# metadata.py -- code related to various metadata computation and access.

#

# Copyright 2019 Google, Inc <martinvonz@google.com>

# Copyright 2020 Pierre-Yves David <pierre-yves.david@octobus.net>

#

# 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, print_function

import multiprocessing

import struct

from . import (

    error,

    node,

    pycompat,

    util,

)

from .revlogutils import (

    flagutil as sidedataflag,

    sidedata as sidedatamod,

)

class ChangingFiles(object):

    """A class recording the changes made to files by a changeset

    Actions performed on files are gathered into 3 sets:

    - added:   files actively added in the changeset.

    - merged:  files whose history got merged

    - removed: files removed in the revision

    - touched: files affected by the merge

    and copies information is held by 2 mappings

    - copied_from_p1: {"<new-name>": "<source-name-in-p1>"} mapping for copies

    - copied_from_p2: {"<new-name>": "<source-name-in-p2>"} mapping for copies

    See their inline help for details.

    """

    def __init__(

        self,

        touched=None,

        added=None,

        removed=None,

        merged=None,

        p1_copies=None,

        p2_copies=None,

    ):

        self._added = set(() if added is None else added)

        self._merged = set(() if merged is None else merged)

        self._removed = set(() if removed is None else removed)

        self._touched = set(() if touched is None else touched)

        self._touched.update(self._added)

        self._touched.update(self._merged)

        self._touched.update(self._removed)

        self._p1_copies = dict(() if p1_copies is None else p1_copies)

        self._p2_copies = dict(() if p2_copies is None else p2_copies)

    def __eq__(self, other):

        return (

            self.added == other.added

            and self.merged == other.merged

            and self.removed == other.removed

            and self.touched == other.touched

            and self.copied_from_p1 == other.copied_from_p1

            and self.copied_from_p2 == other.copied_from_p2

        )

    @util.propertycache

    def added(self):

        """files actively added in the changeset

        Any file present in that revision that was absent in all the changeset's

        parents.

        In case of merge, this means a file absent in one of the parents but

        existing in the other will *not* be contained in this set. (They were

        added by an ancestor)

        """

        return frozenset(self._added)

    def mark_added(self, filename):

        if 'added' in vars(self):

            del self.added

        self._added.add(filename)

        self.mark_touched(filename)

    def update_added(self, filenames):

        for f in filenames:

            self.mark_added(f)

    @util.propertycache

    def merged(self):

        """files actively merged during a merge

        Any modified files which had modification on both size that needed merging.

        In this case a new filenode was created and it has two parents.

        """

        return frozenset(self._merged)

    def mark_merged(self, filename):

        if 'merged' in vars(self):

            del self.merged

        self._merged.add(filename)

        self.mark_touched(filename)

    def update_merged(self, filenames):

        for f in filenames:

            self.mark_merged(f)

    @util.propertycache

    def removed(self):

        """files actively removed by the changeset

        In case of merge this will only contain the set of files removing "new"

        content. For any file absent in the current changeset:

        a) If the file exists in both parents, it is clearly "actively" removed

        by this changeset.

        b) If a file exists in only one parent and in none of the common

        ancestors, then the file was newly added in one of the merged branches

        and then got "actively" removed.

        c) If a file exists in only one parent and at least one of the common

        ancestors using the same filenode, then the file was unchanged on one

        side and deleted on the other side. The merge "passively" propagated

        that deletion, but didn't "actively" remove the file. In this case the

        file is *not* included in the `removed` set.

        d) If a file exists in only one parent and at least one of the common

        ancestors using a different filenode, then the file was changed on one

        side and removed on the other side. The merge process "actively"

        decided to drop the new change and delete the file. Unlike in the

        previous case, (c), the file included in the `removed` set.

        Summary table for merge:

        case | exists in parents | exists in gca || removed

         (a) |       both        |     *         ||   yes

         (b) |       one         |     none      ||   yes

         (c) |       one         | same filenode ||   no

         (d) |       one         |  new filenode ||   yes

        """

        return frozenset(self._removed)

    def mark_removed(self, filename):

        if 'removed' in vars(self):

            del self.removed

        self._removed.add(filename)

        self.mark_touched(filename)

    def update_removed(self, filenames):

        for f in filenames:

            self.mark_removed(f)

    @util.propertycache

    def touched(self):

        """files either actively modified, added or removed"""

        return frozenset(self._touched)

    def mark_touched(self, filename):

        if 'touched' in vars(self):

            del self.touched

        self._touched.add(filename)

    def update_touched(self, filenames):

        for f in filenames:

            self.mark_touched(f)

    @util.propertycache

    def copied_from_p1(self):

        return self._p1_copies.copy()

    def mark_copied_from_p1(self, source, dest):

        if 'copied_from_p1' in vars(self):

            del self.copied_from_p1

        self._p1_copies[dest] = source

    def update_copies_from_p1(self, copies):

        for dest, source in copies.items():

            self.mark_copied_from_p1(source, dest)

    @util.propertycache

    def copied_from_p2(self):

        return self._p2_copies.copy()

    def mark_copied_from_p2(self, source, dest):

        if 'copied_from_p2' in vars(self):

            del self.copied_from_p2

        self._p2_copies[dest] = source

    def update_copies_from_p2(self, copies):

        for dest, source in copies.items():

            self.mark_copied_from_p2(source, dest)

def computechangesetfilesadded(ctx):

    """return the list of files added in a changeset

    """

    added = []

    for f in ctx.files():

        if not any(f in p for p in ctx.parents()):

            added.append(f)

    return added

def get_removal_filter(ctx, x=None):

    """return a function to detect files "wrongly" detected as `removed`

    When a file is removed relative to p1 in a merge, this

    function determines whether the absence is due to a

    deletion from a parent, or whether the merge commit

    itself deletes the file. We decide this by doing a

    simplified three way merge of the manifest entry for

    the file. There are two ways we decide the merge

    itself didn't delete a file:

    - neither parent (nor the merge) contain the file

    - exactly one parent contains the file, and that

      parent has the same filelog entry as the merge

      ancestor (or all of them if there two). In other

      words, that parent left the file unchanged while the

      other one deleted it.

