""" Mercurial phases support code

    ---

    Copyright 2011 Pierre-Yves David <pierre-yves.david@ens-lyon.org>

                   Logilab SA        <contact@logilab.fr>

                   Augie Fackler     <durin42@gmail.com>

    This software may be used and distributed according to the terms

    of the GNU General Public License version 2 or any later version.

    ---

This module implements most phase logic in mercurial.

Basic Concept

=============

A 'changeset phase' is an indicator that tells us how a changeset is

manipulated and communicated. The details of each phase is described

below, here we describe the properties they have in common.

Like bookmarks, phases are not stored in history and thus are not

permanent and leave no audit trail.

First, no changeset can be in two phases at once. Phases are ordered,

so they can be considered from lowest to highest. The default, lowest

phase is 'public' - this is the normal phase of existing changesets. A

child changeset can not be in a lower phase than its parents.

These phases share a hierarchy of traits:

            immutable shared

    public:     X        X

    draft:               X

    secret:

Local commits are draft by default.

Phase Movement and Exchange

===========================

Phase data is exchanged by pushkey on pull and push. Some servers have

a publish option set, we call such a server a "publishing server".

Pushing a draft changeset to a publishing server changes the phase to

public.

A small list of fact/rules define the exchange of phase:

* old client never changes server states

* pull never changes server states

* publish and old server changesets are seen as public by client

* any secret changeset seen in another repository is lowered to at

  least draft

Here is the final table summing up the 49 possible use cases of phase

exchange:

                           server

                  old     publish      non-publish

                 N   X    N   D   P    N   D   P

    old client

    pull

     N           -   X/X  -   X/D X/P  -   X/D X/P

     X           -   X/X  -   X/D X/P  -   X/D X/P

    push

     X           X/X X/X  X/P X/P X/P  X/D X/D X/P

    new client

    pull

     N           -   P/X  -   P/D P/P  -   D/D P/P

     D           -   P/X  -   P/D P/P  -   D/D P/P

     P           -   P/X  -   P/D P/P  -   P/D P/P

    push

     D           P/X P/X  P/P P/P P/P  D/D D/D P/P

     P           P/X P/X  P/P P/P P/P  P/P P/P P/P

Legend:

    A/B = final state on client / state on server

    * N = new/not present,

    * P = public,

    * D = draft,

    * X = not tracked (i.e., the old client or server has no internal

          way of recording the phase.)

    passive = only pushes

    A cell here can be read like this:

    "When a new client pushes a draft changeset (D) to a publishing

    server where it's not present (N), it's marked public on both

    sides (P/P)."

Note: old client behave as a publishing server with draft only content

- other people see it as public

- content is pushed as draft

"""

from __future__ import absolute_import

import errno

import os

from .i18n import _

from .node import (

    bin,

    hex,

    nullid,

    nullrev,

    short,

)

from . import (

    error,

)

allphases = public, draft, secret = range(3)

trackedphases = allphases[1:]

phasenames = ['public', 'draft', 'secret']

def _readroots(repo, phasedefaults=None):

    """Read phase roots from disk

    phasedefaults is a list of fn(repo, roots) callable, which are

    executed if the phase roots file does not exist. When phases are

    being initialized on an existing repository, this could be used to

    set selected changesets phase to something else than public.

    Return (roots, dirty) where dirty is true if roots differ from

    what is being stored.

    """

    repo = repo.unfiltered()

    dirty = False

    roots = [set() for i in allphases]

    try:

        f = None

        if 'HG_PENDING' in os.environ:

            try:

                f = repo.svfs('phaseroots.pending')

            except IOError as inst:

                if inst.errno != errno.ENOENT:

                    raise

        if f is None:

            f = repo.svfs('phaseroots')

        try:

            for line in f:

                phase, nh = line.split()

                roots[int(phase)].add(bin(nh))

        finally:

            f.close()

    except IOError as inst:

        if inst.errno != errno.ENOENT:

            raise

        if phasedefaults:

            for f in phasedefaults:

                roots = f(repo, roots)

        dirty = True

    return roots, dirty

class phasecache(object):

    def __init__(self, repo, phasedefaults, _load=True):

        if _load:

