代码很简单,调用了MFC里的几个函数。这里的冗余判断,是要遍历文件内容,进行两两比较。
需要注意的地方有两点:
1.源文件里头文件<afx.h>必须放在最前面。这里是为了避免nafxcwd.lib error LNK2005,由于CRT 库对 new、delete 和 DllMain 函数使用弱外部链接,MFC 库也包含 new、delete 和 DllMain 函数,这些函数要求先链接 MFC 库,然后再链接 CRT 库。
2.MFC库采取静态编译。这里是为了避免nafxcwd.lib error LNK2001。
代码实现:
1 #include <afx.h> 2 #include <iostream> 3 #include <vector> 4 #include <algorithm> 5 using namespace std; 6 7 vector<CFileStatus> cf; 8 bool cmp(const CFileStatus &r1,const CFileStatus &r2){ 9 return r1.m_size<r2.m_size; 10 } 11 12 int main(){ 13 CFileFind finder; 14 CFile cfile; 15 CFileStatus rStatus; 16 BOOL bWorking=finder.FindFile(_T("*.txt")); 17 18 cout<<"正在搜索当前目录下冗余文件..."<<endl; 19 while (bWorking){ 20 bWorking = finder.FindNextFile(); 21 CString fp = (LPCTSTR)finder.GetFilePath(); 22 CFile::GetStatus(fp,rStatus); 23 cf.insert(cf.end(), rStatus); 24 } 25 sort(cf.begin(),cf.end(),cmp); 26 for(int i=0;i < cf.size(); i++){ 27 int size = cf[i].m_size; 28 int num = 0; 29 bool tag = false; 30 CFile file1(cf[i].m_szFullName,CFile::modeRead); 31 char *FileContent1 = new char[cf[i].m_size]; 32 file1.Read(FileContent1,cf[i].m_size); 33 for(int j=i+1;j < cf.size(); j++){ 34 if(cf[i].m_size == cf[j].m_size){ 35 CFile file2(cf[j].m_szFullName,CFile::modeRead); 36 char *FileContent2 = new char[cf[j].m_size]; 37 file2.Read(FileContent2,cf[j].m_size); 38 for(num =0; num <size; num++){ 39 if(FileContent1[num] != FileContent2[num]){ 40 break; 41 } 42 } 43 file2.Close(); 44 if(num == size){ 45 cout<<"找到一组冗余文件,正在删除其中冗余文件! "<<endl; 46 file2.Remove(cf[j].m_szFullName); 47 cf.erase(cf.begin()+j); 48 j--; 49 delete FileContent2; 50 } 51 }else break; 52 file1.Close(); 53 } 54 } 55 cout<<"已完成操作!"<<endl; 56 return 0; 57 }
下面是加了MD5的版本(采取多文件组织):
md5.h:
1 #ifndef MD5_H 2 #define MD5_H 3 4 typedef struct 5 { 6 unsigned int count[2]; 7 unsigned int state[4]; 8 unsigned char buffer[64]; 9 }MD5_CTX; 10 11 12 #define F(x,y,z) ((x & y) | (~x & z)) 13 #define G(x,y,z) ((x & z) | (y & ~z)) 14 #define H(x,y,z) (x^y^z) 15 #define I(x,y,z) (y ^ (x | ~z)) 16 #define ROTATE_LEFT(x,n) ((x << n) | (x >> (32-n))) 17 #define FF(a,b,c,d,x,s,ac) \ 18 { \ 19 a += F(b,c,d) + x + ac; \ 20 a = ROTATE_LEFT(a,s); \ 21 a += b; \ 22 } 23 #define GG(a,b,c,d,x,s,ac) \ 24 { \ 25 a += G(b,c,d) + x + ac; \ 26 a = ROTATE_LEFT(a,s); \ 27 a += b; \ 28 } 29 #define HH(a,b,c,d,x,s,ac) \ 30 { \ 31 a += H(b,c,d) + x + ac; \ 32 a = ROTATE_LEFT(a,s); \ 33 a += b; \ 34 } 35 #define II(a,b,c,d,x,s,ac) \ 36 { \ 37 a += I(b,c,d) + x + ac; \ 38 a = ROTATE_LEFT(a,s); \ 