comparison bin/preExtract.sh @ 51:427056f1784e

a few tweaks after 2nd parallel run
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Sat, 11 Apr 2020 13:41:46 +0100
parents 5de261eb0deb
children 9cd9daf75183
comparison
equal deleted inserted replaced
50:5de261eb0deb 51:427056f1784e
34 cut -f 2,3 in.txt| sort -u | tr '\011' '\012' |\ 34 cut -f 2,3 in.txt| sort -u | tr '\011' '\012' |\
35 parallel --will-cite -j 16 -N 2 h="$h"' 35 parallel --will-cite -j 16 -N 2 h="$h"'
36 function sus () { sort "$@" | uniq -c | sort -k1nr,1 ; } 36 function sus () { sort "$@" | uniq -c | sort -k1nr,1 ; }
37 s={1} 37 s={1}
38 p={2} 38 p={2}
39 mkdir -p $s/logs 39 mkdir -p /dev/shm/rex/$s/logs
40 cd $s 40 cd /dev/shm/rex/$s
41 echo $(date) starting $s/$p > log 41 echo $(date) starting $s/$p > log
42 # Sigh, should not have used this in the extraction ... 42 # Sigh, should not have used this in the extraction ...
43 jobid=$(tar -tf ${h}/${s}/extract_0.tar logs/ | head -1 | \ 43 jobid=$(tar -tf ${h}/${s}/extract_0.tar logs/ | head -1 | \
44 cut -f 2 -d / |cut -f 1 -d _) 44 cut -f 2 -d / |cut -f 1 -d _)
45 for e in $(egrep "\b$s\b" ../in.txt |cut -f 1 | sort -u) 45 for e in $(egrep "\b$s\b" ../in.txt |cut -f 1 | sort -u)
88 ^" "[0-9]*" > 1 < 1 --- 1 "[0-9]*c[0-9]*" 1 "[0-9]*"a"[0-9,]*" "$ ]] 88 ^" "[0-9]*" > 1 < 1 --- 1 "[0-9]*c[0-9]*" 1 "[0-9]*"a"[0-9,]*" "$ ]]
89 then 89 then
90 : 90 :
91 else 91 else
92 echo " " "extra lines in ${e}_check.txt" >> log 92 echo " " "extra lines in ${e}_check.txt" >> log
93 cd ..
94 continue 93 continue
95 fi 94 fi
96 elif [ $(fgrep -c a ${e}_check.txt) -ne $ni ] 95 elif [ $(fgrep -c a ${e}_check.txt) -ne $ni ]
97 then 96 then
98 echo " " "non-addition lines in ${e}_check.txt" >> log 97 echo " " "non-addition lines in ${e}_check.txt" >> log
99 cd ..
100 continue 98 continue
101 fi 99 fi
102 echo " " starting tar update >> log 100 echo " " starting tar update >> log
103 egrep "^> " ${e}_diff.txt | cut -f 2 > ${e}_new.txt 101 egrep "^> " ${e}_diff.txt | cut -f 2 > ${e}_new.txt
104 tar --delete -f ${h}/${s}/extract_${e}.tar "${lff[@]}" 102 tar --delete -f ${h}/${s}/extract_${e}.tar "${lff[@]}"
105 tar --append -f ${h}/${s}/extract_${e}.tar --files-from=${e}_new.txt "${lff[@]}" 103 tar --append -f ${h}/${s}/extract_${e}.tar --files-from=${e}_new.txt "${lff[@]}"
106 else 104 else
107 echo "no diff, no update" $e >> log 105 echo "no diff, no update" $e >> log
108 fi 106 fi
109 echo end extract: $e >> log 107 echo end extract: $e >> log
110 done
111 cd ..
112 ' 108 '