Rework multiset methods to use less memory and to make fewer calls to __hash__.
diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py
index bd19614..a6bcaea 100644
--- a/Lib/collections/__init__.py
+++ b/Lib/collections/__init__.py
@@ -601,10 +601,13 @@
if not isinstance(other, Counter):
return NotImplemented
result = Counter()
- for elem in set(self) | set(other):
- newcount = self[elem] + other[elem]
+ for elem, count in self.items():
+ newcount = count + other[elem]
if newcount > 0:
result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count > 0:
+ result[elem] = count
return result
def __sub__(self, other):
@@ -617,10 +620,13 @@
if not isinstance(other, Counter):
return NotImplemented
result = Counter()
- for elem in set(self) | set(other):
- newcount = self[elem] - other[elem]
+ for elem, count in self.items():
+ newcount = count - other[elem]
if newcount > 0:
result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count < 0:
+ result[elem] = 0 - count
return result
def __or__(self, other):
@@ -633,11 +639,14 @@
if not isinstance(other, Counter):
return NotImplemented
result = Counter()
- for elem in set(self) | set(other):
- p, q = self[elem], other[elem]
- newcount = q if p < q else p
+ for elem, count in self.items():
+ other_count = other[elem]
+ newcount = other_count if count < other_count else count
if newcount > 0:
result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count > 0:
+ result[elem] = count
return result
def __and__(self, other):
@@ -650,11 +659,9 @@
if not isinstance(other, Counter):
return NotImplemented
result = Counter()
- if len(self) < len(other):
- self, other = other, self
- for elem in filter(self.__contains__, other):
- p, q = self[elem], other[elem]
- newcount = p if p < q else q
+ for elem, count in self.items():
+ other_count = other[elem]
+ newcount = count if count < other_count else other_count
if newcount > 0:
result[elem] = newcount
return result