C++ Checksum algorithm for File Transfer - c++

I have been asked to create a checksum algorithm for a file transfer, the C++ code I have been given is as follows:
// ChecksumTestTool.cpp : Defines the entry point for the console
application.
//
#include "stdafx.h"
#include <string>
#include <stdio.h>
#include <iostream>
unsigned long CalculateChecksum(FILE* pFile);
int main(int argc, char *argv[])
{
int result = 0;
//Get filename from command args
std::string fileName;
if (argc >= 1)
{
fileName = argv[0];
//Open file with read access
FILE* pFile = nullptr;
int error = fopen_s(&pFile, fileName.c_str(), "r");
if (error != 0 || pFile == nullptr)
{
printf("Failed to open file with error %d\r\n", error);
result = -1;
}
else
{
//Calculate the checksum
unsigned long checksum = CalculateChecksum(pFile);
printf("Calculated Checksum for %s is %lu (0x%04X)\r\n",
fileName.c_str(), checksum, checksum);
}
}
else
{
printf("Must enter filename on command line\r\n");
result = -1;
}
//Wait here so we can see result
printf("\r\nPress Any Key to Exit\r\n");
getchar();
return 0;
}
unsigned long CalculateChecksum(FILE* pFile)
{
unsigned long checksum = 0;
//TODO:: Calculate the checksum
return checksum;
}
I need to create the checksum at the point '//TODO:: Calculate the checksum'. The algorithm need to check whether the file transfers or not.
So far I have tried:
unsigned long CalculateChecksum(FILE* pFile)
{
unsigned long checksum = 0;
//TODO:: Calculate the checksum
unsigned long word = 0;
while (file.read(reinterpret_cast<char*>(&word), sizeof(word))); {
checksum += word;
}
if (file.gcount()); {
word &= (~0U >> ((sizeof(unsigned long) - file.gcount()) * 8));
checksum += word;
}
return checksum;
}
and I get errors saying 'file' is an undeclared identifier and that left '.gcount' must have class/struct/union
I have searched around for multiple checksums and this algorithm is the only one I found that works within this code

Some things:
you pass a variable called pFile to the function, within the function you use file.
You use if(expression);, therefore the part after the if will always be executed, as the if() has no influence whatsoever.
I didn't even consider whether the checksum function works, but when you do
if(term);
{
// Do something
}
the Do something will always be reached. It should rather be
if (term)
{
// Do something
}
so it will only do it if the term evaluates true

Related

EOF sign in the middle of a textfile [duplicate]

I am writing a XOR encryption program which works fine during encryption but during decryption
the
char ca2=fgetc(f);
gets stuck at one point and no decryption takes place after that my best guess about the problem is (the encrypted file contains all sorts of characters ) as soon as fgetc reaches EOF mark which can be present before the actual end of the file it gets stuck there and stop reading the next characters .
is this some kind of limitation of getc() ? here is my rubbish code
int get_file_size(char filename[])
{
FILE *p_file = NULL;
p_file = fopen(filename,"rb");
fseek(p_file,0,SEEK_END);
int size = ftell(p_file);
fclose(p_file);
return size;
}
int endec(char filename[],char psdw[])
{
FILE *f;
int hashed=0,ed=0;
int inphash=inhash(psdw);
inphash=inphash%50;
f=fopen(filename,"r");
if(f==NULL)
printf("failed");
char temps[999999];
long int crs=0,j=0;
int filesz=get_file_size(filename);
printf("file size = %d\n\n",filesz);
while(1){
inphash=inphash+2;
char ca=(char)inphash;
char ca2=fgetc(f);
printf("%c\n",ca2);
if(crs>=filesz)
break;
temps[crs]= ca2 ^ ca;
crs++;
}
fclose(f);
printf("%d",strlen(temps));
FILE *fp;
fp=fopen(filename,"wt");
for(j=0;j<crs;j++){
putc (temps[j] , fp);
printf("%c",temps[j]);
}
fclose(fp);
}
Your problem is right here:
f=fopen(filename,"r");
You open the file for text reading, not for binary. Your file size function gets it right, but your decoder function does not.
The idiomatic way to read a file character by character using the C-style IO routines is like this:
f = fopen(filename, "rb");
if (!f)
// handle error
int c; // NOTE: int, not char!
while ( (c = fgetc(f)) != EOF )
{
// do something with 'c'
}
This idiom does not require you to get the file size as a separate operation. You can rewrite your XOR "encryption" routine with a simple loop of the above form. It will be much clearer and more concise.
Your entire decoder function could be rewritten as follows: (minus the debug code)
int endec(char filename[], char psdw[])
{
int inphash = inhash(psdw) % 50;
char temp[999999]; // really, should be std::vector<char>
FILE *f;
if ( (f = fopen(filename, "rb")) == NULL )
{
printf("opening for read failed\n");
return -1;
}
size_t crs = 0;
int c;
while ( (c = fgetc(f)) != EOF )
{
inphash += 2;
temp[crs++] = (char)(inphash ^ c);
}
fclose(f);
if ( (f = fopen(filename, "wt")) == NULL )
{
printf("opening for write failed\n");
return -1;
}
if (fwrite(temp, crs, 1, f) != crs)
{
printf("short write\n");
fclose(f);
return -1;
}
fclose(f);
return 0;
}
Not stellar error handling, but it is error handling.

