Remove Cases from NumberingPatterns (#5059)

This commit is contained in:
emilylime 2024-09-30 18:22:46 +03:00 committed by GitHub
parent 7ff83db757
commit 1a24b29d86
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 276 additions and 280 deletions

View File

@ -9,7 +9,6 @@ use typst::foundations::Label;
use typst::introspection::Location; use typst::introspection::Location;
use typst::layout::{Abs, Page}; use typst::layout::{Abs, Page};
use typst::model::{Destination, Numbering}; use typst::model::{Destination, Numbering};
use typst::text::Case;
use crate::content; use crate::content;
use crate::{ use crate::{
@ -246,26 +245,23 @@ impl PdfPageLabel {
return None; return None;
}; };
let (prefix, kind, case) = pat.pieces.first()?; let (prefix, kind) = pat.pieces.first()?;
// If there is a suffix, we cannot use the common style optimisation, // If there is a suffix, we cannot use the common style optimisation,
// since PDF does not provide a suffix field. // since PDF does not provide a suffix field.
let mut style = None; let style = if pat.suffix.is_empty() {
if pat.suffix.is_empty() {
use {typst::model::NumberingKind as Kind, PdfPageLabelStyle as Style}; use {typst::model::NumberingKind as Kind, PdfPageLabelStyle as Style};
match (kind, case) { match kind {
(Kind::Arabic, _) => style = Some(Style::Arabic), Kind::Arabic => Some(Style::Arabic),
(Kind::Roman, Case::Lower) => style = Some(Style::LowerRoman), Kind::LowerRoman => Some(Style::LowerRoman),
(Kind::Roman, Case::Upper) => style = Some(Style::UpperRoman), Kind::UpperRoman => Some(Style::UpperRoman),
(Kind::Letter, Case::Lower) if number <= 26 => { Kind::LowerLatin if number <= 26 => Some(Style::LowerAlpha),
style = Some(Style::LowerAlpha) Kind::LowerLatin if number <= 26 => Some(Style::UpperAlpha),
} _ => None,
(Kind::Letter, Case::Upper) if number <= 26 => {
style = Some(Style::UpperAlpha)
}
_ => {}
} }
} } else {
None
};
// Prefix and offset depend on the style: If it is supported by the PDF // Prefix and offset depend on the style: If it is supported by the PDF
// spec, we use the given prefix and an offset. Otherwise, everything // spec, we use the given prefix and an offset. Otherwise, everything

View File

@ -1,9 +1,10 @@
use std::str::FromStr; use std::str::FromStr;
use chinese_number::{ChineseCase, ChineseCountMethod, ChineseVariant, NumberToChinese}; use chinese_number::{
from_usize_to_chinese_ten_thousand as usize_to_chinese, ChineseCase, ChineseVariant,
};
use comemo::Tracked; use comemo::Tracked;
use ecow::{eco_format, EcoString, EcoVec}; use ecow::{eco_format, EcoString, EcoVec};
use smallvec::{smallvec, SmallVec};
use crate::diag::SourceResult; use crate::diag::SourceResult;
use crate::engine::Engine; use crate::engine::Engine;
@ -150,7 +151,7 @@ cast! {
/// - `(I)` /// - `(I)`
#[derive(Debug, Clone, Eq, PartialEq, Hash)] #[derive(Debug, Clone, Eq, PartialEq, Hash)]
pub struct NumberingPattern { pub struct NumberingPattern {
pub pieces: EcoVec<(EcoString, NumberingKind, Case)>, pub pieces: EcoVec<(EcoString, NumberingKind)>,
pub suffix: EcoString, pub suffix: EcoString,
trimmed: bool, trimmed: bool,
} }
@ -161,24 +162,21 @@ impl NumberingPattern {
let mut fmt = EcoString::new(); let mut fmt = EcoString::new();
let mut numbers = numbers.iter(); let mut numbers = numbers.iter();
for (i, ((prefix, kind, case), &n)) in for (i, ((prefix, kind), &n)) in self.pieces.iter().zip(&mut numbers).enumerate()
self.pieces.iter().zip(&mut numbers).enumerate()
{ {
if i > 0 || !self.trimmed { if i > 0 || !self.trimmed {
fmt.push_str(prefix); fmt.push_str(prefix);
} }
fmt.push_str(&kind.apply(n, *case)); fmt.push_str(&kind.apply(n));
} }
for ((prefix, kind, case), &n) in for ((prefix, kind), &n) in self.pieces.last().into_iter().cycle().zip(numbers) {
self.pieces.last().into_iter().cycle().zip(numbers)
{
if prefix.is_empty() { if prefix.is_empty() {
fmt.push_str(&self.suffix); fmt.push_str(&self.suffix);
} else { } else {
fmt.push_str(prefix); fmt.push_str(prefix);
} }
fmt.push_str(&kind.apply(n, *case)); fmt.push_str(&kind.apply(n));
} }
if !self.trimmed { if !self.trimmed {
@ -191,16 +189,16 @@ impl NumberingPattern {
/// Apply only the k-th segment of the pattern to a number. /// Apply only the k-th segment of the pattern to a number.
