doxa-maps/internal/check-hardcoded-english.mjs

#!/usr/bin/env node
/**
 * check-hardcoded-english — user-visible English that never reaches a translator. Headless.
 *
 * ONE GATE INSTEAD OF FOUR PRIVATE SCANNERS. sr, upg100, gospel and regions each wrote one of these
 * on 2026-09-28 and each found real defects; four copies means four sets of blind spots and four
 * allow-lists drifting apart. This is the merge, and every rule below earns its place from a defect
 * one of those scanners actually caught.
 *
 * ★ PARSED, NEVER REGEXED. A regex for string literals matches from the CLOSING quote of one to the
 * OPENING quote of the next, so a file with adjacent imports yields phantom "strings" — the first
 * version of regions' scanner reported 137 of them. Templates go through @vue/compiler-sfc and
 * scripts through @babel/parser.
 *
 * ★ ALIASES ARE DISCOVERED, NOT LISTED. `const t2 = t` defeats a callee-name check, and that cost a
 * false positive. The alias set is read out of each file (`const X = t`), so a rename cannot make
 * translated text look hardcoded.
 *
 * ★ te()-GUARDED FALLBACKS ARE NOT LEAKS. `te(key) ? t(key) : 'Some English'` is the documented way
 * to fall back when a key is absent; the English is reachable only when no translation exists. A
 * literal inside a conditional whose test calls te() is therefore allowed (sr's pattern).
 *
 * ⚠ SECOND BLIND SPOT, AND IT BIT ON THE FIRST DAY. A guarded fallback is judged by its SHAPE, not
 * by whether the lookup it guards actually works. `msg !== 'messages.engineMissing' ? msg : 'English'`
 * is treated as a fallback — but if the key is looked up with the wrong prefix, the lookup ALWAYS
 * misses and the English arm becomes the NORMAL path, in every locale, while this gate stays quiet.
 * That is exactly what exp-shepherd found in cities-internet after I triaged the same line as "not a
 * leak". A hardcoded-English scan cannot see a misconfigured lookup; check:i18n-keys-exist and a
 * locale render are what catch that. Treat a guarded fallback as "not a leak HERE", never as "this
 * string is not reaching users".
 *
 * ⚠ KNOWN BLIND SPOT, STATED SO NOBODY READS A GREEN RUN AS MORE THAN IT IS: THIS CANNOT SEE
 * SINGLE-WORD STRINGS. A bare 'Other' used as a fallback label is user-visible English and this gate
 * will not report it — regions found eight of them by grep, not with this tool. Single words carry
 * too many non-prose meanings (ids, class fragments, enum values) to flag without drowning the
 * signal. If that trade is ever revisited, the missing piece is context (what the value is ASSIGNED
 * to), not a longer word list.
 *
 * Exit 0 clean, 1 with findings, 2 on a parse error. `--self-test` runs the planted cases only.
 */
import { readFileSync, readdirSync, existsSync } from 'node:fs'
import { join } from 'node:path'
import { pathToFileURL } from 'node:url'
import { execSync } from 'node:child_process'
import { parse } from '@vue/compiler-sfc'
import * as babel from '@babel/parser'

// ── what counts as user-visible ─────────────────────────────────────────────────────────────────
const VISIBLE_ATTRS = new Set(['title', 'placeholder', 'aria-label', 'alt', 'label'])
const isProse = (s) => /[A-Za-z]/.test(s) && /[A-Za-z]{2,}/.test(s.trim())

