From f16376c9fa7b51c71bc7752e85e3d001adc244e2 Mon Sep 17 00:00:00 2001
From: Juhani Krekelä
Date: Mon, 26 Jul 2021 19:52:13 +0300
Subject: Don't consider punctuation as part of the URL

We currently consider periods, commas, colons, semicolons, exclamation
points and question marks following a URL as part of it. While ending a
URL with these characters is technically speaking valid, more commonly
they are a result of people ending a clause with a URL. Let's ignore
such characters if they are present at the very end of a URL.

Make sure to still match them, however, if any non-punctuation
characters follow. This way, almost all actual usage of punctuation
within URLs is unaffected.
---
 terminal.vala | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/terminal.vala b/terminal.vala
index c392d7f..47c33bc 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|gopher):\/\/[^[:punct:][:space:]](?>[^][)(><"“”[:space:]]+|\([^)([:space:]]*\)|"[^"[:space:]]*")+""";
+	const string URL_REGEX = """(?>https?|ftp|gopher):\/\/[^[: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