pub fn apply_kth(&self, k: usize, number: usize) -> EcoString { pub fn apply_kth(&self, k: usize, number: usize) -> EcoString {
let mut fmt = EcoString::new(); let mut fmt = EcoString::new();
if let Some((prefix, _, _)) = self.pieces.first() { if let Some((prefix, _)) = self.pieces.first() {
fmt.push_str(prefix); fmt.push_str(prefix);
} }
if let Some((_, kind, case)) = self if let Some((_, kind)) = self
.pieces .pieces
.iter() .iter()
.chain(self.pieces.last().into_iter().cycle()) .chain(self.pieces.last().into_iter().cycle())
.nth(k) .nth(k)
{ {
fmt.push_str(&kind.apply(number, *case)); fmt.push_str(&kind.apply(number));
} }
fmt.push_str(&self.suffix); fmt.push_str(&self.suffix);
fmt fmt
@ -220,14 +218,12 @@ impl FromStr for NumberingPattern {
let mut handled = 0; let mut handled = 0;
for (i, c) in pattern.char_indices() { for (i, c) in pattern.char_indices() {
let Some(kind) = NumberingKind::from_char(c.to_ascii_lowercase()) else { let Some(kind) = NumberingKind::from_char(c) else {
continue; continue;
}; };
let prefix = pattern[handled..i].into(); let prefix = pattern[handled..i].into();
let case = pieces.push((prefix, kind));
if c.is_uppercase() || c == '壹' { Case::Upper } else { Case::Lower };
pieces.push((prefix, kind, case));
handled = c.len_utf8() + i; handled = c.len_utf8() + i;
} }
@ -244,13 +240,9 @@ cast! {
NumberingPattern, NumberingPattern,
self => { self => {
let mut pat = EcoString::new(); let mut pat = EcoString::new();
for (prefix, kind, case) in &self.pieces { for (prefix, kind) in &self.pieces {
pat.push_str(prefix); pat.push_str(prefix);
let mut c = kind.to_char(); pat.push(kind.to_char());
if *case == Case::Upper {
c = c.to_ascii_uppercase();
}
pat.push(c);
} }
pat.push_str(&self.suffix); pat.push_str(&self.suffix);
pat.into_value() pat.into_value()
@ -263,26 +255,36 @@ cast! {
pub enum NumberingKind { pub enum NumberingKind {
/// Arabic numerals (1, 2, 3, etc.). /// Arabic numerals (1, 2, 3, etc.).
Arabic, Arabic,
/// Latin letters (A, B, C, etc.). Items beyond Z use multiple symbols. /// Lowercase Latin letters (a, b, c, etc.). Items beyond z use base-26.
/// Uses both cases. LowerLatin,
Letter, /// Uppercase Latin letters (A, B, C, etc.). Items beyond Z use base-26.
/// Roman numerals (I, II, III, etc.). Uses both cases. UpperLatin,
Roman, /// Lowercase Roman numerals (i, ii, iii, etc.).
/// The symbols *, †, ‡, §, ¶, and ‖. Further items use multiple symbols. LowerRoman,
/// Uppercase Roman numerals (I, II, III, etc.).
UpperRoman,
/// Paragraph/note-like symbols: *, †, ‡, §, ¶, and ‖. Further items use repeated symbols.
Symbol, Symbol,
/// Hebrew numerals. /// Hebrew numerals, including Geresh/Gershayim.
