/*****************************************************************************************
*** MD5Checksum.cpp: implementation of the MD5Checksum class.
*** Developed by Langfine Ltd.
*** Released to the public domain 12/Nov/2001.
*** Please visit our website www.langfine.com
*** Any modifications must be clearly commented to distinguish them from Langfine's
*** original source code. Please advise Langfine of useful modifications so that we
*** can make them generally available.
*** Modified by John Arrizza 09/23/2002
*** - replaced all MFC classes with STL
*** - converted all CString to string
*** - UCHAR to unsigned char
*** - BYTE to unsigned char
*** - UINT to unsigned long
*** - DWORD to unsigned long
*** - ULONG to unsigned long
*** - ASSERT to assert
*** - removed stdafx.cpp, stdafx.h, resource.h and md5.rc
*** - removed .pch settings, _AFXDLL defines,
*** - added const in a few places
*** - converted to VC7 (i.e. .NET unmanaged C++)
*****************************************************************************************/
/****************************************************************************************
This software is derived from the RSA Data Security, Inc. MD5 Message-Digest Algorithm.
Incorporation of this statement is a condition of use; please see the RSA
Data Security Inc copyright notice below:-
Copyright (C) 1990-2, RSA Data Security, Inc. Created 1990. All
rights reserved.
RSA Data Security, Inc. makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
These notices must be retained in any copies of any part of this
documentation and/or software.
Copyright (C) 1991-2, RSA Data Security, Inc. Created 1991. All
rights reserved.
License to copy and use this software is granted provided that it
is identified as the "RSA Data Security, Inc. MD5 Message-Digest
Algorithm" in all material mentioning or referencing this software
or this function.
License is also granted to make and use derivative works provided
that such works are identified as "derived from the RSA Data
Security, Inc. MD5 Message-Digest Algorithm" in all material
mentioning or referencing the derived work.
RSA Data Security, Inc. makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
These notices must be retained in any copies of any part of this
documentation and/or software.
*****************************************************************************************/
/****************************************************************************************
This implementation of the RSA MD5 Algorithm was written by Langfine Ltd
(www.langfine.com).
Langfine Ltd makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
In addition to the above, Langfine make no warrant or assurances regarding the
accuracy of this implementation of the MD5 checksum algorithm nor any assurances regarding
its suitability for any purposes.
This implementation may be used freely provided that Langfine is credited
in a copyright or similar notices (eg, RSA MD5 Algorithm implemented by Langfine
Ltd.) and provided that the RSA Data Security notices are complied with.
*/
#include <exception>
#include <fstream>
using namespace std;
#include <assert.h>
#include "MD5Checksum.h"
#include "MD5ChecksumDefines.h"
/*****************************************************************************************
FUNCTION: CMD5Checksum::GetMD5
DETAILS: static, public
DESCRIPTION: Gets the MD5 checksum for a specified file
RETURNS: string : the hexadecimal MD5 checksum for the specified file
ARGUMENTS: string& strFilePath : the full pathname of the specified file
NOTES: Provides an interface to the CMD5Checksum class. 'strFilePath' name should
hold the full pathname of the file, eg C:\My Documents\Arcticle.txt.
NB. If any problems occur with opening or reading this file, a CFileException
will be thrown; callers of this function should be ready to catch this
exception.
*****************************************************************************************/
string CMD5Checksum::GetMD5(const string& strFilePath)
{
//open the file as a binary file in readonly mode, denying write access
//CFile File(strFilePath, CFile::modeRead | CFile::shareDenyWrite | CFile::typeBinary);
ifstream File(strFilePath.c_str());
//the file has been successfully opened, so now get and return its checksum
return GetMD5(File);
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::GetMD5
DETAILS: static, public
DESCRIPTION: Gets the MD5 checksum for a specified file
RETURNS: string : the hexadecimal MD5 checksum for the specified file
ARGUMENTS: CFile& File : the specified file
NOTES: Provides an interface to the CMD5Checksum class. 'File' should be open in
binary readonly mode before calling this function.
