xxhash 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +17 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +31 -0
- data/Rakefile +20 -0
- data/ext/xxhash/extconf.rb +8 -0
- data/ext/xxhash/libxxhash.c +342 -0
- data/ext/xxhash/libxxhash.h +128 -0
- data/ext/xxhash/xxhash.cc +19 -0
- data/lib/xxhash.rb +8 -0
- data/lib/xxhash/version.rb +3 -0
- data/test/test_helper.rb +4 -0
- data/test/xxhash_test.rb +7 -0
- data/xxhash.gemspec +20 -0
- metadata +68 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Vasiliy Ermolovich
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
## xxHash
|
2
|
+
|
3
|
+
Ruby wrapper for [xxHash](http://code.google.com/p/xxhash/)
|
4
|
+
|
5
|
+
### Install
|
6
|
+
|
7
|
+
gem install xxhash
|
8
|
+
|
9
|
+
### Usage
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
require 'xxhash'
|
13
|
+
|
14
|
+
text = "test"
|
15
|
+
seed = 12345
|
16
|
+
|
17
|
+
XXhash.xxh32(text, seed) # => 3834992036
|
18
|
+
```
|
19
|
+
|
20
|
+
## Contributing
|
21
|
+
|
22
|
+
1. Fork it
|
23
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
24
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
25
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
26
|
+
5. Create new Pull Request
|
27
|
+
|
28
|
+
### Copyright
|
29
|
+
|
30
|
+
Copyright (c) 2012 Vasiliy Ermolovich. See LICENSE.txt for
|
31
|
+
further details.
|
data/Rakefile
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
2
|
+
|
3
|
+
require 'rake/testtask'
|
4
|
+
require 'rake/clean'
|
5
|
+
|
6
|
+
Rake::TestTask.new do |t|
|
7
|
+
t.libs << 'test'
|
8
|
+
t.pattern = 'test/*_test.rb'
|
9
|
+
t.verbose = true
|
10
|
+
end
|
11
|
+
|
12
|
+
desc "Run tests"
|
13
|
+
task :default => :test
|
14
|
+
|
15
|
+
require 'rake/extensiontask'
|
16
|
+
Rake::ExtensionTask.new('xxhash') do |ext|
|
17
|
+
ext.lib_dir = 'lib/xxhash'
|
18
|
+
end
|
19
|
+
|
20
|
+
Rake::Task[:test].prerequisites << :compile
|
@@ -0,0 +1,342 @@
|
|
1
|
+
/*
|
2
|
+
xxHash - Fast Hash algorithm
|
3
|
+
Copyright (C) 2012, Yann Collet.
|
4
|
+
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
5
|
+
|
6
|
+
Redistribution and use in source and binary forms, with or without
|
7
|
+
modification, are permitted provided that the following conditions are
|
8
|
+
met:
|
9
|
+
|
10
|
+
* Redistributions of source code must retain the above copyright
|
11
|
+
notice, this list of conditions and the following disclaimer.
|
12
|
+
* Redistributions in binary form must reproduce the above
|
13
|
+
copyright notice, this list of conditions and the following disclaimer
|
14
|
+
in the documentation and/or other materials provided with the
|
15
|
+
distribution.
|
16
|
+
|
17
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
18
|
+
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
19
|
+
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
20
|
+
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
21
|
+
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
22
|
+
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
23
|
+
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
24
|
+
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
25
|
+
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
26
|
+
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
27
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
28
|
+
|
29
|
+
You can contact the author at :
|
30
|
+
- xxHash source repository : http://code.google.com/p/xxhash/
|
31
|
+
*/
|
32
|
+
|
33
|
+
|
34
|
+
|
35
|
+
//**************************************
|
36
|
+
// Tuning parameters
|
37
|
+
//**************************************
|
38
|
+
// FORCE_NATIVE_FORMAT :
|
39
|
+
// By default, xxHash library provides endian-independant Hash values.
|
40
|
+
// Results are therefore identical for big-endian and little-endian CPU.