Hebrew, Hebrew,
/// Simplified Chinese numerals. Uses standard numerals for lowercase and /// Simplified Chinese standard numerals. This corresponds to the
/// "banknote" numerals for uppercase. /// `ChineseCase::Lower` variant.
SimplifiedChinese, LowerSimplifiedChinese,
/// Simplified Chinese "banknote" numerals. This corresponds to the
/// `ChineseCase::Upper` variant.
UpperSimplifiedChinese,
// TODO: Pick the numbering pattern based on languages choice. // TODO: Pick the numbering pattern based on languages choice.
// As the first character of Simplified and Traditional Chinese numbering // As the first character of Simplified and Traditional Chinese numbering
// are the same, we are unable to determine if the context requires // are the same, we are unable to determine if the context requires
// Simplified or Traditional by only looking at this character. // Simplified or Traditional by only looking at this character.
#[allow(unused)] #[allow(unused)]
/// Traditional Chinese numerals. Uses standard numerals for lowercase and /// Traditional Chinese standard numerals. This corresponds to the
/// "banknote" numerals for uppercase. /// `ChineseCase::Lower` variant.
TraditionalChinese, LowerTraditionalChinese,
#[allow(unused)]
/// Traditional Chinese "banknote" numerals. This corresponds to the
/// `ChineseCase::Upper` variant.
UpperTraditionalChinese,
/// Hiragana in the gojūon order. Includes n but excludes wi and we. /// Hiragana in the gojūon order. Includes n but excludes wi and we.
HiraganaAiueo, HiraganaAiueo,
/// Hiragana in the iroha order. Includes wi and we but excludes n. /// Hiragana in the iroha order. Includes wi and we but excludes n.
@ -312,15 +314,18 @@ pub enum NumberingKind {
} }
impl NumberingKind { impl NumberingKind {
/// Create a numbering kind from a lowercase character. /// Create a numbering kind from a representative character.
pub fn from_char(c: char) -> Option<Self> { pub fn from_char(c: char) -> Option<Self> {
Some(match c { Some(match c {
'1' => NumberingKind::Arabic, '1' => NumberingKind::Arabic,
'a' => NumberingKind::Letter, 'a' => NumberingKind::LowerLatin,
'i' => NumberingKind::Roman, 'A' => NumberingKind::UpperLatin,
'i' => NumberingKind::LowerRoman,
'I' => NumberingKind::UpperRoman,
'*' => NumberingKind::Symbol, '*' => NumberingKind::Symbol,
'א' => NumberingKind::Hebrew, 'א' => NumberingKind::Hebrew,
'一' | '壹' => NumberingKind::SimplifiedChinese, '一' => NumberingKind::LowerSimplifiedChinese,
'壹' => NumberingKind::UpperSimplifiedChinese,
'あ' => NumberingKind::HiraganaAiueo, 'あ' => NumberingKind::HiraganaAiueo,
'い' => NumberingKind::HiraganaIroha, 'い' => NumberingKind::HiraganaIroha,
'ア' => NumberingKind::KatakanaAiueo, 'ア' => NumberingKind::KatakanaAiueo,
@ -338,16 +343,18 @@ impl NumberingKind {
}) })
} }
/// The lowercase character for this numbering kind. /// The representative character for this numbering kind.
pub fn to_char(self) -> char { pub fn to_char(self) -> char {
match self { match self {
Self::Arabic => '1', Self::Arabic => '1',
Self::Letter => 'a', Self::LowerLatin => 'a',
Self::Roman => 'i', Self::UpperLatin => 'A',
Self::LowerRoman => 'i',
Self::UpperRoman => 'I',
Self::Symbol => '*', Self::Symbol => '*',
Self::Hebrew => 'א', Self::Hebrew => 'א',
Self::SimplifiedChinese => '一', Self::LowerSimplifiedChinese | Self::LowerTraditionalChinese => '一',
Self::TraditionalChinese => '', Self::UpperSimplifiedChinese | Self::UpperTraditionalChinese => '',
Self::HiraganaAiueo => 'あ', Self::HiraganaAiueo => 'あ',
Self::HiraganaIroha => 'い', Self::HiraganaIroha => 'い',
Self::KatakanaAiueo => 'ア', Self::KatakanaAiueo => 'ア',
@ -365,109 +372,11 @@ impl NumberingKind {
} }
/// Apply the numbering to the given number. /// Apply the numbering to the given number.
