# HG changeset patch # User Henry S. Thompson # Date 1781114821 -3600 # Node ID b3ba45af45c9f924c83a9e75fc9f1eceef483b2a # Parent af18b50744649484d66a8c52e9855228580f0e63 prep for exercise 4 diff -r af18b5074464 -r b3ba45af45c9 bin/_atest3.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bin/_atest3.sh Wed Jun 10 19:07:01 2026 +0100 @@ -0,0 +1,12 @@ +#!/usr/bin/bash +# Usage: _atest3.sh j n +# Process the jth group of cdx files taken n at a time, doing 10 at a time +j=$1 +n=$2 +sleep 5 +h_s=$((n * j)) +h_e=$(( ( ( n * (j + 1) ) - 1 ) )) +echo _a passed j=$j n=$n, processing "[$h_s,$h_e]" +#seq --format "%03g" $h_s $h_e | parallel -j 10 echo '$(date)' cdx-00'{}.gz' ' {#} \| sus' #| uniq_merge.py +cd /work/dc007/dc007/hst/results/CC-MAIN-2025-33/warc_lmhx/idx +seq --format "%03g" $h_s $h_e | parallel -j 10 'uz cdx-00{}.gz | /work/dc007/dc007/shared/bin/cdx2tsv.sh languages | egrep -v "NA|," | sus' | uniq_merge.py