|
41
|
+
// This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
|
42
|
+
// Should endian-independance be of no importance to your application, you may uncomment the #define below
|
43
|
+
// It will improve speed for Big-endian CPU.
|
44
|
+
// This option has no impact on Little_Endian CPU.
|
45
|
+
//#define FORCE_NATIVE_FORMAT 1
|
46
|
+
|
47
|
+
|
48
|
+
|
49
|
+
//**************************************
|
50
|
+
// Includes
|
51
|
+
//**************************************
|
52
|
+
#include <stdlib.h> // for malloc(), free()
|
53
|
+
#include <string.h> // for memcpy()
|
54
|
+
#include "libxxhash.h"
|
55
|
+
|
56
|
+
|
57
|
+
|
58
|
+
//**************************************
|
59
|
+
// CPU Feature Detection
|
60
|
+
//**************************************
|
61
|
+
// Little Endian or Big Endian ?
|
62
|
+
// You can overwrite the #define below if you know your architecture endianess
|
63
|
+
#if defined(FORCE_NATIVE_FORMAT) && (FORCE_NATIVE_FORMAT==1)
|
64
|
+
// Force native format. The result will be endian dependant.
|
65
|
+
# define XXH_BIG_ENDIAN 0
|
66
|
+
#elif defined (__GLIBC__)
|
67
|
+
# include <endian.h>
|
68
|
+
# if (__BYTE_ORDER == __BIG_ENDIAN)
|
69
|
+
# define XXH_BIG_ENDIAN 1
|
70
|
+
# endif
|
71
|
+
#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))
|
72
|
+
# define XXH_BIG_ENDIAN 1
|
73
|
+
#elif defined(__sparc) || defined(__sparc__) \
|
74
|
+
|| defined(__ppc__) || defined(_POWER) || defined(__powerpc__) || defined(_ARCH_PPC) || defined(__PPC__) || defined(__PPC) || defined(PPC) || defined(__powerpc__) || defined(__powerpc) || defined(powerpc) \
|
75
|
+
|| defined(__hpux) || defined(__hppa) \
|
76
|
+
|| defined(_MIPSEB) || defined(__s390__)
|
77
|
+
# define XXH_BIG_ENDIAN 1
|
78
|
+
#endif
|
79
|
+
|
80
|
+
#if !defined(XXH_BIG_ENDIAN)
|
81
|
+
// Little Endian assumed. PDP Endian and other very rare endian format are unsupported.
|
82
|
+
# define XXH_BIG_ENDIAN 0
|
83
|
+
#endif
|
84
|
+
|
85
|
+
|
86
|
+
|
87
|
+
//**************************************
|
88
|
+
// Compiler-specific Options & Functions
|
89
|
+
//**************************************
|
90
|
+
#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
|
91
|
+
|
92
|
+
// Note : under GCC, it may sometimes be faster to enable the (2nd) macro definition, instead of using win32 intrinsic
|
93
|
+
#if defined(_WIN32)
|
94
|
+
# define XXH_rotl32(x,r) _rotl(x,r)
|
95
|
+
#else
|
96
|
+
# define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
|
97
|
+
#endif
|
98
|
+
|
99
|
+
#if defined(_MSC_VER) // Visual Studio
|
100
|
+
# define XXH_swap32 _byteswap_ulong
|
101
|
+
#elif GCC_VERSION >= 403
|
102
|
+
# define XXH_swap32 __builtin_bswap32
|
103
|
+
#else
|
104
|
+
static inline unsigned int XXH_swap32 (unsigned int x) {
|
105
|
+
return ((x << 24) & 0xff000000 ) |
|
106
|
+
((x << 8) & 0x00ff0000 ) |
|
107
|
+
((x >> 8) & 0x0000ff00 ) |
|
108
|
+
((x >> 24) & 0x000000ff );
|
109
|
+
}
|
110
|
+
#endif
|
111
|
+
|
112
|
+
|
113
|
+
|
114
|
+
