|
|
Boost-Commit : |
Subject: [Boost-commit] svn:boost r72181 - in sandbox/bloom_filter/trunk: . include include/murmurhash3 lib/murmurhash3 test
From: cpp.cabrera_at_[hidden]
Date: 2011-05-26 09:18:13
Author: alejandro
Date: 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
New Revision: 72181
URL: http://svn.boost.org/trac/boost/changeset/72181
Log:
Updated test suite to use Boost.Test rather than GoogleTest. Reorganized a bit more. Updated README to include more details on compression and deletion policies.
Added:
sandbox/bloom_filter/trunk/include/murmurhash3/
sandbox/bloom_filter/trunk/include/murmurhash3/MurmurHash3.h (contents, props changed)
- copied, changed from r72180, /sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.h
sandbox/bloom_filter/trunk/test/boost_test.cpp (contents, props changed)
sandbox/bloom_filter/trunk/test/murmurhash3.cpp (contents, props changed)
- copied, changed from r72180, /sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.cpp
Removed:
sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.cpp
sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.h
sandbox/bloom_filter/trunk/test/test_bloom.cpp
Text files modified:
sandbox/bloom_filter/trunk/README | 38 +++++++++++++++++++++++++++++
sandbox/bloom_filter/trunk/include/bloom.hpp | 51 ++++++++++++++++++++-------------------
sandbox/bloom_filter/trunk/include/hash.hpp | 14 ++++++++++
sandbox/bloom_filter/trunk/test/makefile | 17 +++++++------
4 files changed, 86 insertions(+), 34 deletions(-)
Modified: sandbox/bloom_filter/trunk/README
==============================================================================
--- sandbox/bloom_filter/trunk/README (original)
+++ sandbox/bloom_filter/trunk/README 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
@@ -10,5 +10,41 @@
To run:
$> ./test_bloom
--Alejandro Cabrera
+===== Compression =====
+
+(Lossless) Compression policies to investigate:
+- LZ (Lempel-Ziv), e.g., DEFLATE
+- LZR (LZ-Renau), Zip
+- LZX, MSFT Cab format
+- Burrows-Wheeler
+- check wiki page on compression
+
+A compression policy looks as below:
+template <size_t Size>
+struct CompressionPolicy {
+ size_t compress(const char *const in, char *out, const size_t insize);
+ void decompress(const char *const in, char *out, const size_t insize);
+};
+
+compress() returns the size of the data when compressed.
+
+Since compress and decompress will only ever used in association
+with the bits of a Bloom filter, the Size parameter can be embedded in
+the policy template. This represents the uncompressed size of the Bloom
+filter.
+===== Deleting Variants =====
+
+Deletion should not be embedded as a policy. Inherently,
+Bloom filters that use a deletion policy have different data layouts.
+For example, Scalable Bloom filters must be grown to always satisfy
+the desired false positive rate. There are also Counting Bloom filters,
+that instead of storing a bit array, require storing an array of 3-4 bit
+counters.
