""" 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

"""

import heapq

import struct

import typing

import weakref

from typing import (

    Any,

    Callable,

    Collection,

    Dict,

    Iterable,

    List,

    Optional,

    Set,

    Tuple,

)

from .i18n import _

from .node import (

    bin,

    hex,

    nullrev,

    short,

    wdirrev,

)

from . import (

    error,

    requirements,

    smartset,

    txnutil,

    util,

)

Phaseroots = Dict[int, Set[int]]

PhaseSets = Dict[int, Set[int]]

if typing.TYPE_CHECKING:

    from . import (

        localrepo,

        ui as uimod,

    )

    # keeps pyflakes happy

    assert [uimod]

    Phasedefaults = List[

        Callable[[localrepo.localrepository, Phaseroots], Phaseroots]

    ]

_fphasesentry = struct.Struct(b'>i20s')

# record phase index

public: int = 0

draft: int = 1

secret: int = 2

archived = 32  # non-continuous for compatibility

internal = 96  # non-continuous for compatibility

allphases = (public, draft, secret, archived, internal)

trackedphases = (draft, secret, archived, internal)

not_public_phases = trackedphases

# record phase names

cmdphasenames = [b'public', b'draft', b'secret']  # known to `hg phase` command

phasenames = dict(enumerate(cmdphasenames))

phasenames[archived] = b'archived'

phasenames[internal] = b'internal'

# map phase name to phase number

phasenumber = {name: phase for phase, name in phasenames.items()}

# like phasenumber, but also include maps for the numeric and binary

# phase number to the phase number

phasenumber2 = phasenumber.copy()

phasenumber2.update({phase: phase for phase in phasenames})

phasenumber2.update({b'%i' % phase: phase for phase in phasenames})

# record phase property

mutablephases = (draft, secret, archived, internal)

relevant_mutable_phases = (draft, secret)  # could be obsolete or unstable

remotehiddenphases = (secret, archived, internal)

localhiddenphases = (internal, archived)

all_internal_phases = tuple(p for p in allphases if p & internal)

# We do not want any internal content to exit the repository, ever.

no_bundle_phases = all_internal_phases

def supportinternal(repo: "localrepo.localrepository") -> bool:

    """True if the internal phase can be used on a repository"""

    return requirements.INTERNAL_PHASE_REQUIREMENT in repo.requirements

def supportarchived(repo: "localrepo.localrepository") -> bool:

    """True if the archived phase can be used on a repository"""

    return requirements.ARCHIVED_PHASE_REQUIREMENT in repo.requirements

def _readroots(

    repo: "localrepo.localrepository",

    phasedefaults: Optional["Phasedefaults"] = None,

) -> Tuple[Phaseroots, bool]:

    """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 = {i: set() for i in allphases}

    to_rev = repo.changelog.index.get_rev

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

    try:

        f, pending = txnutil.trypending(repo.root, repo.svfs, b'phaseroots')

        try:

            for line in f:

                str_phase, hex_node = line.split()

                phase = int(str_phase)

                node = bin(hex_node)

                rev = to_rev(node)

                if rev is None:

                    repo.ui.debug(unknown_msg % (short(hex_node), phase))

                    dirty = True

                else:

                    roots[phase].add(rev)

        finally:

            f.close()

    except FileNotFoundError:

        if phasedefaults:

            for f in phasedefaults:

                roots = f(repo, roots)

        dirty = True

    return roots, dirty

def binaryencode(phasemapping: Dict[int, List[bytes]]) -> bytes:

    """encode a 'phase -> nodes' mapping into a binary stream

    The revision lists are encoded as (phase, root) pairs.

