# copies.py - copy detection for Mercurial

#

# Copyright 2008 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 heapq

from . import (

    node,

    pathutil,

    scmutil,

    util,

)

def _findlimit(repo, a, b):

    """

    Find the last revision that needs to be checked to ensure that a full

    transitive closure for file copies can be properly calculated.

    Generally, this means finding the earliest revision number that's an

    ancestor of a or b but not both, except when a or b is a direct descendent

    of the other, in which case we can return the minimum revnum of a and b.

    None if no such revision exists.

    """

    # basic idea:

    # - mark a and b with different sides

    # - if a parent's children are all on the same side, the parent is

    #   on that side, otherwise it is on no side

    # - walk the graph in topological order with the help of a heap;

    #   - add unseen parents to side map

    #   - clear side of any parent that has children on different sides

    #   - track number of interesting revs that might still be on a side

    #   - track the lowest interesting rev seen

    #   - quit when interesting revs is zero

    cl = repo.changelog

    working = len(cl) # pseudo rev for the working directory

    if a is None:

        a = working

    if b is None:

        b = working

    side = {a: -1, b: 1}

    visit = [-a, -b]

    heapq.heapify(visit)

    interesting = len(visit)

    hascommonancestor = False

    limit = working

    while interesting:

        r = -heapq.heappop(visit)

        if r == working:

            parents = [cl.rev(p) for p in repo.dirstate.parents()]

        else:

            parents = cl.parentrevs(r)

        for p in parents:

            if p < 0:

                continue

            if p not in side:

                # first time we see p; add it to visit

                side[p] = side[r]

                if side[p]:

                    interesting += 1

                heapq.heappush(visit, -p)

            elif side[p] and side[p] != side[r]:

                # p was interesting but now we know better

                side[p] = 0

                interesting -= 1

                hascommonancestor = True

        if side[r]:

            limit = r # lowest rev visited

            interesting -= 1

    if not hascommonancestor:

        return None

    # Consider the following flow (see test-commit-amend.t under issue4405):

    # 1/ File 'a0' committed

    # 2/ File renamed from 'a0' to 'a1' in a new commit (call it 'a1')

    # 3/ Move back to first commit

    # 4/ Create a new commit via revert to contents of 'a1' (call it 'a1-amend')

    # 5/ Rename file from 'a1' to 'a2' and commit --amend 'a1-msg'

    #

    # During the amend in step five, we will be in this state:

    #

    # @  3 temporary amend commit for a1-amend

    # |

    # o  2 a1-amend

    # |

    # | o  1 a1

    # |/

    # o  0 a0

    #

    # When _findlimit is called, a and b are revs 3 and 0, so limit will be 2,

    # yet the filelog has the copy information in rev 1 and we will not look

    # back far enough unless we also look at the a and b as candidates.

    # This only occurs when a is a descendent of b or visa-versa.

    return min(limit, a, b)

def _chain(src, dst, a, b):

    '''chain two sets of copies a->b'''

    t = a.copy()

    for k, v in b.iteritems():

        if v in t:

            # found a chain

            if t[v] != k:

                # file wasn't renamed back to itself

                t[k] = t[v]

            if v not in dst:

                # chain was a rename, not a copy

                del t[v]

        if v in src:

            # file is a copy of an existing file

            t[k] = v

    # remove criss-crossed copies

    for k, v in t.items():

        if k in src and v in dst:

            del t[k]

    return t

def _tracefile(fctx, am, limit=-1):

    '''return file context that is the ancestor of fctx present in ancestor

    manifest am, stopping after the first ancestor lower than limit'''

    for f in fctx.ancestors():

        if am.get(f.path(), None) == f.filenode():

            return f

        if limit >= 0 and f.linkrev() < limit and f.rev() < limit:

            return None

def _dirstatecopies(d):

    ds = d._repo.dirstate

    c = ds.copies().copy()

    for k in c.keys():

        if ds[k] not in 'anm':

            del c[k]

    return c

def _computeforwardmissing(a, b, match=None):

    """Computes which files are in b but not a.

    This is its own function so extensions can easily wrap this call to see what

    files _forwardcopies is about to process.

