Mercurial > hg > cc > cirrus_home
comparison bin/doExtract.sh @ 33:4c23b1766692
towards sub-division of resulting tar files
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Tue, 24 Mar 2020 17:53:35 +0000 |
parents | 1e479e3ea9c4 |
children | ec99b2d1d2fc |
comparison
equal
deleted
inserted
replaced
32:9676e7ad02e1 | 33:4c23b1766692 |
---|---|
5 segid=$3 | 5 segid=$3 |
6 echo $(date) $(hostname) $jobid $segid | 6 echo $(date) $(hostname) $jobid $segid |
7 mkdir -p $segid/logs | 7 mkdir -p $segid/logs |
8 cd $segid | 8 cd $segid |
9 ls /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/CC-MAIN-*.warc.gz | \ | 9 ls /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/CC-MAIN-*.warc.gz | \ |
10 parallel --joblog job_${jobid}.log -j 12 -N 1 'id=$(echo {} | cut -f 6 -d / | cut -f 3- -d - | cut -f 1 -d .) ; \ | 10 parallel --joblog job_${jobid}.log -j 18 -N 1 'id=$(echo {} | cut -f 6 -d / | cut -f 3- -d - | cut -f 1 -d .) ; \ |
11 echo starting $id $(date) >> logs/${jobid}_{#}_log ; \ | 11 echo starting $id $(date) >> logs/${jobid}_{#}_log ; \ |
12 unpigz -dp 1 -c {} | $HOME/lib/valhalla/bin/warc.sh ${id} application/pdf 2>> logs/${jobid}_{#}_log ; \ | 12 unpigz -dp 1 -c {} | $HOME/lib/valhalla/bin/warc.sh ${id} application/pdf 2>> logs/${jobid}_{#}_log ; \ |
13 echo finished ${id} $(date) >> logs/${jobid}_{#}_log' | 13 echo finished ${id} $(date) >> logs/${jobid}_{#}_log' |
14 res=$? | 14 res=$? |
15 echo $(date) $(hostname) $jobid $segid $res | 15 echo $(date) $(hostname) $jobid $segid $res |
16 if [ $res = 0 ] | 16 if [ $res = 0 ] |
17 then | 17 then |
18 tar -cf /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extracts.tar * | 18 cat ../by11s.txt | while read |
19 tar -cf /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extracts.tar * && | |
19 echo $(date) $(hostname) $jobid /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extracts.tar | 20 echo $(date) $(hostname) $jobid /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extracts.tar |
20 fi | 21 fi |