#!/usr/bin/env bun
import { isEnglishContent, NON_ENGLISH_RE, JUNIOR_TITLE_RE } from "../fetch.ts";

const CSV = "./jobs.csv";
const existingLinks = new Set<string>();
try {
  const text = await Bun.file(CSV).text();
  for (const line of text.split("\n").slice(1)) {
    const url = line.match(/"(https?:\/\/[^"]+)"/)?.[1];
    if (url) existingLinks.add(url);
  }
} catch {}

const RUBY_KEYWORDS = [
  "Ruby on Rails", "Rails Engineer", "Ruby Engineer",
  "Rails Developer", "Ruby Developer",
].join(" OR ");

const searches = [
  { label: "United States Remote (Ruby)", location: "United States", workType: "2" },
];

const RUBY_RE = /\bruby\b|\brails\b/i;

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

function unescape(s: string) {
  return s.replace(/&amp;/g, "&").replace(/&lt;/g, "<").replace(/&gt;/g, ">")
    .replace(/&#39;/g, "'").replace(/&quot;/g, '"').replace(/\s+/g, " ").trim();
}

async function fetchPage(location: string, workType: string, start: number): Promise<Job[]> {
  const params = new URLSearchParams({
    keywords: RUBY_KEYWORDS,
    location,
    f_TPR: "r2592000",
    f_WT: workType,
    start: String(start),
  });
  const url = `https://www.linkedin.com/jobs/search/?${params}`;
  const res = await fetch(url, {
    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" }
  });
  const html = await res.text();

  const jobs: Job[] = [];
  const cardRe = /<div[^>]*class="[^"]*base-search-card[^"]*"[^>]*data-entity-urn="urn:li:jobPosting:(\d+)"[^>]*>([\s\S]*?)(?=<div[^>]*class="[^"]*base-search-card[^"]*"[^>]*data-entity-urn|<\/ul>)/g;
  let m;
  while ((m = cardRe.exec(html)) !== null) {
    const id = m[1];
    const chunk = m[2];
    const titleM = chunk.match(/class="[^"]*base-search-card__title[^"]*"[^>]*>\s*([\s\S]*?)\s*<\/h3>/);
    const companyM = chunk.match(/class="[^"]*base-search-card__subtitle[^"]*"[\s\S]*?<a[^>]*>\s*([\s\S]*?)\s*<\/a>/);
    const locationM = chunk.match(/class="[^"]*job-search-card__location[^"]*"[^>]*>\s*([\s\S]*?)\s*<\//);
    const postedM = chunk.match(/datetime="([^"]+)"/);

    const title = titleM ? unescape(titleM[1].replace(/<[^>]+>/g, "")) : "";
    const company = companyM ? unescape(companyM[1].replace(/<[^>]+>/g, "")) : "";
    const location = locationM ? unescape(locationM[1]) : "";
    const postedAt = postedM ? postedM[1] : "";

    if (!title || !id) continue;
    jobs.push({ id, title, company, location, link: `https://www.linkedin.com/jobs/view/${id}/`, postedAt });
  }
  return jobs;
}

const newJobs: Array<Job & { search: string }> = [];
const seenIds = new Set<string>();

for (const s of searches) {
  console.log(`\n[${s.label}]`);
  let totalFound = 0, added = 0;

  for (let page = 0; page < 4; page++) {
    const jobs = await fetchPage(s.location, s.workType, page * 25);
    if (jobs.length === 0) { console.log(`  page ${page + 1} empty, stopping`); break; }
    console.log(`  page ${page + 1} … ${jobs.length} cards`);
    totalFound += jobs.length;

    for (const job of jobs) {
      if (existingLinks.has(job.link) || seenIds.has(job.id)) continue;
      if (NON_ENGLISH_RE.test(job.title) || JUNIOR_TITLE_RE.test(job.title)) continue;
      if (!RUBY_RE.test(job.title)) continue;

      seenIds.add(job.id);
      process.stdout.write(`  checking: ${job.title} @ ${job.company} (${job.location}) … `);
      const english = await isEnglishContent(job.id);
      if (!english) { console.log("dropped (non-English)"); continue; }
      console.log("ok");
      newJobs.push({ ...job, search: s.label });
      added++;
    }
  }
  console.log(`  ${totalFound} total, ${added} new`);
}

console.log(`\n=== ${newJobs.length} Ruby remote jobs ===\n`);
for (const j of newJobs) {
  console.log(`${j.title} | ${j.company} | ${j.location} | ${j.link}`);
}