检测重复文件功能实现

      因为硬盘空间有限，最近硬盘快装满了，又发现不少文件是重复的，不想手动的一个一个去对比删除，于是写一个程序来做这件事情。时间不多，没有全部完成，但重要的计算比较重复的功能已经完成。

        思路：输入几个目标文件夹，检测到所有重复的文件结果。

文件重复的检测标准有几种方案：

1. MD5值一样，这样对于大量占空间的文件计算来说比较耗费时间，而且可能存在碰撞情况，可以再加上文件名相同可修改时间相同的条件，目前是以MD5值为键值来保存所有计算完的文件数据。

2. 可以使用文件的属性，包括文件名，文件大小，修改时间；这样的话，可以基本检测到重复文件，而且消耗时间应该比计算MD5要少，目前没有使用这种方式。

后续需要使用第二种方案与第一种对比，从时间和效果上做出数据对比。接着做一个界面方便操作，确认删除对应的重复文件。

以下代码仅指定一个文件夹计算所有文件的MD5值。

#include "stdafx.h"#include <stdio.h>#include <stdlib.h>#include <map>#include <list>#include <direct.h>#include <Shlwapi.h>#include <windows.h>#include "md5.h"typedef std::multimap<INT64,WIN32_FIND_DATA> map_type;typedef std::list<std::wstring> list_type;union union_MD5{INT64 i64_md5;unsigned char c_md5[16];};typedef struct MIX_WIN32_FIND_DATA{std::wstring fullpath;WIN32_FIND_DATA wfd;}MIX_WIN32_FIND_DATA;DWORD RecurseGetFileList(std::wstring &fullpath,map_type &map_data){DWORD count = 0;WIN32_FIND_DATA fd;HANDLE hFile = ::FindFirstFile(fullpath.c_str(),&fd);if ( INVALID_HANDLE_VALUE == hFile ){return 0;}do{if ( ( 0 != _tcscmp(fd.cFileName,_T(".")))&& ( 0 != _tcscmp(fd.cFileName,_T("..")) ) ){if ( fd.dwFileAttributes == INVALID_FILE_ATTRIBUTES ){return 0;}if ( FILE_ATTRIBUTE_DIRECTORY & fd.dwFileAttributes ){std::wstring newdir = fullpath.substr(0,fullpath.length()-2);newdir.append(_T("\\")).append(fd.cFileName).append(_T("\\*"));count += RecurseGetFileList(newdir,map_data);}else{union_MD5 uMd5;std::wstring filepath = fullpath.substr(0,fullpath.length()-2);filepath.append(_T("\\")).append(fd.cFileName);BOOL bRet = MD5File(filepath.c_str(), uMd5.c_md5);map_data.insert(std::make_pair(uMd5.i64_md5,fd));int lowpart = uMd5.i64_md5>>32;int highpart = uMd5.i64_md5&0xFFFFFFFF;_tprintf(_T("MD5:%04x %04x filepath: %s\n"),highpart,lowpart,filepath.c_str());count++;}}if (::FindNextFile(hFile,&fd) == FALSE){break;}}while(1);return count;}DWORD GetMultimapForDirList(list_type dirlist,map_type &out_map){DWORD count = 0;WIN32_FILE_ATTRIBUTE_DATA fad;list_type::iterator it = dirlist.begin();while (it!=dirlist.end()){count += RecurseGetFileList(*it,out_map);}return count;}int main(int argc,char ** argv){list_type find_list;map_type find_map;find_list.push_front(std::wstring(_T("D:\\SetupFiles\\*")));GetMultimapForDirList(find_list,find_map);getchar();return 0;}

附MD5算法文件：

作者是：Copyright (C) 2000 by Robert Hubley. 

#if !defined(_LGY_MD5_H)#define _LGY_MD5_H/* MD5 Class. */class MD5_CTX {public:MD5_CTX();virtual ~MD5_CTX();void MD5Update ( unsigned char *input, unsigned int inputLen);void MD5Final (unsigned char digest[16]);private:unsigned long int state[4];/* state (ABCD) */unsigned long int count[2];/* number of bits, modulo 2^64 (lsb first) */unsigned char buffer[64];                   /* input buffer */unsigned char PADDING[64];            /* What? */private:void MD5Init ();void MD5Transform (unsigned long int state[4], unsigned char block[64]);void MD5_memcpy (unsigned char* output, unsigned char* input,unsigned int len);void Encode (unsigned char *output, unsigned long int *input,unsigned int len);void Decode (unsigned long int *output, unsigned char *input, unsigned int len);void MD5_memset (unsigned char* output,int value,unsigned int len);};#define MD5_BLEN        16#define MD5_SLEN        32#define NULL_MD5           "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"#define MD5_ISNULL(MD5BIN) (memcmp((const void *)NULL_MD5,(const void *)MD5BIN,MD5_BLEN)==0)BOOL MD5Data(unsigned char *buff,unsigned int len, unsigned char digest[16]);BOOL MD5File(LPCTSTR lpszFileName, unsigned char digest[16], unsigned int * pFileLen=NULL);#endif

