Mercurial > hg > cc > cirrus_home
annotate bin/doCLM.sh @ 203:2aa9db279d56
--array + -m now working
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Wed, 22 Apr 2026 18:50:07 +0100 |
| parents | ef961d91eea5 |
| children |
| rev | line source |
|---|---|
|
163
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
1 #!/usr/bin/bash |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
2 mkdir -p /dev/shm/hst |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
3 |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
4 c=$1 |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
5 i=$2 |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
6 f=$(printf 'cdx-%05.0f.gz' $i) |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
7 |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
8 unpigz -dp 1 -c data/$c/cdx/warc/$f | parallel --willcite --pipe -N 50000 -j10 "ix.py -x -h -c '/lustre/home/dc007/hst/bin/clm.sh /dev/shm/hst/'$i'.lmh_{#}.txt' 2>/dev/shm/hst/$i.lmh_{#}.errs" |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
9 |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
10 cd /dev/shm/hst |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
11 tar -czf $HOME/results/${i}.lmh.tar.gz ${i}.lmh_*.{txt,errs} |
|
ef961d91eea5
previous approach to lang/field extraction
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff
changeset
|
12 |