//**************************************
|
115
|
+
// Constants
|
116
|
+
//**************************************
|
117
|
+
#define PRIME32_1 2654435761U
|
118
|
+
#define PRIME32_2 2246822519U
|
119
|
+
#define PRIME32_3 3266489917U
|
120
|
+
#define PRIME32_4 668265263U
|
121
|
+
#define PRIME32_5 374761393U
|
122
|
+
|
123
|
+
|
124
|
+
|
125
|
+
//**************************************
|
126
|
+
// Macros
|
127
|
+
//**************************************
|
128
|
+
#define XXH_LE32(p) (XXH_BIG_ENDIAN ? XXH_swap32(*(unsigned int*)(p)) : *(unsigned int*)(p))
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
//****************************
|
133
|
+
// Simple Hash Functions
|
134
|
+
//****************************
|
135
|
+
|
136
|
+
unsigned int XXH32(const void* input, int len, unsigned int seed)
|
137
|
+
{
|
138
|
+
#if 0
|
139
|
+
// Simple version, good for code maintenance, but unfortunately slow for small inputs
|
140
|
+
void* state = XXH32_init(seed);
|
141
|
+
XXH32_feed(state, input, len);
|
142
|
+
return XXH32_result(state);
|
143
|
+
#else
|
144
|
+
|
145
|
+
const unsigned char* p = (const unsigned char*)input;
|
146
|
+
const unsigned char* const bEnd = p + len;
|
147
|
+
unsigned int h32;
|
148
|
+
|
149
|
+
if (len>=16)
|
150
|
+
{
|
151
|
+
const unsigned char* const limit = bEnd - 16;
|
152
|
+
unsigned int v1 = seed + PRIME32_1 + PRIME32_2;
|
153
|
+
unsigned int v2 = seed + PRIME32_2;
|
154
|
+
unsigned int v3 = seed + 0;
|
155
|
+
unsigned int v4 = seed - PRIME32_1;
|
156
|
+
|
157
|
+
do
|
158
|
+
{
|
159
|
+
v1 += XXH_LE32(p) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
|
160
|
+
v2 += XXH_LE32(p) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
|
161
|
+
v3 += XXH_LE32(p) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
|
162
|
+
v4 += XXH_LE32(p) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
|
163
|
+
} while (p<=limit) ;
|
164
|
+
|
165
|
+
h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
|
166
|
+
}
|
167
|
+
else
|
168
|
+
{
|
169
|
+
h32 = seed + PRIME32_5;
|
170
|
+
}
|
171
|
+
|
172
|
+
h32 += (unsigned int) len;
|
173
|
+
|
174
|
+
while (p<=bEnd-4)
|
175
|
+
{
|
176
|
+
h32 += XXH_LE32(p) * PRIME32_3;
|
177
|
+
h32 = XXH_rotl32(h32, 17) * PRIME32_4 ;
|
178
|
+
p+=4;
|
179
|
+
}
|
180
|
+
|
181
|
+
while (p<bEnd)
|
182
|
+
{
|
183
|
+
h32 += (*p) * PRIME32_5;
|
184
|
+
h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
|
185
|
+
p++;
|
186
|
+
}
|
187
|
+
|
188
|
+
h32 ^= h32 >> 15;
|
189
|
+
h32 *= PRIME32_2;
|
190
|
+
h32 ^= h32 >> 13;
|
191
|
+
h32 *= PRIME32_3;
|
192
|
+
h32 ^= h32 >> 16;
|
193
|
+
|
194
|
+
return h32;
|
195
|
+
|
196
|
+
#endif
|
197
|
+
}
|
198
|
+
|
199
|
+
|
200
|
+
//****************************
|
201
|
+
// Advanced Hash Functions
|
202
|
+
//****************************
|
203
|
+
|
204
|
+
struct XXH_state32_t
|
205
|
+
{
|
206
|
+
unsigned int seed;
|
207
|
+
unsigned int v1;
|
208
|
+
unsigned int v2;
|
209
|
+
unsigned int v3;
|
210
|
+
unsigned int v4;
|
211
