Question

I am writing a simple program to flip all the bits in a file, but right now it only does the first 1000 bytes until I get that much working. Why does my call to read() ignore \r characters? When I run this code on a file that only contains \r\n\r\n, the read call returns 2 and the buffer contains \n\n. The \r characters are completely ignored. I’m running this on Windows (this wouldn’t even be an issue on Linux machines)

Why does read(2) skip over the \r character when it finds it? Or is that what is happening?

EDIT: Conclusion is that windows defaults to opening files in “text” mode as opposed to “binary” mode. For this reason, when calling open, we must specify O_BINARY as the mode.

Thanks, code below.

#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <sys/stat.h>
#include <fcntl.h>

void invertBytes(size_t amount, char* buffer);

int main(int argv, char** argc)
{
   int fileCount = 1;
   char* fileName;
   int fd = 0;
   size_t bufSize = 1000;
   size_t amountRead = 0;
   char* text;
   int offset = 0;

   if(argv <= 1)
   {
      printf("Usages: encode [filenames...]\n");
      return 0;
   }

   text = (char *)malloc(sizeof(char) * bufSize);

   for(fileCount = 1; fileCount < argv; fileCount++)
   {
      fileName = argc[fileCount];
      fd = open(fileName, O_RDWR);
      printf("fd: %d\n", fd);
      amountRead = read(fd, (void *)text, bufSize);
      printf("Amount read: %d\n", amountRead);
      invertBytes(amountRead, text);
      offset = (int)lseek(fd, 0, SEEK_SET);
      printf("Lseek to %d\n", offset);
      offset = write(fd, text, amountRead);
      printf("write returned %d\n", offset);
      close(fd);
   }

   return 0;
}

void invertBytes(size_t amount, char* buffer)
{
   int byteCount = 0;
   printf("amount: %d\n", amount);
   for(byteCount = 0; byteCount < amount; byteCount++)
   {
      printf("%x, ", buffer[byteCount]);
      buffer[byteCount] = ~buffer[byteCount];
      printf("%x\r\n", buffer[byteCount]);
   }
   printf("byteCount: %d\n", byteCount);
}

Answer 1

fd = open(fileName, O_RDWR);

should be

fd = open(fileName, O_RDWR | O_BINARY);

See read() only reads a few bytes from file for details.