spsays-training/scripts/seed-journals.ts

/**
 * seed-journals.ts — Push Journals into MongoDB.
 *
 * Collections written:
 *   - journal_meta      → one doc per journal
 *   - journal_chapters  → N chapter docs per journal
 *
 * Usage:
 *   npx tsx scripts/seed-journals.ts
 */

import dotenv from "dotenv";
import fs from "fs";
import path from "path";
import { MongoClient } from "mongodb";

dotenv.config({ path: ".env.local" });
dotenv.config({ path: ".env" });

const DATABASE_URL = process.env.DATABASE_URL;
if (!DATABASE_URL) {
  console.error("❌ DATABASE_URL is not set");
  process.exit(1);
}

const BASE_DIR = path.resolve(__dirname, "..");
const JOURNALS_DIR = path.join(BASE_DIR, "lib", "jsons", "journals");

type IntroJson = {
  book: string;
  title: string;
  author: string;
  year: number | null;
  description: string | null;
  totalChapters: number;
  chapters: unknown[];
};
type ChapterJson = {
  book: string;
  chapter: number;
  title: string;
  type: string;
  slug?: string;
  paragraphs: string[];
};

function readJson<T>(filePath: string): T {
  return JSON.parse(fs.readFileSync(filePath, "utf-8"));
}

function sanitizeDoc(obj: unknown): unknown {
  if (typeof obj === "string") {
    let s = obj.normalize("NFC");
    s = s.replace(/[\x00-\x08\x0b\x0c\x0e-\x1f]/g, "");
    s = s.replace(/[\uD800-\uDFFF]/g, "");
    s = s.replace(/[\u200B-\u200F\u2028-\u202F\uFEFF]/g, "");
    s = Buffer.from(s, "utf-8").toString("utf-8");
    return s;
  }
  if (Array.isArray(obj)) return obj.map(sanitizeDoc);
  if (obj !== null && typeof obj === "object") {
    const result: Record<string, unknown> = {};
    for (const [key, value] of Object.entries(obj as Record<string, unknown>))
      result[key] = sanitizeDoc(value);
    return result;
  }
  return obj;
}

async function seedOneJournal(
  db: ReturnType<MongoClient["db"]>,
  docDir: string,
): Promise<{ bookCode: string; chapters: number }> {
  const introPath = path.join(docDir, "intro.json");
  if (!fs.existsSync(introPath)) throw new Error(`No intro.json in ${docDir}`);
  const intro = sanitizeDoc(readJson<IntroJson>(introPath)) as IntroJson;
  const bookCode = intro.book;

  const metaCol = db.collection("journal_meta");
  await metaCol.deleteMany({ book: bookCode });
  await metaCol.insertOne({ book: bookCode, data: intro });
  console.log(`  📖 Inserted journal_meta for "${intro.title}" (${bookCode})`);

  const chaptersCol = db.collection("journal_chapters");
  await chaptersCol.deleteMany({ book: bookCode });

  const chaptersDir = path.join(docDir, "chapters");
  let inserted = 0;
  if (fs.existsSync(chaptersDir)) {
    const files = fs
      .readdirSync(chaptersDir)
      .filter((f) => f.endsWith(".json"))
      .sort();
    for (const file of files) {
      const ch = sanitizeDoc(
        readJson<ChapterJson>(path.join(chaptersDir, file)),
      ) as ChapterJson;
      const chNum = ch.chapter ?? parseInt(file.replace(".json", ""), 10);
      const slug = ch.slug ?? String(chNum);
      await chaptersCol.insertOne({
        book: bookCode,
        chapter: chNum,
        title: ch.title,
        type: ch.type || "chapter",
        slug,
        order: 100 + chNum,
        paragraphs: ch.paragraphs,
      });
      inserted++;
    }
    console.log(`  📄 Chapters: ${inserted}`);
  }

  const total = await chaptersCol.countDocuments({ book: bookCode });
  console.log(`  ✅ ${bookCode}: ${total} chapter entries`);
  return { bookCode, chapters: inserted };
}

async function main() {
  console.log("🌱 Seeding Journals...\n");
  const client = new MongoClient(DATABASE_URL!);
  await client.connect();
  console.log("📡 Connected to MongoDB\n");
  const db = client.db();
  const start = Date.now();

  if (!fs.existsSync(JOURNALS_DIR)) {
    console.error(`❌ ${JOURNALS_DIR} not found`);
    process.exit(1);
  }

  const subdirs = fs
    .readdirSync(JOURNALS_DIR)
    .filter((e) => {
      const p = path.join(JOURNALS_DIR, e);
      return (
        fs.statSync(p).isDirectory() &&
        fs.existsSync(path.join(p, "intro.json"))
      );
    })
    .sort();

  if (subdirs.length === 0) {
    console.error("❌ No journal directories found");
    process.exit(1);
  }
  console.log(`📂 Found ${subdirs.length} journal(s)\n`);

  let totalChapters = 0;
  const bookCodes: string[] = [];
  for (const subdir of subdirs) {
    console.log(`\n📝 Processing: ${subdir}`);
    const result = await seedOneJournal(db, path.join(JOURNALS_DIR, subdir));
    bookCodes.push(result.bookCode);
    totalChapters += result.chapters;
  }

  const elapsed = ((Date.now() - start) / 1000).toFixed(1);
  console.log("\n" + "─".repeat(50));
  console.log(
    `📊 Summary: ${subdirs.length} journals, ${totalChapters} chapters`,
  );
  console.log(`   Book codes: ${bookCodes.join(", ")}`);
  console.log(`\n🎉 Done in ${elapsed}s`);
  await client.close();
}

main().catch((err) => {
  console.error("❌ Seed failed:", err);
  process.exit(1);
});