Schulcloud-MCP/test/render.test.ts

import assert from 'node:assert/strict';
import { describe, it } from 'node:test';
import { daysUntil, formatDate, htmlToText, joinSections, normalizeObjectId } from '../src/core/text.ts';

describe('htmlToText', () => {
	it('unwraps the CKEditor markup Schulcloud stores', () => {
		assert.equal(htmlToText('<p>Hallo <strong>Welt</strong></p>'), 'Hallo Welt');
	});

	it('keeps the href when the link text differs from it', () => {
		assert.equal(
			htmlToText('<p><a href="https://example.org/x">Beispiel</a></p>'),
			'Beispiel (https://example.org/x)',
		);
	});

	it('does not duplicate a bare URL used as its own label', () => {
		assert.equal(htmlToText('<a href="https://example.org">https://example.org</a>'), 'https://example.org');
	});

	it('renders list items as bullets and collapses blank runs', () => {
		assert.equal(htmlToText('<ul><li>eins</li><li>zwei</li></ul>'), '- eins\n- zwei');
	});

	it('decodes entities, ampersand last so &amp;lt; stays literal', () => {
		assert.equal(htmlToText('<p>a &amp;lt; b &lt; c</p>'), 'a &lt; b < c');
	});

	it('collapses runs of spaces, including the non-breaking ones', () => {
		// Schulcloud content is full of &nbsp; used as padding; keeping it would
		// reproduce that padding in the plain-text output for no benefit.
		assert.equal(htmlToText('<p>a &nbsp;b</p>'), 'a b');
	});

	it('strips the source template\'s indentation from every line', () => {
		// Paragraphs still separate with a blank line; what goes is the leading
		// run of spaces the server-side template left on each line.
		const html = '<p>\n                    first line<br>\n                    second line</p>';
		assert.equal(htmlToText(html), 'first line\nsecond line');
	});

	it('separates table cells so columns do not run together', () => {
		const html = '<table><tr><td>Bestandteil</td><td>Funktion</td></tr>' +
			'<tr><td>Gehirn</td><td>steuert</td></tr></table>';
		assert.equal(htmlToText(html), 'Bestandteil | Funktion\nGehirn | steuert');
	});

	it('keeps a cell that wraps its text in a paragraph on one row', () => {
		const html = '<table><tr><td><p>Bestandteil</p></td><td>Gehirn</td></tr></table>';
		assert.equal(htmlToText(html), 'Bestandteil | Gehirn');
	});

	it('separates paragraphs with a blank line', () => {
		assert.equal(htmlToText('<p>first</p>\n   <p>second</p>'), 'first\n\nsecond');
	});

	it('returns an empty string for missing input', () => {
		assert.equal(htmlToText(undefined), '');
		assert.equal(htmlToText(null), '');
	});
});

describe('formatDate', () => {
	it('renders ISO timestamps as minute-precision UTC', () => {
		assert.equal(formatDate('2026-08-17T08:00:00.000Z'), '2026-08-17 08:00');
	});

	it('passes through unparseable values rather than printing Invalid Date', () => {
		assert.equal(formatDate('not a date'), 'not a date');
	});

	it('marks absent dates', () => {
		assert.equal(formatDate(null), '—');
	});
});

describe('daysUntil', () => {
	it('is negative for past dates and undefined when unset', () => {
		const yesterday = new Date(Date.now() - 86_400_000).toISOString();
		assert.ok((daysUntil(yesterday) ?? 0) < 0);
		assert.equal(daysUntil(undefined), undefined);
	});
});

describe('joinSections', () => {
	it('drops empty and falsy parts', () => {
		assert.equal(joinSections(['a', '', undefined, false, '  ', 'b']), 'a\n\nb');
	});
});

describe('normalizeObjectId', () => {
	it('converts the buffer shape the legacy lesson API returns', () => {
		const id = { buffer: { type: 'Buffer', data: [106, 130, 219, 101, 127, 25, 207, 115, 254, 60, 242, 13] } };
		assert.equal(normalizeObjectId(id), '6a82db657f19cf73fe3cf20d');
	});

	it('passes plain strings through and gives up on anything else', () => {
		assert.equal(normalizeObjectId('abc'), 'abc');
		assert.equal(normalizeObjectId({}), undefined);
	});
});

describe('decodeEntities', () => {
	it('decodes German umlauts, which the legacy pages emit as named entities', () => {
		assert.equal(htmlToText('<p>vollst&auml;ndig und nachvollziehbar</p>'), 'vollständig und nachvollziehbar');
		assert.equal(htmlToText('<p>Gr&ouml;&szlig;e, &Uuml;bung</p>'), 'Größe, Übung');
	});

	it('decodes decimal and hex numeric references', () => {
		assert.equal(htmlToText('<p>&#8364; &#x20AC; &#228;</p>'), '€ € ä');
	});

	it('does not double-decode: &amp;auml; stays literal text', () => {
		assert.equal(htmlToText('<p>&amp;auml;</p>'), '&auml;');
	});

	it('leaves unknown entities alone rather than mangling them', () => {
		assert.equal(htmlToText('<p>&notarealentity; &amp;</p>'), '&notarealentity; &');
	});

	it('ignores out-of-range numeric references', () => {
		assert.equal(htmlToText('<p>&#1114112;</p>'), '&#1114112;');
	});
});