diff mercurial/revset.py @ 25191:08d1ef09ed37

revset: optimize not public revset

This patvh speeds up the computation of the not public() changeset
and incidentally speed up the computation of divergents() changeset on our big
repo by 100x from 50% to 0.5% of the time spent in smartlog with evolve.

In this patch we optimize not public() to _notpublic() (new revset) and use
the work on phaseset (from the previous commit) to be able to compute
_notpublic() quickly.

We use a non-lazy approach making the assumption the number of notpublic
change will not be in the order of magnitude of the repo size. Adopting a
lazy approach gives a speedup of 5x (vs 100x) only due to the overhead of the
code for lazy generation.

--- a/mercurial/revset.py	Wed Apr 01 11:17:17 2015 -0700
+++ b/mercurial/revset.py	Fri Apr 24 14:30:30 2015 -0700
@@ -1478,6 +1478,22 @@
     except error.RepoLookupError:
         return baseset()
 
+def _notpublic(repo, subset, x):
+    """``_notpublic()``
+    Changeset not in public phase."""
+    # i18n: "public" is a keyword
+    getargs(x, 0, 0, _("_notpublic takes no arguments"))
+    if repo._phasecache._phasesets:
+        s = set()
+        for u in repo._phasecache._phasesets[1:]:
+            s.update(u)
+        return subset & s
+    else:
+        phase = repo._phasecache.phase
+        target = phases.public
+        condition = lambda r: phase(repo, r) != target
+        return subset.filter(condition, cache=False)
+
 def public(repo, subset, x):
     """``public()``
     Changeset in public phase."""
@@ -1984,6 +2000,7 @@
     "parents": parents,
     "present": present,
     "public": public,
+    "_notpublic": _notpublic,
     "remote": remote,
     "removes": removes,
     "rev": rev,
@@ -2058,6 +2075,7 @@
     "parents",
     "present",
     "public",
+    "_notpublic",
     "remote",
     "removes",
     "rev",
@@ -2149,8 +2167,14 @@
             wb, wa = wa, wb
         return max(wa, wb), (op, ta, tb)
     elif op == 'not':
-        o = optimize(x[1], not small)
-        return o[0], (op, o[1])
+        # Optimize not public() to _notpublic() because we have a fast version
+        if x[1] == ('func', ('symbol', 'public'), None):
+            newsym =  ('func', ('symbol', '_notpublic'), None)
+            o = optimize(newsym, not small)
+            return o[0], o[1]
+        else:
+            o = optimize(x[1], not small)
+            return o[0], (op, o[1])
     elif op == 'parentpost':
         o = optimize(x[1], small)
         return o[0], (op, o[1])