#!/usr/bin/env node
/**
 * applyBrand.mjs — brand TEXT from the bind mount (PLAN.md §7)
 *
 * Runs immediately before the server, as part of `npm start`. For an empty mount — the
 * stock deployment, and the common case — it reads two small files, finds nothing to do
 * and exits. It is not a build step and it is not a template engine.
 *
 * ---------------------------------------------------------------------------------------
 * THE PROBLEM THIS SOLVES
 * ---------------------------------------------------------------------------------------
 * §7 promises that renaming the product, changing the Discord invite or publishing a
 * different contact address is the same class of change as swapping a logo: edit the file
 * in the mount, restart, done. §6 prerenders every page. Those two are in direct conflict,
 * because a value read at build time is baked into HTML that no mounted file can reach.
 *
 * Assets escape the conflict by being served per request from `/brand/*`. Text cannot: it
 * is inside the markup.
 *
 * Three ways out were considered and the org lead chose this one (2026-08-20):
 *
 *   1. THIS — rewrite the built HTML at boot, before the server opens a socket. Every page
 *      stays prerendered, Pagefind still has static HTML to index in phase 10, and the docs
 *      are covered by the same pass as the marketing pages.
 *   2. Mark the brand-bearing pages `prerender = false`. Simpler, but the footer is on
 *      every page, so "the handful" is the whole site — and the docs would have to stay
 *      static for search anyway, leaving them showing the stock name.
 *   3. Accept text as build-time and amend §7. Cheapest, and it gives up the promise.
 *
 * ---------------------------------------------------------------------------------------
 * WHY IT REWRITES FROM A RECORD RATHER THAN FROM THE DEFAULTS
 * ---------------------------------------------------------------------------------------
 * The obvious version of this script replaces the DEFAULT value with the mounted one. It
 * works exactly once. The second time an operator edits the mount — renaming from "Foo" to
 * "Bar" — the default no longer appears anywhere in the HTML, every replacement matches
 * nothing, and the site silently keeps saying "Foo". The bug would surface as "the first
 * change worked and the second did nothing", which is a miserable thing to debug.
 *
 * So the script records what it baked, in `dist/.brand-applied.json`, and the next run
 * rewrites from that record to the new values. A fresh image has no record and starts from
 * the defaults, which is the same thing said differently.
 *
 * ---------------------------------------------------------------------------------------
 * WHAT MAKES PLAIN STRING REPLACEMENT SAFE HERE
 * ---------------------------------------------------------------------------------------
 * Not much, on its own — which is why `scripts/checkBrand.mjs` exists. It fails the build
 * if any rewritable default is short enough to collide with ordinary markup or prose. The
 * check is the mechanism; the eight-character minimum below is only its last line.
 *
 * Replacing the site name across the docs as well as the marketing pages is deliberate. If
 * the product is renamed, prose that says "Runic Gateway" should say the new name too.
 */

import { readFileSync, writeFileSync, existsSync, readdirSync, statSync } from 'node:fs';
import { fileURLToPath } from 'node:url';
import path from 'node:path';

const ROOT = fileURLToPath(new URL('..', import.meta.url));

const DIST = process.env.BRAND_DIST || path.join(ROOT, 'dist');
const CLIENT = path.join(DIST, 'client');
const RECORD = path.join(DIST, '.brand-applied.json');

const MOUNT_DIR = process.env.BRAND_DIR || path.join(process.cwd(), 'brand');
const DEFAULT_DIR = process.env.BRAND_DEFAULT_DIR || path.join(process.cwd(), 'brand-default');

/**
 * The fields that appear in markup as literal text, and may therefore be rewritten.
 *
 * `demoUrl` is not one of them and is handled separately below: its default is the empty
 * string, and there is no such thing as replacing every occurrence of "".
 */
const TEXT_FIELDS = ['siteName', 'tagline', 'contactEmail', 'discordInvite', 'giteaOrg'];

