#!/bin/sh -e
# wwwoffle-duplicate-headers -- Investigate headers of articles repeatedly fetched
# Copyright       : http://www.fsf.org/copyleft/gpl.html
# Author          : Dan Jacobson -- http://jidanni.org/comp/wwwoffle/
# Created On      : Fri Jul  4 15:58:16 2003
# Last Modified On: Fri Nov 21 09:24:40 2003
# Update Count    : 9

#Discussion: http://article.gmane.org/gmane.network.wwwoffle.user/297
#Usage: just run this script any time when offline
#Output: repeat count, URL, and HTTP headers by repeat count
if test $# -ne 0; then echo 1>&2 $0: no args allowed; exit 33; fi
cd ${wwwoffle_cache-/var/spool/wwwoffle}
find *time* -name U\* -print|sort -t/ -k2|uniq -t/ -f1 -cd|sort -nr|
while read n u;do echo -e "\n$n: \c";sed : $u;echo
awk '/^\r/{nextfile};{sub("\r","")};1' *time*/D${u#*/U}|sort|uniq -c;done