convert to binary file

Question

I need to convert a text file of the following format to binary file. The input file only contains characters A, B, C or D. 'A' changes to '00','B' changes to '01', C changes to '10', D changes to '11'. Sample input file:

ABBCDA
BBAABCD
BACBB

Sample output file:

000101101100
01010000011011
0100100101

I have wrote the following code, but it doesn't work.

int main()
{
    FILE * fop;
    FILE * fout;
    int length=0;
    int i;
    char buffer[1000];
    fop = fopen("filename.txt","r");
    fout = fopen("filename.bin", "wb");
    while(!feof(fop))
    {
        fgets(buffer,1000,fop);
        length = strlen(buffer)-1;
        for(i=0; i<length; i++)
         {
           if(buffer[i]=='A')
           strcpy(buffer[i],'00');
           if(buffer[i]=='B')
           strcpy(buffer[i],'01');
           if(buffer[i]=='C')
           strcpy(buffer[i],'10');
           if(buffer[i]=='D')
           strcpy(buffer[i],'11'); 
         }
      fwrite(buffer, 1, sizeof(char)*length, fout);
      fwrite("\n",1,sizeof(char),fout);
    }
    fclose(fop);
    fclose(fout);
    return 0;
}

What's wrong? How to solve it? Thank you.

Answer 1

This is the part to be fixed

while(fgets(buffer,1000,fop))
{
    length = strlen(buffer)-1;
    char sout[3];
    for(i=0; i<length; i++)
    {
        *sout = '\0';
        if(buffer[i]=='A')
            strcpy(sout,"00");
        if(buffer[i]=='B')
            strcpy(sout,"01");
        if(buffer[i]=='C')
            strcpy(sout,"10");
        if(buffer[i]=='D')
            strcpy(sout,"11"); 
        fwrite(sout, 1, strlen(sout), fout);
    }
    fwrite("\n",1,sizeof(char),fout);
}

Notes

• the fgets within the while condition
• sout to store temporarily the 2-bits (as string)
• fwrite writes to sout (does not overwrite buffer), and is integrated within the for loop while the writing of \n is outside.

---

Version to write actual bytes (in binary) ...

while(fgets(buffer,1000,fop))
{
    length = strlen(buffer)-1;
    for(i=0; i<length; i++)
    {
        unsigned char byte = 0;
        if(buffer[i]=='A')
            byte = 0x0;
        if(buffer[i]=='B')
            byte = 0x1;
        if(buffer[i]=='C')
            byte = 0x2;
        if(buffer[i]=='D')
            byte = 0x3; 
        fwrite(&byte, 1, 1, fout);
    }
    // no more : fwrite("\n",1,sizeof(char),fout);
}

Using 0x notation to show I'm dealing with binary stuff...

And version David C. Rankin (perfectionist!)

while (fgets (buf, MAXC, fop)) {    /* read each line */
    char *p = buf;                  /* pointer to buf */
    while (*p) {                    /* while not '\0' */
        uint8_t byte = 0;           /* declare byte */
        if ('A' <= *p && *p <= 'Z') /* if char is A-Z */
            byte = *p - 'A';        /* encode 0 - 25 */
        else
            byte = *p;              /* write char as is */
        if (fwrite (&byte, 1, 1, fout) != 1) {   /* validate write */
            fprintf (stderr, "error: write of '%c' failed.\n", *p);
            goto badwrite;          /* jump out of loops on fail */
        }
        p++;    /* increment pointer */
    }
}
badwrite:;

fclose (fop);                /* close input file */
if (fclose (fout) == -1)     /* close/validate output file */
    fprintf (stderr, "error: on fout close.\n");

There is yet some stuff that can be improved, but for now ...