1
/*
2
 * Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
3
 *
4
 * Permission is hereby granted, free of charge, to any person
5
 * obtaining a copy of this software and associated documentation
6
 * files (the "Software"), to deal in the Software without
7
 * restriction, including without limitation the rights to use, copy,
8
 * modify, merge, publish, distribute, sublicense, and/or sell copies
9
 * of the Software, and to permit persons to whom the Software is
10
 * furnished to do so, subject to the following conditions:
11
 *
12
 * The above copyright notice and this permission notice shall be
13
 * included in all copies or substantial portions of the Software.
14
 *
15
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
19
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
20
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
21
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22
 * SOFTWARE.
23
 */
24

25
#include "gmid.h"
26

27
#include <stddef.h>
28
#include <stdint.h>
29

30
#define UTF8_ACCEPT 0
31
#define UTF8_REJECT 1
32

33
static const uint8_t utf8d[] = {
34
	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f
35
	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f
36
	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f
37
	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f
38
	1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f
39
	7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf
40
	8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df
41
	0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
42
	0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
43
	0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
44
	1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2
45
	1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4
46
	1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6
47
	1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8
48
};
49

50
static inline uint32_t
51
utf8_decode(uint32_t* state, uint32_t* codep, uint8_t byte) {
52
	uint32_t type = utf8d[byte];
53

54
	*codep = (*state != UTF8_ACCEPT) ?
55
		(byte & 0x3fu) | (*codep << 6) :
56
		(0xff >> type) & (byte);
57

58
	*state = utf8d[256 + *state*16 + type];
59
	return *state;
60
}
61

62
/* for the iri parser.  Modelled after printCodePoints */
63
int
64
valid_multibyte_utf8(struct parser *p)
65
{
66
	uint32_t cp = 0, state = 0;
67

68
	for (; *p->iri; p->iri++)
69
		if (!utf8_decode(&state, &cp, *p->iri))
70
			break;
71

72
	/* reject the ASCII range */
73
	if (state || cp <= 0x7F) {
74
		/* XXX: do some error recovery? */
75
		if (state)
76
			p->err = "invalid UTF-8 character";
77
		return 0;
78
	}
79
	return 1;
80
}
81

82
char *
83
utf8_nth(char *s, size_t n)
84
{
85
	size_t i;
86
	uint32_t cp = 0, state = 0;
87

88
	for (i = 0; *s && i < n; ++s)
89
		if (!utf8_decode(&state, &cp, *s))
90
			++i;
91

92
	if (state != UTF8_ACCEPT)
93
		return NULL;
94
	if (i == n)
95
		return s;
96
	return NULL;
97
}