|
// Written by retoor@molodetz.nl
|
|
|
|
// This code defines a URL parser in C that extracts components such as the
|
|
// scheme, hostname, port, path, and query from a given URL.
|
|
|
|
// Includes:
|
|
// - <stdio.h> for standard I/O operations
|
|
// - <string.h> for string manipulation functions
|
|
// - <stdlib.h> for memory allocation and management
|
|
|
|
// MIT License
|
|
// Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
// of this software and associated documentation files (the "Software"), to deal
|
|
// in the Software without restriction, including without limitation the rights
|
|
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
// copies of the Software, and to permit persons to whom the Software is
|
|
// furnished to do so, subject to the following conditions: The above copyright
|
|
// notice and this permission notice shall be included in all copies or
|
|
// substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS",
|
|
// WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
|
|
// TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
// NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
|
|
// FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
|
// TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR
|
|
// THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
|
|
|
#ifndef R_URL_H
|
|
#define R_URL_H
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
typedef struct {
|
|
char scheme[16];
|
|
char hostname[256];
|
|
char port[8];
|
|
char path[512];
|
|
char query[512];
|
|
} url_t;
|
|
|
|
int parse_url(const char *url, url_t *parsed_url) {
|
|
memset(parsed_url, 0, sizeof(url_t));
|
|
|
|
const char *scheme_end = strstr(url, "://");
|
|
if (!scheme_end) {
|
|
return -1;
|
|
}
|
|
|
|
strncpy(parsed_url->scheme, url, scheme_end - url);
|
|
parsed_url->scheme[scheme_end - url] = '\0';
|
|
|
|
const char *hostname_start = scheme_end + 3;
|
|
const char *port_start = strchr(hostname_start, ':');
|
|
const char *path_start = strchr(hostname_start, '/');
|
|
const char *query_start = strchr(hostname_start, '?');
|
|
|
|
if (port_start && (!path_start || port_start < path_start)) {
|
|
size_t hostname_length = port_start - hostname_start;
|
|
if (hostname_length >= sizeof(parsed_url->hostname)) {
|
|
fprintf(stderr, "Hostname is too long\n");
|
|
return -1;
|
|
}
|
|
strncpy(parsed_url->hostname, hostname_start, hostname_length);
|
|
parsed_url->hostname[hostname_length] = '\0';
|
|
|
|
size_t port_length = query_start ? (size_t)(query_start - port_start - 1)
|
|
: strlen(port_start + 1);
|
|
if (port_length >= sizeof(parsed_url->port)) {
|
|
fprintf(stderr, "Port value is too long\n");
|
|
return -1;
|
|
}
|
|
strncpy(parsed_url->port, port_start + 1, port_length);
|
|
parsed_url->port[port_length] = '\0';
|
|
} else {
|
|
size_t hostname_length =
|
|
path_start ? (size_t)(path_start - hostname_start)
|
|
: (query_start ? (size_t)(query_start - hostname_start)
|
|
: strlen(hostname_start));
|
|
if (hostname_length >= sizeof(parsed_url->hostname)) {
|
|
fprintf(stderr, "Hostname is too long\n");
|
|
return -1;
|
|
}
|
|
strncpy(parsed_url->hostname, hostname_start, hostname_length);
|
|
parsed_url->hostname[hostname_length] = '\0';
|
|
}
|
|
|
|
if (path_start) {
|
|
if (query_start) {
|
|
strncpy(parsed_url->path, path_start, query_start - path_start);
|
|
parsed_url->path[query_start - path_start] = '\0';
|
|
} else {
|
|
strcpy(parsed_url->path, path_start);
|
|
}
|
|
}
|
|
|
|
if (query_start) {
|
|
strcpy(parsed_url->query, query_start + 1);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
#endif |