/**
* The HTML sanitizer of the storefront: one implementation for the server and the browser, and for every runtime the
* template is deployed to (Node, Vercel, Cloudflare Workers).
*
* Why not `isomorphic-dompurify`: on the server it loads jsdom, and jsdom reads `/browser/default-stylesheet.css` from
* the file system when it loads. A Worker has no such file, so every page that sanitised merchant HTML answered 500.
* DOMPurify with linkedom was tried and REJECTED: DOMPurify detects the unsupported DOM and returns its input
* UNSANITISED (script, onerror and javascript: all survived), without an error. Never put DOMPurify on a DOM that is not
* a full browser DOM.
*
* This module has no DOM dependency (htmlparser2 underneath), so server HTML equals client HTML (no hydration mismatch).
*
* The allow-lists are the ones the previous DOMPurify configuration had; `scripts/check-sanitizer.mjs` (run on every
* publish of the CLI) feeds an XSS corpus through both entry points and fails if anything dangerous survives.
*/
import sanitizeHtmlLib from 'sanitize-html';
/** Embeds the merchant may include. An iframe survives only when its src starts with one of these. */
const TRUSTED_IFRAME_PREFIXES = [
'https://www.youtube.com/embed/',
'https://www.youtube-nocookie.com/embed/',
'https://player.vimeo.com/video/',
];
const PRODUCT_TAGS = [
'p', 'br', 'strong', 'b', 'em', 'i', 'u', 's', 'strike', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
'ul', 'ol', 'li', 'a', 'blockquote', 'code', 'pre', 'div', 'span', 'img', 'table', 'thead',
'tbody', 'tr', 'th', 'td', 'colgroup', 'col', 'iframe', 'video', 'source',
];
// DOMPurify's default tag set plus iframe, which `sanitizeHtml` (rich text, pages, FAQ) allowed.
const CONTENT_TAGS = [
...PRODUCT_TAGS, 'abbr', 'address', 'article', 'aside', 'caption', 'center', 'cite', 'dd', 'del',
'details', 'dfn', 'dl', 'dt', 'figcaption', 'figure', 'footer', 'header', 'hr', 'ins', 'kbd',
'main', 'mark', 'nav', 'q', 'section', 'small', 'sub', 'summary', 'sup', 'tfoot', 'audio',
];
const PRODUCT_ATTRS = [
'href', 'target', 'rel', 'class', 'src', 'alt', 'width', 'height', 'colspan', 'rowspan', 'allow',
'allowfullscreen', 'frameborder', 'loading', 'title', 'controls', 'poster', 'preload', 'muted',
'loop', 'playsinline', 'type',
];
const CONTENT_ATTRS = [...PRODUCT_ATTRS, 'id', 'dir', 'lang', 'scrolling', 'style'];
// Inline styles survive only for these properties and only with plain values: rich text keeps its colours, alignment and
// sizes, while position, url(), expression() and anything else is dropped. Product descriptions get no style attribute.
const COLOR = [/^#[0-9a-f]{3,8}$/i, /^rgba?\([0-9\s,.%]+\)$/i, /^[a-z]{3,20}$/i];
const LENGTH = [/^-?[0-9]{1,4}(\.[0-9]{1,3})?(px|em|rem|%|pt)?$/];
const ALLOWED_STYLES = {
'*': {
color: COLOR,
'background-color': COLOR,
'text-align': [/^(left|right|center|justify|start|end)$/],
direction: [/^(ltr|rtl)$/],
'font-size': LENGTH,
'line-height': LENGTH,
'font-weight': [/^(normal|bold|[1-9]00)$/],
'font-style': [/^(normal|italic)$/],
'text-decoration': [/^(none|underline|line-through)$/],
margin: LENGTH,
'margin-top': LENGTH,
'margin-bottom': LENGTH,
padding: LENGTH,
width: LENGTH,
height: LENGTH,
},
};
function run(html: string, tags: string[], attrs: string[], demoteH1 = false): string {
return sanitizeHtmlLib(html, {
allowedTags: tags,
allowedAttributes: { '*': attrs },
allowedSchemes: ['http', 'https', 'mailto', 'tel'],
allowedSchemesByTag: {
img: ['http', 'https', 'data'],
source: ['http', 'https'],
video: ['http', 'https'],
},
allowedSchemesAppliedToAttributes: ['href', 'src', 'poster'],
allowProtocolRelative: false,
...(attrs.includes('style') ? { allowedStyles: ALLOWED_STYLES } : {}),
exclusiveFilter: (frame) =>
frame.tag === 'iframe' &&
!TRUSTED_IFRAME_PREFIXES.some((prefix) => (frame.attribs.src || '').startsWith(prefix)),
transformTags: {
// A product page already has one H1, the product name. A heading level 1 inside the merchant's description (pasted
// from a word processor or another store) would make a second one, which search engines read as a page without a
// clear title, so a description's H1 becomes an H2. Pages and rich text blocks keep theirs.
...(demoteH1 ? { h1: 'h2' } : {}),
// A link that opens a new tab never gets the opener, and carries nofollow.
a: (tagName, attribs) => ({
tagName,
attribs: attribs.target === '_blank' ? { ...attribs, rel: 'noopener noreferrer nofollow' } : attribs,
}),
// A data: image must be an actual image type. A browser does not run HTML from an
, but there is no reason to
// let `data:text/html` (or anything else) through where only a picture belongs.
img: (tagName, attribs) => {
const src = attribs.src || '';
if (/^\s*data:/i.test(src) && !/^\s*data:image\/(png|jpe?g|gif|webp|avif);base64,/i.test(src)) {
const { src: _dropped, ...rest } = attribs;
return { tagName, attribs: rest };
}
return { tagName, attribs };
},
},
});
}
/** Product descriptions: the tighter list. */
export function sanitizeProduct(html: string): string {
return html ? run(html, PRODUCT_TAGS, PRODUCT_ATTRS, true) : '';
}
/** Rich text blocks, pages, FAQ answers: DOMPurify's default tag set plus iframe. */
export function sanitizeContent(html: string): string {
return html ? run(html, CONTENT_TAGS, CONTENT_ATTRS) : '';
}