diff mercurial/merge.py @ 42522:d29db0a0c4eb

update: fix spurious unclean status bug shown by previous commit

The crux of the problem is:
- the dirstate is corrupted (the sizes/dates are assigned to the wrong files)
- because when worker.worker is used with a return value (batchget in
  merge.py here), the return value when worker.worker effectively parallelizes
  is permuted
- this is because worker.worker's partition of input and combination of output
  values are not inverses of one another: it split [1,2,3,4,5,6] into
  [[1,3,5],[2,4,6]], but combines that into [1,3,5,2,4,6].

Given that worker.worker doesn't call its function argument on contiguous
chunks on the input arguments, sticking with lists means we'd need to
know the relation between the inputs of worker.worker function argument
(for instance, requiring that every input element is mapped to exactly
one output element). It seems better to instead switch return values to
dicts, which can combined reliably with a straighforward restriction.

Differential Revision: https://phab.mercurial-scm.org/D6581

--- a/mercurial/merge.py	Thu Jun 27 11:09:09 2019 +0200
+++ b/mercurial/merge.py	Thu Jun 27 11:39:35 2019 +0200
@@ -1472,10 +1472,10 @@
 
     Yields arbitrarily many (False, tuple) for progress updates, followed by
     exactly one (True, filedata). When wantfiledata is false, filedata is an
-    empty list. When wantfiledata is true, filedata[i] is a triple (mode, size,
-    mtime) of the file written for action[i].
+    empty dict. When wantfiledata is true, filedata[f] is a triple (mode, size,
+    mtime) of the file f written for each action.
     """
-    filedata = []
+    filedata = {}
     verbose = repo.ui.verbose
     fctx = mctx.filectx
     ui = repo.ui
@@ -1509,7 +1509,7 @@
                 s = wfctx.lstat()
                 mode = s.st_mode
                 mtime = s[stat.ST_MTIME]
-                filedata.append((mode, size, mtime)) # for dirstate.normal
+                filedata[f] = ((mode, size, mtime)) # for dirstate.normal
             if i == 100:
                 yield False, (i, f)
                 i = 0
@@ -1670,7 +1670,7 @@
                          actions[ACTION_GET],
                          threadsafe=threadsafe,
                          hasretval=True)
-    getfiledata = []
+    getfiledata = {}
     for final, res in prog:
         if final:
             getfiledata = res
@@ -1803,7 +1803,8 @@
             actions[k].extend(acts)
             if k == ACTION_GET and wantfiledata:
                 # no filedata until mergestate is updated to provide it
-                getfiledata.extend([None] * len(acts))
+                for a in acts:
+                    getfiledata[a[0]] = None
             # Remove these files from actions[ACTION_MERGE] as well. This is
             # important because in recordupdates, files in actions[ACTION_MERGE]
             # are processed after files in other actions, and the merge driver
@@ -1873,11 +1874,11 @@
         pass
 
     # get
-    for i, (f, args, msg) in enumerate(actions.get(ACTION_GET, [])):
+    for f, args, msg in actions.get(ACTION_GET, []):
         if branchmerge:
             repo.dirstate.otherparent(f)
         else:
-            parentfiledata = getfiledata[i] if getfiledata else None
+            parentfiledata = getfiledata[f] if getfiledata else None
             repo.dirstate.normal(f, parentfiledata=parentfiledata)
 
     # merge