pub fn apply(self, mut n: usize, case: Case) -> EcoString { pub fn apply(self, n: usize) -> EcoString {
match self { match self {
Self::Arabic => { Self::Arabic => eco_format!("{n}"),
eco_format!("{n}") Self::LowerRoman => roman_numeral(n, Case::Lower),
} Self::UpperRoman => roman_numeral(n, Case::Upper),
Self::Letter => zeroless::<26>(
|x| match case {
Case::Lower => char::from(b'a' + x as u8),
Case::Upper => char::from(b'A' + x as u8),
},
n,
),
Self::HiraganaAiueo => zeroless::<46>(
|x| {
[
'あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ',
'し', 'す', 'せ', 'そ', 'た', 'ち', 'つ', 'て', 'と', 'な', 'に',
'ぬ', 'ね', 'の', 'は', 'ひ', 'ふ', 'へ', 'ほ', 'ま', 'み', 'む',
'め', 'も', 'や', 'ゆ', 'よ', 'ら', 'り', 'る', 'れ', 'ろ', 'わ',
'を', 'ん',
][x]
},
n,
),
Self::HiraganaIroha => zeroless::<47>(
|x| {
[
'い', 'ろ', 'は', 'に', 'ほ', 'へ', 'と', 'ち', 'り', 'ぬ', 'る',
'を', 'わ', 'か', 'よ', 'た', 'れ', 'そ', 'つ', 'ね', 'な', 'ら',
'む', 'う', 'ゐ', 'の', 'お', 'く', 'や', 'ま', 'け', 'ふ', 'こ',
'え', 'て', 'あ', 'さ', 'き', 'ゆ', 'め', 'み', 'し', 'ゑ', 'ひ',
'も', 'せ', 'す',
][x]
},
n,
),
Self::KatakanaAiueo => zeroless::<46>(
|x| {
[
'ア', 'イ', 'ウ', 'エ', 'オ', 'カ', 'キ', 'ク', 'ケ', 'コ', 'サ',
'シ', 'ス', 'セ', 'ソ', 'タ', 'チ', 'ツ', 'テ', 'ト', 'ナ', 'ニ',
'ヌ', 'ネ', '', 'ハ', 'ヒ', 'フ', 'ヘ', 'ホ', 'マ', 'ミ', 'ム',
'メ', 'モ', 'ヤ', 'ユ', 'ヨ', 'ラ', 'リ', 'ル', 'レ', 'ロ', 'ワ',
'ヲ', 'ン',
][x]
},
n,
),
Self::KatakanaIroha => zeroless::<47>(
|x| {
[
'イ', 'ロ', 'ハ', 'ニ', 'ホ', 'ヘ', 'ト', 'チ', 'リ', 'ヌ', 'ル',
'ヲ', 'ワ', 'カ', 'ヨ', 'タ', 'レ', 'ソ', 'ツ', 'ネ', 'ナ', 'ラ',
'ム', 'ウ', 'ヰ', '', 'オ', 'ク', 'ヤ', 'マ', 'ケ', 'フ', 'コ',
'エ', 'テ', 'ア', 'サ', 'キ', 'ユ', 'メ', 'ミ', 'シ', 'ヱ', 'ヒ',
'モ', 'セ', 'ス',
][x]
},
n,
),
Self::Roman => {
if n == 0 {
return 'N'.into();
}
// Adapted from Yann Villessuzanne's roman.rs under the
// Unlicense, at https://github.com/linfir/roman.rs/
let mut fmt = EcoString::new();
for &(name, value) in &[
("", 1000000),
("", 500000),
("", 100000),
("", 50000),
("", 10000),
("", 5000),
("I̅V̅", 4000),
("M", 1000),
("CM", 900),
("D", 500),
("CD", 400),
("C", 100),
("XC", 90),
("L", 50),
("XL", 40),
("X", 10),
("IX", 9),
("V", 5),
("IV", 4),
("I", 1),
] {
while n >= value {
n -= value;
for c in name.chars() {
match case {
Case::Lower => fmt.extend(c.to_lowercase()),
Case::Upper => fmt.push(c),
}
}
}
}
fmt
}
Self::Symbol => { Self::Symbol => {
if n == 0 { if n == 0 {
return '-'.into(); return '-'.into();
@ -478,130 +387,221 @@ impl NumberingKind {
let amount = ((n - 1) / SYMBOLS.len()) + 1; let amount = ((n - 1) / SYMBOLS.len()) + 1;
std::iter::repeat(symbol).take(amount).collect() std::iter::repeat(symbol).take(amount).collect()
} }
Self::Hebrew => { Self::Hebrew => hebrew_numeral(n),
