1 /*
2 * Copyright (C) 2017 The Android Open Source Project
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * * Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in
12 * the documentation and/or other materials provided with the
13 * distribution.
14 *
15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
16 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
17 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
18 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
19 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
20 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
21 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
22 * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
23 * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
25 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28
29 #include <wchar.h>
30
31 #include "private/icu.h"
32
wcwidth(wchar_t wc)33 int wcwidth(wchar_t wc) {
34 // Fast-path ASCII.
35 if (wc >= 0x20 && wc < 0x7f) return 1;
36
37 // ASCII NUL is a special case.
38 if (wc == 0) return 0;
39
40 // C0.
41 if (wc < ' ' || (wc >= 0x7f && wc <= 0xa0)) return -1;
42
43 // Now for the i18n part. This isn't defined or standardized, so a lot of the choices are
44 // pretty arbitrary. See https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c for more details.
45
46 // Fancy unicode control characters?
47 switch (__icu_charType(wc)) {
48 case -1:
49 // No icu4c available; give up.
50 return -1;
51 case U_CONTROL_CHAR:
52 return -1;
53 case U_NON_SPACING_MARK:
54 case U_ENCLOSING_MARK:
55 return 0;
56 case U_FORMAT_CHAR:
57 // A special case for soft hyphen (U+00AD) to match historical practice.
58 // See the tests for more commentary.
59 return (wc == 0x00ad) ? 1 : 0;
60 }
61
62 // Medial and final jamo render as zero width when used correctly,
63 // so we handle them specially rather than relying on East Asian Width.
64 switch (__icu_getIntPropertyValue(wc, UCHAR_HANGUL_SYLLABLE_TYPE)) {
65 case U_HST_VOWEL_JAMO:
66 case U_HST_TRAILING_JAMO:
67 return 0;
68 case U_HST_LEADING_JAMO:
69 case U_HST_LV_SYLLABLE:
70 case U_HST_LVT_SYLLABLE:
71 return 2;
72 }
73
74 // Hangeul choseong filler U+115F is default ignorable, so we check default
75 // ignorability only after we've already handled Hangeul jamo above.
76 if (__icu_hasBinaryProperty(wc, UCHAR_DEFAULT_IGNORABLE_CODE_POINT, nullptr)) return 0;
77
78 // A few weird special cases where EastAsianWidth is not helpful for us.
79 if (wc >= 0x3248 && wc <= 0x4dff) {
80 // Circled two-digit CJK "speed sign" numbers. EastAsianWidth is ambiguous,
81 // but wide makes more sense.
82 if (wc <= 0x324f) return 2;
83 // Hexagrams. EastAsianWidth is neutral, but wide seems better.
84 if (wc >= 0x4dc0) return 2;
85 }
86
87 // The EastAsianWidth property is at least defined by the Unicode standard!
88 // https://www.unicode.org/reports/tr11/
89 switch (__icu_getIntPropertyValue(wc, UCHAR_EAST_ASIAN_WIDTH)) {
90 case U_EA_AMBIGUOUS:
91 case U_EA_HALFWIDTH:
92 case U_EA_NARROW:
93 case U_EA_NEUTRAL:
94 return 1;
95 case U_EA_FULLWIDTH:
96 case U_EA_WIDE:
97 return 2;
98 }
99
100 return 0;
101 }
102