Getting rid of all comments in C - c

Question

Right now this code doesn't remove inline comments, how do I change it so it also removes inline comments?
FILE *output;
output = fopen("preprocess_output.c", "w");
while (fgets(line, LINE_LENGTH, file) != NULL)
{
for (int i = 0; i < strlen(line); i++)
{
if (line[i] == '/' && line[i + 1] == '/')
{
comment_lines++;
}
else
{
fprintf(output, line);
}
if (line[i] != '\n' && line[i] != '\t')
{
non_blank++;
break;
}
}
}

Answer 1

Here is a small program that strips C comments in almost all cases.
/* strip C comments by chqrlie */
#include <errno.h>
#include <stdio.h>
#include <string.h>
/* read the next byte from the C source file, handing escaped newlines */
int getcpp(FILE *fp, int *lineno_p) {
int ch;
while ((ch = getc(fp)) == '\\') {
if ((ch = getc(fp)) != '\n') {
ungetc(ch, fp);
return '\\';
}
*lineno_p += 1;
}
if (ch == '\n')
*lineno_p += 1;
return ch;
}
int main(int argc, char *argv[]) {
FILE *fp = stdin, *ft = stdout;
const char *filename = "<stdin>";
int ch, lineno;
if (argc > 1) {
if ((fp = fopen(filename = argv[1], "r")) == NULL) {
fprintf(stderr, "Cannot open input file %s: %s\n",
filename, strerror(errno));
return 1;
}
}
if (argc > 2) {
if ((ft = fopen(argv[2], "w")) == NULL) {
fprintf(stderr, "Cannot open output file %s: %s\n",
argv[2], strerror(errno));
return 1;
}
}
lineno = 1;
while ((ch = getcpp(fp, &lineno)) != EOF) {
int startline = lineno;
if (ch == '/') {
if ((ch = getcpp(fp, &lineno)) == '/') {
/* single-line comment */
while ((ch = getcpp(fp, &lineno)) != EOF && ch != '\n')
continue;
if (ch == EOF) {
fprintf(stderr, "%s:%d: unterminated single line comment\n",
filename, startline);
break;
}
putc('\n', ft); /* replace comment with newline */
continue;
}
if (ch == '*') {
/* multi-line comment */
int lastc = 0;
while ((ch = getcpp(fp, &lineno)) != EOF) {
if (ch == '/' && lastc == '*') {
break;
}
lastc = ch;
}
if (ch == EOF) {
fprintf(stderr, "%s:%d: unterminated comment\n",
filename, startline);
break;
}
putc(' ', ft); /* replace comment with single space */
continue;
}
putc('/', ft);
/* keep parsing to handle n/"a//"[i] */
}
if (ch == '\'' || ch == '"') {
int sep = ch;
const char *const_type = (ch == '"') ? "string" : "character";
putc(sep, ft);
while ((ch = getcpp(fp, &lineno)) != EOF) {
putc(ch, ft);
if (ch == sep)
break;;
if (ch == '\\') {
if ((ch = getcpp(fp, &lineno)) == EOF)
break;
putc(ch, ft);
}
if (ch == '\n') {
fprintf(stderr, "%s:%d: unescaped newline in %s constant\n",
filename, lineno - 1, const_type);
/* This is a syntax error but keep going as if constant was terminated */
break;
}
}
if (ch == EOF) {
fprintf(stderr, "%s:%d: unterminated %s constant\n",
filename, startline, const_type);
break;
}
continue;
}
putc(ch, ft);
}
if (fp != stdin)
fclose(fp);
if (ft != stdout)
fclose(ft);
return 0;
}
Since you get a full answer for free, try and learn how the above code handles strings and escaped newlines. There are still some corner cases that are not supported, can you find them?
one such corner case is the code does not parse trigraphs, an obsolescent feature that may be used to hide \ characters.

Answer 2

in the following solution, there is a single pass over the line. If a comment was found (//), we terminate and print it. supporting (/* */) requires more work.
while (fgets(line, LINE_LENGTH, file) != NULL)
{
size_t len = strlen(line);
size_t i;
for (i=0; i<len; i++)
{
if (line[i]=='/' && line[i + 1]=='/')
{
line[i] = '\0';
break;
}
}
fprintf(output, "%s", line);
}
note to two points in addition to the logic:
when printing using printf, always use a format string. If the line contains % it might do unexpected things.
do not put strlen in the condition of a loop. It generates a lot of unnecessary loops to calculate the length.