OpenSSL SHA256 Wrong result

I have following piece of code that is supposed to calculate the SHA256 of a file. I am reading the file chunk by chunk and using EVP_DigestUpdate for the chunk. When I test the code with the file that has content
Test Message
Hello World
in Windows, it gives me SHA256 value of 97b2bc0cd1c3849436c6532d9c8de85456e1ce926d1e872a1e9b76a33183655f but the value is supposed to be 318b20b83a6730b928c46163a2a1cefee4466132731c95c39613acb547ccb715, which can be verified here too.
Here is the code:
#include <openssl\evp.h>
#include <iostream>
#include <string>
#include <fstream>
#include <cstdio>
const int MAX_BUFFER_SIZE = 1024;
std::string FileChecksum(std::string, std::string);
int main()
{
std::string checksum = FileChecksum("C:\\Users\\Dell\\Downloads\\somefile.txt","sha256");
std::cout << checksum << std::endl;
return 0;
}
std::string FileChecksum(std::string file_path, std::string algorithm)
{
EVP_MD_CTX *mdctx;
const EVP_MD *md;
unsigned char md_value[EVP_MAX_MD_SIZE];
int i;
unsigned int md_len;
OpenSSL_add_all_digests();
md = EVP_get_digestbyname(algorithm.c_str());
if(!md) {
printf("Unknown message digest %s\n",algorithm);
exit(1);
}
mdctx = EVP_MD_CTX_create();
std::ifstream readfile(file_path,std::ifstream::in|std::ifstream::binary);
if(!readfile.is_open())
{
std::cout << "COuldnot open file\n";
return 0;
}
readfile.seekg(0, std::ios::end);
long filelen = readfile.tellg();
std::cout << "LEN IS " << filelen << std::endl;
readfile.seekg(0, std::ios::beg);
if(filelen == -1)
{
std::cout << "Return Null \n";
return 0;
}
EVP_DigestInit_ex(mdctx, md, NULL);
long temp_fil = filelen;
while(!readfile.eof() && readfile.is_open() && temp_fil>0)
{
int bufferS = (temp_fil < MAX_BUFFER_SIZE) ? temp_fil : MAX_BUFFER_SIZE;
char *buffer = new char[bufferS+1];
buffer[bufferS] = 0;
readfile.read(buffer, bufferS);
std::cout << strlen(buffer) << std::endl;
EVP_DigestUpdate(mdctx, buffer, strlen(buffer));
temp_fil -= bufferS;
delete[] buffer;
}
EVP_DigestFinal_ex(mdctx, md_value, &md_len);
EVP_MD_CTX_destroy(mdctx);
printf("Digest is: ");
//char *checksum_msg = new char[md_len];
//int cx(0);
for(i = 0; i < md_len; i++)
{
//_snprintf(checksum_msg+cx,md_len-cx,"%02x",md_value[i]);
printf("%02x", md_value[i]);
}
//std::string res(checksum_msg);
//delete[] checksum_msg;
printf("\n");
/* Call this once before exit. */
EVP_cleanup();
return "";
}
I tried to write the hash generated by program as string using _snprintf but it didn't worked. How can I generate the correct hash and return the value as string from FileChecksum Function? Platform is Windows.
EDIT: It seems the problem was because of CRLF issue. As Windows in saving file using \r\n, the Checksum calculated was different. How to handle this?
MS-DOS used the CR-LF convention,So basically while saving the file in windows, \r\n comes in effect for carriage return and newline. And while testing on online (given by you), only \n character comes in effect.
Thus either you have to check the checksum of Test Message\r\nHello World\r\n in string which is equivalent to creating and reading file in windows(as given above), which is the case here.
However, the checksum of files,wherever created, will be same.
Note: your code works fine :)
It seems the problem was associated with the value of length I passed in EVP_DigestUpdate. I had passed value from strlen, but replacing it with bufferS did fixed the issue.
The code was modified as:
while(!readfile.eof() && readfile.is_open() && temp_fil>0)
{
int bufferS = (temp_fil < MAX_BUFFER_SIZE) ? temp_fil : MAX_BUFFER_SIZE;
char *buffer = new char[bufferS+1];
buffer[bufferS] = 0;
readfile.read(buffer, bufferS);
EVP_DigestUpdate(mdctx, buffer, bufferS);
temp_fil -= bufferS;
delete[] buffer;
}
and to send the checksum string, I modified the code as:
EVP_DigestFinal_ex(mdctx, md_value, &md_len);
EVP_MD_CTX_destroy(mdctx);
char str[128] = { 0 };
char *ptr = str;
std::string ret;
for(i = 0; i < md_len; i++)
{
//_snprintf(checksum_msg+cx,md_len-cx,"%02x",md_value[i]);
sprintf(ptr,"%02x", md_value[i]);
ptr += 2;
}
ret = str;
/* Call this once before exit. */
EVP_cleanup();
return ret;
As for the wrong checksum earlier, the problem was associated in how windows keeps the line feed. As suggested by Zangetsu, Windows was making text file as CRLF, but linux and the site I mentioned earlier was using LF. Thus there was difference in the checksum value. For files other than text, eg dll the code now computes correct checksum as string

