1 /*
2  * Copyright (c) 2021 Omar Polo <op@omarpolo.com>
3  *
4  * Permission to use, copy, modify, and distribute this software for any
5  * purpose with or without fee is hereby granted, provided that the above
6  * copyright notice and this permission notice appear in all copies.
7  *
8  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
9  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
10  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
11  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
12  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
13  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
14  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
15  */
16 
17 #include "telescope.h"
18 
19 #include <ctype.h>
20 #include <fnmatch.h>
21 #include <string.h>
22 
23 static int	check_for_utf8(char*);
24 
25 static struct parser_table {
26 	const char	*mediatype;
27 	void		(*parserinit)(struct parser*);
28 } ptable[] = {
29 	{ "text/gemini",	gemtext_initparser },
30 	{ "text/*",		textplain_initparser },
31 	{ NULL, NULL}
32 };
33 
34 static int
35 check_for_utf8(char *b)
36 {
37 	for (;;) {
38 		while (*b != '\0' && isspace(*b))
39 			b++;
40 		if (*b == '\0')
41 			break;
42 		if (!has_prefix(b, "charset=")) {
43 			while (*b != '\0' && *b != ';')
44 				b++;
45 			if (*b == '\0')
46 				break;
47 			b++;
48 			continue;
49 		}
50 
51 		/* is charset= */
52 		b += strlen("charset=");
53 		/* TODO: improve the matching */
54 		return has_prefix(b, "ASCII") || has_prefix(b, "ascii") ||
55 			has_prefix(b, "UTF-8") || has_prefix(b, "utf-8");
56 	}
57 
58 	return 1;
59 }
60 
61 int
62 setup_parser_for(struct tab *tab)
63 {
64 	char			*b, buf[GEMINI_URL_LEN] = {0};
65 	struct parser_table	*t;
66 
67         memcpy(buf, tab->meta, sizeof(tab->meta));
68 
69 	for (b = buf; *b != ';' && *b != '\0'; ++b)
70 		;
71 
72 	if (*b == ';') {
73 		*b = '\0';
74 		++b;
75 	}
76 
77 	if (!check_for_utf8(b))
78 		return 0;
79 
80 	for (t = ptable; t->mediatype != NULL; ++t) {
81 		if (!fnmatch(t->mediatype, buf, 0)) {
82 			t->parserinit(&tab->page);
83 			return 1;
84 		}
85 	}
86 
87 	return 0;
88 }