copies: fix the changeset based algorithm regarding merge

In 99ebde4fec99, we changed the list of files stored into the `files` field.
This lead to the changeset centric copy algorithm to break in various merge
situation involving merge. Older information could reach the merge through
`p1`, and while information from `p2` was strictly fresher, it would get
overwritten anyway.

We update the situation with more details about which revision introduces rename
information. This help use making the right decision in case of merge.

We are now running a more comprehensive suite of test with include this kind of
situation. The behavior differ slightly from the filelog based in a couple of
instance. There is mostly two distinct cases:

1) there are conflicting rename information in a merge (different rename history
on each side). In this case the filelog based implementation arbitrarily pick a
side based on the file-revision-number. So it depends on a local factor. The
changeset centric algorithm will use a deterministic approach, by picking the
information coming from the first parent of the merge. This is stable across
different clone.

2) rename information related to file that exist in both source and destination.
The filelog based implementation do not even try to detect these, however the
changeset centric one get them for "free" (it is simpler to detect them than
not).

The new implementation focus on correctness. Performance improvement will come
later.

Differential Revision: https://phab.mercurial-scm.org/D8244

mercurial/copies.py

@@ -1,1171 +1,1241 b''
 # 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 version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import multiprocessing
 import os
 
 from .i18n import _
 
 
 from .revlogutils.flagutil import REVIDX_SIDEDATA
 
 from . import (
     error,
     match as matchmod,
     node,
     pathutil,
     pycompat,
     util,
 )
 
 from .revlogutils import sidedata as sidedatamod
 
 from .utils import stringutil
 
 
 def _filter(src, dst, t):
     """filters out invalid copies after chaining"""
 
     # When _chain()'ing copies in 'a' (from 'src' via some other commit 'mid')
     # with copies in 'b' (from 'mid' to 'dst'), we can get the different cases
     # in the following table (not including trivial cases). For example, case 2
     # is where a file existed in 'src' and remained under that name in 'mid' and
     # then was renamed between 'mid' and 'dst'.
     #
     # case src mid dst result
     #   1   x   y   -    -
     #   2   x   y   y   x->y
     #   3   x   y   x    -
     #   4   x   y   z   x->z
     #   5   -   x   y    -
     #   6   x   x   y   x->y
     #
     # _chain() takes care of chaining the copies in 'a' and 'b', but it
     # cannot tell the difference between cases 1 and 2, between 3 and 4, or
     # between 5 and 6, so it includes all cases in its result.
     # Cases 1, 3, and 5 are then removed by _filter().
 
     for k, v in list(t.items()):
         # remove copies from files that didn't exist
         if v not in src:
             del t[k]
         # remove criss-crossed copies
         elif k in src and v in dst:
             del t[k]
         # remove copies to files that were then removed
         elif k not in dst:
             del t[k]
 
 
 def _chain(prefix, suffix):
     """chain two sets of copies 'prefix' and 'suffix'"""
     result = prefix.copy()
     for key, value in pycompat.iteritems(suffix):
         result[key] = prefix.get(value, value)
     return result
 
 
 def _tracefile(fctx, am, basemf):
     """return file context that is the ancestor of fctx present in ancestor
     manifest am
 
     Note: we used to try and stop after a given limit, however checking if that
     limit is reached turned out to be very expensive. we are better off
     disabling that feature."""
 
     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
 
 
 def _dirstatecopies(repo, match=None):
     ds = repo.dirstate
     c = ds.copies().copy()
     for k in list(c):
         if ds[k] not in b'anm' or (match and not match(k)):
             del c[k]
     return c
 
 
 def _computeforwardmissing(a, b, match=None):
     """Computes which files are in b but not a.
     This is its own function so extensions can easily wrap this call to see what
     files _forwardcopies is about to process.
     """
     ma = a.manifest()
     mb = b.manifest()
     return mb.filesnotin(ma, match=match)
 
 
 def usechangesetcentricalgo(repo):
     """Checks if we should use changeset-centric copy algorithms"""
     if repo.filecopiesmode == b'changeset-sidedata':
         return True
     readfrom = repo.ui.config(b'experimental', b'copies.read-from')
     changesetsource = (b'changeset-only', b'compatibility')
     return readfrom in changesetsource
 
 
 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
 
     if usechangesetcentricalgo(repo):
         return _changesetforwardcopies(a, b, match)
 
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     dbg = repo.ui.debug
     if debug:
         dbg(b'debug.copies:    looking into rename from %s to %s\n' % (a, b))
     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 = {}
 
     # Computing the forward missing is quite expensive on large manifests, since
     # it compares the entire manifests. We can optimize it in the common use
     # case of computing what copies are in a commit versus its parent (like
     # during a rebase or histedit). Note, we exclude merge commits from this
     # optimization, since the ctx.files() for a merge commit is not correct for
     # this comparison.
     forwardmissingmatch = match
     if b.p1() == a and b.p2().node() == node.nullid:
         filesmatcher = matchmod.exact(b.files())
         forwardmissingmatch = matchmod.intersectmatchers(match, filesmatcher)
     missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
 
     if debug:
         dbg(b'debug.copies:      missing files to search: %d\n' % len(missing))
 
     for f in sorted(missing):
         if debug:
             dbg(b'debug.copies:        tracing file: %s\n' % f)
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
 
         if debug:
             start = util.timer()
         opath = _tracefile(fctx, am, basemf)
         if opath:
             if debug:
                 dbg(b'debug.copies:          rename of: %s\n' % opath)
             cm[f] = opath
         if debug:
             dbg(
                 b'debug.copies:          time: %f seconds\n'
                 % (util.timer() - start)
             )
     return cm
 
 
 def _revinfogetter(repo):
     """return a function that return multiple data given a <rev>"i
 
     * p1: revision number of first parent
     * p2: revision number of first parent
     * p1copies: mapping of copies from p1
     * p2copies: mapping of copies from p2
     * removed: a list of removed files
+    * ismerged: a callback to know if file was merged in that revision
     """
     cl = repo.changelog
     parents = cl.parentrevs
 
+    def get_ismerged(rev):
+        ctx = repo[rev]
+
+        def ismerged(path):
+            if path not in ctx.files():
+                return False
+            fctx = ctx[path]
+            parents = fctx._filelog.parents(fctx._filenode)
+            nb_parents = 0
+            for n in parents:
+                if n != node.nullid:
+                    nb_parents += 1
+            return nb_parents >= 2
+
+        return ismerged
+
     if repo.filecopiesmode == b'changeset-sidedata':
         changelogrevision = cl.changelogrevision
         flags = cl.flags
 