|
+
unsigned long long total_len;
|
212
|
+
char memory[16];
|
213
|
+
int memsize;
|
214
|
+
};
|
215
|
+
|
216
|
+
|
217
|
+
void* XXH32_init (unsigned int seed)
|
218
|
+
{
|
219
|
+
struct XXH_state32_t * state = (struct XXH_state32_t *) malloc ( sizeof(struct XXH_state32_t));
|
220
|
+
state->seed = seed;
|
221
|
+
state->v1 = seed + PRIME32_1 + PRIME32_2;
|
222
|
+
state->v2 = seed + PRIME32_2;
|
223
|
+
state->v3 = seed + 0;
|
224
|
+
state->v4 = seed - PRIME32_1;
|
225
|
+
state->total_len = 0;
|
226
|
+
state->memsize = 0;
|
227
|
+
|
228
|
+
return (void*)state;
|
229
|
+
}
|
230
|
+
|
231
|
+
|
232
|
+
int XXH32_feed (void* state_in, const void* input, int len)
|
233
|
+
{
|
234
|
+
struct XXH_state32_t * state = state_in;
|
235
|
+
const unsigned char* p = (const unsigned char*)input;
|
236
|
+
const unsigned char* const bEnd = p + len;
|
237
|
+
|
238
|
+
state->total_len += len;
|
239
|
+
|
240
|
+
if (state->memsize + len < 16) // fill in tmp buffer
|
241
|
+
{
|
242
|
+
memcpy(state->memory + state->memsize, input, len);
|
243
|
+
state->memsize += len;
|
244
|
+
return 0;
|
245
|
+
}
|
246
|
+
|
247
|
+
if (state->memsize) // some data left from previous feed
|
248
|
+
{
|
249
|
+
memcpy(state->memory + state->memsize, input, 16-state->memsize);
|
250
|
+
{
|
251
|
+
const unsigned int* p32 = (const unsigned int*)state->memory;
|
252
|
+
state->v1 += XXH_LE32(p32) * PRIME32_2; state->v1 = XXH_rotl32(state->v1, 13); state->v1 *= PRIME32_1; p32++;
|
253
|
+
state->v2 += XXH_LE32(p32) * PRIME32_2; state->v2 = XXH_rotl32(state->v2, 13); state->v2 *= PRIME32_1; p32++;
|
254
|
+
state->v3 += XXH_LE32(p32) * PRIME32_2; state->v3 = XXH_rotl32(state->v3, 13); state->v3 *= PRIME32_1; p32++;
|
255
|
+
state->v4 += XXH_LE32(p32) * PRIME32_2; state->v4 = XXH_rotl32(state->v4, 13); state->v4 *= PRIME32_1; p32++;
|
256
|
+
}
|
257
|
+
p += 16-state->memsize;
|
258
|
+
state->memsize = 0;
|
259
|
+
}
|
260
|
+
|
261
|
+
{
|
262
|
+
const unsigned char* const limit = bEnd - 16;
|
263
|
+
unsigned int v1 = state->v1;
|
264
|
+
unsigned int v2 = state->v2;
|
265
|
+
unsigned int v3 = state->v3;
|
266
|
+
unsigned int v4 = state->v4;
|
267
|
+
|
268
|
+
while (p<=limit)
|
269
|
+
{
|
270
|
+
v1 += XXH_LE32(p) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
|
271
|
+
v2 += XXH_LE32(p) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
|
272
|
+
v3 += XXH_LE32(p) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
|
273
|
+
v4 += XXH_LE32(p) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
|
274
|
+
}
|
275
|
+
|
276
|
+
state->v1 = v1;
|
277
|
+
state->v2 = v2;
|
278
|
+
state->v3 = v3;
|
279
|
+
state->v4 = v4;
|
280
|
+
}
|
281
|
+
|
282
|
+
if (p < bEnd)
|
283
|
+
{
|
284
|
+
memcpy(state->memory, p, bEnd-p);
|
285
|
+
state->memsize = bEnd-p;
|
286
|
+
}
|
287
|
+
|
288
|
+
return 0;
|
289
|
+
}
|
290
|
+
|
291
|
+
|
292
|
+
unsigned int XXH32_getIntermediateResult (void* state_in)
|
293
|
+
{
|
294
|
+
struct XXH_state32_t * state = state_in;
|