// ── the allow-list: SHAPES first, names only where a shape cannot express it ─────────────────────
// Each entry records the class and why it is not a leak. A shape is preferred over a literal so the
// list does not need editing every time a new font or status code appears.
const ALLOW = [
  { why: 'CSS: declarations, selectors, at-rules — read by the DOM, not by a person',
    test: (s) => /[{}]/.test(s) || /[a-z-]+\s*:\s*[^;]+;/.test(s) || /^\s*@(media|supports|keyframes|font-face)/.test(s) || /^\s*[.#][a-zA-Z]/.test(s) || /^\s*\[[a-z-]+[~|^$*]?=/.test(s) },
  { why: 'HTML fragments: these plugins build popup markup in template literals, so a quasi is often '
       + 'a tag, or the seam between two attributes ("\" alt=\"" / "\" loading=\"lazy\">")',
    test: (s) => /<\/?[a-zA-Z][^>]*>?/.test(s)
      || /\b(class|href|src|alt|loading|width|height|style|id|target|rel)\s*=/.test(s)
      || /^["'>\s]*$/.test(s) || /^<\/|^["']?\s*>/.test(s) },
  { why: 'URLs and url fragments, absolute OR relative (gospel: a relative URL was reported as prose)',
    test: (s) => /^(https?:|\/\/|\/|\?|&|#)/.test(s)
      || /^\.{0,2}\/[^\s]*$/.test(s)
      || (/^[^\s]+\.(json|js|css|svg|png|jpe?g|webp|geojson|csv|html?)$/i.test(s)) },
  { why: 'CSS class/id SUFFIXES built by interpolation (gospel: `${x}-fill`, `${x}-line` read as prose)',
    test: (s) => /^[-_][a-z0-9][a-z0-9-]*$/.test(s) },
  { why: 'custom-element tag names: lowercase and hyphenated, a tag is not a sentence',
    test: (s) => /^<?\/?[a-z][a-z0-9]*(-[a-z0-9]+)+>?$/.test(s) },
  { why: 'BCP-47 locale extensions and language tags (e.g. the latin-digits override)',
    test: (s) => /^-?[a-z]{2,3}(-[A-Za-z0-9]{2,8})*$/.test(s) || /-u-[a-z]{2}-/.test(s) },
  { why: 'developer error text: a bracketed module prefix or an HTTP status, for the console',
    test: (s) => /^\[[a-z0-9-]+\]/i.test(s) || /^HTTP\b/.test(s) },
  { why: 'DOM id / class / data-key fragments: hyphenated or BEM identifiers, alone or as a class LIST',
    // Every token must carry a separator. That is what tells `rd-card is-open` from `the map`:
    // prose words do not contain hyphens, and this codebase's classes always do. A class list with
    // no hyphen anywhere (`card open`) is deliberately NOT allowed — flagging is the safe direction.
    // A trailing separator is allowed because that is the shape of an id PREFIX built by
    // interpolation — `id="country-${code}"` leaves the quasi "country-".
    test: (s) => s.split(/\s+/).every((tok) => /^[a-z][a-z0-9]*(?:[-_]{1,2}[a-z0-9]*)+$/.test(tok)) },
  { why: 'font family names: typeface identifiers, never translated',
    test: (s) => /^(Bebas Neue|Poppins|Oswald|Figtree|Segoe UI|Helvetica Neue|Times New Roman)$/.test(s) },
  { why: 'engine/provider tokens and well-known proper nouns that are not prose',
    test: (s) => /^(mapbox|maplibre|mercator|globe|Mapbox|MapLibre)$/.test(s) },
]
const allowedBy = (s) => ALLOW.find((a) => a.test(s))

// ── localisation calls: base names plus aliases discovered per file ──────────────────────────────
function localizedNames(code) {
  const names = new Set(['t', 'tf', '$t'])
  for (const m of code.matchAll(/\bconst\s+([A-Za-z_$][\w$]*)\s*=\s*(t|tf)\b\s*(?![(.])/g)) names.add(m[1])
  return names
}
// ★ A DOM QUERY ARGUMENT IS A SELECTOR, NOT PROSE — and a selector made of custom-element tags
// reads as English only because the tag names are English words. gospel found
// `querySelector("gospel-resources-dashboard, gospel-resources-map")` reported as user-visible text:
// the single-tag rule matched neither, because it is a comma-separated LIST. Exempting by CALL SITE
// is the right shape (as with developer strings) — the site is the fact, and no content rule can
// reliably tell a tag list from a sentence.
const DOM_QUERY = new Set([
  'querySelector', 'querySelectorAll', 'closest', 'matches', 'getElementById',
  'getElementsByClassName', 'getElementsByTagName', 'getElementsByName',
])
function isDomQuerySite(parent) {
  return !!parent && parent.type === 'CallExpression'
    && parent.callee?.type === 'MemberExpression'
    && DOM_QUERY.has(parent.callee.property?.name || '')
}

// A literal that is an argument to one of these never reaches a reader, whatever it says.
function isDeveloperSite(parent) {
  if (!parent) return false
  if (parent.type === 'CallExpression' && parent.callee?.object?.name === 'console') return true
  if (parent.type === 'NewExpression' && /^[A-Z]\w*Error$|^Error$/.test(parent.callee?.name || '')) return true
  if (parent.type === 'CallExpression' && /^[A-Z]\w*Error$|^Error$/.test(parent.callee?.name || '')) return true
  return false
}
const calleeName = (node) => node?.callee?.type === 'Identifier' ? node.callee.name
  : node?.callee?.type === 'MemberExpression' ? (node.callee.property?.name || '') : ''

