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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
|
/* $Id$
Part of SWI-Prolog
Author: Austin Appleby
License: Public domain
See: http://murmurhash.googlepages.com/
*/
#include <config.h>
#include <SWI-Prolog.h> /* het uintptr_t */
/* - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
The first one is actually MurmurHashNeutral2(). It produces the same
hash as MurmurHashAligned2() on little endian machines, but is
significantly slower. MurmurHashAligned2() however is broken on
big-endian machines, as it produces different hashes, depending on the
alignment.
NOTE: This file is a copy of src/pl-hash.c from SWI-Prolog.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - */
#if WORDS_BIGENDIAN
unsigned int
rdf_murmer_hash(const void * key, int len, unsigned int seed)
{ const unsigned int m = 0x5bd1e995;
const int r = 24;
unsigned int h = seed ^ len;
const unsigned char * data = (const unsigned char *)key;
while( len >= 4 )
{ unsigned int k;
k = data[0];
k |= data[1] << 8;
k |= data[2] << 16;
k |= data[3] << 24;
k *= m;
k ^= k >> r;
k *= m;
h *= m;
h ^= k;
data += 4;
len -= 4;
}
switch( len )
{ case 3: h ^= data[2] << 16;
case 2: h ^= data[1] << 8;
case 1: h ^= data[0];
h *= m;
};
h ^= h >> 13;
h *= m;
h ^= h >> 15;
return h;
}
#else /*WORDS_BIGENDIAN*/
#define MIX(h,k,m) { k *= m; k ^= k >> r; k *= m; h *= m; h ^= k; }
unsigned int
rdf_murmer_hash(const void *key, int len, unsigned int seed)
{ const unsigned int m = 0x5bd1e995;
const int r = 24;
const unsigned char * data = (const unsigned char *)key;
unsigned int h = seed ^ len;
int align = (int)(uintptr_t)data & 3;
if ( align && (len >= 4) )
{ unsigned int t = 0, d = 0;
int sl, sr;
switch( align )
{ case 1: t |= data[2] << 16;
case 2: t |= data[1] << 8;
case 3: t |= data[0];
}
t <<= (8 * align);
data += 4-align;
len -= 4-align;
sl = 8 * (4-align);
sr = 8 * align;
while ( len >= 4 )
{ unsigned int k;
d = *(unsigned int *)data;
t = (t >> sr) | (d << sl);
k = t;
MIX(h,k,m);
t = d;
data += 4;
len -= 4;
}
d = 0;
if ( len >= align )
{ unsigned int k;
switch( align )
{ case 3: d |= data[2] << 16;
case 2: d |= data[1] << 8;
case 1: d |= data[0];
}
k = (t >> sr) | (d << sl);
MIX(h,k,m);
data += align;
len -= align;
switch(len)
{ case 3: h ^= data[2] << 16;
case 2: h ^= data[1] << 8;
case 1: h ^= data[0];
h *= m;
};
} else
{ switch(len)
{ case 3: d |= data[2] << 16;
case 2: d |= data[1] << 8;
case 1: d |= data[0];
case 0: h ^= (t >> sr) | (d << sl);
h *= m;
}
}
h ^= h >> 13;
h *= m;
h ^= h >> 15;
return h;
} else
{ while( len >= 4 )
{ unsigned int k = *(unsigned int *)data;
MIX(h,k,m);
data += 4;
len -= 4;
}
switch(len)
{ case 3: h ^= data[2] << 16;
case 2: h ^= data[1] << 8;
case 1: h ^= data[0];
h *= m;
};
h ^= h >> 13;
h *= m;
h ^= h >> 15;
return h;
}
}
#endif /*WORDS_BIGENDIAN*/
|