    """

    ma = a.manifest()

    mb = b.manifest()

    if match:

        ma = ma.matches(match)

        mb = mb.matches(match)

    return mb.filesnotin(ma)

def _forwardcopies(a, b, match=None):

    '''find {dst@b: src@a} copy mapping where a is an ancestor of b'''

    # check for working copy

    w = None

    if b.rev() is None:

        w = b

        b = w.p1()

        if a == b:

            # short-circuit to avoid issues with merge states

            return _dirstatecopies(w)

    # files might have to be traced back to the fctx parent of the last

    # one-side-only changeset, but not further back than that

    limit = _findlimit(a._repo, a.rev(), b.rev())

    if limit is None:

        limit = -1

    am = a.manifest()

    # find where new files came from

    # we currently don't try to find where old files went, too expensive

    # this means we can miss a case like 'hg rm b; hg cp a b'

    cm = {}

    # Computing the forward missing is quite expensive on large manifests, since

    # it compares the entire manifests. We can optimize it in the common use

    # case of computing what copies are in a commit versus its parent (like

    # during a rebase or histedit). Note, we exclude merge commits from this

    # optimization, since the ctx.files() for a merge commit is not correct for

    # this comparison.

    forwardmissingmatch = match

    if not match and b.p1() == a and b.p2().node() == node.nullid:

        forwardmissingmatch = scmutil.matchfiles(a._repo, b.files())

    missing = _computeforwardmissing(a, b, match=forwardmissingmatch)

    ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)

    for f in missing:

        fctx = b[f]

        fctx._ancestrycontext = ancestrycontext

        ofctx = _tracefile(fctx, am, limit)

        if ofctx:

            cm[f] = ofctx.path()

    # combine copies from dirstate if necessary

    if w is not None:

        cm = _chain(a, w, cm, _dirstatecopies(w))

    return cm

def _backwardrenames(a, b):

    if a._repo.ui.configbool('experimental', 'disablecopytrace'):

        return {}

    # Even though we're not taking copies into account, 1:n rename situations

    # can still exist (e.g. hg cp a b; hg mv a c). In those cases we

    # arbitrarily pick one of the renames.

    f = _forwardcopies(b, a)

    r = {}

    for k, v in sorted(f.iteritems()):

        # remove copies

        if v in a:

            continue

        r[v] = k

    return r

def pathcopies(x, y, match=None):

    '''find {dst@y: src@x} copy mapping for directed compare'''

    if x == y or not x or not y:

        return {}

    a = y.ancestor(x)

    if a == x:

        return _forwardcopies(x, y, match=match)

    if a == y:

        return _backwardrenames(x, y)

    return _chain(x, y, _backwardrenames(x, a),

                  _forwardcopies(a, y, match=match))

def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2, baselabel=''):

    """Computes, based on addedinm1 and addedinm2, the files exclusive to c1

    and c2. This is its own function so extensions can easily wrap this call

    to see what files mergecopies is about to process.

    Even though c1 and c2 are not used in this function, they are useful in

    other extensions for being able to read the file nodes of the changed files.

    "baselabel" can be passed to help distinguish the multiple computations

    done in the graft case.

    """

    u1 = sorted(addedinm1 - addedinm2)

    u2 = sorted(addedinm2 - addedinm1)

    header = "  unmatched files in %s"

    if baselabel:

        header += ' (from %s)' % baselabel

    if u1:

        repo.ui.debug("%s:\n   %s\n" % (header % 'local', "\n   ".join(u1)))

    if u2:

        repo.ui.debug("%s:\n   %s\n" % (header % 'other', "\n   ".join(u2)))

    return u1, u2

def _makegetfctx(ctx):

    """return a 'getfctx' function suitable for _checkcopies usage

    We have to re-setup the function building 'filectx' for each

    '_checkcopies' to ensure the linkrev adjustment is properly setup for

    each. Linkrev adjustment is important to avoid bug in rename

    detection. Moreover, having a proper '_ancestrycontext' setup ensures

    the performance impact of this adjustment is kept limited. Without it,

    each file could do a full dag traversal making the time complexity of

    the operation explode (see issue4537).

    This function exists here mostly to limit the impact on stable. Feel

    free to refactor on default.

    """

    rev = ctx.rev()

    repo = ctx._repo

    ac = getattr(ctx, '_ancestrycontext', None)

    if ac is None:

        revs = [rev]

        if rev is None:

            revs = [p.rev() for p in ctx.parents()]

        ac = repo.changelog.ancestors(revs, inclusive=True)

        ctx._ancestrycontext = ac

    def makectx(f, n):

        if n in node.wdirnodes:  # in a working context?

            if ctx.rev() is None:

                return ctx.filectx(f)

            return repo[None][f]

        fctx = repo.filectx(f, fileid=n)

        # setup only needed for filectx not create from a changectx

        fctx._ancestrycontext = ac

        fctx._descendantrev = rev

        return fctx

    return util.lrucachefunc(makectx)

def _combinecopies(copyfrom, copyto, finalcopy, diverge, incompletediverge):

    """combine partial copy paths"""

    remainder = {}

    for f in copyfrom:

        if f in copyto:

            finalcopy[copyto[f]] = copyfrom[f]

            del copyto[f]

    for f in incompletediverge:

        assert f not in diverge

        ic = incompletediverge[f]

        if ic[0] in copyto:

            diverge[f] = [copyto[ic[0]], ic[1]]

        else:

            remainder[f] = ic

    return remainder

def mergecopies(repo, c1, c2, base):

    """

    Find moves and copies between context c1 and c2 that are relevant

    for merging. 'base' will be used as the merge base.

    Returns five dicts: "copy", "movewithdir", "diverge", "renamedelete" and

    "dirmove".

    "copy" is a mapping from destination name -> source name,

    where source is in c1 and destination is in c2 or vice-versa.

    "movewithdir" is a mapping from source name -> destination name,

    where the file at source present in one context but not the other

    needs to be moved to destination by the merge process, because the

    other context moved the directory it is in.

    "diverge" is a mapping of source name -> list of destination names

    for divergent renames.

    "renamedelete" is a mapping of source name -> list of destination

    names for files deleted in c1 that were renamed in c2 or vice-versa.

    "dirmove" is a mapping of detected source dir -> destination dir renames.

    This is needed for handling changes to new files previously grafted into

    renamed directories.

    """

    # avoid silly behavior for update from empty dir

    if not c1 or not c2 or c1 == c2:

        return {}, {}, {}, {}, {}

    # avoid silly behavior for parent -> working dir

    if c2.node() is None and c1.node() == repo.dirstate.p1():

        return repo.dirstate.copies(), {}, {}, {}, {}

    # Copy trace disabling is explicitly below the node == p1 logic above

    # because the logic above is required for a simple copy to be kept across a

    # rebase.

    if repo.ui.configbool('experimental', 'disablecopytrace'):

        return {}, {}, {}, {}, {}

    # In certain scenarios (e.g. graft, update or rebase), base can be

    # overridden We still need to know a real common ancestor in this case We

    # can't just compute _c1.ancestor(_c2) and compare it to ca, because there

    # can be multiple common ancestors, e.g. in case of bidmerge.  Because our

    # caller may not know if the revision passed in lieu of the CA is a genuine

    # common ancestor or not without explicitly checking it, it's better to

    # determine that here.

    #

    # base.descendant(wc) and base.descendant(base) are False, work around that

    _c1 = c1.p1() if c1.rev() is None else c1

    _c2 = c2.p1() if c2.rev() is None else c2

    # an endpoint is "dirty" if it isn't a descendant of the merge base

    # if we have a dirty endpoint, we need to trigger graft logic, and also

    # keep track of which endpoint is dirty

    dirtyc1 = not (base == _c1 or base.descendant(_c1))

    dirtyc2 = not (base== _c2 or base.descendant(_c2))

    graft = dirtyc1 or dirtyc2

    tca = base

    if graft:

        tca = _c1.ancestor(_c2)

    limit = _findlimit(repo, c1.rev(), c2.rev())

    if limit is None:

        # no common ancestor, no copies

        return {}, {}, {}, {}, {}

    repo.ui.debug("  searching for copies back to rev %d\n" % limit)

    m1 = c1.manifest()

    m2 = c2.manifest()

    mb = base.manifest()

    # gather data from _checkcopies:

    # - diverge = record all diverges in this dict

    # - copy = record all non-divergent copies in this dict

    # - fullcopy = record all copies in this dict

    # - incomplete = record non-divergent partial copies here

    # - incompletediverge = record divergent partial copies here

    diverge = {} # divergence data is shared

    incompletediverge  = {}

    data1 = {'copy': {},

             'fullcopy': {},

             'incomplete': {},

             'diverge': diverge,

             'incompletediverge': incompletediverge,