3
0
mirror of https://github.com/larvit/adf-codec.git synced 2026-11-18 22:25:44 +01:00
Files
adf-codec/src/markdown/commonmark/case-folding.test.ts
T

61 lines
2.0 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import assert from 'node:assert/strict'
import { readFileSync } from 'node:fs'
import { dirname, join } from 'node:path'
import test from 'node:test'
import { fileURLToPath } from 'node:url'
import { foldCase } from './case-folding.ts'
const source = readFileSync(join(dirname(fileURLToPath(import.meta.url)), '..', '..', '..', 'spec', 'unicode', 'CaseFolding.txt'), 'utf8')
function characters(hexes: string): string {
return hexes
.split(' ')
.map((hex) => String.fromCodePoint(parseInt(hex, 16)))
.join('')
}
// `CaseFolding.txt`'s common and full mappings, as `0041; C; 0061;` and `00DF; F; 0073 0073;` give them.
const mappings = new Map(
source
.split('\n')
.map((line) => /^([0-9A-F]+); [CF]; ([0-9A-F ]+);/.exec(line))
.filter((match) => match !== null)
.map((match): [string, string] => [characters(match[1] ?? ''), characters(match[2] ?? '')]),
)
test('the vendored file gives the mappings the other tests hold the table to', () => {
assert.equal(mappings.size, 1606)
assert.equal(mappings.get('ẞ'), 'ss')
assert.equal(mappings.get('ß'), 'ss')
assert.equal(mappings.get('İ'), 'i̇')
})
test('folds every code point to the mapping the standard gives it', () => {
assert.deepEqual(
[...mappings].filter(([from, to]) => foldCase(from) !== to).map(([from]) => from),
[],
)
})
test('leaves every other code point as it is', () => {
const changed: number[] = []
for (let point = 0; point <= 0x10ffff; point++) {
const character = String.fromCodePoint(point)
if (!mappings.has(character) && foldCase(character) !== character) changed.push(point)
}
assert.deepEqual(changed, [])
})
test('folds a string code point by code point, a surrogate pair as one', () => {
assert.equal(foldCase('Ab\u{10400}Ç ẞ'), 'ab\u{10428}ç ss')
assert.equal(foldCase(''), '')
assert.equal(foldCase('\ud801'), '\ud801')
})
test('keeps the dotless i and the capital I apart, as the standard does', () => {
assert.equal(foldCase('I'), 'i')
assert.equal(foldCase('ı'), 'ı')
assert.notEqual(foldCase('ı'), foldCase('I'))
})