         # A small cache to avoid doing the work twice for merges
         #
         # In the vast majority of cases, if we ask information for a revision
         # about 1 parent, we'll later ask it for the other. So it make sense to
         # keep the information around when reaching the first parent of a merge
         # and dropping it after it was provided for the second parents.
         #
         # It exists cases were only one parent of the merge will be walked. It
         # happens when the "destination" the copy tracing is descendant from a
         # new root, not common with the "source". In that case, we will only walk
         # through merge parents that are descendant of changesets common
         # between "source" and "destination".
         #
         # With the current case implementation if such changesets have a copy
         # information, we'll keep them in memory until the end of
         # _changesetforwardcopies. We don't expect the case to be frequent
         # enough to matters.
         #
         # In addition, it would be possible to reach pathological case, were
         # many first parent are met before any second parent is reached. In
         # that case the cache could grow. If this even become an issue one can
         # safely introduce a maximum cache size. This would trade extra CPU/IO
         # time to save memory.
         merge_caches = {}
 
         def revinfo(rev):
             p1, p2 = parents(rev)
+            value = None
             if flags(rev) & REVIDX_SIDEDATA:
                 e = merge_caches.pop(rev, None)
                 if e is not None:
                     return e
                 c = changelogrevision(rev)
                 p1copies = c.p1copies
                 p2copies = c.p2copies
                 removed = c.filesremoved
                 if p1 != node.nullrev and p2 != node.nullrev:
                     # XXX some case we over cache, IGNORE
-                    merge_caches[rev] = (p1, p2, p1copies, p2copies, removed)
+                    value = merge_caches[rev] = (
+                        p1,
+                        p2,
+                        p1copies,
+                        p2copies,
+                        removed,
+                        get_ismerged(rev),
+                    )
             else:
                 p1copies = {}
                 p2copies = {}
                 removed = []
-            return p1, p2, p1copies, p2copies, removed
+
+            if value is None:
+                value = (p1, p2, p1copies, p2copies, removed, get_ismerged(rev))
+            return value
 
     else:
 
         def revinfo(rev):
             p1, p2 = parents(rev)
             ctx = repo[rev]
             p1copies, p2copies = ctx._copies
             removed = ctx.filesremoved()
-            return p1, p2, p1copies, p2copies, removed
+            return p1, p2, p1copies, p2copies, removed, get_ismerged(rev)
 
     return revinfo
 
 
 def _changesetforwardcopies(a, b, match):
     if a.rev() in (node.nullrev, b.rev()):
         return {}
 
     repo = a.repo().unfiltered()
     children = {}
     revinfo = _revinfogetter(repo)
 
     cl = repo.changelog
+    isancestor = cl.isancestorrev  # XXX we should had chaching to this.
     missingrevs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()])
     mrset = set(missingrevs)
     roots = set()
     for r in missingrevs:
         for p in cl.parentrevs(r):
             if p == node.nullrev:
                 continue
             if p not in children:
                 children[p] = [r]
             else:
                 children[p].append(r)
             if p not in mrset:
                 roots.add(p)
     if not roots:
         # no common revision to track copies from
         return {}
     min_root = min(roots)
 
     from_head = set(
         cl.reachableroots(min_root, [b.rev()], list(roots), includepath=True)
     )
 
     iterrevs = set(from_head)
     iterrevs &= mrset
     iterrevs.update(roots)
     iterrevs.remove(b.rev())
     revs = sorted(iterrevs)
-    return _combinechangesetcopies(revs, children, b.rev(), revinfo, match)
+    return _combinechangesetcopies(
+        revs, children, b.rev(), revinfo, match, isancestor
+    )
 
 
-def _combinechangesetcopies(revs, children, targetrev, revinfo, match):
+def _combinechangesetcopies(
+    revs, children, targetrev, revinfo, match, isancestor
+):
     """combine the copies information for each item of iterrevs
 
     revs: sorted iterable of revision to visit
     children: a {parent: [children]} mapping.
     targetrev: the final copies destination revision (not in iterrevs)
     revinfo(rev): a function that return (p1, p2, p1copies, p2copies, removed)
     match: a matcher
 
     It returns the aggregated copies information for `targetrev`.
     """
     all_copies = {}
     alwaysmatch = match.always()
     for r in revs:
         copies = all_copies.pop(r, None)
         if copies is None:
             # this is a root
             copies = {}
         for i, c in enumerate(children[r]):
-            p1, p2, p1copies, p2copies, removed = revinfo(c)
+            p1, p2, p1copies, p2copies, removed, ismerged = revinfo(c)
             if r == p1:
                 parent = 1
                 childcopies = p1copies
             else:
                 assert r == p2
                 parent = 2
                 childcopies = p2copies
             if not alwaysmatch:
                 childcopies = {
                     dst: src for dst, src in childcopies.items() if match(dst)
                 }
             newcopies = copies
             if childcopies:
-                newcopies = _chain(newcopies, childcopies)
-                # _chain makes a copies, we can avoid doing so in some
-                # simple/linear cases.
+                newcopies = copies.copy()
+                for dest, source in pycompat.iteritems(childcopies):
+                    prev = copies.get(source)
+                    if prev is not None and prev[1] is not None:
+                        source = prev[1]
+                    newcopies[dest] = (c, source)
                 assert newcopies is not copies
             for f in removed:
                 if f in newcopies:
                     if newcopies is copies:
                         # copy on write to avoid affecting potential other
                         # branches.  when there are no other branches, this
                         # could be avoided.
                         newcopies = copies.copy()
-                    del newcopies[f]
+                    newcopies[f] = (c, None)
             othercopies = all_copies.get(c)
             if othercopies is None:
                 all_copies[c] = newcopies
             else:
                 # we are the second parent to work on c, we need to merge our
                 # work with the other.
                 #
-                # Unlike when copies are stored in the filelog, we consider
-                # it a copy even if the destination already existed on the
-                # other branch. It's simply too expensive to check if the
-                # file existed in the manifest.
-                #
                 # In case of conflict, parent 1 take precedence over parent 2.
                 # This is an arbitrary choice made anew when implementing
                 # changeset based copies. It was made without regards with
                 # potential filelog related behavior.
                 if parent == 1:
-                    othercopies.update(newcopies)
+                    _merge_copies_dict(
+                        othercopies, newcopies, isancestor, ismerged
+                    )
                 else:
-                    newcopies.update(othercopies)
+                    _merge_copies_dict(
+                        newcopies, othercopies, isancestor, ismerged
+                    )
                     all_copies[c] = newcopies
-    return all_copies[targetrev]
+
+    final_copies = {}
+    for dest, (tt, source) in all_copies[targetrev].items():
+        if source is not None:
+            final_copies[dest] = source
+    return final_copies
+
+
+def _merge_copies_dict(minor, major, isancestor, ismerged):
+    """merge two copies-mapping together, minor and major
+
+    In case of conflict, value from "major" will be picked.
+
+    - `isancestors(low_rev, high_rev)`: callable return True if `low_rev` is an
+                                        ancestors of `high_rev`,
+
+    - `ismerged(path)`: callable return True if `path` have been merged in the
+                        current revision,
+    """
+    for dest, value in major.items():
+        other = minor.get(dest)
+        if other is None:
+            minor[dest] = value
+        else:
+            new_tt = value[0]
+            other_tt = other[0]
+            if value[1] == other[1]:
+                continue
+            # content from "major" wins, unless it is older
+            # than the branch point or there is a merge
+            if (
+                new_tt == other_tt
+                or not isancestor(new_tt, other_tt)
+                or ismerged(dest)
+            ):
+                minor[dest] = value
 
