scalajavac++使用murmur3计算hash值保持跨语言之间一致

    技术2022-07-11  106

    目标:在java/scala中对word计算出无符号数字(uint64)的hash值,与c++中计算的hash值一样

     

    方案:

    因为java没有uint64,而c++的murmur3是用的uint64,所以java这边直接asLong会出现负数,所以需要取原始二进制值,转换成guava提供的无符号long

    scala端:

    import com.google.common.hash.Hashing import com.google.common.primitives.UnsignedLong ... private def hash(word: String): String = { UnsignedLong.valueOf(Hashing.murmur3_128().hashString(word,StandardCharsets.UTF_8).asLong().toBinaryString,2).toString }

    c++端:

    uint64_t hash(const std::string& word) { int str_len = word.length(); const char* c_origin = word.c_str(); uint64_t res[2]; const uint32_t seed = 0; MurmurHash3_x64_128(c_origin, str_len, seed, res); return res[0]; } ... 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; int i; 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(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 = fmix64(h1); h2 = fmix64(h2); h1 += h2; h2 += h1; ((uint64_t*)out)[0] = h1; ((uint64_t*)out)[1] = h2; }

     

    Processed: 0.010, SQL: 9