NB. Callers of this function should be ready to catch any CFileException
thrown by the CFile functions
*****************************************************************************************/
string CMD5Checksum::GetMD5(ifstream& File)
{
try
{
CMD5Checksum MD5Checksum; //checksum object
int nLength = 0; //number of bytes read from the file
const int nBufferSize = 1024; //checksum the file in blocks of 1024 bytes
unsigned char Buffer[nBufferSize]; //buffer for data read from the file
//checksum the file in blocks of 1024 bytes
for(;;)
{
File.read( (char*) Buffer, nBufferSize );
nLength = File.gcount();
if (nLength <= 0 )
break;
MD5Checksum.Update( Buffer, nLength );
}
//finalise the checksum and return it
return MD5Checksum.Final();
}
//report any file exceptions in debug mode only
catch (exception& e)
{
//OutputDebugString("CMD5Checksum::GetMD5: CFileException caught\n");
throw e;
}
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::GetMD5
DETAILS: static, public
DESCRIPTION: Gets the MD5 checksum for data in a char array
RETURNS: string : the hexadecimal MD5 checksum for the specified data
ARGUMENTS: char* pBuf : pointer to the char array
unsigned long nLength : number of BYTEs of data to be checksumed
NOTES: Provides an interface to the CMD5Checksum class. Any data that can
be cast to a char array of known length can be checksummed by this
function. Typically, string and char arrays will be checksumed,
although this function can be used to check the integrity of any char array.
A buffer of zero length can be checksummed; all buffers of zero length
will return the same checksum.
*****************************************************************************************/
string CMD5Checksum::GetMD5(const unsigned char* pBuf, unsigned long nLength)
{
//calculate and return the checksum
CMD5Checksum MD5Checksum;
MD5Checksum.Update( pBuf, nLength );
return MD5Checksum.Final();
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::RotateLeft
DETAILS: private
DESCRIPTION: Rotates the bits in a 32 bit unsigned long left by a specified amount
RETURNS: The rotated unsigned long
ARGUMENTS: unsigned long x : the value to be rotated
int n : the number of bits to rotate by
*****************************************************************************************/
unsigned long CMD5Checksum::RotateLeft(unsigned long x, int n)
{
//check that unsigned long is 4 bytes long - true in Visual C++ 6 and 32 bit Windows
assert( sizeof(x) == 4 );
//rotate and return x
return (x << n) | (x >> (32-n));
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::FF
DETAILS: protected
DESCRIPTION: Implementation of basic MD5 transformation algorithm
RETURNS: none
ARGUMENTS: unsigned long &A, B, C, D : Current (partial) checksum
unsigned long X : Input data
unsigned long S : MD5_SXX Transformation constant
unsigned long T : MD5_TXX Transformation constant
NOTES: None
*****************************************************************************************/
void CMD5Checksum::FF( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T)
{
unsigned long F = (B & C) | (~B & D);
A += F + X + T;
A = RotateLeft(A, S);
A += B;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::GG
DETAILS: protected
DESCRIPTION: Implementation of basic MD5 transformation algorithm
RETURNS: none
ARGUMENTS: unsigned long &A, B, C, D : Current (partial) checksum
unsigned long X : Input data
unsigned long S : MD5_SXX Transformation constant
unsigned long T : MD5_TXX Transformation constant
NOTES: None
*****************************************************************************************/
void CMD5Checksum::GG( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T)
{
unsigned long G = (B & D) | (C & ~D);
A += G + X + T;
A = RotateLeft(A, S);
A += B;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::HH
DETAILS: protected
DESCRIPTION: Implementation of basic MD5 transformation algorithm
RETURNS: none
ARGUMENTS: unsigned long &A, B, C, D : Current (partial) checksum
unsigned long X : Input data
unsigned long S : MD5_SXX Transformation constant
unsigned long T : MD5_TXX Transformation constant
NOTES: None
*****************************************************************************************/
void CMD5Checksum::HH( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T)
{
unsigned long H = (B ^ C ^ D);
A += H + X + T;
A = RotateLeft(A, S);
A += B;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::II
DETAILS: protected
DESCRIPTION: Implementation of basic MD5 transformation algorithm
RETURNS: none
ARGUMENTS: unsigned long &A, B, C, D : Current (partial) checksum
unsigned long X : Input data
unsigned long S : MD5_SXX Transformation constant
unsigned long T : MD5_TXX Transformation constant
NOTES: None
*****************************************************************************************/
void CMD5Checksum::II( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T)
{
unsigned long I = (C ^ (B | ~D));
A += I + X + T;
A = RotateLeft(A, S);
A += B;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::ByteToDWord
DETAILS: private
DESCRIPTION: Transfers the data in an 8 bit array to a 32 bit array
RETURNS: void
ARGUMENTS: unsigned long* Output : the 32 bit (unsigned long) destination array
char* Input : the 8 bit (unsigned char) source array
unsigned long nLength : the number of 8 bit data items in the source array
NOTES: Four BYTES from the input array are transferred to each unsigned long entry
of the output array. The first char is transferred to the bits (0-7)
of the output unsigned long, the second char to bits 8-15 etc.