 
 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(b'experimental', b'copytrace') == b'off':
         return {}
 
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     # We don't want to pass in "match" here, since that would filter
     # the destination by it. Since we're reversing the copies, we want
     # to filter the source instead.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(pycompat.iteritems(f)):
         if match and not match(v):
             continue
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 
 def pathcopies(x, y, match=None):
     """find {dst@y: src@x} copy mapping for directed compare"""
     repo = x._repo
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     if debug:
         repo.ui.debug(
             b'debug.copies: searching copies from %s to %s\n' % (x, y)
         )
     if x == y or not x or not y:
         return {}
     if y.rev() is None and x == y.p1():
         if debug:
             repo.ui.debug(b'debug.copies: search mode: dirstate\n')
         # short-circuit to avoid issues with merge states
         return _dirstatecopies(repo, match)
     a = y.ancestor(x)
     if a == x:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: forward\n')
         copies = _forwardcopies(x, y, match=match)
     elif a == y:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: backward\n')
         copies = _backwardrenames(x, y, match=match)
     else:
         if debug:
             repo.ui.debug(b'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):
     """
     Finds moves and copies between context c1 and c2 that are relevant for
     merging. 'base' will be used as the merge base.
 
     Copytracing is used in commands like rebase, merge, unshelve, etc to merge
     files that were moved/ copied in one merge parent and modified in another.
     For example:
 
     o          ---> 4 another commit
     |
     |   o      ---> 3 commit that modifies a.txt
     |  /
     o /        ---> 2 commit that moves a.txt to b.txt
     |/
     o          ---> 1 merge base
 
     If we try to rebase revision 3 on revision 4, since there is no a.txt in
     revision 4, and if user have copytrace disabled, we prints the following
     message:
 
     ```other changed <file> which local deleted```
 
     Returns a tuple where:
 
     "branch_copies" an instance of branch_copies.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     This function calls different copytracing algorithms based on config.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return branch_copies(), branch_copies(), {}
 
     narrowmatch = c1.repo().narrowmatch()
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return (
             branch_copies(_dirstatecopies(repo, narrowmatch)),
             branch_copies(),
             {},
         )
 
     copytracing = repo.ui.config(b'experimental', b'copytrace')
     if stringutil.parsebool(copytracing) is False:
         # stringutil.parsebool() returns None when it is unable to parse the
         # value, so we should rely on making sure copytracing is on such cases
         return branch_copies(), branch_copies(), {}
 
     if usechangesetcentricalgo(repo):
         # The heuristics don't make sense when we need changeset-centric algos
         return _fullcopytracing(repo, c1, c2, base)
 
     # Copy trace disabling is explicitly below the node == p1 logic above
     # because the logic above is required for a simple copy to be kept across a
     # rebase.
     if copytracing == b'heuristics':
         # Do full copytracing if only non-public revisions are involved as
         # that will be fast enough and will also cover the copies which could
         # be missed by heuristics
         if _isfullcopytraceable(repo, c1, base):
             return _fullcopytracing(repo, c1, c2, base)
         return _heuristicscopytracing(repo, c1, c2, base)
     else:
         return _fullcopytracing(repo, c1, c2, base)
 
 
 def _isfullcopytraceable(repo, c1, base):
     """ Checks that if base, source and destination are all no-public branches,
     if yes let's use the full copytrace algorithm for increased capabilities
     since it will be fast enough.
 
     `experimental.copytrace.sourcecommitlimit` can be used to set a limit for
     number of changesets from c1 to base such that if number of changesets are
     more than the limit, full copytracing algorithm won't be used.
     """
     if c1.rev() is None:
         c1 = c1.p1()
     if c1.mutable() and base.mutable():
         sourcecommitlimit = repo.ui.configint(
             b'experimental', b'copytrace.sourcecommitlimit'
         )
         commits = len(repo.revs(b'%d::%d', base.rev(), c1.rev()))
         return commits < sourcecommitlimit
     return False
 
 
 def _checksinglesidecopies(
     src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
 ):
     if src not in m2:
         # deleted on side 2
         if src not in m1:
             # renamed on side 1, deleted on side 2
             renamedelete[src] = dsts1
     elif src not in mb:
         # Work around the "short-circuit to avoid issues with merge states"
         # thing in pathcopies(): pathcopies(x, y) can return a copy where the
         # destination doesn't exist in y.
         pass
     elif m2[src] != mb[src]:
         if not _related(c2[src], base[src]):
             return
         # modified on side 2
         for dst in dsts1:
             copy[dst] = src
 
 
 class branch_copies(object):
     """Information about copies made on one side of a merge/graft.
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
 
     "dirmove" is a mapping of detected source dir -> destination dir renames.
     This is needed for handling changes to new files previously grafted into
     renamed directories.
     """
 
     def __init__(
         self, copy=None, renamedelete=None, dirmove=None, movewithdir=None
     ):
         self.copy = {} if copy is None else copy
         self.renamedelete = {} if renamedelete is None else renamedelete
         self.dirmove = {} if dirmove is None else dirmove
         self.movewithdir = {} if movewithdir is None else movewithdir
 
 
 def _fullcopytracing(repo, c1, c2, base):
     """ The full copytracing algorithm which finds all the new files that were
     added from merge base up to the top commit and for each file it checks if
     this file was copied from another file.
 
