Schulcloud-MCP/src/http/app/markdown.js

/*
 * Markdown in, formatted text out, and back again.
 *
 * The notes are Markdown files — that is what the indexer reads, what
 * `subjectFromHeading` takes a lesson apart with, and what survives this
 * project. The editor shows them as formatted text anyway, so this module is
 * the hinge: `markdownToHtml` on the way into the editor, `markdownFromDom` on
 * the way back out to the file.
 *
 * Three properties matter more than completeness, because what passes through
 * here is the only record of what was said in a lesson:
 *
 * - **Round-trip stability.** `fromDom(toHtml(x))` may tidy `x` once — `*a*`
 *   becomes `_a_`, a ragged table lines up — but doing it again must change
 *   nothing. `editor.js` checks exactly that before it opens a note in
 *   formatted mode, and falls back to the Markdown view when it does not hold.
 * - **Nothing is dropped.** An element this module does not model keeps its
 *   words and loses its tag. A note is better off plain than short.
 * - **No HTML is trusted.** `markdownToHtml` escapes everything that is not a
 *   construct it produced itself, so a note containing `<script>` is text, not
 *   script. Pasted HTML never reaches the document either: it is converted to
 *   Markdown first and parsed back, which reduces it to the subset below.
 *
 * The subset is what these notes are made of: headings, paragraphs, bold,
 * italic, strikethrough, code (inline and fenced), links, bullet / numbered /
 * task lists with nesting, blockquotes, tables and rules. Underline is
 * deliberately absent — Markdown has no way to write it, so the toolbar does
 * not offer what the file cannot keep.
 */

/**
 * Where a code span sat while the emphasis rules ran over the line.
 *
 * A control character, because it is the one thing a note cannot contain: the
 * store strips NUL out of extracted text, and nothing types one.
 */
const PLACEHOLDER = '\u0000';
const PLACEHOLDERS = /\u0000(\d+)\u0000/g;

/** Ordered and bullet items, with their indentation and marker. */
const ITEM = /^(\s*)([-*+]|\d{1,9}[.)])\s+(.*)$/;
/** How far a continuation line must be indented to belong to the item above. */
const CONTINUATION = 2;

// --- Markdown → HTML -----------------------------------------------------

/**
 * A note's body as HTML for the editor.
 *
 * The output is the only HTML the editor ever starts from, which is what makes
 * the serializer's job finite.
 */
export function markdownToHtml(markdown) {
	const lines = String(markdown ?? '')
		.replace(/\r\n?/g, '\n')
		.split('\n')
		.map(expandLeadingTabs);
	return parseBlocks(lines);
}

/**
 * Tabs only in the indentation, and only there.
 *
 * Indentation is measured in columns to decide what nests inside what, so a
 * tab has to become a known number of spaces first. Tabs inside the text are
 * left alone — in a code block they are content.
 */
function expandLeadingTabs(line) {
	const match = /^[ \t]+/.exec(line);
	if (!match) return line;
	return match[0].replace(/\t/g, '    ') + line.slice(match[0].length);
}

function parseBlocks(lines) {
	const out = [];
	let i = 0;

	while (i < lines.length) {
		const line = lines[i];
		if (!line.trim()) {
			i++;
			continue;
		}

		const fence = /^ {0,3}(```+|~~~+)\s*([A-Za-z0-9_+#-]*)\s*$/.exec(line);
		if (fence) {
			const closing = new RegExp('^ {0,3}' + fence[1][0] + '{' + fence[1].length + ',}\\s*$');
			const body = [];
			i++;
			while (i < lines.length && !closing.test(lines[i])) {
				body.push(lines[i]);
				i++;
			}
			// An unclosed fence still ends the block; the note is what it is.
			i++;
			const language = fence[2] ? ' class="language-' + escapeHtml(fence[2]) + '"' : '';
			out.push('<pre><code' + language + '>' + escapeHtml(body.join('\n')) + '</code></pre>');
			continue;
		}

		const heading = /^ {0,3}(#{1,6})\s+(.*?)\s*#*$/.exec(line);
		if (heading) {
			const level = heading[1].length;
			out.push('<h' + level + '>' + inlineToHtml(heading[2]) + '</h' + level + '>');
			i++;
			continue;
		}

