merge: refactor unknown file conflict checking

Previously, we would do a full working directory walk including
unknown files to perform a merge. In many cases, this was painful
because unknown files greatly outnumbered tracked files and generally
had no useful effect on the merge.

Here we instead wait until we find a file in the destination that's
not tracked locally and detect if it exists and is not ignored. This
is usually cheaper but can be -more- expensive in the case where we're
adding a huge number of files. On the other hand, the cost of statting
the new files should be dwarfed by the cost of eventually writing
them.

In this version, case collisions are detected implicitly by
os.path.exists and wctx[f] lookup.

hgext/largefiles/overrides.py

@@ -265,13 +265,10 b' def override_update(orig, ui, repo, *pat'
 # The overridden function filters the unknown files by removing any
 # largefiles. This makes the merge proceed and we can then handle this
 # case further in the overridden manifestmerge function below.
-def override_checkunknown(origfn, wctx, mctx, folding):
-    origunknown = wctx.unknown()
-    wctx._unknown = filter(lambda f: lfutil.standin(f) not in wctx, origunknown)
-    try:
-        return origfn(wctx, mctx, folding)
-    finally:
-        wctx._unknown = origunknown
+def override_checkunknownfile(origfn, repo, wctx, mctx, f):
+    if lfutil.standin(f) in wctx:
+        return False
+    return origfn(repo, wctx, mctx, f)
 
 # The manifest merge handles conflicts on the manifest level. We want
 # to handle changes in largefile-ness of files at this level too.

hgext/largefiles/uisetup.py

@@ -64,8 +64,8 b' def uisetup(ui):'
                                    overrides.override_update)
     entry = extensions.wrapcommand(commands.table, 'pull',
                                    overrides.override_pull)
-    entry = extensions.wrapfunction(merge, '_checkunknown',
-                                    overrides.override_checkunknown)
+    entry = extensions.wrapfunction(merge, '_checkunknownfile',
+                                    overrides.override_checkunknownfile)
     entry = extensions.wrapfunction(merge, 'manifestmerge',
                                     overrides.override_manifestmerge)
     entry = extensions.wrapfunction(filemerge, 'filemerge',

mercurial/merge.py

@@ -81,22 +81,19 b' class mergestate(object):'
             self.mark(dfile, 'r')
         return r
 
-def _checkunknown(wctx, mctx, folding):
+def _checkunknownfile(repo, wctx, mctx, f):
+    return (not repo.dirstate._ignore(f)
+        and os.path.exists(repo.wjoin(f))
+        and mctx[f].cmp(wctx[f]))
+
+def _checkunknown(repo, wctx, mctx):
     "check for collisions between unknown files and files in mctx"
-    if folding:
-        foldf = util.normcase
-    else:
-        foldf = lambda fn: fn
-    folded = {}
-    for fn in mctx:
-        folded[foldf(fn)] = fn
 
     error = False
-    for fn in wctx.unknown():
-        f = foldf(fn)
-        if f in folded and mctx[folded[f]].cmp(wctx[f]):
+    for f in mctx:
+        if f not in wctx and _checkunknownfile(repo, wctx, mctx, f):
             error = True
-            wctx._repo.ui.warn(_("%s: untracked file differs\n") % fn)
+            wctx._repo.ui.warn(_("%s: untracked file differs\n") % f)
     if error:
         raise util.Abort(_("untracked files in working directory differ "
                            "from files in requested revision"))
@@ -565,7 +562,7 b' def update(repo, node, branchmerge, forc'
         wc.status(unknown=True) # prime cache
         folding = not util.checkcase(repo.path)
         if not force:
-            _checkunknown(wc, p2, folding)
+            _checkunknown(repo, wc, p2)
         if folding:
             _checkcollision(p2, branchmerge and p1)
         action += _forgetremoved(wc, p2, branchmerge)