feat: add discovermassId to church-matcher ExistingChurch and ChurchCandidate

Add discovermassId field to ExistingChurch interface and ChurchCandidate type,
insert a dedicated matching pass in findDuplicateChurch, and update all 15 importer
push blocks plus 16 loadExistingChurches select queries to include the new field.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
albertfj114
2026-03-11 06:52:05 -04:00
parent 2706708c51
commit a046928ed0
17 changed files with 11576 additions and 0 deletions

View File

@@ -0,0 +1,641 @@
#!/usr/bin/env tsx
/**
* Import Catholic churches and mass schedules from bohosluzby.cz (Czech Republic)
*
* bohosluzby.cz is the official Czech bishops' conference mass schedule finder.
* It exposes a JSON API with two main endpoints:
* - POST /index.php/apiWeb/allData — returns all churches (clustered by zoom level)
* - GET /index.php/apiWeb/detailById?id={id} — returns mass schedule details
*
* The API requires no authentication. We fetch all churches at zoom=7 (covers
* all of Czech Republic in one request with clustered results), then fetch
* individual detail pages for mass schedules.
*
* Import strategy:
* 1. Fetch all churches via allData endpoint (zoom=7, centered on Czech Republic)
* 2. Flatten clustered results to get individual church records
* 3. For each church, fetch detail to get mass schedules
* 4. Match against existing Czech churches via church-matcher
* 5. Upsert churches and mass schedules
*
* Usage:
* npx tsx scripts/import-bohosluzby.ts --all --dry-run
* npx tsx scripts/import-bohosluzby.ts --all
* npx tsx scripts/import-bohosluzby.ts --id 10009 --dry-run # Single church
* npx tsx scripts/import-bohosluzby.ts --all --resume-from 500
*/
import dotenv from 'dotenv';
import path from 'path';
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 });
import { findDuplicateChurch } from '../src/lib/church-matcher';
import type { ExistingChurch } from '../src/lib/church-matcher';
// ─── Constants ───────────────────────────────────────────────────────────────
const BASE_URL = 'https://bohosluzby.cirkev.cz';
const USER_AGENT = 'NearestMass-Importer/1.0 (parish data aggregator; contact: privacy@nearestmass.com)';
const REQUEST_DELAY_MS = 500; // Be polite — 0.5s between detail requests
const RETRY_DELAY_MS = 5000;
const MAX_RETRIES = 3;
// Czech Republic center coordinates for the allData request
const CZ_CENTER_LAT = 49.8;
const CZ_CENTER_LNG = 15.5;
const CZ_ZOOM = 7; // Returns all churches clustered into ~7 groups
// ─── Types ───────────────────────────────────────────────────────────────────
interface BohosluzbyChurch {
id: string;
name: string;
street: string | null;
city: string | null;
psc: string | null; // zip code
latitude: number;
longitude: number;
type: string; // KOSTEL, KAPLE, etc.
}
interface BohosluzbySchedule {
dayOfWeek: number; // 0=Sunday, 1=Monday, ...
time: string; // HH:MM
language: string;
type: string; // "mše sv.", "růženec", etc.
note: string | null;
}
interface ImportStats {
churchesFetched: number;
detailsFetched: number;
churchesMatched: number;
churchesCreated: number;
churchesSkipped: number;
schedulesCreated: number;
errors: number;
}
interface CLIArgs {
all: boolean;
dryRun: boolean;
resumeFrom?: number;
churchId?: string;
jobId?: string;
}
// ─── HTTP Client ─────────────────────────────────────────────────────────────
let requestCount = 0;
function delay(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
async function fetchWithRetry(url: string, options: RequestInit = {}): Promise<any | null> {
if (requestCount > 0) {
await delay(REQUEST_DELAY_MS);
}
requestCount++;
for (let attempt = 1; attempt <= MAX_RETRIES; attempt++) {
try {
const response = await fetch(url, {
...options,
headers: {
'User-Agent': USER_AGENT,
...options.headers,
},
});
if (response.status === 503 || response.status === 429) {
if (attempt < MAX_RETRIES) {
console.log(` HTTP ${response.status} — retrying in ${RETRY_DELAY_MS / 1000}s (attempt ${attempt}/${MAX_RETRIES})`);
await delay(RETRY_DELAY_MS);
continue;
}
console.error(` HTTP ${response.status} after ${MAX_RETRIES} attempts`);
return null;
}
if (!response.ok) {
console.error(` HTTP ${response.status} from ${url}`);
return null;
}
return await response.json();
} catch (error) {
if (attempt < MAX_RETRIES) {
console.log(` Network error — retrying in ${RETRY_DELAY_MS / 1000}s (attempt ${attempt}/${MAX_RETRIES})`);
await delay(RETRY_DELAY_MS);
continue;
}
console.error(` API error after ${MAX_RETRIES} attempts: ${error instanceof Error ? error.message : error}`);
return null;
}
}
return null;
}
// ─── API Methods ─────────────────────────────────────────────────────────────
/**
* Fetch all churches from the allData endpoint.