            # Cheap trick to allow shallow-copy without copy module

            self.phaseroots, self.dirty = _readroots(repo, phasedefaults)

            self._phaserevs = None

            self._phasesets = None

            self.filterunknown(repo)

            self.opener = repo.svfs

    def copy(self):

        # Shallow copy meant to ensure isolation in

        # advance/retractboundary(), nothing more.

        ph = self.__class__(None, None, _load=False)

        ph.phaseroots = self.phaseroots[:]

        ph.dirty = self.dirty

        ph.opener = self.opener

        ph._phaserevs = self._phaserevs

        ph._phasesets = self._phasesets

        return ph

    def replace(self, phcache):

        """replace all values in 'self' with content of phcache"""

        for a in ('phaseroots', 'dirty', 'opener', '_phaserevs', '_phasesets'):

            setattr(self, a, getattr(phcache, a))

    def _getphaserevsnative(self, repo):

        repo = repo.unfiltered()

        nativeroots = []

        for phase in trackedphases:

            nativeroots.append(map(repo.changelog.rev, self.phaseroots[phase]))

        return repo.changelog.computephases(nativeroots)

    def _computephaserevspure(self, repo):

        repo = repo.unfiltered()

        revs = [public] * len(repo.changelog)

        self._phaserevs = revs

        self._populatephaseroots(repo)

        for phase in trackedphases:

            roots = map(repo.changelog.rev, self.phaseroots[phase])

            if roots:

                for rev in roots:

                    revs[rev] = phase

                for rev in repo.changelog.descendants(roots):

                    revs[rev] = phase

    def loadphaserevs(self, repo):

        """ensure phase information is loaded in the object"""

        if self._phaserevs is None:

            try:

                if repo.ui.configbool('experimental',

                                      'nativephaseskillswitch'):

                    self._computephaserevspure(repo)

                else:

                    res = self._getphaserevsnative(repo)

                    self._phaserevs, self._phasesets = res

            except AttributeError:

                self._computephaserevspure(repo)

    def invalidate(self):

        self._phaserevs = None

        self._phasesets = None

    def _populatephaseroots(self, repo):

        """Fills the _phaserevs cache with phases for the roots.

        """

        cl = repo.changelog

        phaserevs = self._phaserevs

        for phase in trackedphases:

            roots = map(cl.rev, self.phaseroots[phase])

            for root in roots:

                phaserevs[root] = phase

    def phase(self, repo, rev):

        # We need a repo argument here to be able to build _phaserevs

        # if necessary. The repository instance is not stored in

        # phasecache to avoid reference cycles. The changelog instance

        # is not stored because it is a filecache() property and can

        # be replaced without us being notified.

        if rev == nullrev:

            return public

        if rev < nullrev:

            raise ValueError(_('cannot lookup negative revision'))

        if self._phaserevs is None or rev >= len(self._phaserevs):

            self.invalidate()

            self.loadphaserevs(repo)

        return self._phaserevs[rev]

    def write(self):

        if not self.dirty:

            return

        f = self.opener('phaseroots', 'w', atomictemp=True)

        try:

            self._write(f)

        finally:

            f.close()

    def _write(self, fp):

        for phase, roots in enumerate(self.phaseroots):

            for h in roots:

                fp.write('%i %s\n' % (phase, hex(h)))

        self.dirty = False

    def _updateroots(self, phase, newroots, tr):

        self.phaseroots[phase] = newroots

        self.invalidate()

        self.dirty = True

        tr.addfilegenerator('phase', ('phaseroots',), self._write)

        tr.hookargs['phases_moved'] = '1'

    def advanceboundary(self, repo, tr, targetphase, nodes):

        # Be careful to preserve shallow-copied values: do not update

        # phaseroots values, replace them.

        repo = repo.unfiltered()

        delroots = [] # set of root deleted by this path

        for phase in xrange(targetphase + 1, len(allphases)):

