#!/usr/bin/env bun
import { KEYWORDS } from "../config.ts";
import { fetchJobs, isEnglishContent } from "../fetch.ts";
import type { SearchConfig } from "../config.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 searches: SearchConfig[] = [
  { label: "Zürich city", keywords: KEYWORDS, geoId: "102436504", workType: ["onsite", "hybrid"], timePosted: "month" },
  { label: "Zürich Metro", keywords: KEYWORDS, geoId: "107814425", workType: ["onsite", "hybrid"], timePosted: "month" },
  { label: "Zürich Area", keywords: KEYWORDS, geoId: "90009888", workType: ["onsite", "hybrid"], timePosted: "month" },
];

type Job = { id: string; title: string; company: string; link: string; search: string };
const results: Job[] = [];
const seen = new Set<string>();

for (const config of searches) {
  console.log(`\n[${config.label}]`);
  const jobs = await fetchJobs(config);
  if (jobs.length === 0) { console.log("  no results"); continue; }

  let added = 0;
  for (const job of jobs) {
    if (seen.has(job.id) || existingLinks.has(job.link)) continue;
    seen.add(job.id);
    process.stdout.write(`  ${job.title} @ ${job.company} … `);
    const english = await isEnglishContent(job.id);
    if (!english) { console.log("dropped (lang)"); continue; }
    console.log("ok");
    results.push({ ...job, search: config.label });
    added++;
  }
  console.log(`  => ${added} new`);
}

console.log(`\n=== TOTAL NEW: ${results.length} ===\n`);
for (const j of results) {
  console.log(`[${j.search}] ${j.title} | ${j.company} | ${j.id}`);
}