diff --git a/MANIFEST.in b/MANIFEST.in index 33c9835..059fdb0 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,5 +1,5 @@ include *.cpp include MurmurHash3.h -include README +include README.rst include setup.py include MANIFEST.in diff --git a/MurmurHash3.cpp b/MurmurHash3.cpp index 7d62b63..302e974 100644 --- a/MurmurHash3.cpp +++ b/MurmurHash3.cpp @@ -1,338 +1,335 @@ -//----------------------------------------------------------------------------- -// 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. -// -// modification in mmh3: -// __attribute__((always_inline)) is replaced to inline by Hajime Senuma - -#include "MurmurHash3.h" - -//----------------------------------------------------------------------------- -// Platform-specific functions and macros - -// Microsoft Visual Studio - -#if defined(_MSC_VER) - -#define FORCE_INLINE __forceinline - -#include - -#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 - -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; -} - -//----------------------------------------------------------------------------- - +//----------------------------------------------------------------------------- +// 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 + +#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; + + const uint32_t c1 = 0xcc9e2d51; + const 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(k1,15); 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; + + const uint32_t c1 = 0x239b961b; + const uint32_t c2 = 0xab0e9789; + const uint32_t c3 = 0x38b34ae5; + const 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; + + const uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5); + const 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; +} + +//----------------------------------------------------------------------------- + diff --git a/PKG-INFO b/PKG-INFO index 95b5d0e..a8b02e9 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,6 +1,6 @@ Metadata-Version: 1.0 Name: mmh3 -Version: 2.0 +Version: 2.1 Summary: Python library for MurmurHash3, a set of fast and robust hash functions. Home-page: http://packages.python.org/mmh3 Author: Hajime Senuma @@ -8,7 +8,7 @@ Author-email: hajime.senuma@gmail.com License: Public Domain Description: Python library for MurmurHash3, a set of fast and robust hash functions. - mmh3 2.0 now supports both Python 2.7 and 3.x. The interface is greatly changed. + mmh3 2.1 supports both Python 2.7 and 3.x. Sample usage: >>> import mmh3 @@ -24,7 +24,7 @@ Description: Python library for MurmurHash3, a set of fast and robust hash funct >>> mmh3.hash('foo', 42) # uses 42 for a seed 725194882 - hash64 and hash_bytes have a third argument for architecture optimization. Use True for x64 and False for x86 (default: True). + hash64 and hash_bytes have the third argument for architecture optimization. Use True for x64 and False for x86 (default: True). >>> mmh3.hash64('foo', 42, True) (-840311307571801102, -6739155424061121879) diff --git a/README b/README deleted file mode 100644 index 22a22b3..0000000 --- a/README +++ /dev/null @@ -1,25 +0,0 @@ -Python library for MurmurHash3, a set of fast and robust hash functions. - -mmh3 2.0 now supports both Python 2.7 and 3.x. The interface is greatly changed. - -Sample usage: - >>> import mmh3 - >>> mmh3.hash('foo') # 32 bit signed int - -292180858 - - >>> mmh3.hash64('foo') # two 64 bit signed ints - (-2129773440516405919, 9128664383759220103) - - >>> mmh3.hash_bytes('foo') # 128 bit value as bytes - 'aE\xf5\x01W\x86q\xe2\x87}\xba+\xe4\x87\xaf~' - - >>> mmh3.hash('foo', 42) # uses 42 for a seed - 725194882 - -hash64 and hash_bytes have a third argument for architecture optimization. Use True for x64 and False for x86 (default: True). - >>> mmh3.hash64('foo', 42, True) - (-840311307571801102, -6739155424061121879) - -MurmurHash3 was created by Austin Appleby, http://code.google.com/p/smhasher/ - -Modified by Hajime Senuma diff --git a/README.rst b/README.rst new file mode 100644 index 0000000..ddb3492 --- /dev/null +++ b/README.rst @@ -0,0 +1,61 @@ +mmh3 +==== + +Python wrapper for MurmurHash (MurmurHash3), a set of fast and robust hash functions. + +mmh3 2.1 supports both Python 2.7 and 3.x. + +Usage +----- + +Sample Usage:: + + >>> import mmh3 + >>> mmh3.hash('foo') # 32 bit signed int + -156908512 + >>> mmh3.hash64('foo') # two 64 bit signed ints + (-2129773440516405919, 9128664383759220103) + >>> mmh3.hash_bytes('foo') # 128 bit value as bytes + 'aE\xf5\x01W\x86q\xe2\x87}\xba+\xe4\x87\xaf~' + >>> mmh3.hash('foo', 42) # uses 42 for its seed + -1322301282 + +hash64 and hash_bytes have the third argument for architecture optimization. Use True for x64 and False for x86 (default: True).:: + + >>> mmh3.hash64('foo', 42, True) + (-840311307571801102, -6739155424061121879) + +Changes +======= + +2.1 (2013-02-25) +---------------- + +* Add `__version__` constant. Check if it exists when the following revision matters for your application. +* Incorporate the revision r147, which includes robustness improvement and minor tweaks. + +Beware that due to this revision, **the result of 32-bit version of 2.1 is NOT the same as that of 2.0**. E.g.,:: + + >>> mmh3.hash('foo') # in mmh3 2.0 + -292180858 + >>> mmh3.hash('foo') # in mmh3 2.1 + -156908512 + +The results of hash64 and hash_bytes remain unchanged. Austin Appleby, the author of Murmurhash, ensured this revision was the final modification to MurmurHash3's results and any future changes would be to improve performance only. + +License +======= + +Public Domain + +Authors +======= + +MurmurHash3 was created by Austin Appleby + +* http://code.google.com/p/smhasher/ + +Modified by Hajime Senuma + +* http://pypi.python.org/pypi/mmh3 +* http://github.com/hajimes/mmh3 diff --git a/mmh3module.cpp b/mmh3module.cpp index 3a02450..68adf70 100644 --- a/mmh3module.cpp +++ b/mmh3module.cpp @@ -10,7 +10,12 @@ #include "MurmurHash3.h" #if defined(_MSC_VER) +typedef signed char int8_t; +typedef signed long int32_t; typedef signed __int64 int64_t; +typedef unsigned char uint8_t; +typedef unsigned long uint32_t; +typedef unsigned __int64 uint64_t; // Other compilers #else // defined(_MSC_VER) #include @@ -112,7 +117,7 @@ static PyMethodDef Mmh3Methods[] = { "hash64(key[, seed=0, x64arch=True]) -> (hash value 1, hash value 2)\n Return a tuple of two 64 bit integers for a string. Optimized for the x64 bit architecture when x64arch=True, otherwise for x86."}, {"hash_bytes", (PyCFunction)mmh3_hash_bytes, METH_VARARGS | METH_KEYWORDS, - "hash_bytes(key[, seed=0, x64arch=True]) -> bytes\n Return a 128 bit hash value as bytes for a string. Optimized for the x64 bit architecture when x64arch=True, otherwise for the x86."}, + "hash_bytes(key[, seed=0, x64arch=True]) -> bytes\n Return a 128 bit hash value as bytes for a string. Optimized for the x64 bit architecture when x64arch=True, otherwise for the x86."}, {NULL, NULL, 0, NULL} }; @@ -164,6 +169,8 @@ initmmh3(void) if (module == NULL) INITERROR; + PyModule_AddStringConstant(module, "__version__", "2.1"); + struct module_state *st = GETSTATE(module); st->error = PyErr_NewException((char *) "mmh3.Error", NULL, NULL); diff --git a/setup.py b/setup.py index ea073af..dbffa78 100644 --- a/setup.py +++ b/setup.py @@ -8,15 +8,16 @@ sources = ['mmh3module.cpp', 'MurmurHash3.cpp']) setup(name = 'mmh3', - version = '2.0', - description = 'Python library for MurmurHash3, a set of fast and robust hash functions.', + version = '2.1', + description = 'Python library for MurmurHash (MurmurHash3), a set of fast and robust hash functions.', license = 'Public Domain', author = 'Hajime Senuma', author_email = 'hajime.senuma@gmail.com', url = 'http://packages.python.org/mmh3', ext_modules = [mmh3module], - long_description = open('README').read(), - classifiers = ['Development Status :: 4 - Beta', + keywords = "utility hash MurmurHash", + long_description = open('README.rst').read(), + classifiers = ['Development Status :: 5 - Production/Stable', 'Intended Audience :: Developers', 'License :: Public Domain', 'Programming Language :: Python :: 2.7',