     This is pretty slow when a lot of changesets are involved but will track all
     the copies.
     """
     m1 = c1.manifest()
     m2 = c2.manifest()
     mb = base.manifest()
 
     copies1 = pathcopies(base, c1)
     copies2 = pathcopies(base, c2)
 
     if not (copies1 or copies2):
         return branch_copies(), branch_copies(), {}
 
     inversecopies1 = {}
     inversecopies2 = {}
     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:
             # copied/renamed on both sides
             if src not in m1 and src not in m2:
                 # renamed on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 # If there's some overlap in the rename destinations, we
                 # 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())
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
     header = b"  unmatched files in %s"
     if u1:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1)))
     if u2:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2)))
 
     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 side, copies in ((b"local", copies1), (b"remote", copies2)):
             if not copies:
                 continue
             repo.ui.debug(b"   on %s side:\n" % side)
             for f in sorted(copies):
                 note = b""
                 if f in copy1 or f in copy2:
                     note += b"*"
                 if f in divergeset:
                     note += b"!"
                 if f in renamedeleteset:
                     note += b"%"
                 repo.ui.debug(
                     b"    src: '%s' -> dst: '%s' %s\n" % (copies[f], f, note)
                 )
         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)
 
     branch_copies1 = branch_copies(copy1, renamedelete1, dirmove1, movewithdir1)
     branch_copies2 = branch_copies(copy2, renamedelete2, dirmove2, movewithdir2)
 
     return branch_copies1, branch_copies2, diverge
 
 
 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:
             # looks good so far
             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)}
 
     for d in dirmove:
         repo.ui.debug(
             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) :]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(
                             b"   pending file src: '%s' -> dst: '%s'\n"
                             % (f, df)
                         )
                     break
 
     return dirmove, movewithdir
 
 
 def _heuristicscopytracing(repo, c1, c2, base):
     """ Fast copytracing using filename heuristics
 
     Assumes that moves or renames are of following two types:
 
     1) Inside a directory only (same directory name but different filenames)
     2) Move from one directory to another
                     (same filenames but different directory names)
 
     Works only when there are no merge commits in the "source branch".
     Source branch is commits from base up to c2 not including base.
 
     If merge is involved it fallbacks to _fullcopytracing().
 
     Can be used by setting the following config:
 
         [experimental]
         copytrace = heuristics
 
     In some cases the copy/move candidates found by heuristics can be very large
     in number and that will make the algorithm slow. The number of possible
     candidates to check can be limited by using the config
     `experimental.copytrace.movecandidateslimit` which defaults to 100.
     """
 
     if c1.rev() is None:
         c1 = c1.p1()
     if c2.rev() is None:
         c2 = c2.p1()
 
     changedfiles = set()
     m1 = c1.manifest()
     if not repo.revs(b'%d::%d', base.rev(), c2.rev()):
         # If base is not in c2 branch, we switch to fullcopytracing
         repo.ui.debug(
             b"switching to full copytracing as base is not "
             b"an ancestor of c2\n"
         )
         return _fullcopytracing(repo, c1, c2, base)
 
     ctx = c2
     while ctx != base:
         if len(ctx.parents()) == 2:
             # To keep things simple let's not handle merges
             repo.ui.debug(b"switching to full copytracing because of merges\n")
             return _fullcopytracing(repo, c1, c2, base)
         changedfiles.update(ctx.files())
         ctx = ctx.p1()
 
     copies2 = {}
     cp = _forwardcopies(base, c2)
     for dst, src in pycompat.iteritems(cp):
         if src in m1:
             copies2[dst] = src
 
     # file is missing if it isn't present in the destination, but is present in
     # the base and present in the source.
     # Presence in the base is important to exclude added files, presence in the
     # source is important to exclude removed files.
     filt = lambda f: f not in m1 and f in base and f in c2
     missingfiles = [f for f in changedfiles if filt(f)]
 
     copies1 = {}
     if missingfiles:
         basenametofilename = collections.defaultdict(list)
         dirnametofilename = collections.defaultdict(list)
 
         for f in m1.filesnotin(base.manifest()):
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             basenametofilename[basename].append(f)
             dirnametofilename[dirname].append(f)
 
         for f in missingfiles:
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             samebasename = basenametofilename[basename]
             samedirname = dirnametofilename[dirname]
             movecandidates = samebasename + samedirname
             # f is guaranteed to be present in c2, that's why
             # c2.filectx(f) won't fail
             f2 = c2.filectx(f)
             # we can have a lot of candidates which can slow down the heuristics
             # config value to limit the number of candidates moves to check
             maxcandidates = repo.ui.configint(
                 b'experimental', b'copytrace.movecandidateslimit'
             )
 
             if len(movecandidates) > maxcandidates:
                 repo.ui.status(
                     _(
                         b"skipping copytracing for '%s', more "
                         b"candidates than the limit: %d\n"
                     )
                     % (f, len(movecandidates))
                 )
                 continue
 
             for candidate in movecandidates:
                 f1 = c1.filectx(candidate)
                 if _related(f1, f2):
                     # if there are a few related copies then we'll merge
                     # changes into all of them. This matches the behaviour
                     # of upstream copytracing
                     copies1[candidate] = f
 
     return branch_copies(copies1), branch_copies(copies2), {}
 
 
 def _related(f1, f2):
     """return True if f1 and f2 filectx have a common ancestor
 
     Walk back to common ancestor to see if the two files originate
     from the same file. Since workingfilectx's rev() is None it messes
     up the integer comparison logic, hence the pre-step check for
     None (f1 and f2 can only be workingfilectx's initially).
     """
 
     if f1 == f2:
         return True  # a match
 
     g1, g2 = f1.ancestors(), f2.ancestors()
     try:
         f1r, f2r = f1.linkrev(), f2.linkrev()
 
         if f1r is None:
             f1 = next(g1)
         if f2r is None:
             f2 = next(g2)
 
         while True:
             f1r, f2r = f1.linkrev(), f2.linkrev()
             if f1r > f2r:
                 f1 = next(g1)
             elif f2r > f1r:
                 f2 = next(g2)
             else:  # f1 and f2 point to files in the same linkrev
                 return f1 == f2  # true if they point to the same file
     except StopIteration:
         return False
 
 
 def graftcopies(wctx, ctx, base):
     """reproduce copies between base and ctx in the wctx
 
     Unlike mergecopies(), this function will only consider copies between base
     and ctx; it will ignore copies between base and wctx. Also unlike
     mergecopies(), this function will apply copies to the working copy (instead
     of just returning information about the copies). That makes it cheaper
     (especially in the common case of base==ctx.p1()) and useful also when
     experimental.copytrace=off.
 
     merge.update() will have already marked most copies, but it will only
     mark copies if it thinks the source files are related (see
     merge._related()). It will also not mark copies if the file wasn't modified
     on the local side. This function adds the copies that were "missed"
     by merge.update().
     """
     new_copies = pathcopies(base, ctx)
     _filter(wctx.p1(), wctx, new_copies)
     for dst, src in pycompat.iteritems(new_copies):
         wctx[dst].markcopied(src)
 
 
 def computechangesetfilesadded(ctx):
     """return the list of files added in a changeset
     """
     added = []
     for f in ctx.files():
         if not any(f in p for p in ctx.parents()):
             added.append(f)
     return added
 
 
 def computechangesetfilesremoved(ctx):
     """return the list of files removed in a changeset
     """
     removed = []
     for f in ctx.files():
         if f not in ctx:
             removed.append(f)
     return removed
 
 
 def computechangesetcopies(ctx):
     """return the copies data for a changeset
 
     The copies data are returned as a pair of dictionnary (p1copies, p2copies).
 
