From cc145132da5ed17bee1436403802e9a046f319bb Mon Sep 17 00:00:00 2001
From: Mehdi Rejraji <mehdi.rejraji@gmail.com>
Date: Thu, 3 Mar 2016 15:30:24 +0100
Subject: [PATCH] Updated Regex to exclude mailto: links only

The rationale being it's covering all of the cases while still having a good performance.
Tracking a non-standard URL is not a user experience problem in a way. It's embedded in a <a href> tag.
---
 src/regexp-utils.coffee | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/regexp-utils.coffee b/src/regexp-utils.coffee
index f7456d446..cc4ad4c3a 100644
--- a/src/regexp-utils.coffee
+++ b/src/regexp-utils.coffee
@@ -34,15 +34,17 @@ RegExpUtils =
   # 5. the closing tag
   linkTagRegex: -> new RegExp(/(<a.*?href\s*?=\s*?['"])(.*?)(['"].*?>)([\s\S]*?)(<\/a>)/gim)
 
-  # Test cases: https://regex101.com/r/cK0zD8/2
-  # Catches link tags containing a valid URL using the Gruber Regex.
+  # Test cases: https://regex101.com/r/cK0zD8/3
+  # Catches link tags containing which are:
+  # - Non empty
+  # - Not a mailto: link
   # Returns the following capturing groups:
   # 1. start of the opening a tag to href="
-  # 2. The contents of the href without quotes if it's a valid URL
+  # 2. The contents of the href without quotes
   # 3. the rest of the opening a tag
   # 4. the contents of the a tag
   # 5. the closing tag
-  urlLinkTagRegex: -> new RegExp(/(<a.*?href\s*?=\s*?['"])((?:https?:\/\/|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}\/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’]))(['"].*?>)([\s\S]*?)(<\/a>)/gim)
+  urlLinkTagRegex: -> new RegExp(/(<a.*?href\s*?=\s*?['"])((?!mailto).+)(['"].*?>)([\s\S]*?)(<\/a>)/gim)
 
   # https://regex101.com/r/zG7aW4/3
   imageTagRegex: -> /<img\s+[^>]*src="([^"]*)"[^>]*>/g