* Returns clustered results at zoom=7 — we flatten the clusters to get
* individual church records with id, name, lat, lng, city, street.
*/
async function fetchAllChurches(): Promise<BohosluzbyChurch[]> {
console.log('Fetching all churches from allData endpoint...');
const params = new URLSearchParams();
params.append('institutionTypes', "'KOSTEL'");
params.append('latitude', String(CZ_CENTER_LAT));
params.append('longitude', String(CZ_CENTER_LNG));
params.append('zoom', String(CZ_ZOOM));
const data = await fetchWithRetry(`${BASE_URL}/index.php/apiWeb/allData`, {
method: 'POST',
body: params,
headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
});
if (!data) {
console.error('Failed to fetch allData');
return [];
}
const churches: BohosluzbyChurch[] = [];
const kostelData = data["'KOSTEL'"] || [];
for (const cluster of kostelData) {
// Add the cluster representative
churches.push({
id: cluster.id,
name: cluster.name,
street: cluster.street || null,
city: cluster.city || null,
psc: cluster.psc || null,
latitude: parseFloat(cluster.latitude),
longitude: parseFloat(cluster.longitude),
type: cluster.type || 'KOSTEL',
});
// Add churches from the indices array (sub-items in the cluster)
if (Array.isArray(cluster.indices)) {
for (const sub of cluster.indices) {
churches.push({
id: sub.id,
name: sub.name,
street: sub.street || null,
city: sub.city || null,
psc: sub.psc || null,
latitude: parseFloat(sub.latitude),
longitude: parseFloat(sub.longitude),
type: sub.type || 'KOSTEL',
});
}
}
}
console.log(`Fetched ${churches.length} churches from allData`);
return churches;
}
/**
* Fetch mass schedule details for a single church.
* Returns parsed regular mass schedules.
*/
async function fetchChurchDetail(churchId: string): Promise<BohosluzbySchedule[]> {
const data = await fetchWithRetry(`${BASE_URL}/index.php/apiWeb/detailById?id=${churchId}`);
if (!data || !data.church) return [];
const schedules: BohosluzbySchedule[] = [];
const regular = data.church.regular || [];
for (const entry of regular) {
// Only import "mše sv." (Holy Mass) entries
if (entry.chst_name && !entry.chst_name.includes('mše')) continue;
const time = entry.cas; // Already in HH:MM format
if (!time) continue;
// Parse periodic_days: "12345" = Mon-Fri, "6" = Sat, "7" = Sun
// Convert to our dayOfWeek: 0=Sun, 1=Mon, ..., 6=Sat
const periodicDays = entry.periodic_days || '';
for (const dayChar of periodicDays) {
const bohosluzbyDay = parseInt(dayChar);
if (isNaN(bohosluzbyDay)) continue;
// bohosluzby: 1=Mon, 2=Tue, ..., 6=Sat, 7=Sun
// Our format: 0=Sun, 1=Mon, ..., 6=Sat
const dayOfWeek = bohosluzbyDay === 7 ? 0 : bohosluzbyDay;
const key = `${dayOfWeek}:${time}`;
// Deduplicate within this church
if (!schedules.some(s => `${s.dayOfWeek}:${s.time}` === key)) {
schedules.push({
dayOfWeek,
time,
language: entry.chsl_name || 'česky',
type: entry.chst_name || 'mše sv.',
note: entry.note || null,
});
}
}
}
return schedules;
}
// ─── Database Operations ─────────────────────────────────────────────────────
async function loadExistingCzechChurches(): Promise<ExistingChurch[]> {
console.log('Loading existing Czech churches for deduplication...');
const churches = await prisma.church.findMany({
where: { country: 'CZ' },
select: {
id: true,
name: true,
latitude: true,
longitude: true,
osmId: true,
baiduId: true,
masstimesId: true,
orarimesseId: true,
massSchedulesPhId: true,
philmassId: true,
horariosMisasId: true,
mszeInfoId: true,
weekdayMassesId: true,
messesInfoId: true,
bohosluzbyId: true,
miserendId: true,
kerknetId: true,
gottesdienstzeitenId: true,
discovermassId: true,
source: true,
website: true,
phone: true,
address: true,
},
});
console.log(`Loaded ${churches.length} existing Czech churches`);
return churches;
}
// ─── Import Logic ────────────────────────────────────────────────────────────
async function processChurch(
church: BohosluzbyChurch,
existingChurches: ExistingChurch[],
dryRun: boolean,
stats: ImportStats,
): Promise<void> {
if (church.latitude === 0 && church.longitude === 0) {
stats.churchesSkipped++;
return;
}
// Fetch mass schedules
let schedules: BohosluzbySchedule[] = [];
if (!dryRun) {
schedules = await fetchChurchDetail(church.id);
stats.detailsFetched++;
}
const candidate = {
name: church.name,
lat: church.latitude,
lng: church.longitude,
bohosluzbyId: church.id,
};
const duplicate = findDuplicateChurch(candidate, existingChurches);
if (dryRun) {
if (duplicate) {
stats.churchesMatched++;
} else {
stats.churchesCreated++;
}
return;
}
if (duplicate) {
stats.churchesMatched++;
const updateData: Record<string, unknown> = { bohosluzbyId: church.id };
if (!duplicate.address && church.street) updateData.address = church.street;
try {
await prisma.church.update({
where: { id: duplicate.id },
data: updateData,
});
} catch (error) {
if (error instanceof Error && error.message.includes('Unique constraint')) {
stats.churchesSkipped++;
return;
}
throw error;
}
if (schedules.length > 0) {
try {
await prisma.$transaction(async (tx) => {
await tx.massSchedule.deleteMany({ where: { churchId: duplicate.id } });
await tx.massSchedule.createMany({
data: schedules.map((s) => ({
churchId: duplicate.id,
dayOfWeek: s.dayOfWeek,
time: s.time,
language: 'Czech',
})),
});
await tx.church.update({
where: { id: duplicate.id },
data: { lastScrapedAt: new Date() },
});
});
stats.schedulesCreated += schedules.length;
} catch (error) {
stats.errors++;
console.error(` Error saving schedules for ${church.id}: ${error instanceof Error ? error.message : error}`);
}
}
} else {
try {
const newChurch = await prisma.church.create({
data: {
name: church.name,
latitude: church.latitude,
longitude: church.longitude,
address: church.street,
zip: church.psc,
city: church.city,
country: 'CZ',
bohosluzbyId: church.id,
source: 'bohosluzby',
websiteLanguage: 'cs',
},
});
stats.churchesCreated++;
existingChurches.push({
id: newChurch.id,
name: church.name,
latitude: church.latitude,
longitude: church.longitude,
osmId: null,
baiduId: null,
masstimesId: null,
orarimesseId: null,
massSchedulesPhId: null,
philmassId: null,
horariosMisasId: null,
mszeInfoId: null,
weekdayMassesId: null,
messesInfoId: null,
bohosluzbyId: church.id,
miserendId: null,
kerknetId: null,
gottesdienstzeitenId: null,
discovermassId: null,
source: 'bohosluzby',
website: null,
phone: null,
address: church.street,
});
if (schedules.length > 0) {
await prisma.massSchedule.createMany({
data: schedules.map((s) => ({
churchId: newChurch.id,
dayOfWeek: s.dayOfWeek,
time: s.time,
language: 'Czech',
})),
});
await prisma.church.update({
where: { id: newChurch.id },
data: { lastScrapedAt: new Date() },
});
stats.schedulesCreated += schedules.length;
}
} catch (error) {
if (error instanceof Error && error.message.includes('Unique constraint')) {
stats.churchesSkipped++;
return;
}
stats.errors++;
console.error(` Error creating ${church.id}: ${error instanceof Error ? error.message : error}`);
}
}
}
// ─── CLI ─────────────────────────────────────────────────────────────────────
function parseArgs(): CLIArgs {
const args = process.argv.slice(2);
const result: CLIArgs = { all: false, dryRun: false };
for (let i = 0; i < args.length; i++) {
switch (args[i]) {
case '--all':
result.all = true;
break;
case '--dry-run':
result.dryRun = true;
break;
case '--resume-from':
result.resumeFrom = parseInt(args[++i]);
break;
case '--id':
result.churchId = args[++i];
break;
case '--job-id':
result.jobId = args[++i];
break;
case '--help':
case '-h':
console.log(`
Usage: npx tsx scripts/import-bohosluzby.ts [options]
Options:
--all Import all churches
--id <id> Import a single church by bohosluzby ID
--dry-run No database writes, just report what would happen
--resume-from <n> Skip first N churches
--job-id <uuid> Background job tracking ID
--help, -h Show this help message
Examples:
npx tsx scripts/import-bohosluzby.ts --id 10009 --dry-run
npx tsx scripts/import-bohosluzby.ts --all --dry-run
npx tsx scripts/import-bohosluzby.ts --all
`);
process.exit(0);
}
}
if (!result.all && !result.churchId) {
console.error('Error: specify --all or --id <bohosluzby_id>');
process.exit(1);
}
return result;
}
