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 "telescope.h"
25 
26 #include <assert.h>
27 #include <stddef.h>
28 #include <stdint.h>
29 #include <wchar.h>
30 
31 #define UTF8_ACCEPT 0
32 #define UTF8_REJECT 1
33 
34 static const uint8_t utf8d[] = {
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, // 00..1f
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, // 20..3f
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, // 40..5f
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, // 60..7f
39 	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
40 	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
41 	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
42 	0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
43 	0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
44 	0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
45 	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
46 	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
47 	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
48 	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
49 };
50 
51 uint32_t
52 utf8_decode(uint32_t* restrict state, uint32_t* restrict codep, uint8_t byte) {
53 	uint32_t type = utf8d[byte];
54 
55 	*codep = (*state != UTF8_ACCEPT) ?
56 		(byte & 0x3fu) | (*codep << 6) :
57 		(0xff >> type) & (byte);
58 
59 	*state = utf8d[256 + *state*16 + type];
60 	return *state;
61 }
62 
63 
64 /* end of the converter, utility functions ahead */
65 
66 /* encode cp in s.  s must be at least 4 bytes wide */
67 size_t
68 utf8_encode(uint32_t cp, char *s)
69 {
70 	if (cp <= 0x7F) {
71                 *s = (uint8_t)cp;
72 		return 1;
73 	} else if (cp <= 0x7FF) {
74                 s[1] = (uint8_t)(( cp        & 0x3F ) + 0x80);
75 		s[0] = (uint8_t)(((cp >>  6) & 0x1F) + 0xC0);
76 		return 2;
77 	} else if (cp <= 0xFFFF) {
78                 s[2] = (uint8_t)(( cp        & 0x3F) + 0x80);
79 		s[1] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
80 		s[0] = (uint8_t)(((cp >> 12) & 0x0F) + 0xE0);
81 		return 3;
82 	} else if (cp <= 0x10FFFF) {
83                 s[3] = (uint8_t)(( cp        & 0x3F) + 0x80);
84 		s[2] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
85 		s[1] = (uint8_t)(((cp >> 12) & 0x3F) + 0x80);
86 		s[0] = (uint8_t)(((cp >> 18) & 0x07) + 0xF0);
87 		return 4;
88 	} else {
89 		s[0] = '\0';
90 		return 0;
91 	}
92 }
93 
94 char *
95 utf8_nth(char *s, size_t n)
96 {
97 	size_t i;
98 	uint32_t cp = 0, state = 0;
99 
100 	for (i = 0; *s && i < n; ++s)
101 		if (!utf8_decode(&state, &cp, *s))
102 			++i;
103 
104 	if (state != UTF8_ACCEPT)
105 		return NULL;
106 	if (i == n)
107 		return s;
108 	return NULL;
109 }
110 
111 size_t
112 utf8_cplen(char *s)
113 {
114 	uint32_t cp = 0, state = 0;
115 	size_t len;
116 
117 	len = 0;
118 	for (; *s; ++s)
119 		if (!utf8_decode(&state, &cp, *s))
120 			len++;
121 	return len;
122 }
123 
124 /* returns only 0, 1, 2 or 8.  assumes sizeof(wchar_t) is 4 */
125 size_t
126 utf8_chwidth(uint32_t cp)
127 {
128 	/* XXX: if we're running on a platform where sizeof(wchar_t)
129 	 * == 2 what to do?  The manpage for wcwidth and wcs isn't
130 	 * clear about the encoding, but if it's 16 bit wide I assume
131 	 * it must use UTF-16... right? */
132 	assert(sizeof(wchar_t) == 4);
133 
134 	/*
135 	 * quick and dirty fix for the tabs.  In the future we may
136 	 * want to expand tabs into N spaces, but for the time being
137 	 * this seems to be good enough (tm).
138 	 */
139 	if (cp == '\t')
140 		return 8;
141 
142 	return wcwidth((wchar_t)cp);
143 }
144 
145 /* NOTE: n is the number of codepoints, NOT the byte length.  In
146  * other words, s MUST be NUL-terminated. */
147 size_t
148 utf8_snwidth(const char *s, size_t n)
149 {
150 	size_t i, tot;
151 	uint32_t cp = 0, state = 0;
152 
153 	tot = 0;
154 	for (i = 0; *s && i < n; ++s)
155 		if (!utf8_decode(&state, &cp, *s)) {
156 			i++;
157 			tot += utf8_chwidth(cp);
158 		}
159 
160 	return tot;
161 }
162 
163 size_t
164 utf8_swidth(const char *s)
165 {
166 	size_t tot;
167 	uint32_t cp = 0, state = 0;
168 
169 	tot = 0;
170 	for (; *s; ++s)
171 		if (!utf8_decode(&state, &cp, *s))
172 			tot += utf8_chwidth(cp);
173 
174 	return tot;
175 }
176 
177 size_t
178 utf8_swidth_between(const char *str, const char *end)
179 {
180 	size_t tot;
181 	uint32_t cp = 0, state = 0;
182 
183 	tot = 0;
184 	for (; *str && str < end; ++str)
185 		if (!utf8_decode(&state, &cp, *str))
186 			tot += utf8_chwidth(cp);
187 	return tot;
188 }
189 
190 char *
191 utf8_next_cp(const char *s)
192 {
193 	uint32_t cp = 0, state = 0;
194 
195 	for (; *s; ++s)
196 		if (!utf8_decode(&state, &cp, *s))
197 			break;
198 	return (char*)s+1;
199 }
200 
201 char *
202 utf8_prev_cp(const char *start, const char *base)
203 {
204 	uint8_t c;
205 
206 	for (; start > base; start--) {
207 		c = *start;
208                 if ((c & 0xC0) != 0x80)
209 			return (char*)start;
210 	}
211 
212 	return (char*)base;
213 }