stack check fail in sha-1 c++

I'm having a __stack_chk_fail in the main thread.
I have no idea why is this happening?
I got the codes from this website:
http://www.packetizer.com/security/sha1/
Im trying to add a function to compute the digest of a file using the example.
.h file
#include <stdio.h>
#include <string>
std::string digestFile( char *filename );
.cpp file
std::string SHA1::digestFile( char *filename )
{
Reset();
FILE *fp = NULL;
if (!(fp = fopen(filename, "rb")))
{
printf("sha: unable to open file %s\n", filename);
return NULL;
}
char c = fgetc(fp);
while(!feof(fp))
{
Input(c);
c = fgetc(fp);
}
fclose(fp);
unsigned message_digest[5];
if (!Result(message_digest))
{ printf("sha: could not compute message digest for %s\n", filename); }
std::string hash;
for (int i = 0; i < 5; i++)
{
char buffer[8];
int count = sprintf(buffer, "%08x", message_digest[i]);
if (count != 8)
{ printf("converting unsiged to char ERROR"); }
hash.append(buffer);
}
return hash;
}
__stack_chk_fail occurs when you write to invalid address.
It turns out you do:
char buffer[8];
int count = sprintf(buffer, "%08x", message_digest[i]);
C strings are NUL-terminated. That means that when sprintf writes 8 digits, it adds 9-th char, '\0'. But buffer only has space for 8 chars, so the 9-th goes past the end of the buffer.
You need char buffer[9]. Or do it the C++ way with std::stringstream, which does not involve any fixed sizes and thus no risk of buffer overrun.

How to read past EOF from getc?