#include "stdafx.h"#include "md5.h"/* Constants for MD5Transform routine.*/#define S11 7#define S12 12#define S13 17#define S14 22#define S21 5#define S22 9#define S23 14#define S24 20#define S31 4#define S32 11#define S33 16#define S34 23#define S41 6#define S42 10#define S43 15#define S44 21/* F, G, H and I are basic MD5 functions.*/#define F(x, y, z) (((x) & (y)) | ((~x) & (z)))#define G(x, y, z) (((x) & (z)) | ((y) & (~z)))#define H(x, y, z) ((x) ^ (y) ^ (z))#define I(x, y, z) ((y) ^ ((x) | (~z)))/* ROTATE_LEFT rotates x left n bits.*/#define ROTATE_LEFT(x, n) (((x) << (n)) | ((x) >> (32-(n))))/* FF, GG, HH, and II transformations for rounds 1, 2, 3, and 4.Rotation is separate from addition to prevent recomputation.*/#define FF(a, b, c, d, x, s, ac) { \(a) += F ((b), (c), (d)) + (x) + (unsigned long int)(ac); \(a) = ROTATE_LEFT ((a), (s)); \(a) += (b); \}#define GG(a, b, c, d, x, s, ac) { \(a) += G ((b), (c), (d)) + (x) + (unsigned long int)(ac); \(a) = ROTATE_LEFT ((a), (s)); \(a) += (b); \}#define HH(a, b, c, d, x, s, ac) { \(a) += H ((b), (c), (d)) + (x) + (unsigned long int)(ac); \(a) = ROTATE_LEFT ((a), (s)); \(a) += (b); \}#define II(a, b, c, d, x, s, ac) { \(a) += I ((b), (c), (d)) + (x) + (unsigned long int)(ac); \(a) = ROTATE_LEFT ((a), (s)); \(a) += (b); \}/* MD5 initialization. Begins an MD5 operation, writing a new context.*/MD5_CTX::MD5_CTX(){MD5Init ();}MD5_CTX::~MD5_CTX(){}void MD5_CTX::MD5Init (){this->count[0] = this->count[1] = 0;/* Load magic initialization constants.*/this->state[0] = 0x67452301;this->state[1] = 0xefcdab89;this->state[2] = 0x98badcfe;this->state[3] = 0x10325476;/* Add by Liguangyi */MD5_memset(PADDING, 0, sizeof(PADDING));*PADDING=0x80;//PADDING = {//0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,//0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,//0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};}/* MD5 block update operation. Continues an MD5 message-digestoperation, processing another message block, and updating thecontext.*/void MD5_CTX::MD5Update (unsigned char *input,unsigned int inputLen){unsigned int i, index, partLen;/* Compute number of bytes mod 64 */index = (unsigned int)((this->count[0] >> 3) & 0x3F);/* Update number of bits */if ((this->count[0] += ((unsigned long int)inputLen << 3))< ((unsigned long int)inputLen << 3))this->count[1]++;this->count[1] += ((unsigned long int)inputLen >> 29);partLen = 64 - index;/* Transform as many times as possible.*/if (inputLen >= partLen) {MD5_memcpy((unsigned char*)&this->buffer[index], (unsigned char*)input, partLen);MD5Transform (this->state, this->buffer);for (i = partLen; i + 63 < inputLen; i += 64)MD5Transform (this->state, &input[i]);index = 0;}elsei = 0;/* Buffer remaining input */MD5_memcpy ((unsigned char*)&this->buffer[index], (unsigned char*)&input[i], inputLen-i);}/* MD5 finalization. Ends an MD5 message-digest operation, writing thethe message digest and zeroizing the context.*/void MD5_CTX::MD5Final (unsigned char digest[16]){unsigned char bits[8];unsigned int index, padLen;/* Save number of bits */Encode (bits, this->count, 8);/* Pad out to 56 mod 64.*/index = (unsigned int)((this->count[0] >> 3) & 0x3f);padLen = (index < 56) ? (56 - index) : (120 - index);MD5Update ( PADDING, padLen);/* Append length (before padding) */MD5Update (bits, 8);/* Store state in digest */Encode (digest, this->state, 16);/* Zeroize sensitive information.