39 a += b; \ 40 } 41 void MD5Init(MD5_CTX *context); 42 void MD5Update(MD5_CTX *context,unsigned char *input,unsigned int inputlen); 43 void MD5Final(MD5_CTX *context,unsigned char digest[16]); 44 void MD5Transform(unsigned int state[4],unsigned char block[64]); 45 void MD5Encode(unsigned char *output,unsigned int *input,unsigned int len); 46 void MD5Decode(unsigned int *output,unsigned char *input,unsigned int len); 47 48 #endif
md5.cpp:
1 #include <memory.h> 2 #include "md5.h" 3 4 unsigned char PADDING[]={0x80,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 5 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 6 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 7 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0}; 8 9 void MD5Init(MD5_CTX *context) 10 { 11 context->count[0] = 0; 12 context->count[1] = 0; 13 context->state[0] = 0x67452301; 14 context->state[1] = 0xEFCDAB89; 15 context->state[2] = 0x98BADCFE; 16 context->state[3] = 0x10325476; 17 } 18 void MD5Update(MD5_CTX *context,unsigned char *input,unsigned int inputlen) 19 { 20 unsigned int i = 0,index = 0,partlen = 0; 21 index = (context->count[0] >> 3) & 0x3F; 22 partlen = 64 - index; 23 context->count[0] += inputlen << 3; 24 if(context->count[0] < (inputlen << 3)) 25 context->count[1]++; 26 context->count[1] += inputlen >> 29; 27 28 if(inputlen >= partlen) 29 { 30 memcpy(&context->buffer[index],input,partlen); 31 MD5Transform(context->state,context->buffer); 32 for(i = partlen;i+64 <= inputlen;i+=64) 33 MD5Transform(context->state,&input[i]); 34 index = 0; 35 } 36 else 37 { 38 i = 0; 39 } 40 memcpy(&context->buffer[index],&input[i],inputlen-i); 41 } 42 void MD5Final(MD5_CTX *context,unsigned char digest[16]) 43 { 44 unsigned int index = 0,padlen = 0; 45 unsigned char bits[8]; 46 index = (context->count[0] >> 3) & 0x3F; 47 padlen = (index < 56)?(56-index):(120-index); 48 MD5Encode(bits,context->count,8); 49 MD5Update(context,PADDING,padlen); 50 MD5Update(context,bits,8); 51 MD5Encode(digest,context->state,16); 52 } 53 void MD5Encode(unsigned char *output,unsigned int *input,unsigned int len) 54 { 55 unsigned int i = 0,j = 0; 56 while(j < len) 57 { 58 output[j] = input[i] & 0xFF; 59 output[j+1] = (input[i] >> 8) & 0xFF; 60 output[j+2] = (input[i] >> 16) & 0xFF; 61 output[j+3] = (input[i] >> 24) & 0xFF; 62 i++; 63 j+=4; 64 } 65 } 66 void MD5Decode(unsigned int *output,unsigned char *input,unsigned int len) 67 { 68 unsigned int i = 0,j = 0; 69 while(j < len) 70 { 71 output[i] = (input[j]) | 