Patchwork [v3] graft: support grafting across move/copy (issue4028)

login
register
mail settings
Submitter Gábor Stefanik
Date Aug. 3, 2016, 11:22 a.m.
Message ID <7d38836dbd5efec50251.1470223368@waste.org>
Download mbox | patch
Permalink /patch/16050/
State Superseded
Headers show

Comments

Gábor Stefanik - Aug. 3, 2016, 11:22 a.m.
# HG changeset patch
# User Gábor Stefanik <gabor.stefanik@nng.com>
# Date 1470047695 -7200
#      Mon Aug 01 12:34:55 2016 +0200
# Node ID 7d38836dbd5efec50251615060c6cdef8174113a
# Parent  73ff159923c1f05899c27238409ca398342d9ae0
graft: support grafting across move/copy (issue4028)

Graft performs a merge with a false common ancestor, which must be taken into
account when tracking copies. Explicitly pass the real common ancestor in this
case, and track copies between the real and false common ancestors in reverse.

With this change, when grafting a commit with a change to a file moved earlier
on the graft's source branch, the change is merged as expected into the original
(unmoved) file, rather than recreating it under its new name.
It should also make it possible to eventually enable cross-branch updates with
merge.

v2: handle the case when target branch also has a rename
v3: address review comments

Patch

diff --git a/mercurial/copies.py b/mercurial/copies.py
--- a/mercurial/copies.py
+++ b/mercurial/copies.py
@@ -8,6 +8,7 @@ 
 from __future__ import absolute_import
 
 import heapq
+import operator
 
 from . import (
     node,
@@ -231,7 +232,7 @@ 
     return _chain(x, y, _backwardrenames(x, a),
                   _forwardcopies(a, y, match=match))
 
-def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2):
+def _computenonoverlap(repo, c1, c2, addedinm1, addedinm2, silent=False):
     """Computes, based on addedinm1 and addedinm2, the files exclusive to c1
     and c2. This is its own function so extensions can easily wrap this call
     to see what files mergecopies is about to process.
@@ -242,10 +243,10 @@ 
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
-    if u1:
+    if u1 and not silent:
         repo.ui.debug("  unmatched files in local:\n   %s\n"
                       % "\n   ".join(u1))
-    if u2:
+    if u2 and not silent:
         repo.ui.debug("  unmatched files in other:\n   %s\n"
                       % "\n   ".join(u2))
     return u1, u2
@@ -285,7 +286,7 @@ 
         return fctx
     return util.lrucachefunc(makectx)
 
-def mergecopies(repo, c1, c2, ca):
+def mergecopies(repo, c1, c2, ca, cta=None):
     """
     Find moves and copies between context c1 and c2 that are relevant
     for merging.
@@ -321,6 +322,12 @@ 
     if repo.ui.configbool('experimental', 'disablecopytrace'):
         return {}, {}, {}, {}
 
+    # cta will only differ from ca when grafting or during non-linear updates
+    graft = True
+    if cta is None:
+        graft = False
+        cta = ca
+
     limit = _findlimit(repo, c1.rev(), c2.rev())
     if limit is None:
         # no common ancestor, no copies
@@ -330,28 +337,44 @@ 
     m1 = c1.manifest()
     m2 = c2.manifest()
     ma = ca.manifest()
+    mta = cta.manifest()
 
+    # see checkcopies documentation below for these dicts
     copy1, copy2, = {}, {}
+    copyfrom, copyto = {}, {}
     movewithdir1, movewithdir2 = {}, {}
     fullcopy1, fullcopy2 = {}, {}
     diverge = {}
 
     # find interesting file sets from manifests
-    addedinm1 = m1.filesnotin(ma)
-    addedinm2 = m2.filesnotin(ma)
-    u1, u2 = _computenonoverlap(repo, c1, c2, addedinm1, addedinm2)
+    addedinm1 = m1.filesnotin(mta)
+    addedinm2 = m2.filesnotin(mta)
+    u1, u2 = _computenonoverlap(repo, c1, c2, addedinm1, addedinm2, graft)
+    if not graft:
+        unmatched = u1 + u2
+    else: # need to recompute this for directory move handling when grafting
+        unmatched = operator.add(*_computenonoverlap(repo, c1, c2,
+                                 m1.filesnotin(ma), m2.filesnotin(ma), False))
+
     bothnew = sorted(addedinm1 & addedinm2)
 
     for f in u1:
-        checkcopies(c1, f, m1, m2, ca, limit, diverge, copy1, fullcopy1)
+        checkcopies(c1, f, m1, m2, ca, cta, limit, diverge, copy1,
+                    fullcopy1, copyfrom, copyto)
 
     for f in u2:
-        checkcopies(c2, f, m2, m1, ca, limit, diverge, copy2, fullcopy2)
+        checkcopies(c2, f, m2, m1, ca, cta, limit, diverge, copy2,
+                    fullcopy2, copyfrom, copyto)
 
     copy = dict(copy1.items() + copy2.items())
     movewithdir = dict(movewithdir1.items() + movewithdir2.items())
     fullcopy = dict(fullcopy1.items() + fullcopy2.items())
 