The algorithm assumes that the input array is a multiple of 4 bytes long
so that there is a perfect fit into the array of 32 bit words.
*****************************************************************************************/
void CMD5Checksum::ByteToDWord(unsigned long* Output, const unsigned char* Input, unsigned long nLength)
{
//entry invariants
assert( nLength % 4 == 0 );
// assert( AfxIsValidAddress(Output, nLength/4, TRUE) );
// assert( AfxIsValidAddress(Input, nLength, FALSE) );
//initialisations
unsigned long i=0; //index to Output array
unsigned long j=0; //index to Input array
//transfer the data by shifting and copying
for ( ; j < nLength; i++, j += 4)
{
Output[i] = (unsigned long)Input[j] |
(unsigned long)Input[j+1] << 8 |
(unsigned long)Input[j+2] << 16 |
(unsigned long)Input[j+3] << 24;
}
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::Transform
DETAILS: protected
DESCRIPTION: MD5 basic transformation algorithm; transforms 'm_lMD5'
RETURNS: void
ARGUMENTS: char Block[64]
NOTES: An MD5 checksum is calculated by four rounds of 'Transformation'.
The MD5 checksum currently held in m_lMD5 is merged by the
transformation process with data passed in 'Block'.
*****************************************************************************************/
void CMD5Checksum::Transform(const unsigned char Block[64])
{
//initialise local data with current checksum
unsigned long a = m_lMD5[0];
unsigned long b = m_lMD5[1];
unsigned long c = m_lMD5[2];
unsigned long d = m_lMD5[3];
//copy BYTES from input 'Block' to an array of ULONGS 'X'
unsigned long X[16];
ByteToDWord( X, Block, 64 );
//Perform Round 1 of the transformation
FF (a, b, c, d, X[ 0], MD5_S11, MD5_T01);
FF (d, a, b, c, X[ 1], MD5_S12, MD5_T02);
FF (c, d, a, b, X[ 2], MD5_S13, MD5_T03);
FF (b, c, d, a, X[ 3], MD5_S14, MD5_T04);
FF (a, b, c, d, X[ 4], MD5_S11, MD5_T05);
FF (d, a, b, c, X[ 5], MD5_S12, MD5_T06);
FF (c, d, a, b, X[ 6], MD5_S13, MD5_T07);
FF (b, c, d, a, X[ 7], MD5_S14, MD5_T08);
FF (a, b, c, d, X[ 8], MD5_S11, MD5_T09);
FF (d, a, b, c, X[ 9], MD5_S12, MD5_T10);
FF (c, d, a, b, X[10], MD5_S13, MD5_T11);
FF (b, c, d, a, X[11], MD5_S14, MD5_T12);
FF (a, b, c, d, X[12], MD5_S11, MD5_T13);
FF (d, a, b, c, X[13], MD5_S12, MD5_T14);
FF (c, d, a, b, X[14], MD5_S13, MD5_T15);
FF (b, c, d, a, X[15], MD5_S14, MD5_T16);
//Perform Round 2 of the transformation
GG (a, b, c, d, X[ 1], MD5_S21, MD5_T17);
GG (d, a, b, c, X[ 6], MD5_S22, MD5_T18);
GG (c, d, a, b, X[11], MD5_S23, MD5_T19);
GG (b, c, d, a, X[ 0], MD5_S24, MD5_T20);
GG (a, b, c, d, X[ 5], MD5_S21, MD5_T21);
GG (d, a, b, c, X[10], MD5_S22, MD5_T22);
GG (c, d, a, b, X[15], MD5_S23, MD5_T23);
GG (b, c, d, a, X[ 4], MD5_S24, MD5_T24);
GG (a, b, c, d, X[ 9], MD5_S21, MD5_T25);
GG (d, a, b, c, X[14], MD5_S22, MD5_T26);
GG (c, d, a, b, X[ 3], MD5_S23, MD5_T27);
GG (b, c, d, a, X[ 8], MD5_S24, MD5_T28);
GG (a, b, c, d, X[13], MD5_S21, MD5_T29);
GG (d, a, b, c, X[ 2], MD5_S22, MD5_T30);
GG (c, d, a, b, X[ 7], MD5_S23, MD5_T31);
GG (b, c, d, a, X[12], MD5_S24, MD5_T32);
//Perform Round 3 of the transformation
HH (a, b, c, d, X[ 5], MD5_S31, MD5_T33);
HH (d, a, b, c, X[ 8], MD5_S32, MD5_T34);
HH (c, d, a, b, X[11], MD5_S33, MD5_T35);
HH (b, c, d, a, X[14], MD5_S34, MD5_T36);
HH (a, b, c, d, X[ 1], MD5_S31, MD5_T37);
