import { KEYWORDS } from "../config.ts";
import { JUNIOR_TITLE_RE, JAVA_TITLE_RE, SOFTWARE_TITLE_RE } from "../fetch.ts";

// Supplement for Portuguese job titles not caught by SOFTWARE_TITLE_RE
const PT_SOFT_RE = /\b(desenvolvedor|engenheiro\s+de\s+software|arquiteto|analista\s+de\s+(sistemas|dados)|tech\s+lead|dados|plataforma|ia\b|inteligência\s+artificial)\b/i;

const HEADERS = {
  "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
  "Accept-Language": "en-US,en;q=0.9",
  Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
};

function clean(raw: string): string {
  return raw
    .replace(/<[^>]+>/g, "")
    .replace(/&amp;/g, "&").replace(/&lt;/g, "<").replace(/&gt;/g, ">")
    .replace(/&quot;/g, '"').replace(/&#39;/g, "'")
    .replace(/&ndash;/g, "–").replace(/&mdash;/g, "—")
    .replace(/\s+/g, " ").trim();
}

interface Job {
  id: string;
  title: string;
  company: string;
  location: string;
  postedAt: string;
  link: string;
}

function parseJobs(html: string): Job[] {
  const jobs: Job[] = [];
  const idRe = /data-entity-urn="urn:li:jobPosting:(\d+)"/g;
  const positions: { id: string; start: number }[] = [];
  let m;
  while ((m = idRe.exec(html)) !== null) positions.push({ id: m[1], start: m.index });

  for (let i = 0; i < positions.length; i++) {
    const { id, start } = positions[i];
    const card = html.slice(start, Math.min(positions[i + 1]?.start ?? Infinity, start + 3000));

    const titleM = card.match(/<h3 class="base-search-card__title">\s*([\s\S]*?)\s*<\/h3>/);
    if (!titleM) continue;

    const companyM = card.match(/<h4 class="base-search-card__subtitle">[\s\S]{0,300}?<a[^>]*>\s*([\s\S]*?)\s*<\/a>/);
    const timeM = card.match(/<time[^>]+datetime="([^"]+)"/);
    const locM = card.match(/job-search-card__location[^>]*>\s*([^<]+)/);
    const jobLocation = locM ? locM[1].trim() : "";

    // Accept Brazil locations, Remote, or empty (unknown)
    // Reject jobs clearly anchored to other countries
    const loc = jobLocation.toLowerCase();
    const isBrazil = loc.includes("brazil") || loc.includes("brasil") || loc === "" || loc.includes("remote");
    const isOtherCountry = /switzerland|germany|deutschland|united states|france|uk\b|united kingdom|netherlands|spain|italy/i.test(jobLocation);
    if (!isBrazil || isOtherCountry) continue;

    jobs.push({
      id,
      title: clean(titleM[1]),
      company: companyM ? clean(companyM[1]) : "",
      location: jobLocation || "Remote",
      postedAt: timeM ? timeM[1] : "",
      link: `https://www.linkedin.com/jobs/view/${id}/`,
    });
  }

  return jobs;
}

const PAGE_SIZE = 25;
const MAX_PAGES = 6;
const baseUrl = `https://www.linkedin.com/jobs/search/?keywords=${encodeURIComponent(KEYWORDS)}&location=Brazil&f_WT=2&f_TPR=r2592000`;

const allJobs: Job[] = [];
const seen = new Set<string>();

for (let page = 0; page < MAX_PAGES; page++) {
  if (page > 0) await Bun.sleep(500);
  const url = `${baseUrl}&start=${page * PAGE_SIZE}`;
  process.stdout.write(`  page ${page + 1} … `);

  const res = await fetch(url, { headers: HEADERS });
  if (!res.ok) { console.error(`failed (${res.status})`); break; }

  const html = await res.text();
  const jobs = parseJobs(html)
    .filter((j) => !JUNIOR_TITLE_RE.test(j.title))
    .filter((j) => !JAVA_TITLE_RE.test(j.title))
    .filter((j) => SOFTWARE_TITLE_RE.test(j.title) || PT_SOFT_RE.test(j.title));

  let newOnPage = 0;
  for (const job of jobs) {
    if (!seen.has(job.id)) { seen.add(job.id); allJobs.push(job); newOnPage++; }
  }

  console.log(`${jobs.length} found, ${newOnPage} new`);
  if (newOnPage === 0) break;
}

console.log(`\nTotal: ${allJobs.length} vagas remotas no Brasil\n`);
for (const j of allJobs) {
  console.log(`${j.title} — ${j.company} (${j.location})`);
  console.log(`  ${j.link}`);
}