+    # combine partial copy paths discovered in the previous step
+    for f in copyfrom:
+        if f in copyto:
+            copy[copyto[f]] = copyfrom[f]
+
     renamedelete = {}
     renamedeleteset = set()
     divergeset = set()
@@ -369,10 +392,13 @@ 
     if bothnew:
         repo.ui.debug("  unmatched files new in both:\n   %s\n"
                       % "\n   ".join(bothnew))
-    bothdiverge, _copy, _fullcopy = {}, {}, {}
+    bothdiverge = {}
+    _copy, _fullcopy, _copyfrom, _copyto = {}, {}, {}, {} # dummy dicts
     for f in bothnew:
-        checkcopies(c1, f, m1, m2, ca, limit, bothdiverge, _copy, _fullcopy)
-        checkcopies(c2, f, m2, m1, ca, limit, bothdiverge, _copy, _fullcopy)
+        checkcopies(c1, f, m1, m2, ca, cta, limit, bothdiverge, _copy,
+                    _fullcopy, _copyfrom, _copyto)
+        checkcopies(c2, f, m2, m1, ca, cta, limit, bothdiverge, _copy,
+                    _fullcopy, _copyfrom, _copyto)
     for of, fl in bothdiverge.items():
         if len(fl) == 2 and fl[0] == fl[1]:
             copy[fl[0]] = of # not actually divergent, just matching renames
@@ -438,7 +464,7 @@ 
                       (d, dirmove[d]))
 
     # check unaccounted nonoverlapping files against directory moves
-    for f in u1 + u2:
+    for f in unmatched:
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
@@ -452,7 +478,8 @@ 
 
     return copy, movewithdir, diverge, renamedelete
 
-def checkcopies(ctx, f, m1, m2, ca, limit, diverge, copy, fullcopy):
+def checkcopies(ctx, f, m1, m2, ca, cta, limit, diverge, copy, fullcopy,
+                copyfrom, copyto):
     """
     check possible copies of f from m1 to m2
 
@@ -460,14 +487,19 @@ 
     f = the filename to check
     m1 = the source manifest
     m2 = the destination manifest
-    ca = the changectx of the common ancestor
+    ca = the changectx of the common ancestor, overridden on graft
+    cta = topological common ancestor for graft-like scenarios
     limit = the rev number to not search beyond
     diverge = record all diverges in this dict
     copy = record all non-divergent copies in this dict
     fullcopy = record all copies in this dict
+    copyfrom = source sides of partially known copy tracks
+    copyto = destination sides of partially known copytracks
     """
 
     ma = ca.manifest()
+    mta = cta.manifest()
+    backwards = f in ma # graft common ancestor already contains the rename
     getfctx = _makegetfctx(ctx)
 
     def _related(f1, f2, limit):
@@ -513,20 +545,32 @@ 
             continue
         seen.add(of)
 
-        fullcopy[f] = of # remember for dir rename detection
+        # remember for dir rename detection
+        if backwards:
+            fullcopy[of] = f # grafting backwards through renames
+        else:
+            fullcopy[f] = of
         if of not in m2:
             continue # no match, keep looking
         if m2[of] == ma.get(of):
             break # no merge needed, quit early
         c2 = getfctx(of, m2[of])
-        cr = _related(oc, c2, ca.rev())
+        cr = _related(oc, c2, cta.rev())
         if cr and (of == f or of == c2.path()): # non-divergent
-            copy[f] = of
+            if backwards:
+                copy[of] = f
+            else:
+                copy[f] = of
             of = None
             break
 
     if of in ma:
         diverge.setdefault(of, []).append(f)
+    elif of in mta:
+        if backwards:
+            copyfrom[of] = f
+        else:
+            copyto[of] = f
 
 def duplicatecopies(repo, rev, fromrev, skiprev=None):
     '''reproduce copies from fromrev to rev in the dirstate
diff --git a/mercurial/merge.py b/mercurial/merge.py
--- a/mercurial/merge.py
+++ b/mercurial/merge.py
@@ -779,13 +779,14 @@ 
     return True
 
 def manifestmerge(repo, wctx, p2, pa, branchmerge, force, matcher,
-                  acceptremote, followcopies):
+                  acceptremote, followcopies, pta=None):
     """
     Merge p1 and p2 with ancestor pa and generate merge action list
 