		if (isRule(line)) {
			out.push('<hr>');
			i++;
			continue;
		}

		if (/^ {0,3}>/.test(line)) {
			const body = [];
			while (i < lines.length && lines[i].trim()) {
				if (/^ {0,3}>/.test(lines[i])) body.push(lines[i].replace(/^ {0,3}> ?/, ''));
				// A wrapped line with no `>` still belongs to the quote it follows.
				else body.push(lines[i].trim());
				i++;
			}
			out.push('<blockquote>' + parseBlocks(body) + '</blockquote>');
			continue;
		}

		if (startsTable(lines, i)) {
			const header = splitRow(lines[i]);
			i += 2;
			const rows = [];
			while (i < lines.length && lines[i].trim() && lines[i].includes('|')) {
				rows.push(splitRow(lines[i]));
				i++;
			}
			out.push(tableToHtml(header, rows));
			continue;
		}

		if (ITEM.test(line)) {
			const list = parseList(lines, i);
			out.push(list.html);
			i = list.next;
			continue;
		}

		// A paragraph, whose single newlines are line breaks rather than
		// paragraph breaks. That is how a note reads in a plain editor and how
		// Notes.app behaved, and it round-trips exactly — unlike the two
		// trailing spaces CommonMark wants, which no one can see.
		const paragraph = [];
		while (i < lines.length && lines[i].trim() && !startsBlock(lines, i)) {
			paragraph.push(lines[i].trim());
			i++;
		}
		out.push('<p>' + paragraph.map(inlineToHtml).join('<br>') + '</p>');
	}

	return out.join('');
}

/** Everything that interrupts a paragraph. */
function startsBlock(lines, index) {
	const line = lines[index];
	return (
		/^ {0,3}(```+|~~~+)/.test(line) ||
		/^ {0,3}#{1,6}\s/.test(line) ||
		/^ {0,3}>/.test(line) ||
		isRule(line) ||
		ITEM.test(line) ||
		startsTable(lines, index)
	);
}

function isRule(line) {
	return /^ {0,3}([-*_])\s*(?:\1\s*){2,}$/.test(line);
}

function startsTable(lines, index) {
	if (!lines[index].includes('|')) return false;
	const next = lines[index + 1];
	return Boolean(next) && /^\s*\|?(\s*:?-{1,}:?\s*\|)+\s*:?-*:?\s*\|?\s*$/.test(next) && next.includes('-');
}

function splitRow(line) {
	let value = line.trim();
	if (value.startsWith('|')) value = value.slice(1);
	if (value.endsWith('|') && !value.endsWith('\\|')) value = value.slice(0, -1);
	// Split on pipes that are not escaped, then give the cells their pipes back.
	return value.split(/(?<!\\)\|/).map((cell) => cell.trim().replace(/\\\|/g, '|'));
}

function tableToHtml(header, rows) {
	const width = Math.max(header.length, ...rows.map((row) => row.length), 1);
	const cells = (row, tag) => {
		let out = '';
		for (let i = 0; i < width; i++) {
			// A break in an empty cell: a `<td></td>` with nothing in it cannot be
			// clicked into, so a blank cell would be uneditable. It serializes
			// back to an empty cell.
			out += '<' + tag + '>' + (inlineToHtml(row[i] ?? '') || '<br>') + '</' + tag + '>';
		}
		return out;
	};
	const body = rows.map((row) => '<tr>' + cells(row, 'td') + '</tr>').join('');
	return '<table><thead><tr>' + cells(header, 'th') + '</tr></thead><tbody>' + body + '</tbody></table>';
}

/**
 * One list, and everything nested inside it.
 *
 * Continuation is by indentation: a line indented at least two columns past
 * the item's own marker belongs to that item, which is what makes nesting and
 * multi-paragraph items work without tracking marker widths through the
 * recursion. Indentation inside an item is relative, so the nested list parses
 * as a list of its own.
 */
function parseList(lines, start) {
	const first = ITEM.exec(lines[start]);
	const base = first[1].length;
	const ordered = /^\d/.test(first[2]);
	const startNumber = ordered ? Number.parseInt(first[2], 10) : 1;
	const items = [];
	let i = start;

	while (i < lines.length) {
		const match = ITEM.exec(lines[i]);
		if (!match) break;
		// A shallower item ends this list; a deeper one is swallowed below as
		// part of the item above it, so reaching one here means the list is over.
		if (match[1].length !== base) break;
		if (/^\d/.test(match[2]) !== ordered) break;