// ── CROSS-AREA KEYS THROUGH A NAMESPACED TRANSLATOR ─────────────────────────────────────────────
// ★ A REAL BUG, FOUND TWICE IN ONE DAY (pplr a56d06c8, cities-internet 7b3fb78d5), that no gate saw.
// `const t = useOptionalT('connectivity')` then `t('messages.engineMissing')` — qualify() makes that
// `connectivity.messages.engineMissing`, which cannot exist, so the English fallback is the NORMAL
// path in every locale. check:i18n-keys-exist passes it because the key AS WRITTEN does exist; the
// key as QUALIFIED is what misses. The user-visible outcome is identical to a hardcoded string,
// which is why it belongs in this gate: a reader sees English where their language was promised.
// Detected by SHAPE — qualified key absent AND unqualified key present — so it cannot fire on an
// ordinary missing key, which is check:i18n-keys-exist's job, not this one.
const qualifyKey = (ns, key) => (ns && !key.startsWith(`${ns}.`) ? `${ns}.${key}` : key)

let CATALOGUE = null
function catalogue(root = '.') {
  if (CATALOGUE) return CATALOGUE
  CATALOGUE = {}
  const dir = join(root, 'library/i18n/locales/en')
  if (!existsSync(dir)) return CATALOGUE
  for (const f of readdirSync(dir)) {
    if (!f.endsWith('.json')) continue
    try { CATALOGUE[f.replace(/\.json$/, '')] = JSON.parse(readFileSync(join(dir, f), 'utf8')) } catch { /* skip */ }
  }
  return CATALOGUE
}
// `a.b.c` resolves as area `a` then path b.c inside it — the shape library/i18n/index.js builds.
function resolveKey(key, root = '.') {
  const cat = catalogue(root)
  const [area, ...rest] = String(key).split('.')
  let node = cat[area]
  if (node === undefined) return undefined
  for (const seg of rest) {
    if (node === null || typeof node !== 'object') return undefined
    node = node[seg]
    if (node === undefined) return undefined
  }
  return node
}

// ★ WRAPPER FACTORIES CARRY THE NAMESPACE ONE INDIRECTION AWAY, and missing that is why the first
// version of this check caught cities-internet but NOT pplr — the bug it was written for. pplr does
// `const t = usePplrT()` with NO argument, and usePplrT() is `return useOptionalT('pplr')`. A check
// that only reads a literal argument sees no namespace and stays silent on the exact defect twice
// over. So wrappers are resolved from source first.
let WRAPPERS = null
function wrapperNamespaces(root = '.') {
  if (WRAPPERS) return WRAPPERS
  WRAPPERS = {}
  const roots = [join(root, 'library/composables'), join(root, 'plugin-designs')]
  const visit = (d, depth = 0) => {
    if (depth > 4 || !existsSync(d)) return
    for (const e of readdirSync(d, { withFileTypes: true })) {
      const f = join(d, e.name)
      if (e.isDirectory()) { if (!/node_modules|dist/.test(e.name)) visit(f, depth + 1); continue }
      if (!e.name.endsWith('.js')) continue
      let src = ''
      try { src = readFileSync(f, 'utf8') } catch { continue }
      for (const m of src.matchAll(/export\s+function\s+(use[A-Za-z]*T)\s*\([^)]*\)\s*\{[^}]*useOptionalT\s*\(\s*['"]([^'"]+)['"]/g)) {
        WRAPPERS[m[1]] = m[2]
      }
    }
  }
  roots.forEach((r) => visit(r))
  return WRAPPERS
}

// `const t = useOptionalT('connectivity')` → { t: 'connectivity' }
// `const t = usePplrT()`                   → { t: 'pplr' }, via the wrapper map above
function namespacedTranslators(code, root = '.') {
  const map = {}
  for (const m of code.matchAll(/\bconst\s+([A-Za-z_$][\w$]*)\s*=\s*use[A-Za-z]*T\s*\(\s*['"]([^'"]+)['"]/g)) map[m[1]] = m[2]
  const wrappers = wrapperNamespaces(root)
  for (const m of code.matchAll(/\bconst\s+([A-Za-z_$][\w$]*)\s*=\s*(use[A-Za-z]*T)\s*\(\s*\)/g)) {
    if (wrappers[m[2]]) map[m[1]] = wrappers[m[2]]
  }
  return map
}

export function crossAreaKeys(code, file, root = '.') {
  const out = []
  const ns = namespacedTranslators(code, root)
  if (!Object.keys(ns).length) return out
  let ast
  try { ast = babel.parse(code, { sourceType: 'module', plugins: ['jsx'], errorRecovery: true }) } catch { return out }
  walkAst(ast, (node) => {
    if (node.type !== 'CallExpression') return
    const name = node.callee?.type === 'Identifier' ? node.callee.name : ''
    if (!ns[name]) return
    const arg = node.arguments?.[0]
    if (arg?.type !== 'StringLiteral' || !arg.value.includes('.')) return
    const qualified = qualifyKey(ns[name], arg.value)
    if (resolveKey(qualified, root) !== undefined) return          // resolves: fine
    if (resolveKey(arg.value, root) === undefined) return          // plain missing key: keys-exist's job
    out.push({ file, kind: 'cross-area-key', text: `${name}('${arg.value}') → ${qualified} (never resolves; '${arg.value}' does)` })
  })
  return out
}

