add support for stripHtml in NodeJS, decode HTML Entities

Author: fquffio

.changeset/funny-carrots-add.md

@@ -0,0 +1,5 @@
+---
+"@chialab/sveltekit-utils": minor
+---
+
+Add support for `stripHtml` in NodeJS, decode HTML Entities.

packages/utils/package.json

@@ -48,11 +48,13 @@
 	"dependencies": {
 		"@heyputer/kv.js": "fquffio/kv.js#fix/strict-mode",
 		"cookie": "^1.0.2",
+		"html-entities": "^2.6.0",
 		"pino": "^9.5.0",
 		"redis": "^4.7.0",
 		"xml-js": "^1.6.11"
 	},
 	"devDependencies": {
+		"@chialab/isomorphic-dom": "workspace:*",
 		"@chialab/sveltekit-dev-utils": "workspace:*",
 		"@sveltejs/adapter-static": "^3.0.6",
 		"@sveltejs/kit": "^2.8.1",

packages/utils/src/lib/utils/browser.ts

@@ -1,13 +1,3 @@
-/**
- * Sanitize HTML string by removing all tags and returning only text content.
- */
-export const sanitizeHtml = (html: string | null | undefined): string => {
-	const div = document.createElement('div');
-	div.innerHTML = html ?? '';
-
-	return div.innerText;
-};
-
 /**
  * Check if is a mobile device.
  */

packages/utils/src/lib/utils/html.ts

@@ -0,0 +1,22 @@
+import { document } from '@chialab/isomorphic-dom';
+import { decode } from 'html-entities';
+
+/**
+ * Strip all HTML tags, attributes and comments and returning only text content.
+ *
+ * @param html The string to strip HTML from.
+ */
+export const stripHtml = (html: string | null | undefined): string => {
+	const element = document.createElement('div');
+	element.innerHTML = html ?? '';
+
+	return decode(element.innerText);
+};
+
+/**
+ * Strip all HTML tags, attributes and comments and returning only text content.
+ *
+ * @deprecated Use `stripHtml` instead. The functionality is identical.
+ * @param html The string to strip HTML from.
+ */
+export const sanitizeHtml = stripHtml;

packages/utils/src/lib/utils/index.ts

@@ -1,6 +1,7 @@
 export * from './browser.js';
 export * from './collections.js';
 export * from './fetch.js';
+export * from './html.js';
 export * from './misc.js';
 export * from './promises.js';
 export * from './string.js';

packages/utils/tests/utils/browser.test.ts renamed to packages/utils/tests/utils/html.test.ts

@@ -1,14 +1,18 @@
-import { sanitizeHtml } from '$lib/utils/browser';
+import { stripHtml } from '$lib/utils/html';
 import { describe, expect, it } from 'vitest';
 
-describe(sanitizeHtml.name, async () => {
+describe(stripHtml.name, async () => {
 	const CASES = {
 		'should remove tag': { html: 'hello <a href="https://example.org/">world</a>', expected: 'hello world' },
+		'should remove comments and HTML entities': {
+			html: '<span lang="it">questo &egrave; un test <!-- This is a test --></span>',
+			expected: 'questo è un test ',
+		},
 	} satisfies Record<string, { html: string | undefined | null; expected: string }>;
 
 	Object.entries(CASES).forEach(([label, { html, expected }]) =>
 		it(label, () => {
-			expect(sanitizeHtml(html)).to.equal(expected);
+			expect(stripHtml(html)).to.equal(expected);
 		}),
 	);
 });

packages/utils/vitest.workspace.ts

@@ -4,7 +4,7 @@ export default defineWorkspace([
 	{
 		extends: './vitest.config.ts',
 		test: {
-			include: ['tests/**/*.{test,spec}.ts', '!tests/**/*.browser.{test,spec}.ts', '!tests/**/browser.{test,spec}.ts'],
+			include: ['tests/**/*.{test,spec}.ts', '!tests/**/*.browser.{test,spec}.ts'],
 			name: 'server',
 			environment: 'node',
 		},