integration/luprex/cpp/core/spookyv2.hpp

//
// SpookyHash: a 128-bit noncryptographic hash function
// By Bob Jenkins, public domain
//   Oct 31 2010: alpha, framework + SpookyHash::Mix appears right
//   Oct 31 2011: alpha again, Mix only good to 2^^69 but rest appears right
//   Dec 31 2011: beta, improved Mix, tested it for 2-bit deltas
//   Feb  2 2012: production, same bits as beta
//   Feb  5 2012: adjusted definitions of uint* to be more portable
//   Mar 30 2012: 3 bytes/cycle, not 4.  Alpha was 4 but wasn't thorough enough.
//   August 5 2012: SpookyV2 (different results)
// 
// Up to 3 bytes/cycle for long messages.  Reasonably fast for short messages.
// All 1 or 2 bit deltas achieve avalanche within 1% bias per output bit.
//
// This was developed for and tested on 64-bit x86-compatible processors.
// It assumes the processor is little-endian.  There is a macro
// controlling whether unaligned reads are allowed (by default they are).
// This should be an equally good hash on big-endian machines, but it will
// compute different results on them than on little-endian machines.
//
// Google's CityHash has similar specs to SpookyHash, and CityHash is faster
// on new Intel boxes.  MD4 and MD5 also have similar specs, but they are orders
// of magnitude slower.  CRCs are two or more times slower, but unlike 
// SpookyHash, they have nice math for combining the CRCs of pieces to form 
// the CRCs of wholes.  There are also cryptographic hashes, but those are even 
// slower than MD5.
//

#pragma once

#include <cstddef>
#include <cstdint>
#include <string_view>
#include <utility>

class SpookyHash
{
public:
    // A hash is two uint64's.
    //
    using HashValue = std::pair<uint64_t, uint64_t>;

    //
    // SpookyHash: hash a single message in one call, produce 128-bit output
    //
    static void ChainHash128(
        const void *message,  // message to hash
        size_t length,        // length of message in bytes
        uint64_t *hash1,      // input seed0, output hash0
        uint64_t *hash2);     // input seed1, output hash1


    static inline HashValue QkHash128(const void *message, size_t len) {
        uint64_t hash1 = 0;
        uint64_t hash2 = 0;
        ChainHash128(message, len, &hash1, &hash2);
        return std::make_pair(hash1, hash2);
    }

    static inline HashValue QkHash128(std::string_view v) {
        uint64_t hash1 = 0;
        uint64_t hash2 = 0;
        ChainHash128(v.data(), v.size(), &hash1, &hash2);
        return std::make_pair(hash1, hash2);
    }

    static inline uint64_t QkHash64(const void *message, size_t len) {
        uint64_t hash1 = 0;
        uint64_t hash2 = 0;
        ChainHash128(message, len, &hash1, &hash2);
        return hash1;
    }

    static inline uint64_t QkHash64(std::string_view v) {
        uint64_t hash1 = 0;
        uint64_t hash2 = 0;
        ChainHash128(v.data(), v.size(), &hash1, &hash2);
        return hash1;
    }
};