// ── the walk ────────────────────────────────────────────────────────────────────────────────────
function walkAst(node, visit, parent = null, stack = []) {
  if (!node || typeof node.type !== 'string') return
  visit(node, parent, stack)
  const next = [...stack, node]
  for (const k of Object.keys(node)) {
    if (k === 'loc' || k === 'leadingComments' || k === 'trailingComments') continue
    const v = node[k]
    if (Array.isArray(v)) { for (const c of v) if (c && typeof c.type === 'string') walkAst(c, visit, node, next) }
    else if (v && typeof v.type === 'string') walkAst(v, visit, node, next)
  }
}
// A literal is a GUARDED FALLBACK — reachable only when a translation is absent — in two shapes:
//   · te(key) ? t(key) : 'English'        the documented existence check (sr)
//   · t.search || 'Search…'               a PROXY t whose member read misses (people-groups-grid)
// Both mean "the catalogue had nothing", so the English is the designed last resort rather than a
// string that skipped translation. Ancestors are walked, not just the immediate parent, because the
// fallback is often nested (`a ?? (te(k) ? t(k) : 'X')`).
function guardedFallback(stack, names) {
  return stack.some((n) => {
    if (n.type !== 'ConditionalExpression' && n.type !== 'LogicalExpression') return false
    let found = false
    walkAst(n.test || n.left, (x) => {
      if (x.type === 'CallExpression' && /^te$/.test(calleeName(x))) found = true
      // a member read on a localisation object or alias: t.search, i18n.t.search
      if (x.type === 'MemberExpression' && x.object?.type === 'Identifier' && names.has(x.object.name)) found = true
      // THE "DID t() RETURN THE KEY?" IDIOM. vue-i18n returns the key itself when it is missing, so
      // `msg !== 'messages.engineMissing' ? msg : 'English'` is a miss check and its English arm is a
      // fallback. Matched on the KEY SHAPE (dotted, no spaces) rather than on any string comparison,
      // so an ordinary `x !== 'yes'` is not mistaken for one. (cities-internet, triaged 2026-09-28.)
      if (x.type === 'BinaryExpression' && /^[!=]==?$/.test(x.operator)) {
        for (const side of [x.left, x.right]) {
          if (side?.type === 'StringLiteral' && /^[a-z][\w-]*(\.[\w-]+)+$/.test(side.value)) found = true
        }
      }
    })
    return found
  })
}

function scanScript(code, file, out) {
  const names = localizedNames(code)
  const ast = babel.parse(code, { sourceType: 'module', plugins: ['jsx'], errorRecovery: true })
  walkAst(ast, (node, parent, stack) => {
    const isStr = node.type === 'StringLiteral'
    const isTpl = node.type === 'TemplateLiteral'
    if (!isStr && !isTpl) return
    if (parent && parent.type === 'CallExpression' && names.has(calleeName(parent))) return   // t('…')
    // ★ DEVELOPER STRINGS ARE EXEMPT BY CALL SITE, NOT BY CONTENT (upg100). `throw new Error('…')`
    // and console.* never reach a reader, and judging them by their text means inventing a rule for
    // every sentence a developer might write. The SITE is the fact; the wording is not.
    if (isDeveloperSite(parent) || isDomQuerySite(parent)) return
    if (parent && /Import|Export/.test(parent.type)) return
    if (parent && parent.type === 'TaggedTemplateExpression') return
    if (guardedFallback(stack, names)) return

    if (isStr) {
      const text = node.value.trim()
      if (!text.length || !isProse(text)) return   // gospel: empty matches were being reported
      if (!/\s/.test(text)) return                 // ⚠ the single-word blind spot, documented above
      if (allowedBy(text)) return
      out.push({ file, kind: 'script-string', text })
      return
    }
    // ★ ONE TEMPLATE LITERAL IS ONE FINDING (upg100). Reporting each quasi separately turned a single
    // string into 'polys ·', 'zones ·', 'px;' — three hits for one defect, which inflates every count
    // and makes a triage list read as worse than the code is. Each quasi is still JUDGED on its own,
    // so an allow-listed fragment cannot drag a whole literal in; only the REPORT is joined.
    const quasis = node.quasis.map((q) => String(q.value.cooked ?? q.value.raw ?? ''))
    const leaks = quasis.some((raw) => {
      const text = raw.trim()
      return text.length && isProse(text) && !allowedBy(text)
    })
    if (!leaks) return
    const whole = quasis.map((q) => q.trim()).filter(Boolean).join(' {…} ').trim()
    out.push({ file, kind: 'template-literal', text: whole })
  })
}

