Why my levenshtein distance calculator fails with PDF file?

I'm trying to create a program that calculate edit distance between two files. I read with the funcution fread and I use the code to read binary ("rb"). I put in input two PDF files and during the debug I found out that when I try to fill the matrix of the Levenshtein distance algorithm I get a "SIGSEGV (Segmentation fault)" at char n° 1354 of the first file and the program exit with:

Process finished with exit code -1073741819 (0xC0000005)

I controlled and char n° 1354 is \n .

The code that I use to read the files is:

long getFileSize(FILE *file) {
long int size;
fseek(file, 0, SEEK_END);
size = ftell(file);
fseek(file, 0, SEEK_SET);
return size;
}

char *readFromBinary(char *path) {
FILE *file;
file = fopen(path, "rb");
if (file == NULL)
    printf("Error!\n");

long fileSize = getFileSize(file);
char *buffer = malloc((fileSize + 1) * sizeof(char));

fread(buffer, sizeof(char), fileSize, file);
return buffer;
}

This is the code that I use to calculate the edit distance:

int calculateDistance(char *pathFile1, char *pathFile2, int choice, char *path) {
FILE *f1 = fopen(pathFile1, "rb");
FILE *f2 = fopen(pathFile2, "rb");
char *contentFile1 = readFromBinary(pathFile1);
char *contentFile2 = readFromBinary(pathFile2);

int distance = 0;
int dim1 = getFileSize(f1);
int dim2 = getFileSize(f2);

int **matrix = constructMatrix(dim1, dim2);
fillMatrix(matrix, dim1, dim2, contentFile1, contentFile2);

distance = matrix[dim1][dim2];
struct Instruction instruction[distance + 1];

int initActions = initInstructions(matrix, pathFile1, &dim1, pathFile2, &dim2, instruction);
endInstructions(pathFile1, &dim1, pathFile2, &dim2, instruction, initActions);

if (choice == 1)
    printOnFile(instruction, distance, path);

for (int i = 0; i <= dim1; i++)
    free(matrix[i]);
free(matrix);

if (numberOfDivisions > 0)
    numberOfDivisions--;

return distance;
}

And this is the code that i use to create and fill the matrix:

int **constructMatrix(int dim1, int dim2) {
//matrice di puntatori
int **matrice = (int **) malloc((dim1 + 1) * sizeof(int *));

//matrice di puntatori
for (int i = 0; i <= dim1; i++)
    matrice[i] = (int *) malloc((dim2 + 1) * sizeof(int));

return matrice;
}

 void fillMatrix(int **matrix, int dim1, int dim2, char *file1, char *file2) {
  for (int i = 0; i <= dim1; i++)
    matrix[i][0] = i;
  for (int j = 1; j <= dim2; j++)
    matrix[0][j] = j;
  for (int i = 1; i <= dim1; i++) {
    for (int j = 1; j <= dim2; j++) {
        if (file1[i - 1] != file2[j - 1]) {
            int k = minimum(matrix[i][j - 1], matrix[i - 1][j], matrix[i - 1][j - 1]);
            matrix[i][j] = k + 1;
        } else
            matrix[i][j] = matrix[i - 1][j - 1];
    }
  }
}

In particular the debugger stops in this line of calculateDistance(fillMatrix(matrix, dim1, dim2, contentFile1, contentFile2);), and in this line of fillMatrix(matrix[i][0] = i;) when i=1354.

Information about PDF:

The PDF file is 188671 byte

It has 1355 lines

PS. My program works with txt files.

You're allocating at least 188671 * 1355 * 4 bytes = 1022596820 bytes. You really need to check the return value from malloc to be sure that it was able to allocate successfully.