295
|
+
unsigned char * p = (unsigned char*)state->memory;
|
296
|
+
unsigned char* bEnd = (unsigned char*)state->memory + state->memsize;
|
297
|
+
unsigned int h32;
|
298
|
+
|
299
|
+
|
300
|
+
if (state->total_len >= 16)
|
301
|
+
{
|
302
|
+
h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
|
303
|
+
}
|
304
|
+
else
|
305
|
+
{
|
306
|
+
h32 = state->seed + PRIME32_5;
|
307
|
+
}
|
308
|
+
|
309
|
+
h32 += (unsigned int) state->total_len;
|
310
|
+
|
311
|
+
while (p<=bEnd-4)
|
312
|
+
{
|
313
|
+
h32 += XXH_LE32(p) * PRIME32_3;
|
314
|
+
h32 = XXH_rotl32(h32, 17) * PRIME32_4 ;
|
315
|
+
p+=4;
|
316
|
+
}
|
317
|
+
|
318
|
+
while (p<bEnd)
|
319
|
+
{
|
320
|
+
h32 += (*p) * PRIME32_5;
|
321
|
+
h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
|
322
|
+
p++;
|
323
|
+
}
|
324
|
+
|
325
|
+
h32 ^= h32 >> 15;
|
326
|
+
h32 *= PRIME32_2;
|
327
|
+
h32 ^= h32 >> 13;
|
328
|
+
h32 *= PRIME32_3;
|
329
|
+
h32 ^= h32 >> 16;
|
330
|
+
|
331
|
+
return h32;
|
332
|
+
}
|
333
|
+
|
334
|
+
|
335
|
+
unsigned int XXH32_result (void* state_in)
|
336
|
+
{
|
337
|
+
unsigned int h32 = XXH32_getIntermediateResult(state_in);
|
338
|
+
|
339
|
+
free(state_in);
|
340
|
+
|
341
|
+
return h32;
|
342
|
+
}
|
@@ -0,0 +1,128 @@
|
|
1
|
+
/*
|
2
|
+
xxHash - Fast Hash algorithm
|
3
|
+
Header File
|
4
|
+
Copyright (C) 2012, Yann Collet.
|
5
|
+
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
6
|
+
|
7
|
+
Redistribution and use in source and binary forms, with or without
|
8
|
+
modification, are permitted provided that the following conditions are
|
9
|
+
met:
|
10
|
+
|
11
|
+
* Redistributions of source code must retain the above copyright
|
12
|
+
notice, this list of conditions and the following disclaimer.
|
13
|
+
* Redistributions in binary form must reproduce the above
|
14
|
+
copyright notice, this list of conditions and the following disclaimer
|
15
|
+
in the documentation and/or other materials provided with the
|
16
|
+
distribution.
|
17
|
+
|
18
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
19
|
+
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
20
|
+
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
21
|
+
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
22
|
+
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
23
|
+
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
24
|
+
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
25
|
+
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
26
|
+
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
27
|
+
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
28
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
29
|
+
|
30
|
+
You can contact the author at :
|
31
|
+
- xxHash source repository : http://code.google.com/p/xxhash/
|
32
|
+
*/
|
33
|
+
|
34
|
+
/* Notice extracted from xxHash homepage :
|
35
|
+
|
36
|
+
xxHash is an extremely fast Hash algorithm, running at RAM speed limits.
|
37
|
+
It also successfully passes all tests from the SMHasher suite.