// ★ BOUND ATTRIBUTES HIDE LEAKS FROM A TEMPLATE WALKER. `:title="`Sort by ${col}`"` is a DIRECTIVE
// whose value is an EXPRESSION, not a static attribute, so a scan that reads only static attrs sees
// nothing — a blind spot every one of the four private scanners shared (sr, 2026-09-28; real case
// DashboardDataTable.vue:884). The expression is parsed with the same rules as a script block, so a
// literal inside t()/tf(), or behind a te() guard, still passes.
function scanBoundExpr(expr, file, attrName, out) {
  const code = String(expr || '').trim()
  if (!code) return
  const found = []
  try { scanScript(`(${code})`, file, found) } catch { return }   // not parseable as an expression: skip
  for (const f of found) out.push({ file, kind: `bind:${attrName}`, text: f.text })
}

// ★ dir="ltr" MARKS TEXT THAT IS MEANT TO STAY ENGLISH. gospel's plugins use it as the island
// marker for content the agent ruled stays English (a BLUF, a source citation), so flagging it as a
// leak would ask someone to "fix" a deliberate decision. Such findings are marked deliberate, listed
// SEPARATELY, and excluded from the count a gate would fail on — visible, but not a defect.
// Inherited down the subtree: a dir="ltr" wrapper covers everything inside it.
const hasLtr = (node) => (node.props || []).some((p) =>
  (p.type === 6 && p.name === 'dir' && p.value?.content === 'ltr')
  || (p.type === 7 && p.name === 'bind' && p.arg?.content === 'dir' && /['"]ltr['"]/.test(p.exp?.content || '')))

function walkTemplate(node, file, out, ltr = false) {
  if (!node) return
  const inLtr = ltr || (node.type === 1 && hasLtr(node))
  if (node.type === 2) {
    const raw = String(node.content || '').trim()
    if (raw.length && isProse(raw) && !allowedBy(raw)) out.push({ file, kind: 'template-text', text: raw, deliberate: inLtr })
  }
  if (node.type === 1) for (const p of node.props || []) {
    if (p.type === 6 && VISIBLE_ATTRS.has(p.name)) {
      const v = p.value && p.value.content
      if (v && isProse(v) && !allowedBy(v)) out.push({ file, kind: `attr:${p.name}`, text: v, deliberate: inLtr })
    }
    // (interpolations are handled below, on the node itself)
    // type 7 = DIRECTIVE. v-bind carries the attribute name in `arg`.
    if (p.type === 7 && p.name === 'bind' && p.exp?.content) {
      const attrName = p.arg?.content || 'bind'
      // :style and :class carry CSS and identifiers, never prose. Skipping them by ATTRIBUTE is
      // better than allow-listing their contents: `background-image: url(` has no semicolon and so
      // slipped the CSS shape test, and widening that test to catch it would start swallowing real
      // sentences that happen to contain a colon.
      if (attrName !== 'style' && attrName !== 'class') {
        const before = out.length
        scanBoundExpr(p.exp.content, file, attrName, out)
        for (let i = before; i < out.length; i++) out[i].deliberate = inLtr
      }
    }
  }
  // type 5 = INTERPOLATION. `{{ cond ? 'Yes' : 'No' }}` is the same defect as a bound attribute —
  // a literal the reader sees, assembled in an expression the template walker would otherwise skip.
  // `{{ t('Foo') }}` stays quiet because the expression is parsed with the same translator rules.
  if (node.type === 5 && node.content?.content) {
    const before = out.length
    scanBoundExpr(node.content.content, file, 'interpolation', out)
    for (let i = before; i < out.length; i++) out[i].deliberate = inLtr
  }
  for (const c of node.children || []) walkTemplate(c, file, out, inLtr)
}

export function scanSfc(src, file) {
  const out = []
  const { descriptor, errors } = parse(src, { filename: file })
  if (errors && errors.length) throw new Error(`${file}: ${errors[0].message}`)
  if (descriptor.template && descriptor.template.ast) walkTemplate(descriptor.template.ast, file, out)
  const code = [descriptor.script?.content, descriptor.scriptSetup?.content].filter(Boolean).join('\n')
  if (code) { scanScript(code, file, out); out.push(...crossAreaKeys(code, file)) }
  return out
}

// ── production plugins: the scope this gate defends ─────────────────────────────────────────────
// Read from the built manifest so the list cannot drift from what actually ships.
function productionPluginDirs(root = '.') {
  const mf = join(root, 'public/dx-maps/manifest.json')
  if (!existsSync(mf)) return []
  const m = JSON.parse(readFileSync(mf, 'utf8'))
  const names = m.bundles.filter((b) => b.stage === 'production').map((b) => b.bundle)
  return names.map((n) => join(root, 'plugin-designs', n)).filter((d) => existsSync(d))
}
const sfcsIn = (dir) => {
  const out = []
  const walk = (d) => { for (const e of readdirSync(d, { withFileTypes: true })) {
    const p = join(d, e.name)
    if (e.isDirectory()) { if (!/node_modules|dist|snapshots|fixtures/.test(e.name)) walk(p) }
    else if (e.name.endsWith('.vue')) out.push(p)
  } }
  walk(dir); return out
}