HH (d, a, b, c, X[ 4], MD5_S32, MD5_T38);
HH (c, d, a, b, X[ 7], MD5_S33, MD5_T39);
HH (b, c, d, a, X[10], MD5_S34, MD5_T40);
HH (a, b, c, d, X[13], MD5_S31, MD5_T41);
HH (d, a, b, c, X[ 0], MD5_S32, MD5_T42);
HH (c, d, a, b, X[ 3], MD5_S33, MD5_T43);
HH (b, c, d, a, X[ 6], MD5_S34, MD5_T44);
HH (a, b, c, d, X[ 9], MD5_S31, MD5_T45);
HH (d, a, b, c, X[12], MD5_S32, MD5_T46);
HH (c, d, a, b, X[15], MD5_S33, MD5_T47);
HH (b, c, d, a, X[ 2], MD5_S34, MD5_T48);
//Perform Round 4 of the transformation
II (a, b, c, d, X[ 0], MD5_S41, MD5_T49);
II (d, a, b, c, X[ 7], MD5_S42, MD5_T50);
II (c, d, a, b, X[14], MD5_S43, MD5_T51);
II (b, c, d, a, X[ 5], MD5_S44, MD5_T52);
II (a, b, c, d, X[12], MD5_S41, MD5_T53);
II (d, a, b, c, X[ 3], MD5_S42, MD5_T54);
II (c, d, a, b, X[10], MD5_S43, MD5_T55);
II (b, c, d, a, X[ 1], MD5_S44, MD5_T56);
II (a, b, c, d, X[ 8], MD5_S41, MD5_T57);
II (d, a, b, c, X[15], MD5_S42, MD5_T58);
II (c, d, a, b, X[ 6], MD5_S43, MD5_T59);
II (b, c, d, a, X[13], MD5_S44, MD5_T60);
II (a, b, c, d, X[ 4], MD5_S41, MD5_T61);
II (d, a, b, c, X[11], MD5_S42, MD5_T62);
II (c, d, a, b, X[ 2], MD5_S43, MD5_T63);
II (b, c, d, a, X[ 9], MD5_S44, MD5_T64);
//add the transformed values to the current checksum
m_lMD5[0] += a;
m_lMD5[1] += b;
m_lMD5[2] += c;
m_lMD5[3] += d;
}
/*****************************************************************************************
CONSTRUCTOR: CMD5Checksum
DESCRIPTION: Initialises member data
ARGUMENTS: None
NOTES: None
*****************************************************************************************/
CMD5Checksum::CMD5Checksum()
{
// zero members
memset( m_lpszBuffer, 0, 64 );
m_nCount[0] = m_nCount[1] = 0;
// Load magic state initialization constants
m_lMD5[0] = MD5_INIT_STATE_0;
m_lMD5[1] = MD5_INIT_STATE_1;
m_lMD5[2] = MD5_INIT_STATE_2;
m_lMD5[3] = MD5_INIT_STATE_3;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::DWordToByte
DETAILS: private
DESCRIPTION: Transfers the data in an 32 bit array to a 8 bit array
RETURNS: void
ARGUMENTS: char* Output : the 8 bit destination array
unsigned long* Input : the 32 bit source array
unsigned long nLength : the number of 8 bit data items in the source array
NOTES: One unsigned long from the input array is transferred into four BYTES
in the output array. The first (0-7) bits of the first unsigned long are
transferred to the first output char, bits bits 8-15 are transferred from
the second char etc.
The algorithm assumes that the output array is a multiple of 4 bytes long
so that there is a perfect fit of 8 bit BYTES into the 32 bit DWORDs.
*****************************************************************************************/
void CMD5Checksum::DWordToByte(unsigned char* Output, unsigned long* Input, unsigned long nLength )
{
//entry invariants
assert( nLength % 4 == 0 );
// assert( AfxIsValidAddress(Output, nLength, TRUE) );
// assert( AfxIsValidAddress(Input, nLength/4, FALSE) );
//transfer the data by shifting and copying
unsigned long i = 0;
unsigned long j = 0;
for ( ; j < nLength; 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);
}
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::Final
DETAILS: protected
DESCRIPTION: Implementation of main MD5 checksum algorithm; ends the checksum calculation.
