feat: add skills

This commit is contained in:
Prad Nukala committed 2026-08-26 10:35:34 -04:00
1 parent 6984212b17
commit c50aa92862
150 files changed
+12702

No files matched your search

@@ -0,0 +1,38 @@
import { describe, expect, test } from "bun:test";
import { runCLI } from "./helpers";
describe("Jobindex CLI error contract", () => {
test("search without a query fails with JSON on stderr", async () => {
const result = await runCLI(["search"]);
expect(result.exitCode).toBe(1);
expect(result.stdout).toBe("");
expect(JSON.parse(result.stderr)).toEqual({
error: "--query is required",
code: "MISSING_REQUIRED",
});
});
test("detail without an ID fails before making a request", async () => {
const result = await runCLI(["detail"]);
expect(result.exitCode).toBe(1);
expect(result.stdout).toBe("");
expect(JSON.parse(result.stderr)).toEqual({
error: "Job ID or URL is required",
code: "MISSING_REQUIRED",
});
});
test("an invalid numeric option fails before making a request", async () => {
const result = await runCLI(["search", "--query", "test", "--page", "not-a-number"]);
const error = JSON.parse(result.stderr);
expect(result.exitCode).toBe(1);
expect(result.stdout).toBe("");
expect(error.ok).toBe(false);
expect(error.error.kind).toBe("validation");
expect(error.error.option).toBe("page");
expect(error.error.message).toContain("Expected number");
});
});
@@ -0,0 +1,80 @@
import { describe, expect, test } from "bun:test";
import { runCLI } from "./helpers";
// All cases fail schema validation (or the required-flag guard) before any
// network request, so the suite is network-free. Regression context: a bare
// z.coerce.number() accepted --limit=-1, and slice(0, -1) then silently
// dropped the last result instead of erroring. Filter flags (--jobage) also
// accepted negative and fractional values that were sent raw to the portal.
function expectValidationError(result: { exitCode: number; stdout: string; stderr: string }, option: string) {
expect(result.exitCode).toBe(1);
expect(result.stdout).toBe("");
const error = JSON.parse(result.stderr);
expect(error.ok).toBe(false);
expect(error.error.kind).toBe("validation");
expect(error.error.option).toBe(option);
}
describe("Jobindex CLI flag validation", () => {
test("--limit=-1 is rejected instead of silently dropping the last result", async () => {
const result = await runCLI(["search", "--query", "test", "--limit=-1"]);
expectValidationError(result, "limit");
expect(JSON.parse(result.stderr).error.message).toContain("greater than or equal to 1");
});
test("--limit=0 is rejected", async () => {
const result = await runCLI(["search", "--query", "test", "--limit=0"]);
expectValidationError(result, "limit");
});
test("--limit=1.5 is rejected as non-integer", async () => {
const result = await runCLI(["search", "--query", "test", "--limit=1.5"]);
expectValidationError(result, "limit");
expect(JSON.parse(result.stderr).error.message).toContain("Expected integer");
});
test("--page=0 is rejected on the 1-indexed portal", async () => {
const result = await runCLI(["search", "--query", "test", "--page=0"]);
expectValidationError(result, "page");
});
test("--jobage=-5 is rejected", async () => {
const result = await runCLI(["search", "--query", "test", "--jobage=-5"]);
expectValidationError(result, "jobage");
expect(JSON.parse(result.stderr).error.message).toContain("greater than or equal to 1");
});
test("--jobage=1.5 is rejected as non-integer", async () => {
const result = await runCLI(["search", "--query", "test", "--jobage=1.5"]);
expectValidationError(result, "jobage");
expect(JSON.parse(result.stderr).error.message).toContain("Expected integer");
});
test("valid numeric flags pass schema validation (proven offline via the required-flag guard)", async () => {
const result = await runCLI(["search", "--page=2", "--limit=5"]);
expect(result.exitCode).toBe(1);
expect(JSON.parse(result.stderr)).toEqual({
error: "--query is required",
code: "MISSING_REQUIRED",
});
});
});
describe("unknown flag rejection", () => {
// add-portal.md's contract: "a bogus flag or missing required arg exits 1
// with a JSON error on stderr". A silently discarded flag is worse than an
// error: on jobdanmark a wrong flag name returned the entire database
// (13,862 results) as if it matched the query (review finding F13,
// 2026-08-19). Rejection happens before dispatch, so these are network-free.