    One way to think about this is that deleting a file is

    similar to emptying it, so the list of changed files

    should be similar either way. The computation

    described above is not done directly in _filecommit

    when creating the list of changed files, however

    it does something very similar by comparing filelog

    nodes.

    """

    if x is not None:

        p1, p2, m1, m2 = x

    else:

        p1 = ctx.p1()

        p2 = ctx.p2()

        m1 = p1.manifest()

        m2 = p2.manifest()

    @util.cachefunc

    def mas():

        p1n = p1.node()

        p2n = p2.node()

        cahs = ctx.repo().changelog.commonancestorsheads(p1n, p2n)

        if not cahs:

            cahs = [node.nullrev]

        return [ctx.repo()[r].manifest() for r in cahs]

    def deletionfromparent(f):

        if f in m1:

            return f not in m2 and all(

                f in ma and ma.find(f) == m1.find(f) for ma in mas()

            )

        elif f in m2:

            return all(f in ma and ma.find(f) == m2.find(f) for ma in mas())

        else:

            return True

    return deletionfromparent

def computechangesetfilesremoved(ctx):

    """return the list of files removed in a changeset

    """

    removed = []

    for f in ctx.files():

        if f not in ctx:

            removed.append(f)

    if removed:

        rf = get_removal_filter(ctx)

        removed = [r for r in removed if not rf(r)]

    return removed

def computechangesetfilesmerged(ctx):

    """return the list of files merged in a changeset

    """

    merged = []

    if len(ctx.parents()) < 2:

        return merged

    for f in ctx.files():

        if f in ctx:

            fctx = ctx[f]

            parents = fctx._filelog.parents(fctx._filenode)

            if parents[1] != node.nullid:

                merged.append(f)

    return merged

def computechangesetcopies(ctx):

    """return the copies data for a changeset

    The copies data are returned as a pair of dictionnary (p1copies, p2copies).

    Each dictionnary are in the form: `{newname: oldname}`

    """

    p1copies = {}

    p2copies = {}

    p1 = ctx.p1()

    p2 = ctx.p2()

    narrowmatch = ctx._repo.narrowmatch()

    for dst in ctx.files():

        if not narrowmatch(dst) or dst not in ctx:

            continue

        copied = ctx[dst].renamed()

        if not copied:

            continue

        src, srcnode = copied

        if src in p1 and p1[src].filenode() == srcnode:

            p1copies[dst] = src

        elif src in p2 and p2[src].filenode() == srcnode:

            p2copies[dst] = src

    return p1copies, p2copies

def encodecopies(files, copies):

    items = []

    for i, dst in enumerate(files):

        if dst in copies:

            items.append(b'%d\0%s' % (i, copies[dst]))

    if len(items) != len(copies):

        raise error.ProgrammingError(

            b'some copy targets missing from file list'

        )

    return b"\n".join(items)

def decodecopies(files, data):

    try:

        copies = {}

        if not data:

            return copies

        for l in data.split(b'\n'):

            strindex, src = l.split(b'\0')

            i = int(strindex)

            dst = files[i]

            copies[dst] = src

        return copies

    except (ValueError, IndexError):

        # Perhaps someone had chosen the same key name (e.g. "p1copies") and

        # used different syntax for the value.

        return None

def encodefileindices(files, subset):

    subset = set(subset)

    indices = []

    for i, f in enumerate(files):

        if f in subset:

            indices.append(b'%d' % i)

    return b'\n'.join(indices)

def decodefileindices(files, data):

    try:

        subset = []

        if not data:

            return subset

        for strindex in data.split(b'\n'):

            i = int(strindex)

            if i < 0 or i >= len(files):

                return None

            subset.append(files[i])

        return subset

    except (ValueError, IndexError):

        # Perhaps someone had chosen the same key name (e.g. "added") and

        # used different syntax for the value.

        return None

# see mercurial/helptext/internals/revlogs.txt for details about the format

ACTION_MASK = int("111" "00", 2)

# note: untouched file used as copy source will as `000` for this mask.

ADDED_FLAG = int("001" "00", 2)

MERGED_FLAG = int("010" "00", 2)

REMOVED_FLAG = int("011" "00", 2)

# `100` is reserved for future use

TOUCHED_FLAG = int("101" "00", 2)

COPIED_MASK = int("11", 2)

COPIED_FROM_P1_FLAG = int("10", 2)

COPIED_FROM_P2_FLAG = int("11", 2)

# structure is <flag><filename-end><copy-source>

INDEX_HEADER = struct.Struct(">L")

INDEX_ENTRY = struct.Struct(">bLL")

def encode_files_sidedata(files):

    all_files = set(files.touched)

    all_files.update(files.copied_from_p1.values())

    all_files.update(files.copied_from_p2.values())

    all_files = sorted(all_files)

    file_idx = {f: i for (i, f) in enumerate(all_files)}