     Each dictionnary are in the form: `{newname: oldname}`
     """
     p1copies = {}
     p2copies = {}
     p1 = ctx.p1()
     p2 = ctx.p2()
     narrowmatch = ctx._repo.narrowmatch()
     for dst in ctx.files():
         if not narrowmatch(dst) or dst not in ctx:
             continue
         copied = ctx[dst].renamed()
         if not copied:
             continue
         src, srcnode = copied
         if src in p1 and p1[src].filenode() == srcnode:
             p1copies[dst] = src
         elif src in p2 and p2[src].filenode() == srcnode:
             p2copies[dst] = src
     return p1copies, p2copies
 
 
 def encodecopies(files, copies):
     items = []
     for i, dst in enumerate(files):
         if dst in copies:
             items.append(b'%d\0%s' % (i, copies[dst]))
     if len(items) != len(copies):
         raise error.ProgrammingError(
             b'some copy targets missing from file list'
         )
     return b"\n".join(items)
 
 
 def decodecopies(files, data):
     try:
         copies = {}
         if not data:
             return copies
         for l in data.split(b'\n'):
             strindex, src = l.split(b'\0')
             i = int(strindex)
             dst = files[i]
             copies[dst] = src
         return copies
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "p1copies") and
         # used different syntax for the value.
         return None
 
 
 def encodefileindices(files, subset):
     subset = set(subset)
     indices = []
     for i, f in enumerate(files):
         if f in subset:
             indices.append(b'%d' % i)
     return b'\n'.join(indices)
 
 
 def decodefileindices(files, data):
     try:
         subset = []
         if not data:
             return subset
         for strindex in data.split(b'\n'):
             i = int(strindex)
             if i < 0 or i >= len(files):
                 return None
             subset.append(files[i])
         return subset
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "added") and
         # used different syntax for the value.
         return None
 
 
 def _getsidedata(srcrepo, rev):
     ctx = srcrepo[rev]
     filescopies = computechangesetcopies(ctx)
     filesadded = computechangesetfilesadded(ctx)
     filesremoved = computechangesetfilesremoved(ctx)
     sidedata = {}
     if any([filescopies, filesadded, filesremoved]):
         sortedfiles = sorted(ctx.files())
         p1copies, p2copies = filescopies
         p1copies = encodecopies(sortedfiles, p1copies)
         p2copies = encodecopies(sortedfiles, p2copies)
         filesadded = encodefileindices(sortedfiles, filesadded)
         filesremoved = encodefileindices(sortedfiles, filesremoved)
         if p1copies:
             sidedata[sidedatamod.SD_P1COPIES] = p1copies
         if p2copies:
             sidedata[sidedatamod.SD_P2COPIES] = p2copies
         if filesadded:
             sidedata[sidedatamod.SD_FILESADDED] = filesadded
         if filesremoved:
             sidedata[sidedatamod.SD_FILESREMOVED] = filesremoved
     return sidedata
 
 
 def getsidedataadder(srcrepo, destrepo):
     use_w = srcrepo.ui.configbool(b'experimental', b'worker.repository-upgrade')
     if pycompat.iswindows or not use_w:
         return _get_simple_sidedata_adder(srcrepo, destrepo)
     else:
         return _get_worker_sidedata_adder(srcrepo, destrepo)
 
 
 def _sidedata_worker(srcrepo, revs_queue, sidedata_queue, tokens):
     """The function used by worker precomputing sidedata
 
     It read an input queue containing revision numbers
     It write in an output queue containing (rev, <sidedata-map>)
 
     The `None` input value is used as a stop signal.
 
     The `tokens` semaphore is user to avoid having too many unprocessed
     entries. The workers needs to acquire one token before fetching a task.
     They will be released by the consumer of the produced data.
     """
     tokens.acquire()
     rev = revs_queue.get()
     while rev is not None:
         data = _getsidedata(srcrepo, rev)
         sidedata_queue.put((rev, data))
         tokens.acquire()
         rev = revs_queue.get()
     # processing of `None` is completed, release the token.
     tokens.release()
 
 
 BUFF_PER_WORKER = 50
 
 
 def _get_worker_sidedata_adder(srcrepo, destrepo):
     """The parallel version of the sidedata computation
 
     This code spawn a pool of worker that precompute a buffer of sidedata
     before we actually need them"""
     # avoid circular import copies -> scmutil -> worker -> copies
     from . import worker
 
     nbworkers = worker._numworkers(srcrepo.ui)
 
     tokens = multiprocessing.BoundedSemaphore(nbworkers * BUFF_PER_WORKER)
     revsq = multiprocessing.Queue()
     sidedataq = multiprocessing.Queue()
 
     assert srcrepo.filtername is None
     # queue all tasks beforehand, revision numbers are small and it make
     # synchronisation simpler
     #
     # Since the computation for each node can be quite expensive, the overhead
     # of using a single queue is not revelant. In practice, most computation
     # are fast but some are very expensive and dominate all the other smaller
     # cost.
     for r in srcrepo.changelog.revs():
         revsq.put(r)
     # queue the "no more tasks" markers
     for i in range(nbworkers):
         revsq.put(None)
 
     allworkers = []
     for i in range(nbworkers):
         args = (srcrepo, revsq, sidedataq, tokens)
         w = multiprocessing.Process(target=_sidedata_worker, args=args)
         allworkers.append(w)
         w.start()
 
     # dictionnary to store results for revision higher than we one we are
     # looking for. For example, if we need the sidedatamap for 42, and 43 is
     # received, when shelve 43 for later use.
     staging = {}
 
     def sidedata_companion(revlog, rev):
         sidedata = {}
         if util.safehasattr(revlog, b'filteredrevs'):  # this is a changelog
             # Is the data previously shelved ?
             sidedata = staging.pop(rev, None)
             if sidedata is None:
                 # look at the queued result until we find the one we are lookig
                 # for (shelve the other ones)
                 r, sidedata = sidedataq.get()
                 while r != rev:
                     staging[r] = sidedata
                     r, sidedata = sidedataq.get()
             tokens.release()
         return False, (), sidedata
 
     return sidedata_companion
 
 
 def _get_simple_sidedata_adder(srcrepo, destrepo):
     """The simple version of the sidedata computation
 
     It just compute it in the same thread on request"""
 
     def sidedatacompanion(revlog, rev):
         sidedata = {}
         if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
             sidedata = _getsidedata(srcrepo, rev)
         return False, (), sidedata
 
     return sidedatacompanion
 
 
 def getsidedataremover(srcrepo, destrepo):
     def sidedatacompanion(revlog, rev):
         f = ()
         if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
             if revlog.flags(rev) & REVIDX_SIDEDATA:
                 f = (
                     sidedatamod.SD_P1COPIES,
                     sidedatamod.SD_P2COPIES,
                     sidedatamod.SD_FILESADDED,
                     sidedatamod.SD_FILESREMOVED,
                 )
         return False, f, {}
 
     return sidedatacompanion

tests/test-copies-chain-merge.t

@@ -1,798 +1,855 b''
+#testcases filelog compatibility sidedata
+
 =====================================================
 Test Copy tracing for chain of copies involving merge
 =====================================================
 
 This test files covers copies/rename case for a chains of commit where merges
 are involved. It cheks we do not have unwanted update of behavior and that the
 different options to retrieve copies behave correctly.
 
