import db, { initDB } from './src/crawler/db';
import { fetchPage } from './src/crawler/fetcher';
import { extractAndNormalize } from './src/crawler/extractor';
import { sliceAndDiff } from './src/crawler/differ';

async function test() {
  initDB();

  const source_id = 'test_source';
  const job_id = 'test_job';

  db.prepare(`
    INSERT OR IGNORE INTO source_registry (
      source_id, source_name, source_type, domain, entry_url, url_pattern,
      parser_type, crawl_frequency, priority, enabled, topic_tags
    ) VALUES (
      ?, '测试官网', 'peer_bank', 'httpbin.org', 'http://httpbin.org/html', '',
      'html_main_content', 'daily', 'high', 1, '[]'
    )
  `).run(source_id);

  db.prepare(`
    INSERT OR IGNORE INTO crawl_job (
      job_id, source_id, trigger_type, status, started_at
    ) VALUES (
      ?, ?, 'manual', 'queued', ?
    )
  `).run(job_id, source_id, new Date().toISOString());

  console.log('Fetching...');
  const snapshot = await fetchPage(job_id, source_id);
  console.log('Fetched snapshot:', snapshot.snapshot_id);

  console.log('Extracting...');
  const doc = extractAndNormalize(snapshot);
  if (doc) {
    console.log('Normalized document:', doc.doc_id);
    console.log('Diffing...');
    sliceAndDiff(doc);
    console.log('Diff done.');
  } else {
    console.log('No new version.');
  }

  // print stats
  const chunks = db.prepare('SELECT count(*) as c FROM clause_chunk').get() as any;
  const events = db.prepare('SELECT count(*) as c FROM diff_event').get() as any;
  console.log('Chunks:', chunks.c);
  console.log('Events:', events.c);
}

test().catch(console.error);