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/x-patch",	textpatch_initparser },
34 	{ "text/*",		textplain_initparser },
35 	{ NULL, NULL}
36 };
37 
38 static int
39 check_for_utf8(char *b)
40 {
41 	for (;;) {
42 		while (*b != '\0' && isspace(*b))
43 			b++;
44 		if (*b == '\0')
45 			break;
46 		if (!has_prefix(b, "charset=")) {
47 			while (*b != '\0' && *b != ';')
48 				b++;
49 			if (*b == '\0')
50 				break;
51 			b++;
52 			continue;
53 		}
54 
55 		/* is charset= */
56 		b += strlen("charset=");
57 		/* TODO: improve the matching */
58 		return has_prefix(b, "ASCII") || has_prefix(b, "ascii") ||
59 			has_prefix(b, "UTF-8") || has_prefix(b, "utf-8");
60 	}
61 
62 	return 1;
63 }
64 
65 int
66 setup_parser_for(struct tab *tab)
67 {
68 	char			*b, buf[GEMINI_URL_LEN] = {0};
69 	struct parser_table	*t;
70 
71         memcpy(buf, tab->meta, sizeof(tab->meta));
72 
73 	for (b = buf; *b != ';' && *b != '\0'; ++b)
74 		;
75 
76 	if (*b == ';') {
77 		*b = '\0';
78 		++b;
79 	}
80 
81 	if (!check_for_utf8(b))
82 		return 0;
83 
84 	for (t = ptable; t->mediatype != NULL; ++t) {
85 		if (!fnmatch(t->mediatype, buf, 0)) {
86 			t->parserinit(&tab->buffer.page);
87 			return 1;
88 		}
89 	}
90 
91 	return 0;
92 }