*/MD5_memset ((unsigned char*)this, 0, sizeof (*this));this->MD5Init();}/* MD5 basic transformation. Transforms state based on block.*/void MD5_CTX::MD5Transform (unsigned long int state[4], unsigned char block[64]){unsigned long int a = state[0], b = state[1], c = state[2], d = state[3], x[16];Decode (x, block, 64);/* Round 1 */FF (a, b, c, d, x[ 0], S11, 0xd76aa478); /* 1 */FF (d, a, b, c, x[ 1], S12, 0xe8c7b756); /* 2 */FF (c, d, a, b, x[ 2], S13, 0x242070db); /* 3 */FF (b, c, d, a, x[ 3], S14, 0xc1bdceee); /* 4 */FF (a, b, c, d, x[ 4], S11, 0xf57c0faf); /* 5 */FF (d, a, b, c, x[ 5], S12, 0x4787c62a); /* 6 */FF (c, d, a, b, x[ 6], S13, 0xa8304613); /* 7 */FF (b, c, d, a, x[ 7], S14, 0xfd469501); /* 8 */FF (a, b, c, d, x[ 8], S11, 0x698098d8); /* 9 */FF (d, a, b, c, x[ 9], S12, 0x8b44f7af); /* 10 */FF (c, d, a, b, x[10], S13, 0xffff5bb1); /* 11 */FF (b, c, d, a, x[11], S14, 0x895cd7be); /* 12 */FF (a, b, c, d, x[12], S11, 0x6b901122); /* 13 */FF (d, a, b, c, x[13], S12, 0xfd987193); /* 14 */FF (c, d, a, b, x[14], S13, 0xa679438e); /* 15 */FF (b, c, d, a, x[15], S14, 0x49b40821); /* 16 *//* Round 2 */GG (a, b, c, d, x[ 1], S21, 0xf61e2562); /* 17 */GG (d, a, b, c, x[ 6], S22, 0xc040b340); /* 18 */GG (c, d, a, b, x[11], S23, 0x265e5a51); /* 19 */GG (b, c, d, a, x[ 0], S24, 0xe9b6c7aa); /* 20 */GG (a, b, c, d, x[ 5], S21, 0xd62f105d); /* 21 */GG (d, a, b, c, x[10], S22,  0x2441453); /* 22 */GG (c, d, a, b, x[15], S23, 0xd8a1e681); /* 23 */GG (b, c, d, a, x[ 4], S24, 0xe7d3fbc8); /* 24 */GG (a, b, c, d, x[ 9], S21, 0x21e1cde6); /* 25 */GG (d, a, b, c, x[14], S22, 0xc33707d6); /* 26 */GG (c, d, a, b, x[ 3], S23, 0xf4d50d87); /* 27 */GG (b, c, d, a, x[ 8], S24, 0x455a14ed); /* 28 */GG (a, b, c, d, x[13], S21, 0xa9e3e905); /* 29 */GG (d, a, b, c, x[ 2], S22, 0xfcefa3f8); /* 30 */GG (c, d, a, b, x[ 7], S23, 0x676f02d9); /* 31 */GG (b, c, d, a, x[12], S24, 0x8d2a4c8a); /* 32 *//* Round 3 */HH (a, b, c, d, x[ 5], S31, 0xfffa3942); /* 33 */HH (d, a, b, c, x[ 8], S32, 0x8771f681); /* 34 */HH (c, d, a, b, x[11], S33, 0x6d9d6122); /* 35 */HH (b, c, d, a, x[14], S34, 0xfde5380c); /* 36 */HH (a, b, c, d, x[ 1], S31, 0xa4beea44); /* 37 */HH (d, a, b, c, x[ 4], S32, 0x4bdecfa9); /* 38 */HH (c, d, a, b, x[ 7], S33, 0xf6bb4b60); /* 39 */HH (b, c, d, a, x[10], S34, 0xbebfbc70); /* 40 */HH (a, b, c, d, x[13], S31, 0x289b7ec6); /* 41 */HH (d, a, b, c, x[ 0], S32, 0xeaa127fa); /* 42 */HH (c, d, a, b, x[ 3], S33, 0xd4ef3085); /* 43 */HH (b, c, d, a, x[ 6], S34,  0x4881d05); /* 44 */HH (a, b, c, d, x[ 9], S31, 0xd9d4d039); /* 45 */HH (d, a, b, c, x[12], S32, 0xe6db99e5); /* 46 */HH (c, d, a, b, x[15], S33, 0x1fa27cf8); /* 47 */HH (b, c, d, a, x[ 2], S34, 0xc4ac5665); /* 48 *//* Round 4 */II (a, b, c, d, x[ 0], S41, 0xf4292244); /* 49 */II (d, a, b, c, x[ 7], S42, 0x432aff97); /* 50 */II (c, d, a, b, x[14], S43, 0xab9423a7); /* 51 */II (b, c, d, a, x[ 5], S44, 0xfc93a039); /* 52 */II (a, b, c, d, x[12], S41, 0x655b59c3); /* 53 */II (d, a, b, c, x[ 3], S42, 0x8f0ccc92); /* 54 */II (c, d, a, b, x[10], S43, 0xffeff47d); /* 55 */II (b, c, d, a, x[ 1], S44, 0x85845dd1); /* 56 */II (a, b, c, d, x[ 8], S41, 0x6fa87e4f); /* 57 */II (d, a, b, c, x[15], S42, 0xfe2ce6e0); /* 58 */II (c, d, a, b, x[ 6], S43, 0xa3014314); /* 59 */II (b, c, d, a, x[13], S44, 0x4e0811a1); /* 60 */II (a, b, c, d, x[ 4], S41, 0xf7537e82); /* 61 */II (d, a, b, c, x[11], S42, 0xbd3af235); /* 62 */II (c, d, a, b, x[ 2], S43, 0x2ad7d2bb); /* 63 */II (b, c, d, a, x[ 9], S44, 0xeb86d391); /* 64 */state[0] += a;state[1] += b;state[2] += c;state[3] += d;/* Zeroize sensitive information.