From 59767124ed7768c82621c414549d24d33096b16e Mon Sep 17 00:00:00 2001
From: Juhani Krekelä
Date: Thu, 8 Jul 2021 09:14:41 +0300
Subject: Improve URL matching

Currently the weltschmerz URL regex does not match URLs with quotes or
parentheses, considering the URL to end when one is encountered. On the
other hand, if a URL is surrounded by angle brackets it includes the
closing '>' in the URL match. Additionally, the regex allows URL to
contain a space if and only if it is the second character of the host
component of the URL.

Most of this appears to be down to bugs in the regex as it is currently
written. This rewrites the regex to be cleaner and easier to read, while
maintaining the intended logic of the original.
---
 terminal.vala | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/terminal.vala b/terminal.vala
index 86f086f..b2a610f 100644
--- a/terminal.vala
+++ b/terminal.vala
@@ -1,6 +1,6 @@
 [GtkTemplate (ui = "/weltschmerz/ui/terminal.ui")]
 class Terminal : Gtk.Overlay {
-	const string URL_REGEX = """(?>https?|ftp):\/\/[^\s\$.?#].(?>[^\s()"]*|\([^\s]*\)|"[^\s"]*")""";
+	const string URL_REGEX = """(?>https?|ftp):\/\/[^[:punct:][:space:]](?>[^][)(><"“”[:space:]]+|\([^)([:space:]]*\)|"[^"[:space:]]*")+""";
 	const uint PCRE2_CASELESS  = 0x00000008u;
 	const uint PCRE2_MULTILINE = 0x00000400u;
 	const uint PCRE2_NO_UTF_CHECK = 0x00080000u;
-- 
cgit v1.2.3-2-gb3c3