Mercurial > hg > cc > cirrus_work
changeset 142:0326805aa6df
change path to merge_date.py
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Mon, 02 Oct 2023 18:54:10 +0100 |
parents | 14d3802112b2 |
children | f63a8477c9df |
files | bin/do_idx.sh |
diffstat | 1 files changed, 8 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/bin/do_idx.sh Mon Oct 02 18:52:43 2023 +0100 +++ b/bin/do_idx.sh Mon Oct 02 18:54:10 2023 +0100 @@ -1,14 +1,21 @@ #!/bin/bash +# Usage: do_idx.sh [-d...] [-m previously-merged-log] result-dir cdx-source-dir while [ "$1" = "-d" ] do shift debug="$debug -d" done +if [ "$1" = "-m" ] +then + shift + merged="-m $1" + shift +fi export res="$1" orig="$2" # igzip was faster, but produced bigger files, so went to gzip one step # smaller than default (-6), which produces slightly _smaller_ blocks. -merge_date.py $debug <(LC_ALL=C sort -m -k1,3 -s $res/ks_[0-9]*.tsv) \ +~/lib/python/cc/lmh/merge_date.py $debug $merged <(LC_ALL=C sort -m -k1,3 -s $res/ks_[0-9]*.tsv) \ $orig $res/idx 2>$res/merge.log | \ parallel -j 10 'echo {#} {} >$res/merge_{#}.log echo $(date) {#} {}