/** * -------------------------------------------------------------------------- * Bootstrap util/sanitizer.js * Licensed under MIT (https://github.com/twbs/bootstrap/blob/main/LICENSE) * -------------------------------------------------------------------------- */ // js-docs-start allow-list const ARIA_ATTRIBUTE_PATTERN = /^aria-[\w-]*$/i export const DefaultAllowlist = { // Global attributes allowed on any supplied element below. '*': ['class', 'dir', 'id', 'lang', 'role', ARIA_ATTRIBUTE_PATTERN], a: ['target', 'href', 'title', 'rel'], area: [], b: [], br: [], col: [], code: [], div: [], em: [], hr: [], h1: [], h2: [], h3: [], h4: [], h5: [], h6: [], i: [], img: ['src', 'srcset', 'alt', 'title', 'width', 'height'], li: [], ol: [], p: [], pre: [], s: [], small: [], span: [], sub: [], sup: [], strong: [], u: [], ul: [] } // js-docs-end allow-list const uriAttributes = new Set([ 'background', 'cite', 'href', 'itemtype', 'longdesc', 'poster', 'src', 'xlink:href' ]) /** * A pattern that recognizes URLs that are safe wrt. XSS in URL navigation * contexts. * * Shout-out to Angular https://github.com/angular/angular/blob/15.2.8/packages/core/src/sanitization/url_sanitizer.ts#L38 */ // eslint-disable-next-line unicorn/better-regex const SAFE_URL_PATTERN = /^(?!javascript:)(?:[a-z0-9+.-]+:|[^&:/?#]*(?:[/?#]|$))/i const allowedAttribute = (attribute, allowedAttributeList) => { const attributeName = attribute.nodeName.toLowerCase() if (allowedAttributeList.includes(attributeName)) { if (uriAttributes.has(attributeName)) { return Boolean(SAFE_URL_PATTERN.test(attribute.nodeValue)) } return true } // Check if a regular expression validates the attribute. return allowedAttributeList.filter(attributeRegex => attributeRegex instanceof RegExp) .some(regex => regex.test(attributeName)) } export function sanitizeHtml(unsafeHtml, allowList, sanitizeFunction) { if (!unsafeHtml.length) { return unsafeHtml } if (sanitizeFunction && typeof sanitizeFunction === 'function') { return sanitizeFunction(unsafeHtml) } const domParser = new window.DOMParser() const createdDocument = domParser.parseFromString(unsafeHtml, 'text/html') const elements = [].concat(...createdDocument.body.querySelectorAll('*')) for (const element of elements) { const elementName = element.nodeName.toLowerCase() if (!Object.keys(allowList).includes(elementName)) { element.remove() continue } const attributeList = [].concat(...element.attributes) const allowedAttributes = [].concat(allowList['*'] || [], allowList[elementName] || []) for (const attribute of attributeList) { if (!allowedAttribute(attribute, allowedAttributes)) { element.removeAttribute(attribute.nodeName) } } } return createdDocument.body.innerHTML }