RETURNS: string : the final hexadecimal MD5 checksum result
ARGUMENTS: None
NOTES: Performs the final MD5 checksum calculation ('Update' does most of the work,
this function just finishes the calculation.)
*****************************************************************************************/
string CMD5Checksum::Final()
{
//Save number of bits
unsigned char Bits[8];
DWordToByte( Bits, m_nCount, 8 );
//Pad out to 56 mod 64.
unsigned long nIndex = (unsigned long)((m_nCount[0] >> 3) & 0x3f);
unsigned long nPadLen = (nIndex < 56) ? (56 - nIndex) : (120 - nIndex);
Update( PADDING, nPadLen );
//Append length (before padding)
Update( Bits, 8 );
//Store final state in 'lpszMD5'
const int nMD5Size = 16;
unsigned char lpszMD5[ nMD5Size ];
DWordToByte( lpszMD5, m_lMD5, nMD5Size );
//Convert the hexadecimal checksum to a string
string strMD5;
for ( int i=0; i < nMD5Size; i++)
{
string Str;
if (lpszMD5[i] == 0) {
Str = string("00");
}
else if (lpszMD5[i] <= 15) {
char buf[5];
sprintf(buf, "0%x",lpszMD5[i]);
Str = buf;
}
else {
char buf[5];
sprintf(buf, "%x",lpszMD5[i]);
Str = buf;
}
assert( Str.size() == 2 );
strMD5 += Str;
}
assert( strMD5.size()== 32 );
return strMD5;
}
/*****************************************************************************************
FUNCTION: CMD5Checksum::Update
DETAILS: protected
DESCRIPTION: Implementation of main MD5 checksum algorithm
RETURNS: void
ARGUMENTS: char* Input : input block
unsigned long nInputLen : length of input block
NOTES: Computes the partial MD5 checksum for 'nInputLen' bytes of data in 'Input'
*****************************************************************************************/
void CMD5Checksum::Update( const unsigned char* Input, unsigned long nInputLen )
{
//Compute number of bytes mod 64
unsigned long nIndex = (unsigned long)((m_nCount[0] >> 3) & 0x3F);
//Update number of bits
if ( ( m_nCount[0] += nInputLen << 3 ) < ( nInputLen << 3) )
{
m_nCount[1]++;
}
m_nCount[1] += (nInputLen >> 29);
//Transform as many times as possible.
unsigned long i=0;
unsigned long nPartLen = 64 - nIndex;
if (nInputLen >= nPartLen)
{
memcpy( &m_lpszBuffer[nIndex], Input, nPartLen );
Transform( m_lpszBuffer );
for (i = nPartLen; i + 63 < nInputLen; i += 64)
{
Transform( &Input[i] );
}
nIndex = 0;
}
else
{
i = 0;
}
// Buffer remaining input
memcpy( &m_lpszBuffer[nIndex], &Input[i], nInputLen-i);
}
|
/*****************************************************************************************
*** MD5Checksum.h: interface for the MD5Checksum class.
*** Developed by Langfine Ltd.
*** Released to the public domain 12/Nov/2001.
*** Please visit our website www.langfine.com
*** Any modifications must be clearly commented to distinguish them from Langfine's
*** original source code. Please advise Langfine of useful modifications so that we
*** can make them generally available.
*****************************************************************************************/
#if !defined(AFX_MD5CHECKSUM_H__2BC7928E_4C15_11D3_B2EE_A4A60E20D2C3__INCLUDED_)
#define AFX_MD5CHECKSUM_H__2BC7928E_4C15_11D3_B2EE_A4A60E20D2C3__INCLUDED_
#if _MSC_VER > 1000
#pragma once
#endif // _MSC_VER > 1000
#include <fstream>
#include <string>
using std::ifstream;
using std::string;
/****************************************************************************************
This software is derived from the RSA Data Security, Inc. MD5 Message-Digest Algorithm.
Incorporation of this statement is a condition of use; please see the RSA
Data Security Inc copyright notice below:-
Copyright (C) 1990-2, RSA Data Security, Inc. Created 1990. All
rights reserved.
RSA Data Security, Inc. makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
These notices must be retained in any copies of any part of this
documentation and/or software.
Copyright (C) 1991-2, RSA Data Security, Inc. Created 1991. All
rights reserved.
License to copy and use this software is granted provided that it
is identified as the "RSA Data Security, Inc. MD5 Message-Digest
Algorithm" in all material mentioning or referencing this software
or this function.
License is also granted to make and use derivative works provided
that such works are identified as "derived from the RSA Data
Security, Inc. MD5 Message-Digest Algorithm" in all material
mentioning or referencing the derived work.