*/MD5_memset ((unsigned char*)x, 0, sizeof (x));}/* Encodes input (unsigned long int) into output (unsigned char). Assumes len isa multiple of 4.*/void MD5_CTX::Encode (unsigned char *output, unsigned long int *input,unsigned int len){unsigned int i, j;for (i = 0, j = 0; j < len; i++, j += 4) {output[j] = (unsigned char)(input[i] & 0xff);output[j+1] = (unsigned char)((input[i] >> 8) & 0xff);output[j+2] = (unsigned char)((input[i] >> 16) & 0xff);output[j+3] = (unsigned char)((input[i] >> 24) & 0xff);}}/* Decodes input (unsigned char) into output (unsigned long int). Assumes len isa multiple of 4.*/void MD5_CTX::Decode (unsigned long int *output, unsigned char *input, unsigned int len){unsigned int i, j;for (i = 0, j = 0; j < len; i++, j += 4)output[i] = ((unsigned long int)input[j]) | (((unsigned long int)input[j+1]) << 8) |(((unsigned long int)input[j+2]) << 16) | (((unsigned long int)input[j+3]) << 24);}/* Note: Replace "for loop" with standard memcpy if possible.*/void MD5_CTX::MD5_memcpy (unsigned char* output, unsigned char* input,unsigned int len){unsigned int i;for (i = 0; i < len; i++)output[i] = input[i];}/* Note: Replace "for loop" with standard memset if possible.*/void MD5_CTX::MD5_memset (unsigned char* output,int value,unsigned int len){unsigned int i;for (i = 0; i < len; i++)((char *)output)[i] = (char)value;}BOOL MD5Data(unsigned char *buff,unsigned int len, unsigned char digest[16]){MD5_CTX md5;md5.MD5Update ((unsigned char *)buff, len);md5.MD5Final (digest);    return TRUE;}BOOL MD5File(LPCTSTR lpszFileName, unsigned char digest[16], unsigned int * pFileLen){    BOOL bRet=FALSE;    memset(digest,0,sizeof(digest));    HANDLE hFile = CreateFile(lpszFileName, GENERIC_READ , FILE_SHARE_READ | FILE_SHARE_WRITE , NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL, NULL);    if (hFile != INVALID_HANDLE_VALUE)    {        DWORD dwFileSizeHigh;        DWORD dwFileSizeLow = GetFileSize(hFile, &dwFileSizeHigh);        if (dwFileSizeLow)        {            if (pFileLen) *pFileLen=dwFileSizeLow;            SECURITY_DESCRIPTOR secutityDese;            ::InitializeSecurityDescriptor(&secutityDese, SECURITY_DESCRIPTOR_REVISION);            ::SetSecurityDescriptorDacl(&secutityDese,TRUE,NULL,FALSE);            SECURITY_ATTRIBUTES securityAttr;            securityAttr.nLength = sizeof SECURITY_ATTRIBUTES;            securityAttr.bInheritHandle = FALSE;            securityAttr.lpSecurityDescriptor = &secutityDese;            HANDLE hFileMap = CreateFileMapping(hFile, &securityAttr, PAGE_READONLY, dwFileSizeHigh, dwFileSizeLow, NULL);            if (hFileMap)            {                LPBYTE lpbMapAddress = (LPBYTE)MapViewOfFile(hFileMap, FILE_MAP_READ, 0, 0, 0);                if (lpbMapAddress)                {                    bRet=MD5Data((unsigned char *)lpbMapAddress, dwFileSizeLow, digest);                    UnmapViewOfFile(lpbMapAddress);                }                CloseHandle(hFileMap);            }        }        CloseHandle(hFile);    }    return bRet;}