libpostal-sys 0.1.1

Low-level wrappers for libpostal address normalization (with locks to support thread-safe initialization)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118

//-----------------------------------------------------------------------------
// 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 "murmur.h"

#define FORCE_INLINE inline static

FORCE_INLINE uint64_t rotl64 ( uint64_t x, int8_t r )
{
    return (x << r) | (x >> (64 - r));
}

#define ROTL64(x,y) rotl64(x,y)

#define BIG_CONSTANT(x) (x##LLU)

#define getblock(x, i) (x[i])

//-----------------------------------------------------------------------------
// Finalization mix - force all bits of a hash block to avalanche

FORCE_INLINE uint64_t fmix64(uint64_t k)
{
    k ^= k >> 33;
    k *= BIG_CONSTANT(0xff51afd7ed558ccd);
    k ^= k >> 33;
    k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53);
    k ^= k >> 33;

    return k;
}

//-----------------------------------------------------------------------------

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);

    int i;

    //----------
    // 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;
}