// ── self-test: the gate must be shown able to SEE, and able to stay quiet ────────────────────────
const PLANTED_BAD = `<template>
  <div>
    <h2>Prayer Coverage</h2>
    <button title="Reset the map">x</button>
    <th :title="\`Sort this table by \${col}\`">h</th>
    <button :title="'Reset the view'">r</button>
    <span>{{ ok ? 'Everything loaded' : 'Nothing loaded' }}</span>
    <p dir="ltr">Counted BY LANGUAGE, so groups collapse.</p>
    <div dir="ltr"><em>Source: eBible, checked 2026-09</em></div>
    <p><bdi dir="ltr">Of {{ tally.langs }} sign languages on this map, covering {{ tally.people }} people,
      {{ tally.both }} have both a film and a text Scripture.</bdi></p>
  </div>
</template>
<script setup>
import { a } from './a.js'
import { b } from '../b/c.js'
const msg = 'No results were found'
const split = \`\${a} polys · \${b} zones · \`
const ctx = \`\${n} countries\`
</script>`
const PLANTED_GOOD = `<template>
  <div class="rd-card is-open">
    <h2>{{ t('Prayer Coverage') }}</h2>
    <th :title="t('Sort this table')" :class="\`rd-card \${x}\`" :id="\`country-\${code}\`">h</th>
    <span>{{ t('Prayer Coverage') }}</span>
    <span>{{ n }} {{ t('Countries') }}</span>
  </div>
</template>
<script setup>
import { alpha } from './alpha.js'
import { beta } from '../beta/gamma.js'
const t2 = t
const viaAlias = t2('All Regions')
const guarded = te(key) ? t(key) : 'Regions List'
const cls = 'rd-card is-open'
const url = 'https://example.test/a/b'
const lang = \`\${l}-u-nu-latn\`
const err = \`HTTP \${res.status}\`
const lone = 'Other'
const proxyMiss = t.search || 'Search names, country, religion…'
const keyMiss = msg !== 'messages.engineMissing' ? msg : 'The map engine did not load.'
const devThrow = () => { throw new Error('table not found for this request') }
const devWarn = () => console.warn('boundaries failed to load for this map')
const host = document.querySelector('gospel-resources-dashboard, gospel-resources-map')
const one = el.closest('regions-dashboard, doxa-simple-map')
</script>`

const XAREA_BAD = `const t = useOptionalT('regions')
const msg = t('messages.engineMissing')`
// The wrapper shape: no literal namespace at the call site, so it is only detectable by resolving
// usePplrT() back to useOptionalT('pplr'). This is the shape pplr actually had.
const XAREA_WRAPPED = `const t = usePplrT()
const msg = t('messages.mapUnavailable')`
const XAREA_GOOD = `const t = useOptionalT('messages')
const msg = t('engineMissing')
const t2 = useOptionalT('regions')
const ok2 = t2('Countries')`