test("a bogus --flag exits 1 with a JSON error instead of being silently discarded", async () => {
const result = await runCLI(["search", "--query", "test", "--bogus-flag", "xyz"]);
expect(result.exitCode).toBe(1);
expect(result.stdout).toBe("");
const error = JSON.parse(result.stderr);
expect(error.code).toBe("UNKNOWN_FLAG");
expect(error.error).toContain("--bogus-flag");
});
});
@@ -0,0 +1,152 @@
import { describe, expect, test } from "bun:test";
import { parseDetailPage } from "../src/commands/detail";
// Jobindex redesigned its detail pages; every selector the old parser used
// (job-text, jix-info, jix_robotjob--area, jix-toolbar-top__company) is gone
// from live pages, so detail returned null company/location/date, CSS-comment
// text as the deadline, and an external ATS URL as its own id/url - exit 0,
// nothing signalling breakage (review finding F14, 2026-08-19, measured on
// 5/5 live postings). These fixtures are trimmed from live pages captured
// 2026-08-19: the jobindex-native "jd-*" shape and the external-ATS
// (hr-manager/Talentech) passthrough shape.
const NATIVE_PAGE = `<!DOCTYPE html>
<html lang="da">
<head>
<title>VELLIV - Udvikler til Camunda/AWS</title>
<meta property="og:title" content="Udvikler til Camunda/AWS" />
<meta property="og:url" content="https://www.jobindex.dk/jobannonce/h1690934" />
<meta property="og:description" content="VELLIV" />
</head>
<body>
<div class="jd-appetizer">
<h1>Udvikler til Camunda/AWS</h1>
</div>
<div id="container" class="container">
<div class="row">
<div class="twelve columns jd-details">
<div class="jd-description">
<p class="appetizer">En virksomhed med mere end 100 &aring;rs historie, der samtidig er cloud-only, er ikke hverdagskost.</p>
<p>Hos Velliv f&aring;r du mulighed for at arbejde med Camunda, AWS og automatisering af processer.</p>
</div>
</div>
<div class="four columns jd-facts">
<div class="jd-type">
<h3>Jobtype:</h3>
<p>Fast</p>
</div>
<div class="jd-workhours">
<h3>Arbejdstid:</h3>
<p>Fuldtid</p>
</div>
<div class="jd-worktime">
<h3>Arbejdsdage:</h3>
<p>Dag</p>
</div>
<div class="jd-deadline">
<h3>Ans&oslash;gningsfrist:</h3>
<p>13. september 2026</p>
</div>
<div class="jd-location">
<h3>Arbejdssted:</h3>
<p>Ballerup</p>
</div>
</div>
</div>
</div>
</body>
</html>`;
// The external shape: an employer's ATS-hosted ad served through jobindex.
// og:url points at the ATS (NOT the posting), og:site_name is the ATS brand,
// and the only occurrence of the deadline label outside the widget is inside
// a CSS comment - the exact text the old regex captured as the deadline.
const EXTERNAL_PAGE = `<!DOCTYPE html>
<html>
<head>
<title>
Talentech - C#-udvikler til kritiske analysel&oslash;sninger i elnettet
</title>
<meta name="description" content="Vi s&oslash;ger en udvikler til elnettet" />
<meta itemprop="name" content="C#-udvikler til kritiske analysel&oslash;sninger i elnettet" />
<meta property="og:title" content="C#-udvikler til kritiske analysel&oslash;sninger i elnettet" />
<meta property="og:site_name" content="Talentech" />
<meta property="og:url" content="https://candidate.hr-manager.net/ApplicationInit.aspx?cid=316&amp;ProjectId=188792" />
<style>
/* Defines the style of the Application Due text */
/* DK: Ansøgningsfrist */
/* BOKSTAV: K */
.frist { padding-bottom: 15px; }
</style>
</head>
<body>
<h1>C#-udvikler til kritiske analysel&oslash;sninger i elnettet</h1>
<p>Vil du v&aelig;re med til at udvikle og drifte de systemer, der underst&oslash;tter udbygningen af Danmarks kommende elnet? Vi arbejder i krydsfeltet mellem IT og energi.</p>
<div class="workplacelist emptyparent"><div id="workplacelist_lang" class="rowheader">Workplace</div><div class="widget-line"></div><span class="empty">Fredericia</span><br></div>
<div class="frist emptyparent"><div id="frist_lang" class="rowheader">Application due</div><div class="widget-line"></div><span class="empty">21-09-2026</span><br></div>
</body>
</html>`;
const JOBANNONCE_URL = "https://www.jobindex.dk/jobannonce/";
describe("parseDetailPage - jobindex-native (jd-*) shape", () => {
const job = parseDetailPage(NATIVE_PAGE, `${JOBANNONCE_URL}h1690934`, "h1690934");
test("extracts the contract fields", () => {
expect(job).toMatchObject({
id: "h1690934",
title: "Udvikler til Camunda/AWS",
company: "VELLIV",
location: "Ballerup",
deadline: "2026-09-13",
url: `${JOBANNONCE_URL}h1690934`,
});
});
test("converts the Danish long date to ISO", () => {
expect(job.deadline).toBe("2026-09-13");
});
test("extracts employment metadata and the description body", () => {
expect(job.employmentType).toBe("Fast");
expect(job.hours).toBe("Fuldtid");
expect(job.description).toContain("Camunda, AWS og automatisering");
});
});
describe("parseDetailPage - external ATS passthrough shape", () => {
const job = parseDetailPage(EXTERNAL_PAGE, `${JOBANNONCE_URL}h1690445`, "h1690445");
test("keeps the jobindex id and jobannonce URL, never the ATS og:url", () => {
expect(job.id).toBe("h1690445");
expect(job.url).toBe(`${JOBANNONCE_URL}h1690445`);
expect(job.url).not.toContain("hr-manager.net");
});
test("extracts the title and never reports the ATS brand as the company", () => {
expect(job.title).toBe("C#-udvikler til kritiske analyseløsninger i elnettet");
expect(job.company).toBeNull();
});
test("extracts the workplace widget location", () => {
expect(job.location).toBe("Fredericia");
});
test("finds the real deadline, not the CSS comment", () => {
expect(job.deadline).toBe("2026-09-21");
});
test("description is readable body text, not a stylesheet", () => {
expect(job.description).toContain("udbygningen af Danmarks kommende elnet");
expect(job.description).not.toContain("padding-bottom");
});
test("deadline is null when only the CSS comment mentions the label", () => {
const noDueWidget = EXTERNAL_PAGE.replace(
/<div class="frist emptyparent">[\s\S]*?<br><\/div>/,
"",
);
const parsed = parseDetailPage(noDueWidget, `${JOBANNONCE_URL}h9`, "h9");
expect(parsed.deadline).toBeNull();
});
});
+39
View File
@@ -0,0 +1,39 @@
import { join } from "path";
const CLI_PATH = join(import.meta.dir, "../src/cli.ts");
export interface CLIResult {
stdout: string;
stderr: string;
exitCode: number;
}
export async function runCLI(args: string[]): Promise<CLIResult> {
const proc = Bun.spawn(["bun", "run", CLI_PATH, ...args], {
stdout: "pipe",
stderr: "pipe",
});
const [stdout, stderr, exitCode] = await Promise.all([
new Response(proc.stdout).text(),
new Response(proc.stderr).text(),
proc.exited,
]);
return { stdout: stdout.trim(), stderr: stderr.trim(), exitCode };
}
export function parseJSON<T = unknown>(result: CLIResult): T {
if (result.exitCode !== 0) {
throw new Error(
`CLI exited with code ${result.exitCode}. stderr: ${result.stderr}`
);
}
try {
return JSON.parse(result.stdout) as T;
} catch {
throw new Error(
`Failed to parse JSON. stdout: ${result.stdout}\nstderr: ${result.stderr}`
);
}
}
+98
View File
@@ -0,0 +1,98 @@
import { describe, test, expect } from "bun:test";
import { parseJobCards, extractDivContent } from "../src/helpers";
// Minimal jobad-wrapper markup: parseJobCards splits on `jobad-wrapper-<id>`
// and reads the title from the <h4><a href>…</a></h4> and the company from the
// jix-toolbar-top__company link. We inject HTML entities to exercise decoding.
