Merge pull request #425 from groutr/faster-dissoc

Faster dissoc

Author: eriknw

toolz/curried/__init__.py

@@ -61,6 +61,7 @@
 assoc_in = toolz.curry(toolz.assoc_in)
 cons = toolz.curry(toolz.cons)
 countby = toolz.curry(toolz.countby)
+dissoc = toolz.curry(toolz.dissoc)
 do = toolz.curry(toolz.do)
 drop = toolz.curry(toolz.drop)
 excepts = toolz.curry(toolz.excepts)

toolz/dicttoolz.py

@@ -1,4 +1,3 @@
-import copy
 import operator
 from toolz.compatibility import (map, zip, iteritems, iterkeys, itervalues,
                                  reduce)
@@ -197,7 +196,7 @@ def assoc(d, key, value, factory=dict):
     return d2
 
 
-def dissoc(d, *keys):
+def dissoc(d, *keys, **kwargs):
     """ Return a new dict with the given key(s) removed.
 
     New dict has d[key] deleted for each supplied key.
@@ -210,10 +209,19 @@ def dissoc(d, *keys):
     >>> dissoc({'x': 1}, 'y') # Ignores missing keys
     {'x': 1}
     """
-    d2 = copy.copy(d)
-    for key in keys:
-        if key in d2:
-            del d2[key]
+    factory = _get_factory(dissoc, kwargs)
+    d2 = factory()
+
+    if len(keys) < len(d) * .6:
+        d2.update(d)
+        for key in keys:
+            if key in d2:
+                del d2[key]
+    else:
+        remaining = set(d)
+        remaining.difference_update(keys)
+        for k in remaining:
+            d2[k] = d[k]
     return d2
 
 

toolz/tests/test_dicttoolz.py

@@ -90,16 +90,16 @@ def test_assoc(self):
 
     def test_dissoc(self):
         D, kw = self.D, self.kw
-        assert dissoc(D({"a": 1}), "a") == D({})
-        assert dissoc(D({"a": 1, "b": 2}), "a") == D({"b": 2})
-        assert dissoc(D({"a": 1, "b": 2}), "b") == D({"a": 1})
-        assert dissoc(D({"a": 1, "b": 2}), "a", "b") == D({})
-        assert dissoc(D({"a": 1}), "a") == dissoc(dissoc(D({"a": 1}), "a"), "a")
+        assert dissoc(D({"a": 1}), "a", **kw) == D({})
+        assert dissoc(D({"a": 1, "b": 2}), "a", **kw) == D({"b": 2})
+        assert dissoc(D({"a": 1, "b": 2}), "b", **kw) == D({"a": 1})
+        assert dissoc(D({"a": 1, "b": 2}), "a", "b", **kw) == D({})
+        assert dissoc(D({"a": 1}), "a", **kw) == dissoc(dissoc(D({"a": 1}), "a", **kw), "a", **kw)
 
         # Verify immutability:
         d = D({'x': 1})
         oldd = d
-        d2 = dissoc(d, 'x')
+        d2 = dissoc(d, 'x', **kw)
         assert d is oldd
         assert d2 is not oldd