From 0688743c21e9d13c5ce4e0f27d5170aa9b7e464f Mon Sep 17 00:00:00 2001
From: Jay Baird <jay.baird@me.com>
Date: Fri, 11 Mar 2011 14:28:01 -0500
Subject: [PATCH] re #2, add changelog, union, intersection and copy to
 BloomFilter, not yet available in SBF. Bumped version number to 1.1

---
 CHANGES.txt        |  3 +++
 LICENSE.txt        |  2 +-
 pybloom/pybloom.py | 29 ++++++++++++++++++++++++++++-
 pybloom/tests.py   | 27 +++++++++++++++++++++++++++
 4 files changed, 59 insertions(+), 2 deletions(-)
 create mode 100644 CHANGES.txt

diff --git a/CHANGES.txt b/CHANGES.txt
new file mode 100644
index 0000000..44a24e2
--- /dev/null
+++ b/CHANGES.txt
@@ -0,0 +1,3 @@
+Changes in 1.1
+==============
+Added copy, intersection and union functions to BloomFilter
\ No newline at end of file
diff --git a/LICENSE.txt b/LICENSE.txt
index 1353e37..11a07db 100644
--- a/LICENSE.txt
+++ b/LICENSE.txt
@@ -1,4 +1,4 @@
-Copyright (c) <2009> <Jay Baird and Bob Ippolito>
+Copyright (c) <2011> <Jay Baird and Bob Ippolito>
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation
diff --git a/pybloom/pybloom.py b/pybloom/pybloom.py
index 504cea1..dcb48d9 100644
--- a/pybloom/pybloom.py
+++ b/pybloom/pybloom.py
@@ -42,7 +42,7 @@
 except ImportError:
     raise ImportError('pybloom requires bitarray >= 0.3.4')
 
-__version__ = '1.0.3'
+__version__ = '1.1'
 __author__  = "Jay Baird <jay@mochimedia.com>, Bob Ippolito <bob@redivi.com>,\
                Marius Eriksen <marius@monkey.org>, Alex Brassetvik <alex@brasetvik.com>"
 
@@ -187,6 +187,33 @@ def add(self, key, skip_check=False):
         self.count += 1
         return False
 
+    def copy(self):
+        """Return a copy of this bloom filter.
+        """
+        new_filter = BloomFilter(self.capacity, self.error_rate)
+        new_filter.bitarray = self.bitarray.copy()
+        return new_filter
+
+    def union(self, other):
+        """ Calculates the union of the two underlying bitarrays and returns
+        a new bloom filter object."""
+        new_bloom = self.copy()
+        new_bloom.bitarray = new_bloom.bitarray | other.bitarray
+        return new_bloom
+
+    def __or__(self, other):
+        return self.union(other)
+
+    def intersection(self, other):
+        """ Calculates the union of the two underlying bitarrays and returns
+        a new bloom filter object."""
+        new_bloom = self.copy()
+        new_bloom.bitarray = new_bloom.bitarray & other.bitarray
+        return new_bloom
+    
+    def __and__(self, other):
+        return self.intersection(other)
+        
     def tofile(self, f):
         """Write the bloom filter to file object `f'. Underlying bits
         are written as machine values. This is much more space
diff --git a/pybloom/tests.py b/pybloom/tests.py
index 32f34ae..d7d59bb 100644
--- a/pybloom/tests.py
+++ b/pybloom/tests.py
@@ -14,6 +14,33 @@ def additional_tests():
         suite.addTest(doctest.DocFileSuite(readme_fn, module_relative=False))
     return suite
 
+class TestUnionIntersection(unittest.TestCase):
+    def test_union(self):
+        bloom_one = BloomFilter(100, 0.001)
+        bloom_two = BloomFilter(100, 0.001)
+        chars = [chr(i) for i in range(97, 123)]
+        for char in chars[len(chars)/2:]:
+            bloom_one.add(char)
+        for char in chars[:len(chars)/2]:
+            bloom_two.add(char)
+        new_bloom = bloom_one.union(bloom_two)
+        for char in chars:
+            assert(char in new_bloom)
+            
+    def test_intersection(self):
+        bloom_one = BloomFilter(100, 0.001)
+        bloom_two = BloomFilter(100, 0.001)
+        chars = [chr(i) for i in range(97, 123)]
+        for char in chars:
+            bloom_one.add(char)
+        for char in chars[:len(chars)/2]:
+            bloom_two.add(char)
+        new_bloom = bloom_one.intersection(bloom_two)
+        for char in chars[:len(chars)/2]:
+            assert(char in new_bloom)
+        for char in chars[len(chars)/2:]:
+            assert(char not in new_bloom)    
+
 class Serialization(unittest.TestCase):
     SIZE = 12345
     EXPECTED = set([random.randint(0, 10000100) for _ in xrange(SIZE)])