搜尋引擎的那些事（32位MD5演算法）

【 聲明：著作權，歡迎轉載，請勿用於商業用途。  聯絡信箱：feixiaoxing @163.com】 

    對於學過密碼學的同學來說，md5演算法肯定不會很陌生。但是，對於我來說，md5是一個新的命題。那什麼是md5呢？md5就是對已有的資料進行加密處理。當然，它還有別的用處，什麼呢？比如說，可以驗證下載的軟體是否完整，可以驗證儲存的字串是否發生重名等等。我在這裡提到這個演算法，主要是為了後面一個目的，防止url重名使用的。整個演算法的內容其實比較複雜的，我們自己只要學會使用就可以了。這裡使用的就兩個檔案，一個是md5.h，另外一個是md5.c，標頭檔內容如下所示，

/* See md5.c for explanation and copyright information.  */#ifndef MD5_H#define MD5_H/* Unlike previous versions of this code, uint32 need not be exactly   32 bits, merely 32 bits or more.  Choosing a data type which is 32   bits instead of 64 is not important; speed is considerably more   important.  ANSI guarantees that "unsigned long" will be big enough,   and always using it seems to have few disadvantages.  */typedef unsigned long uint32;struct MD5Context {uint32 buf[4];uint32 bits[2];unsigned char in[64];};void MD5Init(struct MD5Context *context);void MD5Update(struct MD5Context *context, unsigned char const *buf, unsigned len);void MD5Final(unsigned char digest[16], struct MD5Context *context);void MD5Transform(uint32 buf[4], const unsigned char in[64]);/* * This is needed to make RSAREF happy on some MS-DOS compilers. */typedef struct MD5Context MD5_CTX;#endif /* !MD5_H */

