diff bin/ix.sh @ 105:baf56ff538f8

convert to rich directory structure per 2019-35
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Tue, 20 Apr 2021 11:12:35 +0000
parents 0332076afc37
children 1d6fde73789d
line wrap: on
line diff
--- a/bin/ix.sh	Mon Apr 19 18:09:51 2021 +0000
+++ b/bin/ix.sh	Tue Apr 20 11:12:35 2021 +0000
@@ -52,8 +52,10 @@
 else
     cat
 fi | \
-while { IFS=$'\t' read l o f; }
+while { IFS=$'\t' read l o wf; }
 do
+  ff=($(echo $wf | tr '/' ' '))
+  f="/beegfs/common_crawl/${ff[0]}/${ff[1]}/orig/warc/${ff[2]}"
   if [ -z "$d" ]
   then
       dd if="$f" of=/dev/stdout skip=$o count=$l \