I am writing a XOR encryption program which works fine during encryption but during decryption
the
char ca2=fgetc(f);
gets stuck at one point and no decryption takes place after that my best guess about the problem is (the encrypted file contains all sorts of characters ) as soon as fgetc reaches EOF mark which can be present before the actual end of the file it gets stuck there and stop reading the next characters .
is this some kind of limitation of getc() ? here is my rubbish code
int get_file_size(char filename[])
{
FILE *p_file = NULL;
p_file = fopen(filename,"rb");
fseek(p_file,0,SEEK_END);
int size = ftell(p_file);
fclose(p_file);
return size;
}
int endec(char filename[],char psdw[])
{
FILE *f;
int hashed=0,ed=0;
int inphash=inhash(psdw);
inphash=inphash%50;
f=fopen(filename,"r");
if(f==NULL)
printf("failed");
char temps[999999];
long int crs=0,j=0;
int filesz=get_file_size(filename);
printf("file size = %d\n\n",filesz);
while(1){
inphash=inphash+2;
char ca=(char)inphash;
char ca2=fgetc(f);
printf("%c\n",ca2);
if(crs>=filesz)
break;
temps[crs]= ca2 ^ ca;
crs++;
}
fclose(f);
printf("%d",strlen(temps));
FILE *fp;
fp=fopen(filename,"wt");
for(j=0;j<crs;j++){
putc (temps[j] , fp);
printf("%c",temps[j]);
}
fclose(fp);
}
Your problem is right here:
f=fopen(filename,"r");
You open the file for text reading, not for binary. Your file size function gets it right, but your decoder function does not.
The idiomatic way to read a file character by character using the C-style IO routines is like this:
f = fopen(filename, "rb");
if (!f)
// handle error
int c; // NOTE: int, not char!
while ( (c = fgetc(f)) != EOF )
{
// do something with 'c'
}
This idiom does not require you to get the file size as a separate operation. You can rewrite your XOR "encryption" routine with a simple loop of the above form. It will be much clearer and more concise.
Your entire decoder function could be rewritten as follows: (minus the debug code)
int endec(char filename[], char psdw[])
{
int inphash = inhash(psdw) % 50;
char temp[999999]; // really, should be std::vector<char>
FILE *f;
if ( (f = fopen(filename, "rb")) == NULL )
{
printf("opening for read failed\n");
return -1;
}
size_t crs = 0;
int c;
while ( (c = fgetc(f)) != EOF )
{
inphash += 2;
temp[crs++] = (char)(inphash ^ c);
}
fclose(f);
if ( (f = fopen(filename, "wt")) == NULL )
{
printf("opening for write failed\n");
return -1;
}
if (fwrite(temp, crs, 1, f) != crs)
{
printf("short write\n");
fclose(f);
return -1;
}
fclose(f);
return 0;
}
Not stellar error handling, but it is error handling.

