Mercurial > hg > cc > cirrus_work

changeset 377:b3ba45af45c9 plus

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
prep for exercise 4
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Wed, 10 Jun 2026 19:07:01 +0100
parents af18b5074464
children e44d214699be
files bin/_atest3.sh
diffstat 1 files changed, 12 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /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