#!/usr/bin/env bun
import { searches } from "./config.ts";
import { fetchJobs, isEnglishContent } from "./fetch.ts";

const CSV = "./jobs.csv";
const HEADER = "date_found,posted_at,search,title,company,link";

// Load existing IDs from CSV to deduplicate across runs
const existingIds = new Set<string>();
try {
  const text = await Bun.file(CSV).text();
  for (const line of text.split("\n").slice(1)) {
    const id = line.match(/\/jobs\/view\/(\d+)\//)?.[1];
    if (id) existingIds.add(id);
  }
} catch {
  // first run — file doesn't exist yet
}

const date = new Date().toISOString().slice(0, 10);
const newRows: string[] = [];

function csvCell(val: string): string {
  return `"${val.replace(/"/g, '""')}"`;
}

for (const config of searches) {
  console.log(`\n[${config.label}]`);
  const jobs = await fetchJobs(config);

  if (jobs.length === 0) {
    console.log("  No jobs found.");
    continue;
  }

  let added = 0;
  let langDropped = 0;
  for (const job of jobs) {
    if (!existingIds.has(job.id)) {
      process.stdout.write(`  checking content: ${job.title} … `);
      const english = await isEnglishContent(job.id);
      if (!english) {
        console.log("dropped (non-English)");
        langDropped++;
        continue;
      }
      console.log("ok");
      existingIds.add(job.id);
      newRows.push(
        [date, job.postedAt, config.label, job.title, job.company, job.link]
          .map(csvCell)
          .join(",")
      );
      added++;
    }
  }
  console.log(`  ${jobs.length} found, ${added} new, ${langDropped} non-English dropped`);
}

if (newRows.length === 0) {
  console.log("\nNo new jobs.");
  process.exit(0);
}

// Append to CSV (write header if first run)
const existing = await Bun.file(CSV).exists();
const append = existing
  ? await Bun.file(CSV).text()
  : HEADER + "\n";

await Bun.write(CSV, append + newRows.join("\n") + "\n");

console.log(`\n${newRows.length} new jobs → ${CSV}`);