SnapOtter/tests/integration/pdf-to-text.test.ts

import { readFileSync } from "node:fs";
import { join } from "node:path";
import { afterAll, beforeAll, describe, expect, it } from "vitest";
import { hasFitz } from "../helpers/python-gate.js";
import { buildTestApp, createMultipartPayload, loginAsAdmin, type TestApp } from "./test-server.js";

const PDF = readFileSync(join(__dirname, "..", "fixtures", "test-3page.pdf"));

let testApp: TestApp;
let adminToken: string;

beforeAll(async () => {
  testApp = await buildTestApp();
  adminToken = await loginAsAdmin(testApp.app);
}, 30_000);

afterAll(async () => {
  await testApp.cleanup();
}, 10_000);

async function runTool(settings: Record<string, unknown> = {}) {
  const { body, contentType } = createMultipartPayload([
    { name: "file", filename: "test-3page.pdf", contentType: "application/pdf", content: PDF },
    { name: "settings", content: JSON.stringify(settings) },
  ]);
  return testApp.app.inject({
    method: "POST",
    url: "/api/v1/tools/pdf-to-text",
    headers: { authorization: `Bearer ${adminToken}`, "content-type": contentType },
    body,
  });
}

describe.skipIf(!hasFitz)("pdf-to-text (requires PyMuPDF)", () => {
  it("extracts text and returns a .txt file", async () => {
    const res = await runTool();
    expect(res.statusCode).toBe(200);
    const envelope = JSON.parse(res.body);
    expect(envelope.downloadUrl).toBeDefined();

    const dl = await testApp.app.inject({
      method: "GET",
      url: envelope.downloadUrl,
    });
    expect(dl.statusCode).toBe(200);
    // The text output should have content (the 3-page fixture has text).
    expect(dl.rawPayload.length).toBeGreaterThan(0);
  }, 60_000);
});