summaryrefslogtreecommitdiff
path: root/utils/url.c
blob: 50059a1082bb8e43dec1e00db4daef569b4d3d18 (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
/*
 * 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 <assert.h>
#include <string.h>
#include <stdlib.h>

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


/**
 * Convert a hex digit to a hex value
 *
 * Must be called with valid hex char, results undefined otherwise.
 *
 * \param[in]  c  char to convert yo value
 * \return the value of c
 */
static inline char xdigit_to_hex(char c)
{
	if (c >= '0' && c <= '9') {
		return c - '0';
	} else if (c >= 'A' && c <= 'F') {
		return c - 'A' + 10;
	} else {
		return c - 'a' + 10;
	}
}


/* exported interface documented in utils/url.h */
nserror url_unescape(const char *str, size_t length,
		size_t *length_out, char **result_out)
{
	const char *str_end;
	size_t new_len;
	char *res_pos;
	char *result;

	if (length == 0) {
		length = strlen(str);
	}

	result = malloc(length + 1);
	if (result == NULL) {
		return NSERROR_NOMEM;
	}

	res_pos = result;
	str_end = str + length;
	if (length >= 3) {
		str_end -= 2;
		while (str < str_end) {
			char c = *str;
			char c1 = *(str + 1);
			char c2 = *(str + 2);

			if (c == '%' && isxdigit(c1) && isxdigit(c2)) {
				c = xdigit_to_hex(c1) << 4 | xdigit_to_hex(c2);
				str += 2;
			}
			*res_pos++ = c;
			str++;
		}
		str_end += 2;
	}

	while (str < str_end) {
		*res_pos++ = *str++;
	}

	*res_pos = '\0';
	new_len = res_pos - result;

	if (new_len != length) {
		/* Shrink wrap the allocaiton around the string */
		char *tmp = realloc(result, new_len + 1);
		if (tmp != NULL) {
			result = tmp;
		}
	}

	if (length_out != NULL) {
		*length_out = new_len;
	}
	*result_out = result;
	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;
}