RSA Data Security, Inc. makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
These notices must be retained in any copies of any part of this
documentation and/or software.
*****************************************************************************************/
/****************************************************************************************
This implementation of the RSA MD5 Algorithm was written by Langfine Ltd.
Langfine Ltd makes no representations concerning either
the merchantability of this software or the suitability of this
software for any particular purpose. It is provided "as is"
without express or implied warranty of any kind.
In addition to the above, Langfine make no warrant or assurances regarding the
accuracy of this implementation of the MD5 checksum algorithm nor any assurances regarding
its suitability for any purposes.
This implementation may be used freely provided that Langfine is credited
in a copyright or similar notices (eg, RSA MD5 Algorithm implemented by Langfine
Ltd.) and provided that the RSA Data Security notices are complied with.
Langfine may be contacted at mail@langfine.com
*/
/*****************************************************************************************
CLASS: CMD5Checksum
DESCRIPTION: Implements the "RSA Data Security, Inc. MD5 Message-Digest Algorithm".
NOTES: Calculates the RSA MD5 checksum for a file or congiguous array of data.
Below are extracts from a memo on The MD5 Message-Digest Algorithm by R. Rivest of MIT
Laboratory for Computer Science and RSA Data Security, Inc., April 1992.
1. Executive Summary
This document describes the MD5 message-digest algorithm. The
algorithm takes as input a message of arbitrary length and produces
as output a 128-bit "fingerprint" or "message digest" of the input.
It is conjectured that it is computationally infeasible to produce
two messages having the same message digest, or to produce any
message having a given prespecified target message digest. The MD5
algorithm is intended for digital signature applications, where a
large file must be "compressed" in a secure manner before being
encrypted with a private (secret) key under a public-key cryptosystem
such as RSA.
The MD5 algorithm is designed to be quite fast on 32-bit machines. In
addition, the MD5 algorithm does not require any large substitution
tables; the algorithm can be coded quite compactly.
The MD5 algorithm is an extension of the MD4 message-digest algorithm
1,2]. MD5 is slightly slower than MD4, but is more "conservative" in
design. MD5 was designed because it was felt that MD4 was perhaps
being adopted for use more quickly than justified by the existing
critical review; because MD4 was designed to be exceptionally fast,
it is "at the edge" in terms of risking successful cryptanalytic
attack. MD5 backs off a bit, giving up a little in speed for a much
greater likelihood of ultimate security. It incorporates some
suggestions made by various reviewers, and contains additional
optimizations. The MD5 algorithm is being placed in the public domain
for review and possible adoption as a standard.
2. Terminology and Notation
In this document a "word" is a 32-bit quantity and a "byte" is an
eight-bit quantity. A sequence of bits can be interpreted in a
natural manner as a sequence of bytes, where each consecutive group
of eight bits is interpreted as a byte with the high-order (most
significant) bit of each byte listed first. Similarly, a sequence of
bytes can be interpreted as a sequence of 32-bit words, where each
consecutive group of four bytes is interpreted as a word with the
low-order (least significant) byte given first.
Let x_i denote "x sub i". If the subscript is an expression, we
surround it in braces, as in x_{i+1}. Similarly, we use ^ for
superscripts (exponentiation), so that x^i denotes x to the i-th power.
Let the symbol "+" denote addition of words (i.e., modulo-2^32
addition). Let X <<< s denote the 32-bit value obtained by circularly
shifting (rotating) X left by s bit positions. Let not(X) denote the
bit-wise complement of X, and let X v Y denote the bit-wise OR of X
and Y. Let X xor Y denote the bit-wise XOR of X and Y, and let XY
denote the bit-wise AND of X and Y.
3. MD5 Algorithm Description
We begin by supposing that we have a b-bit message as input, and that
we wish to find its message digest. Here b is an arbitrary
nonnegative integer; b may be zero, it need not be a multiple of
eight, and it may be arbitrarily large. We imagine the bits of the
message written down as follows: m_0 m_1 ... m_{b-1}
The following five steps are performed to compute the message digest
of the message.
3.1 Step 1. Append Padding Bits
The message is "padded" (extended) so that its length (in bits) is
congruent to 448, modulo 512. That is, the message is extended so
that it is just 64 bits shy of being a multiple of 512 bits long.
Padding is always performed, even if the length of the message is
already congruent to 448, modulo 512.
Padding is performed as follows: a single "1" bit is appended to the
message, and then "0" bits are appended so that the length in bits of
the padded message becomes congruent to 448, modulo 512. In all, at
least one bit and at most 512 bits are appended.
