use strict;
use warnings;

my @words = ();
my @cvs = ();

# push some hash data onto the arrays, in real life this would be
# huge files with  phonetical transcripton, not VC toilets
push @cvs, { file => 1, text => 'v' };
push @cvs, { file => 1, text => 'c' };
push @cvs, { file => 1, text => 'c' };
push @cvs, { file => 2, text => 'c' };
push @cvs, { file => 2, text => 'v' };
push @cvs, { file => 2, text => 'c' };
push @cvs, { file => 2, text => 'c' };

push @words, { file => 1, text => 'üks' };
push @words, { file => 2, text => 'kaks' };

my $cv_as_text;
my @cvs_to_delete = ();

# for each word we have to find its consistents
for my $w_i (0 .. $#words) {
    my %word = %{$words[$w_i]};
    
    my $cv_as_text = '';
    my @cvs_to_delete = ();
    
    print "$w_i: $word{text}\n   ";
    # now loop through the consistents and find correct  match
    for my $c_i (0 .. $#cvs) {
        my %cv = %{$cvs[$c_i]};
        # in real life this is done with micro seconds, not file nr
        if( $cv{file} == $word{file}) {
            $cv_as_text .= $cv{text};
            push @cvs_to_delete, $c_i;
            print $cv{text};
        }
        # we don't want to search to the end (data is ordered)
        elsif ($cv{file} > $word{file}) {
            last;
        }
    }
    print "\n";
    # now delete all cvs we extracted
    @cvs_to_delete = reverse sort @cvs_to_delete;
    for my $del (@cvs_to_delete) {
        splice (@cvs, $del, 1);
    }
}