This gives your "expected output" but there's a conflict between my sort and your sort description.
#!/usr/bin/perl -l # http://perlmonks.org/?node_id=1198131 use strict; use warnings; my %one; while(<DATA>) { my ($one, $two, $three, $four) = split; push @{ $one{$one} }, [ $two, $three, $four ]; } for my $one (sort keys %one) { my %groups; LOOP: for ( sort { $a->[1] cmp $b->[1] or $b->[2] <=> $a->[2] or $a->[0] <=> $b->[0] } @{ $one{$one} } ) { my ( $two, $three, $four ) = @$_; if( keys %groups ) { for ( sort keys %groups ) { if( ( $_ ^ "$three" ) =~ tr/\0//c <= 2 ) { push @{ $groups{$_} }, [ $two, $three, $four ]; next LOOP; } } push @{ $groups{$three} }, [ $two, $three, $four ]; } else { push @{ $groups{$three} }, [ $two, $three, $four ]; } } for ( sort keys %groups ) { print 'CLUSTER'; for ( values @{ $groups{$_} } ) { print join "\t", $one, @$_; } } } __DATA__ chrM:307 0 AGCGGGGA 129 chrM:307 0 AGCGGGGA 130 chrM:307 0 AGCGGGGA 129 chrM:308 0 AGCGGGGA 129 chrM:308 0 AGCGGGGA 130 chrM:308 0 AGCGGGGA 129 chrM:309 0 AGCGGGGA 129 chrM:309 0 AGCGGGGA 130 chrM:309 0 AGCGGGGA 129 chrM:307 0 TCAAAATG 130 chrM:308 0 TCAAAATG 130 chrM:309 0 TCAAAATG 130 chrM:307 0 TCACGGTG 130 chrM:308 0 TCACGGTG 130 chrM:309 0 TCACGGTG 130 chrM:307 0 TCAGCCTG 129 chrM:308 0 TCAGCCTG 129 chrM:309 0 TCAGCCTG 129 chrM:307 0 TCAGGGAG 130 chrM:308 0 TCAGGGAG 130 chrM:309 0 TCAGGGAG 130 chrM:307 1 TCAGGGTG 106 chrM:307 2 TCAGGGTG 130 chrM:307 2 TCAGGGTG 129 chrM:308 1 TCAGGGTG 106 chrM:308 2 TCAGGGTG 130 chrM:308 2 TCAGGGTG 129 chrM:309 1 TCAGGGTG 106 chrM:309 2 TCAGGGTG 130 chrM:309 2 TCAGGGTG 129
Output:
CLUSTER chrM:307 0 AGCGGGGA 130 chrM:307 0 AGCGGGGA 129 chrM:307 0 AGCGGGGA 129 CLUSTER chrM:307 0 TCAAAATG 130 CLUSTER chrM:307 0 TCACGGTG 130 chrM:307 0 TCAGGGAG 130 chrM:307 2 TCAGGGTG 130 chrM:307 2 TCAGGGTG 129 chrM:307 1 TCAGGGTG 106 CLUSTER chrM:307 0 TCAGCCTG 129 CLUSTER chrM:308 0 AGCGGGGA 130 chrM:308 0 AGCGGGGA 129 chrM:308 0 AGCGGGGA 129 CLUSTER chrM:308 0 TCAAAATG 130 CLUSTER chrM:308 0 TCACGGTG 130 chrM:308 0 TCAGGGAG 130 chrM:308 2 TCAGGGTG 130 chrM:308 2 TCAGGGTG 129 chrM:308 1 TCAGGGTG 106 CLUSTER chrM:308 0 TCAGCCTG 129 CLUSTER chrM:309 0 AGCGGGGA 130 chrM:309 0 AGCGGGGA 129 chrM:309 0 AGCGGGGA 129 CLUSTER chrM:309 0 TCAAAATG 130 CLUSTER chrM:309 0 TCACGGTG 130 chrM:309 0 TCAGGGAG 130 chrM:309 2 TCAGGGTG 130 chrM:309 2 TCAGGGTG 129 chrM:309 1 TCAGGGTG 106 CLUSTER chrM:309 0 TCAGCCTG 129
In reply to Re: Find duplicate based on specific fields while allowing 2 mismatch
by tybalt89
in thread Find duplicate based on specific fields while allowing 2 mismatch
by amitgsir
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |