comparison master/wecu/run_sac.sh @ 57:ac1a20e627a9

from lukasz git repo 2020-05-26 (see ~/src/wecu), then editted, sac not quite working yet
author Henry S. Thompson <ht@markup.co.uk>
date Wed, 27 May 2020 20:54:34 +0000
parents
children
comparison
equal deleted inserted replaced
56:8ce6a81e2bb4 57:ac1a20e627a9
1 #!/bin/bash
2 cores=$1
3 hosts=$2
4 wd=$3
5 shift
6 shift
7 shift
8 rm -f allout
9
10 parallel -v \
11 --sshloginfile $hosts \
12 --retries 3 \
13 --transferfile $(which sac_mapper.py|sed 's/sac_/.\/sac_/') \
14 --will-cite \
15 --jobs $cores \
16 --workdir $wd \
17 -a input_paths \
18 "hostname 1>&2 ; export PYTHONIOENCODING=utf-8; curl -s -N https://commoncrawl.s3.amazonaws.com/{} | unpigz -dp 1 -c | tee >(wc -l 1>&2) | ./sac_mapper.py $* 2>&1" | tee -a allout | grep -v 'Authorized uses only' | \
19 sac_reducer.py "$*"