    源檔案內容如下所示，

/* * This code implements the MD5 message-digest algorithm. * The algorithm is due to Ron Rivest.  This code was * written by Colin Plumb in 1993, no copyright is claimed. * This code is in the public domain; do with it what you wish. * * Equivalent code is available from RSA Data Security, Inc. * This code has been tested against that, and is equivalent, * except that you don't need to include two pages of legalese * with every copy. * * To compute the message digest of a chunk of bytes, declare an * MD5Context structure, pass it to MD5Init, call MD5Update as * needed on buffers full of bytes, and then call MD5Final, which * will fill a supplied 16-byte array with the digest. *//* This code was modified in 1997 by Jim Kingdon of Cyclic Software to   not require an integer type which is exactly 32 bits.  This work   draws on the changes for the same purpose by Tatu Ylonen   <ylo@cs.hut.fi> as part of SSH, but since I didn't actually use   that code, there is no copyright issue.  I hereby disclaim   copyright in any changes I have made; this code remains in the   public domain.  */#include <stdio.h>#include <memory.h>#include <string.h>#include <sys/types.h>#include "md5.h"/* Little-endian byte-swapping routines.  Note that these do not   depend on the size of datatypes such as uint32, nor do they require   us to detect the endianness of the machine we are running on.  It   is possible they should be macros for speed, but I would be   surprised if they were a performance bottleneck for MD5.  */static uint32getu32 (addr)     const unsigned char *addr;{return (((((unsigned long)addr[3] << 8) | addr[2]) << 8)| addr[1]) << 8 | addr[0];}static voidputu32 (data, addr)     uint32 data;     unsigned char *addr;{addr[0] = (unsigned char)data;addr[1] = (unsigned char)(data >> 8);addr[2] = (unsigned char)(data >> 16);addr[3] = (unsigned char)(data >> 24);}/* * Start MD5 accumulation.  Set bit count to 0 and buffer to mysterious * initialization constants. */voidMD5Init(ctx)     struct MD5Context *ctx;{ctx->buf[0] = 0x67452301;ctx->buf[1] = 0xefcdab89;ctx->buf[2] = 0x98badcfe;ctx->buf[3] = 0x10325476;ctx->bits[0] = 0;ctx->bits[1] = 0;}/* * Update context to reflect the concatenation of another buffer full * of bytes. */voidMD5Update(ctx, buf, len)     struct MD5Context *ctx;     unsigned char const *buf;     unsigned len;{uint32 t;/* Update bitcount */t = ctx->bits[0];if ((ctx->bits[0] = (t + ((uint32)len << 3)) & 0xffffffff) < t)ctx->bits[1]++;/* Carry from low to high */ctx->bits[1] += len >> 29;t = (t >> 3) & 0x3f;/* Bytes already in shsInfo->data *//* Handle any leading odd-sized chunks */if ( t ) {unsigned char *p = ctx->in + t;t = 64-t;if (len < t) {memcpy(p, buf, len);return;}memcpy(p, buf, t);MD5Transform(ctx->buf, ctx->in);buf += t;len -= t;}/* Process data in 64-byte chunks */while (len >= 64) {memcpy(ctx->in, buf, 64);MD5Transform(ctx->buf, ctx->in);buf += 64;len -= 64;}/* Handle any remaining bytes of data. */memcpy(ctx->in, buf, len);}/* * Final wrapup - pad to 64-byte boundary with the bit pattern  * 1 0* (64-bit count of bits processed, MSB-first) */voidMD5Final(digest, ctx)     unsigned char digest[16];     struct MD5Context *ctx;{unsigned count;unsigned char *p;/* Compute number of bytes mod 64 */count = (ctx->bits[0] >> 3) & 0x3F;/* Set the first char of padding to 0x80.  This is safe since there is   always at least one byte free */p = ctx->in + count;*p++ = 0x80;/* Bytes of padding needed to make 64 bytes */count = 64 - 1 - count;/* Pad out to 56 mod 64 */if (count < 8) {/* Two lots of padding:  Pad the first block to 64 bytes */memset(p, 0, count);MD5Transform(ctx->buf, ctx->in);/* Now fill the next block with 56 bytes */memset(ctx->in, 0, 56);} else {/* Pad block to 56 bytes */memset(p, 0, count-8);}/* Append length in bits and transform */putu32(ctx->bits[0], ctx->in + 56);putu32(ctx->bits[1], ctx->in + 60);MD5Transform(ctx->buf, ctx->in);putu32(ctx->buf[0], digest);putu32(ctx->buf[1], digest + 4);putu32(ctx->buf[2], digest + 8);putu32(ctx->buf[3], digest + 12);memset(ctx, 0, sizeof(ctx));/* In case it's sensitive */}#ifndef ASM_MD5/* The four core functions - F1 is optimized somewhat *//* #define F1(x, y, z) (x & y | ~x & z) */#define F1(x, y, z) (z ^ (x & (y ^ z)))#define F2(x, y, z) F1(z, x, y)#define F3(x, y, z) (x ^ y ^ z)#define F4(x, y, z) (y ^ (x | ~z))/* This is the central step in the MD5 algorithm. */#define MD5STEP(f, w, x, y, z, data, s) \( w += f(x, y, z) + data, w &= 0xffffffff, w = w<<s | w>>(32-s), w += x )/* * The core of the MD5 algorithm, this alters an existing MD5 hash to * reflect the addition of 16 longwords of new data.  