+
+A few deleting variants:
+- Scalable Counting Bloom filter
+- Counting Bloom filter
+- Bloomier filters
+
+-Alejandro Cabrera
Modified: sandbox/bloom_filter/trunk/include/bloom.hpp
==============================================================================
--- sandbox/bloom_filter/trunk/include/bloom.hpp (original)
+++ sandbox/bloom_filter/trunk/include/bloom.hpp 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
@@ -8,7 +8,8 @@
#include <boost/config.hpp>
#include <bitset>
#include <tuple>
-#include "hash.hpp"
+
+#include <hash.hpp>
template <size_t N,
typename T,
@@ -85,37 +86,37 @@
this->bits.reset();
}
- // \todo: need to add compiler check for rvalue references
- bloom_filter(const bloom_filter&&);
- bloom_filter& operator=(const bloom_filter&& other);
-
bloom_filter& operator|=(const bloom_filter& rhs) {
this->bits |= rhs.bits;
+ return *this;
}
-
+
bloom_filter& operator&=(const bloom_filter& rhs) {
this->bits &= rhs.bits;
+ return *this;
}
-
- template<class _T, size_t _Size, class _HashFunctions>
- friend bloom_filter<_T, _Size, _HashFunctions>&
- operator|(const bloom_filter<_T, _Size, _HashFunctions>& lhs,
- const bloom_filter<_T, _Size, _HashFunctions>& rhs)
- {
- bloom_filter<_T, _Size, _HashFunctions> ret = lhs;
- return (ret |= rhs);
- }
-
- template<class _T, size_t _Size, class _HashFunctions>
- friend bloom_filter<_T, _Size, _HashFunctions>&
- operator&(const bloom_filter<_T, _Size, _HashFunctions>& lhs,
- const bloom_filter<_T, _Size, _HashFunctions>& rhs)
- {
- bloom_filter<_T, _Size, _HashFunctions> ret = lhs;
- return (ret &= rhs);
- }
-
+
private:
std::bitset<Size> bits;
};
+
+template<class _T, size_t _Size, class _HashFunctions>
+bloom_filter<_T, _Size, _HashFunctions>
+operator|(const bloom_filter<_T, _Size, _HashFunctions>& lhs,
+ const bloom_filter<_T, _Size, _HashFunctions>& rhs)
+{
+ bloom_filter<_T, _Size, _HashFunctions> ret = lhs;
+ ret |= rhs;
+ return ret;
+}
+
+template<class _T, size_t _Size, class _HashFunctions>
+bloom_filter<_T, _Size, _HashFunctions>
+operator&(const bloom_filter<_T, _Size, _HashFunctions>& lhs,
+ const bloom_filter<_T, _Size, _HashFunctions>& rhs)
+{
+ bloom_filter<_T, _Size, _HashFunctions> ret = lhs;
+ ret &= rhs;
+ return ret;
+}
#endif
Modified: sandbox/bloom_filter/trunk/include/hash.hpp
==============================================================================
--- sandbox/bloom_filter/trunk/include/hash.hpp (original)
+++ sandbox/bloom_filter/trunk/include/hash.hpp 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
@@ -8,6 +8,7 @@
* \todo Provide 64-bit implementation of murmurhash3.
*/
#include <cstdint>
+#include <murmurhash3/MurmurHash3.h>
template <typename UnsignedIntT>
inline UnsignedIntT rotl(const UnsignedIntT x, uint8_t r)
@@ -101,4 +102,17 @@
return out;
}
};
+
+// uses public domain implementation of murmurhash3
+template <typename T, size_t Seed>
+struct OHash {
+ static size_t hash(const T& t) {
+ size_t out = 0;
+ MurmurHash3_x86_32(static_cast<const void *const>(&t),
+ sizeof(t),
+ Seed,
+ &out);
+ return out;
+ }
+};
#endif
Copied: sandbox/bloom_filter/trunk/include/murmurhash3/MurmurHash3.h (from r72180, /sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.h)
==============================================================================
Deleted: sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.cpp
==============================================================================
--- sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.cpp 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
+++ (empty file)
@@ -1,335 +0,0 @@
-//-----------------------------------------------------------------------------
-// MurmurHash3 was written by Austin Appleby, and is placed in the public
-// domain. The author hereby disclaims copyright to this source code.
-
-// Note - The x86 and x64 versions do _not_ produce the same results, as the
-// algorithms are optimized for their respective platforms. You can still
-// compile and run any of them on any platform, but your performance with the
-// non-native version will be less than optimal.