+
 Setup
 =====
 
 use git diff to see rename
 
   $ cat << EOF >> $HGRCPATH
   > [diff]
   > git=yes
   > [ui]
   > logtemplate={rev} {desc}\n
   > EOF
 
+#if compatibility
+  $ cat >> $HGRCPATH << EOF
+  > [experimental]
+  > copies.read-from = compatibility
+  > EOF
+#endif
+
+#if sidedata
+  $ cat >> $HGRCPATH << EOF
+  > [format]
+  > exp-use-side-data = yes
+  > exp-use-copies-side-data-changeset = yes
+  > EOF
+#endif
+
+
   $ hg init repo-chain
   $ cd repo-chain
 
 Add some linear rename initialy
 
   $ touch a b h
   $ hg ci -Am 'i-0 initial commit: a b h'
   adding a
   adding b
   adding h
   $ hg mv a c
   $ hg ci -Am 'i-1: a -move-> c'
   $ hg mv c d
   $ hg ci -Am 'i-2: c -move-> d'
   $ hg log -G
   @  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 And having another branch with renames on the other side
 
   $ hg mv d e
   $ hg ci -Am 'a-1: d -move-> e'
   $ hg mv e f
   $ hg ci -Am 'a-2: e -move-> f'
   $ hg log -G --rev '::.'
   @  4 a-2: e -move-> f
   |
   o  3 a-1: d -move-> e
   |
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 Have a branching with nothing on one side
 
   $ hg up 'desc("i-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo foo > b
   $ hg ci -m 'b-1: b update'
   created new head
   $ hg log -G --rev '::.'
   @  5 b-1: b update
   |
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 Create a branch that delete a file previous renamed
 
   $ hg up 'desc("i-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg rm d
   $ hg ci -m 'c-1 delete d'
   created new head
   $ hg log -G --rev '::.'
   @  6 c-1 delete d
   |
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 Create a branch that delete a file previous renamed and recreate it
 
   $ hg up 'desc("i-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg rm d
   $ hg ci -m 'd-1 delete d'
   created new head
   $ echo bar > d
   $ hg add d
   $ hg ci -m 'd-2 re-add d'
   $ hg log -G --rev '::.'
   @  8 d-2 re-add d
   |
   o  7 d-1 delete d
   |
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 Having another branch renaming a different file to the same filename as another
 
   $ hg up 'desc("i-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg mv b g
   $ hg ci -m 'e-1 b -move-> g'
   created new head
   $ hg mv g f
   $ hg ci -m 'e-2 g -move-> f'
   $ hg log -G --rev '::.'
   @  10 e-2 g -move-> f
   |
   o  9 e-1 b -move-> g
   |
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 merging with unrelated change does not interfere with the renames
 ---------------------------------------------------------------
 
 - rename on one side
 - unrelated change on the other side
 
   $ hg up 'desc("b-1")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg merge 'desc("a-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mBAm-0 simple merge - one way'
   $ hg up 'desc("a-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("b-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mABm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mABm")+desc("mBAm"))'
   @    12 mABm-0 simple merge - the other way
   |\
   +---o  11 mBAm-0 simple merge - one way
   | |/
   | o  5 b-1: b update
   | |
   o |  4 a-2: e -move-> f
   | |
   o |  3 a-1: d -move-> e
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mABm")'
   A f
     d
   R d
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mBAm")'
   A f
     d
   R d
   $ hg status --copies --rev 'desc("a-2")' --rev 'desc("mABm")'
   M b
   $ hg status --copies --rev 'desc("a-2")' --rev 'desc("mBAm")'
   M b
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mABm")'
   M b
   A f
     d
   R d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mBAm")'
   M b
   A f
     d
   R d
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mABm")'
   M b
   A f
     a
   R a
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mBAm")'
   M b
   A f
     a
   R a
 
 merging with the side having a delete
 -------------------------------------
 
 case summary:
 - one with change to an unrelated file
 - one deleting the change
 and recreate an unrelated file after the merge
 
   $ hg up 'desc("b-1")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg merge 'desc("c-1")'
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mBCm-0 simple merge - one way'
   $ echo bar > d
   $ hg add d
   $ hg ci -m 'mBCm-1 re-add d'
   $ hg up 'desc("c-1")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg merge 'desc("b-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mCBm-0 simple merge - the other way'
   created new head
   $ echo bar > d
   $ hg add d
   $ hg ci -m 'mCBm-1 re-add d'
   $ hg log -G --rev '::(desc("mCBm")+desc("mBCm"))'
   @  16 mCBm-1 re-add d
   |
   o    15 mCBm-0 simple merge - the other way
   |\
   | | o  14 mBCm-1 re-add d
   | | |
   +---o  13 mBCm-0 simple merge - one way
   | |/
   | o  6 c-1 delete d
   | |
   o |  5 b-1: b update
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 - comparing from the merge
 
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mBCm-0")'
   R d
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mCBm-0")'
   R d
   $ hg status --copies --rev 'desc("c-1")' --rev 'desc("mBCm-0")'
   M b
   $ hg status --copies --rev 'desc("c-1")' --rev 'desc("mCBm-0")'
   M b
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mBCm-0")'
   M b
   R d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mCBm-0")'
   M b
   R d
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mBCm-0")'
   M b
   R a
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mCBm-0")'
   M b
   R a
 
 - comparing with the merge children re-adding the file
 
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mBCm-1")'
   M d
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mCBm-1")'
   M d
   $ hg status --copies --rev 'desc("c-1")' --rev 'desc("mBCm-1")'
   M b
   A d
   $ hg status --copies --rev 'desc("c-1")' --rev 'desc("mCBm-1")'
   M b
   A d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mBCm-1")'
   M b
   M d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mCBm-1")'
   M b
   M d
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mBCm-1")'
   M b
   A d
   R a
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mCBm-1")'
   M b
   A d
   R a
 
 Comparing with a merge re-adding the file afterward
 ---------------------------------------------------
 
 Merge:
 - one with change to an unrelated file
 - one deleting and recreating the change
 
 Note:
 | In this case, one of the merge wrongly record a merge while there is none.
 | This lead to bad copy tracing information to be dug up.
 
