dicthelpers.diff: compare against default for missing values

This is not only a bit faster, but also aligns with callers' expectations
better since we can legitimately have manifestdict's _flags set to '' instead
of unset.

hg perfmergecalculate -r .
before: ! wall 0.139582 comb 0.140000 user 0.140000 sys 0.000000 (best of 59)
after:  ! wall 0.126154 comb 0.120000 user 0.120000 sys 0.000000 (best of 74)

hg perfmergecalculate -r .^
before: ! wall 0.236333 comb 0.240000 user 0.240000 sys 0.000000 (best of 36)
after:  ! wall 0.212265 comb 0.210000 user 0.210000 sys 0.000000 (best of 45)

mercurial/dicthelpers.py

@@ -1,55 +1,55 b''
 # dicthelpers.py - helper routines for Python dicts
 #
 # Copyright 2013 Facebook
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 def diff(d1, d2, default=None):
     '''Return all key-value pairs that are different between d1 and d2.
 
     This includes keys that are present in one dict but not the other, and
     keys whose values are different. The return value is a dict with values
     being pairs of values from d1 and d2 respectively, and missing values
-    represented as default.'''
+    treated as default, so if a value is missing from one dict and the same as
+    default in the other, it will not be returned.'''
     res = {}
     if d1 is d2:
         # same dict, so diff is empty
         return res
 
     for k1, v1 in d1.iteritems():
-        if k1 in d2:
-            v2 = d2[k1]
-            if v1 != v2:
-                res[k1] = (v1, v2)
-        else:
-            res[k1] = (v1, default)
+        v2 = d2.get(k1, default)
+        if v1 != v2:
+            res[k1] = (v1, v2)
 
     for k2 in d2:
         if k2 not in d1:
-            res[k2] = (default, d2[k2])
+            v2 = d2[k2]
+            if v2 != default:
+                res[k2] = (default, v2)
 
     return res
 
 def join(d1, d2, default=None):
     '''Return all key-value pairs from both d1 and d2.
 
     This is akin to an outer join in relational algebra. The return value is a
     dict with values being pairs of values from d1 and d2 respectively, and
     missing values represented as default.'''
     res = {}
 
     for k1, v1 in d1.iteritems():
         if k1 in d2:
             res[k1] = (v1, d2[k1])
         else:
             res[k1] = (v1, default)
 
     if d1 is d2:
         return res
 
     for k2 in d2:
         if k2 not in d1:
             res[k2] = (default, d2[k2])
 
     return res

tests/test-dicthelpers.py

@@ -1,53 +1,59 b''
 from mercurial.dicthelpers import diff, join
 import unittest
 import silenttestrunner
 
 class testdicthelpers(unittest.TestCase):
     def test_dicthelpers(self):
         # empty dicts
         self.assertEqual(diff({}, {}), {})
         self.assertEqual(join({}, {}), {})
 
         d1 = {}
         d1['a'] = 'foo'
         d1['b'] = 'bar'
         d1['c'] = 'baz'
 
         # same identity
         self.assertEqual(diff(d1, d1), {})
         self.assertEqual(join(d1, d1), {'a': ('foo', 'foo'),
                                         'b': ('bar', 'bar'),
                                         'c': ('baz', 'baz')})
 
         # vs empty
         self.assertEqual(diff(d1, {}), {'a': ('foo', None),
                                         'b': ('bar', None),
                                         'c': ('baz', None)})
         self.assertEqual(diff(d1, {}), {'a': ('foo', None),
                                         'b': ('bar', None),
                                         'c': ('baz', None)})
 
         d2 = {}
         d2['a'] = 'foo2'
         d2['b'] = 'bar'
         d2['d'] = 'quux'
 
         self.assertEqual(diff(d1, d2), {'a': ('foo', 'foo2'),
                                         'c': ('baz', None),
                                         'd': (None, 'quux')})
         self.assertEqual(join(d1, d2), {'a': ('foo', 'foo2'),
                                         'b': ('bar', 'bar'),
                                         'c': ('baz', None),
                                         'd': (None, 'quux')})
 
         # with default argument
         self.assertEqual(diff(d1, d2, 123), {'a': ('foo', 'foo2'),
                                              'c': ('baz', 123),
                                              'd': (123, 'quux')})
         self.assertEqual(join(d1, d2, 456), {'a': ('foo', 'foo2'),
                                              'b': ('bar', 'bar'),
                                              'c': ('baz', 456),
                                              'd': (456, 'quux')})
 
+        # check that we compare against default
+        self.assertEqual(diff(d1, d2, 'baz'), {'a': ('foo', 'foo2'),
+                                               'd': ('baz', 'quux')})
+        self.assertEqual(diff(d1, d2, 'quux'), {'a': ('foo', 'foo2'),
+                                                'c': ('baz', 'quux')})
+
 if __name__ == '__main__':
     silenttestrunner.main(__name__)