From 608e267413cf7f8399cacbbfc4269d3c3820a3aa Mon Sep 17 00:00:00 2001
From: =?utf8?q?Paul=20H=C3=A4nsch?= <paul@plutz.net>
Date: Wed, 29 Jan 2020 18:32:26 +0100
Subject: [PATCH] altered groupmatch algorithm

---
 list.sh | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/list.sh b/list.sh
index b941aa7..a4bdbc7 100644
--- a/list.sh
+++ b/list.sh
@@ -88,15 +88,18 @@ list_filter(){
 }
 
 groupmatch(){
-  if [ ${#1} -gt ${#2} ]; then
-    long="$1" short="$2"
-  else
-    long="$2" short="$1"
-  fi
+  a="${1%$CR}" b="${2%$CR}"
+#  if [ ${#a} -gt ${#b} ]; then
+#    long="$a" short="$b"
+#  else
+#    long="$b" short="$a"
+#  fi
   # com="$(expr substr "$long" 1 $((${#long} * 3 / 4)))"
-  com="$(expr substr "$long" 1 $((${#long} - 3)))"
-  cut="${short#$com}"
-  if [ ${#cut} -lt ${#short} ]; then
+  # com="$(expr substr "$long" 1 $((${#long} - 3)))"
+  ## Cut off youtube- and other site suffixes. Cut of last three characters
+  com="$(printf %s "$a" |sed -E 's;-([0-9a-zA-Z_-]{11}|ph[0-9a-f]{13}|[0-9]{8})$;;; s;...$;;;')"
+  cut="${b#$com}"
+  if [ "${cut}" != "${b}" ]; then
     return 0
   else
     return 1
-- 
2.39.2