Function url_normalize_1

urlmatch.c:115–437

}

static char *url_normalize_1(const char *url, struct url_info *out_info, char allow_globs)
{
	/*
	 * Normalize NUL-terminated url using the following rules:
	 *
	 * 1. Case-insensitive parts of url will be converted to lower case
	 * 2. %-encoded characters that do not need to be will be unencoded
	 * 3. Characters that are not %-encoded and must be will be encoded
	 * 4. All %-encodings will be converted to upper case hexadecimal
	 * 5. Leading 0s are removed from port numbers
	 * 6. If the default port for the scheme is given it will be removed
	 * 7. A path part (including empty) not starting with '/' has one added
	 * 8. Any dot segments (. or ..) in the path are resolved and removed
	 * 9. IPv6 host literals are allowed (but not normalized or validated)
	 *
	 * The rules are based on information in RFC 3986.
	 *
	 * Please note this function requires a full URL including a scheme
	 * and host part (except for file: URLs which may have an empty host).
	 *
	 * The return value is a newly allocated string that must be freed
	 * or NULL if the url is not valid.
	 *
	 * If out_info is non-NULL, the url and err fields therein will always
	 * be set.  If a non-NULL value is returned, it will be stored in
	 * out_info->url as well, out_info->err will be set to NULL and the
	 * other fields of *out_info will also be filled in.  If a NULL value
	 * is returned, NULL will be stored in out_info->url and out_info->err
	 * will be set to a brief, translated, error message, but no other
	 * fields will be filled in.
	 *
	 * This is NOT a URL validation function.  Full URL validation is NOT
	 * performed.  Some invalid host names are passed through this function
	 * undetected.  However, most all other problems that make a URL invalid
	 * will be detected (including a missing host for non file: URLs).
	 */

	size_t url_len = strlen(url);
	struct strbuf norm;
	size_t spanned;
	size_t scheme_len, user_off=0, user_len=0, passwd_off=0, passwd_len=0;
	size_t host_off=0, host_len=0, port_off=0, port_len=0, path_off, path_len, result_len;
	const char *slash_ptr, *at_ptr, *colon_ptr, *path_start;
	char *result;

	/*
	 * Copy lowercased scheme and :// suffix, %-escapes are not allowed
	 * First character of scheme must be URL_ALPHA
	 */
	spanned = strspn(url, URL_SCHEME_CHARS);
	if (!spanned || !isalpha(url[0]) || spanned + 3 > url_len ||
	    url[spanned] != ':' || url[spanned+1] != '/' || url[spanned+2] != '/') {
		if (out_info) {
			out_info->url = NULL;
			out_info->err = _("invalid URL scheme name or missing '://' suffix");
		}
		return NULL; /* Bad scheme and/or missing "://" part */
	}