comparison mercurial/copies.py @ 44196:6ca9f45b32b0

copies: make mergecopies() distinguish between copies on each side

I find it confusing that most of the dicts returned from
`mergecopies()` have entries specific to one branch of the merge, but
they're still combined into dict. For example, you can't tell if `copy
= {"bar": "foo"}` means that "foo" was copied to "bar" on the first
branch or the second.

It also feels like there are bugs lurking here because we may mistake
which side the copy happened on. However, for most of the dicts, it's
not possible that there is disagreement. For example, `renamedelete`
keeps track of renames that happened on one side of the merge where
the other side deleted the file. There can't be a disagreement there
(because we record that in the `diverge` dict instead). For regular
copies/renames, there can be a disagreement. Let's say file "foo" was
copied to "bar" on one branch and file "baz" was copied to "bar" on
the other. Beacause we only return one `copy` dict, we end up
replacing the `{"bar": "foo"}` entry by `{"bar": "baz"}`. The merge
code (`manifestmerge()`) will then decide that that means "both
renamed from 'baz'". We should probably treat it as a conflict
instead.

The next few patches will make `mergecopies()` return two instances of
most of the returned copies. That will lead to a bit more code (~40
lines), but I think it makes both `copies.mergecopies()` and
`merge.manifestmerge()` clearer.

Differential Revision: https://phab.mercurial-scm.org/D7986

44195:51c86c6167c1

    for dst, src in copies1.items():
        inversecopies1.setdefault(src, []).append(dst)
    for dst, src in copies2.items():
        inversecopies2.setdefault(src, []).append(dst)

    copy = {}
    diverge = {}
    renamedelete = {}
    allsources = set(inversecopies1) | set(inversecopies2)
    for src in allsources:
        dsts1 = inversecopies1.get(src)
        dsts2 = inversecopies2.get(src)
        if dsts1 and dsts2:

                # consider it not divergent. For example, if side 1 copies 'a'
                # to 'b' and 'c' and deletes 'a', and side 2 copies 'a' to 'c'
                # and 'd' and deletes 'a'.
                if dsts1 & dsts2:
                    for dst in dsts1 & dsts2:
                        copy[dst] = src
                else:
                    diverge[src] = sorted(dsts1 | dsts2)
            elif src in m1 and src in m2:
                # copied on both sides
                dsts1 = set(dsts1)
                dsts2 = set(dsts2)
                for dst in dsts1 & dsts2:
                    copy[dst] = src
            # TODO: Handle cases where it was renamed on one side and copied
            # on the other side
        elif dsts1:
            # copied/renamed only on side 1
            _checksinglesidecopies(
                src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
            )
        elif dsts2:
            # copied/renamed only on side 2
            _checksinglesidecopies(
                src, dsts2, m2, m1, mb, c1, base, copy, renamedelete
            )

    # find interesting file sets from manifests
    addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
    addedinm2 = m2.filesnotin(mb, repo.narrowmatch())

    if repo.ui.debugflag:
        renamedeleteset = set()
        divergeset = set()
        for dsts in diverge.values():
            divergeset.update(dsts)
        for dsts in renamedelete.values():
            renamedeleteset.update(dsts)

        repo.ui.debug(
            b"  all copies found (* = to merge, ! = divergent, "
            b"% = renamed and deleted):\n"
        )
        for f in sorted(fullcopy):
            note = b""
            if f in copy:
                note += b"*"
            if f in divergeset:
                note += b"!"
            if f in renamedeleteset:
                note += b"%"

        del renamedeleteset
        del divergeset

    repo.ui.debug(b"  checking for directory renames\n")

    dirmove, movewithdir = _dir_renames(repo, c1, c2, copy, fullcopy, u1, u2)

    return copy, movewithdir, diverge, renamedelete, dirmove


def _dir_renames(repo, c1, c2, copy, fullcopy, u1, u2):
    # generate a directory move map
    d1, d2 = c1.dirs(), c2.dirs()
    invalid = set()
    dirmove = {}

    # examine each file copy for a potential directory move, which is
    # when all the files in a directory are moved to a new directory
    for dst, src in pycompat.iteritems(fullcopy):
        dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
        if dsrc in invalid:
            # already seen to be uninteresting
            continue
        elif dsrc in d1 and ddst in d1:
            # directory wasn't entirely moved locally
            invalid.add(dsrc)
        elif dsrc in d2 and ddst in d2:
            # directory wasn't entirely moved remotely
            invalid.add(dsrc)
        elif dsrc in dirmove and dirmove[dsrc] != ddst:
            # files from the same directory moved to two different places
            invalid.add(dsrc)
        else:

            dirmove[dsrc] = ddst

    for i in invalid:
        if i in dirmove:
            del dirmove[i]
    del d1, d2, invalid

    if not dirmove:
        return {}, {}

    dirmove = {k + b"/": v + b"/" for k, v in pycompat.iteritems(dirmove)}

            b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
        )

    movewithdir = {}
    # check unaccounted nonoverlapping files against directory moves
    for f in u1 + u2:
        if f not in fullcopy:
            for d in dirmove:
                if f.startswith(d):
                    # new file added in a directory that was moved, move it
                    df = dirmove[d] + f[len(d) :]

