petal/web/src/hooks/spellchecker.test.ts

import { describe, it, expect } from 'vitest'
import { combine, interleave, withElision, type Dictionary, type Loaded } from './useSpellChecker'

// The both-dictionaries rule (SUGGESTIONS.md §3a), separated from the fetching
// so it can be checked without a 15 MB word list. What matters here is not
// "does nspell work" but which way the combination is allowed to be wrong.

// A dictionary that accepts exactly the words it was given.
function dict(lang: string, words: string[], corrections: string[] = [], extendedAlphabet = false): Loaded {
  const set = new Set(words)
  return {
    lang,
    extendedAlphabet,
    spell: {
      correct: (w: string) => set.has(w),
      suggest: () => corrections,
      add: (w: string) => set.add(w),
    },
  }
}

const en = dict('en', ['sale', 'the', 'river'], ['sailed', 'salt'])
const pt = dict('pt-PT', ['sale', 'coração', 'jardim'], ['salte', 'sala'], true)

describe('the both-dictionaries rule', () => {
  it('accepts a word either dictionary knows', () => {
    const c = combine(() => [en, pt])
    expect(c.correct('river')).toBe(true) // English only
    expect(c.correct('jardim')).toBe(true) // Portuguese only
    expect(c.correct('sale')).toBe(true) // both — the collision case
  })

  it('flags only what every dictionary rejects', () => {
    expect(combine(() => [en, pt]).correct('qqzzx')).toBe(false)
  })

  it('never flags a Portuguese word just because English has not heard of it', () => {
    // The property the whole design exists for. With English alone, "coração"
    // is a misspelling; with her own dictionary loaded it is a word she wrote.
    expect(combine(() => [en]).correct('coração')).toBe(false)
    expect(combine(() => [en, pt]).correct('coração')).toBe(true)
  })

  it('accepts everything when no dictionary loaded', () => {
    // A failed fetch must not underline every word in the document. Silence is
    // the safe failure; a page of red is not.
    expect(combine(() => []).correct('qqzzx')).toBe(true)
  })

  it('sees a dictionary that arrives after the checker was built', () => {
    // English loads immediately; hers lands a moment later, once /api/me has
    // named her pair. The checker reads through a getter for exactly this.
    let loaded: Loaded[] = [en]
    const c = combine(() => loaded)
    expect(c.correct('jardim')).toBe(false)
    expect(c.extendedAlphabet).toBe(false)
    loaded = [en, pt]
    expect(c.correct('jardim')).toBe(true)
    expect(c.extendedAlphabet).toBe(true)
  })
})

describe('correction pills', () => {
  it('interleaves the two dictionaries rather than letting one fill the list', () => {
    // Five pills fit. Concatenating would spend all of them on English and
    // leave a misspelt Portuguese word with no Portuguese correction — the one
    // case the second dictionary was loaded for.
    expect(combine(() => [en, pt]).suggest('salle')).toEqual(['sailed', 'salte', 'salt', 'sala'])
  })

  it('drops duplicates, keeping the first dictionary to offer one', () => {
    expect(interleave([['a', 'b'], ['a', 'c']])).toEqual(['a', 'b', 'c'])
  })

  it('keeps going when one dictionary runs out of ideas', () => {
    expect(interleave([['a'], ['x', 'y', 'z']])).toEqual(['a', 'x', 'y', 'z'])
    expect(interleave([[], []])).toEqual([])
    expect(interleave([])).toEqual([])
  })
})

// French elision (Phase 24). The word list is built without the elided forms
// because carrying them costs 8.25 MB gzipped instead of 1.19 MB, so the split
// happens here instead. What is being checked is not "does French work" but the
// same question as everywhere else in this file: which way is it allowed to be
// wrong.
describe('elision', () => {
  const FR = ['l', 'd', 'j', 'qu', 'jusqu']
  const base: Dictionary = {
    correct: (w) => ['arbre', 'accord', 'elle', 'ici', "aujourd'hui", 'Étang'].includes(w),
    suggest: (w) => (w === 'arbrz' ? ['arbre', 'arbres'] : []),
    add: () => undefined,
  }
  const fr = withElision(base, FR)

  it('looks past a clitic the language actually elides', () => {
    // The whole reason this exists: every one of these is absent from the built
    // word list, and every one of them is ordinary French.
    for (const w of ["l'arbre", "d'accord", "qu'elle", "jusqu'ici"]) {
      expect(base.correct(w), `${w} should not be in the list`).toBe(false)
      expect(fr.correct(w), w).toBe(true)
    }
  })

  it('leaves a word that carries its own apostrophe alone', () => {
    // "aujourd" is not a clitic, so this is never split — it matches directly,
    // which is why the build script keeps such stems verbatim.
    expect(fr.correct("aujourd'hui")).toBe(true)
  })

  it('still flags an apostrophe that is not an elision', () => {
    // Both halves have to hold up: an unknown clitic on a real word, and a real
    // clitic on an unknown word. Splitting is a second lookup, not an amnesty.
    expect(fr.correct("zzz'arbre")).toBe(false)
    expect(fr.correct("l'zzzz")).toBe(false)
  })

  it('is case-insensitive about the clitic, because a sentence can start with one', () => {
    expect(fr.correct("L'Étang")).toBe(true)
  })

  it('puts the clitic back on its corrections', () => {
    // The pill replaces the whole token. Offering "arbre" for "l'arbrz" would
    // silently delete the article she wrote.
    expect(fr.suggest("l'arbrz")).toEqual(["l'arbre", "l'arbres"])
  })

  it('does not split what has no apostrophe to split on', () => {
    expect(fr.correct("'arbre")).toBe(false) // nothing before the mark
    expect(fr.correct("l'")).toBe(false) // nothing after it
  })

  it('hands back the same dictionary for a language that elides nothing', () => {
    // pt-PT and English pay nothing for this.
    expect(withElision(base, [])).toBe(base)
    expect(withElision(base, undefined)).toBe(base)
  })
})