feat: add remark plugin to strip emojis

[mnkiefer]

• Introduces a new custom remark plugin by stripping emojis from text, code blocks, image metadata, etc. to ensure a more professional appearance.

[Copilot]

Pull request overview

This PR introduces a custom remark plugin to strip emoji characters from rendered documentation, aiming for a more professional appearance. The plugin recursively traverses the markdown AST and removes emojis from text nodes, code blocks, image/link metadata, and MDX JSX attributes.

Changes:

• Added a new remark plugin at docs/src/lib/remark/stripEmojis.js that implements tree traversal and emoji stripping logic
• Integrated the plugin into the Astro markdown pipeline via astro.config.mjs

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File	Description
docs/src/lib/remark/stripEmojis.js	New remark plugin that recursively visits AST nodes and strips emojis using a replacement map and Unicode property escapes
docs/astro.config.mjs	Registers the stripEmojis plugin in the markdown.remarkPlugins configuration array

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Stripping emojis from code blocks and inline code could break code examples that intentionally include emoji characters. For example, string literals, test cases, or documentation examples that demonstrate emoji handling would be modified. Consider whether code should be excluded from emoji stripping to preserve code examples as written.

[Copilot]

The string replacement approach using split().join() is inefficient for multiple replacements on the same string. Each replacement iterates through the entire string, resulting in O(n*m) complexity where n is string length and m is number of replacements. Consider using a single pass with a regex combining all patterns, or use replaceAll() which is more efficient and clearer in intent.

Suggested change

	* @param {string} input
	*/
	function stripEmojis(input) {
	let output = input;
	for (const [from, to] of replacements.entries()) {
	if (output.includes(from)) output = output.split(from).join(to);
	}
	* Escape special characters in a string for use in a RegExp.
	* @param {string} value
	* @returns {string}
	*/
	function escapeRegex(value) {
	return value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
	}
	// Build a single regex that matches any of the replacement keys.
	const replacementPattern = Array.from(replacements.keys())
	.sort((a, b) => b.length - a.length) // longer first to prefer longer matches
	.map((key) => escapeRegex(key))
	.join('|');
	const replacementsRegex = new RegExp(replacementPattern, 'gu');
	/**
	* @param {string} input
	*/
	function stripEmojis(input) {
	let output = input.replace(
	replacementsRegex,
	(match) => replacements.get(match) ?? match,
	);

[Copilot]

The transform function should return the tree after modifications. While remark plugins that mutate the tree in-place may work without an explicit return, it's a best practice to return the tree to follow the unified plugin specification and ensure compatibility with the remark ecosystem. Add return tree; after the visit call.

Suggested change

	visit(tree);
	visit(tree);
	return tree;