xref: /openbsd/usr.bin/tmux/utf8-combined.c (revision 3d40d63a)
1 /* $OpenBSD: utf8-combined.c,v 1.4 2025/01/01 15:17:36 nicm Exp $ */
2 
3 /*
4  * Copyright (c) 2023 Nicholas Marriott <nicholas.marriott@gmail.com>
5  *
6  * Permission to use, copy, modify, and distribute this software for any
7  * purpose with or without fee is hereby granted, provided that the above
8  * copyright notice and this permission notice appear in all copies.
9  *
10  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
13  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
14  * WHATSOEVER RESULTING FROM LOSS OF MIND, USE, DATA OR PROFITS, WHETHER
15  * IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
16  * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
17  */
18 
19 #include <sys/types.h>
20 
21 #include <stdlib.h>
22 #include <string.h>
23 #include <wchar.h>
24 
25 #include "tmux.h"
26 
27 /* Has this got a zero width joiner at the end? */
28 int
utf8_has_zwj(const struct utf8_data * ud)29 utf8_has_zwj(const struct utf8_data *ud)
30 {
31 	if (ud->size < 3)
32 		return (0);
33 	return (memcmp(ud->data + ud->size - 3, "\342\200\215", 3) == 0);
34 }
35 
36 /* Is this a zero width joiner? */
37 int
utf8_is_zwj(const struct utf8_data * ud)38 utf8_is_zwj(const struct utf8_data *ud)
39 {
40 	if (ud->size != 3)
41 		return (0);
42 	return (memcmp(ud->data, "\342\200\215", 3) == 0);
43 }
44 
45 /* Is this a variation selector? */
46 int
utf8_is_vs(const struct utf8_data * ud)47 utf8_is_vs(const struct utf8_data *ud)
48 {
49 	if (ud->size != 3)
50 		return (0);
51 	return (memcmp(ud->data, "\357\270\217", 3) == 0);
52 }
53 
54 /* Is this in the modifier table? */
55 int
utf8_is_modifier(const struct utf8_data * ud)56 utf8_is_modifier(const struct utf8_data *ud)
57 {
58 	wchar_t	wc;
59 
60 	if (utf8_towc(ud, &wc) != UTF8_DONE)
61 		return (0);
62 	switch (wc) {
63 	case 0x1F1E6:
64 	case 0x1F1E7:
65 	case 0x1F1E8:
66 	case 0x1F1E9:
67 	case 0x1F1EA:
68 	case 0x1F1EB:
69 	case 0x1F1EC:
70 	case 0x1F1ED:
71 	case 0x1F1EE:
72 	case 0x1F1EF:
73 	case 0x1F1F0:
74 	case 0x1F1F1:
75 	case 0x1F1F2:
76 	case 0x1F1F3:
77 	case 0x1F1F4:
78 	case 0x1F1F5:
79 	case 0x1F1F6:
80 	case 0x1F1F7:
81 	case 0x1F1F8:
82 	case 0x1F1F9:
83 	case 0x1F1FA:
84 	case 0x1F1FB:
85 	case 0x1F1FC:
86 	case 0x1F1FD:
87 	case 0x1F1FE:
88 	case 0x1F1FF:
89 	case 0x1F3FB:
90 	case 0x1F3FC:
91 	case 0x1F3FD:
92 	case 0x1F3FE:
93 	case 0x1F3FF:
94 		return (1);
95 	}
96 	return (0);
97 }
98