From 2023623b1640533da1d8d0178d42c92d1c12532c Mon Sep 17 00:00:00 2001
From: Yuri D'Elia <yuri.delia@eurac.edu>
Date: Thu, 6 Mar 2014 18:05:22 +0100
Subject: [PATCH] Fix URL matching regex

The URL matching regex as currently used by dust is too liberal, and will just
match about anything.

Some examples:

  "establishing connection..." => connection...
  "setting volume to [50%]" => 50%]

The following expression is an adapted copy of urxvt's URL matcher.
---
 menu.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/menu.c b/menu.c
index 12e1ae2..90b7095 100644
--- a/menu.c
+++ b/menu.c
@@ -28,7 +28,9 @@ char *extract_urls(const char *to_match)
 
         if (!is_initialized) {
                 char *regex =
-                    "((http[s]?|ftp[s]?)(://))?(www\\.)?[[:alnum:]._-]+\\.[^[:space:].\"<>]{2,}";
+                    "\\b(https?://|ftps?://|news://|mailto:|file://|www\\.)"
+                    "[[:alnum:]\\-\\@;/?:&=%$.+!*\x27,~#]*"
+                    "(\\([[:alnum:]\\-\\@;/?:&=%$.+!*\x27,~#]*\\)|[[:alnum:]\\-\\@;/?:&=%$+*~])+";
                 int ret = regcomp(&cregex, regex, REG_EXTENDED | REG_ICASE);
                 if (ret != 0) {
                         printf("failed to compile regex\n");