petal/web/src/i18n/i18n.test.ts

import { beforeEach, describe, expect, it, vi } from 'vitest'

import { onPackChange, pack, resetPackForTests, setPackLang, shippedPacks } from './index'
import { zh } from './packs/zh'
import { ptPT } from './packs/pt-PT'
import { fr } from './packs/fr'
import type { Pack } from './types'

// Every pack that ships. Shape assertions run over all of them, because the
// point of Phase 19 was that a language is data — and data that only the first
// author's pack satisfies isn't a shape, it's a coincidence.
const PACKS: Pack[] = [zh, ptPT, fr]

beforeEach(() => {
  resetPackForTests()
})

describe('pack selection', () => {
  it('speaks the default pair before /api/me answers', () => {
    // Modules that build copy at import time (the companion, the prose checker)
    // read the pack before the session is known. That read must not be blank.
    expect(pack()).toBe(zh)
    expect(pack().code).toBe('zh')
  })

  it('switches to a shipped pack when the session names one', () => {
    setPackLang('pt-PT')
    expect(pack()).toBe(ptPT)
    expect(pack().code).toBe('pt-PT')
    // And back — a writer moving pairs must not strand the app on the old copy.
    setPackLang('zh')
    expect(pack()).toBe(zh)
  })

  it('falls back rather than blanking on a pair with no pack yet', () => {
    // A pair_lang the deployment has no copy for is a deployment that got ahead
    // of its translation. She should still get a working editor. (This was 'fr'
    // until Phase 24 gave fr a pack; 'es' is the pair still waiting for one.)
    setPackLang('es')
    expect(pack()).toBe(zh)
    setPackLang('klingon')
    expect(pack()).toBe(zh)
    setPackLang('')
    expect(pack()).toBe(zh)
    setPackLang(null)
    expect(pack()).toBe(zh)
    setPackLang(undefined)
    expect(pack()).toBe(zh)
  })

  it('notifies readers on a real switch, and only on a real one', () => {
    const seen = vi.fn()
    onPackChange(seen)

    setPackLang('zh') // already the current pack — nothing changed
    expect(seen).not.toHaveBeenCalled()

    // An unshipped pair resolves back to zh, which is also not a change.
    setPackLang('es')
    expect(seen).not.toHaveBeenCalled()

    setPackLang('pt-PT')
    expect(seen).toHaveBeenCalledTimes(1)
  })

  // What the sidebar picker offers. It is derived from the packs rather than
  // listed a second time, so a pack that ships is a pair she can choose — and a
  // pair with no pack can never be offered, which is the invariant the server's
  // matching allowlist exists to enforce from the other side.
  it('offers exactly the pairs it has copy for', () => {
    const codes = shippedPacks().map((p) => p.code)
    expect(codes.sort()).toEqual(['fr', 'pt-PT', 'zh'])
    // Every offered pair names itself, because a writer stranded on the wrong
    // pack can only read the label that is in her own language.
    for (const p of shippedPacks()) expect(p.nativeName.length).toBeGreaterThan(0)
    // Anything the picker offers must actually resolve.
    for (const code of codes) {
      setPackLang(code)
      expect(pack().code).toBe(code)
    }
  })

  it('stops notifying after unsubscribe', () => {
    const seen = vi.fn()
    const off = onPackChange(seen)
    off()
    setPackLang('zh')
    expect(seen).not.toHaveBeenCalled()
  })
})

describe('the zh pack', () => {
  // Sentinels: a handful of strings copied from the pre-Phase-19 source. The
  // point of the extraction was that nothing she reads changed, and a reworded
  // label would otherwise be invisible in a diff of this size.
  it('carries the original copy verbatim', () => {
    expect(zh.docs.searchPlaceholder).toBe('搜索 · Search')
    expect(zh.editor.addToDictionary).toBe('添加到词典 · Add to dictionary')
    expect(zh.status.savedLocally).toBe('已保存在本机 · Kept on this device')
    expect(zh.garden.titleWithFlower).toBe('🌷 词汇花园 · Vocabulary Garden')
    expect(zh.companion.greeting).toEqual({
      native: '嗨～我在这儿陪你写作哦 🐱',
      en: "Hi! I'm right here keeping you company. 🐱",
    })
    expect(zh.prose.itsOwn).toBe('“it’s” = “it is”；表示“它的”要用 “its”，所以是 “its own”。')
  })