3.2 Step 2. Append Length
A 64-bit representation of b (the length of the message before the
padding bits were added) is appended to the result of the previous
step. In the unlikely event that b is greater than 2^64, then only
the low-order 64 bits of b are used. (These bits are appended as two
32-bit words and appended low-order word first in accordance with the
previous conventions.)
At this point the resulting message (after padding with bits and with
b) has a length that is an exact multiple of 512 bits. Equivalently,
this message has a length that is an exact multiple of 16 (32-bit)
words. Let M[0 ... N-1] denote the words of the resulting message,
where N is a multiple of 16.
3.3 Step 3. Initialize MD Buffer
A four-word buffer (A,B,C,D) is used to compute the message digest.
Here each of A, B, C, D is a 32-bit register. These registers are
initialized to the following values in hexadecimal, low-order bytes first):
word A: 01 23 45 67 word B: 89 ab cd ef
word C: fe dc ba 98 word D: 76 54 32 10
3.4 Step 4. Process Message in 16-Word Blocks
We first define four auxiliary functions that each take as input
three 32-bit words and produce as output one 32-bit word.
F(X,Y,Z) = XY v not(X) Z G(X,Y,Z) = XZ v Y not(Z)
H(X,Y,Z) = X xor Y xor Z I(X,Y,Z) = Y xor (X v not(Z))
In each bit position F acts as a conditional: if X then Y else Z.
The function F could have been defined using + instead of v since XY
and not(X)Z will never have 1's in the same bit position.) It is
interesting to note that if the bits of X, Y, and Z are independent
and unbiased, the each bit of F(X,Y,Z) will be independent and unbiased.
The functions G, H, and I are similar to the function F, in that they
act in "bitwise parallel" to produce their output from the bits of X,
Y, and Z, in such a manner that if the corresponding bits of X, Y,
and Z are independent and unbiased, then each bit of G(X,Y,Z),
H(X,Y,Z), and I(X,Y,Z) will be independent and unbiased. Note that
the function H is the bit-wise "xor" or "parity" function of its inputs.
This step uses a 64-element table T[1 ... 64] constructed from the
sine function. Let T[i] denote the i-th element of the table, which
is equal to the integer part of 4294967296 times abs(sin(i)), where i
is in radians. The elements of the table are given in the appendix.
Do the following:
//Process each 16-word block.
For i = 0 to N/16-1 do // Copy block i into X.
For j = 0 to 15 do
Set X[j] to M[i*16+j].
end //of loop on j
// Save A as AA, B as BB, C as CC, and D as DD.
AA = A BB = B
CC = C DD = D
// Round 1.
// Let [abcd k s i] denote the operation
// a = b + ((a + F(b,c,d) + X[k] + T[i]) <<< s).
// Do the following 16 operations.
[ABCD 0 7 1] [DABC 1 12 2] [CDAB 2 17 3] [BCDA 3 22 4]
[ABCD 4 7 5] [DABC 5 12 6] [CDAB 6 17 7] [BCDA 7 22 8]
[ABCD 8 7 9] [DABC 9 12 10] [CDAB 10 17 11] [BCDA 11 22 12]
[ABCD 12 7 13] [DABC 13 12 14] [CDAB 14 17 15] [BCDA 15 22 16]
// Round 2.
// Let [abcd k s i] denote the operation
// a = b + ((a + G(b,c,d) + X[k] + T[i]) <<< s).
// Do the following 16 operations.
[ABCD 1 5 17] [DABC 6 9 18] [CDAB 11 14 19] [BCDA 0 20 20]
[ABCD 5 5 21] [DABC 10 9 22] [CDAB 15 14 23] [BCDA 4 20 24]
[ABCD 9 5 25] [DABC 14 9 26] [CDAB 3 14 27] [BCDA 8 20 28]
[ABCD 13 5 29] [DABC 2 9 30] [CDAB 7 14 31] [BCDA 12 20 32]
// Round 3.
// Let [abcd k s t] denote the operation
// a = b + ((a + H(b,c,d) + X[k] + T[i]) <<< s).
// Do the following 16 operations.
[ABCD 5 4 33] [DABC 8 11 34] [CDAB 11 16 35] [BCDA 14 23 36]
[ABCD 1 4 37] [DABC 4 11 38] [CDAB 7 16 39] [BCDA 10 23 40]
[ABCD 13 4 41] [DABC 0 11 42] [CDAB 3 16 43] [BCDA 6 23 44]
[ABCD 9 4 45] [DABC 12 11 46] [CDAB 15 16 47] [BCDA 2 23 48]
// Round 4.