72 (input[j+1] << 8) | 73 (input[j+2] << 16) | 74 (input[j+3] << 24); 75 i++; 76 j+=4; 77 } 78 } 79 void MD5Transform(unsigned int state[4],unsigned char block[64]) 80 { 81 unsigned int a = state[0]; 82 unsigned int b = state[1]; 83 unsigned int c = state[2]; 84 unsigned int d = state[3]; 85 unsigned int x[64]; 86 MD5Decode(x,block,64); 87 FF(a, b, c, d, x[ 0], 7, 0xd76aa478); /* 1 */ 88 FF(d, a, b, c, x[ 1], 12, 0xe8c7b756); /* 2 */ 89 FF(c, d, a, b, x[ 2], 17, 0x242070db); /* 3 */ 90 FF(b, c, d, a, x[ 3], 22, 0xc1bdceee); /* 4 */ 91 FF(a, b, c, d, x[ 4], 7, 0xf57c0faf); /* 5 */ 92 FF(d, a, b, c, x[ 5], 12, 0x4787c62a); /* 6 */ 93 FF(c, d, a, b, x[ 6], 17, 0xa8304613); /* 7 */ 94 FF(b, c, d, a, x[ 7], 22, 0xfd469501); /* 8 */ 95 FF(a, b, c, d, x[ 8], 7, 0x698098d8); /* 9 */ 96 FF(d, a, b, c, x[ 9], 12, 0x8b44f7af); /* 10 */ 97 FF(c, d, a, b, x[10], 17, 0xffff5bb1); /* 11 */ 98 FF(b, c, d, a, x[11], 22, 0x895cd7be); /* 12 */ 99 FF(a, b, c, d, x[12], 7, 0x6b901122); /* 13 */ 100 FF(d, a, b, c, x[13], 12, 0xfd987193); /* 14 */ 101 FF(c, d, a, b, x[14], 17, 0xa679438e); /* 15 */ 102 FF(b, c, d, a, x[15], 22, 0x49b40821); /* 16 */ 103 104 /* Round 2 */ 105 GG(a, b, c, d, x[ 1], 5, 0xf61e2562); /* 17 */ 106 GG(d, a, b, c, x[ 6], 9, 0xc040b340); /* 18 */ 107 GG(c, d, a, b, x[11], 14, 0x265e5a51); /* 19 */ 108 GG(b, c, d, a, x[ 0], 20, 0xe9b6c7aa); /* 20 */ 109 GG(a, b, c, d, x[ 5], 5, 0xd62f105d); /* 21 */ 110 GG(d, a, b, c, x[10], 9, 0x2441453); /* 22 */ 111 GG(c, d, a, b, x[15], 14, 0xd8a1e681); /* 23 */ 112 GG(b, c, d, a, x[ 4], 20, 0xe7d3fbc8); /* 24 */ 113 GG(a, b, c, d, x[ 9], 5, 0x21e1cde6); /* 25 */ 114 GG(d, a, b, c, x[14], 9, 0xc33707d6); /* 26 */ 115 GG(c, d, a, b, x[ 3], 14, 0xf4d50d87); /* 27 */ 116 GG(b, c, d, a, x[ 8], 20, 0x455a14ed); /* 28 */ 117 GG(a, b, c, d, x[13], 5, 0xa9e3e905); /* 29 */ 118 GG(d, a, b, c, x[ 2], 9, 0xfcefa3f8); /* 30 */ 119 GG(c, d, a, b, x[ 7], 14, 0x676f02d9); /* 31 */ 120 GG(b, c, d, a, x[12], 20, 0x8d2a4c8a); /* 32 */ 121 122 /* Round 3 */ 123 HH(a, b, c, d, x[ 5], 4, 0xfffa3942); /* 33 */ 124 HH(d, a, b, c, x[ 8], 11, 0x8771f681); /* 34 */ 125 HH(c, d, a, b, x[11], 16, 0x6d9d6122); /* 35 */ 126 HH(b, c, d, a, x[14], 23, 0xfde5380c); /* 36 */ 127 HH(a, b, c, d, x[ 1], 4, 0xa4beea44); /* 37 */ 128 HH(d, a, b, c, x[ 4], 11, 0x4bdecfa9); /* 38 */ 129 HH(c, d, a, b, x[ 7], 16, 0xf6bb4b60); /* 39 */ 130 HH(b, c, d, a, x[10], 23, 0xbebfbc70); /* 40 */ 131 HH(a, b, c, d, x[13], 4, 0x289b7ec6); /* 41 */ 132 HH(d, a, b, c, x[ 0], 