fetch.c revision 40975 
1/*-
2 * Copyright (c) 1998 Dag-Erling Co�dan Sm�rgrav
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer
10 *    in this position and unchanged.
11 * 2. Redistributions in binary form must reproduce the above copyright
12 *    notice, this list of conditions and the following disclaimer in the
13 *    documentation and/or other materials provided with the distribution.
14 * 3. The name of the author may not be used to endorse or promote products
15 *    derived from this software without specific prior written permission
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
18 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
19 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
20 * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
21 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
22 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
23 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
24 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
26 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27 *
28 *	$Id: fetch.c,v 1.5 1998/11/05 19:48:17 des Exp $
29 */
30
31#include <sys/param.h>
32#include <sys/errno.h>
33
34#include <ctype.h>
35#include <stdio.h>
36#include <stdlib.h>
37#include <string.h>
38
39#include "fetch.h"
40#include "common.h"
41
42
43/*** Local data **************************************************************/
44
45/*
46 * Error messages for parser errors
47 */
48#define URL_MALFORMED		1
49#define URL_BAD_SCHEME		2
50#define URL_BAD_PORT		3
51static struct fetcherr _url_errlist[] = {
52    { URL_MALFORMED,	FETCH_URL,	"Malformed URL" },
53    { URL_BAD_SCHEME,	FETCH_URL,	"Invalid URL scheme" },
54    { URL_BAD_PORT,	FETCH_URL,	"Invalid server port" },
55    { -1,		FETCH_UNKNOWN,	"Unknown parser error" }
56};
57
58
59/*** Public API **************************************************************/
60
61/*
62 * Select the appropriate protocol for the URL scheme, and return a
63 * read-only stream connected to the document referenced by the URL.
64 */
65FILE *
66fetchGet(struct url *URL, char *flags)
67{
68    if (strcasecmp(URL->scheme, "file") == 0)
69	return fetchGetFile(URL, flags);
70    else if (strcasecmp(URL->scheme, "http") == 0)
71	return fetchGetHTTP(URL, flags);
72    else if (strcasecmp(URL->scheme, "ftp") == 0)
73	return fetchGetFTP(URL, flags);
74    else {
75	_url_seterr(URL_BAD_SCHEME);
76	return NULL;
77    }
78}
79
80/*
81 * Select the appropriate protocol for the URL scheme, and return a
82 * write-only stream connected to the document referenced by the URL.
83 */
84FILE *
85fetchPut(struct url *URL, char *flags)
86{
87    if (strcasecmp(URL->scheme, "file") == 0)
88	return fetchPutFile(URL, flags);
89    else if (strcasecmp(URL->scheme, "http") == 0)
90	return fetchPutHTTP(URL, flags);
91    else if (strcasecmp(URL->scheme, "ftp") == 0)
92	return fetchPutFTP(URL, flags);
93    else {
94	_url_seterr(URL_BAD_SCHEME);
95	return NULL;
96    }
97}
98
99/*
100 * Select the appropriate protocol for the URL scheme, and return the
101 * size of the document referenced by the URL if it exists.
102 */
103int
104fetchStat(struct url *URL, struct url_stat *us, char *flags)
105{
106    if (strcasecmp(URL->scheme, "file") == 0)
107	return fetchStatFile(URL, us, flags);
108    else if (strcasecmp(URL->scheme, "http") == 0)
109	return fetchStatHTTP(URL, us, flags);
110    else if (strcasecmp(URL->scheme, "ftp") == 0)
111	return fetchStatFTP(URL, us, flags);
112    else {
113	_url_seterr(URL_BAD_SCHEME);
114	return -1;
115    }
116}
117
118/*
119 * Attempt to parse the given URL; if successful, call fetchGet().
120 */
121FILE *
122fetchGetURL(char *URL, char *flags)
123{
124    struct url *u;
125    FILE *f;
126
127    if ((u = fetchParseURL(URL)) == NULL)
128	return NULL;
129
130    f = fetchGet(u, flags);
131
132    free(u);
133    return f;
134}
135
136
137/*
138 * Attempt to parse the given URL; if successful, call fetchPut().
