# HG changeset patch
# User Henry S. Thompson <ht@markup.co.uk>
# Date 1539959119 0
# Node ID 9631fca89cc6ab420916e03b88b8a20fb0447046
# Parent  2a2c1fb03c5496185a41603ecfb55715f36bfb26
F2-related stuff, and new experiment

diff -r 2a2c1fb03c54 -r 9631fca89cc6 workers/bin/_timedWhich.sh
--- a/workers/bin/_timedWhich.sh	Fri Oct 19 11:36:31 2018 +0000
+++ b/workers/bin/_timedWhich.sh	Fri Oct 19 14:25:19 2018 +0000
@@ -1,5 +1,5 @@
 #!/bin/bash
-egrep -o'("WARC-Target-URI":"https?:|"Last-Modified":"[^"]*")'|\
+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/'|\
diff -r 2a2c1fb03c54 -r 9631fca89cc6 workers/bin/installInTemplate.sh
--- a/workers/bin/installInTemplate.sh	Fri Oct 19 11:36:31 2018 +0000
+++ b/workers/bin/installInTemplate.sh	Fri Oct 19 14:25:19 2018 +0000
@@ -7,5 +7,8 @@
 sudo apt-get -y update
 sudo apt-get -y install azure-cli
 sudo adduser --disabled-password -GECOS "CC master" cc
-sudo su -c 'ssh-keygen -t rsa -N "" -f /home/cc/.ssh/id_rsa' cc
+if [ ! -d ~cc/.ssh ]
+then
+ sudo su -c 'ssh-keygen -t rsa -N "" -f /home/cc/.ssh/id_rsa' cc
+fi
 sudo cat ~cc/.ssh/id_rsa.pub
diff -r 2a2c1fb03c54 -r 9631fca89cc6 workers/bin/timedWhich.sh
--- a/workers/bin/timedWhich.sh	Fri Oct 19 11:36:31 2018 +0000
+++ b/workers/bin/timedWhich.sh	Fri Oct 19 14:25:19 2018 +0000
@@ -42,8 +42,8 @@
   ln -s ../nohup.cc .
   tar -czhf - CC* $res | \
    ssh -o StrictHostKeyChecking=no -q $home \"{ cd data
-                    mkdir -p pdf/wat
-                    cd pdf/wat
+                    mkdir -p which
+                    cd which
                     tar -xzf - ; } 2>>errs\"
   rm -rf $res CC* ifile.txt *.pid
   ( sleep 5 ; rm nohup.cc ) &