ScraperControl/scripts/import-hk-parishes.ts

#!/usr/bin/env tsx
/**
 * Import HK Diocese parish directory from plain-text paste.
 * Usage: npx tsx scripts/import-hk-parishes.ts [--dry-run] [--file scripts/hk-parishes.txt]
 */

import dotenv from 'dotenv';
import path from 'path';
import fs from 'fs';

dotenv.config({ path: path.resolve(process.cwd(), '.env.local') });
dotenv.config({ path: path.resolve(process.cwd(), '.env') });

import { Pool } from 'pg';
import { PrismaPg } from '@prisma/adapter-pg';
import { PrismaClient } from '@prisma/client';

const dbUrl = process.env.DATABASE_URL || 'postgresql://postgres:postgres@localhost:5432/nearestmass';
console.log(`Connecting to database: ${dbUrl.replace(/:[^:@]+@/, ':***@')}`);
const pool = new Pool({
  connectionString: dbUrl,
  ssl: dbUrl.includes('neon') ? { rejectUnauthorized: false } : undefined,
});
const adapter = new PrismaPg(pool);
const prisma = new PrismaClient({ adapter });

// ─── Types ────────────────────────────────────────────────────────────────────

export interface ParsedSchedule {
  dayOfWeek: number;   // 0=Sun, 1=Mon, ..., 6=Sat
  time: string;        // "HH:MM"
  language: string;    // "English" | "Cantonese" | "Tagalog"
  notes: string | null;
}

export interface ParsedEntry {
  locationName: string;
  parishName: string | null;
  address: string | null;
  phone: string | null;
  email: string | null;
  schedules: ParsedSchedule[];
}

interface ExistingChurch {
  id: string;
  name: string;
  address: string | null;
  phone: string | null;
  email: string | null;
}

interface ImportStats {
  matched: number;
  created: number;
  schedulesWritten: number;
  skipped: number;
}