From ea225eac1b0e3d2b85e092b8ea457031efcd5ee4 Mon Sep 17 00:00:00 2001
From: Ian Jackson <ijackson@chiark.greenend.org.uk>
Date: Mon, 9 Sep 2013 12:36:33 +0100
Subject: [PATCH] fix regexp not to loop stupidly: 1. the regexp was too loose
 and matched /in/ not just /\bin\b/. 2. chiark.peer.fu-berlin.de consists
 mostly of stopwords by this rule 3. A bug meant that when it got to the end,
 it didn't stop, but always ate the TLD as if it were a stopword.

---
 cgi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cgi b/cgi
index b9acb94..968745e 100755
--- a/cgi
+++ b/cgi
@@ -203,7 +203,7 @@ foreach my $site (keys %news_sources) {
     my $sk= $site;
     for (;;) {
         last unless $sk =~
-            s/^[^.]*(?:chiark|greenend|news|nntp|peer|feed|in|out)[^.]*\.//;
+  s/^[^. ]*\b(?:chiark|greenend|news|nntp|peer|feed|in|out)\b[^.]*\.//;
         $sk .= " $&";
     }
     foreach my $inout (keys %{ $news_sources{$site} }) {
-- 
2.30.2