as not to be tracked by the collector. However, this has no

        # effect on when GCs are triggered, only on what objects the GC looks

        # into. This means that O(number of files) GCs are unavoidable.

        # Depending on when in the process's lifetime the dirstate is parsed,

        # this can get very expensive. As a workaround, disable GC while

        # parsing the dirstate.

        #

        # (we cannot decorate the function directly since it is in a C module)

        parse_dirstate = util.nogc(parsers.parse_dirstate)

        p = parse_dirstate(self._map._map, self._map.copymap, st)

        if not self._dirtypl:

            self._pl = p

    def invalidate(self):

        '''Causes the next access to reread the dirstate.

        This is different from localrepo.invalidatedirstate() because it always

        rereads the dirstate. Use localrepo.invalidatedirstate() if you want to

        check whether the dirstate has changed before rereading it.'''

        for a in ("_map", "_identity",

                  "_filefoldmap", "_dirfoldmap", "_branch",

                  "_pl", "_dirs", "_ignore", "_nonnormalset",

                  "_otherparentset"):

            if a in self.__dict__:

                delattr(self, a)

        self._lastnormaltime = 0

        self._dirty = False

        self._updatedfiles.clear()

        self._parentwriters = 0

        self._origpl = None

    def copy(self, source, dest):

        """Mark dest as a copy of source. Unmark dest if source is None."""

        if source == dest:

            return

        self._dirty = True

        if source is not None:

            self._map.copymap[dest] = source

            self._updatedfiles.add(source)

            self._updatedfiles.add(dest)

        elif self._map.copymap.pop(dest, None):

            self._updatedfiles.add(dest)

    def copied(self, file):