|
38
|
+
|
39
|
+
Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 Duo @3GHz)
|
40
|
+
|
41
|
+
Name Speed Q.Score Author
|
42
|
+
xxHash 5.4 GB/s 10
|
43
|
+
CrapWow 3.2 GB/s 2 Andrew
|
44
|
+
MumurHash 3a 2.7 GB/s 10 Austin Appleby
|
45
|
+
SpookyHash 2.0 GB/s 10 Bob Jenkins
|
46
|
+
SBox 1.4 GB/s 9 Bret Mulvey
|
47
|
+
Lookup3 1.2 GB/s 9 Bob Jenkins
|
48
|
+
SuperFastHash 1.2 GB/s 1 Paul Hsieh
|
49
|
+
CityHash64 1.05 GB/s 10 Pike & Alakuijala
|
50
|
+
FNV 0.55 GB/s 5 Fowler, Noll, Vo
|
51
|
+
CRC32 0.43 GB/s 9
|
52
|
+
MD5-32 0.33 GB/s 10 Ronald L. Rivest
|
53
|
+
SHA1-32 0.28 GB/s 10
|
54
|
+
|
55
|
+
Q.Score is a measure of quality of the hash function.
|
56
|
+
It depends on successfully passing SMHasher test set.
|
57
|
+
10 is a perfect score.
|
58
|
+
*/
|
59
|
+
|
60
|
+
#pragma once
|
61
|
+
|
62
|
+
#if defined (__cplusplus)
|
63
|
+
extern "C" {
|
64
|
+
#endif
|
65
|
+
|
66
|
+
|
67
|
+
//****************************
|
68
|
+
// Simple Hash Functions
|
69
|
+
//****************************
|
70
|
+
|
71
|
+
unsigned int XXH32 (const void* input, int len, unsigned int seed);
|
72
|
+
|
73
|
+
/*
|
74
|
+
XXH32() :
|
75
|
+
Calculate the 32-bits hash of "input", of length "len"
|
76
|
+
"seed" can be used to alter the result
|
77
|
+
This function successfully passes all SMHasher tests.
|
78
|
+
Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s
|
79
|
+
Note that "len" is type "int", which means it is limited to 2^31-1.
|
80
|
+
If your data is larger, use the advanced functions below.
|
81
|
+
*/
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
//****************************
|
86
|
+
// Advanced Hash Functions
|
87
|
+
//****************************
|
88
|
+
|
89
|
+
void* XXH32_init (unsigned int seed);
|
90
|
+
int XXH32_feed (void* state, const void* input, int len);
|
91
|
+
unsigned int XXH32_result (void* state);
|
92
|
+
|
93
|
+
/*
|
94
|
+
These functions calculate the xxhash of an input provided in several small packets,
|
95
|
+
as opposed to an input provided as a single block.
|
96
|
+
|
97
|
+
You must start with :
|
98
|
+
void* XXH32_init()
|
99
|
+
The function returns a pointer which holds the state of calculation.
|
100
|
+
|
101
|
+
This pointer must be provided as "void* state" parameter for XXH32_feed().
|
102
|
+
XXH32_feed() can be called as many times as necessary.
|
103
|
+
The function returns an error code, with 0 meaning OK, and all other values meaning there is an error.
|
104
|
+
Note that "len" is type "int", which means it is limited to 2^31-1.
|
105
|
+
If your data is larger, it is recommended
|
106
|
+
to chunk your data into blocks of size 2^30 (1GB) to avoid any "int" overflow issue.
|
107
|
+
|
108
|
+
Finally, you can end the calculation anytime, by using XXH32_result().
|
109
|
+
This function returns the final 32-bits hash.
|
110
|
+
You must provide the same "void* state" parameter created by XXH32_init().
|
111
|
+
|
112
|
+
Memory will be freed by XXH32_result().
|
113
|
+
*/
|
114
|
+
|
115
|
+
|
116
|
+
unsigned int XXH32_getIntermediateResult (void* state);
|
117
|
+
/*
|
118
|
+
This function does the same as XXH32_result(), generating a 32-bit hash,
|
119
|
+
but preserve memory context.
|
120
|
+
This way, it becomes possible to generate intermediate hashes, and then continue feeding data with XXH32_feed().