-
-#include "MurmurHash3.h"
-
-//-----------------------------------------------------------------------------
-// Platform-specific functions and macros
-
-// Microsoft Visual Studio
-
-#if defined(_MSC_VER)
-
-#define FORCE_INLINE __forceinline
-
-#include <stdlib.h>
-
-#define ROTL32(x,y) _rotl(x,y)
-#define ROTL64(x,y) _rotl64(x,y)
-
-#define BIG_CONSTANT(x) (x)
-
-// Other compilers
-
-#else // defined(_MSC_VER)
-
-#define FORCE_INLINE __attribute__((always_inline))
-
-inline uint32_t rotl32 ( uint32_t x, int8_t r )
-{
- return (x << r) | (x >> (32 - r));
-}
-
-inline uint64_t rotl64 ( uint64_t x, int8_t r )
-{
- return (x << r) | (x >> (64 - r));
-}
-
-#define ROTL32(x,y) rotl32(x,y)
-#define ROTL64(x,y) rotl64(x,y)
-
-#define BIG_CONSTANT(x) (x##LLU)
-
-#endif // !defined(_MSC_VER)
-
-//-----------------------------------------------------------------------------
-// Block read - if your platform needs to do endian-swapping or can only
-// handle aligned reads, do the conversion here
-
-FORCE_INLINE uint32_t getblock ( const uint32_t * p, int i )
-{
- return p[i];
-}
-
-FORCE_INLINE uint64_t getblock ( const uint64_t * p, int i )
-{
- return p[i];
-}
-
-//-----------------------------------------------------------------------------
-// Finalization mix - force all bits of a hash block to avalanche
-
-FORCE_INLINE uint32_t fmix ( uint32_t h )
-{
- h ^= h >> 16;
- h *= 0x85ebca6b;
- h ^= h >> 13;
- h *= 0xc2b2ae35;
- h ^= h >> 16;
-
- return h;
-}
-
-//----------
-
-FORCE_INLINE uint64_t fmix ( uint64_t k )
-{
- k ^= k >> 33;
- k *= BIG_CONSTANT(0xff51afd7ed558ccd);
- k ^= k >> 33;
- k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53);
- k ^= k >> 33;
-
- return k;
-}
-
-//-----------------------------------------------------------------------------
-
-void MurmurHash3_x86_32 ( const void * key, int len,
- uint32_t seed, void * out )
-{
- const uint8_t * data = (const uint8_t*)key;
- const int nblocks = len / 4;
-
- uint32_t h1 = seed;
-
- uint32_t c1 = 0xcc9e2d51;
- uint32_t c2 = 0x1b873593;
-
- //----------
- // body
-
- const uint32_t * blocks = (const uint32_t *)(data + nblocks*4);
-
- for(int i = -nblocks; i; i++)
- {
- uint32_t k1 = getblock(blocks,i);
-
- k1 *= c1;
- k1 = ROTL32(k1,15);
- k1 *= c2;
-
- h1 ^= k1;
- h1 = ROTL32(h1,13);
- h1 = h1*5+0xe6546b64;
- }
-
- //----------
- // tail
-
- const uint8_t * tail = (const uint8_t*)(data + nblocks*4);
-
- uint32_t k1 = 0;
-
- switch(len & 3)
- {
- case 3: k1 ^= tail[2] << 16;
- case 2: k1 ^= tail[1] << 8;
- case 1: k1 ^= tail[0];
- k1 *= c1; k1 = ROTL32(k1,16); k1 *= c2; h1 ^= k1;
- };
-
- //----------
- // finalization
-
- h1 ^= len;
-
- h1 = fmix(h1);
-
- *(uint32_t*)out = h1;
-}
-
-//-----------------------------------------------------------------------------
-
-void MurmurHash3_x86_128 ( const void * key, const int len,
- uint32_t seed, void * out )
-{
- const uint8_t * data = (const uint8_t*)key;
- const int nblocks = len / 16;
-
- uint32_t h1 = seed;
- uint32_t h2 = seed;
- uint32_t h3 = seed;
- uint32_t h4 = seed;
-
- uint32_t c1 = 0x239b961b;
- uint32_t c2 = 0xab0e9789;
- uint32_t c3 = 0x38b34ae5;
- uint32_t c4 = 0xa1e38b93;
-
- //----------
- // body
-
- const uint32_t * blocks = (const uint32_t *)(data + nblocks*16);
-
- for(int i = -nblocks; i; i++)
- {
- uint32_t k1 = getblock(blocks,i*4+0);
- uint32_t k2 = getblock(blocks,i*4+1);
- uint32_t k3 = getblock(blocks,i*4+2);
- uint32_t k4 = getblock(blocks,i*4+3);
-
- k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
-
- h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b;
-
- k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
-
- h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747;
-
- k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
-
- h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35;
-
- k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
-
- h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17;