  it('renders its interpolated lines with the value in place', () => {
    expect(zh.app.duplicateTitle('Spring')).toBe('Spring (副本)')
    expect(zh.companion.milestone(300).native).toBe('哇！已经 300 个词了，太厉害了 🎉')
    expect(zh.prose.articleAn('apple')).toContain('“an apple”')
    expect(zh.prose.uncountable('informations', 'information')).toContain('“information”')
    expect(zh.garden.reviewDue(4)).toBe('复习 4 个词 · Review 4 due 🌸')
    // English pluralisation is the pack's job, not the call site's.
    expect(zh.garden.growing(1)).toContain('1 blossom growing')
    expect(zh.garden.growing(2)).toContain('2 blossoms growing')
    expect(zh.history.daysAgo(1)).toBe('1 day ago · 1 天前')
    expect(zh.history.daysAgo(3)).toBe('3 days ago · 3 天前')
    expect(zh.journal.kept(1)).toContain('1 thing you took on board')
    expect(zh.journal.kept(9)).toContain('9 things you took on board')
    expect(zh.journal.stuck('make a decision', 3)).toContain('3 of your pieces')
  })

  // A pack with a hole in it renders an empty label rather than failing, which
  // is exactly the kind of thing that reaches production. Types catch a missing
  // *key*; only this catches an empty *value*.
  it.each(PACKS)('has no empty strings anywhere ($code)', (p) => {
    const empties: string[] = []
    const walk = (node: unknown, path: string) => {
      if (typeof node === 'string') {
        if (node.trim() === '') empties.push(path)
        return
      }
      if (typeof node === 'function') return // exercised above
      if (node && typeof node === 'object') {
        for (const [k, v] of Object.entries(node)) walk(v, path ? `${path}.${k}` : k)
      }
    }
    walk(p, '')
    expect(empties).toEqual([])
  })

  // The voice read-aloud speaks this pair in. A pack that names a locale no
  // Piper voice exists for degrades to Web Speech, which is survivable; a pack
  // that names the *wrong region* does not announce itself at all — it just
  // reads her language back to her in the accent the pair exists to avoid.
  it.each(PACKS)('names a speakable locale for its own language ($code)', (p) => {
    expect(p.locale, `${p.code} has no locale`).toMatch(/^[a-z]{2}(-[A-Za-z]{2,4})?$/)
    expect(p.locale.split('-')[0]).toBe(p.code.split('-')[0])
    if (p.code === 'pt-PT') expect(p.locale).toBe('pt-PT') // never pt-BR
  })

  it.each(PACKS)('labels every companion, tone and style ($code)', async (p) => {
    const { COMPANIONS } = await import('../components/Companion/companions')
    for (const c of COMPANIONS) {
      expect(p.companion.names[c.id], `no name for companion ${c.id}`).toBeTruthy()
    }

    const { TONES } = await import('../components/Editor/ToneSelect')
    for (const tone of TONES) {
      expect(p.tones[tone.value], `no label for tone ${tone.value}`).toBeTruthy()
    }

    const { REWRITE_STYLES } = await import('../components/Editor/SelectionBubble')
    for (const style of REWRITE_STYLES) {
      expect(p.styles[style.value], `no label for style ${style.value}`).toBeTruthy()
    }
  })

  it.each(PACKS)('labels every word band the popover can show ($code)', async (p) => {
    // wordBand returns a band name, never a label — an unlabelled band would
    // render as an empty chip, which reads as a bug rather than as no data.
    const { wordBand } = await import('../components/Editor/wordband')
    const bands = new Set(
      [
        wordBand(0, 0.1),
        wordBand(0, 0.5),
        wordBand(0, 0.9),
        wordBand(1000, -1),
        wordBand(500, -1),
        wordBand(10, -1),
      ].filter((b) => b !== null),
    )
    expect(bands.size).toBe(3)
    for (const band of bands) {
      expect(p.editor.wordBands[band], `no label for word band ${band}`).toBeTruthy()
    }
  })
})

describe('the pt-PT pack', () => {
  // The pack is European Portuguese or it is nothing: a Brazilian form in the
  // chrome is exactly the drift SUGGESTIONS.md §3 says to guard against, and it
  // is invisible to anyone who doesn't read Portuguese — including whoever
  // reviews this diff.
  it('is European Portuguese, not Brazilian', () => {
    const text = JSON.stringify(ptPT, (_k, v) => (typeof v === 'function' ? v(1, 'x') : v))

