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 <ctype.h>
18 #include <fnmatch.h>
19 #include <string.h>
20 
21 #include "parser.h"
22 #include "telescope.h"
23 
24 static int	check_for_utf8(char*);
25 
26 static struct parser_table {
27 	const char	*mediatype;
28 	void		(*parserinit)(struct parser*);
29 } ptable[] = {
30 	{ "text/gemini",	gemtext_initparser },
31 	{ "text/*",		textplain_initparser },
32 	{ NULL, NULL}
33 };
34 
35 static int
36 check_for_utf8(char *b)
37 {
38 	for (;;) {
39 		while (*b != '\0' && isspace(*b))
40 			b++;
41 		if (*b == '\0')
42 			break;
43 		if (!has_prefix(b, "charset=")) {
44 			while (*b != '\0' && *b != ';')
45 				b++;
46 			if (*b == '\0')
47 				break;
48 			b++;
49 			continue;
50 		}
51 
52 		/* is charset= */
53 		b += strlen("charset=");
54 		/* TODO: improve the matching */
55 		return has_prefix(b, "ASCII") || has_prefix(b, "ascii") ||
56 			has_prefix(b, "UTF-8") || has_prefix(b, "utf-8");
57 	}
58 
59 	return 1;
60 }
61 
62 int
63 setup_parser_for(struct tab *tab)
64 {
65 	char			*b, buf[GEMINI_URL_LEN] = {0};
66 	struct parser_table	*t;
67 
68         memcpy(buf, tab->meta, sizeof(tab->meta));
69 
70 	for (b = buf; *b != ';' && *b != '\0'; ++b)
71 		;
72 
73 	if (*b == ';') {
74 		*b = '\0';
75 		++b;
76 	}
77 
78 	if (!check_for_utf8(b))
79 		return 0;
80 
81 	for (t = ptable; t->mediatype != NULL; ++t) {
82 		if (!fnmatch(t->mediatype, buf, 0)) {
83 			t->parserinit(&tab->buffer.page);
84 			return 1;
85 		}
86 	}
87 
88 	return 0;
89 }