- }
-
- //----------
- // tail
-
- const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
-
- uint32_t k1 = 0;
- uint32_t k2 = 0;
- uint32_t k3 = 0;
- uint32_t k4 = 0;
-
- switch(len & 15)
- {
- case 15: k4 ^= tail[14] << 16;
- case 14: k4 ^= tail[13] << 8;
- case 13: k4 ^= tail[12] << 0;
- k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
-
- case 12: k3 ^= tail[11] << 24;
- case 11: k3 ^= tail[10] << 16;
- case 10: k3 ^= tail[ 9] << 8;
- case 9: k3 ^= tail[ 8] << 0;
- k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
-
- case 8: k2 ^= tail[ 7] << 24;
- case 7: k2 ^= tail[ 6] << 16;
- case 6: k2 ^= tail[ 5] << 8;
- case 5: k2 ^= tail[ 4] << 0;
- k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
-
- case 4: k1 ^= tail[ 3] << 24;
- case 3: k1 ^= tail[ 2] << 16;
- case 2: k1 ^= tail[ 1] << 8;
- case 1: k1 ^= tail[ 0] << 0;
- k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
- };
-
- //----------
- // finalization
-
- h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len;
-
- h1 += h2; h1 += h3; h1 += h4;
- h2 += h1; h3 += h1; h4 += h1;
-
- h1 = fmix(h1);
- h2 = fmix(h2);
- h3 = fmix(h3);
- h4 = fmix(h4);
-
- h1 += h2; h1 += h3; h1 += h4;
- h2 += h1; h3 += h1; h4 += h1;
-
- ((uint32_t*)out)[0] = h1;
- ((uint32_t*)out)[1] = h2;
- ((uint32_t*)out)[2] = h3;
- ((uint32_t*)out)[3] = h4;
-}
-
-//-----------------------------------------------------------------------------
-
-void MurmurHash3_x64_128 ( const void * key, const int len,
- const uint32_t seed, void * out )
-{
- const uint8_t * data = (const uint8_t*)key;
- const int nblocks = len / 16;
-
- uint64_t h1 = seed;
- uint64_t h2 = seed;
-
- uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
- uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f);
-
- //----------
- // body
-
- const uint64_t * blocks = (const uint64_t *)(data);
-
- for(int i = 0; i < nblocks; i++)
- {
- uint64_t k1 = getblock(blocks,i*2+0);
- uint64_t k2 = getblock(blocks,i*2+1);
-
- k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
-
- h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;
-
- k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
-
- h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
- }
-
- //----------
- // tail
-
- const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
-
- uint64_t k1 = 0;
- uint64_t k2 = 0;
-
- switch(len & 15)
- {
- case 15: k2 ^= uint64_t(tail[14]) << 48;
- case 14: k2 ^= uint64_t(tail[13]) << 40;
- case 13: k2 ^= uint64_t(tail[12]) << 32;
- case 12: k2 ^= uint64_t(tail[11]) << 24;
- case 11: k2 ^= uint64_t(tail[10]) << 16;
- case 10: k2 ^= uint64_t(tail[ 9]) << 8;
- case 9: k2 ^= uint64_t(tail[ 8]) << 0;
- k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
-
- case 8: k1 ^= uint64_t(tail[ 7]) << 56;
- case 7: k1 ^= uint64_t(tail[ 6]) << 48;
- case 6: k1 ^= uint64_t(tail[ 5]) << 40;
- case 5: k1 ^= uint64_t(tail[ 4]) << 32;
- case 4: k1 ^= uint64_t(tail[ 3]) << 24;
- case 3: k1 ^= uint64_t(tail[ 2]) << 16;
- case 2: k1 ^= uint64_t(tail[ 1]) << 8;
- case 1: k1 ^= uint64_t(tail[ 0]) << 0;
- k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
- };
-
- //----------
- // finalization
-
- h1 ^= len; h2 ^= len;
-
- h1 += h2;
- h2 += h1;
-
- h1 = fmix(h1);
- h2 = fmix(h2);
-
- h1 += h2;
- h2 += h1;
-
- ((uint64_t*)out)[0] = h1;
- ((uint64_t*)out)[1] = h2;
-}
-
-//-----------------------------------------------------------------------------
-
Deleted: sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.h
==============================================================================
--- sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.h 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
+++ (empty file)
@@ -1,37 +0,0 @@
-//-----------------------------------------------------------------------------
-// MurmurHash3 was written by Austin Appleby, and is placed in the public
-// domain. The author hereby disclaims copyright to this source code.
