The number of characters of comments in a file (C programming)

Question

I can\'t seem to get it right, tried everything, but..

int commentChars() {
char str[256], fileName[256];
FILE *fp;
int i;


do{
    long commentCount=0;
    ffl         


        

Answer 1

I think you best use regular expressions. They seem scary, but they're really not that bad for things like this. You can always try playing some regex golf to practice ;-)

I'd approach it as follows:

• Build a regular expression that captures comments
• Scan your file for it
• Count the characters in the match

Using some regex code and a bit about matching comments in C, I hacked this together which should allow you to count all the bytes that are part of a block style comment /* */ - Including the delimiters. I only tested it on OS X. I suppose you can handle the rest?

#include 
#include 
#include 

#define MAX_ERROR_MSG 0x1000

int compile_regex(regex_t *r, char * regex_text)
{
    int status = regcomp (r, regex_text, REG_EXTENDED|REG_NEWLINE|REG_ENHANCED);
    if (status != 0) {
        char error_message[MAX_ERROR_MSG];
        regerror (status, r, error_message, MAX_ERROR_MSG);
        printf ("Regex error compiling '%s': %s\n",
            regex_text, error_message);
        return 1;
    }
    return 0;
}
int match_regex(regex_t *r, const char * to_match, long long *nbytes)
{
    /* Pointer to end of previous match */
    const char *p = to_match;
    /* Maximum number of matches */
    size_t n_matches = 10;
    /* Array of matches */
    regmatch_t m[n_matches];

    while(1) {
        int i = 0;
        int nomatch = regexec (r, p, n_matches, m, 0);
        if(nomatch) {
            printf("No more matches.\n");
            return nomatch;
        }
        //Just handle first match (the entire match), don't care
        //about groups
        int start;
        int finish;
        start = m[0].rm_so + (p - to_match);
        finish = m[0].rm_eo + (p - to_match);
        *nbytes += m[0].rm_eo - m[0].rm_so;

        printf("match length(bytes) : %lld\n", m[0].rm_eo - m[0].rm_so);
        printf("Match: %.*s\n\n", finish - start, to_match + start);
        p += m[0].rm_eo;
    }
    return 0;
}

int main(int argc, char *argv[])
{
    regex_t r;
    char regex_text[128] = "/\\*(.|[\r\n])*?\\*/";
    long long comment_bytes = 0;

    char *file_contents;
    size_t input_file_size;
    FILE *input_file;
    if(argc != 2) {
        printf("Usage : %s ", argv[0]);
        return 0;
    }
    input_file = fopen(argv[1], "rb");
    fseek(input_file, 0, SEEK_END);
    input_file_size = ftell(input_file);
    rewind(input_file);
    file_contents = malloc(input_file_size * (sizeof(char)));
    fread(file_contents, sizeof(char), input_file_size, input_file);

    compile_regex(&r, regex_text);
    match_regex(&r, file_contents, &comment_bytes);
    regfree(&r);
    printf("Found %lld bytes in comments\n", comment_bytes);

    return 0;
}