test(portals): cover linkedin card date/location and jobindex parseSearchPage

The linkedin fixture was purpose-built for entity decoding and had no <time> or location element, so removing the date extraction - a /scrape contract field on a default-ON portal - survived the suite. jobindex's parseSearchPage (the Stash parser behind every search) had zero tests, so meta.total silently dropping hitcount survived too. Both mutations now fail exactly the new tests. The ASAP deadline branch is deliberately left to the F12 fix, which changes its behaviour to null. Review finding F35 (2026-08-19). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 00:26:26 +00:00 · 2026-08-19 20:03:00 +02:00
parent 65fbe8b8a4
commit 2edf8c41f1
3 changed files with 101 additions and 0 deletions
@@ -0,0 +1,54 @@
+import { describe, expect, test } from "bun:test";
+import { parseSearchPage } from "../src/helpers";
+
+// parseSearchPage had no tests at all: mutating total to stop using
+// sr.hitcount survived the whole suite (review finding F35, 2026-08-19).
+// The fixture mirrors the real Stash nesting documented in helpers.ts:
+// jobsearch/result_app -> storeData -> searchResponse -> { hitcount, results[] }.
+function stashPage(searchResponse: object): string {
+  const stash = { jobsearch: { result_app: { storeData: { searchResponse } } } };
+  return `<html><head><script>var Stash = ${JSON.stringify(stash)};</script></head></html>`;
+}
+
+const RESULT = {
+  tid: "h1689961",
+  headline: "Softwareudvikler",
+  company: { name: "Acme A/S", homeurl: "https://acme.example" },
+  area: "Aarhus",
+  firstdate: "2026-08-10",
+  apply_deadline: "2026-09-11T00:00:00",
+};
+
+describe("parseSearchPage", () => {
+  test("total comes from hitcount, not the page's result count", () => {
+    const page = stashPage({ hitcount: 435, results: [RESULT] });
+    const parsed = parseSearchPage(page);
+    expect(parsed.total).toBe(435);
+    expect(parsed.results).toHaveLength(1);
+  });
+
+  test("total falls back to the result count when hitcount is absent", () => {
+    const page = stashPage({ results: [RESULT, { ...RESULT, tid: "h2" }] });
+    expect(parseSearchPage(page).total).toBe(2);
+  });
+
+  test("maps the contract fields from a Stash result", () => {
+    const [job] = parseSearchPage(stashPage({ hitcount: 1, results: [RESULT] })).results;
+    expect(job).toMatchObject({
+      id: "h1689961",
+      title: "Softwareudvikler",
+      company: "Acme A/S",
+      location: "Aarhus",
+      date: "2026-08-10",
+      deadline: "2026-09-11",
+      url: "https://www.jobindex.dk/jobannonce/h1689961",
+    });
+  });
+
+  test("falls back to lastdate when apply_deadline is absent", () => {
+    const [job] = parseSearchPage(
+      stashPage({ hitcount: 1, results: [{ ...RESULT, apply_deadline: undefined, lastdate: "2026-09-30" }] }),
+    ).results;
+    expect(job.deadline).toBe("2026-09-30");
+  });
+});
@@ -14,6 +14,46 @@ function searchCard(id: string, title: string, company = "Acme"): string {
  </li>`;
 }

+// The /scrape contract fields beyond title/company. The original fixture had
+// no <time> or location element at all, so deleting the date extraction from
+// parseJobCards left every test green (review finding F35, 2026-08-19).
+function searchCardWithMeta(id: string, datetimeAttr: string, listdateClass = "job-search-card__listdate"): string {
+  return `<li>
+    <div data-entity-urn="urn:li:jobPosting:${id}">
+      <a class="base-card__full-link" href="https://www.linkedin.com/jobs/view/${id}"></a>
+      <h3 class="base-search-card__title">Data Engineer</h3>
+      <h4 class="base-search-card__subtitle"><a href="https://www.linkedin.com/company/acme">Acme</a></h4>
+      <span class="job-search-card__location">Copenhagen, Denmark</span>
+      <time class="${listdateClass}" datetime="${datetimeAttr}">3 days ago</time>
+    </div>
+  </li>`;
+}
+
+describe("parseJobCards contract fields", () => {
+  test("extracts date from the listdate <time> element", () => {
+    const [card] = parseJobCards(searchCardWithMeta("200", "2026-08-10"));
+    expect(card.date).toBe("2026-08-10");
+  });
+
+  test("extracts date from the listdate--new variant class", () => {
+    const [card] = parseJobCards(
+      searchCardWithMeta("201", "2026-08-15", "job-search-card__listdate--new"),
+    );
+    expect(card.date).toBe("2026-08-15");
+  });
+
+  test("extracts location from the location span", () => {
+    const [card] = parseJobCards(searchCardWithMeta("202", "2026-08-10"));
+    expect(card.location).toBe("Copenhagen, Denmark");
+  });
+
+  test("date and location are null when the elements are absent", () => {
+    const [card] = parseJobCards(searchCard("203", "Bare Card"));
+    expect(card.date).toBeNull();
+    expect(card.location).toBeNull();
+  });
+});
+
 describe("decodeHtmlEntities (via parseJobCards)", () => {
  test("decodes hexadecimal numeric entities (&#xE9;)", () => {
    const [card] = parseJobCards(searchCard("123", "Caf&#xE9; Manager"));
@@ -15,6 +15,13 @@ per-file diff commands.

 ### Added

+- **Fixture coverage for linkedin's date/location and jobindex's `parseSearchPage`** -
+  linkedin's search-card fixture carried no `<time>` or location element, so deleting
+  the `date` extraction (a `/scrape` contract field on a default-ON portal) left every
+  test green; jobindex's Stash parser had no tests at all, so `meta.total` could stop
+  using `hitcount` unnoticed. Four new linkedin cases (both listdate class variants,
+  location, absent-element nulls) and a new jobindex `search-page.test.ts` (hitcount
+  vs page count, contract-field mapping, deadline fallbacks). Both mutation-verified.
 - **Tests for `check_framework_version.py`** - the CI gate that stops a framework file
  from being edited without a `framework_version` bump had zero tests, so the one-line
  mutation `return meaningful_changes > 0` -> `return False` disabled it while the suite