-
-#ifndef _MURMURHASH3_H_
-#define _MURMURHASH3_H_
-
-//-----------------------------------------------------------------------------
-// Platform-specific functions and macros
-
-// Microsoft Visual Studio
-
-#if defined(_MSC_VER)
-
-typedef unsigned char uint8_t;
-typedef unsigned long uint32_t;
-typedef unsigned __int64 uint64_t;
-
-// Other compilers
-
-#else // defined(_MSC_VER)
-
-#include <stdint.h>
-
-#endif // !defined(_MSC_VER)
-
-//-----------------------------------------------------------------------------
-
-void MurmurHash3_x86_32 ( const void * key, int len, uint32_t seed, void * out );
-
-void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out );
-
-void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out );
-
-//-----------------------------------------------------------------------------
-
-#endif // _MURMURHASH3_H_
Added: sandbox/bloom_filter/trunk/test/boost_test.cpp
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/trunk/test/boost_test.cpp 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
@@ -0,0 +1,174 @@
+#define BOOST_TEST_DYN_LINK
+#define BOOST_TEST_MODULE "Boost Bloom Filter" 1
+#include <iostream>
+
+#include <bloom.hpp>
+#include <boost/test/unit_test.hpp>
+
+BOOST_AUTO_TEST_CASE(defaultConstructor) {
+ typedef std::tuple<
+ OHash <int, 2>,
+ OHash<int, 3>,
+ OHash<int, 5>,
+ OHash<int, 7>,
+ OHash<int, 11>,
+ OHash<int, 13>,
+ OHash<int, 17>,
+ OHash<int, 19>> EightHashFunctions_O;
+
+ bloom_filter<int, 8> bloom1;
+ bloom_filter<int, 8, EightHashFunctions_O> bloom2;
+}
+
+BOOST_AUTO_TEST_CASE(assignment)
+{
+ bloom_filter<int, 8> bloom1;
+ bloom_filter<int, 8> bloom2;
+
+ for (size_t i = 0; i < 200; ++i) {
+ bloom1.insert(i);
+ BOOST_CHECK_EQUAL(bloom1.contains(i), true);
+ }
+
+ bloom2 = bloom1;
+
+ for (size_t i = 0; i < 200; ++i) {
+ BOOST_CHECK_EQUAL(bloom2.contains(i), true);
+ }
+}
+
+BOOST_AUTO_TEST_CASE(size) {
+ bloom_filter<size_t, 8> bloom_8;
+ bloom_filter<size_t, 256> bloom_256;
+ bloom_filter<size_t, 2048> bloom_2048;
+
+ BOOST_CHECK_EQUAL(bloom_8.size(), 8ul);
+ BOOST_CHECK_EQUAL(bloom_256.size(), 256ul);
+ BOOST_CHECK_EQUAL(bloom_2048.size(), 2048ul);
+}
+
+BOOST_AUTO_TEST_CASE(contains) {
+ bloom_filter<size_t, 8> bloom;
+
+ bloom.insert(1);
+ BOOST_CHECK_EQUAL(bloom.contains(1), true);
+}
+
+BOOST_AUTO_TEST_CASE(containsOperator) {
+ bloom_filter<size_t, 8> bloom;
+
+ bloom.insert(1);
+ BOOST_CHECK_EQUAL(bloom.contains(1), true);
+}
+
+BOOST_AUTO_TEST_CASE(doesNotContain) {
+ bloom_filter<size_t, 8> bloom;
+
+ BOOST_CHECK_EQUAL(bloom.contains(1), false);
+}
+
+BOOST_AUTO_TEST_CASE(insertNoFalseNegatives) {
