Incognito-Wiki/tests/previous-wiki.test.mjs

import assert from 'node:assert/strict';
import { access, mkdtemp, readFile, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import test from 'node:test';

import {
  classifyPreviousPage,
  convertCourseSource,
  crawlPreviousWiki,
  destinationForPageId,
  extractSitemapEntries,
} from '../scripts/lib/previous-wiki.mjs';

test('extracts unique namespace and page IDs from a DokuWiki sitemap', () => {
  const html = `
    <div id="index__tree">
      <a class="idx_dir" href="/wiki/start?idx=study%3Abachelor">Bachelor</a>
      <a class="idx_dir" href="/wiki/start?idx=study%3Abachelor">Bachelor duplicate</a>
      <a class="wikilink1" data-wiki-id="study:bachelor:year_1:block_1:calculus">Calculus</a>
      <a class="wikilink1" data-wiki-id="study:bachelor:year_1:block_1:calculus">Calculus duplicate</a>
    </div>`;

  assert.deepEqual(extractSitemapEntries(html), {
    namespaces: ['study:bachelor'],
    pageIds: ['study:bachelor:year_1:block_1:calculus'],
  });
});

test('classifies course pages separately from represented and excluded pages', () => {
  const represented = new Set(['study:bachelor:year_1']);
  assert.equal(classifyPreviousPage('study:bachelor:year_1', represented), 'represented');
  assert.equal(
    classifyPreviousPage('study:bachelor:year_1:block_1:calculus', represented),
    'migrate',
  );
  assert.equal(classifyPreviousPage('wiki:syntax', represented), 'excluded');
  assert.equal(classifyPreviousPage('sidebar', represented), 'excluded');
  assert.equal(classifyPreviousPage('study:useful_information', represented), 'excluded');
  assert.equal(
    classifyPreviousPage(
      'study:master_ai:year_2:block_1:placeholder',
      represented,
      '====== placeholder ======\n\nThis course is a placeholder',
    ),
    'empty',
  );
});

test('maps in-scope course IDs to stable Starlight destinations', () => {
  assert.equal(
    destinationForPageId('study:bachelor:year_1:block_1:discrete_mathematics'),
    'src/content/docs/data-science-and-ai/year-1/block-1/discrete-mathematics.md',
  );
  assert.equal(
    destinationForPageId('study:master_ai:year_2:block_3:agents'),
    'src/content/docs/master-ai/year-2/block-3/agents.md',
  );
  assert.equal(destinationForPageId('study:useful_information'), null);
});

test('recursively crawls sitemap namespaces and saves every raw page once', async () => {
  const outputRoot = await mkdtemp(join(tmpdir(), 'incognito-previous-wiki-'));
  const requests = [];
  const responses = new Map([
    ['/wiki/start?do=index', '<div id="index__tree"><a class="idx_dir" href="?idx=study">Study</a><a data-wiki-id="start">Start</a></div>'],
    ['/wiki/start?do=index&idx=study', '<div id="index__tree"><a class="idx_dir" href="?idx=study%3Abachelor">Bachelor</a><a data-wiki-id="study">Study</a></div>'],
    ['/wiki/start?do=index&idx=study%3Abachelor', '<div id="index__tree"><a data-wiki-id="study:bachelor:year_1:block_1:calculus">Calculus</a></div>'],
    ['/wiki/_export/raw/start', '====== Home ======'],
    ['/wiki/_export/raw/study', '====== Study ======'],
    ['/wiki/_export/raw/study%3Abachelor%3Ayear_1%3Ablock_1%3Acalculus', '====== Calculus ======'],
  ]);
  try {
    const manifest = await crawlPreviousWiki({
      capturedAt: '2026-08-03',
      outputRoot,
      fetchText: async (path) => {
        requests.push(path);
        if (!responses.has(path)) throw new Error(`unexpected request ${path}`);
        return responses.get(path);
      },
    });

