# HG changeset patch # User Henry S. Thompson # Date 1781562707 -3600 # Node ID 615efac7fc0918d9841ca6ff716d9522393b4906 # Parent 7245d684b0b5a148e04336d4b925c5d735edf072 working for ex4a diff -r 7245d684b0b5 -r 615efac7fc09 bin/ex4_1.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bin/ex4_1.sh Mon Jun 15 23:31:47 2026 +0100 @@ -0,0 +1,14 @@ +#!/usr/bin/bash +# Usage: ex4_1.sh j n +# Process the jth group of cdx files taken n at a time +# with 10 parallel threads at a time +j=$1 +n=$2 +c_s=$((n * j)) +c_e=$(( ( ( n * (j + 1) ) - 1 ) )) +echo ex4_1 passed j=$j n=$n, processing "[$c_s,$c_e]" +cd /work/dc007/dc007/hst/results/CC-MAIN-2025-33/warc_lmhx/idx +seq --format "%03g" $c_s $c_e | parallel -j 10 \ + /work/dc007/dc007/hst/bin/ex4_2.sh '{}' | uniq_merge.py + + diff -r 7245d684b0b5 -r 615efac7fc09 bin/ex4_2.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bin/ex4_2.sh Mon Jun 15 23:31:47 2026 +0100 @@ -0,0 +1,3 @@ +#!/usr/bin/bash +# Usage: ex4_2.sh [000-299] +uz cdx-00${1}.gz | cdx2tsv.sh languages | egrep '^[^N]..$' | sus diff -r 7245d684b0b5 -r 615efac7fc09 lib/python/cc/ex4.py --- a/lib/python/cc/ex4.py Fri Jun 12 16:14:55 2026 +0100 +++ b/lib/python/cc/ex4.py Mon Jun 15 23:31:47 2026 +0100 @@ -1,3 +1,4 @@ +# cython: profile=False, language_level=3str '''Use this to get called by cdx2tsv.py''' from collections import defaultdict