c++ - Why do I get a 'ÿ' char after every include that is extracted by my parser? - C

Question

I have this function:

/*This func runs *.c1 file, and replace every include file with its content
It will save those changes to *.c2 file*/
void includes_extractor(FILE *c1_fp, char *c1_file_name ,int c1_file_str_len )
{
    int i=0;
    FILE *c2_fp , *header_fp;
    char ch, *c2_file_name,header_name[80]; /* we can assume line length 80 chars MAX*/
    char inc_name[]="include"; 
    char inc_chk[INCLUDE_LEN+1]; /*INCLUDE_LEN is defined | +1 for null*/

    /* making the c2 file name */

    c2_file_name=(char *) malloc ((c1_file_str_len)*sizeof(char));
    if (c2_file_name == NULL)
    {
     printf("Out of memory !
");
     exit(0);
    } 

    strcpy(c2_file_name , c1_file_name); 
    c2_file_name[c1_file_str_len-1] = ''; 
    c2_file_name[c1_file_str_len-2] = '2';

/*Open source & destination files + ERR check */

    if( !(c1_fp = fopen (c1_file_name,"r") ) )
    {
     fprintf(stderr,"
cannot open *.c1 file !
");
     exit(0);
    }

    if( !(c2_fp = fopen (c2_file_name,"w+") ) )
    {
     fprintf(stderr,"
cannot open *.c2 file !
");
     exit(0);
    }

/*next code lines are copy char by char from c1 to c2,
  but if meet header file, copy its content */

    ch=fgetc(c1_fp);
    while (!feof(c1_fp))
    {
        i=0;    /*zero i */ 
        if (ch == '#') /*potential #include case*/
        {
             fgets(inc_chk, INCLUDE_LEN+1, c1_fp); /*8 places for "include" + null*/
         if(strcmp(inc_chk,inc_name)==0) /*case #include*/
         {
          ch=fgetc(c1_fp);
          while(ch==' ') /* stop when head with a '<' or '"' */
          {
           ch=fgetc(c1_fp);
          } /*while(2)*/

          ch=fgetc(c1_fp); /*start read header file name*/

          while((ch!='"') && (ch!='>')) /*until we get the end of header name*/
          {
           header_name[i] = ch;
           i++;
           ch=fgetc(c1_fp);
          }/*while(3)*/
          header_name[i]='';  /*close the header_name array*/


          if( !(header_fp = fopen (header_name,"r") ) ) /*open *.h for read + ERR chk*/
          {
               fprintf(stderr,"cannot open header file !
");
           exit(0);
              }

          while (!feof(header_fp)) /*copy header file content to *.c2 file*/
          {
           ch=fgetc(header_fp);
           fputc(ch,c2_fp);
          }/*while(4)*/
          fclose(header_fp);
         }
                }/*frst if*/
        else
        {
         fputc(ch,c2_fp);
        }
     ch=fgetc(c1_fp);
    }/*while(1)*/ 

fclose(c1_fp);
fclose(c2_fp);
free (c2_file_name);    
}

This function reads a single *.c1 file and saves a copy of it to *.c2 file, but all the include files from *.c1 file are extracted and their contents expanded in *.c2.

After every include file that is extracted, I get '?' sign.

The include can contain 1 line or 1000 lines, but the '?' sign will appear only once after each include that is extracted.

Can't find why...

Answer 1

"ÿ" corresponds to the code point 0xFF. fgetc returns EOF when the end of file is reached, which is (usually) defined as -1. Store -1 in a char and you'll wind up with 0xFF. You must check for EOF between calling fgetc and fpuc.

int ch;
...
/*copy header file content to *.c2 file*/
for (ch=fgetc(header_fp); ch > -1; ch=fgetc(header_fp)) {
   fputc(ch,c2_fp);
}

Instead of getting characters one at a time, you could use fgets to get a block of characters.

#ifndef BUFSIZE
#  define BUFSIZE 1024
#endif
char buf[BUFSIZE], *read;
...
/*copy header file content to *.c2 file*/
while ((read = fgets(buf, BUFSIZE, header_fp))) {
    fputs(buf, c2_fp);
}