if n == 0 {
return '-'.into();
}
let mut fmt = EcoString::new(); Self::LowerLatin => zeroless(
'outer: for &(name, value) in &[ [
('ת', 400), 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
('ש', 300), 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
('ר', 200), ],
('ק', 100),
('צ', 90),
('פ', 80),
('ע', 70),
('ס', 60),
('נ', 50),
('מ', 40),
('ל', 30),
('כ', 20),
('י', 10),
('ט', 9),
('ח', 8),
('ז', 7),
('ו', 6),
('ה', 5),
('ד', 4),
('ג', 3),
('ב', 2),
('א', 1),
] {
while n >= value {
match n {
15 => fmt.push_str("ט״ו"),
16 => fmt.push_str("ט״ז"),
_ => {
let append_geresh = n == value && fmt.is_empty();
if n == value && !fmt.is_empty() {
fmt.push('״');
}
fmt.push(name);
if append_geresh {
fmt.push('׳');
}
n -= value;
continue;
}
}
break 'outer;
}
}
fmt
}
l @ (Self::SimplifiedChinese | Self::TraditionalChinese) => {
let chinese_case = match case {
Case::Lower => ChineseCase::Lower,
Case::Upper => ChineseCase::Upper,
};
match (n as u64).to_chinese(
match l {
Self::SimplifiedChinese => ChineseVariant::Simple,
Self::TraditionalChinese => ChineseVariant::Traditional,
_ => unreachable!(),
},
chinese_case,
ChineseCountMethod::TenThousand,
) {
Ok(num_str) => EcoString::from(num_str),
Err(_) => '-'.into(),
}
}
Self::KoreanJamo => zeroless::<14>(
|x| {
[
'ㄱ', 'ㄴ', 'ㄷ', 'ㄹ', 'ㅁ', 'ㅂ', 'ㅅ', 'ㅇ', 'ㅈ', 'ㅊ', 'ㅋ',
'ㅌ', 'ㅍ', 'ㅎ',
][x]
},
n, n,
), ),
Self::KoreanSyllable => zeroless::<14>( Self::UpperLatin => zeroless(
|x| { [
[ 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N',
'가', '나', '다', '라', '마', '바', '사', '아', '자', '차', '카', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
'타', '파', '하', ],
][x]
},
n, n,
), ),
Self::HiraganaAiueo => zeroless(
[
'あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ',
'し', 'す', 'せ', 'そ', 'た', 'ち', 'つ', 'て', 'と', 'な', 'に',
'ぬ', 'ね', 'の', 'は', 'ひ', 'ふ', 'へ', 'ほ', 'ま', 'み', 'む',
'め', 'も', 'や', 'ゆ', 'よ', 'ら', 'り', 'る', 'れ', 'ろ', 'わ',
'を', 'ん',
],
n,
),
Self::HiraganaIroha => zeroless(
[
'い', 'ろ', 'は', 'に', 'ほ', 'へ', 'と', 'ち', 'り', 'ぬ', 'る',
'を', 'わ', 'か', 'よ', 'た', 'れ', 'そ', 'つ', 'ね', 'な', 'ら',
'む', 'う', 'ゐ', 'の', 'お', 'く', 'や', 'ま', 'け', 'ふ', 'こ',
'え', 'て', 'あ', 'さ', 'き', 'ゆ', 'め', 'み', 'し', 'ゑ', 'ひ',
'も', 'せ', 'す',
],
n,
),
Self::KatakanaAiueo => zeroless(
[
'ア', 'イ', 'ウ', 'エ', 'オ', 'カ', 'キ', 'ク', 'ケ', 'コ', 'サ',
'シ', 'ス', 'セ', 'ソ', 'タ', 'チ', 'ツ', 'テ', 'ト', 'ナ', 'ニ',
'ヌ', 'ネ', '', 'ハ', 'ヒ', 'フ', 'ヘ', 'ホ', 'マ', 'ミ', 'ム',
'メ', 'モ', 'ヤ', 'ユ', 'ヨ', 'ラ', 'リ', 'ル', 'レ', 'ロ', 'ワ',
'ヲ', 'ン',
],
n,
),
Self::KatakanaIroha => zeroless(
[
'イ', 'ロ', 'ハ', 'ニ', 'ホ', 'ヘ', 'ト', 'チ', 'リ', 'ヌ', 'ル',
'ヲ', 'ワ', 'カ', 'ヨ', 'タ', 'レ', 'ソ', 'ツ', 'ネ', 'ナ', 'ラ',