		const body = [match[3]];
		i++;
		while (i < lines.length) {
			const line = lines[i];
			if (!line.trim()) {
				// A blank line keeps the item open only if something indented
				// follows it; otherwise the list ends here.
				const after = lines[i + 1];
				if (after && after.trim() && indentOf(after) >= base + CONTINUATION) {
					body.push('');
					i++;
					continue;
				}
				break;
			}
			if (indentOf(line) >= base + CONTINUATION) {
				body.push(line.slice(base + CONTINUATION));
				i++;
				continue;
			}
			if (ITEM.test(line) || startsBlock(lines, i)) break;
			// A wrapped line, typed without indentation.
			body.push(line.trim());
			i++;
		}
		items.push(body);
	}

	const tag = ordered ? 'ol' : 'ul';
	const open = ordered && startNumber !== 1 ? '<ol start="' + startNumber + '">' : '<' + tag + '>';
	return { html: open + items.map(itemToHtml).join('') + '</' + tag + '>', next: i };
}

function itemToHtml(body) {
	const task = /^\[([ xX])\]\s+([\s\S]*)$/.exec(body[0] ?? '');
	if (task) body = [task[2], ...body.slice(1)];

	let inner = parseBlocks(body);
	// A tight item: its first paragraph is the item's own text, not a paragraph
	// inside it. Unwrapping only the first keeps multi-paragraph items intact.
	inner = inner.replace(/^<p>([\s\S]*?)<\/p>/, '$1');

	if (!task) return '<li>' + inner + '</li>';
	const checked = task[1] !== ' ';
	return (
		'<li class="task"><input type="checkbox" contenteditable="false"' +
		(checked ? ' checked' : '') +
		'>' +
		inner +
		'</li>'
	);
}

function indentOf(line) {
	return /^[ ]*/.exec(line)[0].length;
}

/**
 * Inline Markdown as HTML.
 *
 * Code spans are taken out first and put back last, so the stars and
 * underscores inside `**bold**` written as code stay literal.
 */
function inlineToHtml(text) {
	const literals = [];
	const park = (html) => {
		literals.push(html);
		return PLACEHOLDER + (literals.length - 1) + PLACEHOLDER;
	};

	// Backslash escapes first, or `\*` would still be read as emphasis and a
	// backslashed backtick would still open a code span. Parked as literal
	// text, they take no further part in anything.
	let value = String(text).replace(/\\([\\`*_[\]#>~|+.()-])/g, (all, character) => park(escapeHtml(character)));

	value = value.replace(/(`+)([\s\S]*?)\1/g, (all, fence, body) =>
		park('<code>' + escapeHtml(body.replace(/^ (.*) $/, '$1')) + '</code>'),
	);

	value = escapeHtml(value);

	// Links before emphasis: a label may contain either, and a URL may contain
	// underscores that are not emphasis. One level of balanced parentheses is
	// allowed in the target, because real links have them —
	// de.wikipedia.org/wiki/Erörterung_(Textsorte).
	value = value.replace(/\[([^\]]*)\]\(((?:[^()\s]|\([^()\s]*\))*)\)/g, (all, label, href) => {
		const safe = safeUrl(href);
		if (!safe) return label;
		return '<a href="' + safe + '">' + (label || safe) + '</a>';
	});

	value = value.replace(/(\*\*|__)(?=\S)([\s\S]*?\S)\1/g, '<strong>$2</strong>');
	value = value.replace(/~~(?=\S)([\s\S]*?\S)~~/g, '<del>$1</del>');
	// A single marker, not part of a double one, and not mid-word for `_` —
	// otherwise snake_case_names turn into emphasis.
	value = value.replace(/(?<!\*)\*(?!\*)(?=\S)([\s\S]*?\S)\*(?!\*)/g, '<em>$1</em>');
	value = value.replace(/(?<![\w_])_(?!_)(?=\S)([\s\S]*?\S)_(?![\w_])/g, '<em>$1</em>');

	return value.replace(PLACEHOLDERS, (all, index) => literals[Number(index)]);
}

/**
 * A link target, or nothing.
 *
 * The editor's content comes from the user's own notes, but a note can be
 * written by anything — an import, a paste from a web page — so a `javascript:`
 * url is refused rather than rendered into a document a finger will tap.
 */
function safeUrl(href) {
	const value = href.trim();
	if (!value) return '';
	if (/^[a-z][a-z0-9+.-]*:/i.test(value) && !/^(https?|mailto|tel):/i.test(value)) return '';
	return escapeHtml(value).replace(/"/g, '&quot;');
}

function escapeHtml(value) {
	return String(value).replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
}

