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 "compat.h"
18 
19 #include <ctype.h>
20 #include <fnmatch.h>
21 #include <string.h>
22 
23 #include "parser.h"
24 #include "telescope.h"
25 
26 static int	check_for_utf8(char*);
27 
28 static struct parser_table {
29 	const char	*mediatype;
30 	void		(*parserinit)(struct parser*);
31 } ptable[] = {
32 	{ "text/gemini",	gemtext_initparser },
33 	{ "text/*",		textplain_initparser },
34 	{ NULL, NULL}
35 };
36 
37 static int
38 check_for_utf8(char *b)
39 {
40 	for (;;) {
41 		while (*b != '\0' && isspace(*b))
42 			b++;
43 		if (*b == '\0')
44 			break;
45 		if (!has_prefix(b, "charset=")) {
46 			while (*b != '\0' && *b != ';')
47 				b++;
48 			if (*b == '\0')
49 				break;
50 			b++;
51 			continue;
52 		}
53 
54 		/* is charset= */
55 		b += strlen("charset=");
56 		/* TODO: improve the matching */
57 		return has_prefix(b, "ASCII") || has_prefix(b, "ascii") ||
58 			has_prefix(b, "UTF-8") || has_prefix(b, "utf-8");
59 	}
60 
61 	return 1;
62 }
63 
64 int
65 setup_parser_for(struct tab *tab)
66 {
67 	char			*b, buf[GEMINI_URL_LEN] = {0};
68 	struct parser_table	*t;
69 
70         memcpy(buf, tab->meta, sizeof(tab->meta));
71 
72 	for (b = buf; *b != ';' && *b != '\0'; ++b)
73 		;
74 
75 	if (*b == ';') {
76 		*b = '\0';
77 		++b;
78 	}
79 
80 	if (!check_for_utf8(b))
81 		return 0;
82 
83 	for (t = ptable; t->mediatype != NULL; ++t) {
84 		if (!fnmatch(t->mediatype, buf, 0)) {
85 			t->parserinit(&tab->buffer.page);
86 			return 1;
87 		}
88 	}
89 
90 	return 0;
91 }