'ム', 'ウ', 'ヰ', '', 'オ', 'ク', 'ヤ', 'マ', 'ケ', 'フ', 'コ',
'エ', 'テ', 'ア', 'サ', 'キ', 'ユ', 'メ', 'ミ', 'シ', 'ヱ', 'ヒ',
'モ', 'セ', 'ス',
],
n,
),
Self::KoreanJamo => zeroless(
[
'ㄱ', 'ㄴ', 'ㄷ', 'ㄹ', 'ㅁ', 'ㅂ', 'ㅅ', 'ㅇ', 'ㅈ', 'ㅊ', 'ㅋ',
'ㅌ', 'ㅍ', 'ㅎ',
],
n,
),
Self::KoreanSyllable => zeroless(
[
'가', '나', '다', '라', '마', '바', '사', '아', '자', '차', '카',
'타', '파', '하',
],
n,
),
Self::BengaliLetter => zeroless(
[
'ক', 'খ', 'গ', 'ঘ', 'ঙ', 'চ', 'ছ', 'জ', 'ঝ', 'ঞ', 'ট', 'ঠ', 'ড', 'ঢ',
'ণ', 'ত', 'থ', 'দ', 'ধ', 'ন', 'প', 'ফ', 'ব', 'ভ', 'ম', 'য', 'র', 'ল',
'শ', 'ষ', 'স', 'হ',
],
n,
),
Self::CircledNumber => zeroless(
[
'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',
],
n,
),
Self::DoubleCircledNumber => {
zeroless(['⓵', '⓶', '⓷', '⓸', '⓹', '⓺', '⓻', '⓼', '⓽', '⓾'], n)
}
Self::LowerSimplifiedChinese => {
usize_to_chinese(ChineseVariant::Simple, ChineseCase::Lower, n).into()
}
Self::UpperSimplifiedChinese => {
usize_to_chinese(ChineseVariant::Simple, ChineseCase::Upper, n).into()
}
Self::LowerTraditionalChinese => {
usize_to_chinese(ChineseVariant::Traditional, ChineseCase::Lower, n)
.into()
}
Self::UpperTraditionalChinese => {
usize_to_chinese(ChineseVariant::Traditional, ChineseCase::Upper, n)
.into()
}
Self::EasternArabic => decimal('\u{0660}', n), Self::EasternArabic => decimal('\u{0660}', n),
Self::EasternArabicPersian => decimal('\u{06F0}', n), Self::EasternArabicPersian => decimal('\u{06F0}', n),
Self::DevanagariNumber => decimal('\u{0966}', n), Self::DevanagariNumber => decimal('\u{0966}', n),
Self::BengaliNumber => decimal('\u{09E6}', n), Self::BengaliNumber => decimal('\u{09E6}', n),
Self::BengaliLetter => zeroless::<32>(
|x| {
[
'ক', 'খ', 'গ', 'ঘ', 'ঙ', 'চ', 'ছ', 'জ', 'ঝ', 'ঞ', 'ট', 'ঠ', 'ড',
'ঢ', 'ণ', 'ত', 'থ', 'দ', 'ধ', 'ন', 'প', 'ফ', 'ব', 'ভ', 'ম', 'য',
'র', 'ল', 'শ', 'ষ', 'স', 'হ',
][x]
},
n,
),
Self::CircledNumber => zeroless::<50>(
|x| {
[
'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',
][x]
},
n,
),
Self::DoubleCircledNumber => zeroless::<10>(
|x| ['⓵', '⓶', '⓷', '⓸', '⓹', '⓺', '⓻', '⓼', '⓽', '⓾'][x],
n,
),
} }
} }
} }
fn hebrew_numeral(mut n: usize) -> EcoString {
if n == 0 {
return '-'.into();
}
let mut fmt = EcoString::new();
'outer: for (name, value) in [
('ת', 400),
('ש', 300),
('ר', 200),
('ק', 100),
('צ', 90),
('פ', 80),
('ע', 70),
('ס', 60),
('נ', 50),
('מ', 40),
('ל', 30),
('כ', 20),
('י', 10),
('ט', 9),
('ח', 8),
('ז', 7),
('ו', 6),
('ה', 5),
('ד', 4),
('ג', 3),
('ב', 2),
('א', 1),
] {
while n >= value {
match n {
15 => fmt.push_str("ט״ו"),
16 => fmt.push_str("ט״ז"),
_ => {
let append_geresh = n == value && fmt.is_empty();