139 */
140FILE *
141fetchPutURL(char *URL, char *flags)
142{
143    struct url *u;
144    FILE *f;
145
146    if ((u = fetchParseURL(URL)) == NULL)
147	return NULL;
148
149    f = fetchPut(u, flags);
150
151    free(u);
152    return f;
153}
154
155/*
156 * Attempt to parse the given URL; if successful, call fetchStat().
157 */
158int
159fetchStatURL(char *URL, struct url_stat *us, char *flags)
160{
161    struct url *u;
162    int s;
163
164    if ((u = fetchParseURL(URL)) == NULL)
165	return -1;
166
167    s = fetchStat(u, us, flags);
168
169    free(u);
170    return s;
171}
172
173/*
174 * Split an URL into components. URL syntax is:
175 * method:[//[user[:pwd]@]host[:port]]/[document]
176 * This almost, but not quite, RFC1738 URL syntax.
177 */
178struct url *
179fetchParseURL(char *URL)
180{
181    char *p, *q;
182    struct url *u;
183    int i;
184
185    /* allocate struct url */
186    if ((u = calloc(1, sizeof(struct url))) == NULL) {
187	errno = ENOMEM;
188	_fetch_syserr();
189	return NULL;
190    }
191
192    /* scheme name */
193    for (i = 0; *URL && (*URL != ':'); URL++)
194	if (i < URL_SCHEMELEN)
195	    u->scheme[i++] = *URL;
196    if (!URL[0] || (URL[1] != '/')) {
197	_url_seterr(URL_BAD_SCHEME);
198	goto ouch;
199    }
200    else URL++;
201    if (URL[1] != '/') {
202	p = URL;
203	goto nohost;
204    }
205    else URL += 2;
206
207    p = strpbrk(URL, "/@");
208    if (*p == '@') {
209	/* username */
210	for (q = URL, i = 0; (*q != ':') && (*q != '@'); q++)
211	    if (i < URL_USERLEN)
212		u->user[i++] = *q;
213
214	/* password */
215	if (*q == ':')
216	    for (q++, i = 0; (*q != ':') && (*q != '@'); q++)
217		if (i < URL_PWDLEN)
218		    u->pwd[i++] = *q;
219
220	p++;
221    } else p = URL;
222
223    /* hostname */
224    for (i = 0; *p && (*p != '/') && (*p != ':'); p++)
225	if (i < MAXHOSTNAMELEN)
226	    u->host[i++] = *p;
227
228    /* port */
229    if (*p == ':') {
230	for (q = ++p; *q && (*q != '/'); q++)
231	    if (isdigit(*q))
232		u->port = u->port * 10 + (*q - '0');
233	    else {
234		/* invalid port */
235		_url_seterr(URL_BAD_PORT);
236		goto ouch;
237	    }
238	while (*p && (*p != '/'))
239	    p++;
240    }
241
242nohost:
243    /* document */
244    if (*p) {
245	struct url *t;
246	t = realloc(u, sizeof(*u)+strlen(p)-1);
247	if (t == NULL) {
248	    errno = ENOMEM;
249	    _fetch_syserr();
250	    goto ouch;
251	}
252	u = t;
253	strcpy(u->doc, p);
254    } else {
255	u->doc[0] = '/';
256	u->doc[1] = 0;
257    }
258
259    DEBUG(fprintf(stderr,
260		  "scheme:   [\033[1m%s\033[m]\n"
261		  "user:     [\033[1m%s\033[m]\n"
262		  "password: [\033[1m%s\033[m]\n"
263		  "host:     [\033[1m%s\033[m]\n"
264		  "port:     [\033[1m%d\033[m]\n"
265		  "document: [\033[1m%s\033[m]\n",
266		  u->scheme, u->user, u->pwd,
267		  u->host, u->port, u->doc));
268
269    return u;
270
271ouch:
272    free(u);
273    return NULL;
274}
275