43eb1153e9
The inline markdown regex had `~([^~\s][^~]*?)~` for Pandoc-style subscript
(H~2~O, CO~2~). On models that decorate prose with kaomoji like `thing ~!`
and `cool ~?` — Kimi especially — the opener `~!` paired with the next
stray `~` on the line and dim-formatted everything between them with a
leading `_` character, mangling markdown output.
Tighten the pattern to short alphanumeric-only content (`~[A-Za-z0-9]{1,8}~`)
since real subscript never contains punctuation, spaces, or long runs.
Same tightening applied to stripInlineMarkup so width measurement stays
consistent. Classic CLI was unaffected because it renders these literally.
87 lines
3.6 KiB
TypeScript
87 lines
3.6 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
|
|
import { AUDIO_DIRECTIVE_RE, INLINE_RE, MEDIA_LINE_RE, stripInlineMarkup } from '../components/markdown.js'
|
|
|
|
const matches = (text: string) => [...text.matchAll(INLINE_RE)].map(m => m[0])
|
|
|
|
describe('INLINE_RE emphasis', () => {
|
|
it('matches word-boundary italic/bold', () => {
|
|
expect(matches('say _hi_ there')).toEqual(['_hi_'])
|
|
expect(matches('very __bold__ move')).toEqual(['__bold__'])
|
|
expect(matches('(_paren_) and [_bracket_]')).toEqual(['_paren_', '_bracket_'])
|
|
})
|
|
|
|
it('keeps intraword underscores literal', () => {
|
|
const path = '/home/me/.hermes/cache/screenshots/browser_screenshot_ecc1c3feab.png'
|
|
|
|
expect(matches(path)).toEqual([])
|
|
expect(matches('snake_case_var and MY_CONST')).toEqual([])
|
|
expect(matches('foo__bar__baz')).toEqual([])
|
|
})
|
|
|
|
it('still matches asterisk emphasis intraword', () => {
|
|
expect(matches('a*b*c')).toEqual(['*b*'])
|
|
expect(matches('a**bold**c')).toEqual(['**bold**'])
|
|
})
|
|
|
|
it('matches short alphanumeric subscript (H~2~O, CO~2~, X~n~)', () => {
|
|
expect(matches('H~2~O')).toEqual(['~2~'])
|
|
expect(matches('CO~2~ levels')).toEqual(['~2~'])
|
|
expect(matches('the X~n~ term')).toEqual(['~n~'])
|
|
})
|
|
|
|
it('ignores kaomoji-style ~! and ~? punctuation', () => {
|
|
// Kimi / Qwen / GLM emit these as decorators and the whole span between
|
|
// two tildes used to get collapsed into one dim blob.
|
|
expect(matches('Aww ~! Building step by step, I love it ~!')).toEqual([])
|
|
expect(matches('cool ~? yeah ~?')).toEqual([])
|
|
expect(matches('mixed ~! and ~? flow')).toEqual([])
|
|
})
|
|
|
|
it('ignores tilde spans that contain spaces or punctuation', () => {
|
|
// Real subscript doesn't contain spaces; a tilde followed by words-then-
|
|
// tilde is almost always conversational. Matching it swallows text.
|
|
expect(matches('hello ~good idea~ there')).toEqual([])
|
|
expect(matches('x ~oh no!~ y')).toEqual([])
|
|
})
|
|
|
|
it('does not let strikethrough eat subscript', () => {
|
|
expect(matches('~~strike~~ and H~2~O')).toEqual(['~~strike~~', '~2~'])
|
|
})
|
|
})
|
|
|
|
describe('stripInlineMarkup', () => {
|
|
it('strips word-boundary emphasis only', () => {
|
|
expect(stripInlineMarkup('say _hi_ there')).toBe('say hi there')
|
|
expect(stripInlineMarkup('browser_screenshot_ecc.png')).toBe('browser_screenshot_ecc.png')
|
|
expect(stripInlineMarkup('__bold__ and foo__bar__')).toBe('bold and foo__bar__')
|
|
})
|
|
|
|
it('leaves ~!/~? kaomoji alone and still handles real subscript', () => {
|
|
expect(stripInlineMarkup('Yay ~! nice work ~!')).toBe('Yay ~! nice work ~!')
|
|
expect(stripInlineMarkup('H~2~O and CO~2~')).toBe('H_2O and CO_2')
|
|
})
|
|
})
|
|
|
|
describe('protocol sentinels', () => {
|
|
it('captures MEDIA: paths with surrounding quotes or backticks', () => {
|
|
expect('MEDIA:/tmp/a.png'.match(MEDIA_LINE_RE)?.[1]).toBe('/tmp/a.png')
|
|
expect(' MEDIA: /home/me/.hermes/cache/screenshots/browser_screenshot_ecc.png '.match(MEDIA_LINE_RE)?.[1]).toBe(
|
|
'/home/me/.hermes/cache/screenshots/browser_screenshot_ecc.png'
|
|
)
|
|
expect('`MEDIA:/tmp/a.png`'.match(MEDIA_LINE_RE)?.[1]).toBe('/tmp/a.png')
|
|
expect('"MEDIA:C:\\files\\a.png"'.match(MEDIA_LINE_RE)?.[1]).toBe('C:\\files\\a.png')
|
|
})
|
|
|
|
it('ignores MEDIA: tokens embedded in prose', () => {
|
|
expect('here is MEDIA:/tmp/a.png for you'.match(MEDIA_LINE_RE)).toBeNull()
|
|
expect('the media: section is empty'.match(MEDIA_LINE_RE)).toBeNull()
|
|
})
|
|
|
|
it('matches the [[audio_as_voice]] directive', () => {
|
|
expect(AUDIO_DIRECTIVE_RE.test('[[audio_as_voice]]')).toBe(true)
|
|
expect(AUDIO_DIRECTIVE_RE.test(' [[audio_as_voice]] ')).toBe(true)
|
|
expect(AUDIO_DIRECTIVE_RE.test('audio_as_voice')).toBe(false)
|
|
})
|
|
})
|