Mercurial > hg > cc > cirrus_home
comparison bin/extract.sh @ 25:a82c325e8b32
(none)
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Wed, 18 Mar 2020 11:08:47 +0000 |
parents | c858a4d4bd4f |
children | 7a2bc060230d |
comparison
equal
deleted
inserted
replaced
24:6fdebccf6492 | 25:a82c325e8b32 |
---|---|
1 #!/bin/bash | 1 #!/bin/bash |
2 me=$$ | 2 # Usage extract.sh ccid segid |
3 SHARED=/home/shared/ht | 3 ccid=$1 |
4 cd $SHARED/data/$(hostname) | 4 segid=$2 |
5 @@me=$$ | |
6 @@cd $SHARED/data/$(hostname) | |
5 mkdir -p logs | 7 mkdir -p logs |
6 while read id | 8 while read id |
7 do | 9 do |
8 echo starting ${id} $(date) >> logs/${me}_log | 10 echo starting ${id} $(date) >> logs/${me}_log |
9 unpigz -dp 1 -c /data/common_crawl/CC-MAIN-2019-35/CC-MAIN-${id}.warc.gz|$SHARED/bin/warc.sh ${id} application/pdf 2>> logs/${me}_log | 11 unpigz -dp 1 -c /beegfs/common-crawl/CC-MAIN-${ccid}/${segid}/CC-MAIN-${id}.warc.gz|$HOME/lib/valhalla/bin/warc.sh ${id} application/pdf 2>> logs/@@${me}_log |
10 echo finished ${id} $(date) >> logs/${me}_log | 12 echo finished ${id} $(date) >> logs/@@${me}_log |
11 done | 13 done |