what is wrong with the following code

问题

The following function gets file offsets from the rabin_polynomial structure, opens the input_file for md5 fingerprint generation and writes the result to fpfile

My problem is it seems to use the same chunk_buffer content some times that it generates similar fingerprints for chunks with different legths.

What could be the reason?

I have tested the md5 function with other inputs separately and it generates correct digests.

   int write_rabin_fingerprints_to_binary_file(FILE *fpfile,FILE *input_file,
    struct rabin_polynomial *head)
{        
    struct rabin_polynomial *poly=head;
    unsigned char fing_print[33]={'\0'};
    size_t bytes_read;
      while(poly != NULL)
        {    
       char *chunk_buffer;
       chunk_buffer = (char*) malloc ((poly->length));  
       bytes_read=fread (chunk_buffer,1, poly->length,input_file);          
               if(bytes_read!=poly->length)
                {
                   printf("Error reading from%s ",input_file);
                   return -1;
                }
       strncpy((char*)fing_print,md5(chunk_buffer).c_str(),32);     
       size_t ret_val=fprintf(fpfile, "%llu\t%lu\t%s\n",poly->start,
                                       poly->length,fing_print);

              if(ret_val == 0)
               {
                  fprintf(stderr, "Could not write rabin polynomials to file.");
                  return -1;
               }

         poly=poly->next_polynomial;
      free(chunk_buffer);
        }

   return 0;
}

EDIT:

I am running this program using visual studio 2010. Could typecasting to char * in the malloc() line create the problem?

The number of bytes read is just as specified in the argument.

回答1:

There was nothing wrong in the code to cause such faults. I just found out that it happened because of zero-length strings which are also called as file holes.

回答2:

   int write_rabin_fingerprints_to_binary_file(FILE *fpfile,FILE *input_file
     , struct rabin_polynomial *head)
{        
    struct rabin_polynomial *poly;
    unsigned char fing_print[33];

    for (poly=head; poly != NULL;poly=poly->next_polynomial )   {    
       char *chunk_buffer;
       int retval;

       chunk_buffer = malloc (1+poly->length);  
       retval = fread (chunk_buf,1, poly->length,input_file);

            /* check retval here */

       chunk_buff[poly->length] = 0;     
       strncpy(fing_print,md5(chunk_buffer).c_str(), sizeof fing_print);
       fing_print[sizeof fing_print -1] = 0;
       retval = fprintf(fpfile, "%llu\t%lu\t%s\n"
                      ,poly->start, poly->length, fing_print);

              if(retval <= 0)
               {
                  fprintf(stderr, "Could not write rabin polynomials to file.");
                  return -1;
               }
        free(chunk_buffer);
        }

   return 0;
}

来源：https://stackoverflow.com/questions/9633322/what-is-wrong-with-the-following-code

标签

malloc

md5

collision

fingerprint