   $ hg up 'desc("b-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("d-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mBDm-0 simple merge - one way'
   $ hg up 'desc("d-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("b-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mDBm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mDBm")+desc("mBDm"))'
   @    18 mDBm-0 simple merge - the other way
   |\
   +---o  17 mBDm-0 simple merge - one way
   | |/
   | o  8 d-2 re-add d
   | |
   | o  7 d-1 delete d
   | |
   o |  5 b-1: b update
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mBDm-0")'
   M d
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mDBm-0")'
   M d
   $ hg status --copies --rev 'desc("d-2")' --rev 'desc("mBDm-0")'
   M b
   $ hg status --copies --rev 'desc("d-2")' --rev 'desc("mDBm-0")'
   M b
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mBDm-0")'
   M b
   M d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mDBm-0")'
   M b
   M d
 
 The bugs makes recorded copy is different depending of where we started the merge from since
 
   $ hg manifest --debug --rev 'desc("mBDm-0")' | grep '644   d'
   b004912a8510032a0350a74daa2803dadfb00e12 644   d
   $ hg manifest --debug --rev 'desc("mDBm-0")' | grep '644   d'
   b004912a8510032a0350a74daa2803dadfb00e12 644   d
 
 The 0bb5445dc4d02f4e0d86cf16f9f3a411d0f17744 entry is wrong, since the file was
 deleted on one side (then recreate) and untouched on the other side, no "merge"
 has happened. The resulting `d` file is the untouched version from branch `D`,
 not a merge.
 
   $ hg manifest --debug --rev 'desc("d-2")' | grep '644   d'
   b004912a8510032a0350a74daa2803dadfb00e12 644   d
   $ hg manifest --debug --rev 'desc("b-1")' | grep '644   d'
   01c2f5eabdc4ce2bdee42b5f86311955e6c8f573 644   d
   $ hg debugindex d
      rev linkrev nodeid       p1           p2
        0       2 01c2f5eabdc4 000000000000 000000000000
        1       8 b004912a8510 000000000000 000000000000
 
 (This `hg log` output if wrong, since no merge actually happened).
 
   $ hg log -Gfr 'desc("mBDm-0")' d
   o  8 d-2 re-add d
   |
   ~
 
 This `hg log` output is correct
 
   $ hg log -Gfr 'desc("mDBm-0")' d
   o  8 d-2 re-add d
   |
   ~
 
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mBDm-0")'
   M b
   A d
   R a
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mDBm-0")'
   M b
   A d
   R a
 
 
 Comparing with a merge with colliding rename
 --------------------------------------------
 
 - the "e-" branch renaming b to f (through 'g')
 - the "a-" branch renaming d to f (through e)
 
   $ hg up 'desc("a-2")'
   2 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg merge 'desc("e-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mAEm-0 simple merge - one way'
   $ hg up 'desc("e-2")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("a-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mEAm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mAEm")+desc("mEAm"))'
   @    20 mEAm-0 simple merge - the other way
   |\
   +---o  19 mAEm-0 simple merge - one way
   | |/
   | o  10 e-2 g -move-> f
   | |
   | o  9 e-1 b -move-> g
   | |
   o |  4 a-2: e -move-> f
   | |
   o |  3 a-1: d -move-> e
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
   $ hg manifest --debug --rev 'desc("mAEm-0")' | grep '644   f'
   eb806e34ef6be4c264effd5933d31004ad15a793 644   f
   $ hg manifest --debug --rev 'desc("mEAm-0")' | grep '644   f'
   eb806e34ef6be4c264effd5933d31004ad15a793 644   f
   $ hg manifest --debug --rev 'desc("a-2")' | grep '644   f'
   0dd616bc7ab1a111921d95d76f69cda5c2ac539c 644   f
   $ hg manifest --debug --rev 'desc("e-2")' | grep '644   f'
   6da5a2eecb9c833f830b67a4972366d49a9a142c 644   f
   $ hg debugindex f
      rev linkrev nodeid       p1           p2
        0       4 0dd616bc7ab1 000000000000 000000000000
        1      10 6da5a2eecb9c 000000000000 000000000000
        2      19 eb806e34ef6b 0dd616bc7ab1 6da5a2eecb9c
+
+# Here the filelog based implementation is not looking at the rename
+# information (because the file exist on both side). However the changelog
+# based on works fine. We have different output.
+
   $ hg status --copies --rev 'desc("a-2")' --rev 'desc("mAEm-0")'
   M f
+    b (no-filelog !)
   R b
   $ hg status --copies --rev 'desc("a-2")' --rev 'desc("mEAm-0")'
   M f
+    b (no-filelog !)
   R b
   $ hg status --copies --rev 'desc("e-2")' --rev 'desc("mAEm-0")'
   M f
+    d (no-filelog !)
   R d
   $ hg status --copies --rev 'desc("e-2")' --rev 'desc("mEAm-0")'
   M f
+    d (no-filelog !)
   R d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("a-2")'
   A f
     d
   R d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("e-2")'
   A f
     b
   R b
+
+# From here, we run status against revision where both source file exists.
+#
+# The filelog based implementation picks an arbitrary side based on revision
+# numbers. So the same side "wins" whatever the parents order is. This is
+# sub-optimal because depending on revision numbers means the result can be
+# different from one repository to the next.
+#
+# The changeset based algorithm use the parent order to break tie on conflicting
+# information and will have a different order depending on who is p1 and p2.
+# That order is stable accross repositories. (data from p1 prevails)
+
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mAEm-0")'
   A f
     d
   R b
   R d
   $ hg status --copies --rev 'desc("i-2")' --rev 'desc("mEAm-0")'
   A f
-    d
+    d (filelog !)
+    b (no-filelog !)
   R b
   R d
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mAEm-0")'
   A f
     a
   R a
   R b
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mEAm-0")'
   A f
-    a
+    a (filelog !)
+    b (no-filelog !)
   R a
   R b
 
 
 Note:
 | In this case, one of the merge wrongly record a merge while there is none.
 | This lead to bad copy tracing information to be dug up.
 