    """

    binarydata = []

    for phase, nodes in phasemapping.items():

        for head in nodes:

            binarydata.append(_fphasesentry.pack(phase, head))

    return b''.join(binarydata)

def binarydecode(stream) -> Dict[int, List[bytes]]:

    """decode a binary stream into a 'phase -> nodes' mapping

    The (phase, root) pairs are turned back into a dictionary with

    the phase as index and the aggregated roots of that phase as value."""

    headsbyphase = {i: [] for i in allphases}

    entrysize = _fphasesentry.size

    while True:

        entry = stream.read(entrysize)

        if len(entry) < entrysize:

            if entry:

                raise error.Abort(_(b'bad phase-heads stream'))

            break

        phase, node = _fphasesentry.unpack(entry)

        headsbyphase[phase].append(node)

    return headsbyphase

def _sortedrange_insert(data, idx, rev, t):

    merge_before = False

    if idx:

        r1, t1 = data[idx - 1]

        merge_before = r1[-1] + 1 == rev and t1 == t

    merge_after = False

    if idx < len(data):

        r2, t2 = data[idx]

        merge_after = r2[0] == rev + 1 and t2 == t

    if merge_before and merge_after:

        data[idx - 1] = (range(r1[0], r2[-1] + 1), t)

        data.pop(idx)

    elif merge_before:

        data[idx - 1] = (range(r1[0], rev + 1), t)

    elif merge_after:

        data[idx] = (range(rev, r2[-1] + 1), t)

    else:

        data.insert(idx, (range(rev, rev + 1), t))

def _sortedrange_split(data, idx, rev, t):

    r1, t1 = data[idx]

    if t == t1:

        return

    t = (t1[0], t[1])

    if len(r1) == 1:

        data.pop(idx)

        _sortedrange_insert(data, idx, rev, t)

    elif r1[0] == rev:

        data[idx] = (range(rev + 1, r1[-1] + 1), t1)

        _sortedrange_insert(data, idx, rev, t)

    elif r1[-1] == rev:

        data[idx] = (range(r1[0], rev), t1)

        _sortedrange_insert(data, idx + 1, rev, t)

    else:

        data[idx : idx + 1] = [

            (range(r1[0], rev), t1),

            (range(rev, rev + 1), t),

            (range(rev + 1, r1[-1] + 1), t1),

        ]

def _trackphasechange(data, rev, old, new):

    """add a phase move to the <data> list of ranges

    If data is None, nothing happens.

    """

    if data is None:

        return

    # If data is empty, create a one-revision range and done

    if not data:

        data.insert(0, (range(rev, rev + 1), (old, new)))

        return

    low = 0

    high = len(data)

    t = (old, new)

    while low < high:

        mid = (low + high) // 2

        revs = data[mid][0]

        revs_low = revs[0]

        revs_high = revs[-1]

        if rev >= revs_low and rev <= revs_high:

            _sortedrange_split(data, mid, rev, t)

            return

        if revs_low == rev + 1:

            if mid and data[mid - 1][0][-1] == rev:

                _sortedrange_split(data, mid - 1, rev, t)

            else:

                _sortedrange_insert(data, mid, rev, t)

            return

        if revs_high == rev - 1:

            if mid + 1 < len(data) and data[mid + 1][0][0] == rev:

                _sortedrange_split(data, mid + 1, rev, t)

            else:

                _sortedrange_insert(data, mid + 1, rev, t)

            return

        if revs_low > rev:

            high = mid

        else:

            low = mid + 1

    if low == len(data):

        data.append((range(rev, rev + 1), t))

        return

    r1, t1 = data[low]

    if r1[0] > rev:

        data.insert(low, (range(rev, rev + 1), t))

    else:

        data.insert(low + 1, (range(rev, rev + 1), t))

# consider incrementaly updating the phase set the update set is not bigger

# than this size

#

# Be warned, this number is picked arbitrarily, without any benchmark. It

# should blindly pickup "small update"

INCREMENTAL_PHASE_SETS_UPDATE_MAX_UPDATE = 100

class phasecache:

    def __init__(

        self,

        repo: "localrepo.localrepository",

        phasedefaults: Optional["Phasedefaults"],

        _load: bool = True,

    ):

        if _load:

            # Cheap trick to allow shallow-copy without copy module

            loaded = _readroots(repo, phasedefaults)

            self._phaseroots: Phaseroots = loaded[0]

            self.dirty: bool = loaded[1]

            self._loadedrevslen = 0

            self._phasesets: PhaseSets = None