Adler-32校验算法

Adler-32校验算法

Adler-32是Mark Adler发明的校验和算法，和32位CRC校验算法一样，都是保护数据防止意外更改的算法，但是这个算法较容易被伪造，所以是不安全的保护措施。但是比CRC好点的是，它计算的很快。这个算法那是从Fletcher校验和算法中修改过来的，原始的算法形式略快，但是可依赖性并不高。

Adler-32的一种滚动哈希版本被用在了rsync工具中

Adler-32通过求解两个16位的数值A、B实现，并将结果连结成一个32位整数.

A就是字符串中每个字节的和，而B是A在相加时每一步的阶段值之和。在Adler-32开始运行时，A初始化为1，B初始化为0，最后的校验和要模上65521(继216之后的最小素数)。

A = 1 + D1 + D2 + ... + Dn (mod 65521)
B = (1 + D1) + (1 + D1 + D2) + ... + (1 + D1 + D2 + ... + Dn) (mod 65521)
   = n×D1 + (n-1)×D2 + (n-2)×D3 + ... + Dn + n (mod 65521)
Adler-32(D) = B × 65536 + A
其中D为字符串的字节，n是D的字节长度

下面举例使用Adler-32校验算法产生字符串"Wikipedia"的校验和：

ASCII code          A                   B
   W: 87           1 +  87 =  88        0 +  88 =   88
   i: 105         88 + 105 = 193       88 + 193 =  281
   k: 107        193 + 107 = 300      281 + 300 =  581
   i: 105        300 + 105 = 405      581 + 405 =  986
   p: 112        405 + 112 = 517      986 + 517 = 1503
   e: 101        517 + 101 = 618     1503 + 618 = 2121
   d: 100        618 + 100 = 718     2121 + 718 = 2839
   i: 105        718 + 105 = 823     2839 + 823 = 3662
   a: 97         823 +  97 = 920     3662 + 920 = 4582
   A = 920  =  398 hex
   B = 4582 = 11E6 hex
   Output: 11E60398 hex
都默默的进行过了模65521操作了

例子(一个不高效，但是很直接的实现):

const int MOD_ADLER = 65521;

uint32_t adler32(unsigned char *data, int32_t len) /* where data is the location of the data in physical memory and
                                                       len is the length of the data in bytes */
{
    uint32_t a = 1, b = 0;
    int32_t index;

    /* Process each byte of the data in order */
    for (index = 0; index < len; ++index)
    {
        a = (a + data[index]) % MOD_ADLER;
        b = (b + a) % MOD_ADLER;
    }

    return (b << 16) | a;
}

Advantages and disadvantages[edit]Like the standard CRC-32, the Adler-32 checksum can be forged easily and is therefore unsafe for protecting against intentional modification.It's faster than CRC-32 on many platforms.Adler-32 has a weakness for short messages with few hundred bytes, because the checksums for these messages have a poor coverage of the 32 available bits.

Date: 2014-10-27T20:58+0800

Author: kirchhoff

Org version 7.9.3f with Emacs version 24

Validate XHTML 1.0

c++实现:

#pragma once

#ifndef _ADLER32_H_
#define _ADLER32_H_


unsigned int Adler32(const unsigned char *buf, unsigned int len);


#endif //!_ADLER32_H_

#include "stdafx.h"
#include "Adler32.h"

/* adler32.c -- compute the Adler-32 checksum of a data stream
* Copyright (C) 1995-2007 Mark Adler
* For conditions of distribution and use, see copyright notice in zlib.h
*/

/* @(#) $Id$ */

static const unsigned long BASE = 65521;	/* largest prime smaller than 65536 */
static const unsigned int NMAX = 5552;
/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */

#define DO1(buf,i)  {adler += (buf)[i]; sum2 += adler;}
#define DO2(buf,i)  DO1(buf,i); DO1(buf,i+1);
#define DO4(buf,i)  DO2(buf,i); DO2(buf,i+2);
#define DO8(buf,i)  DO4(buf,i); DO4(buf,i+4);
#define DO16(buf)   DO8(buf,0); DO8(buf,8);

/* use NO_DIVIDE if your processor does not do division in hardware */
#ifdef NO_DIVIDE
#  define MOD(a) \
    do { \
        if (a >= (BASE << 16)) a -= (BASE << 16); \
        if (a >= (BASE << 15)) a -= (BASE << 15); \
        if (a >= (BASE << 14)) a -= (BASE << 14); \
        if (a >= (BASE << 13)) a -= (BASE << 13); \
        if (a >= (BASE << 12)) a -= (BASE << 12); \
        if (a >= (BASE << 11)) a -= (BASE << 11); \
        if (a >= (BASE << 10)) a -= (BASE << 10); \
        if (a >= (BASE << 9)) a -= (BASE << 9); \
        if (a >= (BASE << 8)) a -= (BASE << 8); \
        if (a >= (BASE << 7)) a -= (BASE << 7); \
        if (a >= (BASE << 6)) a -= (BASE << 6); \
        if (a >= (BASE << 5)) a -= (BASE << 5); \
        if (a >= (BASE << 4)) a -= (BASE << 4); \
        if (a >= (BASE << 3)) a -= (BASE << 3); \
        if (a >= (BASE << 2)) a -= (BASE << 2); \
        if (a >= (BASE << 1)) a -= (BASE << 1); \
        if (a >= BASE) a -= BASE; \
    } while (0)
#  define MOD4(a) \
    do { \
        if (a >= (BASE << 4)) a -= (BASE << 4); \
        if (a >= (BASE << 3)) a -= (BASE << 3); \
        if (a >= (BASE << 2)) a -= (BASE << 2); \
        if (a >= (BASE << 1)) a -= (BASE << 1); \
        if (a >= BASE) a -= BASE; \
    } while (0)
#else
#  define MOD(a) (a %= BASE)
#  define MOD4(a) (a %= BASE)
#endif

/* ========================================================================= */
unsigned int Adler32(const unsigned char *buf, unsigned int len)
{
	unsigned long adler = 1;
	unsigned long sum2 = 0;
	unsigned int n;

	/* initial Adler-32 value (deferred check for len == 1 speed) */
	if (NULL == buf)
		return adler;

	/* in case user likes doing a byte at a time, keep it fast */
	if (len == 1) {
		adler += buf[0];
		if (adler >= BASE)
			adler -= BASE;
		sum2 += adler;
		if (sum2 >= BASE)
			sum2 -= BASE;
		return adler | (sum2 << 16);
	}

	/* in case short lengths are provided, keep it somewhat fast */
	if (len < 16) {
		while (len--) {
			adler += *buf++;
			sum2 += adler;
		}
		if (adler >= BASE)
			adler -= BASE;
		MOD4(sum2);             /* only added so many BASE's */
		return adler | (sum2 << 16);
	}

	/* do length NMAX blocks -- requires just one modulo operation */
	while (len >= NMAX) {
		len -= NMAX;
		n = NMAX / 16;          /* NMAX is divisible by 16 */
		do {
			DO16(buf);          /* 16 sums unrolled */
			buf += 16;
		} while (--n);
		MOD(adler);
		MOD(sum2);
	}

	/* do remaining bytes (less than NMAX, still just one modulo) */
	if (len) {                  /* avoid modulos if none remaining */
		while (len >= 16) {
			len -= 16;
			DO16(buf);
			buf += 16;
		}
		while (len--) {
			adler += *buf++;
			sum2 += adler;
		}
		MOD(adler);
		MOD(sum2);
	}

	/* return recombined sums */
	return (unsigned int)(adler | (sum2 << 16));
}