C snippet for taking multiple files in as input and guessing the correct output based off of sheer probability.

guesstimate_correct_file.c

#include <assert.h>
#include <stddef.h>
#include <stdio.h>
#include <limits.h>


/**
  * @return - Element of that list which is the biggest
  * @params len - Lenght of that list
  * @params n - List of ints that you want to search
  **/
size_t biggest(int *n, size_t len) {
  int max = 0;
  for(int i = 0; i < len; i++) {
    if(n[i] > n[max]) {
      max = i;
    }
  }
  return max;
}

int main(int argc, char *argv[]) {
  int retval = 0;
  const size_t filecount = argc - 1;
  FILE *fp[filecount];
  FILE *output = fopen("output.bin", "wb");
  assert(output != NULL);

  // batch open
  for(int i = 0; i < filecount; i++) {
    fp[i] = fopen(argv[1+i], "rb");
    assert(fp[i] != NULL);
  }

  size_t sizes[filecount];
  for(int i = 0; i < filecount; i++) {
    fseek(fp[i], 0, SEEK_END);
    sizes[i] = ftell(fp[i]);
    fseek(fp[i], 0, SEEK_SET);
  }

  size_t average = sizes[0];
  for(int i = 1; i < filecount; i++)
    assert(average == sizes[i]);

  for(int i = 0; i < average; i++) {
    char c[filecount];
    int  n[filecount];
    int  elements = 1;

    for(int j = 0; j < filecount; j++) {
      c[j] = 0;
      n[j] = 0;

      if(j == 0) {
        c[j] = fgetc(fp[j]);
        n[j] = 1;
        continue;
      }

      char new = fgetc(fp[j]);
      for(int k = 0; k <= j; k++) {
        if(c[k] == new) {
          n[k]++;
        } else if (k == j) {
          c[k] = new;
          n[k] = 1;
          elements++;
        }
      }
    }

    int max = biggest(n, elements);
    if(n[max] >= elements/2) {
      fputc(c[max], output);
    } else {
      fprintf(stderr, "Could not find a sane byte at offset %u. Aborting.\n", ftell(output) + 1);
      break;
    }
  }


  fclose(output);

  // batch close
  for(int i = 0; i < filecount; i++) {
    fclose(fp[i]);
  }

  return retval;
}