            # filter nodes that are not in a compatible phase already

            nodes = [n for n in nodes

                     if self.phase(repo, repo[n].rev()) >= phase]

            if not nodes:

                break # no roots to move anymore

            olds = self.phaseroots[phase]

            roots = set(ctx.node() for ctx in repo.set(

                    'roots((%ln::) - (%ln::%ln))', olds, olds, nodes))

            if olds != roots:

                self._updateroots(phase, roots, tr)

                # some roots may need to be declared for lower phases

                delroots.extend(olds - roots)

            # declare deleted root in the target phase

            if targetphase != 0:

                self.retractboundary(repo, tr, targetphase, delroots)

        repo.invalidatevolatilesets()

    def retractboundary(self, repo, tr, targetphase, nodes):

        # Be careful to preserve shallow-copied values: do not update

        # phaseroots values, replace them.

        repo = repo.unfiltered()

        currentroots = self.phaseroots[targetphase]

        newroots = [n for n in nodes

                    if self.phase(repo, repo[n].rev()) < targetphase]

        if newroots:

            if nullid in newroots:

                raise error.Abort(_('cannot change null revision phase'))

            currentroots = currentroots.copy()

            currentroots.update(newroots)

            ctxs = repo.set('roots(%ln::)', currentroots)

            currentroots.intersection_update(ctx.node() for ctx in ctxs)

            self._updateroots(targetphase, currentroots, tr)

        repo.invalidatevolatilesets()

    def filterunknown(self, repo):

        """remove unknown nodes from the phase boundary

        Nothing is lost as unknown nodes only hold data for their descendants.

        """

        filtered = False

        nodemap = repo.changelog.nodemap # to filter unknown nodes

        for phase, nodes in enumerate(self.phaseroots):

            missing = sorted(node for node in nodes if node not in nodemap)

            if missing:

                for mnode in missing:

                    repo.ui.debug(

                        'removing unknown node %s from %i-phase boundary\n'

                        % (short(mnode), phase))

                nodes.symmetric_difference_update(missing)

                filtered = True

        if filtered:

            self.dirty = True

        # filterunknown is called by repo.destroyed, we may have no changes in

        # root but phaserevs contents is certainly invalid (or at least we

        # have not proper way to check that). related to issue 3858.

        #

        # The other caller is __init__ that have no _phaserevs initialized

        # anyway. If this change we should consider adding a dedicated

        # "destroyed" function to phasecache or a proper cache key mechanism

        # (see branchmap one)

        self.invalidate()

def advanceboundary(repo, tr, targetphase, nodes):

    """Add nodes to a phase changing other nodes phases if necessary.

    This function move boundary *forward* this means that all nodes

    are set in the target phase or kept in a *lower* phase.

    Simplify boundary to contains phase roots only."""

    phcache = repo._phasecache.copy()

    phcache.advanceboundary(repo, tr, targetphase, nodes)

    repo._phasecache.replace(phcache)

def retractboundary(repo, tr, targetphase, nodes):

    """Set nodes back to a phase changing other nodes phases if

    necessary.

    This function move boundary *backward* this means that all nodes

    are set in the target phase or kept in a *higher* phase.

    Simplify boundary to contains phase roots only."""

    phcache = repo._phasecache.copy()

    phcache.retractboundary(repo, tr, targetphase, nodes)

    repo._phasecache.replace(phcache)

def listphases(repo):

    """List phases root for serialization over pushkey"""

    keys = {}

    value = '%i' % draft

    for root in repo._phasecache.phaseroots[draft]:

        keys[hex(root)] = value

    if repo.publishing():

        # Add an extra data to let remote know we are a publishing

        # repo. Publishing repo can't just pretend they are old repo.

        # When pushing to a publishing repo, the client still need to

        # push phase boundary

        #

        # Push do not only push changeset. It also push phase data.

        # New phase data may apply to common changeset which won't be

        # push (as they are common). Here is a very simple example:

        #

        # 1) repo A push changeset X as draft to repo B

        # 2) repo B make changeset X public

        # 3) repo B push to repo A. X is not pushed but the data that

        #    X as now public should

        #

        # The server can't handle it on it's own as it has no idea of

        # client phase data.

        keys['publishing'] = 'True'

    return keys

def pushphase(repo, nhex, oldphasestr, newphasestr):

    """List phases root for serialization over pushkey"""