     branchmerge and force are as passed in to update
     matcher = matcher to filter file lists
     acceptremote = accept the incoming changes without prompting
+    pta = topological common ancestor for graft, needed for rename detection
     """
     if matcher is not None and matcher.always():
         matcher = None
@@ -797,7 +798,7 @@ 
      sorted(wctx.parents() + [p2, pa], key=lambda x: x.rev())]
 
     if followcopies:
-        ret = copies.mergecopies(repo, wctx, p2, pa)
+        ret = copies.mergecopies(repo, wctx, p2, pa, pta)
         copy, movewithdir, diverge, renamedelete = ret
 
     repo.ui.note(_("resolving manifests\n"))
@@ -939,12 +940,12 @@ 
 
 def calculateupdates(repo, wctx, mctx, ancestors, branchmerge, force,
                      acceptremote, followcopies, matcher=None,
-                     mergeforce=False):
+                     mergeforce=False, pta=None):
     "Calculate the actions needed to merge mctx into wctx using ancestors"
     if len(ancestors) == 1: # default
         actions, diverge, renamedelete = manifestmerge(
             repo, wctx, mctx, ancestors[0], branchmerge, force, matcher,
-            acceptremote, followcopies)
+            acceptremote, followcopies, pta)
         _checkunknownfiles(repo, wctx, mctx, force, actions, mergeforce)
 
     else: # only when merge.preferancestor=* - the default
@@ -1438,6 +1439,7 @@ 
         pl = wc.parents()
         p1 = pl[0]
         pas = [None]
+        pta = None
         if ancestor is not None:
             pas = [repo[ancestor]]
 
@@ -1455,6 +1457,10 @@ 
                 pas = [repo[anc] for anc in (sorted(cahs) or [nullid])]
             else:
                 pas = [p1.ancestor(p2, warn=branchmerge)]
+        elif not (pas[0].descendant(p1) and pas[0].descendant(p2)):
+            # this can happen during graft or non-linear update
+            # in this case, we still need a true topological common ancestor
+            pta = p1.ancestor(p2)
 
         fp1, fp2, xp1, xp2 = p1.node(), p2.node(), str(p1), str(p2)
 
@@ -1527,7 +1533,7 @@ 
         ### calculate phase
         actionbyfile, diverge, renamedelete = calculateupdates(
             repo, wc, p2, pas, branchmerge, force, mergeancestor,
-            followcopies, matcher=matcher, mergeforce=mergeforce)
+            followcopies, matcher=matcher, mergeforce=mergeforce, pta=pta)
 
         # Prompt and create actions. Most of this is in the resolve phase
         # already, but we can't handle .hgsubstate in filemerge or
diff --git a/tests/test-graft.t b/tests/test-graft.t
--- a/tests/test-graft.t
+++ b/tests/test-graft.t
@@ -179,6 +179,11 @@ 
   committing changelog
   grafting 5:97f8bfe72746 "5"
     searching for copies back to rev 1
+    unmatched files new in both:
+     b
+    all copies found (* = to merge, ! = divergent, % = renamed and deleted):
+     src: 'c' -> dst: 'b' *
+    checking for directory renames
   resolving manifests
    branchmerge: True, force: True, partial: False
    ancestor: 4c60f11aa304, local: 6b9e5368ca4e+, remote: 97f8bfe72746
@@ -193,6 +198,11 @@ 
   scanning for duplicate grafts
   grafting 4:9c233e8e184d "4"
     searching for copies back to rev 1
+    unmatched files new in both:
+     b
+    all copies found (* = to merge, ! = divergent, % = renamed and deleted):
+     src: 'c' -> dst: 'b' *
+    checking for directory renames
   resolving manifests
    branchmerge: True, force: True, partial: False
    ancestor: 4c60f11aa304, local: 1905859650ec+, remote: 9c233e8e184d
@@ -842,3 +852,24 @@ 
   |/
   o  0
   
+Graft from behind a move or rename
+
+  $ hg init graftmove
+  $ cd graftmove
+  $ echo c1 > f1
+  $ hg ci -qAm 0
+  $ hg mv f1 f2
+  $ hg ci -qAm 1
+  $ echo c2 > f2
+  $ hg ci -qAm 2
+  $ hg up -q 0
+  $ hg graft -r 2
+  grafting 2:8a20493ece2a "2" (tip)
+  merging f1 and f2 to f1
+  $ hg status --change .
+  M f1
+  $ hg cat f1
+  c2
+  $ hg cat f2
+  f2: no such file in rev ee1f64f8088b
+  [1]