summaryrefslogtreecommitdiffstats
path: root/cpukit/httpd/url.c
blob: 0258387c5977eac0cb428cee0246fbcb3391d1c3 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
/*
 * url.c -- Parse URLs
 *
 * Copyright (c) GoAhead Software Inc., 1995-2000. All Rights Reserved.
 *
 * See the file "license.txt" for usage and redistribution license requirements
 */

/******************************** Description *********************************/

/*
 *	This module parses URLs into their components.
 */

/********************************* Includes ***********************************/

#include	"wsIntrn.h"

/********************************* Statics ************************************/
/*
 *	htmExt is declared in this way to avoid a Linux and Solaris segmentation
 *	fault when a constant string is passed to strlower which could change its
 *	argument.
 */

char_t	htmExt[] = T(".htm");


/*********************************** Code *************************************/
/*
 *	Return the mime type for the given URL given a URL.
 *	The caller supplies the buffer to hold the result.
 *	charCnt is the number of characters the buffer will hold, ascii or UNICODE.
 */

char_t *websUrlType(char_t *url, char_t *buf, int charCnt)
{
	sym_t	*sp;
	char_t	*ext, *parsebuf;

	a_assert(url && *url);
	a_assert(buf && charCnt > 0);

	if (url == NULL || *url == '\0') {
		gstrcpy(buf, T("text/plain"));
		return buf;
	}
	if (websUrlParse(url, &parsebuf, NULL, NULL, NULL, NULL, NULL, 
			NULL, &ext) < 0) {
		gstrcpy(buf, T("text/plain"));
		return buf;
	}
	strlower(ext);

/*
 *	Lookup the mime type symbol table to find the relevant content type
 */
	if ((sp = symLookup(websMime, ext)) != NULL) {
		gstrncpy(buf, sp->content.value.string, charCnt);
	} else {
		gstrcpy(buf, T("text/plain"));
	}
	bfree(B_L, parsebuf);
	return buf;
}

/******************************************************************************/
/*
 *	Parse the URL. A buffer is allocated to store the parsed URL in *pbuf.
 *	This must be freed by the caller. NOTE: tag is not yet fully supported.
 */

int websUrlParse(char_t *url, char_t **pbuf, char_t **phost, char_t **ppath, 
	char_t **pport, char_t **pquery, char_t **pproto, char_t **ptag, 
	char_t **pext)
{
	char_t		*tok, *cp, *host, *path, *port, *proto, *tag, *query, *ext;
	char_t		*last_delim, *hostbuf, *portbuf, *buf;
	int			c, len, ulen;

	a_assert(url);
	a_assert(pbuf);

	ulen = gstrlen(url);
/*
 *	We allocate enough to store separate hostname and port number fields.
 *	As there are 3 strings in the one buffer, we need room for 3 null chars.
 *	We allocate MAX_PORT_LEN char_t's for the port number.
 */
	len = ulen * 2 + MAX_PORT_LEN + 3;
	if ((buf = balloc(B_L, len * sizeof(char_t))) == NULL) {
		return -1;
	}
	portbuf = &buf[len - MAX_PORT_LEN - 1];
	hostbuf = &buf[ulen+1];
	gstrcpy(buf, url);
	url = buf;

/*
 *	Convert the current listen port to a string. We use this if the URL has
 *	no explicit port setting
 */
	stritoa(websGetPort(), portbuf, MAX_PORT_LEN);
	port = portbuf;
	path = T("/");
	proto = T("http");
	host = T("localhost");
	query = T("");
	ext = htmExt;
	tag = T("");

	if (gstrncmp(url, T("http://"), 7) == 0) {
		tok = &url[7];
		tok[-3] = '\0';
		proto = url;
		host = tok;
		for (cp = tok; *cp; cp++) {
			if (*cp == '/') {
				break;
			}
			if (*cp == ':') {
				*cp++ = '\0';
				port = cp;
				tok = cp;
			}
		}
		if ((cp = gstrchr(tok, '/')) != NULL) {
/*
 *			If a full URL is supplied, we need to copy the host and port 
 *			portions into static buffers.
 */
			c = *cp;
			*cp = '\0';
			gstrncpy(hostbuf, host, ulen);
			gstrncpy(portbuf, port, MAX_PORT_LEN);
			*cp = c;
			host = hostbuf;
			port = portbuf;
			path = cp;
			tok = cp;
		}

	} else {
		path = url;
		tok = url;
	}

/*
 *	Parse the query string
 */
	if ((cp = gstrchr(tok, '?')) != NULL) {
		*cp++ = '\0';
		query = cp;
		path = tok;
		tok = query;
	} 

/*
 *	Parse the fragment identifier
 */
	if ((cp = gstrchr(tok, '#')) != NULL) {
		*cp++ = '\0';
		if (*query == 0) {
			path = tok;
		}
	}

/*
 *	Only do the following if asked for the extension
 */
	if (pext) {
		if ((cp = gstrrchr(path, '.')) != NULL) {
			if ((last_delim = gstrrchr(path, '/')) != NULL) {
				if (last_delim > cp) {
					ext = htmExt;
				} else {
					ext = cp;
				}
			} else {
				ext = cp;
			}
		} else {
			if (path[gstrlen(path) - 1] == '/') {
				ext = htmExt;
			}
		}
	}

/*
 *	Pass back the fields requested (if not NULL)
 */
	if (phost)
		*phost = host;
	if (ppath)
		*ppath = path;
	if (pport)
		*pport = port;
	if (pproto)
		*pproto = proto;
	if (pquery)
		*pquery = query;
	if (ptag)
		*ptag = tag;
	if (pext)
		*pext = ext;
	*pbuf = buf;
	return 0;
}

/******************************************************************************/