if n == value && !fmt.is_empty() {
fmt.push('״');
}
fmt.push(name);
if append_geresh {
fmt.push('׳');
}
n -= value;
continue;
}
}
break 'outer;
}
}
fmt
}
fn roman_numeral(mut n: usize, case: Case) -> EcoString {
if n == 0 {
return match case {
Case::Lower => 'n'.into(),
Case::Upper => 'N'.into(),
};
}
// Adapted from Yann Villessuzanne's roman.rs under the
// Unlicense, at https://github.com/linfir/roman.rs/
let mut fmt = EcoString::new();
for &(name, value) in &[
("", 1000000),
("", 500000),
("", 100000),
("", 50000),
("", 10000),
("", 5000),
("I̅V̅", 4000),
("M", 1000),
("CM", 900),
("D", 500),
("CD", 400),
("C", 100),
("XC", 90),
("L", 50),
("XL", 40),
("X", 10),
("IX", 9),
("V", 5),
("IV", 4),
("I", 1),
] {
while n >= value {
n -= value;
for c in name.chars() {
match case {
Case::Lower => fmt.extend(c.to_lowercase()),
Case::Upper => fmt.push(c),
}
}
}
}
fmt
}
/// Stringify a number using a base-N counting system with no zero digit. /// Stringify a number using a base-N counting system with no zero digit.
/// ///
/// This is best explained by example. Suppose our digits are 'A', 'B', and 'C'. /// This is best explained by example. Suppose our digits are 'A', 'B', and 'C'.
@ -627,19 +627,19 @@ impl NumberingKind {
/// You might be familiar with this scheme from the way spreadsheet software /// You might be familiar with this scheme from the way spreadsheet software
/// tends to label its columns. /// tends to label its columns.
fn zeroless<const N_DIGITS: usize>( fn zeroless<const N_DIGITS: usize>(
mk_digit: impl Fn(usize) -> char, alphabet: [char; N_DIGITS],
mut n: usize, mut n: usize,
) -> EcoString { ) -> EcoString {
if n == 0 { if n == 0 {
return '-'.into(); return '-'.into();
} }
let mut cs: SmallVec<[char; 8]> = smallvec![]; let mut cs = EcoString::new();
while n > 0 { while n > 0 {
n -= 1; n -= 1;
cs.push(mk_digit(n % N_DIGITS)); cs.push(alphabet[n % N_DIGITS]);
n /= N_DIGITS; n /= N_DIGITS;
} }
cs.into_iter().rev().collect() cs.chars().rev().collect()
} }
/// Stringify a number using a base-10 counting system with a zero digit. /// Stringify a number using a base-10 counting system with a zero digit.
@ -649,10 +649,10 @@ fn decimal(start: char, mut n: usize) -> EcoString {
if n == 0 { if n == 0 {
return start.into(); return start.into();
} }
let mut cs: SmallVec<[char; 8]> = smallvec![]; let mut cs = EcoString::new();
while n > 0 { while n > 0 {
cs.push(char::from_u32((start as u32) + ((n % 10) as u32)).unwrap()); cs.push(char::from_u32((start as u32) + ((n % 10) as u32)).unwrap());
n /= 10; n /= 10;
} }
cs.into_iter().rev().collect() cs.chars().rev().collect()
} }