annotate mercurial/copies.py @ 6858:8f256bf98219

Add support for multiple possible bisect results (issue1228, issue1182)

The real reason for both issue is that bisect can not handle cases where there
are multiple possibilities for the result.

Example (from issue1228):
rev 0 -> good
rev 1 -> skipped
rev 2 -> skipped
rev 3 -> skipped
rev 4 -> bad

Note that this patch does not only fix the reported Assertion Error but also
the problem of a non converging bisect:

hg init
for i in `seq 3`; do echo $i > $i; hg add $i; hg ci -m$i; done
hg bisect -b 2
hg bisect -g 0
hg bisect -s

From this state on, you can:
 a) mark as bad forever (non converging!)
 b) mark as good to get an inconsistent state
 c) skip for the Assertion Error

Minor description and code edits by pmezard.

# copies.py - copy detection for Mercurial
#
# Copyright 2008 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

from node import nullid, nullrev
from i18n import _
import util, heapq

def _nonoverlap(d1, d2, d3):
    "Return list of elements in d1 not in d2 or d3"
    l = [d for d in d1 if d not in d3 and d not in d2]
    l.sort()
    return l

def _dirname(f):
    s = f.rfind("/")
    if s == -1:
        return ""
    return f[:s]

def _dirs(files):
    d = {}
    for f in files:
        f = _dirname(f)
        while f not in d:
            d[f] = True
            f = _dirname(f)
    return d

def _findoldnames(fctx, limit):
    "find files that path was copied from, back to linkrev limit"
    old = {}
    seen = {}
    orig = fctx.path()
    visit = [(fctx, 0)]
    while visit:
        fc, depth = visit.pop()
        s = str(fc)
        if s in seen:
            continue
        seen[s] = 1
        if fc.path() != orig and fc.path() not in old:
            old[fc.path()] = (depth, fc.path()) # remember depth
        if fc.rev() < limit and fc.rev() is not None:
            continue
        visit += [(p, depth - 1) for p in fc.parents()]

    # return old names sorted by depth
    old = old.values()
    old.sort()
    return [o[1] for o in old]

def _findlimit(repo, a, b):
    "find the earliest revision that's an ancestor of a or b but not both"
    # 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 = cl.count() # 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)
    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 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
        if side[r]:
            limit = r # lowest rev visited
            interesting -= 1
    return limit

def copies(repo, c1, c2, ca, checkdirs=False):
    """
    Find moves and copies between context c1 and c2
    """
    # avoid silly behavior for update from empty dir
    if not c1 or not c2 or c1 == c2:
        return {}, {}

    limit = _findlimit(repo, c1.rev(), c2.rev())
    m1 = c1.manifest()
    m2 = c2.manifest()
    ma = ca.manifest()

    def makectx(f, n):
        if len(n) != 20: # in a working context?
            if c1.rev() is None:
                return c1.filectx(f)
            return c2.filectx(f)
        return repo.filectx(f, fileid=n)
    ctx = util.cachefunc(makectx)

    copy = {}
    fullcopy = {}
    diverge = {}

    def checkcopies(f, m1, m2):
        '''check possible copies of f from m1 to m2'''
        c1 = ctx(f, m1[f])
        for of in _findoldnames(c1, limit):
            fullcopy[f] = of # remember for dir rename detection
            if of in m2: # original file not in other manifest?
                # if the original file is unchanged on the other branch,
                # no merge needed
                if m2[of] != ma.get(of):
                    c2 = ctx(of, m2[of])
                    ca = c1.ancestor(c2)
                    # related and named changed on only one side?
                    if ca and (ca.path() == f or ca.path() == c2.path()):
                        if c1 != ca or c2 != ca: # merge needed?
                            copy[f] = of
            elif of in ma:
                diverge.setdefault(of, []).append(f)

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

    u1 = _nonoverlap(m1, m2, ma)
    u2 = _nonoverlap(m2, m1, ma)

    if u1:
        repo.ui.debug(_("  unmatched files in local:\n   %s\n")
                      % "\n   ".join(u1))
    if u2:
        repo.ui.debug(_("  unmatched files in other:\n   %s\n")
                      % "\n   ".join(u2))

    for f in u1:
        checkcopies(f, m1, m2)
    for f in u2:
        checkcopies(f, m2, m1)

    diverge2 = {}
    for of, fl in diverge.items():
        if len(fl) == 1:
            del diverge[of] # not actually divergent
        else:
            diverge2.update(dict.fromkeys(fl)) # reverse map for below

    if fullcopy:
        repo.ui.debug(_("  all copies found (* = to merge, ! = divergent):\n"))
        for f in fullcopy:
            note = ""
            if f in copy: note += "*"
            if f in diverge2: note += "!"
            repo.ui.debug(_("   %s -> %s %s\n") % (f, fullcopy[f], note))
    del diverge2

    if not fullcopy or not checkdirs:
        return copy, diverge

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

    # generate a directory move map
    d1, d2 = _dirs(m1), _dirs(m2)
    invalid = {}
    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 fullcopy.items():
        dsrc, ddst = _dirname(src), _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[dsrc] = True
        elif dsrc in d2 and ddst in d2:
            # directory wasn't entirely moved remotely
            invalid[dsrc] = True
        elif dsrc in dirmove and dirmove[dsrc] != ddst:
            # files from the same directory moved to two different places
            invalid[dsrc] = True
        else:
            # looks good so far
            dirmove[dsrc + "/"] = ddst + "/"

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

    if not dirmove:
        return copy, diverge

    for d in dirmove:
        repo.ui.debug(_("  dir %s -> %s\n") % (d, dirmove[d]))

    # 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):]
                    if df not in copy:
                        copy[f] = df
                        repo.ui.debug(_("  file %s -> %s\n") % (f, copy[f]))
                    break

    return copy, diverge