comparison mercurial/copies.py @ 20294:243ea5ffdf31

diff: search beyond ancestor when detecting renames

This removes an optimization that was introduced in 91eb4512edd0 but was too
aggressive - as indicated by how it changed test-mq-merge.t .

We are walking filelogs to find copy sources and we can thus not be sure to hit
the base revision and find the renamed file there - it could also be in the
first ancestor of the base ... in the filelog.

We are walking the filelog and can thus not easily know when we hit the first
ancestor of the base revision and which filename to look for there. Instead, we
use _findlimit like mergecopies do: The lower bound for how far we have to go
is found from the lowest changelog revision that is an ancestor of only one of
the compared revisions. Any filelog ancestor with a revision number lower than
that revision will be the ancestor of both compared revisions, and there is
thus no reason to go further back than that.

20293:2f6b3900be64

        if k in src and v in dst:
            del t[k]

    return t

def _tracefile(fctx, actx):
    '''return file context that is the ancestor of fctx present in actx'''
    stop = actx.rev()
    am = actx.manifest()

    for f in fctx.ancestors():
        if am.get(f.path(), None) == f.filenode():
            return f
        if f.rev() < stop:
            return None

def _dirstatecopies(d):
    ds = d._repo.dirstate
    c = ds.copies().copy()

        b = w.p1()
        if a == b:
            # short-circuit to avoid issues with merge states
            return _dirstatecopies(w)

    # 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 = {}
    missing = set(b.manifest().iterkeys())
    missing.difference_update(a.manifest().iterkeys())

    for f in missing:
        ofctx = _tracefile(b[f], a)
        if ofctx:
            cm[f] = ofctx.path()

    # combine copies from dirstate if necessary
    if w is not None:

20294:243ea5ffdf31

        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 f.rev() < limit:
            return None

def _dirstatecopies(d):
    ds = d._repo.dirstate
    c = ds.copies().copy()

        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 = {}
    missing = set(b.manifest().iterkeys())
    missing.difference_update(a.manifest().iterkeys())

    for f in missing:
        ofctx = _tracefile(b[f], am, limit)
        if ofctx:
            cm[f] = ofctx.path()

    # combine copies from dirstate if necessary
    if w is not None: