chore: sync with Gitea master and restore local-only files

Reset local main to gitea/master (new source of truth) and restored local-only files: web scrapers, admin dashboard, ChromaDB integration, debug scripts, and utility libraries that aren't tracked in Gitea. Gitea master adds: discovermass, buscarmisas-network, hk-parishes, bohosluzby, kerknet, gottesdienstzeiten, miserend importers, ClaimRequest model, forward geocoding, heartbeat healthcheck. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 19:11:22 -04:00
parent 76cca3ba75
commit 2c51513851
133 changed files with 30381 additions and 0 deletions
--- a/scripts/debug/investigate-8-bugs.ts
+++ b/scripts/debug/investigate-8-bugs.ts
@@ -0,0 +1,84 @@
+#!/usr/bin/env tsx
+/**
+ * Investigate the 8 potential parsing bugs
+ */
+
+import { GenericScraper } from '../../src/scrapers/strategies/generic';
+
+const BUGS = [
+  { name: 'Chapelle Saint-Jean-XXIII', country: 'FR', url: 'https://www.chemin-neuf.fr/' },
+  { name: 'St. Marien', country: 'DE', url: 'https://www.willehad.de/start/' },
+  { name: 'Iglesia de San Fernando', country: 'ES', url: 'https://www.parroquiasanfernandomaspalomas.net/de/' },
+  { name: 'Monestir de Sant Esperit', country: 'ES', url: 'https://www.santoespiritu.org/' },
+  { name: 'Santuario de Manalagua', country: 'ES', url: 'http://tierrasdeburgos.blogspot.com.es/2013/12/escultura-del-agua-santuario-de.html' },
+  { name: 'Kościół pw. Najświętszego Serca', country: 'PL', url: 'http://parafialubojna.pl' },
+  { name: 'Paróquia do Desterro', country: 'BR', url: 'https://paroquiaportodegalinhas.blogspot.com.br/' },
+  { name: 'Catedral Diocesana', country: 'BR', url: 'http://diocesedejuazeiro.org.br/' },
+];
+
+async function investigate() {
+  console.log('Investigating 8 potential bugs...\n');
+
+  const scraper = new GenericScraper();
+  await scraper.init();
+
+  for (let i = 0; i < BUGS.length; i++) {
+    const bug = BUGS[i];
+    console.log(`${'='.repeat(80)}`);
+    console.log(`${i + 1}. ${bug.name} (${bug.country})`);
+    console.log(`   ${bug.url}`);
+    console.log('='.repeat(80));
+
+    scraper.setCountry(bug.country);
+
+    try {
+      const result = await scraper.scrape(bug.url);
+
+      console.log(`Success: ${result.success}`);
+      console.log(`Schedules: ${result.schedules.length}`);
+      console.log(`Error: ${result.error || 'none'}`);
+
+      if (!result.success && result.rawHtml) {
+        const text = result.rawHtml
+          .replace(/<script[^>]*>[\s\S]*?<\/script>/gi, '')
+          .replace(/<style[^>]*>[\s\S]*?<\/style>/gi, '')
+          .replace(/<[^>]+>/g, ' ')
+          .replace(/\s+/g, ' ')
+          .toLowerCase();
+
+        // Check page type
+        console.log('\nPage analysis:');
+        if (text.includes('blogspot')) {
+          console.log('  ⚠️  Blogspot page (likely blog post, not church website)');
+        }
+        if (text.includes('hotel') || text.includes('reservation') || text.includes('booking')) {
+          console.log('  ⚠️  Contains hotel/booking keywords');
+        }
+        if (text.includes('restaurant') || text.includes('menu')) {
+          console.log('  ⚠️  Contains restaurant keywords');
+        }
+        if (text.includes('404') || text.includes('not found') || text.includes('error')) {
+          console.log('  ⚠️  Error/404 page');
+        }
+
+        // Check if it has schedule keywords
+        const hasScheduleKeywords = text.match(/(mass|messe|misa|missa|horário|horario|gottesdienst|eucarist)/i);
+        console.log(`  Schedule keywords: ${hasScheduleKeywords ? '✓ Found' : '✗ Not found'}`);
+
+        // Show sample text
+        const massIndex = text.indexOf('mass') || text.indexOf('messe') || text.indexOf('misa') || text.indexOf('missa') || 0;
+        const sampleStart = Math.max(0, massIndex - 50);
+        const sample = text.substring(sampleStart, sampleStart + 300);
+        console.log(`\n  Sample text: "${sample.substring(0, 200)}..."`);
+      }
+
+      console.log('\n');
+    } catch (err: any) {
+      console.log(`ERROR: ${err.message}\n\n`);
+    }
+  }
+
+  await scraper.close();
+}
+
+investigate().catch(console.error);