1 | /// Compute the display width of `text` |
2 | /// |
3 | /// # Examples |
4 | /// |
5 | /// **Note:** When the `unicode` Cargo feature is disabled, all characters are presumed to take up |
6 | /// 1 width. With the feature enabled, function will correctly deal with [combining characters] in |
7 | /// their decomposed form (see [Unicode equivalence]). |
8 | /// |
9 | /// An example of a decomposed character is “é”, which can be decomposed into: “e” followed by a |
10 | /// combining acute accent: “◌́”. Without the `unicode` Cargo feature, every `char` has a width of |
11 | /// 1. This includes the combining accent: |
12 | /// |
13 | /// ## Emojis and CJK Characters |
14 | /// |
15 | /// Characters such as emojis and [CJK characters] used in the |
16 | /// Chinese, Japanese, and Korean languages are seen as double-width, |
17 | /// even if the `unicode-width` feature is disabled: |
18 | /// |
19 | /// # Limitations |
20 | /// |
21 | /// The displayed width of a string cannot always be computed from the |
22 | /// string alone. This is because the width depends on the rendering |
23 | /// engine used. This is particularly visible with [emoji modifier |
24 | /// sequences] where a base emoji is modified with, e.g., skin tone or |
25 | /// hair color modifiers. It is up to the rendering engine to detect |
26 | /// this and to produce a suitable emoji. |
27 | /// |
28 | /// A simple example is “❤️”, which consists of “❤” (U+2764: Black |
29 | /// Heart Symbol) followed by U+FE0F (Variation Selector-16). By |
30 | /// itself, “❤” is a black heart, but if you follow it with the |
31 | /// variant selector, you may get a wider red heart. |
32 | /// |
33 | /// A more complex example would be “👨🦰” which should depict a man |
34 | /// with red hair. Here the computed width is too large — and the |
35 | /// width differs depending on the use of the `unicode-width` feature: |
36 | /// |
37 | /// This happens because the grapheme consists of three code points: |
38 | /// “👨” (U+1F468: Man), Zero Width Joiner (U+200D), and “🦰” |
39 | /// (U+1F9B0: Red Hair). You can see them above in the test. With |
40 | /// `unicode-width` enabled, the ZWJ is correctly seen as having zero |
41 | /// width, without it is counted as a double-width character. |
42 | /// |
43 | /// ## Terminal Support |
44 | /// |
45 | /// Modern browsers typically do a great job at combining characters |
46 | /// as shown above, but terminals often struggle more. As an example, |
47 | /// Gnome Terminal version 3.38.1, shows “❤️” as a big red heart, but |
48 | /// shows "👨🦰" as “👨🦰”. |
49 | /// |
50 | /// [combining characters]: https://en.wikipedia.org/wiki/Combining_character |
51 | /// [Unicode equivalence]: https://en.wikipedia.org/wiki/Unicode_equivalence |
52 | /// [CJK characters]: https://en.wikipedia.org/wiki/CJK_characters |
53 | /// [emoji modifier sequences]: https://unicode.org/emoji/charts/full-emoji-modifiers.html |
54 | #[inline (never)] |
55 | pub(crate) fn display_width(text: &str) -> usize { |
56 | let mut width = 0; |
57 | |
58 | let mut control_sequence = false; |
59 | let control_terminate: char = 'm' ; |
60 | |
61 | for ch in text.chars() { |
62 | if ch.is_ascii_control() { |
63 | control_sequence = true; |
64 | } else if control_sequence && ch == control_terminate { |
65 | control_sequence = false; |
66 | continue; |
67 | } |
68 | |
69 | if !control_sequence { |
70 | width += ch_width(ch); |
71 | } |
72 | } |
73 | width |
74 | } |
75 | |
76 | #[cfg (feature = "unicode" )] |
77 | fn ch_width(ch: char) -> usize { |
78 | unicode_width::UnicodeWidthChar::width(ch).unwrap_or(0) |
79 | } |
80 | |
81 | #[cfg (not(feature = "unicode" ))] |
82 | fn ch_width(_: char) -> usize { |
83 | 1 |
84 | } |
85 | |
86 | #[cfg (test)] |
87 | mod tests { |
88 | use super::*; |
89 | |
90 | #[cfg (feature = "unicode" )] |
91 | use unicode_width::UnicodeWidthChar; |
92 | |
93 | #[test] |
94 | fn emojis_have_correct_width() { |
95 | use unic_emoji_char::is_emoji; |
96 | |
97 | // Emojis in the Basic Latin (ASCII) and Latin-1 Supplement |
98 | // blocks all have a width of 1 column. This includes |
99 | // characters such as '#' and '©'. |
100 | for ch in ' \u{1}' ..' \u{FF}' { |
101 | if is_emoji(ch) { |
102 | let desc = format!("{:?} U+{:04X}" , ch, ch as u32); |
103 | |
104 | #[cfg (feature = "unicode" )] |
105 | assert_eq!(ch.width().unwrap(), 1, "char: {desc}" ); |
106 | |
107 | #[cfg (not(feature = "unicode" ))] |
108 | assert_eq!(ch_width(ch), 1, "char: {desc}" ); |
109 | } |
110 | } |
111 | |
112 | // Emojis in the remaining blocks of the Basic Multilingual |
113 | // Plane (BMP), in the Supplementary Multilingual Plane (SMP), |
114 | // and in the Supplementary Ideographic Plane (SIP), are all 1 |
115 | // or 2 columns wide when unicode-width is used, and always 2 |
116 | // columns wide otherwise. This includes all of our favorite |
117 | // emojis such as 😊. |
118 | for ch in ' \u{FF}' ..' \u{2FFFF}' { |
119 | if is_emoji(ch) { |
120 | let desc = format!("{:?} U+{:04X}" , ch, ch as u32); |
121 | |
122 | #[cfg (feature = "unicode" )] |
123 | assert!(ch.width().unwrap() <= 2, "char: {desc}" ); |
124 | |
125 | #[cfg (not(feature = "unicode" ))] |
126 | assert_eq!(ch_width(ch), 1, "char: {desc}" ); |
127 | } |
128 | } |
129 | |
130 | // The remaining planes contain almost no assigned code points |
131 | // and thus also no emojis. |
132 | } |
133 | |
134 | #[test] |
135 | #[cfg (feature = "unicode" )] |
136 | fn display_width_works() { |
137 | assert_eq!("Café Plain" .len(), 11); // “é” is two bytes |
138 | assert_eq!(display_width("Café Plain" ), 10); |
139 | } |
140 | |
141 | #[test] |
142 | #[cfg (feature = "unicode" )] |
143 | fn display_width_narrow_emojis() { |
144 | assert_eq!(display_width("⁉" ), 1); |
145 | } |
146 | |
147 | #[test] |
148 | #[cfg (feature = "unicode" )] |
149 | fn display_width_narrow_emojis_variant_selector() { |
150 | assert_eq!(display_width("⁉ \u{fe0f}" ), 1); |
151 | } |
152 | |
153 | #[test] |
154 | #[cfg (feature = "unicode" )] |
155 | fn display_width_emojis() { |
156 | assert_eq!(display_width("😂😭🥺🤣✨😍🙏🥰😊🔥" ), 20); |
157 | } |
158 | } |
159 | |