/*
 * MurmurHash3_x86_128 (C) Austin Appleby
 */

#include "init.h"

void
murmur_hash_process3_x86_128(const char * key, uint32_t 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;

  int i;

  //----------
  // body

  const uint32_t * blocks = (const uint32_t *)(data + nblocks*16);

  for(i = -nblocks; i; i++)
  {
    uint32_t k1 = getblock32(blocks,i*4+0);
    uint32_t k2 = getblock32(blocks,i*4+1);
    uint32_t k3 = getblock32(blocks,i*4+2);
    uint32_t k4 = getblock32(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 = fmix32(h1);
  h2 = fmix32(h2);
  h3 = fmix32(h3);
  h4 = fmix32(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;
}

VALUE
murmur3_x86_128_finish(VALUE self)
{
  uint8_t digest[16];
  uint32_t out[4];

  _murmur_finish128(self, out, murmur_hash_process3_x86_128);
  assign_by_endian_128(digest, out);
  return rb_str_new((const char*) digest, 16);
}

VALUE
murmur3_x86_128_s_digest(int argc, VALUE *argv, VALUE klass)
{
  uint8_t digest[16];
  uint32_t out[4];

  _murmur_s_digest128(argc, argv, klass, out, murmur_hash_process3_x86_128);
  assign_by_endian_128(digest, out);
  return rb_str_new((const char*) digest, 16);
}

VALUE
murmur3_x86_128_s_rawdigest(int argc, VALUE *argv, VALUE klass)
{
  uint64_t out[2];

  _murmur_s_digest128(argc, argv, klass, (void*)out, murmur_hash_process3_x86_128);
  return rb_assoc_new(ULL2NUM(out[0]), ULL2NUM(out[1]));
}