 
 Merge:
 - one with change to an unrelated file (b)
 - one overwriting a file (d) with a rename (from h to i to d)
 
   $ hg up 'desc("i-2")'
   2 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg mv h i
   $ hg commit -m "f-1: rename h -> i"
   created new head
   $ hg mv --force i d
   $ hg commit -m "f-2: rename i -> d"
   $ hg debugindex d
      rev linkrev nodeid       p1           p2
        0       2 01c2f5eabdc4 000000000000 000000000000
        1       8 b004912a8510 000000000000 000000000000
        2      22 c72365ee036f 000000000000 000000000000
   $ hg up 'desc("b-1")'
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("f-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mBFm-0 simple merge - one way'
   $ hg up 'desc("f-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("b-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mFBm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mBFm")+desc("mFBm"))'
   @    24 mFBm-0 simple merge - the other way
   |\
   +---o  23 mBFm-0 simple merge - one way
   | |/
   | o  22 f-2: rename i -> d
   | |
   | o  21 f-1: rename h -> i
   | |
   o |  5 b-1: b update
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 The overwriting should take over. However, the behavior is currently buggy
 
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mBFm-0")'
   M b
   A d
     h
     h (false !)
   R a
   R h
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mFBm-0")'
   M b
   A d
     h
   R a
   R h
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mBFm-0")'
   M d
+    h (no-filelog !)
   R h
   $ hg status --copies --rev 'desc("f-2")' --rev 'desc("mBFm-0")'
   M b
   $ hg status --copies --rev 'desc("f-1")' --rev 'desc("mBFm-0")'
   M b
   M d
+    i (no-filelog !)
   R i
   $ hg status --copies --rev 'desc("b-1")' --rev 'desc("mFBm-0")'
   M d
+    h (no-filelog !)
   R h
   $ hg status --copies --rev 'desc("f-2")' --rev 'desc("mFBm-0")'
   M b
   $ hg status --copies --rev 'desc("f-1")' --rev 'desc("mFBm-0")'
   M b
   M d
+    i (no-filelog !)
   R i
 
 The following graphlog is wrong, the "a -> c -> d" chain was overwritten and should not appear.
 
   $ hg log -Gfr 'desc("mBFm-0")' d
   o  22 f-2: rename i -> d
   |
   o  21 f-1: rename h -> i
   :
   o  0 i-0 initial commit: a b h
   
 
 The following output is correct.
 
   $ hg log -Gfr 'desc("mFBm-0")' d
   o  22 f-2: rename i -> d
   |
   o  21 f-1: rename h -> i
   :
   o  0 i-0 initial commit: a b h
   
 
 
 Merge:
 - one with change to a file
 - one deleting and recreating the file
 
 Unlike in the 'BD/DB' cases, an actual merge happened here. So we should
 consider history and rename on both branch of the merge.
 
   $ hg up 'desc("i-2")'
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo "some update" >> d
   $ hg commit -m "g-1: update d"
   created new head
   $ hg up 'desc("d-2")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("g-1")' --tool :union
   merging d
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mDGm-0 simple merge - one way'
   $ hg up 'desc("g-1")'
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("d-2")' --tool :union
   merging d
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mGDm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mDGm")+desc("mGDm"))'
   @    27 mGDm-0 simple merge - the other way
   |\
   +---o  26 mDGm-0 simple merge - one way
   | |/
   | o  25 g-1: update d
   | |
   o |  8 d-2 re-add d
   | |
   o |  7 d-1 delete d
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
+One side of the merge have a long history with rename. The other side of the
+merge point to a new file with a smaller history. Each side is "valid".
+
+(and again the filelog based algorithm only explore one, with a pick based on
+revision numbers)
+
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mDGm-0")'
   A d
-    a
+    a (filelog !)
   R a
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mGDm-0")'
   A d
     a
   R a
   $ hg status --copies --rev 'desc("d-2")' --rev 'desc("mDGm-0")'
   M d
   $ hg status --copies --rev 'desc("d-2")' --rev 'desc("mGDm-0")'
   M d
   $ hg status --copies --rev 'desc("g-1")' --rev 'desc("mDGm-0")'
   M d
   $ hg status --copies --rev 'desc("g-1")' --rev 'desc("mGDm-0")'
   M d
 
   $ hg log -Gfr 'desc("mDGm-0")' d
   o    26 mDGm-0 simple merge - one way
   |\
   | o  25 g-1: update d
   | |
   o |  8 d-2 re-add d
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 
   $ hg log -Gfr 'desc("mDGm-0")' d
   o    26 mDGm-0 simple merge - one way
   |\
   | o  25 g-1: update d
   | |
   o |  8 d-2 re-add d
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
 
 Merge:
 - one with change to a file (d)
 - one overwriting that file with a rename (from h to i, to d)
 
 This case is similar to BF/FB, but an actual merge happens, so both side of the
 history are relevant.
 
 Note:
 | In this case, the merge get conflicting information since on one side we have
 | "a -> c -> d". and one the other one we have "h -> i -> d".
 |
 | The current code arbitrarily pick one side
 
   $ hg up 'desc("f-2")'
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg merge 'desc("g-1")' --tool :union
   merging d
   0 files updated, 1 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mFGm-0 simple merge - one way'
   created new head
   $ hg up 'desc("g-1")'
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg merge 'desc("f-2")' --tool :union
   merging d
   0 files updated, 1 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg ci -m 'mGFm-0 simple merge - the other way'
   created new head
   $ hg log -G --rev '::(desc("mGFm")+desc("mFGm"))'
   @    29 mGFm-0 simple merge - the other way
   |\
   +---o  28 mFGm-0 simple merge - one way
   | |/
   | o  25 g-1: update d
   | |
   o |  22 f-2: rename i -> d
   | |
   o |  21 f-1: rename h -> i
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mFGm-0")'
   A d
-    a
+    h (no-filelog !)
+    a (filelog !)
   R a
   R h
   $ hg status --copies --rev 'desc("i-0")' --rev 'desc("mGFm-0")'
   A d
     a
   R a
   R h
   $ hg status --copies --rev 'desc("f-2")' --rev 'desc("mFGm-0")'
   M d
   $ hg status --copies --rev 'desc("f-2")' --rev 'desc("mGFm-0")'
   M d
   $ hg status --copies --rev 'desc("f-1")' --rev 'desc("mFGm-0")'
   M d
+    i (no-filelog !)
   R i
   $ hg status --copies --rev 'desc("f-1")' --rev 'desc("mGFm-0")'
   M d
+    i (no-filelog !)
   R i
   $ hg status --copies --rev 'desc("g-1")' --rev 'desc("mFGm-0")'
   M d
+    h (no-filelog !)
   R h
   $ hg status --copies --rev 'desc("g-1")' --rev 'desc("mGFm-0")'
   M d
+    h (no-filelog !)
   R h
 
   $ hg log -Gfr 'desc("mFGm-0")' d
   o    28 mFGm-0 simple merge - one way
   |\
   | o  25 g-1: update d
   | |
   o |  22 f-2: rename i -> d
   | |
   o |  21 f-1: rename h -> i
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h
   
 
   $ hg log -Gfr 'desc("mGFm-0")' d
   @    29 mGFm-0 simple merge - the other way
   |\
   | o  25 g-1: update d
   | |
   o |  22 f-2: rename i -> d
   | |
   o |  21 f-1: rename h -> i
   |/
   o  2 i-2: c -move-> d
   |
   o  1 i-1: a -move-> c
   |
   o  0 i-0 initial commit: a b h