comparison bin/splitTars.sh @ 64:0520ee00e35b

misc
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Fri, 24 Apr 2020 19:57:16 +0100
parents
children
comparison
equal deleted inserted replaced
63:d39fd9c7f1be 64:0520ee00e35b
1 #!/bin/bash
2 for segid in $(cat /beegfs/common_crawl/CC-MAIN-2019-35/bigtar.txt)
3 do
4 echo $segid starting
5 ccid=2019-35
6 h=/beegfs/common_crawl/CC-MAIN-${ccid}
7 mkdir -p /dev/shm/rex/${segid}
8 cd /dev/shm/rex/${segid}
9 tar -xf ${h}/${segid}/extracts.tar
10 pfx=$(ls ${h}/${segid}/CC-MAIN-*-00000.warc.gz |\
11 cut -f 6 -d / | cut -f 3,4 -d -)
12 cat ../by11s.txt | while read i j
13 do ((n=i/11))
14 tar -cf /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extract_${n}.tar \
15 $(seq $i $j | xargs -I ^ bash -c "{ k=^; printf \"\${0}-%05.0f_* logs/*_%03.0f_log\n\" $k $k ; }" $pfx)
16 done &&
17 echo $(date) $segid done
18 done