/**
 * Below this length a value is too likely to occur inside unrelated markup — a class name,
 * an attribute, a word in a sentence — for a blind replacement to be safe. `checkBrand.mjs`
 * enforces the same floor at build time, where the failure is cheap; this is the copy that
 * runs in production, where being wrong means corrupted pages.
 */
const MIN_REWRITABLE_LENGTH = 8;

const REWRITABLE_EXTENSIONS = new Set(['.html', '.webmanifest']);

function readJson(file, label) {
  try {
    return JSON.parse(readFileSync(file, 'utf8'));
  } catch (error) {
    if (error.code === 'ENOENT') return null;
    // A malformed mounted brand.json must not take the site down.
    //
    // The alternative — exit non-zero and let the container crash-loop — surfaces the typo
    // immediately, and that is genuinely tempting. But an operator editing a mount is
    // watching the logs, whereas the restart six months later that trips over the same file
    // is unattended, and a marketing site that is up with stock branding beats one that is
    // down with correct branding.
    console.error(`\n[brand] ${label} is not valid JSON and will be IGNORED:\n  ${file}\n  ${error.message}\n`);
    return null;
  }
}

/** `$comment` keys are documentation for whoever opens the mounted copy, not fields. */
const fieldsOf = (object) =>
  Object.fromEntries(Object.entries(object || {}).filter(([key]) => !key.startsWith('$')));

const defaults = fieldsOf(readJson(path.join(DEFAULT_DIR, 'brand.json'), 'the stock brand.json'));
const mounted = fieldsOf(readJson(path.join(MOUNT_DIR, 'brand.json'), 'the mounted brand.json'));

if (!Object.keys(defaults).length) {
  console.error(
    `\n[brand] no stock brand.json at ${path.join(DEFAULT_DIR, 'brand.json')}.\n` +
      `brand-default/ is baked into the image and must always be complete (§7).\n`
  );
  process.exit(1);
}

for (const key of Object.keys(mounted)) {
  if (!(key in defaults)) {
    console.warn(`[brand] the mounted brand.json sets an unknown field "${key}" — ignoring it.`);
  }
}

const resolved = { ...defaults, ...mounted };
const previous = { ...defaults, ...(fieldsOf(readJson(RECORD, 'the applied-brand record')) || {}) };

/* ---------------------------------------------------------------------------------------
   Work out what actually changed
   --------------------------------------------------------------------------------------- */

const escapeHtml = (value) =>
  value.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;').replace(/"/g, '&quot;');

const replacements = [];

for (const field of TEXT_FIELDS) {
  const from = previous[field];
  const to = resolved[field];
  if (typeof from !== 'string' || typeof to !== 'string' || from === to) continue;

  if (from.length < MIN_REWRITABLE_LENGTH) {
    console.error(
      `[brand] refusing to rewrite "${field}": the value being replaced (${JSON.stringify(from)}) ` +
        `is under ${MIN_REWRITABLE_LENGTH} characters and would match unrelated markup.`
    );
    continue;
  }

  replacements.push({ field, from, to });
  // Astro escapes `&`, `<`, `>` and `"` when it writes a value into markup, so a Discord
  // invite or a Gitea URL carrying a query string appears in the HTML in its escaped form.
  // Adding the escaped pair rather than unescaping the document keeps this a string
  // operation on bytes, with no parser to disagree with the browser's.
  const escapedFrom = escapeHtml(from);
  if (escapedFrom !== from) replacements.push({ field, from: escapedFrom, to: escapeHtml(to) });
}

/**
 * The demo slot (§15 / D12) is a rendering decision rather than a piece of text, and this
 * is the one place a string replacement can still express it.
 *
 * The markup contract, which phase 3 writes and this script relies on:
 *
 *     <a class="demo-cta" href="" data-demo-url="">See it running</a>
 *
 * `global.css` hides `[data-demo-url='']`, so a stock build renders nothing. Setting
 * `demoUrl` in the mount turns both empty attributes into the URL, which fills the link and
 * reveals it in the same edit. Going back to an empty value reverses it, because the
 * previous value is in the record.
 */
const demoFrom = previous.demoUrl || '';
const demoTo = resolved.demoUrl || '';

if (demoFrom !== demoTo) {
  const attr = (value) => `href="${escapeHtml(value)}" data-demo-url="${escapeHtml(value)}"`;
  replacements.push({ field: 'demoUrl', from: attr(demoFrom), to: attr(demoTo) });
}

