Properly decode unicode

- properly decode unicode charsets
cyntler · Jun 17, 2024 · 94df695 · 94df695
1 parent d422aac
commit 94df695
Showing 1 changed file with 17 additions and 2 deletions.
diff --git a/src/renderers/html/index.tsx b/src/renderers/html/index.tsx
@@ -6,9 +6,24 @@ import { dataURLFileLoader } from "../../utils/fileLoaders";
 const HTMLRenderer: DocRenderer = ({ mainState: { currentDocument } }) => {
  useEffect(() => {
  const b64String = currentDocument?.fileData as string;
+
+ let encoding = "";
  const bodyBase64 =
- b64String?.replace(/^data:text\/html;([^;]*?;)?base64,/, "") || "";
- const body: string = window.atob(bodyBase64);
+ b64String?.replace(
+ /^data:text\/html;(?:charset=([^;]*);)?base64,/,
+ (_, charset) => {
+ encoding = charset;
+ return "";
+ },
+ ) || "";
+ let body: string = window.atob(bodyBase64);
+
+ if (encoding) {
+ // decode charset
+ const buffer = new Uint8Array(body.length);
+ for (let i = 0; i < body.length; i++) buffer[i] = body.charCodeAt(i);
+ body = new TextDecoder(encoding).decode(buffer);
+ }
 
  const iframeCont = document.getElementById(
  "html-body",