summaryrefslogtreecommitdiff
path: root/utils/url.c
blob: e1903a816e07cca7b837256cfb7204d7bb72eeb7 (plain)
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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
/*
 * Copyright 2006 Richard Wilson <info@tinct.net>
 * Copyright 2005 James Bursa <bursa@users.sourceforge.net>
 * Copyright 2005 John M Bell <jmb202@ecs.soton.ac.uk>
 *
 * This file is part of NetSurf, http://www.netsurf-browser.org/
 *
 * NetSurf is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; version 2 of the License.
 *
 * NetSurf is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

/** \file
 * \brief Implementation of URL parsing and joining operations.
 */

#include <ctype.h>
#include <string.h>
#include <curl/curl.h>

#include "utils/config.h"
#include "utils/log.h"
#include "utils/utils.h"
#include "utils/url.h"


regex_t url_re, url_up_re;

/* exported interface documented in utils/url.h */
nserror url_init(void)
{
	nserror ret;

	/* regex from RFC 2396 */
	ret = regcomp_wrapper(&url_re, "^[[:space:]]*"
#define URL_RE_SCHEME 2
			"(([a-zA-Z][-a-zA-Z0-9+.]*):)?"
#define URL_RE_AUTHORITY 4
			"(//([^/?#[:space:]]*))?"
#define URL_RE_PATH 5
			"([^?#[:space:]]*)"
#define URL_RE_QUERY 7
			"(\\?([^#[:space:]]*))?"
#define URL_RE_FRAGMENT 9
			"(#([^[:space:]]*))?"
			"[[:space:]]*$", REG_EXTENDED);
	if (ret != NSERROR_OK) {
		return ret;
	}

	return regcomp_wrapper(&url_up_re,
			"/([^/]?|[.][^./]|[^./][.]|[^./][^./]|[^/][^/][^/]+)"
			"/[.][.](/|$)",
			REG_EXTENDED);
}

/* exported interface documented in utils/url.h */
bool url_host_is_ip_address(const char *host)
{
	struct in_addr ipv4;
	size_t host_len = strlen(host);
	const char *sane_host;
	const char *slash;
#ifndef NO_IPV6
	struct in6_addr ipv6;
	char ipv6_addr[64];
#endif
	/** @todo FIXME Some parts of urldb.c (and perhaps other parts of
	 * NetSurf) make confusions between hosts and "prefixes", we can
	 * sometimes be erroneously passed more than just a host.  Sometimes
	 * we may be passed trailing slashes, or even whole path segments.
	 * A specific criminal in this class is urldb_iterate_partial, which
	 * takes a prefix to search for, but passes that prefix to functions
	 * that expect only hosts.
	 *
	 * For the time being, we will accept such calls; we check if there
	 * is a / in the host parameter, and if there is, we take a copy and
	 * replace the / with a \0.  This is not a permanent solution; we
	 * should search through NetSurf and find all the callers that are
	 * in error and fix them.  When doing this task, it might be wise
	 * to replace the hideousness below with code that doesn't have to do
	 * this, and add assert(strchr(host, '/') == NULL); somewhere.
	 * -- rjek - 2010-11-04
	 */

	slash = strchr(host, '/');
	if (slash == NULL) {
		sane_host = host;
	} else {
		char *c = strdup(host);
		c[slash - host] = '\0';
		sane_host = c;
		host_len = slash - host - 1;
		LOG(("WARNING: called with non-host '%s'", host));
	}

	if (strspn(sane_host, "0123456789abcdefABCDEF[].:") < host_len)
		goto out_false;

	if (inet_aton(sane_host, &ipv4) != 0) {
		/* This can only be a sane IPv4 address if it contains 3 dots.
		 * Helpfully, inet_aton is happy to treat "a", "a.b", "a.b.c",
		 * and "a.b.c.d" as valid IPv4 address strings where we only
		 * support the full, dotted-quad, form.
		 */
		int num_dots = 0;
		size_t index;

		for (index = 0; index < host_len; index++) {
			if (sane_host[index] == '.')
				num_dots++;
		}

		if (num_dots == 3)
			goto out_true;
		else
			goto out_false;
	}

#ifndef NO_IPV6
	if (sane_host[0] != '[' || sane_host[host_len] != ']')
		goto out_false;

	strncpy(ipv6_addr, sane_host + 1, sizeof(ipv6_addr));
	ipv6_addr[sizeof(ipv6_addr) - 1] = '\0';

	if (inet_pton(AF_INET6, ipv6_addr, &ipv6) == 1)
		goto out_true;
#endif

out_false:
	if (slash != NULL) free((void *)sane_host);
	return false;

out_true:
	if (slash != NULL) free((void *)sane_host);
	return true;
}


/* exported interface documented in utils/url.h */
nserror url_nice(const char *url, char **result,
		bool remove_extensions)
{
	int m;
	regmatch_t match[10];
	regoff_t start, end;
	size_t i;
	char *dot;

	*result = 0;

	m = regexec(&url_re, url, 10, match, 0);
	if (m) {
		LOG(("url '%s' failed to match regex", url));
		return NSERROR_NOT_FOUND;
	}