    assert.equal(manifest.pages.length, 3);
    assert.equal(manifest.failures.length, 0);
    assert.deepEqual(manifest.pages.map(({ id }) => id), [
      'start',
      'study',
      'study:bachelor:year_1:block_1:calculus',
    ]);
    assert.equal(
      await readFile(join(outputRoot, 'pages/study/bachelor/year_1/block_1/calculus.txt'), 'utf8'),
      '====== Calculus ======',
    );
    assert.equal(new Set(requests).size, requests.length);
  } finally {
    await rm(outputRoot, { recursive: true, force: true });
  }
});

test('converts a DokuWiki course source and its file list to clean Starlight Markdown', () => {
  const markdown = convertCourseSource({
    pageId: 'study:bachelor:year_1:block_1:calculus',
    sourceUrl: 'https://msvincognito.nl/wiki/study/bachelor/year_1/block_1/calculus',
    source: [
      '====== Calculus ======',
      '',
      '==== Full course description ====',
      '',
      'See [[https://example.com/course|the course guide]].\\\\',
      '',
      '==== Files ====',
      '',
      '{{filelist>:study:bachelor:year_1:block_1:calculus:*&showdate=1}}',
      '',
      '~~NOCACHE~~',
    ].join('\n'),
    pdfs: [{
      mediaId: 'study:bachelor:year_1:block_1:calculus:exam.pdf',
      publicUrl: '/media/legacy-dokuwiki/study/bachelor/year_1/block_1/calculus/exam.pdf',
    }],
  });

  assert.match(markdown, /^---\ntitle: Calculus\ndescription:/);
  assert.match(markdown, /:::caution\[Historical information\]/);
  assert.match(markdown, /## Full course description/);
  assert.match(markdown, /\[the course guide\]\(https:\/\/example\.com\/course\)/);
  assert.match(markdown, /\[Exam\]\(\/media\/legacy-dokuwiki\/study\/bachelor\/year_1\/block_1\/calculus\/exam\.pdf\)/);
  assert.match(markdown, /\[Previous wiki page\]\(https:\/\/msvincognito\.nl\/wiki\/study\/bachelor\/year_1\/block_1\/calculus\)/);
  assert.doesNotMatch(markdown, /\[\[|\{\{|~~NOCACHE~~|^# /m);
});

test('replaces a generic Course Title heading with the course page name', () => {
  const markdown = convertCourseSource({
    pageId: 'study:master_dsdm:year_1:block_5:planning_and_scheduling',
    sourceUrl: 'https://msvincognito.nl/wiki/study/master_dsdm/year_1/block_5/planning_and_scheduling',
    source: '====== Course Title ======\n\nCourse description.',
    pdfs: [],
  });
  assert.match(markdown, /^---\ntitle: Planning And Scheduling\n/);
});

test('all 54 substantive live course pages are published and registered', async () => {
  const rows = (await readFile('docs/live-course-recovery.tsv', 'utf8')).trim().split(/\r?\n/).slice(1)
    .map((line) => {
      const [id, sourceUrl, status, destination] = line.split('\t');
      return { id, sourceUrl, status, destination };
    });
  const migrated = rows.filter(({ status }) => status === 'migrated');
  assert.equal(migrated.length, 54);
  assert.equal(rows.filter(({ status }) => status === 'migrate').length, 0);

  const supplemental = JSON.parse(await readFile('docs/supplemental-content.json', 'utf8'));
  const supplementalByDestination = new Map(supplemental.map((entry) => [entry.destination, entry]));
  const recoveredSidebar = await readFile('src/config/recovered-course-sidebar.mjs', 'utf8');
  for (const record of migrated) {
    await access(record.destination);
    const content = await readFile(record.destination, 'utf8');
    assert.match(content, /:::caution\[Historical information\]/, record.destination);
    assert.match(content, new RegExp(record.sourceUrl.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')), record.destination);
    assert.equal(supplementalByDestination.get(record.destination)?.source, record.sourceUrl);
    assert.equal(supplementalByDestination.get(record.destination)?.category, 'live-course-recovery');
    const slug = record.destination.replace(/^src\/content\/docs\//, '').replace(/\.md$/, '');
    assert.match(recoveredSidebar, new RegExp(`slug: '${slug}'`), slug);
  }
  const report = await readFile('docs/live-course-recovery.md', 'utf8');
  assert.match(report, /Course pages migrated \| 54/);
  assert.doesNotMatch(report, /Substantive course pages to migrate/);
});