    // Brazilian spellings and vocabulary that would give the pack away.
    for (const bad of ['sinônimo', 'acadêmico', 'arquivo', 'tela', 'salvar', 'deletar', 'usuário', 'você']) {
      expect(text, `pt-BR form "${bad}" in the pt-PT pack`).not.toContain(bad)
    }

    // And pre-Acordo spellings, which this grep did NOT cover until Phase 24's
    // review pass found *adjectivos*, *actualmente* and *decepção* sitting in a
    // file whose own header commits to post-Acordo. Guarding the pt-BR fault
    // line while leaving the pack's stated spelling policy unchecked is half a
    // test: both are invisible to a reviewer who doesn't read Portuguese.
    // Whole words only — the English "actually" and "factual" contain "actual".
    for (const bad of ['actualmente', 'adjectivo', 'decepção', 'acção', 'óptimo',
                       'recepção', 'objectivo', 'directamente', 'exacto']) {
      expect(text, `pre-Acordo form "${bad}" in the pt-PT pack`).not.toContain(bad)
    }

    // And the European forms that should be there instead.
    expect(ptPT.editor.synonyms).toContain('Sinónimos')
    expect(ptPT.styles.academic.native).toBe('Académico')
    expect(ptPT.auth.signIn).toContain('Iniciar sessão')
  })

  it('renders its interpolated lines with the value in place', () => {
    expect(ptPT.app.duplicateTitle('Primavera')).toBe('Primavera (cópia)')
    expect(ptPT.companion.milestone(300).native).toContain('300 palavras')
    // Portuguese agreement is the pack's business, the same way English
    // pluralisation is — the call site only ever passes a number.
    expect(ptPT.garden.reviewDue(1)).toContain('1 palavra ·')
    expect(ptPT.garden.reviewDue(4)).toContain('4 palavras ·')
    expect(ptPT.garden.growing(1)).toContain('1 flor no jardim')
    expect(ptPT.garden.growing(3)).toContain('3 flores no jardim')
    expect(ptPT.journal.kept(1)).toContain('1 coisa que')
    expect(ptPT.journal.kept(5)).toContain('5 coisas que')
  })

  // The growth journal is the one surface that talks about her progress, so it
  // is the one most easily spoiled by a stray comparison. The rule is enforced
  // in SQL on the backend; here it is enforced in the copy.
  it('keeps the journal to growth and to her own past self', () => {
    const text = JSON.stringify(
      PACKS.map((p) => p.journal),
      (_k, v) => (typeof v === 'function' ? JSON.stringify(v(2, 3)) : v),
    )
    for (const bad of ['error', 'mistake', 'wrong', 'streak', 'average', 'erro', 'errada',
                       'erreur', 'faute', 'moyenne', '错误']) {
      expect(text.toLowerCase(), `the journal must not talk about "${bad}"`).not.toContain(bad)
    }
  })

  it('says the collision line the zh pair never needed (pt-PT)', () => {
    // "sale", "comum" and "tarde" are words on both sides of this pair, so the
    // word card's second reading is reachable copy here — unlike in zh.
    expect(ptPT.editor.alsoIn).toBeTruthy()
    expect(ptPT.editor.alsoIn).not.toBe(zh.editor.alsoIn)
  })
})

describe('the fr pack', () => {
  // French's regional question is not the dictionary's — Debian's fr_FR, fr_CA
  // and fr_BE are all symlinks to one word list — so the whole of it lives in
  // this file, which makes it exactly as invisible to a reviewer as the pt-BR
  // forms were, and worth pinning the same way.
  it('is metropolitan French, not Québécois', () => {
    const text = JSON.stringify(fr, (_k, v) => (typeof v === 'function' ? v(1, 'x') : v))
    for (const bad of ['courriel', 'clavarder', 'magasiner', 'fin de semaine', 'baladodiffusion']) {
      expect(text, `Québécois form "${bad}" in the fr pack`).not.toContain(bad)
    }
    // And the voice it is read in, for the same reason the locale is pinned.
    expect(fr.locale).toBe('fr-FR')
  })

