ScraperControl/scripts/dedup-mass-schedules.ts

#!/usr/bin/env tsx
import dotenv from 'dotenv';
import path from 'path';
dotenv.config({ path: path.resolve(process.cwd(), '.env.local') });
import { Pool } from 'pg';
import { PrismaPg } from '@prisma/adapter-pg';
import { PrismaClient } from '@prisma/client';

const pool = new Pool({ connectionString: process.env.DATABASE_URL });
const adapter = new PrismaPg(pool);
const prisma = new PrismaClient({ adapter });

async function main() {
  const dryRun = !process.argv.includes('--execute');

  if (dryRun) {
    console.log('DRY RUN - pass --execute to actually delete duplicates\n');
  }

  const churches = await prisma.church.findMany({
    where: { massSchedules: { some: { isActive: true } } },
    include: { massSchedules: { where: { isActive: true }, orderBy: { createdAt: 'asc' } } },
  });

  let churchesFixed = 0;
  let rowsDeleted = 0;

  for (const church of churches) {
    const seen = new Map<string, string>();
    const toDelete: string[] = [];

    for (const m of church.massSchedules) {
      const key = `${m.dayOfWeek}:${m.time}:${m.language}`;
      if (seen.has(key)) {
        toDelete.push(m.id);
      } else {
        seen.set(key, m.id);
      }
    }

    if (toDelete.length > 0) {
      churchesFixed++;
      rowsDeleted += toDelete.length;

      if (!dryRun) {
        await prisma.massSchedule.deleteMany({
          where: { id: { in: toDelete } },
        });
      }
    }
  }

  console.log(`Churches with duplicates: ${churchesFixed}`);
  console.log(`Duplicate rows ${dryRun ? 'found' : 'deleted'}: ${rowsDeleted}`);

  await prisma.$disconnect();
  await pool.end();
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});