// --- HTML → Markdown -----------------------------------------------------

/**
 * What the editor holds, as the Markdown that will be written to the file.
 *
 * Deliberately tolerant: browsers put their own tags into a contenteditable
 * element (`<div>` for a line, `<span style="font-weight: bold">` after a
 * paste, `<font>` on older engines), and none of that may cost a word. An
 * element with no meaning here serializes its children.
 *
 * `root` needs only the read-only parts of the DOM — `nodeType`, `nodeName`,
 * `childNodes`, `textContent` and `getAttribute` — so the same function runs
 * against a plain tree in the tests.
 */
export function markdownFromDom(root) {
	return serializeBlocks(root).replace(/[ \t]+$/gm, '').replace(/\n{3,}/g, '\n\n').trim();
}

const BLOCK_TAGS = new Set([
	'P', 'DIV', 'H1', 'H2', 'H3', 'H4', 'H5', 'H6',
	'UL', 'OL', 'BLOCKQUOTE', 'PRE', 'HR', 'TABLE', 'SECTION', 'ARTICLE', 'FIGURE',
]);

function serializeBlocks(node) {
	const out = [];
	let inline = [];

	const flush = () => {
		if (inline.length === 0) return;
		const text = paragraph(inlineFrom(inline));
		if (text) out.push(text);
		inline = [];
	};

	for (const child of children(node)) {
		// A block *inside* an inline element is still a block. WebKit wraps a
		// copied selection in one span carrying the computed style of everything
		// in it, so a paste from Apple Notes arrives as
		// `<span style="font-weight: 700"><div>…</div><div>…</div></span>` —
		// and reading that span as inline flattened a whole note into one
		// paragraph and made every word of it bold.
		if (child.nodeType === 1 && (BLOCK_TAGS.has(child.nodeName) || holdsBlock(child))) {
			flush();
			const block = serializeBlock(child);
			if (block) out.push(block);
		} else {
			inline.push(child);
		}
	}
	flush();

	return out.join('\n\n');
}

function serializeBlock(element) {
	switch (element.nodeName) {
		case 'H1':
		case 'H2':
		case 'H3':
		case 'H4':
		case 'H5':
		case 'H6': {
			const text = inlineFrom(children(element)).replace(/\n+/g, ' ').trim();
			if (!text) return '';
			return '#'.repeat(Number(element.nodeName[1])) + ' ' + text;
		}
		case 'HR':
			return '---';
		case 'PRE': {
			const body = element.textContent.replace(/\n$/, '');
			const language = languageOf(element);
			// A fence longer than any run of backticks inside, or a note about
			// Markdown closes its own code block.
			const longest = Math.max(2, ...[...body.matchAll(/`+/g)].map((match) => match[0].length));
			const fence = '`'.repeat(longest + 1);
			return fence + language + '\n' + body + '\n' + fence;
		}
		case 'BLOCKQUOTE': {
			const inner = serializeBlocks(element).trim();
			if (!inner) return '';
			return inner.split('\n').map((line) => (line ? '> ' + line : '>')).join('\n');
		}
		case 'UL':
		case 'OL':
			return serializeList(element);
		case 'TABLE':
			return serializeTable(element);
		case 'DIV':
		case 'SECTION':
		case 'ARTICLE':
		case 'FIGURE':
			// A browser's line wrapper, or a real container. Both are handled by
			// asking what is inside.
			return hasBlockChild(element) ? serializeBlocks(element) : paragraph(inlineFrom(children(element)));
		default:
			// Anything else that reached this function is here because it holds
			// blocks — a paste wrapper, most often. Its own tag means nothing;
			// what it contains means everything.
			return holdsBlock(element) ? serializeBlocks(element) : paragraph(inlineFrom(children(element)));
	}
}

function serializeList(list, depth = 0) {
	const ordered = list.nodeName === 'OL';
	const start = Number.parseInt(list.getAttribute('start') ?? '', 10);
	let number = Number.isFinite(start) && start > 0 ? start : 1;
	const out = [];

