diff mercurial/copies.py @ 18878:3cfaace0441e

copies._forwardcopies: use set operations to find missing files

This is a performance win for a number of reasons:
- We don't iterate over contexts, which avoids a completely unnecessary sorted
  call + the O(number of files) abstraction cost of doing that.
- We don't check membership in a context, which avoids another
  O(number of files) abstraction cost.
- We iterate over the manifests in C instead of Python.

For a large repo with 170,000 files, this improves perfpathcopies from 0.34
seconds to 0.07. Anything that uses pathcopies, such as rebase or diff --git
between two revisions, benefits.

--- a/mercurial/copies.py	Thu Apr 04 20:36:46 2013 -0700
+++ b/mercurial/copies.py	Thu Apr 04 20:22:29 2013 -0700
@@ -133,11 +133,13 @@
     # 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 = {}
-    for f in b:
-        if f not in a:
-            ofctx = _tracefile(b[f], a)
-            if ofctx:
-                cm[f] = ofctx.path()
+    missing = set(b.manifest().iterkeys())
+    missing.difference_update(a.manifest().iterkeys())
+
+    for f in missing:
+        ofctx = _tracefile(b[f], a)
+        if ofctx:
+            cm[f] = ofctx.path()
 
     # combine copies from dirstate if necessary
     if w is not None: