cc/cirrus_home: bin/extract.sh annotate

annotate bin/extract.sh @ 187:9805323d9969

add lastmod to cdx lines, start writing test case

author	Henry S. Thompson <ht@inf.ed.ac.uk>
date	Mon, 23 Sep 2024 16:35:22 +0100
parents	1e479e3ea9c4
children

rev	line source
27 7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	1 #!/usr/bin/bash
7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	2 # Launch parallel tasks, one per segment from extract_?.txt
29 a95a1b31f5e9 try to fix multi-line lossage Henry S. Thompson <ht@inf.ed.ac.uk> parents: 27 diff changeset	3 # First line thereof gives CC identifier
27 7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	4 echo $(date) $(hostname)
7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	5 h=$(hostname)
7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	6 hn=${h##*n}
7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	7 head -1 extract_${hn}.txt \|\
30 1e479e3ea9c4 better quoting Henry S. Thompson <ht@inf.ed.ac.uk> parents: 29 diff changeset	8 { read cc ; \
29 a95a1b31f5e9 try to fix multi-line lossage Henry S. Thompson <ht@inf.ed.ac.uk> parents: 27 diff changeset	9 tail -n +2 extract_${hn}.txt \|\
30 1e479e3ea9c4 better quoting Henry S. Thompson <ht@inf.ed.ac.uk> parents: 29 diff changeset	10 parallel --joblog topjob.log --will-cite -j 4 -N 1 \$HOME/bin/doExtract.sh "$cc" '{#}' '{}' ; }
27 7a2bc060230d first cut at doing extraction here Henry S. Thompson <ht@inf.ed.ac.uk> parents: 25 diff changeset	11 echo $(date) $(hostname) $?