1 /* Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
2  *
3  * Permission is hereby granted, free of charge, to any person
4  * obtaining a copy of this software and associated documentation
5  * files (the "Software"), to deal in the Software without
6  * restriction, including without limitation the rights to use, copy,
7  * modify, merge, publish, distribute, sublicense, and/or sell copies
8  * of the Software, and to permit persons to whom the Software is
9  * furnished to do so, subject to the following conditions:
10  *
11  * The above copyright notice and this permission notice shall be
12  * included in all copies or substantial portions of the Software.
13  *
14  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17  * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
18  * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
19  * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
20  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21  * SOFTWARE.
22  */
23 
24 #include "gmid.h"
25 
26 #include <stddef.h>
27 #include <stdint.h>
28 
29 #define UTF8_ACCEPT 0
30 #define UTF8_REJECT 1
31 
32 static const uint8_t utf8d[] = {
33 	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
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, // 20..3f
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, // 40..5f
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, // 60..7f
37 	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
38 	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
39 	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
40 	0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
41 	0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
42 	0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
43 	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
44 	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
45 	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
46 	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
47 };
48 
49 static inline uint32_t
50 utf8_decode(uint32_t* state, uint32_t* codep, uint8_t byte) {
51 	uint32_t type = utf8d[byte];
52 
53 	*codep = (*state != UTF8_ACCEPT) ?
54 		(byte & 0x3fu) | (*codep << 6) :
55 		(0xff >> type) & (byte);
56 
57 	*state = utf8d[256 + *state*16 + type];
58 	return *state;
59 }
60 
61 /* for the iri parser.  Modelled after printCodePoints */
62 int
63 valid_multibyte_utf8(struct parser *p)
64 {
65 	uint32_t cp = 0, state = 0;
66 
67         for (; *p->iri; p->iri++)
68 		if (!utf8_decode(&state, &cp, *p->iri))
69 			break;
70 
71 	/* reject the ASCII range */
72 	if (state || cp <= 0x7F) {
73 		/* XXX: do some error recovery? */
74 		if (state)
75 			p->err = "invalid UTF-8 character";
76 		return 0;
77 	}
78 	return 1;
79 }
80 
81 char *
82 utf8_nth(char *s, size_t n)
83 {
84 	size_t i;
85 	uint32_t cp = 0, state = 0;
86 
87 	for (i = 0; *s && i < n; ++s)
88 		if (!utf8_decode(&state, &cp, *s))
89 			++i;
90 
91 	if (state != UTF8_ACCEPT)
92 		return NULL;
93 	if (i == n)
94 		return s;
95 	return NULL;
96 }