comparison mercurial/copies.py @ 42595:819712deac69

copies: follow copies across merge base without source file (issue6163)

As in the previous patch, consider these two histories:

  @  4 'rename x to y'
  |
  o  3 'add x again'
  |
  o  2 'remove x'
  |
  | o  1 'modify x'
  |/
  o  0 'add x'

  @  4 'rename x to y'
  |
  o  3 'add x again'
  |
  | o  2 'modify x'
  | |
  | o  1 'add x'
  |/
  o  0 'base'

We trace copies from the 'modify x' commit to commit 4 by going via
the merge base (commit 0). When tracing file 'y' (_tracefile()) in the
first case, we immediately find the rename from 'x'. We check to see
if 'x' exists in the merge base, which it does, so we consider it a
valid copy. In the second case, 'x' does not exist in the merge base,
so it's not considered a valid copy. As a workaround, this patch makes
it so we also attempt the check in mergecopies's base commit (commit 1
in the second case). That feels pretty ugly to me, but I don't have
any better ideas.

Note that we actually also check not only that the filename matches,
but also that the file's nodeid matches. I don't know why we do that,
but it was like that already before I rewrote mergecopies(). That
means that the rebase will still fail in cases like this (again, it
already failed before my rewrite):


  @  4 'rename x to y'
  |
  o  3 'add x again with content X2'
  |
  o  2 'remove x'
  |
  | o  1 'modify x to content X2'
  |/
  o  1 'modify x to content X1'
  |
  o  0 'add x with content X0'

Differential Revision: https://phab.mercurial-scm.org/D6604

42594:d013099c551b

            t[k] = t[v]
        else:
            t[k] = v
    return t

def _tracefile(fctx, am, limit):
    """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():
        path = f.path()
        if am.get(path, None) == f.filenode():
            return path
        if not f.isintroducedafter(limit):
            return None

def _dirstatecopies(repo, match=None):

def usechangesetcentricalgo(repo):
    """Checks if we should use changeset-centric copy algorithms"""
    return (repo.ui.config('experimental', 'copies.read-from') in
            ('changeset-only', 'compatibility'))

def _committedforwardcopies(a, b, match):
    """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""
    # files might have to be traced back to the fctx parent of the last
    # one-side-only changeset, but not further back than that
    repo = a._repo

            % (a, b))
    limit = _findlimit(repo, a, b)
    if debug:
        dbg('debug.copies:      search limit: %d\n' % limit)
    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 = {}

        fctx = b[f]
        fctx._ancestrycontext = ancestrycontext

        if debug:
            start = util.timer()
        opath = _tracefile(fctx, am, limit)
        if opath:
            if debug:
                dbg('debug.copies:          rename of: %s\n' % opath)
            cm[f] = opath
        if debug:

                if f in newcopies:
                    del newcopies[f]
            heapq.heappush(work, (c, parent, newcopies))
    assert False

def _forwardcopies(a, b, match=None):
    """find {dst@b: src@a} copy mapping where a is an ancestor of b"""

    match = a.repo().narrowmatch(match)
    # check for working copy
    if b.rev() is None:
        cm = _committedforwardcopies(a, b.p1(), match)
        # combine copies from dirstate if necessary
        copies = _chain(cm, _dirstatecopies(b._repo, match))
    else:
        copies  = _committedforwardcopies(a, b, match)
    return copies

def _backwardrenames(a, b, match):
    if a._repo.ui.config('experimental', 'copytrace') == 'off':
        return {}

            repo.ui.debug('debug.copies: search mode: backward\n')
        copies = _backwardrenames(x, y, match=match)
    else:
        if debug:
            repo.ui.debug('debug.copies: search mode: combined\n')
        copies = _chain(_backwardrenames(x, a, match=match),
                        _forwardcopies(a, y, match=match))
    _filter(x, y, copies)
    return copies

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

42595:819712deac69

            t[k] = t[v]
        else:
            t[k] = v
    return t

def _tracefile(fctx, am, basemf, limit):
    """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():
        path = f.path()
        if am.get(path, None) == f.filenode():
            return path
        if basemf and basemf.get(path, None) == f.filenode():
            return path
        if not f.isintroducedafter(limit):
            return None

def _dirstatecopies(repo, match=None):

def usechangesetcentricalgo(repo):
    """Checks if we should use changeset-centric copy algorithms"""
    return (repo.ui.config('experimental', 'copies.read-from') in
            ('changeset-only', 'compatibility'))

def _committedforwardcopies(a, b, base, match):
    """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""
    # files might have to be traced back to the fctx parent of the last
    # one-side-only changeset, but not further back than that
    repo = a._repo

            % (a, b))
    limit = _findlimit(repo, a, b)
    if debug:
        dbg('debug.copies:      search limit: %d\n' % limit)
    am = a.manifest()
    basemf = None if base is None else base.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 = {}

        fctx = b[f]
        fctx._ancestrycontext = ancestrycontext

        if debug:
            start = util.timer()
        opath = _tracefile(fctx, am, basemf, limit)
        if opath:
            if debug:
                dbg('debug.copies:          rename of: %s\n' % opath)
            cm[f] = opath
        if debug:

                if f in newcopies:
                    del newcopies[f]
            heapq.heappush(work, (c, parent, newcopies))
    assert False

def _forwardcopies(a, b, base=None, match=None):
    """find {dst@b: src@a} copy mapping where a is an ancestor of b"""

    if base is None:
        base = a
    match = a.repo().narrowmatch(match)
    # check for working copy
    if b.rev() is None:
        cm = _committedforwardcopies(a, b.p1(), base, match)
        # combine copies from dirstate if necessary
        copies = _chain(cm, _dirstatecopies(b._repo, match))
    else:
        copies  = _committedforwardcopies(a, b, base, match)
    return copies

def _backwardrenames(a, b, match):
    if a._repo.ui.config('experimental', 'copytrace') == 'off':
        return {}

            repo.ui.debug('debug.copies: search mode: backward\n')
        copies = _backwardrenames(x, y, match=match)
    else:
        if debug:
            repo.ui.debug('debug.copies: search mode: combined\n')
        base = None
        if a.rev() != node.nullrev:
            base = x
        copies = _chain(_backwardrenames(x, a, match=match),
                        _forwardcopies(a, y, base, match=match))
    _filter(x, y, copies)
    return copies

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