1 /*-
2 * Copyright 2020 Yuri Pankov <yuripv@FreeBSD.org>
3 *
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions
6 * are met:
7 * 1. Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * 2. Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 *
13 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
14 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
16 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
17 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
18 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
19 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
20 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
21 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
22 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
23 * SUCH DAMAGE.
24 */
25
26 #include <locale.h>
27 #include <stdio.h>
28
29 #include <utf8proc.h>
30
31 static int
width_of(int32_t wc)32 width_of(int32_t wc)
33 {
34
35 /*
36 * Hangul Jamo medial vowels and final consonants are more of
37 * a combining character, and should be considered zero-width.
38 */
39 if (wc >= 0x1160 && wc <= 0x11ff)
40 return (0);
41
42 /* No override by default, trust utf8proc's width. */
43 return (utf8proc_charwidth(wc));
44 }
45
46 int
main(void)47 main(void)
48 {
49 int32_t wc;
50 int i, wcw;
51 utf8proc_category_t wcc;
52
53 setlocale(LC_CTYPE, "C.UTF-8");
54
55 printf("%s\n", utf8proc_version());
56
57 for (wc = 0; wc < 0x110000; wc++) {
58 wcc = utf8proc_category(wc);
59 if (wcc == UTF8PROC_CATEGORY_CC)
60 continue;
61 wcw = width_of(wc);
62 if (wcw == 1)
63 continue;
64
65 printf("%04X %d\n", wc, wcw);
66 }
67
68 return (0);
69 }
70