1 /* -*- Mode: C; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
2 /* soup-uri.c : utility functions to parse URLs */
6 * Bertrand Guiheneuf <bertrand@helixcode.com>
7 * Dan Winship <danw@helixcode.com>
9 * Copyright 1999, 2000 Helix Code, Inc. (http://www.helixcode.com)
11 * This program is free software; you can redistribute it and/or
12 * modify it under the terms of the GNU General Public License as
13 * published by the Free Software Foundation; either version 2 of the
14 * License, or (at your option) any later version.
16 * This program is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 * GNU General Public License for more details.
21 * You should have received a copy of the GNU General Public License
22 * along with this program; if not, write to the Free Software
23 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
30 * Here we deal with URLs following the general scheme:
31 * protocol://user;AUTH=mech:password@host:port/name
32 * where name is a path-like string (ie dir1/dir2/....) See RFC 1738
33 * for the complete description of Uniform Resource Locators. The
34 * ";AUTH=mech" addition comes from RFC 2384, "POP URL Scheme".
38 * recover the words between #'s or ?'s after the path
48 soup_uri_get_default_port (gchar *proto)
52 if (!proto) return -1;
56 if (strncasecmp (proto, "https", len) == 0)
58 else if (strncasecmp (proto, "http", len) == 0)
60 else if (strncasecmp (proto, "mailto", len) == 0)
62 else if (strncasecmp (proto, "ftp", len) == 0)
69 * soup_uri_new: create a SoupUri object from a string
71 * @uri_string: The string containing the URL to scan
73 * This routine takes a gchar and parses it as a
75 * protocol://user;AUTH=mech:password@host:port/path?querystring
76 * There is no test on the values. For example,
77 * "port" can be a string, not only a number!
78 * The SoupUri structure fields are filled with
79 * the scan results. When a member of the
80 * general URL can not be found, the corresponding
81 * SoupUri member is NULL.
82 * Fields filled in the SoupUri structure are allocated
83 * and url_string is not modified.
85 * Return value: a SoupUri structure containing the URL items.
87 SoupUri *soup_uri_new (const gchar* uri_string)
90 char *semi, *colon, *at, *slash, *path, *query;
93 g_uri = g_new (SoupUri,1);
95 /* Find protocol: initial substring until "://" */
96 colon = strchr (uri_string, ':');
97 if (colon && !strncmp (colon, "://", 3)) {
98 g_uri->protocol = g_strndup (uri_string, colon - uri_string);
99 uri_string = colon + 3;
101 g_uri->protocol = NULL;
103 /* If there is an @ sign, look for user, authmech, and
104 * password before it.
106 at = strchr (uri_string, '@');
108 colon = strchr (uri_string, ':');
109 if (colon && colon < at)
110 g_uri->passwd = g_strndup (colon + 1, at - colon - 1);
112 g_uri->passwd = NULL;
116 semi = strchr(uri_string, ';');
117 if (semi && semi < colon && !strncasecmp (semi, ";auth=", 6))
118 g_uri->authmech = g_strndup (semi + 6, colon - semi - 6);
120 g_uri->authmech = NULL;
124 g_uri->user = g_strndup (uri_string, semi - uri_string);
127 g_uri->user = g_uri->passwd = g_uri->authmech = NULL;
129 /* Find host (required) and port. */
130 slash = strchr (uri_string, '/');
131 colon = strchr (uri_string, ':');
132 if (slash && colon > slash)
136 g_uri->host = g_strndup (uri_string, colon - uri_string);
138 g_uri->port = atoi(colon + 1);
140 g_uri->port = atoi(colon + 1);
142 g_uri->host = g_strndup (uri_string, slash - uri_string);
143 g_uri->port = soup_uri_get_default_port (g_uri->protocol);
145 g_uri->host = g_strdup (uri_string);
146 g_uri->port = soup_uri_get_default_port (g_uri->protocol);
149 /* setup a fallback, if relative, then empty string, else
150 it will be from root */
154 if (slash && *slash && g_uri->protocol == NULL)
157 split = g_strsplit(slash, " ", 0);
158 path = g_strjoinv("%20", split);
161 query = strchr (path, '?');
164 g_uri->path = g_strndup (path, query - path);
165 g_uri->querystring = g_strdup (++query);
169 g_uri->querystring = NULL;
175 /* Need to handle mailto which apparantly doesn't use the "//" after the : */
177 soup_uri_to_string (const SoupUri *uri, gboolean show_passwd)
179 if (uri->port != -1 &&
180 uri->port != soup_uri_get_default_port(uri->protocol))
181 return g_strdup_printf(
182 "%s%s%s%s%s%s%s%s%s:%d%s",
183 uri->protocol ? uri->protocol : "",
184 uri->protocol ? "://" : "",
185 uri->user ? uri->user : "",
186 uri->authmech ? ";auth=" : "",
187 uri->authmech ? uri->authmech : "",
188 uri->passwd && show_passwd ? ":" : "",
189 uri->passwd && show_passwd ? uri->passwd : "",
190 uri->user ? "@" : "",
193 uri->path ? uri->path : "");
195 return g_strdup_printf(
196 "%s%s%s%s%s%s%s%s%s%s",
197 uri->protocol ? uri->protocol : "",
198 uri->protocol ? "://" : "",
199 uri->user ? uri->user : "",
200 uri->authmech ? ";auth=" : "",
201 uri->authmech ? uri->authmech : "",
202 uri->passwd && show_passwd ? ":" : "",
203 uri->passwd && show_passwd ? uri->passwd : "",
204 uri->user ? "@" : "",
206 uri->path ? uri->path : "");
210 soup_uri_free (SoupUri *uri)
214 g_free (uri->protocol);
216 g_free (uri->authmech);
217 g_free (uri->passwd);