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 static inline uint32_t
53 decode(uint32_t* restrict state, uint32_t* restrict codep, uint8_t byte)
54 {
55 	uint32_t type = utf8d[byte];
56 
57 	*codep = (*state != UTF8_ACCEPT) ?
58 		(byte & 0x3fu) | (*codep << 6) :
59 		(0xff >> type) & (byte);
60 
61 	*state = utf8d[256 + *state*16 + type];
62 	return *state;
63 }
64 
65 
66 /* end of the converter, utility functions ahead */
67 
68 #define ZERO_WIDTH_SPACE 0x200B
69 
70 /* public version of decode */
71 uint32_t
72 utf8_decode(uint32_t* restrict state, uint32_t* restrict codep, uint8_t byte)
73 {
74 	return decode(state, codep, byte);
75 }
76 
77 /* encode cp in s.  s must be at least 4 bytes wide */
78 size_t
79 utf8_encode(uint32_t cp, char *s)
80 {
81 	if (cp <= 0x7F) {
82                 *s = (uint8_t)cp;
83 		return 1;
84 	} else if (cp <= 0x7FF) {
85                 s[1] = (uint8_t)(( cp        & 0x3F ) + 0x80);
86 		s[0] = (uint8_t)(((cp >>  6) & 0x1F) + 0xC0);
87 		return 2;
88 	} else if (cp <= 0xFFFF) {
89                 s[2] = (uint8_t)(( cp        & 0x3F) + 0x80);
90 		s[1] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
91 		s[0] = (uint8_t)(((cp >> 12) & 0x0F) + 0xE0);
92 		return 3;
93 	} else if (cp <= 0x10FFFF) {
94                 s[3] = (uint8_t)(( cp        & 0x3F) + 0x80);
95 		s[2] = (uint8_t)(((cp >>  6) & 0x3F) + 0x80);
96 		s[1] = (uint8_t)(((cp >> 12) & 0x3F) + 0x80);
97 		s[0] = (uint8_t)(((cp >> 18) & 0x07) + 0xF0);
98 		return 4;
99 	} else {
100 		s[0] = '\0';
101 		return 0;
102 	}
103 }
104 
105 char *
106 utf8_nth(char *s, size_t n)
107 {
108 	size_t i;
109 	uint32_t cp = 0, state = 0;
110 
111 	for (i = 0; *s && i < n; ++s)
112 		if (!decode(&state, &cp, *s))
113 			++i;
114 
115 	if (state != UTF8_ACCEPT)
116 		return NULL;
117 	if (i == n)
118 		return s;
119 	return NULL;
120 }
121 
122 size_t
123 utf8_cplen(char *s)
124 {
125 	uint32_t cp = 0, state = 0;
126 	size_t len;
127 
128 	len = 0;
129 	for (; *s; ++s)
130 		if (!decode(&state, &cp, *s))
131 			len++;
132 	return len;
133 }
134 
135 /* returns only 0, 1, 2 or 8.  assumes sizeof(wchar_t) is 4 */
136 size_t
137 utf8_chwidth(uint32_t cp)
138 {
139 	/* XXX: if we're running on a platform where sizeof(wchar_t)
140 	 * == 2 what to do?  The manpage for wcwidth and wcs isn't
141 	 * clear about the encoding, but if it's 16 bit wide I assume
142 	 * it must use UTF-16... right? */
143 	assert(sizeof(wchar_t) == 4);
144 
145 	/*
146 	 * quick and dirty fix for the tabs.  In the future we may
147 	 * want to expand tabs into N spaces, but for the time being
148 	 * this seems to be good enough (tm).
149 	 */
150 	if (cp == '\t')
151 		return 8;
152 
153 	return wcwidth((wchar_t)cp);
154 }
155 
156 /* NOTE: n is the number of codepoints, NOT the byte length.  In
157  * other words, s MUST be NUL-terminated. */
158 size_t
159 utf8_snwidth(const char *s, size_t n)
160 {
161 	size_t i, tot;
162 	uint32_t cp = 0, state = 0;
163 
164 	tot = 0;
165 	for (i = 0; *s && i < n; ++s)
166 		if (!decode(&state, &cp, *s)) {
167 			i++;
168 			tot += utf8_chwidth(cp);
169 		}
170 
171 	return tot;
172 }
173 
174 size_t
175 utf8_swidth(const char *s)
176 {
177 	size_t tot;
178 	uint32_t cp = 0, state = 0;
179 
180 	tot = 0;
181 	for (; *s; ++s)
182 		if (!decode(&state, &cp, *s))
183 			tot += utf8_chwidth(cp);
184 
185 	return tot;
186 }
187 
188 size_t
189 utf8_swidth_between(const char *str, const char *end)
190 {
191 	size_t tot;
192 	uint32_t cp = 0, state = 0;
193 
194 	tot = 0;
195 	for (; *str && str < end; ++str)
196 		if (!decode(&state, &cp, *str))
197 			tot += utf8_chwidth(cp);
198 	return tot;
199 }
200 
201 char *
202 utf8_next_cp(const char *s)
203 {
204 	uint32_t cp = 0, state = 0;
205 
206 	for (; *s; ++s)
207 		if (!decode(&state, &cp, *s))
208 			break;
209 	return (char*)s+1;
210 }
211 
212 char *
213 utf8_prev_cp(const char *start, const char *base)
214 {
215 	uint8_t c;
216 
217 	for (; start > base; start--) {
218 		c = *start;
219                 if ((c & 0xC0) != 0x80)
220 			return (char*)start;
221 	}
222 
223 	return (char*)base;
224 }
225 
226 int
227 emojied_line(const char *s, const char **space_ret)
228 {
229 	uint32_t cp = 0, state = 0;
230 
231 	for (; *s; ++s) {
232 		if (!decode(&state, &cp, *s)) {
233 			if (cp == ZERO_WIDTH_SPACE)
234 				continue;
235 			if (cp == ' ') {
236 				*space_ret = s;
237 				return 1;
238 			}
239 			if (!is_emoji(cp))
240 				return 0;
241 		}
242 	}
243 
244 	return 0;
245 }