	/* extract the last component of the path, if possible */
	if (match[URL_RE_PATH].rm_so == -1 || match[URL_RE_PATH].rm_so ==
			match[URL_RE_PATH].rm_eo)
		goto no_path;  /* no path, or empty */
	for (end = match[URL_RE_PATH].rm_eo - 1;
			end != match[URL_RE_PATH].rm_so && url[end] == '/';
			end--)
		;
	if (end == match[URL_RE_PATH].rm_so)
		goto no_path;  /* path is a string of '/' */
	end++;
	for (start = end - 1;
			start != match[URL_RE_PATH].rm_so && url[start] != '/';
			start--)
		;
	if (url[start] == '/')
		start++;

	if (!strncasecmp(url + start, "index.", 6) ||
			!strncasecmp(url + start, "default.", 8)) {
		/* try again */
		if (start == match[URL_RE_PATH].rm_so)
			goto no_path;
		for (end = start - 1;
				end != match[URL_RE_PATH].rm_so &&
				url[end] == '/';
				end--)
			;
		if (end == match[URL_RE_PATH].rm_so)
			goto no_path;
		end++;
		for (start = end - 1;
				start != match[URL_RE_PATH].rm_so &&
				url[start] != '/';
				start--)
		;
		if (url[start] == '/')
			start++;
	}

	*result = malloc(end - start + 1);
	if (!*result) {
		LOG(("malloc failed"));
		return NSERROR_NOMEM;
	}
	strncpy(*result, url + start, end - start);
	(*result)[end - start] = 0;

	if (remove_extensions) {
		dot = strchr(*result, '.');
		if (dot && dot != *result)
			*dot = 0;
	}

	return NSERROR_OK;

no_path:

	/* otherwise, use the host name, with '.' replaced by '_' */
	if (match[URL_RE_AUTHORITY].rm_so != -1 &&
			match[URL_RE_AUTHORITY].rm_so !=
			match[URL_RE_AUTHORITY].rm_eo) {
		*result = malloc(match[URL_RE_AUTHORITY].rm_eo -
				match[URL_RE_AUTHORITY].rm_so + 1);
		if (!*result) {
			LOG(("malloc failed"));
			return NSERROR_NOMEM;
		}
		strncpy(*result, url + match[URL_RE_AUTHORITY].rm_so,
				match[URL_RE_AUTHORITY].rm_eo -
				match[URL_RE_AUTHORITY].rm_so);
		(*result)[match[URL_RE_AUTHORITY].rm_eo -
				match[URL_RE_AUTHORITY].rm_so] = 0;

		for (i = 0; (*result)[i]; i++)
			if ((*result)[i] == '.')
				(*result)[i] = '_';

		return NSERROR_OK;
	}

	return NSERROR_NOT_FOUND;
}


/* exported interface documented in utils/url.h */
nserror url_unescape(const char *str, char **result)
{
	char *curlstr;
	char *retstr;

	curlstr = curl_unescape(str, 0);
	if (curlstr == NULL) {
		return NSERROR_NOMEM;
	}

	retstr = strdup(curlstr);
	curl_free(curlstr);

	if (retstr == NULL) {
		return NSERROR_NOMEM;
	}

	*result = retstr;
	return NSERROR_OK;
}


/* exported interface documented in utils/url.h */
nserror url_escape(const char *unescaped, size_t toskip,
		bool sptoplus, const char *escexceptions, char **result)
{
	size_t len;
	char *escaped, *d, *tmpres;
	const char *c;

	if (!unescaped || !result)
		return NSERROR_NOT_FOUND;

	*result = NULL;

	len = strlen(unescaped);
	if (len < toskip)
		return NSERROR_NOT_FOUND;
	len -= toskip;

	escaped = malloc(len * 3 + 1);
	if (!escaped)
		return NSERROR_NOMEM;

	for (c = unescaped + toskip, d = escaped; *c; c++) {
		/* Check if we should escape this byte.
		 * '~' is unreserved and should not be percent encoded, if
		 * you believe the spec; however, leaving it unescaped
		 * breaks a bunch of websites, so we escape it anyway. */
		if (!isascii(*c)
			|| (strchr(":/?#[]@" /* gen-delims */
				  "!$&'()*+,;=" /* sub-delims */
				  "<>%\"{}|\\^`~" /* others */,	*c)
				&& (!escexceptions || !strchr(escexceptions, *c)))
			|| *c <= 0x20 || *c == 0x7f) {
			if (*c == 0x20 && sptoplus) {
				*d++ = '+';
			} else {
				*d++ = '%';
				*d++ = "0123456789ABCDEF"[((*c >> 4) & 0xf)];
				*d++ = "0123456789ABCDEF"[(*c & 0xf)];
			}
		} else {
			/* unreserved characters: [a-zA-Z0-9-._] */
			*d++ = *c;
		}
	}
	*d++ = '\0';

	tmpres = malloc(d - escaped + toskip);
	if (!tmpres) {
		free(escaped);
		return NSERROR_NOMEM;
	}

	memcpy(tmpres, unescaped, toskip); 
	memcpy(tmpres + toskip, escaped, d - escaped);
	*result = tmpres;

	free(escaped);

	return NSERROR_OK;
}