|
121
|
+
To free memory context, use XXH32_result().
|
122
|
+
*/
|
123
|
+
|
124
|
+
|
125
|
+
|
126
|
+
#if defined (__cplusplus)
|
127
|
+
}
|
128
|
+
#endif
|
@@ -0,0 +1,19 @@
|
|
1
|
+
#include <ruby.h>
|
2
|
+
#include "libxxhash.h"
|
3
|
+
|
4
|
+
// Use this typedef to make the compiler happy when
|
5
|
+
// calling rb_define_method()
|
6
|
+
typedef VALUE (ruby_method)(...);
|
7
|
+
|
8
|
+
extern "C" VALUE xxhash_xxh32(VALUE mod, VALUE input, VALUE seed)
|
9
|
+
{
|
10
|
+
return ULL2NUM(XXH32(StringValuePtr(input), RSTRING_LEN(input), NUM2ULL(seed)));
|
11
|
+
}
|
12
|
+
|
13
|
+
extern "C" void Init_xxhash()
|
14
|
+
{
|
15
|
+
VALUE mXXhash = rb_define_module("XXhash");
|
16
|
+
VALUE mInternal = rb_define_module_under(mXXhash, "Internal");
|
17
|
+
|
18
|
+
rb_define_singleton_method(mInternal, "xxh32", (ruby_method*) &xxhash_xxh32, 2);
|
19
|
+
}
|
data/lib/xxhash.rb
ADDED
data/test/test_helper.rb
ADDED
data/test/xxhash_test.rb
ADDED
data/xxhash.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'xxhash/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "xxhash"
|
8
|
+
gem.version = XXhash::VERSION
|
9
|
+
gem.authors = ["Vasiliy Ermolovich"]
|
10
|
+
gem.email = ["younash@gmail.com"]
|
11
|
+
gem.description = %q{Ruby wrapper for xxHash lib}
|
12
|
+
gem.summary = %q{Ruby wrapper for xxHash lib}
|
13
|
+
gem.homepage = "http://github.com/nashby/xxhash"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.extensions = ["ext/xxhash/extconf.rb"]
|
20
|
+
end
|
metadata
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: xxhash
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Vasiliy Ermolovich
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-12-23 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: Ruby wrapper for xxHash lib
|
15
|
+
email:
|
16
|
+
- younash@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions:
|
19
|
+
- ext/xxhash/extconf.rb
|
20
|
+
extra_rdoc_files: []
|
21
|
+
files:
|
22
|
+
- .gitignore
|
23
|
+
- Gemfile
|
24
|
+
- LICENSE.txt
|
25
|
+
- README.md
|
26
|
+
- Rakefile
|
27
|
+
- ext/xxhash/extconf.rb
|
28
|
+
- ext/xxhash/libxxhash.c
|
29
|
+
- ext/xxhash/libxxhash.h
|
30
|
+
- ext/xxhash/xxhash.cc
|
31
|
+
- lib/xxhash.rb
|
32
|
+
- lib/xxhash/version.rb
|
33
|
+
- test/test_helper.rb
|
34
|
+
- test/xxhash_test.rb
|
35
|
+
- xxhash.gemspec
|
36
|
+
homepage: http://github.com/nashby/xxhash
|
37
|
+
licenses: []
|
38
|
+
post_install_message:
|
39
|
+
rdoc_options: []
|
40
|
+
require_paths:
|
41
|
+
- lib
|
42
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
segments:
|
49
|
+
- 0
|
50
|
+
hash: -2742825382786216064
|
51
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
segments:
|
58
|
+
- 0
|
59
|
+
hash: -2742825382786216064
|
60
|
+
requirements: []
|
61
|
+
rubyforge_project:
|
62
|
+
rubygems_version: 1.8.24
|
63
|
+
signing_key:
|
64
|
+
specification_version: 3
|
65
|
+
summary: Ruby wrapper for xxHash lib
|
66
|
+
test_files:
|
67
|
+
- test/test_helper.rb
|
68
|
+
- test/xxhash_test.rb
|