11, 0xeaa127fa); /* 42 */ 133 HH(c, d, a, b, x[ 3], 16, 0xd4ef3085); /* 43 */ 134 HH(b, c, d, a, x[ 6], 23, 0x4881d05); /* 44 */ 135 HH(a, b, c, d, x[ 9], 4, 0xd9d4d039); /* 45 */ 136 HH(d, a, b, c, x[12], 11, 0xe6db99e5); /* 46 */ 137 HH(c, d, a, b, x[15], 16, 0x1fa27cf8); /* 47 */ 138 HH(b, c, d, a, x[ 2], 23, 0xc4ac5665); /* 48 */ 139 140 /* Round 4 */ 141 II(a, b, c, d, x[ 0], 6, 0xf4292244); /* 49 */ 142 II(d, a, b, c, x[ 7], 10, 0x432aff97); /* 50 */ 143 II(c, d, a, b, x[14], 15, 0xab9423a7); /* 51 */ 144 II(b, c, d, a, x[ 5], 21, 0xfc93a039); /* 52 */ 145 II(a, b, c, d, x[12], 6, 0x655b59c3); /* 53 */ 146 II(d, a, b, c, x[ 3], 10, 0x8f0ccc92); /* 54 */ 147 II(c, d, a, b, x[10], 15, 0xffeff47d); /* 55 */ 148 II(b, c, d, a, x[ 1], 21, 0x85845dd1); /* 56 */ 149 II(a, b, c, d, x[ 8], 6, 0x6fa87e4f); /* 57 */ 150 II(d, a, b, c, x[15], 10, 0xfe2ce6e0); /* 58 */ 151 II(c, d, a, b, x[ 6], 15, 0xa3014314); /* 59 */ 152 II(b, c, d, a, x[13], 21, 0x4e0811a1); /* 60 */ 153 II(a, b, c, d, x[ 4], 6, 0xf7537e82); /* 61 */ 154 II(d, a, b, c, x[11], 10, 0xbd3af235); /* 62 */ 155 II(c, d, a, b, x[ 2], 15, 0x2ad7d2bb); /* 63 */ 156 II(b, c, d, a, x[ 9], 21, 0xeb86d391); /* 64 */ 157 state[0] += a; 158 state[1] += b; 159 state[2] += c; 160 state[3] += d; 161 }
main.cpp:
1 #include <afx.h> 2 #include <iostream> 3 #include <vector> 4 #include <cstring> 5 #include "md5.h" 6 using namespace std; 7 8 struct node{ 9 unsigned char *s; 10 CString fp; 11 }tmp; 12 13 vector<node> cf; 14 15 int main(){ 16 MD5_CTX md5; 17 18 CFileFind finder; 19 CFile cfile; 20 CFileStatus rStatus; 21 BOOL bWorking=finder.FindFile(_T("*.txt")); 22 23 cout<<"正在搜索当前目录下冗余文件..."<<endl; 24 while (bWorking){ 25 bWorking = finder.FindNextFile(); 26 tmp.fp = (LPCTSTR)finder.GetFilePath(); 27 CFile::GetStatus(tmp.fp,rStatus); 28 29 CFile file(rStatus.m_szFullName,CFile::modeRead); 30 char *FileConten = new char[rStatus.m_size]; 31 file.Read(FileConten,rStatus.m_size); 32 33 MD5Init(&md5); 34 MD5Update(&md5,(unsigned char*)FileConten,rStatus.m_size); 35 tmp.s=new unsigned char[16]; 36 MD5Final(&md5,tmp.s); 37 cf.push_back(tmp); 38 39 file.Close(); 40 } 41 for(int i=0;i < cf.size(); i++){ 42 for(int j=i+1;j < cf.size(); j++){ 43 if(strcmp((const char*)cf[i].s,(const char*)cf[j].s)){ 44 cout<<"找到一组冗余文件,正在删除其中冗余文件! "<<endl; 45 CFile file(cf[j].fp,CFile::modeRead); 46 file.Close(); 47 file.Remove(cf[j].fp); 48 delete cf[j].s; 49 cf.erase(cf.begin()+j); 50 j--; 51 } 52 } 53 } 54 cout<<"已完成操作!"<<endl; 55 return 0; 56 }