/**
 * The demo's DEEP links (§15 / D25), which `/features/` writes one of per capability that
 * has a stable public route:
 *
 *     <a class="demo-link" href="" data-demo-url="" data-demo-path="/uo/market">see it live</a>
 *
 * The slot above cannot express these. It is a literal string swap of a whole URL, so it
 * can only ever put the demo's root in an `href` — and reversing it would not even find a
 * deep link, whose `href` is the root plus a path and therefore matches no literal the
 * script knows.
 *
 * This pass is a different shape on purpose: it does not replace a previous value, it
 * RECOMPUTES both attributes from `data-demo-path`, which never changes. That makes it
 * idempotent and exactly reversible, so it runs unconditionally in the loop below rather
 * than only when the demo URL moved. `data-demo-url` is still filled with the bare root
 * because `global.css` hides `[data-demo-url='']` — the visibility rule stays one rule for
 * both kinds of link, and only the `href` differs.
 */
const DEEP_LINK = /href="[^"]*" data-demo-url="[^"]*" data-demo-path="([^"]*)"/g;

const deepLinkTo = (demoPath) => {
  const href = demoTo ? `${demoTo.replace(/\/+$/, '')}${demoPath}` : '';
  return (
    `href="${escapeHtml(href)}" data-demo-url="${escapeHtml(demoTo)}" ` +
    `data-demo-path="${demoPath}"`
  );
};

if (!replacements.length) {
  console.log('[brand] mount matches what is already applied; nothing to rewrite.');
  process.exit(0);
}

/* ---------------------------------------------------------------------------------------
   Rewrite
   --------------------------------------------------------------------------------------- */

if (!existsSync(CLIENT)) {
  console.error(`\n[brand] no build to rewrite at ${CLIENT}. Run \`npm run build\` first.\n`);
  process.exit(1);
}

function* walk(dir) {
  for (const entry of readdirSync(dir, { withFileTypes: true })) {
    const full = path.join(dir, entry.name);
    if (entry.isDirectory()) yield* walk(full);
    else if (REWRITABLE_EXTENSIONS.has(path.extname(entry.name))) yield full;
  }
}

const counts = new Map(replacements.map((r) => [r.field, 0]));
counts.set('demoDeep', 0);
let filesTouched = 0;

/**
 * The CSP (§6, D48) hashes every inline `<script>` and `<style>` in the build. This script
 * runs after that hashing and rewrites the same files, so a brand value that happened to
 * sit inside an inline block would change its bytes, invalidate its hash and get the block
 * refused by the browser — with no error anywhere except a console nobody has open. The
 * page would render perfectly and the script simply would not run.
 *
 * Nothing puts brand text in an inline script today, and the replacements are guarded by
 * MIN_REWRITABLE_LENGTH so they are unlikely to collide by accident. "Unlikely" is not the
 * standard for a failure this quiet, so the collision is checked rather than reasoned
 * about: if a rewrite ever lands inside an inline block, this refuses to write that file
 * and says so, and the page keeps its stock text instead of losing its behaviour.
 */
const INLINE_BLOCK = /<(script|style)(?![^>]*\bsrc\s*=)([^>]*)>([\s\S]*?)<\/\1>/g;

/**
 * The structured-data block (D50) is a `<script>` that no browser executes and no CSP hash
 * covers, so it is not one of the blocks this guard protects — and it MUST NOT be, because
 * it contains the site's name. Treating it as a script would make the guard refuse to
 * rewrite the homepage, which is §7 failing on the one page that matters most.
 */
const DATA_BLOCK = /type\s*=\s*["']application\/(ld\+json|json)["']/i;

const inlineRanges = (html) => {
  const ranges = [];
  INLINE_BLOCK.lastIndex = 0;
  let match;
  while ((match = INLINE_BLOCK.exec(html))) {
    if (match[1] === 'script' && DATA_BLOCK.test(match[2])) continue;
    // Where the block's CONTENT starts — measured back from the end of the whole match, so
    // the opening tag's attributes cannot throw the offset off: `</script>` is the tag name
    // plus three characters.
    const closing = match[1].length + 3;
    const start = match.index + match[0].length - closing - match[3].length;
    ranges.push([start, start + match[3].length]);
  }
  return ranges;
};
const hitsInlineBlock = (html, needle) => {
  if (!needle || !html.includes(needle)) return false;
  const ranges = inlineRanges(html);
  if (ranges.length === 0) return false;
  for (let at = html.indexOf(needle); at !== -1; at = html.indexOf(needle, at + 1)) {
    const end = at + needle.length;
    if (ranges.some(([from, to]) => at < to && end > from)) return true;
  }
  return false;
};
const inlineCollisions = [];

