1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
/// Code points that will always be invisible (zero width).
///
/// See also `FontFace::ignore_character`.
#[inline]
pub(super) fn invisible_char(c: char) -> bool {
if c == '\r' {
// A character most vile and pernicious. Don't display it.
return true;
}
// See https://github.com/emilk/egui/issues/336
// From https://www.fileformat.info/info/unicode/category/Cf/list.htm
// TODO(emilk): heed bidi characters
matches!(
c,
'\u{200B}' // ZERO WIDTH SPACE
| '\u{200C}' // ZERO WIDTH NON-JOINER
| '\u{200D}' // ZERO WIDTH JOINER
| '\u{200E}' // LEFT-TO-RIGHT MARK
| '\u{200F}' // RIGHT-TO-LEFT MARK
| '\u{202A}' // LEFT-TO-RIGHT EMBEDDING
| '\u{202B}' // RIGHT-TO-LEFT EMBEDDING
| '\u{202C}' // POP DIRECTIONAL FORMATTING
| '\u{202D}' // LEFT-TO-RIGHT OVERRIDE
| '\u{202E}' // RIGHT-TO-LEFT OVERRIDE
| '\u{2060}' // WORD JOINER
| '\u{2061}' // FUNCTION APPLICATION
| '\u{2062}' // INVISIBLE TIMES
| '\u{2063}' // INVISIBLE SEPARATOR
| '\u{2064}' // INVISIBLE PLUS
| '\u{2066}' // LEFT-TO-RIGHT ISOLATE
| '\u{2067}' // RIGHT-TO-LEFT ISOLATE
| '\u{2068}' // FIRST STRONG ISOLATE
| '\u{2069}' // POP DIRECTIONAL ISOLATE
| '\u{206A}' // INHIBIT SYMMETRIC SWAPPING
| '\u{206B}' // ACTIVATE SYMMETRIC SWAPPING
| '\u{206C}' // INHIBIT ARABIC FORM SHAPING
| '\u{206D}' // ACTIVATE ARABIC FORM SHAPING
| '\u{206E}' // NATIONAL DIGIT SHAPES
| '\u{206F}' // NOMINAL DIGIT SHAPES
| '\u{FEFF}' // ZERO WIDTH NO-BREAK SPACE
)
}
#[inline]
pub(super) fn is_cjk_ideograph(c: char) -> bool {
('\u{4E00}' <= c && c <= '\u{9FFF}')
|| ('\u{3400}' <= c && c <= '\u{4DBF}')
|| ('\u{2B740}' <= c && c <= '\u{2B81F}')
}
#[inline]
pub(super) fn is_kana(c: char) -> bool {
('\u{3040}' <= c && c <= '\u{309F}') // Hiragana block
|| ('\u{30A0}' <= c && c <= '\u{30FF}') // Katakana block
}
#[inline]
pub(super) fn is_cjk(c: char) -> bool {
// TODO(bigfarts): Add support for Korean Hangul.
is_cjk_ideograph(c) || is_kana(c)
}
#[inline]
pub(super) fn is_cjk_break_allowed(c: char) -> bool {
// See: https://en.wikipedia.org/wiki/Line_breaking_rules_in_East_Asian_languages#Characters_not_permitted_on_the_start_of_a_line.
!")]｝〕〉》」』】〙〗〟'\"｠»ヽヾーァィゥェォッャュョヮヵヶぁぃぅぇぉっゃゅょゎゕゖㇰㇱㇲㇳㇴㇵㇶㇷㇸㇹㇺㇻㇼㇽㇾㇿ々〻‐゠–〜?!‼⁇⁈⁉・、:;,。.！％），．：；？］”’…".contains(c)
}
/// Returns `true` if the character is a Unicode combining mark (categories Mn, Mc, Me).
///
/// These characters modify the preceding base character and should not be
/// rendered as standalone replacement glyphs when the shaper can't handle them.
#[inline]
pub(super) fn is_combining_mark(c: char) -> bool {
use unicode_general_category::{GeneralCategory, get_general_category};
matches!(
get_general_category(c),
GeneralCategory::NonspacingMark
| GeneralCategory::SpacingMark
| GeneralCategory::EnclosingMark
)
}