	// Two columns per level, matching what the parser takes back apart.
	const indent = ' '.repeat(CONTINUATION);
	const shift = (block) => block.split('\n').map((line) => (line ? indent + line : '')).join('\n');

	for (const item of children(list)) {
		if (item.nodeType !== 1) continue;
		if (item.nodeName === 'UL' || item.nodeName === 'OL') {
			// A list as a *sibling* of the items rather than inside one. Several
			// engines produce this when Tab indents a bullet, and skipping it
			// would silently drop everything the person nested.
			const nested = shift(serializeList(item, depth + 1));
			if (out.length > 0) out[out.length - 1] += '\n' + nested;
			else out.push(nested);
			continue;
		}
		if (item.nodeName !== 'LI') continue;

		const checkbox = firstCheckbox(item);
		const marker = ordered ? number++ + '.' : '-';
		const box = checkbox ? (checkbox.getAttribute('checked') === null ? '[ ] ' : '[x] ') : '';

		// The item's own text, then whatever blocks hang under it.
		const leading = [];
		const blocks = [];
		for (const child of children(item)) {
			if (child === checkbox) continue;
			if (child.nodeType === 1 && BLOCK_TAGS.has(child.nodeName)) blocks.push(child);
			else if (blocks.length === 0) leading.push(child);
			// Inline content after a nested list is rare and reads as part of it.
			else blocks.push(child);
		}

		// An item whose text the browser wrapped in a div or a p: that is the
		// item's own line, not a block underneath it.
		if (leading.length === 0 && blocks.length > 0 && (blocks[0].nodeName === 'DIV' || blocks[0].nodeName === 'P')) {
			if (!hasBlockChild(blocks[0])) leading.push(...children(blocks.shift()));
		}

		const head = paragraph(inlineFrom(leading));
		const rest = blocks
			.map((child) =>
				child.nodeType === 1 && (child.nodeName === 'UL' || child.nodeName === 'OL')
					? serializeList(child, depth + 1)
					: serializeBlock(child),
			)
			.filter(Boolean);

		const first = marker + ' ' + box + head.split('\n').join('\n' + indent);
		out.push([first, ...rest.map(shift)].join('\n'));
	}

	return out.join('\n');
}

function serializeTable(table) {
	const rows = [];
	const walk = (node) => {
		for (const child of children(node)) {
			if (child.nodeType !== 1) continue;
			if (child.nodeName === 'TR') rows.push(child);
			else walk(child);
		}
	};
	walk(table);
	if (rows.length === 0) return '';

	const cells = rows.map((row) =>
		children(row)
			.filter((cell) => cell.nodeType === 1 && (cell.nodeName === 'TD' || cell.nodeName === 'TH'))
			.map((cell) => inlineFrom(children(cell)).replace(/\n+/g, ' ').replace(/\|/g, '\\|').trim()),
	);
	const width = Math.max(...cells.map((row) => row.length));
	const line = (row) => '| ' + Array.from({ length: width }, (_, i) => row[i] ?? '').join(' | ') + ' |';

	// A header row is required by the syntax: a table whose first row is data
	// would otherwise lose that row entirely.
	return [line(cells[0]), '|' + ' --- |'.repeat(width), ...cells.slice(1).map(line)].join('\n');
}

function inlineFrom(nodes) {
	return nodes.map(inlineNode).join('');
}

function inlineNode(node) {
	if (node.nodeType === 3) return escapeText(node.textContent);
	if (node.nodeType !== 1) return '';

