From 9c27d06ed251e3de5fddb8eb51ab58a8b663bdcf Mon Sep 17 00:00:00 2001
From: jgugliel <julien.guglielmini@pasteur.fr>
Date: Sat, 19 Feb 2022 11:11:54 +0100
Subject: [PATCH] Improved oneliner for genomes pairs
---
wGRR | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/wGRR b/wGRR
index 1172eb4..8f2d006 100755
--- a/wGRR
+++ b/wGRR
@@ -266,7 +266,7 @@ if [[ -f $OUT.allpairs.txt ]] ; then
else
printf "%-10s -- %s\n" "[INFO]" "Writing genomes pairs"
printf "%-10s -- %s\n" "[TIME]" $(textifyDuration $duration)
- $AWKEXE '/^>/{g=substr($1,2);gsub(/_[0-9]+$/,"",g);a[g]++}END{for(i in a){for(j in a){if(i != j && !(j" "i in b)){print i"\t"j;b[i" "j]++}}}}' $PRT > $OUT.allpairs.txt
+ $AWKEXE 'BEGIN{x=1}/^>/{g=substr($1,2);gsub(/_[0-9]+$/,"",g);if(FNR==1){a[x]=g;++x;currg=g;next}if(g!=currg){a[x]=g;x++;currg=g}}END{i=0;while(++i in a){j=i;while(++j in a){print a[i]"\t"a[j]}}}' $PRT > $OUT.allpairs.txt
printf "%-10s -- %s\n" "[INFO]" "$(wc -l $OUT.allpairs.txt | awk '{print $1}') pairs written"
fi
--
GitLab