summaryrefslogtreecommitdiffstats
path: root/xxhash.h
blob: c525e0b803203b5cbebbbe4ebdb83c679bad024d (plain)
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
/*

   xxHash - Fast Hash algorithm

   Header File

   Copyright (C) 2012-2013, Yann Collet.

   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)



   Redistribution and use in source and binary forms, with or without

   modification, are permitted provided that the following conditions are

   met:

  

       * Redistributions of source code must retain the above copyright

   notice, this list of conditions and the following disclaimer.

       * Redistributions in binary form must reproduce the above

   copyright notice, this list of conditions and the following disclaimer

   in the documentation and/or other materials provided with the

   distribution.

  

   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT

   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,

   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT

   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,

   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY

   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.



	You can contact the author at :

	- xxHash source repository : http://code.google.com/p/xxhash/

*/

/* Notice extracted from xxHash homepage :



xxHash is an extremely fast Hash algorithm, running at RAM speed limits.

It also successfully passes all tests from the SMHasher suite.



Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 Duo @3GHz)



Name            Speed       Q.Score   Author

xxHash          5.4 GB/s     10

CrapWow         3.2 GB/s      2       Andrew

MumurHash 3a    2.7 GB/s     10       Austin Appleby

SpookyHash      2.0 GB/s     10       Bob Jenkins

SBox            1.4 GB/s      9       Bret Mulvey

Lookup3         1.2 GB/s      9       Bob Jenkins

SuperFastHash   1.2 GB/s      1       Paul Hsieh

CityHash64      1.05 GB/s    10       Pike & Alakuijala

FNV             0.55 GB/s     5       Fowler, Noll, Vo

CRC32           0.43 GB/s     9

MD5-32          0.33 GB/s    10       Ronald L. Rivest

SHA1-32         0.28 GB/s    10



Q.Score is a measure of quality of the hash function. 

It depends on successfully passing SMHasher test set. 

10 is a perfect score.

*/

#pragma once


#if defined (__cplusplus)

extern "C" {
#endif



//****************************

// Type

//****************************

typedef enum { OK=0, XXH_ERROR } XXH_errorcode;



//****************************

// Simple Hash Functions

//****************************


unsigned int XXH32 (const void* input, int len, unsigned int seed);

/*

XXH32() :

	Calculate the 32-bits hash of sequence of length "len" stored at memory address "input".

    The memory between input & input+len must be valid (allocated and read-accessible).

	"seed" can be used to alter the result predictably.

	This function successfully passes all SMHasher tests.

	Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s

	Note that "len" is type "int", which means it is limited to 2^31-1.

	If your data is larger, use the advanced functions below.

*/



//****************************

// Advanced Hash Functions

//****************************


void*         XXH32_init   (unsigned int seed);
XXH_errorcode XXH32_update (void* state, const void* input, int len);
unsigned int  XXH32_digest (void* state);

/*

These functions calculate the xxhash of an input provided in several small packets,

as opposed to an input provided as a single block.



It must be started with :

void* XXH32_init()

The function returns a pointer which holds the state of calculation.



This pointer must be provided as "void* state" parameter for XXH32_update().

XXH32_update() can be called as many times as necessary.

The user must provide a valid (allocated) input.

The function returns an error code, with 0 meaning OK, and any other value meaning there is an error.

Note that "len" is type "int", which means it is limited to 2^31-1. 

If your data is larger, it is recommended to chunk your data into blocks 

of size for example 2^30 (1GB) to avoid any "int" overflow issue.



Finally, you can end the calculation anytime, by using XXH32_digest().

This function returns the final 32-bits hash.

You must provide the same "void* state" parameter created by XXH32_init().

Memory will be freed by XXH32_digest().

*/


unsigned int XXH32_intermediateDigest (void* state);
/*

This function does the same as XXH32_digest(), generating a 32-bit hash,

but preserve memory context.

This way, it becomes possible to generate intermediate hashes, and then continue feeding data with XXH32_update().

To free memory context, use XXH32_digest().

*/



//****************************

// Deprecated function names

//****************************

// The following translations are provided to ease code transition

// You are encouraged to no longer this function names

#define XXH32_feed   XXH32_update

#define XXH32_result XXH32_digest

#define XXH32_getIntermediateResult XXH32_intermediateDigest




#if defined (__cplusplus)

}
#endif