function formatDuration(ms: number): string {
const seconds = Math.floor(ms / 1000);
const minutes = Math.floor(seconds / 60);
const hours = Math.floor(minutes / 60);
if (hours > 0) return `${hours}h ${minutes % 60}m ${seconds % 60}s`;
if (minutes > 0) return `${minutes}m ${seconds % 60}s`;
return `${seconds}s`;
}
// ─── Main ────────────────────────────────────────────────────────────────────
async function main() {
const args = parseArgs();
const startTime = Date.now();
console.log('\n' + '='.repeat(70));
console.log('BOHOSLUZBY.CZ (CZECH REPUBLIC) IMPORTER');
console.log('='.repeat(70));
console.log(`Mode: ${args.churchId ? `Church ID ${args.churchId}` : 'All churches'}`);
console.log(`Dry run: ${args.dryRun ? 'YES (no DB writes)' : 'NO'}`);
if (args.resumeFrom) console.log(`Resume from: church index ${args.resumeFrom}`);
console.log(`Time: ${new Date().toISOString()}`);
console.log('='.repeat(70) + '\n');
if (args.jobId) {
try {
await prisma.backgroundJob.update({
where: { id: args.jobId },
data: { status: 'running', startedAt: new Date() },
});
} catch { /* Job might not exist */ }
}
const stats: ImportStats = {
churchesFetched: 0,
detailsFetched: 0,
churchesMatched: 0,
churchesCreated: 0,
churchesSkipped: 0,
schedulesCreated: 0,
errors: 0,
};
const existingChurches = await loadExistingCzechChurches();
let churches: BohosluzbyChurch[];
if (args.churchId) {
// Single church mode — create a minimal record and fetch detail
churches = [{
id: args.churchId,
name: `Church ${args.churchId}`,
street: null,
city: null,
psc: null,
latitude: 0,
longitude: 0,
type: 'KOSTEL',
}];
// Fetch detail to get actual data
const detail = await fetchWithRetry(`${BASE_URL}/index.php/apiWeb/detailById?id=${args.churchId}`);
if (detail?.church?.institution?.[0]) {
const inst = detail.church.institution[0];
churches[0].name = inst.name || churches[0].name;
churches[0].street = inst.street || null;
churches[0].city = inst.city || null;
churches[0].latitude = parseFloat(inst.latitude) || 0;
churches[0].longitude = parseFloat(inst.longitude) || 0;
}
} else {
churches = await fetchAllChurches();
}
stats.churchesFetched = churches.length;
if (args.resumeFrom) {
churches = churches.slice(args.resumeFrom);
console.log(`Resuming from index ${args.resumeFrom} (${churches.length} remaining)\n`);
}
console.log(`Processing ${churches.length} churches\n`);
for (let i = 0; i < churches.length; i++) {
const church = churches[i];
if (i % 100 === 0) {
const elapsed = formatDuration(Date.now() - startTime);
console.log(`[${i + 1}/${churches.length}] Processing ${church.name} (${church.id}) [${elapsed} elapsed]`);
}
try {
await processChurch(church, existingChurches, args.dryRun, stats);
} catch (error) {
stats.errors++;
console.error(` ERROR processing church ${church.id}: ${error instanceof Error ? error.message : error}`);
}
}
const totalTime = Date.now() - startTime;
console.log('\n' + '='.repeat(70));
console.log(`IMPORT SUMMARY ${args.dryRun ? '(DRY RUN)' : ''}`);
console.log('='.repeat(70));
console.log(`Churches fetched: ${stats.churchesFetched}`);
console.log(`Details fetched: ${stats.detailsFetched}`);
console.log(` Matched (existing): ${stats.churchesMatched}`);
console.log(` Created (new): ${stats.churchesCreated}`);
console.log(` Skipped: ${stats.churchesSkipped}`);
console.log(`Schedules created: ${stats.schedulesCreated}`);
console.log(`Errors: ${stats.errors}`);
console.log(`Total time: ${formatDuration(totalTime)}`);
console.log(`HTTP requests: ${requestCount}`);
console.log('='.repeat(70) + '\n');
if (args.jobId) {
try {
await prisma.backgroundJob.update({
where: { id: args.jobId },
data: {
status: stats.errors > 0 ? 'completed_with_errors' : 'completed',
completedAt: new Date(),
processed: stats.churchesFetched,
succeeded: stats.churchesCreated + stats.churchesMatched,
failed: stats.errors,
itemsFound: stats.schedulesCreated,
},
});
} catch { /* Ignore */ }
}
}
main()
.catch((error) => {
console.error('Fatal error:', error);
process.exit(1);
})
.finally(async () => {
await prisma.$disconnect();
await pool.end();
});