dorfteich/apps/api/src/import-export/pdf.fidelity.test.ts

import { DEFAULT_FONTS, PondFonts } from '@dorfteich/shared';
import { PDFParse } from 'pdf-parse';
import { beforeAll, describe, expect, it, TestContext } from 'vitest';

import { AppConfig } from '../config/app-config.service';

import { GotenbergHttpRenderer } from './gotenberg.renderer';
import { buildPdfHtml } from './pdf-html';

/**
 * PDF export smoke check (issue #69, ADR 0009): renders a known page to PDF
 * through the real pinned Gotenberg and asserts the output is a PDF whose
 * extracted text carries the expected strings, with a sane page count. This
 * catches a broken renderer or a template regression that unit tests (which use
 * a fake renderer) cannot. Needs a reachable Gotenberg sidecar
 * (`gotenberg/gotenberg:8`); the test skips itself when none is configured, and
 * CI starts one and points `GOTENBERG_URL` at it.
 */
const GOTENBERG_URL = process.env.GOTENBERG_URL ?? 'http://localhost:3000';

const renderer = new GotenbergHttpRenderer({ env: { GOTENBERG_URL } } as unknown as AppConfig);

let reachable = false;

/** Extract the concatenated text and page count from PDF bytes. */
async function readPdf(pdf: Buffer): Promise<{ text: string; pages: number }> {
  const parser = new PDFParse({ data: new Uint8Array(pdf) });
  try {
    const result = await parser.getText();
    return { text: result.text, pages: result.total };
  } finally {
    await parser.destroy();
  }
}

describe('PDF export smoke (real Gotenberg, issue #69)', () => {
  beforeAll(async () => {
    reachable = await renderer.reachable().catch(() => false);
  });

  it('renders a page to a PDF containing its text, with a sane page count', async (ctx: TestContext) => {
    if (!reachable) ctx.skip();
    const html = buildPdfHtml({
      title: 'Pond Fidelity Report',
      pondName: 'Fidelity Pond',
      // A forced page break so we can assert multi-page sanity; the markers are
      // distinctive strings we can look for in the extracted text.
      bodyHtml:
        '<p>The northern reeds have spread noticeably this season.</p>' +
        '<div style="page-break-before: always"></div>' +
        '<p>Recorded water temperature was fourteen degrees.</p>',
      fonts: DEFAULT_FONTS as PondFonts,
      // No inlined font faces — the render falls back to the system stack, which
      // still produces selectable text (fonts are covered by the #66/#67 tests).
      fontFaceCss: '',
    });

    const pdf = await renderer.renderHtmlToPdf(html);
    expect(pdf.subarray(0, 5).toString('latin1')).toBe('%PDF-');

    const { text, pages } = await readPdf(pdf);
    // Title + pond name (from the header) and both body markers survive to text.
    expect(text).toContain('Pond Fidelity Report');
    expect(text).toContain('Fidelity Pond');
    expect(text).toContain('northern reeds');
    expect(text).toContain('water temperature');
    // Page-count sanity: the forced break must produce a second page (≥ 2), and
    // this trivial document must not balloon (≤ 3) — a runaway render from a CSS
    // regression would blow well past that.
    expect(pages).toBeGreaterThanOrEqual(2);
    expect(pages).toBeLessThanOrEqual(3);
  });
});