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 <assert.h>
25 #include <stddef.h>
26 #include <stdint.h>
27 #include <wchar.h>
28 
29 #include "telescope.h"
30 #include "utf8.h"
31 
32 #define UTF8_ACCEPT 0
33 #define UTF8_REJECT 1
34 
35 static const uint8_t utf8d[] = {
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, // 00..1f
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, // 20..3f
38 	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
39 	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
40 	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
41 	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
42 	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
43 	0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
44 	0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
45 	0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
46 	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
47 	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
48 	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
49 	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
50 };
51 
52 uint32_t
53 utf8_decode(uint32_t* restrict state, uint32_t* restrict codep, uint8_t byte) {
54 	uint32_t type = utf8d[byte];
55 
56 	*codep = (*state != UTF8_ACCEPT) ?
57 		(byte & 0x3fu) | (*codep << 6) :
58 		(0xff >> type) & (byte);
59 
60 	*state = utf8d[256 + *state*16 + type];
61 	return *state;
62 }
63 
64 
65 /* end of the converter, utility functions ahead */
66 
67 /* encode cp in s.  s must be at least 4 bytes wide */
68 size_t
69 utf8_encode(uint32_t cp, char *s)
70 {
71 	if (cp <= 0x7F) {
72                 *s = (uint8_t)cp;
73 		return 1;
74 	} else if (cp <= 0x7FF) {
75                 s[1] = (uint8_t)(( cp        & 0x3F ) + 0x80);
76 		s[0] = (uint8_t)(((cp >>  6) & 0x1F) + 0xC0);
77 		return 2;
78 	} else if (cp <= 0xFFFF) {
79                 s[2] = (uint8_t)(( cp        & 0x3F) + 0x80);
80 		s[1] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
81 		s[0] = (uint8_t)(((cp >> 12) & 0x0F) + 0xE0);
82 		return 3;
83 	} else if (cp <= 0x10FFFF) {
84                 s[3] = (uint8_t)(( cp        & 0x3F) + 0x80);
85 		s[2] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
86 		s[1] = (uint8_t)(((cp >> 12) & 0x3F) + 0x80);
87 		s[0] = (uint8_t)(((cp >> 18) & 0x07) + 0xF0);
88 		return 4;
89 	} else {
90 		s[0] = '\0';
91 		return 0;
92 	}
93 }
94 
95 char *
96 utf8_nth(char *s, size_t n)
97 {
98 	size_t i;
99 	uint32_t cp = 0, state = 0;
100 
101 	for (i = 0; *s && i < n; ++s)
102 		if (!utf8_decode(&state, &cp, *s))
103 			++i;
104 
105 	if (state != UTF8_ACCEPT)
106 		return NULL;
107 	if (i == n)
108 		return s;
109 	return NULL;
110 }
111 
112 size_t
113 utf8_cplen(char *s)
114 {
115 	uint32_t cp = 0, state = 0;
116 	size_t len;
117 
118 	len = 0;
119 	for (; *s; ++s)
120 		if (!utf8_decode(&state, &cp, *s))
121 			len++;
122 	return len;
123 }
124 
125 /* returns only 0, 1, 2 or 8.  assumes sizeof(wchar_t) is 4 */
126 size_t
127 utf8_chwidth(uint32_t cp)
128 {
129 	/* XXX: if we're running on a platform where sizeof(wchar_t)
130 	 * == 2 what to do?  The manpage for wcwidth and wcs isn't
131 	 * clear about the encoding, but if it's 16 bit wide I assume
132 	 * it must use UTF-16... right? */
133 	assert(sizeof(wchar_t) == 4);
134 
135 	/*
136 	 * quick and dirty fix for the tabs.  In the future we may
137 	 * want to expand tabs into N spaces, but for the time being
138 	 * this seems to be good enough (tm).
139 	 */
140 	if (cp == '\t')
141 		return 8;
142 
143 	return wcwidth((wchar_t)cp);
144 }
145 
146 /* NOTE: n is the number of codepoints, NOT the byte length.  In
147  * other words, s MUST be NUL-terminated. */
148 size_t
149 utf8_snwidth(const char *s, size_t n)
150 {
151 	size_t i, tot;
152 	uint32_t cp = 0, state = 0;
153 
154 	tot = 0;
155 	for (i = 0; *s && i < n; ++s)
156 		if (!utf8_decode(&state, &cp, *s)) {
157 			i++;
158 			tot += utf8_chwidth(cp);
159 		}
160 
161 	return tot;
162 }
163 
164 size_t
165 utf8_swidth(const char *s)
166 {
167 	size_t tot;
168 	uint32_t cp = 0, state = 0;
169 
170 	tot = 0;
171 	for (; *s; ++s)
172 		if (!utf8_decode(&state, &cp, *s))
173 			tot += utf8_chwidth(cp);
174 
175 	return tot;
176 }
177 
178 size_t
179 utf8_swidth_between(const char *str, const char *end)
180 {
181 	size_t tot;
182 	uint32_t cp = 0, state = 0;
183 
184 	tot = 0;
185 	for (; *str && str < end; ++str)
186 		if (!utf8_decode(&state, &cp, *str))
187 			tot += utf8_chwidth(cp);
188 	return tot;
189 }
190 
191 char *
192 utf8_next_cp(const char *s)
193 {
194 	uint32_t cp = 0, state = 0;
195 
196 	for (; *s; ++s)
197 		if (!utf8_decode(&state, &cp, *s))
198 			break;
199 	return (char*)s+1;
200 }
201 
202 char *
203 utf8_prev_cp(const char *start, const char *base)
204 {
205 	uint8_t c;
206 
207 	for (; start > base; start--) {
208 		c = *start;
209                 if ((c & 0xC0) != 0x80)
210 			return (char*)start;
211 	}
212 
213 	return (char*)base;
214 }