From 34e5e25bfb341d5dd1b6d23dd1874f0198c5f95d Mon Sep 17 00:00:00 2001
From: Russell Ballestrini <russell.ballestrini@gmail.com>
Date: Sat, 12 Jul 2025 11:13:40 -0400
Subject: [PATCH] replace URL constructor with regex validation for remote URLs

- URL constructor was too strict and failing on valid domains
- new regex pattern validates common URL formats more permissively
- ensures scheme prepending works in both main logic and fetchRemotePageHTML
- fixes issues with domains like www.inrupt.com
---
 src/translate-modal.js | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/translate-modal.js b/src/translate-modal.js
index 9551047..786bcb0 100644
--- a/src/translate-modal.js
+++ b/src/translate-modal.js
@@ -13,12 +13,10 @@ async function fetchRemotePageHTML(url) {
 			normalizedUrl = 'https://' + normalizedUrl;
 		}
 		
-		// Validate URL format
-		let targetUrl;
-		try {
-			targetUrl = new URL(normalizedUrl);
-		} catch (urlError) {
-			throw new Error(`Invalid URL format: ${normalizedUrl}`);
+		// Validate URL format using regex - more permissive than URL constructor
+		const urlPattern = /^https?:\/\/[a-zA-Z0-9]([a-zA-Z0-9-]*[a-zA-Z0-9])?(\.[a-zA-Z0-9]([a-zA-Z0-9-]*[a-zA-Z0-9])?)*(\.[a-zA-Z]{2,})(:\d+)?(\/[^\s]*)?$/;
+		if (!urlPattern.test(normalizedUrl)) {
+			throw new Error(`Please enter a valid website URL (e.g., example.com or https://example.com)`);
 		}
 		
 		// Use our CORS proxy at cors-proxy.uncloseai.com with query parameter
@@ -331,6 +329,10 @@ export function openTranslateModal() {
 				if (!remoteUrl) {
 					throw new Error("Please enter a URL to translate");
 				}
+				// Auto-add https:// if no scheme is provided
+				if (!remoteUrl.startsWith('http://') && !remoteUrl.startsWith('https://')) {
+					remoteUrl = 'https://' + remoteUrl;
+				}
 				// Fetch full HTML content from remote URL
 				rawContent = await fetchRemotePageHTML(remoteUrl);
 			}