	switch (node.nodeName) {
		case 'BR':
			return '\n';
		case 'IMG':
			// No note here has an image; one arriving by paste says so rather
			// than vanishing.
			return node.getAttribute('alt') ? '[' + escapeText(node.getAttribute('alt')) + ']' : '';
		case 'INPUT':
			// Only ever a task checkbox, and `serializeList` has already read it.
			return '';
		case 'CODE': {
			const body = node.textContent;
			if (!body) return '';
			const longest = Math.max(0, ...[...body.matchAll(/`+/g)].map((match) => match[0].length));
			const fence = '`'.repeat(longest + 1);
			const pad = body.startsWith('`') || body.endsWith('`') ? ' ' : '';
			return fence + pad + body + pad + fence;
		}
		case 'A': {
			const label = inlineFrom(children(node));
			const href = (node.getAttribute('href') ?? '').trim();
			if (!href) return label;
			if (!label.trim()) return href;
			return '[' + label + '](' + href + ')';
		}
		case 'STRONG':
		case 'B':
			return emphasise(inlineFrom(children(node)), '**');
		case 'EM':
		case 'I':
			return emphasise(inlineFrom(children(node)), '_');
		case 'DEL':
		case 'S':
		case 'STRIKE':
			return emphasise(inlineFrom(children(node)), '~~');
		case 'SPAN':
		case 'FONT': {
			// What a paste leaves behind. The tag says nothing; the style might
			// — but only for a span wrapping one run of text. A span with
			// elements inside it is a container carrying inherited style, not
			// emphasis: WebKit hangs the whole computed style of a copied
			// selection on such a wrapper, and honouring its `font-weight: 700`
			// is what made an entire pasted note bold.
			const inner = inlineFrom(children(node));
			if (!isTextOnly(node)) return inner;
			const style = node.getAttribute('style') ?? '';
			if (/font-weight:\s*(bold|[6-9]00)/i.test(style)) return emphasise(inner, '**');
			if (/font-style:\s*italic/i.test(style)) return emphasise(inner, '_');
			return inner;
		}
		default:
			return inlineFrom(children(node));
	}
}

/** Markers hug their text: `** bold **` is four literal stars, not emphasis. */
function emphasise(inner, marker) {
	const parts = /^(\s*)([\s\S]*?)(\s*)$/.exec(inner);
	if (!parts[2]) return inner;
	// Already carrying the same marker (nested `<b><b>`, or a paste): once is enough.
	if (parts[2].startsWith(marker) && parts[2].endsWith(marker)) return inner;
	return parts[1] + marker + parts[2] + marker + parts[3];
}

/**
 * A run of inline content as one paragraph.
 *
 * Line starts are escaped here rather than in `escapeText`, because whether a
 * `-` opens a list depends on where in the line it sits.
 */
function paragraph(text) {
	return text
		.split('\n')
		.map((line) =>
			line
				.replace(/^(\s*)([#>]|[-*+](?=\s))/, '$1\\$2')
				// The backslash goes before the dot, never before the digit: a
				// backslash in front of anything but punctuation is a literal
				// backslash, and `\1.` would be written into the file as it looks.
				.replace(/^(\s*\d{1,9})([.)](?=\s))/, '$1\\$2'),
		)
		.join('\n')
		.replace(/^\n+|\n+$/g, '');
}

function escapeText(value) {
	return String(value)
		.replace(/\\/g, '\\\\')
		.replace(/([`*[\]])/g, '\\$1')
		// Only where it could be read as emphasis: `snake_case` stays readable.
		.replace(/(^|[^\w_])_/g, '$1\\_')
		.replace(/_($|[^\w_])/g, '\\_$1')
		.replace(/~~/g, '\\~\\~')
		// A lone `<` only matters when it could open a tag.
		.replace(/<(?=[a-zA-Z/!])/g, '\\<');
}

function languageOf(pre) {
	for (const child of children(pre)) {
		if (child.nodeType === 1 && child.nodeName === 'CODE') {
			const match = /language-([A-Za-z0-9_+#-]+)/.exec(child.getAttribute('class') ?? '');
			if (match) return match[1];
		}
	}
	return '';
}

function firstCheckbox(item) {
	for (const child of children(item)) {
		if (child.nodeType === 1 && child.nodeName === 'INPUT' && child.getAttribute('type') === 'checkbox') return child;
	}
	return undefined;
}

function hasBlockChild(element) {
	return children(element).some((child) => child.nodeType === 1 && BLOCK_TAGS.has(child.nodeName));
}

/**
 * Whether a block hides anywhere under this element.
 *
 * Pastes nest wrappers several deep — `<span><span><div>` — so the answer has
 * to be looked for rather than checked one level down. Bounded, because the
 * tree comes from a clipboard and nothing here should be able to hang on one.
 */
function holdsBlock(element, depth = 0) {
	if (depth > 6) return false;
	return children(element).some(
		(child) =>
			child.nodeType === 1 && (BLOCK_TAGS.has(child.nodeName) || child.nodeName === 'LI' || holdsBlock(child, depth + 1)),
	);
}

/** A span with nothing but text in it — the only shape whose style is emphasis. */
function isTextOnly(element) {
	return children(element).every((child) => child.nodeType === 3 || child.nodeName === 'BR');
}

function children(node) {
	return Array.prototype.slice.call(node.childNodes ?? []);
}