+ bloom_filter<size_t, 2048> bloom;
+
+ for (size_t i = 0; i < 100; ++i) {
+ bloom.insert(i);
+ BOOST_CHECK_EQUAL(bloom.contains(i), true);
+ }
+}
+
+BOOST_AUTO_TEST_CASE(clear) {
+ bloom_filter<size_t, 8> bloom;
+
+ for (size_t i = 0; i < 1000; ++i)
+ bloom.insert(i);
+
+ bloom.clear();
+ BOOST_CHECK_EQUAL(bloom.contains(1), false);
+}
+
+BOOST_AUTO_TEST_CASE(testUnion) {
+ bloom_filter<size_t, 32> bloom_1;
+ bloom_filter<size_t, 32> bloom_2;
+ bloom_filter<size_t, 32> bloom_union;
+
+ for (size_t i = 0; i < 100; ++i)
+ bloom_1.insert(i);
+
+ for (size_t i = 100; i < 200; ++i)
+ bloom_2.insert(i);
+
+ bloom_union = bloom_1 | bloom_2;
+
+ for (size_t i = 0; i < 200; ++i)
+ BOOST_CHECK_EQUAL(bloom_union.contains(i), true);
+}
+
+BOOST_AUTO_TEST_CASE(testUnionAssign) {
+ bloom_filter<size_t, 32> bloom_1;
+ bloom_filter<size_t, 32> bloom_2;
+
+ for (size_t i = 0; i < 100; ++i)
+ bloom_1.insert(i);
+
+ bloom_2 |= bloom_1;
+
+ for (size_t i = 0; i < 100; ++i)
+ BOOST_CHECK_EQUAL(bloom_2.contains(i), true);
+}
+
+BOOST_AUTO_TEST_CASE(testIntersect) {
+ bloom_filter<size_t, 8> bloom_1;
+ bloom_filter<size_t, 8> bloom_2;
+ bloom_filter<size_t, 8> bloom_intersect;
+
+ for (size_t i = 0; i < 100; ++i)
+ bloom_1.insert(i);
+
+ for (size_t i = 100; i < 200; ++i)
+ bloom_2.insert(i);
+
+ bloom_intersect = bloom_1 & bloom_2;
+
+ for (size_t i = 0; i < 200; ++i)
+ BOOST_CHECK_EQUAL(bloom_intersect.contains(i), false);
+}
+
+BOOST_AUTO_TEST_CASE(testIntersectAssign) {
+ bloom_filter<size_t, 8> bloom_1;
+ bloom_filter<size_t, 8> bloom_2;
+
+ for (size_t i = 0; i < 100; ++i)
+ bloom_1.insert(i);
+
+ bloom_2 &= bloom_1;
+
+ for (size_t i = 0; i < 100; ++i)
+ BOOST_CHECK_EQUAL(bloom_2.contains(i), false);
+}
+
+BOOST_AUTO_TEST_CASE(collisionBenchmark) {
+ typedef std::tuple<
+ OHash <size_t, 2>,
+ OHash<size_t, 3>,
+ OHash<size_t, 5>,
+ OHash<size_t, 7>,
+ OHash<size_t, 11>,
+ OHash<size_t, 13>,
+ OHash<size_t, 17>,
+ OHash<size_t, 19>> EightHashFunctions_O;
+
+ static const size_t INSERT_VAL = 100;
+ static const size_t SEARCH_SPACE = 10000000;
+ static const size_t FILTER_SIZE = 64;
+ size_t collisions = 0;
+ bloom_filter<size_t, FILTER_SIZE, EightHashFunctions_O> bloom;
+
+ std::cout << "bloom size " << bloom.size() << std::endl;
+ bloom.insert(INSERT_VAL);
+ for (size_t i = 0; i < SEARCH_SPACE; ++i) {
+ if (bloom[i] && i != INSERT_VAL) ++collisions;
+ }
+
+ std::cout << collisions << " collisions" << std::endl;
+ bloom.clear();
+}
Modified: sandbox/bloom_filter/trunk/test/makefile
==============================================================================