44196:6ca9f45b32b0

    for dst, src in copies1.items():
        inversecopies1.setdefault(src, []).append(dst)
    for dst, src in copies2.items():
        inversecopies2.setdefault(src, []).append(dst)

    copy1 = {}
    copy2 = {}
    diverge = {}
    renamedelete1 = {}
    renamedelete2 = {}
    allsources = set(inversecopies1) | set(inversecopies2)
    for src in allsources:
        dsts1 = inversecopies1.get(src)
        dsts2 = inversecopies2.get(src)
        if dsts1 and dsts2:

                # consider it not divergent. For example, if side 1 copies 'a'
                # to 'b' and 'c' and deletes 'a', and side 2 copies 'a' to 'c'
                # and 'd' and deletes 'a'.
                if dsts1 & dsts2:
                    for dst in dsts1 & dsts2:
                        copy1[dst] = src
                        copy2[dst] = src
                else:
                    diverge[src] = sorted(dsts1 | dsts2)
            elif src in m1 and src in m2:
                # copied on both sides
                dsts1 = set(dsts1)
                dsts2 = set(dsts2)
                for dst in dsts1 & dsts2:
                    copy1[dst] = src
                    copy2[dst] = src
            # TODO: Handle cases where it was renamed on one side and copied
            # on the other side
        elif dsts1:
            # copied/renamed only on side 1
            _checksinglesidecopies(
                src, dsts1, m1, m2, mb, c2, base, copy1, renamedelete1
            )
        elif dsts2:
            # copied/renamed only on side 2
            _checksinglesidecopies(
                src, dsts2, m2, m1, mb, c1, base, copy2, renamedelete2
            )

    # find interesting file sets from manifests
    addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
    addedinm2 = m2.filesnotin(mb, repo.narrowmatch())

    if repo.ui.debugflag:
        renamedeleteset = set()
        divergeset = set()
        for dsts in diverge.values():
            divergeset.update(dsts)
        for dsts in renamedelete1.values():
            renamedeleteset.update(dsts)
        for dsts in renamedelete2.values():
            renamedeleteset.update(dsts)

        repo.ui.debug(
            b"  all copies found (* = to merge, ! = divergent, "
            b"% = renamed and deleted):\n"
        )
        for f in sorted(fullcopy):
            note = b""
            if f in copy1 or f in copy2:
                note += b"*"
            if f in divergeset:
                note += b"!"
            if f in renamedeleteset:
                note += b"%"

        del renamedeleteset
        del divergeset

    repo.ui.debug(b"  checking for directory renames\n")

    dirmove1, movewithdir2 = _dir_renames(repo, c1, copy1, copies1, u2)
    dirmove2, movewithdir1 = _dir_renames(repo, c2, copy2, copies2, u1)

    copy1.update(copy2)
    renamedelete1.update(renamedelete2)
    movewithdir1.update(movewithdir2)
    dirmove1.update(dirmove2)

    return copy1, movewithdir1, diverge, renamedelete1, dirmove1


def _dir_renames(repo, ctx, copy, fullcopy, addedfiles):
    """Finds moved directories and files that should move with them.

    ctx: the context for one of the sides
    copy: files copied on the same side (as ctx)
    fullcopy: files copied on the same side (as ctx), including those that
              merge.manifestmerge() won't care about
    addedfiles: added files on the other side (compared to ctx)
    """
    # generate a directory move map
    d = ctx.dirs()
    invalid = set()
    dirmove = {}

    # examine each file copy for a potential directory move, which is
    # when all the files in a directory are moved to a new directory
    for dst, src in pycompat.iteritems(fullcopy):
        dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
        if dsrc in invalid:
            # already seen to be uninteresting
            continue
        elif dsrc in d and ddst in d:
            # directory wasn't entirely moved locally
            invalid.add(dsrc)
        elif dsrc in dirmove and dirmove[dsrc] != ddst:
            # files from the same directory moved to two different places
            invalid.add(dsrc)
        else:

            dirmove[dsrc] = ddst

    for i in invalid:
        if i in dirmove:
            del dirmove[i]
    del d, invalid

    if not dirmove:
        return {}, {}

    dirmove = {k + b"/": v + b"/" for k, v in pycompat.iteritems(dirmove)}

            b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
        )

    movewithdir = {}
    # check unaccounted nonoverlapping files against directory moves
    for f in addedfiles:
        if f not in fullcopy:
            for d in dirmove:
                if f.startswith(d):
                    # new file added in a directory that was moved, move it
                    df = dirmove[d] + f[len(d) :]