for (const file of walk(CLIENT)) {
  const before = readFileSync(file, 'utf8');
  let after = before;

  if (path.extname(file) === '.html') {
    const colliding = replacements.filter(({ from }) => hitsInlineBlock(before, from));
    if (colliding.length) {
      inlineCollisions.push({
        file: path.relative(CLIENT, file),
        fields: [...new Set(colliding.map((c) => c.field))],
      });
      continue;
    }
  }

  for (const { field, from, to } of replacements) {
    if (!after.includes(from)) continue;
    counts.set(field, counts.get(field) + after.split(from).length - 1);
    after = after.split(from).join(to);
  }

  // After the literal swaps, never before: the plain-slot replacement also matches the
  // first two attributes of a deep link, so it runs first and this pass corrects the
  // `href` it just wrote. Recomputing rather than replacing is what makes that safe.
  after = after.replace(DEEP_LINK, (whole, demoPath) => {
    const rebuilt = deepLinkTo(demoPath);
    if (rebuilt !== whole) counts.set('demoDeep', counts.get('demoDeep') + 1);
    return rebuilt;
  });

  if (after !== before) {
    writeFileSync(file, after);
    filesTouched++;
  }
}

writeFileSync(RECORD, `${JSON.stringify(resolved, null, 2)}\n`);

console.log(`[brand] applied the mounted brand to ${filesTouched} file(s):`);
for (const { field, from, to } of replacements) {
  if (from.startsWith('href=')) continue; // the demo pair, reported once below
  console.log(`  ${field.padEnd(14)} ${JSON.stringify(from)} -> ${JSON.stringify(to)}  (${counts.get(field)}x)`);
}
if (demoFrom !== demoTo) {
  console.log(`  ${'demoUrl'.padEnd(14)} ${demoTo ? `slot shown -> ${demoTo}` : 'slot hidden'}  (${counts.get('demoUrl')}x)`);
}
if (counts.get('demoDeep')) {
  console.log(
    `  ${'demoUrl deep'.padEnd(14)} ${demoTo ? `linked -> ${demoTo}/…` : 'links hidden'}  (${counts.get('demoDeep')}x)`
  );
}

if (inlineCollisions.length) {
  console.error(
    `\n[brand] ${inlineCollisions.length} file(s) were LEFT UNCHANGED: a brand value occurs ` +
      `inside an inline <script> or <style>, and rewriting it would break that block's CSP ` +
      `hash (§6, D48) — the page would render and the script would silently not run.\n`
  );
  for (const { file, fields } of inlineCollisions) {
    console.error(`  ! ${file}  (${fields.join(', ')})`);
  }
  console.error(
    `\n  Those pages keep the stock text. Fix it by taking the brand value out of the inline\n` +
      `  block — move it into markup the CSP does not hash, or into /brand/theme.css.\n`
  );
}

/* ---------------------------------------------------------------------------------------
   Search
   --------------------------------------------------------------------------------------- */

/**
 * Pagefind builds its index from the built HTML at BUILD time, so everything above reaches
 * the pages and none of it reaches the search results: a site renamed through the mount
 * would answer a search for its own name with the stock one, and every result title would
 * still carry the old suffix. Phase 2 recorded that and left it for this phase, when
 * search became site-wide (D47).
 *
 * The fix is to re-index, which is cheap and needs nothing the container does not already
 * have — Pagefind is what Starlight ran at build. It only runs when a rewrite actually
 * happened, so the stock deployment, which is the common case, still pays nothing.
 */
if (filesTouched > 0) {
  const pagefind = await import('pagefind');
  try {
    const { index } = await pagefind.createIndex();
    const { page_count } = await index.addDirectory({ path: CLIENT });
    await index.writeFiles({ outputPath: path.join(CLIENT, 'pagefind') });
    console.log(`[brand] re-indexed ${page_count} page(s) for search so results agree with it.`);
  } catch (error) {
    // Search degrading to stale titles is not a reason to refuse to serve the site.
    console.error(`[brand] could not rebuild the search index; it keeps the built one: ${error.message}`);
  } finally {
    await pagefind.close();
  }
}