# HG changeset patch
# User Henry S. Thompson <ht@markup.co.uk>
# Date 1540051889 0
# Node ID d4f186655bcc0ec492a0f3923a9b85f0892519b0
# Parent  9631fca89cc6ab420916e03b88b8a20fb0447046
lots of tweaking, reached the 80/20 point

diff -r 9631fca89cc6 -r d4f186655bcc workers/bin/_timedWhich.sh
--- a/workers/bin/_timedWhich.sh	Fri Oct 19 14:25:19 2018 +0000
+++ b/workers/bin/_timedWhich.sh	Sat Oct 20 16:11:29 2018 +0000
@@ -2,6 +2,6 @@
 egrep -o '("WARC-Target-URI":"https?:|"Last-Modified":"[^"]*")'|\
  egrep -o '(https?:|:".*"$)' |\
  tr '\012' \# | sed 's/:#:/ /g'|tr \# '\012' | tr -d \"|\
- sed 's/ [[:digit:]][[:digit:]]\?:[[:digit:]][[:digit:]]:[[:digit:]][[:digit:]] / /;s/\(https\? \)\(: \)\?[MTWFSa-z]..\.\?, \?/\1/;s/ \([-+][[:digit:]]\{4\}\|[[:upper:]]\{2,3\}\)$//;s/ [[:digit:]]\{1,2\} / /;s/\/[[:digit:]]\{1,2\}\/\([[:digit:]]\{4\}\)$/ \1/'|\
+sed ';s/gmt//ig;s/ [[:digit:]][[:digit:]]\?:[[:digit:]][[:digit:]]:[[:digit:]][[:digit:]]\(\.[[:digit:]]*\)\?\b//;s/^\(https\? \)\(: \)/\1/;s/ [MTWFSa-z]..\.\?, \?/ /;s/\( [[:upper:]][[:alnum:]]\{1,3\}\)\{1,2\}$//;s/ [-+][[:digit:]]\{4\}\b//;s/ [[:digit:]]\{1,2\} / /;s/ [[:upper:]][[:alnum:]]*\/[[:upper:]][[:alnum:]]*$//;s/ \+$//'|\
 awk '{c[$0]+=1} END {for (k in c) {print k, c[k]}}'