  // The pack punctuates the way French does, which is the same habit
  // prose.spaceBeforePunct tells her not to carry into her English. Both halves
  // of that are deliberate and either would look like a typo to a tidier.
  it('keeps French spacing and guillemets in its own copy', () => {
    expect(fr.companion.greeting.native).toContain(' !')
    expect(fr.prose.articleAn('apple')).toContain('« an apple »')
    expect(fr.prose.spaceBeforePunct).toContain('inverse du français')
  })

  it('renders its interpolated lines with the value in place', () => {
    expect(fr.app.duplicateTitle('Printemps')).toBe('Printemps (copie)')
    expect(fr.companion.milestone(300).native).toContain('300 mots')
    // French agreement is the pack's business, the same way English
    // pluralisation is — the call site only ever passes a number.
    expect(fr.garden.reviewDue(1)).toContain('1 mot ·')
    expect(fr.garden.reviewDue(4)).toContain('4 mots ·')
    expect(fr.garden.growing(1)).toContain('1 fleur au jardin')
    expect(fr.garden.growing(3)).toContain('3 fleurs au jardin')
    expect(fr.journal.kept(1)).toContain('1 chose que tu as retenue')
    expect(fr.journal.kept(5)).toContain('5 choses que tu as retenues')
  })

  it('says the collision line, which this pair needs most of all', () => {
    // English took so much from French that the collisions are the rule rather
    // than the exception: chat, pain, coin, sale, four, car, or.
    expect(fr.editor.alsoIn).toBeTruthy()
    expect(fr.editor.alsoIn).not.toBe(zh.editor.alsoIn)
    expect(fr.editor.alsoIn).not.toBe(ptPT.editor.alsoIn)
  })
})

// False friends are a per-pair dataset rather than copy: the Latin pairs carry
// the traps their writers actually fall into, and the zh pair legitimately has
// none. Both halves of that are worth pinning.
describe('false friends', () => {
  it('the zh pair has none, because the trap needs a shared script', () => {
    expect(Object.keys(zh.falseFriends)).toHaveLength(0)
  })

  it('the pt-PT pair carries the ones that cost most', () => {
    // Not an exhaustive list — these are the four every European Portuguese
    // speaker meets in their first month of writing English.
    for (const word of ['actually', 'pretend', 'realize', 'library']) {
      expect(ptPT.falseFriends[word], word).toBeDefined()
    }
    expect(Object.keys(ptPT.falseFriends).length).toBeGreaterThan(10)
  })

  it('the fr pair carries the ones that cost most', () => {
    // "attend" and "pass" are the two this pair has and pt-PT does not: French
    // *attendre* is to wait, and *passer un examen* is to sit one, not to pass
    // it — which is the false friend most likely to end up in a real letter.
    for (const word of ['actually', 'library', 'attend', 'pass', 'sensible']) {
      expect(fr.falseFriends[word], word).toBeDefined()
    }
    expect(Object.keys(fr.falseFriends).length).toBeGreaterThan(10)
  })

  it('is keyed by the lowercase English word, so a lookup can find it', () => {
    for (const p of PACKS) {
      for (const key of Object.keys(p.falseFriends)) {
        expect(key, `${p.code}: "${key}" must be lowercase`).toBe(key.toLowerCase())
        expect(p.falseFriends[key].native.trim(), key).not.toBe('')
        expect(p.falseFriends[key].en.trim(), key).not.toBe('')
      }
    }
  })

  // The heads-up must never read as an accusation: she may well have meant the
  // word. It says what the English one means and stops there.
  it('never tells her she is wrong', () => {
    const forbidden = /wrong|mistake|error|incorrect|don't use|do not use|errado|erro|incorrecto/i
    for (const p of PACKS) {
      for (const [key, line] of Object.entries(p.falseFriends)) {
        expect(line.native, `${p.code}/${key}`).not.toMatch(forbidden)
        expect(line.en, `${p.code}/${key}`).not.toMatch(forbidden)
      }
    }
  })
})