From a44debdcfe0a01e2a48362b7d34848a57a5e976c Mon Sep 17 00:00:00 2001
From: Richard Hansen <rhansen@rhansen.org>
Date: Sat, 12 Dec 2020 18:26:48 -0500
Subject: [PATCH] Add `'` and `*` to acceptable URL characters

These characters are in the RFC3986 reserved set.

These characters are added to the set of characters that cannot be the
last character of a URL to avoid mislinkification.
---
 src/static/js/pad_utils.js                    | 4 ++--
 tests/frontend/specs/urls_become_clickable.js | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/static/js/pad_utils.js b/src/static/js/pad_utils.js
index ccd0d6771..f428da157 100644
--- a/src/static/js/pad_utils.js
+++ b/src/static/js/pad_utils.js
@@ -60,10 +60,10 @@ const wordCharRegex = new RegExp(`[${[
 const urlRegex = (() => {
   // TODO: wordCharRegex matches many characters that are not permitted in URIs. Are they included
   // here as an attempt to support IRIs? (See https://tools.ietf.org/html/rfc3987.)
-  const urlChar = `[-:@_.,~%+/?=&#!;()$${wordCharRegex.source.slice(1, -1)}]`;
+  const urlChar = `[-:@_.,~%+/?=&#!;()$'*${wordCharRegex.source.slice(1, -1)}]`;
   // Matches a single character that should not be considered part of the URL if it is the last
   // character that matches urlChar.
-  const postUrlPunct = '[:.,;?!)]';
+  const postUrlPunct = '[:.,;?!)\'*]';
   // Schemes that must be followed by ://
   const withAuth = `(?:${[
     '(?:x-)?man',
diff --git a/tests/frontend/specs/urls_become_clickable.js b/tests/frontend/specs/urls_become_clickable.js
index c4b28fd4e..a027de9ff 100644
--- a/tests/frontend/specs/urls_become_clickable.js
+++ b/tests/frontend/specs/urls_become_clickable.js
@@ -31,7 +31,7 @@ describe('urls', function () {
   });
 
   describe('special characters inside URL', function () {
-    for (const char of '-:@_.,~%+/?=&#!;()$') {
+    for (const char of '-:@_.,~%+/?=&#!;()$\'*') {
       const url = `https://etherpad.org/${char}foo`;
       it(url, async function () {
         await helper.edit(url);
@@ -44,7 +44,7 @@ describe('urls', function () {
   });
 
   describe('punctuation after URL is ignored', function () {
-    for (const char of ':.,;?!)]') {
+    for (const char of ':.,;?!)\'*]') {
       const want = 'https://etherpad.org';
       const input = want + char;
       it(input, async function () {