changeset 49:b8a88cad75d5

revert cci pattern
author Henry S. Thompson <ht@markup.co.uk>
date Sat, 15 Dec 2018 10:34:14 +0000
parents 3b951980206d
children 44dc512f897e
files workers/bin/ptimedWhich.sh
diffstat 1 files changed, 2 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/workers/bin/ptimedWhich.sh	Mon Dec 10 14:51:52 2018 +0000
+++ b/workers/bin/ptimedWhich.sh	Sat Dec 15 10:34:14 2018 +0000
@@ -66,8 +66,8 @@
 while read s
 do
  url="https://commoncrawl.s3.amazonaws.com/$s"
- # below for 2018-04, for 2017-04 needs $13 instead of $14
- cci=$(echo $s | tr '/-' ' ' | awk '{print $3,$4,$8,$14}' |tr ' ' \-)
+ # below for 2014-04, 2017-04: for 2018-04, needs $14 instead of $13
+ cci=$(echo $s | tr '/-' ' ' | awk '{print $3,$4,$8,$13}' |tr ' ' \-)
  echo $url /var/data/$cci
 done < ifile.txt 2>> $res/errs | \
  parallel --pipe -N$((N / wp)) -j $wp "bash -c \"tryread 2>>$res/errs{#}\"" 2>>$res/errs || pRes=$?