mirror of
https://github.com/Smaug123/KaTeX
synced 2025-10-08 12:38:39 +00:00
484d44ee70
* Unicode accents * Lexer now looks for combining dicritical marks and adds them to the same character * Parser's `parseSymbol` now recognizes both combined and uncombined forms of Unicode accents, and builds accent objects just like the accent functions * Added CJK support to math mode (not just text mode) * Add invalid combining character test * Add MathML test * Add weak support for other Latin-1 characters This maintains backwards compatibility, but it uses the wrong font. There's a TODO to fix this later. Also refactor symbol code to use for..of * Update Unicode screenshot * Remove dot from accented i and j (in math mode) Also add dotless Unicode characters to support some accented i's and j's * Fix \imath, \jmath, \pounds, and more tests * Switch from for..of to .split().forEach() Save around 800 bytes in minified code * Fix split * normalize() detection * Convert back to vanilla for loops * Fix merge * Move normalize dependency to unicodeMake.js * Make unicodeSymbols into a lookup table instead of macros This is important for multi-accented characters. * Add comments about when to run * Move symbols definition into unicodeMake/Symbols.js * Remove CJK support in text mode * Add missing semicolon * Refactor unicodeAccents to its own file * Dotless i/j support in text mode * Remove excess character mappings * Fix Åå in math mode (still via Times) * Update to support #1030 * Add accented Greek letter support (for supported Greek symbols) * Update screenshot * remove Æ, æ, Ø, ø, and ß from math mode test
60 lines
2.1 KiB
JavaScript
60 lines
2.1 KiB
JavaScript
/* eslint no-console:0 */
|
|
|
|
// This is an internal Node tool, not part of the KaTeX distribution,
|
|
// whose purpose is to generate unicodeSymbols.js in this directory.
|
|
// In this way, only this tool, and not the distribution/browser,
|
|
// needs String's normalize function.
|
|
//
|
|
// This tool should be run (via `node unicodeMake.js` or `make unicode`)
|
|
// whenever KaTeX adds support for new accents, and whenever
|
|
// the Unicode spec adds new symbols that should be supported.
|
|
|
|
const accents = require('./unicodeAccents');
|
|
|
|
console.log("// This file is GENERATED by unicodeMake.js. DO NOT MODIFY.");
|
|
console.log("");
|
|
|
|
const encode = function(string) {
|
|
let output = '"';
|
|
for (let i = 0; i < string.length; i++) {
|
|
let hex = string.charCodeAt(i).toString(16);
|
|
while (hex.length < 4) {
|
|
hex = `0${hex}`;
|
|
}
|
|
output += `\\u${hex}`;
|
|
}
|
|
output = `${output}"`;
|
|
return output;
|
|
};
|
|
|
|
console.log("export default {");
|
|
|
|
const letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ" +
|
|
"αβγδεϵζηθϑικλμνξοπϖρϱςστυφϕχψωΓΔΘΛΞΠΣΥΦΨΩ";
|
|
for (const letter of letters) {
|
|
for (const accent of Object.getOwnPropertyNames(accents)) {
|
|
const combined = letter + accent;
|
|
const normalized = combined.normalize('NFC');
|
|
if (normalized.length === 1) {
|
|
console.log(
|
|
` ${encode(normalized)}: ${encode(combined)},`
|
|
+ ` // ${normalized} = ${accents[accent].text}{${letter}}`);
|
|
}
|
|
for (const accent2 of Object.getOwnPropertyNames(accents)) {
|
|
if (accent === accent2) {
|
|
continue;
|
|
}
|
|
const combined2 = combined + accent2;
|
|
const normalized2 = combined2.normalize('NFC');
|
|
if (normalized2.length === 1) {
|
|
console.log(
|
|
` ${encode(normalized2)}: ${encode(combined2)},`
|
|
+ ` // ${normalized2} = ${accents[accent].text}`
|
|
+ `${accents[accent2].text}{${letter}}`);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
console.log("};");
|