// Let [abcd k s t] denote the operation
// a = b + ((a + I(b,c,d) + X[k] + T[i]) <<< s).
// Do the following 16 operations.
[ABCD 0 6 49] [DABC 7 10 50] [CDAB 14 15 51] [BCDA 5 21 52]
[ABCD 12 6 53] [DABC 3 10 54] [CDAB 10 15 55] [BCDA 1 21 56]
[ABCD 8 6 57] [DABC 15 10 58] [CDAB 6 15 59] [BCDA 13 21 60]
[ABCD 4 6 61] [DABC 11 10 62] [CDAB 2 15 63] [BCDA 9 21 64]
// Then perform the following additions. (That is increment each
// of the four registers by the value it had before this block
// was started.)
A = A + AA B = B + BB C = C + CC D = D + DD
end // of loop on i
3.5 Step 5. Output
The message digest produced as output is A, B, C, D. That is, we
begin with the low-order byte of A, and end with the high-order byte of D.
This completes the description of MD5.
Summary
The MD5 message-digest algorithm is simple to implement, and provides
a "fingerprint" or message digest of a message of arbitrary length.
It is conjectured that the difficulty of coming up with two messages
having the same message digest is on the order of 2^64 operations,
and that the difficulty of coming up with any message having a given
message digest is on the order of 2^128 operations. The MD5 algorithm
has been carefully scrutinized for weaknesses. It is, however, a
relatively new algorithm and further security analysis is of course
justified, as is the case with any new proposal of this sort.
5. Differences Between MD4 and MD5
The following are the differences between MD4 and MD5:
1. A fourth round has been added.
2. Each step now has a unique additive constant.
3. The function g in round 2 was changed from (XY v XZ v YZ) to
(XZ v Y not(Z)) to make g less symmetric.
4. Each step now adds in the result of the previous step. This
promotes a faster "avalanche effect".
5. The order in which input words are accessed in rounds 2 and
3 is changed, to make these patterns less like each other.
6. The shift amounts in each round have been approximately
optimized, to yield a faster "avalanche effect." The shifts in
different rounds are distinct.
References
[1] Rivest, R., "The MD4 Message Digest Algorithm", RFC 1320, MIT and
RSA Data Security, Inc., April 1992.
[2] Rivest, R., "The MD4 message digest algorithm", in A.J. Menezes
and S.A. Vanstone, editors, Advances in Cryptology - CRYPTO '90
Proceedings, pages 303-311, Springer-Verlag, 1991.
[3] CCITT Recommendation X.509 (1988), "The Directory -
Authentication Framework."APPENDIX A - Reference Implementation
The level of security discussed in this memo is considered to be
sufficient for implementing very high security hybrid digital-
signature schemes based on MD5 and a public-key cryptosystem.
Author's Address
Ronald L. Rivest Massachusetts Institute of Technology
Laboratory for Computer Science NE43-324 545 Technology Square
Cambridge, MA 02139-1986 Phone: (617) 253-5880
EMail: rivest@theory.lcs.mit.edu
*****************************************************************************************/
class CMD5Checksum
{
public:
//interface functions for the RSA MD5 calculation
static string GetMD5(const unsigned char* pBuf, unsigned long nLength);
static string GetMD5(ifstream& File);
static string GetMD5(const string& strFilePath);
protected:
//constructor/destructor
CMD5Checksum();
virtual ~CMD5Checksum() {};
//RSA MD5 implementation
void Transform(const unsigned char Block[64]);
void Update(const unsigned char* Input, unsigned long nInputLen);
string Final();
inline unsigned long RotateLeft(unsigned long x, int n);
inline void FF( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T);
inline void GG( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T);
inline void HH( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T);
inline void II( unsigned long& A, unsigned long B, unsigned long C, unsigned long D, unsigned long X, unsigned long S, unsigned long T);
//utility functions
inline void DWordToByte(unsigned char* Output, unsigned long* Input, unsigned long nLength);
inline void ByteToDWord(unsigned long* Output, const unsigned char* Input, unsigned long nLength);
private:
unsigned char m_lpszBuffer[64]; //input buffer
unsigned long m_nCount[2]; //number of bits, modulo 2^64 (lsb first)
unsigned long m_lMD5[4]; //MD5 checksum
};
#endif // !defined(AFX_MD5CHECKSUM_H__2BC7928E_4C15_11D3_B2EE_A4A60E20D2C3__INCLUDED_)
|