fn combining_char(accent: char) -> Option<char> {
Some(match accent {
'\'' => '\u{0301}', '`' => '\u{0300}', '^' => '\u{0302}', '"' => '\u{0308}', '~' => '\u{0303}', '=' => '\u{0304}', '.' => '\u{0307}', 'u' => '\u{0306}', 'v' => '\u{030C}', 'H' => '\u{030B}', 'c' => '\u{0327}', 'k' => '\u{0328}', 'r' => '\u{030A}', 'b' => '\u{0331}', 'd' => '\u{0323}', 't' => '\u{0361}', _ => return None,
})
}
fn precomposed_lower(accent: char, base: char) -> Option<char> {
let c = match (accent, base) {
('\'', 'a') => 'á',
('\'', 'c') => 'ć',
('\'', 'e') => 'é',
('\'', 'g') => 'ǵ',
('\'', 'i') => 'í',
('\'', 'l') => 'ĺ',
('\'', 'n') => 'ń',
('\'', 'o') => 'ó',
('\'', 'r') => 'ŕ',
('\'', 's') => 'ś',
('\'', 'u') => 'ú',
('\'', 'y') => 'ý',
('\'', 'z') => 'ź',
('`', 'a') => 'à',
('`', 'e') => 'è',
('`', 'i') => 'ì',
('`', 'o') => 'ò',
('`', 'u') => 'ù',
('`', 'n') => 'ǹ',
('`', 'w') => 'ẁ',
('`', 'y') => 'ỳ',
('^', 'a') => 'â',
('^', 'c') => 'ĉ',
('^', 'e') => 'ê',
('^', 'g') => 'ĝ',
('^', 'h') => 'ĥ',
('^', 'i') => 'î',
('^', 'j') => 'ĵ',
('^', 'o') => 'ô',
('^', 's') => 'ŝ',
('^', 'u') => 'û',
('^', 'w') => 'ŵ',
('^', 'y') => 'ŷ',
('^', 'z') => 'ẑ',
('"', 'a') => 'ä',
('"', 'e') => 'ë',
('"', 'h') => 'ḧ',
('"', 'i') => 'ï',
('"', 'o') => 'ö',
('"', 't') => 'ẗ',
('"', 'u') => 'ü',
('"', 'w') => 'ẅ',
('"', 'x') => 'ẍ',
('"', 'y') => 'ÿ',
('~', 'a') => 'ã',
('~', 'e') => 'ẽ',
('~', 'i') => 'ĩ',
('~', 'n') => 'ñ',
('~', 'o') => 'õ',
('~', 'u') => 'ũ',
('~', 'v') => 'ṽ',
('~', 'y') => 'ỹ',
('=', 'a') => 'ā',
('=', 'e') => 'ē',
('=', 'g') => 'ḡ',
('=', 'i') => 'ī',
('=', 'o') => 'ō',
('=', 'u') => 'ū',
('=', 'y') => 'ȳ',
('.', 'b') => 'ḃ',
('.', 'c') => 'ċ',
('.', 'd') => 'ḋ',
('.', 'e') => 'ė',
('.', 'f') => 'ḟ',
('.', 'g') => 'ġ',
('.', 'h') => 'ḣ',
('.', 'i') => 'i', ('.', 'm') => 'ṁ',
('.', 'n') => 'ṅ',
('.', 'o') => 'ȯ',
('.', 'p') => 'ṗ',
('.', 's') => 'ṡ',
('.', 't') => 'ṫ',
('.', 'w') => 'ẇ',
('.', 'x') => 'ẋ',
('.', 'y') => 'ẏ',
('.', 'z') => 'ż',
('v', 'a') => 'ǎ',
('v', 'c') => 'č',
('v', 'd') => 'ď',
('v', 'e') => 'ě',
('v', 'g') => 'ǧ',
('v', 'h') => 'ȟ',
('v', 'i') => 'ǐ',
('v', 'j') => 'ǰ',
('v', 'k') => 'ǩ',
('v', 'l') => 'ľ',
('v', 'n') => 'ň',
('v', 'o') => 'ǒ',
('v', 'r') => 'ř',
('v', 's') => 'š',
('v', 't') => 'ť',
('v', 'u') => 'ǔ',
('v', 'z') => 'ž',
('u', 'a') => 'ă',
('u', 'e') => 'ĕ',
('u', 'g') => 'ğ',
('u', 'i') => 'ĭ',
('u', 'o') => 'ŏ',
('u', 'u') => 'ŭ',
('H', 'o') => 'ő',
('H', 'u') => 'ű',
('H', 'y') => 'ӳ',
('c', 'c') => 'ç',
('c', 'd') => 'ḑ',
('c', 'e') => 'ȩ',
('c', 'g') => 'ģ',
('c', 'h') => 'ḩ',
('c', 'k') => 'ķ',
('c', 'l') => 'ļ',
