# HG changeset patch
# User Henry S. Thompson <ht@inf.ed.ac.uk>
# Date 1585236552 0
# Node ID e912ed51146a81bf4e11518b1fa048354c8eb5d2
# Parent  ec99b2d1d2fccba67d7d32f239c439e19567535e
fixed scope pblm in tar step

diff -r ec99b2d1d2fc -r e912ed51146a bin/doExtract.sh
--- a/bin/doExtract.sh	Thu Mar 26 12:24:30 2020 +0000
+++ b/bin/doExtract.sh	Thu Mar 26 15:29:12 2020 +0000
@@ -22,8 +22,8 @@
 
   cat ../by11s.txt | while read i j
      do ((n=i/11))
-     tar -cf /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extract_${n}.tar.gz \
-       $(seq $i $j | xargs -I ^ bash -c '{ k=^; printf "${pfx}-%05.0f_* logs/?_%03.0f_log\n" $k $k ; }')
+     tar -cf /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extract_${n}.tar \
+       $(seq $i $j | xargs -I ^ bash -c '{ k=^; printf "${0}-%05.0f_* logs/*_%03.0f_log\n" $k $k ; }' $pfx)
      done &&
   echo $(date) $(hostname) $jobid /beegfs/common_crawl/CC-MAIN-${ccid}/${segid}/extracts_\{0..${n}\}.tar
 fi