archicratie-edition/scripts/build-para-index.mjs

// scripts/build-para-index.mjs
import fs from "node:fs/promises";
import path from "node:path";

function parseArgs(argv) {
  const out = { inDir: "dist", outFile: "dist/para-index.json" };

  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];

    if (a === "--in" && argv[i + 1]) {
      out.inDir = argv[++i];
      continue;
    }
    if (a.startsWith("--in=")) {
      out.inDir = a.slice("--in=".length);
      continue;
    }

    if (a === "--out" && argv[i + 1]) {
      out.outFile = argv[++i];
      continue;
    }
    if (a.startsWith("--out=")) {
      out.outFile = a.slice("--out=".length);
      continue;
    }
  }

  return out;
}

async function exists(p) {
  try {
    await fs.access(p);
    return true;
  } catch {
    return false;
  }
}

async function walk(dir) {
  const out = [];
  const ents = await fs.readdir(dir, { withFileTypes: true });
  for (const e of ents) {
    const p = path.join(dir, e.name);
    if (e.isDirectory()) out.push(...(await walk(p)));
    else out.push(p);
  }
  return out;
}

function stripTags(html) {
  return String(html || "")
    .replace(/<script\b[\s\S]*?<\/script>/gi, " ")
    .replace(/<style\b[\s\S]*?<\/style>/gi, " ")
    .replace(/<[^>]+>/g, " ");
}

function decodeEntities(s) {
  // minimal, volontairement (évite dépendances)
  return String(s || "")
    .replace(/&nbsp;/g, " ")
    .replace(/&amp;/g, "&")
    .replace(/&lt;/g, "<")
    .replace(/&gt;/g, ">")
    .replace(/&quot;/g, '"')
    .replace(/&#39;/g, "'");
}

function normalizeSpaces(s) {
  return decodeEntities(s).replace(/\s+/g, " ").trim();
}

function relPageFromIndexHtml(inDirAbs, fileAbs) {
  const rel = path.relative(inDirAbs, fileAbs).replace(/\\/g, "/");
  if (!/index\.html$/i.test(rel)) return null;

  // dist/<page>/index.html -> "/<page>/"
  const page = "/" + rel.replace(/index\.html$/i, "");
  return page;
}

async function main() {
  const { inDir, outFile } = parseArgs(process.argv.slice(2));
  const CWD = process.cwd();

  const inDirAbs = path.isAbsolute(inDir) ? inDir : path.join(CWD, inDir);
  const outAbs = path.isAbsolute(outFile) ? outFile : path.join(CWD, outFile);

  // ✅ antifragile: si dist/ (ou inDir) absent -> on SKIP proprement
  if (!(await exists(inDirAbs))) {
    console.log(`ℹ️  para-index: skip (input missing): ${inDir}`);
    process.exit(0);
  }

  const files = (await walk(inDirAbs)).filter((p) => /index\.html$/i.test(p));

  if (!files.length) {
    console.log(`ℹ️  para-index: skip (no index.html found in): ${inDir}`);
    process.exit(0);
  }

  const items = [];
  const byId = Object.create(null);

  // <p ... id="p-...">...</p>
  // (regex volontairement stricte sur l'id pour éviter faux positifs)
  const reP = /<p\b([^>]*\bid\s*=\s*["'](p-\d+-[^"']+)["'][^>]*)>([\s\S]*?)<\/p>/gi;

  for (const f of files) {
    const page = relPageFromIndexHtml(inDirAbs, f);
    if (!page) continue;

    const html = await fs.readFile(f, "utf8");

    let m;
    while ((m = reP.exec(html))) {
      const id = m[2];
      const inner = m[3];

      if (byId[id] != null) continue; // protège si jamais doublons

      const text = normalizeSpaces(stripTags(inner));
      if (!text) continue;

      byId[id] = items.length;
      items.push({ id, page, text });
    }
  }

  const out = {
    schema: 1,
    generatedAt: new Date().toISOString(),
    items,
    byId,
  };

  await fs.mkdir(path.dirname(outAbs), { recursive: true });
  await fs.writeFile(outAbs, JSON.stringify(out), "utf8");

  console.log(`✅ para-index: items=${items.length} -> ${path.relative(CWD, outAbs)}`);
}

main().catch((e) => {
  console.error("FAIL: build-para-index crashed:", e);
  process.exit(1);
});