How to skip a comment in c programming with using fopen

Question

I want to ignore/skip the comments in a text file when I use fgets.

The problem is that I only can skip a comment if the first character in a line starts is #. Comments starts with # in my text file. But there are some # in my file.txt that are not the first character of a line, like so;

#Paths
A B #Path between A and B.
D C #Path between C and D.

A is my first node, B is my second node and when # comes I want to ignore the rest of text until the next line. My new node should be D and C etc. I can only use "r" in fopen function. I have tried fgets but it reads line by line and fgetc doesn't help either.

    bool ignore_comments(const char *s)
    {
        int i = 0;
        while (s[i] && isspace(s[i])) i++;
        return (i >= 0 && s[i] == '#');
    }
    FILE *file;
    char ch[BUFSIZE];
    file = fopen("e.txt", "r");
    if (file == NULL) {
        printf("Error\n");
        fprintf(stderr, "ERROR: No file input\n");
        exit(EXIT_FAILURE);
    }
    while(fgets(ch, BUFSIZE, file) != NULL)
    {
              if (line_is_comment(ch)) {
                        // Ignore comment lines.
                        continue;
                printf("%c",*ch);
                }
     fscanf(file, "%40[0-9a-zA-Z]s", ch);
....
}

Answer 1

Also method names are different, but am I right with this version ? Ignore my dirty method line_is_comment - from first version unless you want to play with ;-)

Extended test input:

#Paths
A B #Path between A and B.
D C #Path between C and D.
E F
G H

Output:

 rest of line read
AB rest of line read
DC rest of line read
EF rest of line read
GH rest of line read

#include <stdio.h>

bool line_is_comment(const char *s)
{
    char *commentPos = const_cast<char*>(strchr(s, '#'));
    if(commentPos != NULL) {
        *commentPos = 0; // cut-off chars after comment
        //return true; // or false then to accept the line
        return commentPos == s;
    }
    return false;
}

#define BUFSIZE 50

int main()
{
    FILE *file;
    char ch[BUFSIZE];
    file = fopen("e.txt", "r");
    if (file == NULL) {
        printf("Error\n");
        fprintf(stderr, "ERROR: No file input\n");
        exit(EXIT_FAILURE);
    }
    int x;
    while(!feof(file)) {
        x = fscanf(file, "%40[0-9a-zA-Z]s", ch);
        if(x == 0) {
            ch[0] = fgetc(file);
            if(ch[0] == '#' || ch[0] == '\n') {
                if(ch[0] != '\n') fgets(ch, BUFSIZE, file);
                printf(" rest of line read\n");
            }
        } else if(x<0) break;
        else {
                 printf("%c",*ch); // continue with ... undisclosed part here
            }
    }

    return 0;
}

Answer 2

the following proposed code:

1. performs the desired functionality
2. cleanly compiles
3. properly checks for errors
4. this answer uses a state machine, based on: 'InComment'

and now, the proposed code:

#include <stdio.h>
#include <stdlib.h>

int main( void )
{
    int InComment = 0;

    FILE *fp = fopen( "file.txt", "r" );
    if( !fp )
    {
        perror( "fopen to read -file.txt- failed" );
        exit( EXIT_FAILURE );
    }

    int ch;

    while( (ch = fgetc(fp)) != EOF )
    {
        if( ch == '#' )
        {
            InComment = 1;
        }

        else if( ch == '\n' )
        {
            InComment = 0;
            fputc( ch, stdout );
        }

        else if( !InComment )
        {
            fputc( ch, stdout );
        }
    }
    fclose( fp );
}

Answer 3

You can also make use of strcspn to trim all comments (and if not present, trim the line-endings from your buffer) in a single simple call. Where you would normally trim the line-ending from the buffer read by fgets() with:

        ch[strcspn (ch, "\r\n")] = 0;  /* trim line-ending */

You can simply add the "#" character to your reject list and nul-terminate there if a comment is present. That would reduce the complete task of removing comments beginning with '#' and outputting the newly formatted line to:

    while (fgets (ch, BUFSIZE, fp)) {   /* read every line */
        ch[strcspn (ch, "#\r\n")] = 0;  /* trim comment or line-ending */
        puts (ch);                      /* output line w/o comment */
    }

A short example taking the file to read as the first argument to the program (or reading from stdin by default if no argument is given), you could do:

#include <stdio.h>
#include <string.h>

#define BUFSIZE 1024    /* if you need a constant, #define one (or more) */

int main (int argc, char **argv) {

    char ch[BUFSIZE];
    /* use filename provided as 1st argument (stdin by default) */
    FILE *fp = argc > 1 ? fopen (argv[1], "r") : stdin;

    if (!fp) {  /* validate file open for reading */
        perror ("file open failed");
        return 1;
    }

    while (fgets (ch, BUFSIZE, fp)) {   /* read every line */
        ch[strcspn (ch, "#\r\n")] = 0;  /* trim comment or line-ending */
        puts (ch);                      /* output line w/o comment */
    }

    if (fp != stdin) fclose (fp);       /* close file if not stdin */

    return 0;
}

Example Input File

Borrowing Tom's example file :)

$ cat dat/comments_file.txt
#Paths
A B #Path between A and B.
D C #Path between C and D.
E F
G H

Example Use/Output

$ ./bin/comments_remove <dat/comments_file.txt

A B
D C
E F
G H

Look things over and let me know if you have further questions.