function selfTest() {
  let fails = 0
  const ok = (c, m) => { console.log(`  ${c ? 'ok  ' : 'FAIL'} - ${m}`); if (!c) fails++ }
  // ★ THE FIXTURES MUST PARSE, ASSERTED FIRST. sr's first planted sample was malformed Vue, so the
  // scan found nothing in it and LOOKED blind — a broken fixture and a broken scanner produce the
  // same silence. parse() surfaces template errors that scanSfc would otherwise throw on.
  for (const [name, src] of [['planted-bad', PLANTED_BAD], ['planted-good', PLANTED_GOOD]]) {
    const { errors } = parse(src, { filename: `${name}.vue` })
    ok(!errors || errors.length === 0, `FIXTURE ${name}.vue is valid Vue${errors && errors.length ? ': ' + errors[0].message : ''}`)
  }
  const bad = scanSfc(PLANTED_BAD, 'planted-bad.vue')
  const good = scanSfc(PLANTED_GOOD, 'planted-good.vue')
  ok(bad.some((f) => f.kind === 'template-text' && f.text === 'Prayer Coverage'), 'SEES a hardcoded heading in the TEMPLATE')
  ok(bad.some((f) => f.kind === 'attr:title'), 'SEES a hardcoded title= attribute')
  ok(bad.some((f) => f.kind === 'script-string' && f.text === 'No results were found'), 'SEES a hardcoded sentence in a SCRIPT BLOCK')
  ok(bad.some((f) => f.kind === 'template-literal' && f.text === 'countries'), 'SEES English inside a TEMPLATE LITERAL (the class that held a real defect)')
  ok(bad.some((f) => f.kind === 'bind:title' && /Sort this table by/.test(f.text)), 'SEES a TEMPLATE LITERAL inside a bound attribute (sr: every scanner missed this)')
  ok(bad.some((f) => f.kind === 'bind:title' && f.text === 'Reset the view'), "SEES a quoted '…' literal inside a bound attribute (both quote styles)")
  ok(bad.some((f) => f.kind === 'bind:interpolation' && /Everything loaded|Nothing loaded/.test(f.text)), 'SEES a literal inside an INTERPOLATION expression')
  const splits = bad.filter((f) => /polys|zones/.test(f.text))
  ok(splits.length === 1, `a split template literal is ONE finding, not one per fragment (got ${splits.length})`)
  ok(splits.length === 1 && /polys.*\{…\}.*zones/.test(splits[0].text), 'and it is reported as the WHOLE string with its holes marked')
  const ltr = bad.filter((f) => f.deliberate)
  ok(ltr.some((f) => /Counted BY LANGUAGE/.test(f.text)), 'marks text inside dir="ltr" as DELIBERATE, not a leak')
  ok(ltr.some((f) => /Source: eBible/.test(f.text)), 'and INHERITS the marker down the subtree')
  // ★ gospel's real case: an island SPLIT BY INTERPOLATIONS. Each run between two {{ }} is its own
  // text node, so a check that only marked a whole-text island reported the pieces as separate
  // leaks — and they nearly got translated. <bdi dir="ltr"> is the element they actually use.
  const splitIsland = bad.filter((f) => /sign languages on this map|both a film/.test(f.text))
  ok(splitIsland.length > 0, 'sees the pieces of an interpolation-split island at all')
  ok(splitIsland.every((f) => f.deliberate),
    `every piece of an interpolation-split dir="ltr" island is DELIBERATE (got ${splitIsland.filter((f) => !f.deliberate).length} not marked)`)
  ok(bad.filter((f) => !f.deliberate).some((f) => f.text === 'Prayer Coverage'), 'while a leak OUTSIDE the island is still counted')
  ok(!good.some((f) => f.text === 'All Regions'), 'QUIET on a call through an ALIAS of t()')
  ok(!good.some((f) => f.text === 'Regions List'), 'QUIET on a te()-guarded fallback')
  ok(!good.some((f) => String(f.kind).startsWith('bind:')), 'QUIET on a bound attribute that IS a translator call')
  ok(!good.some((f) => /Search names/.test(f.text)), 'QUIET on a proxy-t member miss (t.search || …) — a fallback, not a leak')
  ok(!good.some((f) => f.kind === 'bind:interpolation'), 'QUIET on interpolations that are translator calls or bare values')
  ok(!good.some((f) => /map engine did not load/.test(f.text)), 'QUIET on the "did t() return the key?" miss idiom (msg !== \'a.dotted.key\')')
  ok(!good.some((f) => /table not found/.test(f.text)), 'QUIET on a throw new Error(…) argument — exempt by CALL SITE')
  ok(!good.some((f) => /boundaries failed/.test(f.text)), 'QUIET on a console.warn(…) argument')
  ok(!good.some((f) => /gospel-resources-dashboard|regions-dashboard, doxa/.test(f.text)),
    'QUIET on a DOM query selector, including a comma-separated list of custom-element tags')
  ok(!good.some((f) => /rd-card|example\.test|nu-latn|HTTP/.test(f.text)), 'QUIET on css, urls, locale extensions and developer error text')
  ok(good.length === 0, `QUIET overall on a correct file (got ${good.length}${good.length ? ': ' + JSON.stringify(good[0]) : ''})`)
  // The blind spot is PINNED, not merely mentioned: if single-word detection is ever added, this
  // fails and whoever adds it must update the header rather than leave it claiming a gap that closed.
  ok(!good.some((f) => f.text === 'Other'), 'DOCUMENTED BLIND SPOT: a single-word leak is NOT reported (see header)')
  // ★ CROSS-AREA KEYS: a real bug found twice in one day, and the shape both instances had.
  const xb = crossAreaKeys(XAREA_BAD, 'planted-xarea.vue')
  const xg = crossAreaKeys(XAREA_GOOD, 'planted-xarea-ok.vue')
  ok(xb.length === 1 && /never resolves/.test(xb[0].text),
    'SEES a cross-area key through a namespaced t() (qualified misses, unqualified exists)')
  ok(xg.length === 0, `QUIET when the key resolves under its own namespace (got ${xg.length})`)
  const xw = crossAreaKeys(XAREA_WRAPPED, 'planted-xarea-wrapped.vue')
  ok(xw.length === 1 && /pplr\.messages\.mapUnavailable/.test(xw[0].text),
    'SEES it through a WRAPPER factory with no literal namespace (usePplrT() → useOptionalT(\'pplr\'))')
  console.log(fails ? `\nSELF-TEST: ${fails} FAIL(s)` : '\nSELF-TEST: the gate can see planted leaks and stays quiet on correct code')
  return fails
}