function card(id: string, title: string, company = "Acme A/S"): string {
return `<div id="jobad-wrapper-${id}" class="PaidJob">
<h4><a href="https://www.jobindex.dk/jobannonce/${id}">${title}</a></h4>
<div class="jix-toolbar-top__company">
<a href="https://www.jobindex.dk/virksomhed/acme">${company}</a>
</div>
</div>`;
}
describe("decodeHtmlEntities (via parseJobCards)", () => {
test("decodes hexadecimal numeric entities (&#xF8; -> ø)", () => {
const [c] = parseJobCards(card("h1", "Sm&#xF8;rrebro Chef"));
expect(c.title).toBe("Smørrebro Chef");
});
test("decodes uppercase-X hexadecimal entities (&#XE6; -> æ)", () => {
const [c] = parseJobCards(card("h2", "K&#XE6;re Kollega"));
expect(c.title).toBe("Kære Kollega");
});
test("still decodes decimal numeric entities (&#229; -> å) — regression", () => {
const [c] = parseJobCards(card("h3", "&#229;rhus Lead"));
expect(c.title).toBe("århus Lead");
});
test("decodes supplementary-plane code points with fromCodePoint (&#128512;)", () => {
const [c] = parseJobCards(card("h4", "Growth &#128512;"));
expect(c.title).toBe("Growth 😀");
});
test("decodes hex supplementary-plane code points (&#x1F600;)", () => {
const [c] = parseJobCards(card("h5", "Growth &#x1F600;"));
expect(c.title).toBe("Growth 😀");
});
test("decodes hex entities in the company name too", () => {
const [c] = parseJobCards(card("h6", "Engineer", "N&#xF8;rrebro ApS"));
expect(c.company).toBe("Nørrebro ApS");
});
});
describe("extractDivContent", () => {
test("extracts content from simple div", () => {
const html = '<div class="job-text">Simple text</div>';
expect(extractDivContent(html, "job-text")).toBe("Simple text");
});
test("extracts content with nested divs — the regression case", () => {
const html = `<div class="job-text">
<div class="highlight">First section</div>
<div class="details">Second section with important info</div>
</div>`;
expect(extractDivContent(html, "job-text")).toBe(
'\n <div class="highlight">First section</div>\n <div class="details">Second section with important info</div>\n ',
);
});
test("returns null when class not found", () => {
expect(extractDivContent("<div>no class</div>", "nonexistent")).toBeNull();
});
test("works with extra attributes on the div", () => {
const html = '<div id="desc" class="job-text" data-x="1">Content</div>';
expect(extractDivContent(html, "job-text")).toBe("Content");
});
test("handles deeply nested divs (3 levels)", () => {
const html = `<div class="job-text">
<div>
<div>Deep content</div>
</div>
</div>`;
expect(extractDivContent(html, "job-text")).toBe(
'\n <div>\n <div>Deep content</div>\n </div>\n ',
);
});
test("handles empty content", () => {
const html = '<div class="job-text"></div>';
expect(extractDivContent(html, "job-text")).toBe("");
});
test("handles br and other non-div tags", () => {
const html = '<div class="job-text">Line1<br>Line2<br>Line3</div>';
expect(extractDivContent(html, "job-text")).toBe("Line1<br>Line2<br>Line3");
});
test("escapes special regex characters in class name", () => {
const html = '<div class="job-text (special)">Content</div>';
expect(extractDivContent(html, "job-text (special)")).toBe("Content");
});
});
@@ -0,0 +1,34 @@
import { afterEach, describe, expect, test } from "bun:test";
import { apiFetch, htmlFetch } from "../src/helpers";
// A stalled upstream connection (accepted socket, no response) would otherwise
// hang the CLI forever - fetch has no default timeout. Assert both request
// wrappers carry an AbortSignal timeout. Fails on the pre-fix code (no signal).