--- sandbox/bloom_filter/trunk/test/makefile (original)
+++ sandbox/bloom_filter/trunk/test/makefile 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
@@ -1,14 +1,15 @@
CXXFLAGS := -Wall -Wextra -pedantic -std=c++0x -O3 -g
-ST_LIBS := ../lib/murmurhash3/MurmurHash3.o
+LD_FLAGS := -lpthread -lboost_unit_test_framework
INCLUDE_DIR := ../include
-INCLUDES := $(INCLUDE_DIR)/bloom.hpp $(INCLUDE_DIR)/hash.hpp
-all : test_bloom
+INCLUDES := -I$(INCLUDE_DIR) -I$(INCLUDE_DIR)/murmurhash3
+EXES := boost_test
+all : $(EXES)
-%.o : %.cpp $(INCLUDES)
- $(CXX) $(CXXFLAGS) -c $<
+%.o : %.cpp $(INCLUDE_DIR)/bloom.hpp
+ $(CXX) $(CXXFLAGS) -c $< $(INCLUDES)
-test_bloom : test_bloom.o $(INCLUDES)
- $(CXX) $(CXXFLAGS) -o $@ $< $(ST_LIBS)
+boost_test : boost_test.o murmurhash3.o
+ $(CXX) $(CXXFLAGS) -o $@ $^ $(INCLUDES) $(LD_FLAGS)
clean:
- rm -f *.o test_bloom
+ rm -f *.o $(EXES)
Copied: sandbox/bloom_filter/trunk/test/murmurhash3.cpp (from r72180, /sandbox/bloom_filter/trunk/lib/murmurhash3/MurmurHash3.cpp)
==============================================================================
Deleted: sandbox/bloom_filter/trunk/test/test_bloom.cpp
==============================================================================
--- sandbox/bloom_filter/trunk/test/test_bloom.cpp 2011-05-26 09:18:11 EDT (Thu, 26 May 2011)
+++ (empty file)
@@ -1,48 +0,0 @@
-#include <iostream>
-#include "../lib/murmurhash3/MurmurHash3.h"
-#include "../include/bloom.hpp"
-
-typedef int BloomType;
-
-template <typename T, size_t Seed>
-struct OHash {
- static size_t hash(const T& t) {
- size_t out = 0;
- MurmurHash3_x86_32(static_cast<const void *const>(&t),
- sizeof(t),
- Seed,
- &out);
- return out;
- }
-};
-
-typedef std::tuple<OHash<BloomType, 2>,
- OHash<BloomType, 3>,
- OHash<BloomType, 5>,
- OHash<BloomType, 7>,
- OHash<BloomType, 11>,
- OHash<BloomType, 13>,
- OHash<BloomType, 17>,
- OHash<BloomType, 19>> EightHashFunctions_O;
-
-//typedef std::tuple<MurmurHash3<BloomType, 19>> SingleHashFunction;
-
-int main()
-{
- static const BloomType INSERT_VAL = 100;
- static const size_t SEARCH_SPACE = 10000000;
- static const size_t FILTER_SIZE = 64;
- size_t collisions = 0;
- bloom_filter<BloomType, FILTER_SIZE, EightHashFunctions_O> bloom;
-
- std::cout << "bloom size " << sizeof(bloom) << std::endl;
- bloom.insert(INSERT_VAL);
- for (size_t i = 0; i < SEARCH_SPACE; ++i) {
- if (bloom[i] && i != INSERT_VAL) ++collisions;
- }
-
- std::cout << collisions << " collisions" << std::endl;
- bloom.clear();
-
- return 0;
-}
Boost-Commit list run by bdawes at acm.org, david.abrahams at rcn.com, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk