ai-job-search/.agents/skills/jobdanmark-search/cli/tests/detail-parsing.test.ts

import { describe, expect, test } from "bun:test";
import { parseJobPostingFromHtml } from "../src/commands/detail";

const HTML_WITHOUT_JSON_LD = `<!doctype html>
<html lang="da">
  <head>
    <title>Journalistisk udvikler s&#xF8;ges | jobdanmark</title>
  </head>
  <body>
    <div class="job-list-details">
      <div class="job-details-head row mx-0">
        <div class="company-logo col-auto">
          <img src="/media/jfm-logo.png?width=100" alt="JFM">
        </div>
        <h3 class="title">Journalistisk udvikler s&#xF8;ges</h3>
        <a href="/virksomheder/jfm">JFM</a>
        <span>Baneg&#xE5;rdspladsen 1, 5000 Odense C</span>
      </div>
      <p>Hvad nu hvis du med f&#xE5; klik kunne unders&#xF8;ge dit lokalomr&#xE5;de?</p>
      <ul>
        <li>identificere relevante datas&#xE6;t og muligheder</li>
      </ul>
    </div>
    <a href="https://jfm.career.emply.com/da/apply/example" class="action primary count-click">Ans&#xF8;g nu</a>
    <ul class="job-overview list-unstyled">
      <li><strong>Udgivet:</strong> 03-07-2026</li>
      <li><strong>Jobtype:</strong> Fuldtid</li>
      <li><strong>Arbejdssted:</strong> Baneg&#xE5;rdspladsen 1, 5000 Odense C</li>
      <li><strong>Ansøgningsfrist:</strong> 02-08-2026 23.59</li>
    </ul>
  </body>
</html>`;

describe("parseJobPostingFromHtml", () => {
  test("falls back to rendered Jobdanmark HTML when JSON-LD is absent", () => {
    const parsed = parseJobPostingFromHtml(
      HTML_WITHOUT_JSON_LD,
      "journalistisk-udvikler",
      "https://jobdanmark.dk/job/journalistisk-udvikler",
    );

    expect(parsed.title).toBe("Journalistisk udvikler søges");
    // The fallback must emit the same shapes as the JSON-LD branch: contract
    // dates, not the page's raw DD-MM-YYYY text (review finding F25, 2026-08-19).
    expect(parsed.datePosted).toBe("2026-07-03");
    expect(parsed.validThrough).toBe("2026-08-02");
    expect(parsed.employmentType).toEqual(["Fuldtid"]);
    expect(parsed.hiringOrganization.name).toBe("JFM");
    expect(parsed.hiringOrganization.logo).toBe("https://jobdanmark.dk/media/jfm-logo.png?width=100");
    expect(parsed.jobLocation.streetAddress).toBe("Banegårdspladsen 1, 5000 Odense C");
    expect(parsed.jobLocation.addressLocality).toBe("Odense C");
    expect(parsed.description).toContain("identificere relevante datasæt");
    expect(parsed.applyUrl).toBe("https://jfm.career.emply.com/da/apply/example");
  });

  test("maps a rolling deadline (Løbende) to null in the HTML fallback", () => {
    // "Løbende" is free text meaning rolling/ongoing - jobbank's parser maps
    // its equivalent to null, and a stored "Løbende" deadline would hit every
    // date-arithmetic consumer (review finding F25, 2026-08-19).
    const html = HTML_WITHOUT_JSON_LD.replace(
      "<li><strong>Ansøgningsfrist:</strong> 02-08-2026 23.59</li>",
      "<li><strong>Ansøgningsfrist:</strong> Løbende</li>",
    );
    const parsed = parseJobPostingFromHtml(html, "s", "https://jobdanmark.dk/job/s");
    expect(parsed.validThrough).toBeNull();
  });

  test("drops a malformed closing tag that the parser left as text (#525)", () => {
    // A live page (konsulent-til-renoveringsprogram) wrote its Jobtype item as
    // `Fuldtid </ li >`; node-html-parser does not recognise `</ li >` as a tag,
    // so it reached employmentType verbatim. The same cleanText feeds the title,
    // company, workplace and description on this branch.
    const html = HTML_WITHOUT_JSON_LD.replace(
      "<li><strong>Jobtype:</strong> Fuldtid</li>",
      "<li><strong>Jobtype:</strong> Fuldtid </ li ></li>",
    ).replace(
      "<p>Hvad nu hvis du med f&#xE5; klik kunne unders&#xF8;ge dit lokalomr&#xE5;de?</p>",
      "<p>Hvad nu hvis du med f&#xE5; klik kunne unders&#xF8;ge dit lokalomr&#xE5;de?</ p ></p>",
    );

    const parsed = parseJobPostingFromHtml(
      html,
      "journalistisk-udvikler",
      "https://jobdanmark.dk/job/journalistisk-udvikler",
    );

    expect(parsed.employmentType).toEqual(["Fuldtid"]);
    expect(parsed.description.split("\n")[0]).toBe("Hvad nu hvis du med få klik kunne undersøge dit lokalområde?");
    expect(JSON.stringify(parsed)).not.toMatch(/<\s*\/?\s*[a-z]+\s*>/i);
  });

  test("keeps author text the page entity-encoded as a literal tag (#525)", () => {
    // node-html-parser decodes entities before cleanText runs, so `&lt;div&gt;`
    // in a description arrives as a literal `<div>`. Only the malformed
    // closing-tag shape is stripped; an opening tag or a type parameter stays.
    const html = HTML_WITHOUT_JSON_LD.replace(
      "<p>Hvad nu hvis du med f&#xE5; klik kunne unders&#xF8;ge dit lokalomr&#xE5;de?</p>",
      "<p>Erfaring med &lt;div&gt; og &lt;span&gt; i HTML, og &lt;T&gt; generics; x &lt; y &gt; z.</p>",
    );

    const parsed = parseJobPostingFromHtml(
      html,
      "journalistisk-udvikler",
      "https://jobdanmark.dk/job/journalistisk-udvikler",
    );

    expect(parsed.description.split("\n")[0]).toBe(
      "Erfaring med <div> og <span> i HTML, og <T> generics; x < y > z.",
    );
  });

  test("does not reject titles containing '404' mid-phrase", () => {
    const htmlWith404InTitle = HTML_WITHOUT_JSON_LD.replace(
      "<title>Journalistisk udvikler s&#xF8;ges | jobdanmark</title>",
      "<title>HTTP 404 Page Designer | jobdanmark</title>",
    ).replace(
      '<h3 class="title">Journalistisk udvikler s&#xF8;ges</h3>',
      '<h3 class="title">HTTP 404 Page Designer</h3>',
    );

    const parsed = parseJobPostingFromHtml(
      htmlWith404InTitle,
      "http-404-designer",
      "https://jobdanmark.dk/job/http-404-designer",
    );

    expect(parsed.title).toBe("HTTP 404 Page Designer");
    expect(parsed.hiringOrganization.name).toBe("JFM");
  });
});