const originalFetch = globalThis.fetch;
afterEach(() => {
globalThis.fetch = originalFetch;
});
describe("request timeout", () => {
test("apiFetch passes an AbortSignal timeout to fetch", async () => {
let init: RequestInit | undefined;
globalThis.fetch = (async (_url: string | URL | Request, i?: RequestInit) => {
init = i;
return new Response("{}", { status: 200 });
}) as unknown as typeof fetch;
await apiFetch("/search");
expect(init?.signal).toBeInstanceOf(AbortSignal);
});
test("htmlFetch passes an AbortSignal timeout to fetch", async () => {
let init: RequestInit | undefined;
globalThis.fetch = (async (_url: string | URL | Request, i?: RequestInit) => {
init = i;
return new Response("<html></html>", { status: 200 });
}) as unknown as typeof fetch;
await htmlFetch("https://www.jobindex.dk/x");
expect(init?.signal).toBeInstanceOf(AbortSignal);
});
});
@@ -0,0 +1,89 @@
import { afterEach, describe, expect, test } from "bun:test";
import { apiFetch, htmlFetch } from "../src/helpers";
// The portal contract requires backoff on 429/5xx. These tests pin the retry
// loop offline: a stubbed fetch counts attempts, and a stubbed setTimeout
// fires immediately so the exhaustion case does not sleep through the real
// 500ms -> 5s backoff schedule. apiFetch and htmlFetch carry separate copies
// of the loop, so both are exercised to keep them from drifting apart.
const originalFetch = globalThis.fetch;
const originalSetTimeout = globalThis.setTimeout;
afterEach(() => {
globalThis.fetch = originalFetch;
globalThis.setTimeout = originalSetTimeout;
});
function instantTimers() {
globalThis.setTimeout = ((fn: () => void) =>
originalSetTimeout(fn, 0)) as unknown as typeof setTimeout;
}
function stubFetch(responses: Array<() => Response>): { calls: number } {
const state = { calls: 0 };
globalThis.fetch = (async () => {
const i = Math.min(state.calls, responses.length - 1);
state.calls++;
return responses[i]();
}) as unknown as typeof fetch;
return state;
}
describe("htmlFetch retry/backoff", () => {
test("retries a 429 and succeeds on the next attempt", async () => {
instantTimers();
const state = stubFetch([
() => new Response("", { status: 429 }),
() => new Response("<html>ok</html>", { status: 200 }),
]);
const html = await htmlFetch("https://www.jobindex.dk/x");
expect(html).toContain("ok");
expect(state.calls).toBe(2);
});
test("does not retry a plain 4xx", async () => {
const state = stubFetch([() => new Response("", { status: 400 })]);
await expect(htmlFetch("https://www.jobindex.dk/x")).rejects.toThrow(/400/);
expect(state.calls).toBe(1);
});
test("gives up after the initial attempt plus six retries on persistent 5xx", async () => {
instantTimers();
const state = stubFetch([() => new Response("", { status: 500 })]);
await expect(htmlFetch("https://www.jobindex.dk/x")).rejects.toThrow(/500/);
expect(state.calls).toBe(7);
});
});
describe("apiFetch retry/backoff", () => {
test("retries a 429 and succeeds on the next attempt", async () => {
instantTimers();
const state = stubFetch([
() => new Response("", { status: 429 }),
() => new Response('{"ok":true}', { status: 200 }),
]);
const data = await apiFetch<{ ok: boolean }>("/x");
expect(data.ok).toBe(true);
expect(state.calls).toBe(2);
});
test("does not retry a plain 4xx", async () => {
const state = stubFetch([() => new Response("", { status: 400 })]);
await expect(apiFetch("/x")).rejects.toThrow(/400/);
expect(state.calls).toBe(1);
});
test("gives up after the initial attempt plus six retries on persistent 5xx", async () => {
instantTimers();
const state = stubFetch([() => new Response("", { status: 500 })]);
await expect(apiFetch("/x")).rejects.toThrow(/500/);
expect(state.calls).toBe(7);
});
});
@@ -0,0 +1,69 @@
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("maps an ASAP posting's deadline to null (no stated deadline)", () => {
// apply_deadline_asap means "no fixed deadline, apply now". The /scrape
// schema defines null as exactly that, and every consumer (rank's expiry
// sweep, notion-sync's typed date column) does date arithmetic on this
// field - a bare "ASAP" string broke all of them on half of live results
// (review finding F12, 2026-08-19). lastdate present too: the flag wins.
const [job] = parseSearchPage(
stashPage({
hitcount: 1,
results: [{ ...RESULT, apply_deadline: undefined, apply_deadline_asap: true, lastdate: "2026-09-30" }],
}),
).results;
expect(job.deadline).toBeNull();
});
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");
});
});