('c', 'n') => 'ņ',
('c', 'r') => 'ŗ',
('c', 's') => 'ş',
('c', 't') => 'ţ',
('k', 'a') => 'ą',
('k', 'e') => 'ę',
('k', 'i') => 'į',
('k', 'o') => 'ǫ',
('k', 'u') => 'ų',
('r', 'a') => 'å',
('r', 'u') => 'ů',
('r', 'w') => 'ẘ',
('r', 'y') => 'ẙ',
_ => return None,
};
Some(c)
}
pub fn compose_accent(accent: char, base: char) -> String {
let lower = base.to_ascii_lowercase();
if let Some(c) = precomposed_lower(accent, lower) {
if base.is_uppercase() {
return c.to_uppercase().collect();
}
return c.to_string();
}
match combining_char(accent) {
Some(mark) => {
let mut s = String::with_capacity(3);
s.push(base);
s.push(mark);
s
}
None => base.to_string(),
}
}
pub fn is_accent_command(name: &str) -> bool {
matches!(
name,
"'" | "`" | "\"" | "^" | "~" | "=" | "." | "u" | "v" | "H" | "c" | "k" | "r" | "b" | "d"
| "t"
)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn composes_common_latin1_accents() {
assert_eq!(compose_accent('"', 'u'), "ü");
assert_eq!(compose_accent('\'', 'e'), "é");
assert_eq!(compose_accent('`', 'a'), "à");
assert_eq!(compose_accent('^', 'o'), "ô");
assert_eq!(compose_accent('~', 'n'), "ñ");
assert_eq!(compose_accent('c', 'c'), "ç");
}
#[test]
fn composes_latin_extended_accents() {
assert_eq!(compose_accent('v', 's'), "š");
assert_eq!(compose_accent('v', 'z'), "ž");
assert_eq!(compose_accent('v', 'c'), "č");
assert_eq!(compose_accent('u', 'g'), "ğ");
assert_eq!(compose_accent('H', 'o'), "ő");
assert_eq!(compose_accent('=', 'a'), "ā");
assert_eq!(compose_accent('k', 'a'), "ą");
assert_eq!(compose_accent('r', 'u'), "ů");
}
#[test]
fn uppercases_derived_from_lowercase_table() {
assert_eq!(compose_accent('"', 'U'), "Ü");
assert_eq!(compose_accent('\'', 'E'), "É");
assert_eq!(compose_accent('v', 'S'), "Š");
assert_eq!(compose_accent('c', 'C'), "Ç");
}
#[test]
fn falls_back_to_combining_marks() {
assert_eq!(compose_accent('d', 'h'), "h\u{0323}");
assert_eq!(compose_accent('b', 'd'), "d\u{0331}");
assert_eq!(compose_accent('t', 's'), "s\u{0361}");
}
#[test]
fn dotless_i_dots_to_i() {
assert_eq!(compose_accent('.', 'i'), "i");
}
#[test]
fn accent_command_names() {
assert!(is_accent_command("'"));
assert!(is_accent_command("`"));
assert!(is_accent_command("\""));
assert!(is_accent_command("^"));
assert!(is_accent_command("~"));
assert!(is_accent_command("="));
assert!(is_accent_command("."));
for name in ["u", "v", "H", "c", "k", "r", "b", "d", "t"] {
assert!(is_accent_command(name), "{name}");
}
assert!(!is_accent_command("cline"));
assert!(!is_accent_command("textbf"));
assert!(!is_accent_command("today"));
assert!(!is_accent_command("underbrace"));
}
}