MD5Update blocks * the data and converts bytes into longwords for this routine. */voidMD5Transform(buf, inraw)     uint32 buf[4];     const unsigned char inraw[64];{register uint32 a, b, c, d;uint32 in[16];int i;for (i = 0; i < 16; ++i)in[i] = getu32 (inraw + 4 * i);a = buf[0];b = buf[1];c = buf[2];d = buf[3];MD5STEP(F1, a, b, c, d, in[ 0]+0xd76aa478,  7);MD5STEP(F1, d, a, b, c, in[ 1]+0xe8c7b756, 12);MD5STEP(F1, c, d, a, b, in[ 2]+0x242070db, 17);MD5STEP(F1, b, c, d, a, in[ 3]+0xc1bdceee, 22);MD5STEP(F1, a, b, c, d, in[ 4]+0xf57c0faf,  7);MD5STEP(F1, d, a, b, c, in[ 5]+0x4787c62a, 12);MD5STEP(F1, c, d, a, b, in[ 6]+0xa8304613, 17);MD5STEP(F1, b, c, d, a, in[ 7]+0xfd469501, 22);MD5STEP(F1, a, b, c, d, in[ 8]+0x698098d8,  7);MD5STEP(F1, d, a, b, c, in[ 9]+0x8b44f7af, 12);MD5STEP(F1, c, d, a, b, in[10]+0xffff5bb1, 17);MD5STEP(F1, b, c, d, a, in[11]+0x895cd7be, 22);MD5STEP(F1, a, b, c, d, in[12]+0x6b901122,  7);MD5STEP(F1, d, a, b, c, in[13]+0xfd987193, 12);MD5STEP(F1, c, d, a, b, in[14]+0xa679438e, 17);MD5STEP(F1, b, c, d, a, in[15]+0x49b40821, 22);MD5STEP(F2, a, b, c, d, in[ 1]+0xf61e2562,  5);MD5STEP(F2, d, a, b, c, in[ 6]+0xc040b340,  9);MD5STEP(F2, c, d, a, b, in[11]+0x265e5a51, 14);MD5STEP(F2, b, c, d, a, in[ 0]+0xe9b6c7aa, 20);MD5STEP(F2, a, b, c, d, in[ 5]+0xd62f105d,  5);MD5STEP(F2, d, a, b, c, in[10]+0x02441453,  9);MD5STEP(F2, c, d, a, b, in[15]+0xd8a1e681, 14);MD5STEP(F2, b, c, d, a, in[ 4]+0xe7d3fbc8, 20);MD5STEP(F2, a, b, c, d, in[ 9]+0x21e1cde6,  5);MD5STEP(F2, d, a, b, c, in[14]+0xc33707d6,  9);MD5STEP(F2, c, d, a, b, in[ 3]+0xf4d50d87, 14);MD5STEP(F2, b, c, d, a, in[ 8]+0x455a14ed, 20);MD5STEP(F2, a, b, c, d, in[13]+0xa9e3e905,  5);MD5STEP(F2, d, a, b, c, in[ 2]+0xfcefa3f8,  9);MD5STEP(F2, c, d, a, b, in[ 7]+0x676f02d9, 14);MD5STEP(F2, b, c, d, a, in[12]+0x8d2a4c8a, 20);MD5STEP(F3, a, b, c, d, in[ 5]+0xfffa3942,  4);MD5STEP(F3, d, a, b, c, in[ 8]+0x8771f681, 11);MD5STEP(F3, c, d, a, b, in[11]+0x6d9d6122, 16);MD5STEP(F3, b, c, d, a, in[14]+0xfde5380c, 23);MD5STEP(F3, a, b, c, d, in[ 1]+0xa4beea44,  4);MD5STEP(F3, d, a, b, c, in[ 4]+0x4bdecfa9, 11);MD5STEP(F3, c, d, a, b, in[ 7]+0xf6bb4b60, 16);MD5STEP(F3, b, c, d, a, in[10]+0xbebfbc70, 23);MD5STEP(F3, a, b, c, d, in[13]+0x289b7ec6,  4);MD5STEP(F3, d, a, b, c, in[ 0]+0xeaa127fa, 11);MD5STEP(F3, c, d, a, b, in[ 3]+0xd4ef3085, 16);MD5STEP(F3, b, c, d, a, in[ 6]+0x04881d05, 23);MD5STEP(F3, a, b, c, d, in[ 9]+0xd9d4d039,  4);MD5STEP(F3, d, a, b, c, in[12]+0xe6db99e5, 11);MD5STEP(F3, c, d, a, b, in[15]+0x1fa27cf8, 16);MD5STEP(F3, b, c, d, a, in[ 2]+0xc4ac5665, 23);MD5STEP(F4, a, b, c, d, in[ 0]+0xf4292244,  6);MD5STEP(F4, d, a, b, c, in[ 7]+0x432aff97, 10);MD5STEP(F4, c, d, a, b, in[14]+0xab9423a7, 15);MD5STEP(F4, b, c, d, a, in[ 5]+0xfc93a039, 21);MD5STEP(F4, a, b, c, d, in[12]+0x655b59c3,  6);MD5STEP(F4, d, a, b, c, in[ 3]+0x8f0ccc92, 10);MD5STEP(F4, c, d, a, b, in[10]+0xffeff47d, 15);MD5STEP(F4, b, c, d, a, in[ 1]+0x85845dd1, 21);MD5STEP(F4, a, b, c, d, in[ 8]+0x6fa87e4f,  6);MD5STEP(F4, d, a, b, c, in[15]+0xfe2ce6e0, 10);MD5STEP(F4, c, d, a, b, in[ 6]+0xa3014314, 15);MD5STEP(F4, b, c, d, a, in[13]+0x4e0811a1, 21);MD5STEP(F4, a, b, c, d, in[ 4]+0xf7537e82,  6);MD5STEP(F4, d, a, b, c, in[11]+0xbd3af235, 10);MD5STEP(F4, c, d, a, b, in[ 2]+0x2ad7d2bb, 15);MD5STEP(F4, b, c, d, a, in[ 9]+0xeb86d391, 21);buf[0] += a;buf[1] += b;buf[2] += c;buf[3] += d;}#endif/* Simple test program.  Can use it to manually run the tests from   RFC1321 for example.  */intmain (int argc, char **argv){struct MD5Context context;unsigned char checksum[16];int i;if (argc < 2){fprintf (stderr, "usage: %s string-to-hash\n", argv[0]);exit (1);}printf ("MD5 (\"%s\") = ", argv[1]);MD5Init (&context);MD5Update (&context, argv[1], strlen (argv[1]));MD5Final (checksum, &context);for (i = 0; i < 16; i++){printf ("%02x", (unsigned int) checksum[i]);}printf ("\n");return 0;}

    整個程式使用也非常簡單，就是md5 + 加密字串。比如說md5  www.163.com，那麼加密得到的數字就是cc4e427b15d6ddd711b304a48f80bdbe。為了驗證我們的演算法是否正確，可以尋找一個md5線上加密網站，輸入加密的字串資料，看看產生的字元數字是不是這個。