Brandon Williams <bmwill@xxxxxxxxxx> writes:
> +/* removes the last path component from 'path' except if 'path' is root */
> +static void strip_last_component(struct strbuf *path)
> +{
> + size_t offset = offset_1st_component(path->buf);
> + size_t len = path->len;
> +
> + /* Find start of the last component */
> + while (offset < len && !is_dir_sep(path->buf[len - 1]))
> + len--;
If somebody at a higher level in the callchain has already
normalized path, this is not a problem, but this will behave
"unexpectedly" when path ends with a dir_sep byte (or more).
E.g. for input path "foo/bar/", the above loop runs zero times and
then ...
> + /* Skip sequences of multiple path-separators */
> + while (offset < len && is_dir_sep(path->buf[len - 1]))
> + len--;
... the slash at the end is removed, leaving "foo/bar" in path.
> + strbuf_setlen(path, len);
> +}
> ...
> +/* get (and remove) the next component in 'remaining' and place it in 'next' */
> +static void get_next_component(struct strbuf *next, struct strbuf *remaining)
> +{
> + char *start = NULL;
> + char *end = NULL;
> +
> + strbuf_reset(next);
> +
> + /* look for the next component */
> + /* Skip sequences of multiple path-separators */
> + for (start = remaining->buf; is_dir_sep(*start); start++)
> + ; /* nothing */
> + /* Find end of the path component */
> + for (end = start; *end && !is_dir_sep(*end); end++)
> + ; /* nothing */
> +
> + strbuf_add(next, start, end - start);
> + /* remove the component from 'remaining' */
> + strbuf_remove(remaining, 0, end - remaining->buf);
> +}
Unlike the strip_last_component(), I think this one is more
carefully done and avoids getting fooled by //extra//slashes// at
the beginning or at the end, which does help in the correctness of
the loop we see below.
> @@ -58,74 +88,112 @@ static const char *real_path_internal(const char *path, int die_on_error)
> goto error_out;
> }
>
> + strbuf_reset(&resolved);
> +
> + if (is_absolute_path(path)) {
> + /* absolute path; start with only root as being resolved */
> + int offset = offset_1st_component(path);
> + strbuf_add(&resolved, path, offset);
> + strbuf_addstr(&remaining, path + offset);
> + } else {
> + /* relative path; can use CWD as the initial resolved path */
> + if (strbuf_getcwd(&resolved)) {
> + if (die_on_error)
> + die_errno("unable to get current working directory");
> + else
> + goto error_out;
> }
> + strbuf_addstr(&remaining, path);
> + }
>
> + /* Iterate over the remaining path components */
> + while (remaining.len > 0) {
> + get_next_component(&next, &remaining);
> +
> + if (next.len == 0) {
> + continue; /* empty component */
> + } else if (next.len == 1 && !strcmp(next.buf, ".")) {
> + continue; /* '.' component */
> + } else if (next.len == 2 && !strcmp(next.buf, "..")) {
> + /* '..' component; strip the last path component */
> + strip_last_component(&resolved);
Wouldn't this let "resolved" eventually run out of the path
components to strip for a malformed input e.g. "/a/../../b"?
> + ...
> + /*
> + * if there are still remaining components to resolve
> + * then append them to symlink
> + */
> + if (remaining.len) {
> + strbuf_addch(&symlink, '/');
This can add duplicate dir_sep if readlink(2)'ed contents of the
symbolic link already ends with a slash, but I think it (together
with the fact that the code does nothing to normalize what is read
from the symbolic link) probably does not matter, given the way how
get_next_component() is implemented.
> + strbuf_addbuf(&symlink, &remaining);
> + }
> +
> + /*
> + * use the symlink as the remaining components that
> + * need to be resloved
> + */
> + strbuf_swap(&symlink, &remaining);
> + }
> }
>
> + retval = resolved.buf;
> +
> error_out:
> + strbuf_release(&remaining);
> + strbuf_release(&next);
> + strbuf_release(&symlink);
>
> return retval;
> }