Generate SHA hash in C++ using OpenSSL library

How can I generate SHA1 or SHA2 hashes using the OpenSSL libarary?
I searched google and could not find any function or example code.
From the command line, it's simply:
printf "compute sha1" | openssl sha1
You can invoke the library like this:
#include <stdio.h>
#include <string.h>
#include <openssl/sha.h>
int main()
{
unsigned char ibuf[] = "compute sha1";
unsigned char obuf[20];
SHA1(ibuf, strlen(ibuf), obuf);
int i;
for (i = 0; i < 20; i++) {
printf("%02x ", obuf[i]);
}
printf("\n");
return 0;
}
OpenSSL has a horrible documentation with no code examples, but here you are:
#include <openssl/sha.h>
bool simpleSHA256(void* input, unsigned long length, unsigned char* md)
{
SHA256_CTX context;
if(!SHA256_Init(&context))
return false;
if(!SHA256_Update(&context, (unsigned char*)input, length))
return false;
if(!SHA256_Final(md, &context))
return false;
return true;
}
Usage:
unsigned char md[SHA256_DIGEST_LENGTH]; // 32 bytes
if(!simpleSHA256(<data buffer>, <data length>, md))
{
// handle error
}
Afterwards, md will contain the binary SHA-256 message digest. Similar code can be used for the other SHA family members, just replace "256" in the code.
If you have larger data, you of course should feed data chunks as they arrive (multiple SHA256_Update calls).
Adaptation of #AndiDog version for big file:
static const int K_READ_BUF_SIZE{ 1024 * 16 };
std::optional<std::string> CalcSha256(std::string filename)
{
// Initialize openssl
SHA256_CTX context;
if(!SHA256_Init(&context))
{
return std::nullopt;
}
// Read file and update calculated SHA
char buf[K_READ_BUF_SIZE];
std::ifstream file(filename, std::ifstream::binary);
while (file.good())
{
file.read(buf, sizeof(buf));
if(!SHA256_Update(&context, buf, file.gcount()))
{
return std::nullopt;
}
}
// Get Final SHA
unsigned char result[SHA256_DIGEST_LENGTH];
if(!SHA256_Final(result, &context))
{
return std::nullopt;
}
// Transform byte-array to string
std::stringstream shastr;
shastr << std::hex << std::setfill('0');
for (const auto &byte: result)
{
shastr << std::setw(2) << (int)byte;
}
return shastr.str();
}
correct syntax at command line should be
echo -n "compute sha1" | openssl sha1
otherwise you'll hash the trailing newline character as well.
Here is OpenSSL example of calculating sha-1 digest using BIO:
#include <openssl/bio.h>
#include <openssl/evp.h>
std::string sha1(const std::string &input)
{
BIO * p_bio_md = nullptr;
BIO * p_bio_mem = nullptr;
try
{
// make chain: p_bio_md <-> p_bio_mem
p_bio_md = BIO_new(BIO_f_md());
if (!p_bio_md) throw std::bad_alloc();
BIO_set_md(p_bio_md, EVP_sha1());
p_bio_mem = BIO_new_mem_buf((void*)input.c_str(), input.length());
if (!p_bio_mem) throw std::bad_alloc();
BIO_push(p_bio_md, p_bio_mem);
// read through p_bio_md
// read sequence: buf <<-- p_bio_md <<-- p_bio_mem
std::vector<char> buf(input.size());
for (;;)
{
auto nread = BIO_read(p_bio_md, buf.data(), buf.size());
if (nread < 0) { throw std::runtime_error("BIO_read failed"); }
if (nread == 0) { break; } // eof
}
// get result
char md_buf[EVP_MAX_MD_SIZE];
auto md_len = BIO_gets(p_bio_md, md_buf, sizeof(md_buf));
if (md_len <= 0) { throw std::runtime_error("BIO_gets failed"); }
std::string result(md_buf, md_len);
// clean
BIO_free_all(p_bio_md);
return result;
}
catch (...)
{
if (p_bio_md) { BIO_free_all(p_bio_md); }
throw;
}
}
Though it's longer than just calling SHA1 function from OpenSSL, but it's more universal and can be reworked for using with file streams (thus processing data of any length).
C version of #Nayfe code, generating SHA1 hash from file:
#include <stdio.h>
#include <openssl/sha.h>
static const int K_READ_BUF_SIZE = { 1024 * 16 };
unsigned char* calculateSHA1(char *filename)
{
if (!filename) {
return NULL;
}
FILE *fp = fopen(filename, "rb");
if (fp == NULL) {
return NULL;
}
unsigned char* sha1_digest = malloc(sizeof(char)*SHA_DIGEST_LENGTH);
SHA_CTX context;
if(!SHA1_Init(&context))
return NULL;
unsigned char buf[K_READ_BUF_SIZE];
while (!feof(fp))
{
size_t total_read = fread(buf, 1, sizeof(buf), fp);
if(!SHA1_Update(&context, buf, total_read))
{
return NULL;
}
}
fclose(fp);
if(!SHA1_Final(sha1_digest, &context))
return NULL;
return sha1_digest;
}
It can be used as follows:
unsigned char *sha1digest = calculateSHA1("/tmp/file1");
The res variable contains the sha1 hash.
You can print it on the screen using the following for-loop:
char *sha1hash = (char *)malloc(sizeof(char) * 41);
sha1hash[40] = '\0';
int i;
for (i = 0; i < SHA_DIGEST_LENGTH; i++)
{
sprintf(&sha1hash[i*2], "%02x", sha1digest[i]);
}
printf("SHA1 HASH: %s\n", sha1hash);