// Short HEAD sha plus a dirty marker, or 'unknown' outside a checkout.
function treeStamp() {
  try {
    const sha = execSync('git rev-parse --short HEAD', { stdio: ['ignore', 'pipe', 'ignore'] }).toString().trim()
    const dirty = execSync('git status --porcelain', { stdio: ['ignore', 'pipe', 'ignore'] }).toString().trim()
    return dirty ? `${sha}+dirty(${dirty.split('\n').length} file(s))` : sha
  } catch { return 'unknown (not a git checkout)' }
}

// ── main ────────────────────────────────────────────────────────────────────────────────────────
// RUN ONLY WHEN INVOKED DIRECTLY. Without this guard, `import`ing the module to reuse scanSfc() runs
// the whole production scan as a side effect — which is how I first "verified" it against sr's real
// example and got a full gate run instead of one file's findings. A gate that cannot be imported
// cannot be unit-tested by whoever owns it.
const isMain = process.argv[1] && import.meta.url === pathToFileURL(process.argv[1]).href
if (!isMain) { /* imported: expose scanSfc and do nothing */ }
else main()

function main() {
const selfOnly = process.argv.includes('--self-test')
let fails = selfTest()
if (fails) { console.log('\nHARDCODED-ENGLISH: self-test failed — findings below would not be trustworthy'); process.exit(1) }
if (selfOnly) process.exit(0)

const dirs = productionPluginDirs('.')
const findings = []
let files = 0
try {
  for (const d of dirs) for (const f of sfcsIn(d)) { files++; findings.push(...scanSfc(readFileSync(f, 'utf8'), f)) }
} catch (e) { console.error('HARDCODED-ENGLISH: parse error —', e.message); process.exit(2) }

const deliberate = findings.filter((f) => f.deliberate)
const leaks = findings.filter((f) => !f.deliberate)
// ★ THE RUN NAMES ITS OWN SHA. Three reports today were true of an older artifact than the one in
// hand, and each cost someone a wasted investigation — the last one nearly had a working island
// check "fixed". gospel's corollary is that the reader cannot check what the writer did not say, so
// the tool says it: any number quoted from this output carries the tree it was measured on, and a
// dirty tree is marked because then the sha alone does not describe what ran.
//
// ★ AND IT PROVED ITSELF WITHIN THE HOUR, in the case that justifies it better than the one it was
// built for. gospel and I compared counts and disagreed — 185/169/155 against 178/168/147 — and
// spent the exchange assuming one set was stale. Neither was: SAME SCRIPT SHA, DIFFERENT SOURCE
// TREES, twelve scanned SFCs apart. Both numbers were honest measurements of different bytes.
// "7 production plugin(s), 19 SFC(s) scanned" describes the SHAPE of a scan and says nothing about
// WHICH BYTES, so two correct runs are indistinguishable in a report. The stamp is therefore not
// only for the writer who forgets to name a sha — it is what lets a READER tell two runs apart at
// all. When counts disagree, compare the tree line before anything else.
console.log(`\n  ${dirs.length} production plugin(s), ${files} SFC(s) scanned  ·  tree ${treeStamp()}`)
for (const f of leaks) console.log(`   ${f.kind.padEnd(16)} ${f.file.replace(/^.*plugin-designs\//, '')}  ${JSON.stringify(f.text).slice(0, 90)}`)
if (deliberate.length) {
  // Listed so nobody wonders where they went, but NOT counted: dir="ltr" is the plugin's own marker
  // for content the agent ruled stays English. Asking someone to "fix" these would be asking them
  // to undo a decision.
  console.log(`\n  ${deliberate.length} inside dir="ltr" islands — DELIBERATE English, not counted:`)
  for (const f of deliberate.slice(0, 8)) console.log(`   · ${f.file.replace(/^.*plugin-designs\//, '')}  ${JSON.stringify(f.text).slice(0, 80)}`)
  if (deliberate.length > 8) console.log(`   · …and ${deliberate.length - 8} more`)
}
// ★ THE STAMP GOES ON THE LINE PEOPLE QUOTE, not only on the header. gospel's qualification is that
// they investigated our mismatch because the ARITHMETIC WOULD NOT CLOSE — an eight-hit gap was too
// large to rationalise — and that a gap of one or two would have been shrugged off as drift. So the
// residual failure is a discrepancy SMALL ENOUGH TO EXPLAIN AWAY, and provenance in a header the
// quoter skips does nothing for it. The verdict line is the one that gets pasted into a report, so
// the tree travels with the number rather than three lines above it.
console.log(leaks.length
  ? `\nHARDCODED-ENGLISH: ${leaks.length} user-visible English string(s) not going through t()  [tree ${treeStamp()}]`
  : `\nHARDCODED-ENGLISH: PASS — no user-visible hardcoded English in any production plugin  [tree ${treeStamp()}]`)
process.exit(leaks.length ? 1 : 0)
}