view mercurial/treediscovery.py @ 35058:a68c3420be41

rebase: exclude descendants of obsoletes w/o a successor in dest (issue5300)

.. feature::

   Let 'hg rebase' avoid content-divergence by skipping obsolete
   changesets (and their descendants) when they are present in the rebase
   set along with one of their successors but none of their successors is
   in destination.

In the following example, when trying to rebase 3:: onto 2, the rebase
will abort with "this rebase will cause divergence from: 4":

    o  7 f
    |
    | o  6 e
    | |
    | o  5 d'
    | |
    x |  4 d (rewritten as 5)
    |/
    o  3 c
    |
    | o  2 x
    | |
    o |  1 b
    |/
    o  0 a

By excluding obsolete changesets without a successor in destination (4
in the example above) and their descendants, we make rebase work in this
case, thus giving:

    o  11 e
    |
    o  10 d'
    |
    o  9 c
    |
    o  8 b
    |
    | o  7 f
    | |
    | | x  6 e (rewritten using rebase as 11)
    | | |
    | | x  5 d' (rewritten using rebase as 10)
    | | |
    | x |  4 d
    | |/
    | x  3 c (rewritten using rebase as 9)
    | |
    o |  2 x
    | |
    | x  1 b (rewritten using rebase as 8)
    |/
    o  0 a

where branch 4:: is left behind while branch 5:: is rebased as expected.

The rationale is that users may not be interested in rebasing orphan
changesets when specifying a rebase set that include them but would
still want "stable" ones to be rebased. Currently, the user is suggested
to allow divergence (but probably does not want it) or they must specify
a rebase set excluding problematic changesets (which might be a bit
cumbersome). The approach proposed here corresponds to "Option 2" in
https://www.mercurial-scm.org/wiki/CEDRebase.


We extend _computeobsoletenotrebased() so that it also return a set of
obsolete changesets in rebase set without a successor in destination but
with at least one successor in rebase set. This
'obsoletewithoutsuccessorindestination' is then stored as an attribute
of rebaseruntime and used in _performrebasesubset() to:

* filter out descendants of these changesets from the revisions to
  rebase;
* issue a message about these revisions being skipped.

This only occurs if 'evolution.allowdivergence' option is off and
'rebaseskipobsolete' is on.

# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 Matt Mackall <[e-mail]>
#
# 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 collections

from .i18n import _
from .node import (
    nullid,
    short,
)
from . import (
    error,
)

def findcommonincoming(repo, remote, heads=None, force=False):
    """Return a tuple (common, fetch, heads) used to identify the common
    subset of nodes between repo and remote.

    "common" is a list of (at least) the heads of the common subset.
    "fetch" is a list of roots of the nodes that would be incoming, to be
      supplied to changegroupsubset.
    "heads" is either the supplied heads, or else the remote's heads.
    """

    knownnode = repo.changelog.hasnode
    search = []
    fetch = set()
    seen = set()
    seenbranch = set()
    base = set()

    if not heads:
        heads = remote.heads()

    if repo.changelog.tip() == nullid:
        base.add(nullid)
        if heads != [nullid]:
            return [nullid], [nullid], list(heads)
        return [nullid], [], heads

    # assume we're closer to the tip than the root
    # and start by examining the heads
    repo.ui.status(_("searching for changes\n"))

    unknown = []
    for h in heads:
        if not knownnode(h):
            unknown.append(h)
        else:
            base.add(h)

    if not unknown:
        return list(base), [], list(heads)

    req = set(unknown)
    reqcnt = 0

    # search through remote branches
    # a 'branch' here is a linear segment of history, with four parts:
    # head, root, first parent, second parent
    # (a branch always has two parents (or none) by definition)
    unknown = collections.deque(remote.branches(unknown))
    while unknown:
        r = []
        while unknown:
            n = unknown.popleft()
            if n[0] in seen:
                continue

            repo.ui.debug("examining %s:%s\n"
                          % (short(n[0]), short(n[1])))
            if n[0] == nullid: # found the end of the branch
                pass
            elif n in seenbranch:
                repo.ui.debug("branch already found\n")
                continue
            elif n[1] and knownnode(n[1]): # do we know the base?
                repo.ui.debug("found incomplete branch %s:%s\n"
                              % (short(n[0]), short(n[1])))
                search.append(n[0:2]) # schedule branch range for scanning
                seenbranch.add(n)
            else:
                if n[1] not in seen and n[1] not in fetch:
                    if knownnode(n[2]) and knownnode(n[3]):
                        repo.ui.debug("found new changeset %s\n" %
                                      short(n[1]))
                        fetch.add(n[1]) # earliest unknown
                    for p in n[2:4]:
                        if knownnode(p):
                            base.add(p) # latest known

                for p in n[2:4]:
                    if p not in req and not knownnode(p):
                        r.append(p)
                        req.add(p)
            seen.add(n[0])

        if r:
            reqcnt += 1
            repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
            repo.ui.debug("request %d: %s\n" %
                        (reqcnt, " ".join(map(short, r))))
            for p in xrange(0, len(r), 10):
                for b in remote.branches(r[p:p + 10]):
                    repo.ui.debug("received %s:%s\n" %
                                  (short(b[0]), short(b[1])))
                    unknown.append(b)

    # do binary search on the branches we found
    while search:
        newsearch = []
        reqcnt += 1
        repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
        for n, l in zip(search, remote.between(search)):
            l.append(n[1])
            p = n[0]
            f = 1
            for i in l:
                repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
                if knownnode(i):
                    if f <= 2:
                        repo.ui.debug("found new branch changeset %s\n" %
                                          short(p))
                        fetch.add(p)
                        base.add(i)
                    else:
                        repo.ui.debug("narrowed branch search to %s:%s\n"
                                      % (short(p), short(i)))
                        newsearch.append((p, i))
                    break
                p, f = i, f * 2
            search = newsearch

    # sanity check our fetch list
    for f in fetch:
        if knownnode(f):
            raise error.RepoError(_("already have changeset ")
                                  + short(f[:4]))

    base = list(base)
    if base == [nullid]:
        if force:
            repo.ui.warn(_("warning: repository is unrelated\n"))
        else:
            raise error.Abort(_("repository is unrelated"))

    repo.ui.debug("found new changesets starting at " +
                 " ".join([short(f) for f in fetch]) + "\n")

    repo.ui.progress(_('searching'), None)
    repo.ui.debug("%d total queries\n" % reqcnt)

    return base, list(fetch), heads